From 8792e5da7b40060ee12afa6e1d7d9db960e784e6 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Tue, 21 Apr 2026 05:52:11 +0000 Subject: [PATCH] flex: drop scripts/benchmarks/results/stats JSONs Remove the raw benchmark output JSONs from the PR diff. The writeup markdowns under scripts/benchmarks/results/*.md keep their filename anchors as a record of what each table was measured from; anyone who wants the raw numbers can re-run the benchmark scripts. 41 files removed, 6068 lines deleted. --- .../results/stats/flex_128_tuned.json | 25 - .../results/stats/flex_128x512_cudagraph.json | 15 - .../results/stats/flex_16_tuned.json | 25 - .../results/stats/flex_32_tuned.json | 25 - .../results/stats/flex_32x512_cudagraph.json | 15 - .../stats/flex_32x512_lora_cudagraph.json | 15 - .../results/stats/flex_64_lora_autotune.json | 25 - .../stats/flex_64_lora_autotune_tma.json | 25 - .../stats/flex_64_lora_fa4prefill.json | 25 - .../stats/flex_64_lora_pinned_blocks.json | 25 - .../stats/flex_64_lora_torch211_10rounds.json | 30 - .../stats/flex_64_lora_torch211_baseline.json | 25 - .../stats/flex_64_lora_torch211_repeat.json | 25 - .../results/stats/flex_64_lora_tuned.json | 25 - .../results/stats/flex_64_tuned.json | 25 - .../stats/flex_64x512_lora_cudagraph.json | 23 - .../results/stats/flex_8_tuned.json | 25 - .../results/stats/grpo_cb_paged_10.json | 352 ------ .../stats/grpo_cb_paged_10.summary.json | 64 - .../results/stats/grpo_cb_paged_30.json | 1052 ---------------- .../stats/grpo_cb_paged_30.summary.json | 144 --- .../results/stats/grpo_fi_false_30.json | 1082 ----------------- .../stats/grpo_fi_false_30.summary.json | 175 --- .../stats/grpo_unsloth_fi_false_10.json | 362 ------ .../grpo_unsloth_fi_false_10.summary.json | 75 -- .../results/stats/grpo_vllm_10.json | 362 ------ .../results/stats/grpo_vllm_10.summary.json | 75 -- .../results/stats/grpo_vllm_30.json | 1082 ----------------- .../results/stats/grpo_vllm_30.summary.json | 175 --- .../results/stats/lora_cb_paged_fa4_gen.json | 29 - .../results/stats/lora_cb_sdpa_paged_gen.json | 29 - .../stats/lora_unsloth_fi_false_gen.json | 27 - .../results/stats/lora_vllm_gen.json | 27 - .../results/stats/notebook_ref_10.json | 362 ------ .../results/stats/vllm_128x512.json | 28 - scripts/benchmarks/results/stats/vllm_16.json | 28 - .../results/stats/vllm_256x512.json | 28 - scripts/benchmarks/results/stats/vllm_32.json | 28 - scripts/benchmarks/results/stats/vllm_64.json | 28 - .../results/stats/vllm_64x512_lora.json | 28 - scripts/benchmarks/results/stats/vllm_8.json | 28 - 41 files changed, 6068 deletions(-) delete mode 100644 scripts/benchmarks/results/stats/flex_128_tuned.json delete mode 100644 scripts/benchmarks/results/stats/flex_128x512_cudagraph.json delete mode 100644 scripts/benchmarks/results/stats/flex_16_tuned.json delete mode 100644 scripts/benchmarks/results/stats/flex_32_tuned.json delete mode 100644 scripts/benchmarks/results/stats/flex_32x512_cudagraph.json delete mode 100644 scripts/benchmarks/results/stats/flex_32x512_lora_cudagraph.json delete mode 100644 scripts/benchmarks/results/stats/flex_64_lora_autotune.json delete mode 100644 scripts/benchmarks/results/stats/flex_64_lora_autotune_tma.json delete mode 100644 scripts/benchmarks/results/stats/flex_64_lora_fa4prefill.json delete mode 100644 scripts/benchmarks/results/stats/flex_64_lora_pinned_blocks.json delete mode 100644 scripts/benchmarks/results/stats/flex_64_lora_torch211_10rounds.json delete mode 100644 scripts/benchmarks/results/stats/flex_64_lora_torch211_baseline.json delete mode 100644 scripts/benchmarks/results/stats/flex_64_lora_torch211_repeat.json delete mode 100644 scripts/benchmarks/results/stats/flex_64_lora_tuned.json delete mode 100644 scripts/benchmarks/results/stats/flex_64_tuned.json delete mode 100644 scripts/benchmarks/results/stats/flex_64x512_lora_cudagraph.json delete mode 100644 scripts/benchmarks/results/stats/flex_8_tuned.json delete mode 100644 scripts/benchmarks/results/stats/grpo_cb_paged_10.json delete mode 100644 scripts/benchmarks/results/stats/grpo_cb_paged_10.summary.json delete mode 100644 scripts/benchmarks/results/stats/grpo_cb_paged_30.json delete mode 100644 scripts/benchmarks/results/stats/grpo_cb_paged_30.summary.json delete mode 100644 scripts/benchmarks/results/stats/grpo_fi_false_30.json delete mode 100644 scripts/benchmarks/results/stats/grpo_fi_false_30.summary.json delete mode 100644 scripts/benchmarks/results/stats/grpo_unsloth_fi_false_10.json delete mode 100644 scripts/benchmarks/results/stats/grpo_unsloth_fi_false_10.summary.json delete mode 100644 scripts/benchmarks/results/stats/grpo_vllm_10.json delete mode 100644 scripts/benchmarks/results/stats/grpo_vllm_10.summary.json delete mode 100644 scripts/benchmarks/results/stats/grpo_vllm_30.json delete mode 100644 scripts/benchmarks/results/stats/grpo_vllm_30.summary.json delete mode 100644 scripts/benchmarks/results/stats/lora_cb_paged_fa4_gen.json delete mode 100644 scripts/benchmarks/results/stats/lora_cb_sdpa_paged_gen.json delete mode 100644 scripts/benchmarks/results/stats/lora_unsloth_fi_false_gen.json delete mode 100644 scripts/benchmarks/results/stats/lora_vllm_gen.json delete mode 100644 scripts/benchmarks/results/stats/notebook_ref_10.json delete mode 100644 scripts/benchmarks/results/stats/vllm_128x512.json delete mode 100644 scripts/benchmarks/results/stats/vllm_16.json delete mode 100644 scripts/benchmarks/results/stats/vllm_256x512.json delete mode 100644 scripts/benchmarks/results/stats/vllm_32.json delete mode 100644 scripts/benchmarks/results/stats/vllm_64.json delete mode 100644 scripts/benchmarks/results/stats/vllm_64x512_lora.json delete mode 100644 scripts/benchmarks/results/stats/vllm_8.json diff --git a/scripts/benchmarks/results/stats/flex_128_tuned.json b/scripts/benchmarks/results/stats/flex_128_tuned.json deleted file mode 100644 index 8b8b2fc681..0000000000 --- a/scripts/benchmarks/results/stats/flex_128_tuned.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": null, - "n_prompts": 128, - "n_decoded_tokens": 56415, - "wall_times_s": [ - 12.628456736041699, - 11.507176020997576, - 10.393205604981631, - 10.137171553040389, - 11.370744699030183 - ], - "median_wall_s": 11.370744699030183, - "best_wall_s": 10.137171553040389, - "decode_tps_median": 4961.416467719275, - "decode_tps_best": 5565.161811144426, - "max_new_tokens": 512, - "peak_memory_gb": 80.88226366043091, - "sample_completions": [ - "Let $h$ be the height of the tetrahedron. Then, the volume of the tetrahedron is $\\frac{1}{3} \\cdot 120 \\cdot h = 40h$.400", - " \nTo solve this problem, we will use the concept of mass points and the properties of similar triangles. \n\nFirst, let's assign masses to the points based on the given information. Since $M$ is the midpoint of $BC$, we can assign a mass of 1 to both $B$ and $C$. This means that the mass at $M$ is 2 (since $", - " To solve this problem, we need to find the value of \\( n \\) that minimizes the sum \\( \\sum_{i=1}^{n} f(i) \\) under the given conditions. Let's break down the problem step by step.\n\n1. **Understanding the Constraints:**\n - \\( f \\) is a non-negative valued function on \\( \\{1, 2" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_128x512_cudagraph.json b/scripts/benchmarks/results/stats/flex_128x512_cudagraph.json deleted file mode 100644 index 8bb4f1dcf5..0000000000 --- a/scripts/benchmarks/results/stats/flex_128x512_cudagraph.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": null, - "n_prompts": 128, - "n_decoded_tokens": 58443, - "wall_times_s": [ - 11.44752091699047, - 8.989795534987934 - ], - "median_wall_s": 11.44752091699047, - "decode_tps": 5105.297507101174, - "max_new_tokens": 512, - "peak_memory_gb": 80.88137865066528 -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_16_tuned.json b/scripts/benchmarks/results/stats/flex_16_tuned.json deleted file mode 100644 index 1a89608d71..0000000000 --- a/scripts/benchmarks/results/stats/flex_16_tuned.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": null, - "n_prompts": 16, - "n_decoded_tokens": 7446, - "wall_times_s": [ - 6.069258489005733, - 4.580210059997626, - 5.2929606509860605, - 5.689690829021856, - 5.988061942043714 - ], - "median_wall_s": 5.689690829021856, - "best_wall_s": 4.580210059997626, - "decode_tps_median": 1308.6827076823927, - "decode_tps_best": 1625.6896304891004, - "max_new_tokens": 512, - "peak_memory_gb": 43.700210094451904, - "sample_completions": [ - " To solve this problem, we need to determine how many ways we can divide a \\(20 \\times 24\\) rectangle into \\(4 \\times 5\\) rectangles. We will consider rotations and reflections as distinct.\n\nFirst, let's calculate the area of the \\(20 \\times 24\\) rectangle:\n\\[\n20 \\times 24 = 480\n", - " To solve this problem, we need to find the area of the region inside the larger circle \\( C \\) with radius 30 and outside the six smaller congruent circles that form a ring and are each internally tangent to \\( C \\).\n\nFirst, let's denote the radius of each of the six smaller circles as \\( r \\). Since the six smaller circles form a ring and are each externally", - " \nA 10-digit palindrome has the form \\( \\overline{abcdefghij} \\) where \\( a = j \\), \\( b = i \\), \\( c = h \\), \\( d = g \\), \\( e = f \\), and \\( f = e \\). This means the number can be written as \\( \\overline{abcdeedcba} \\).\n\nTo determine" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_32_tuned.json b/scripts/benchmarks/results/stats/flex_32_tuned.json deleted file mode 100644 index 41688366aa..0000000000 --- a/scripts/benchmarks/results/stats/flex_32_tuned.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": null, - "n_prompts": 32, - "n_decoded_tokens": 15164, - "wall_times_s": [ - 7.840532291971613, - 5.729173633968458, - 6.219996218045708, - 5.283988946001045, - 4.839393497037236 - ], - "median_wall_s": 5.729173633968458, - "best_wall_s": 4.839393497037236, - "decode_tps_median": 2646.804053920124, - "decode_tps_best": 3133.4505055816758, - "max_new_tokens": 512, - "peak_memory_gb": 43.90812540054321, - "sample_completions": [ - " To solve this problem, we need to find the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirst, let's consider the condition that the line \\(y = mx + 2", - " \nTo find the area of the smaller square, we need to determine its side length. Let's denote the side length of the smaller square as \\( s \\).\n\nFrom the diagram, we can see that the larger square has a side length of 6. The smaller square is inscribed within the larger square such that its vertices touch the midpoints of the sides of the larger square. This means", - " \nTo solve this problem, we need to consider all possible pairs of special fractions \\(\\frac{a}{b}\\) and \\(\\frac{c}{d}\\) where \\(a + b = 15\\) and \\(c + d = 15\\). We will then find the distinct integers that can be written as the sum of these two fractions.\n\nFirst, let's list" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_32x512_cudagraph.json b/scripts/benchmarks/results/stats/flex_32x512_cudagraph.json deleted file mode 100644 index 39575233d4..0000000000 --- a/scripts/benchmarks/results/stats/flex_32x512_cudagraph.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": null, - "n_prompts": 32, - "n_decoded_tokens": 14777, - "wall_times_s": [ - 9.13400061900029, - 6.742950548010413 - ], - "median_wall_s": 9.13400061900029, - "decode_tps": 1617.8015106832052, - "max_new_tokens": 512, - "peak_memory_gb": 43.90812540054321 -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_32x512_lora_cudagraph.json b/scripts/benchmarks/results/stats/flex_32x512_lora_cudagraph.json deleted file mode 100644 index f294bdd4c4..0000000000 --- a/scripts/benchmarks/results/stats/flex_32x512_lora_cudagraph.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 32, - "n_decoded_tokens": 14893, - "wall_times_s": [ - 8.811616113001946, - 6.381639341008849 - ], - "median_wall_s": 8.811616113001946, - "decode_tps": 1690.1553368881664, - "max_new_tokens": 512, - "peak_memory_gb": 43.90812540054321 -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64_lora_autotune.json b/scripts/benchmarks/results/stats/flex_64_lora_autotune.json deleted file mode 100644 index dfad76cea2..0000000000 --- a/scripts/benchmarks/results/stats/flex_64_lora_autotune.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_decoded_tokens": 29566, - "wall_times_s": [ - 8.612908595998306, - 6.458285094005987, - 6.398469406005461, - 6.125680990982801, - 6.644617859972641 - ], - "median_wall_s": 6.458285094005987, - "best_wall_s": 6.125680990982801, - "decode_tps_median": 4577.99548481385, - "decode_tps_best": 4826.565412649157, - "max_new_tokens": 512, - "peak_memory_gb": 44.21115064620972, - "sample_completions": [ - "Let the roots of the equation be $r, r^2, r^3, r^4, r^5$ in geometric progression. By Vieta's formulas, the sum of the roots is $r + r^2 + r^3 + r^4 + r^5 = 180$. Dividing both sides by $r^5$, we get $1", - "First, let's represent the given number in a more manageable form. The number \\(1\\underbrace{00\\ldots 0}_{100\\text{ zeros}}1\\underbrace{00\\ldots 0}_{100\\text{ zeros}}1\\) can be written as \\(10^{201} + 10^{10", - " \nTo solve this problem, we need to find the number of integers \\( n \\) in the range \\( 1 \\leq n \\leq 2016 \\) such that the remainder when \\( n \\) is divided by 20 is smaller than the remainder when \\( n \\) is divided by 16. Let's denote the remainder when \\( n \\)" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64_lora_autotune_tma.json b/scripts/benchmarks/results/stats/flex_64_lora_autotune_tma.json deleted file mode 100644 index a4d51c2259..0000000000 --- a/scripts/benchmarks/results/stats/flex_64_lora_autotune_tma.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_decoded_tokens": 29566, - "wall_times_s": [ - 8.423556671012193, - 6.48478461895138, - 6.419383131025825, - 6.145251678011846, - 6.663184700999409 - ], - "median_wall_s": 6.48478461895138, - "best_wall_s": 6.145251678011846, - "decode_tps_median": 4559.28789270737, - "decode_tps_best": 4811.1943251713, - "max_new_tokens": 512, - "peak_memory_gb": 44.21115064620972, - "sample_completions": [ - "Let the roots of the equation be $r, r^2, r^3, r^4, r^5$ in geometric progression. By Vieta's formulas, the sum of the roots is $r + r^2 + r^3 + r^4 + r^5 = 180$. Dividing both sides by $r^5$, we get $1", - "First, let's represent the given number in a more manageable form. The number \\(1\\underbrace{00\\ldots 0}_{100\\text{ zeros}}1\\underbrace{00\\ldots 0}_{100\\text{ zeros}}1\\) can be written as \\(10^{201} + 10^{10", - " \nTo solve this problem, we need to find the number of integers \\( n \\) in the range \\( 1 \\leq n \\leq 2016 \\) such that the remainder when \\( n \\) is divided by 20 is smaller than the remainder when \\( n \\) is divided by 16. Let's denote the remainder when \\( n \\)" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64_lora_fa4prefill.json b/scripts/benchmarks/results/stats/flex_64_lora_fa4prefill.json deleted file mode 100644 index bef775226e..0000000000 --- a/scripts/benchmarks/results/stats/flex_64_lora_fa4prefill.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_decoded_tokens": 29601, - "wall_times_s": [ - 11.575495404948015, - 6.411582662025467, - 6.848826738016214, - 7.4589985449565575, - 6.9681332929758355 - ], - "median_wall_s": 6.9681332929758355, - "best_wall_s": 6.411582662025467, - "decode_tps_median": 4248.053066068501, - "decode_tps_best": 4616.800805723188, - "max_new_tokens": 512, - "peak_memory_gb": 44.22274446487427, - "sample_completions": [ - "First, let's find the sum of the numbers in Amanda's list. The sum of the first n even numbers is given by the formula n(n+1). In this case, n = 50 (since there are 50 even numbers from 2 to 100). So, the sum of Amanda's list is 50(50+1) = ", - " \nTo find the area of the smaller square, we need to determine its side length. Let's denote the side length of the smaller square as \\( s \\).\n\nFrom the diagram, we can see that the larger square has a side length of 6. The smaller square is inscribed within the larger square such that its vertices touch the midpoints of the sides of the larger square. This means", - " To solve the problem, we need to find the number of ordered pairs \\((x, y)\\) of positive integers that satisfy the inequalities \\(x \\le 2y \\le 60\\) and \\(y \\le 2x \\le 60\\).\n\nFirst, let's rewrite the inequalities in a more convenient form:\n1. \\(x \\le 2y \\le" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64_lora_pinned_blocks.json b/scripts/benchmarks/results/stats/flex_64_lora_pinned_blocks.json deleted file mode 100644 index 2a0080ba0e..0000000000 --- a/scripts/benchmarks/results/stats/flex_64_lora_pinned_blocks.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_decoded_tokens": 29553, - "wall_times_s": [ - 8.755648983002175, - 6.662199873011559, - 6.631406380969565, - 6.668323302001227, - 5.8994951589847915 - ], - "median_wall_s": 6.662199873011559, - "best_wall_s": 5.8994951589847915, - "decode_tps_median": 4435.922152338692, - "decode_tps_best": 5009.411687539311, - "max_new_tokens": 512, - "peak_memory_gb": 44.21115064620972, - "sample_completions": [ - " \nTo find the minimum sum of the labels of the eight chosen squares, we need to consider the arrangement of the numbers on the chessboard. The answer is 10.", - "Let's denote the angles $\\angle BAP = \\angle PAQ = \\angle QAC = \\theta$. Since $AP$ and $AQ$ trisect $\\angle A$, we have $\\angle BAC = 3\\theta$.\n\nWe will use the Angle Bisector Theorem and the Law of Sines to find the ratio $\\frac{SOLUTION}", - "Let's denote the number of pages in the first volume as $x$. Then, the number of pages in the second volume is $x + 50$, and the number of pages in the third volume is $1.5(x + 50)$.\n\nThe sum of the page numbers on the first pages of the three volumes is $1 + (x + 1) + (" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64_lora_torch211_10rounds.json b/scripts/benchmarks/results/stats/flex_64_lora_torch211_10rounds.json deleted file mode 100644 index 975c12f1aa..0000000000 --- a/scripts/benchmarks/results/stats/flex_64_lora_torch211_10rounds.json +++ /dev/null @@ -1,30 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_decoded_tokens": 28565, - "wall_times_s": [ - 8.299892835028004, - 6.869692277978174, - 6.813798578979913, - 5.0465612940024585, - 5.072170660016127, - 5.903178220964037, - 6.141771270020399, - 5.922227941977326, - 7.205250932951458, - 6.960845094989054 - ], - "median_wall_s": 6.813798578979913, - "best_wall_s": 5.0465612940024585, - "decode_tps_median": 4192.228412521762, - "decode_tps_best": 5660.289915421779, - "max_new_tokens": 512, - "peak_memory_gb": 44.21115064620972, - "sample_completions": [ - "First, let's analyze the problem. We are given a natural number $a$ and we need to find the number of elements $b$ in the set $\\{ b \\in \\mathbb{N} \\mid a + b \\text{ is a divisor of } ab \\}$. We need to find the maximum value of $M(a)$ for $a \\leq 1", - "Let the roots of the equation be $r, r^2, r^3, r^4, r^5$ in geometric progression. By Vieta's formulas, the sum of the roots is $r + r^2 + r^3 + r^4 + r^5 = 180$. Dividing both sides by $r^5$, we get $1", - "First, we need to find the total number of possible triples of positive integers $(a, b, c)$ with $1 \\leq a, b, c \\leq 5$. Since each of $a$, $b$, and $c$ can take on 5 different values, the total number of possible triples is $5 \\times 5 \\times 5 = 1" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64_lora_torch211_baseline.json b/scripts/benchmarks/results/stats/flex_64_lora_torch211_baseline.json deleted file mode 100644 index d42c6bbc7f..0000000000 --- a/scripts/benchmarks/results/stats/flex_64_lora_torch211_baseline.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_decoded_tokens": 29019, - "wall_times_s": [ - 14.41304371797014, - 6.878086202952545, - 6.826645737979561, - 5.051277688005939, - 5.077490734984167 - ], - "median_wall_s": 6.826645737979561, - "best_wall_s": 5.051277688005939, - "decode_tps_median": 4250.843110043757, - "decode_tps_best": 5744.883134994633, - "max_new_tokens": 512, - "peak_memory_gb": 44.21115064620972, - "sample_completions": [ - "First, we need to find the length of segment $ABCD is 17.8 units. The length of segment $DB$ is 12.8 units.", - " \nTo solve this problem, we need to consider the different ways people can stand or sit around the table without having two adjacent people standing. Let's denote standing as S and sitting as T. We have 8 people, so there are 2^8 = 256 possible outcomes when flipping the coins.\n\nWe want to find the number of valid configurations where no two adjacent people stand.", - "Let the roots of the equation be $r, r^2, r^3, r^4, r^5$ in geometric progression. By Vieta's formulas, the sum of the roots is $r + r^2 + r^3 + r^4 + r^5 = 180$. Dividing both sides by $r^5$, we get $1" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64_lora_torch211_repeat.json b/scripts/benchmarks/results/stats/flex_64_lora_torch211_repeat.json deleted file mode 100644 index 91b844cd71..0000000000 --- a/scripts/benchmarks/results/stats/flex_64_lora_torch211_repeat.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_decoded_tokens": 29019, - "wall_times_s": [ - 8.298801471013576, - 6.888721746974625, - 6.2715082070208155, - 4.575723551039118, - 4.594870681001339 - ], - "median_wall_s": 6.2715082070208155, - "best_wall_s": 4.575723551039118, - "decode_tps_median": 4627.116642774041, - "decode_tps_best": 6341.947820123435, - "max_new_tokens": 512, - "peak_memory_gb": 44.21115064620972, - "sample_completions": [ - "First, we need to find the length of segment $ABCD is 17.8 units. The length of segment $DB$ is 12.8 units.", - " \nTo solve this problem, we need to consider the different ways people can stand or sit around the table without having two adjacent people standing. Let's denote standing as S and sitting as T. We have 8 people, so there are 2^8 = 256 possible outcomes when flipping the coins.\n\nWe want to find the number of valid configurations where no two adjacent people stand.", - "Let the roots of the equation be $r, r^2, r^3, r^4, r^5$ in geometric progression. By Vieta's formulas, the sum of the roots is $r + r^2 + r^3 + r^4 + r^5 = 180$. Dividing both sides by $r^5$, we get $1" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64_lora_tuned.json b/scripts/benchmarks/results/stats/flex_64_lora_tuned.json deleted file mode 100644 index 9a9a093b84..0000000000 --- a/scripts/benchmarks/results/stats/flex_64_lora_tuned.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_decoded_tokens": 28495, - "wall_times_s": [ - 8.62534567998955, - 6.866325525043067, - 6.2769941369770095, - 5.074044068984222, - 6.802140125015285 - ], - "median_wall_s": 6.802140125015285, - "best_wall_s": 5.074044068984222, - "decode_tps_median": 4189.122757881435, - "decode_tps_best": 5615.836128460044, - "max_new_tokens": 512, - "peak_memory_gb": 44.21115064620972, - "sample_completions": [ - "First, let's find the sum of the numbers in Amanda's list. The sum of the first n even numbers is given by the formula n(n+1). In this case, n = 50 (since there are 50 even numbers from 2 to 100). So, the sum of Amanda's list is 50(50+1) = ", - "Let's denote the number of pages in the first volume as $x$. Then, the number of pages in the second volume is $x + 50$, and the number of pages in the third volume is $1.5(x + 50)$.\n\nThe sum of the page numbers on the first pages of the three volumes is $1 + (x + 1) + (", - "Let the roots of the equation be $r, r^2, r^3, r^4, r^5$ in geometric progression. By Vieta's formulas, the sum of the roots is $r + r^2 + r^3 + r^4 + r^5 = 180$. Dividing both sides by $r^5$, we get $1" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64_tuned.json b/scripts/benchmarks/results/stats/flex_64_tuned.json deleted file mode 100644 index a8c91a11f2..0000000000 --- a/scripts/benchmarks/results/stats/flex_64_tuned.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": null, - "n_prompts": 64, - "n_decoded_tokens": 27985, - "wall_times_s": [ - 8.14494420203846, - 6.53967270400608, - 5.112081662984565, - 5.535065989010036, - 6.894235474988818 - ], - "median_wall_s": 6.53967270400608, - "best_wall_s": 5.112081662984565, - "decode_tps_median": 4279.266144750168, - "decode_tps_best": 5474.286571482827, - "max_new_tokens": 512, - "peak_memory_gb": 44.21115064620972, - "sample_completions": [ - "First, let's find the sum of the numbers in Amanda's list. The sum of the first n even numbers is given by the formula n(n+1). In this case, n = 50 (since there are 50 even numbers from 2 to 100). So, the sum of Amanda's list is 50(50+1) = ", - "Let the roots of the equation be $r, r^2, r^3, r^4, r^5$ in geometric progression. By Vieta's formulas, the sum of the roots is $r + r^2 + r^3 + r^4 + r^5 = 180$. Dividing both sides by $r^5$, we get $1", - "First, let's find the angle \\( \\angle AOB into three equal parts. The area of each smaller triangle is:\n\\[ \\frac{\\sqrt{3}}{12} \\text{ triangle} = \\frac{\\sqrt{3}/4 \\]\n\nNow, let's find the value of \\( k + m + n \\). We have:\n\\[ k = 1 \\]\n\\[" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_64x512_lora_cudagraph.json b/scripts/benchmarks/results/stats/flex_64x512_lora_cudagraph.json deleted file mode 100644 index 7ec37480f1..0000000000 --- a/scripts/benchmarks/results/stats/flex_64x512_lora_cudagraph.json +++ /dev/null @@ -1,23 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_decoded_tokens": 30184, - "wall_times_s": [ - 9.522195567958988, - 7.053195148007944, - 7.056460196967237 - ], - "median_wall_s": 7.056460196967237, - "best_wall_s": 7.053195148007944, - "decode_tps_median": 4277.498796489016, - "decode_tps_best": 4279.478926444416, - "max_new_tokens": 512, - "peak_memory_gb": 44.21115064620972, - "sample_completions": [ - "First, we need to determine how many $4 \\times 5$ rectangles can fit into a $20 \\times 24$ rectangle. We can do this by dividing the dimensions of the larger rectangle by the dimensions of the smaller rectangle.\n\nFor the width, we have $20 \\div 4 = 5$ rectangles that can fit.\nFor the height, we have $", - "First, we need to find the total number of letters in the word \"FLUFFY\". There are 6 letters in total. \n\nNext, we need to find the number of distinct arrangements of these 6 letters. Since there are 6 letters, the total number of arrangements is 6! (6 factorial), which is equal to 6 x 5 x 4 x 3", - "Let the common ratio of the geometric sequence be $r$. Then the second term is $\\frac{3}{4}r=15$, so $r=20$. The $n$th term of the sequence is $\\frac{3}{4}(20)^{n-1}$. We want to find the smallest $n$ such that $\\frac{3}{4}(" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/flex_8_tuned.json b/scripts/benchmarks/results/stats/flex_8_tuned.json deleted file mode 100644 index 8c76fd584a..0000000000 --- a/scripts/benchmarks/results/stats/flex_8_tuned.json +++ /dev/null @@ -1,25 +0,0 @@ -{ - "backend": "qwen3_flex", - "capture_cudagraph": true, - "lora_adapter": null, - "n_prompts": 8, - "n_decoded_tokens": 4096, - "wall_times_s": [ - 8.54062199202599, - 8.53521726100007, - 7.605857895978261, - 6.020388883014675, - 8.549159363028593 - ], - "median_wall_s": 8.53521726100007, - "best_wall_s": 6.020388883014675, - "decode_tps_median": 479.89405245907847, - "decode_tps_best": 680.3547211968393, - "max_new_tokens": 512, - "peak_memory_gb": 43.68726634979248, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$. We can use the Pythagorean theorem to find $x$.\n\nThe height of the trapezoid is 3, and the difference between the lengths", - "Let $P(x)$ be a monic polynomial of degree $2023$ such that $P(k) = k^{2023}P(1-\\frac{1}{k})$ for every positive integer $1 \\leq k \\leq 2023$. We want to find $P(-1)$ in the form $\\frac{a}{b", - " To solve this problem, we need to determine the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirst, let's consider the condition for the line \\(y = mx + 2" - ] -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_cb_paged_10.json b/scripts/benchmarks/results/stats/grpo_cb_paged_10.json deleted file mode 100644 index a8e557b176..0000000000 --- a/scripts/benchmarks/results/stats/grpo_cb_paged_10.json +++ /dev/null @@ -1,352 +0,0 @@ -[ - { - "step": 1, - "loss": -0.0862, - "grad_norm": 716.0, - "learning_rate": 0.0, - "num_tokens": 4262.0, - "completions/mean_length": 953.5, - "completions/min_length": 824.0, - "completions/max_length": 1092.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 953.5, - "completions/min_terminated_length": 824.0, - "completions/max_terminated_length": 1092.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 1.125, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -1.25, - "rewards/check_answer/std": 2.1794495582580566, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.625, - "reward_std": 3.4731109142303467, - "frac_reward_zero_std": 0.0, - "entropy": 0.1351587027311325, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 7.868439688409789e-05, - "time_ms": 56644.44096497027, - "memory_mb": 57451.41162109375, - "memory_gb": 56.104894161224365 - }, - { - "step": 2, - "loss": 0.041, - "grad_norm": 186.0, - "learning_rate": 5e-06, - "num_tokens": 6762.0, - "completions/mean_length": 536.0, - "completions/min_length": 492.0, - "completions/max_length": 603.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 536.0, - "completions/min_terminated_length": 492.0, - "completions/max_terminated_length": 603.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -2.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.05973631516098976, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00015736879376819577, - "time_ms": 29505.720576969907, - "memory_mb": 53805.20556640625, - "memory_gb": 52.5441460609436 - }, - { - "step": 3, - "loss": 0.0, - "grad_norm": 0.0, - "learning_rate": 4.444444444444444e-06, - "num_tokens": 10099.0, - "completions/mean_length": 657.25, - "completions/min_length": 436.0, - "completions/max_length": 1302.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 657.25, - "completions/min_terminated_length": 436.0, - "completions/max_terminated_length": 1302.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.5, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "entropy": 0.06822667270898819, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00023605319065229366, - "time_ms": 62939.08593803644, - "memory_mb": 59249.8505859375, - "memory_gb": 57.86118221282959 - }, - { - "step": 4, - "loss": 0.0855, - "grad_norm": 274.0, - "learning_rate": 3.88888888888889e-06, - "num_tokens": 13644.0, - "completions/mean_length": 721.25, - "completions/min_length": 441.0, - "completions/max_length": 988.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 721.25, - "completions/min_terminated_length": 441.0, - "completions/max_terminated_length": 988.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.75, - "rewards/match_format_approximately/std": 0.8660253882408142, - "rewards/check_answer/mean": -2.25, - "rewards/check_answer/std": 0.28867512941360474, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -1.5, - "reward_std": 2.309401035308838, - "frac_reward_zero_std": 0.0, - "entropy": 0.25085046887397766, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00031473758753639155, - "time_ms": 49076.82833302533, - "memory_mb": 56826.26611328125, - "memory_gb": 55.49440050125122 - }, - { - "step": 5, - "loss": 0.0162, - "grad_norm": 143.0, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 15442.0, - "completions/mean_length": 293.5, - "completions/min_length": 246.0, - "completions/max_length": 365.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 293.5, - "completions/min_terminated_length": 246.0, - "completions/max_terminated_length": 365.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -3.0, - "rewards/check_answer/std": 1.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.0, - "reward_std": 1.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.0809403508901596, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00039342198442048943, - "time_ms": 18123.881562962197, - "memory_mb": 52261.25830078125, - "memory_gb": 51.03638505935669 - }, - { - "step": 6, - "loss": 0.0, - "grad_norm": 0.0, - "learning_rate": 2.7777777777777783e-06, - "num_tokens": 21877.0, - "completions/mean_length": 1511.75, - "completions/min_length": 1112.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.5, - "completions/mean_terminated_length": 1177.5, - "completions/min_terminated_length": 1112.0, - "completions/max_terminated_length": 1243.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "entropy": 0.2572544813156128, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0004721063813045873, - "time_ms": 92771.2398529984, - "memory_mb": 63378.49365234375, - "memory_gb": 61.89306020736694 - }, - { - "step": 7, - "loss": 0.0736, - "grad_norm": 74.0, - "learning_rate": 2.222222222222222e-06, - "num_tokens": 24635.0, - "completions/mean_length": 546.5, - "completions/min_length": 466.0, - "completions/max_length": 585.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 546.5, - "completions/min_terminated_length": 466.0, - "completions/max_terminated_length": 585.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -1.5, - "rewards/check_answer/std": 2.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 1.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.05001620948314667, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0005507907781886852, - "time_ms": 30032.14380296413, - "memory_mb": 53704.75830078125, - "memory_gb": 52.44605302810669 - }, - { - "step": 8, - "loss": -0.0475, - "grad_norm": 97.0, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 27393.0, - "completions/mean_length": 622.5, - "completions/min_length": 533.0, - "completions/max_length": 696.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 622.5, - "completions/min_terminated_length": 533.0, - "completions/max_terminated_length": 696.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -1.5, - "rewards/match_format_approximately/std": 1.7320507764816284, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -0.75, - "rewards/check_numbers/std": 2.872281312942505, - "reward": -4.25, - "reward_std": 4.27200174331665, - "frac_reward_zero_std": 0.0, - "entropy": 0.08264704048633575, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0006294751750727831, - "time_ms": 36016.123837034684, - "memory_mb": 54504.00634765625, - "memory_gb": 53.22656869888306 - }, - { - "step": 9, - "loss": -0.1881, - "grad_norm": 274.0, - "learning_rate": 1.111111111111111e-06, - "num_tokens": 29461.0, - "completions/mean_length": 420.0, - "completions/min_length": 327.0, - "completions/max_length": 647.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 420.0, - "completions/min_terminated_length": 327.0, - "completions/max_terminated_length": 647.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 2.1213202476501465, - "rewards/check_answer/mean": -1.25, - "rewards/check_answer/std": 1.8484227657318115, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -1.5, - "reward_std": 5.16397762298584, - "frac_reward_zero_std": 0.0, - "entropy": 0.22891533374786377, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007081595719568809, - "time_ms": 35705.52668598248, - "memory_mb": 54149.77783203125, - "memory_gb": 52.88064241409302 - }, - { - "step": 10, - "loss": 0.0444, - "grad_norm": 236.0, - "learning_rate": 5.555555555555555e-07, - "num_tokens": 33785.0, - "completions/mean_length": 913.0, - "completions/min_length": 832.0, - "completions/max_length": 998.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 913.0, - "completions/min_terminated_length": 832.0, - "completions/max_terminated_length": 998.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -6.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.1578676998615265, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007868439688409789, - "time_ms": 53879.347916983534, - "memory_mb": 56904.7578125, - "memory_gb": 55.57105255126953 - } -] \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_cb_paged_10.summary.json b/scripts/benchmarks/results/stats/grpo_cb_paged_10.summary.json deleted file mode 100644 index 23237f400e..0000000000 --- a/scripts/benchmarks/results/stats/grpo_cb_paged_10.summary.json +++ /dev/null @@ -1,64 +0,0 @@ -{ - "backend": "cb_paged", - "max_steps": 10, - "train_wall_s": 466.01091928296955, - "median_step_ms_post_warmup": 36016.123837034684, - "n_logged_steps": 10, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - }, - "losses": [ - -0.0862, - 0.041, - 0.0, - 0.0855, - 0.0162, - 0.0, - 0.0736, - -0.0475, - -0.1881, - 0.0444 - ], - "rewards": [ - 0.625, - -2.5, - 0.5, - -1.5, - 0.0, - -7.5, - 1.5, - -4.25, - -1.5, - -6.5 - ], - "kls": [], - "grad_norms": [ - 716.0, - 186.0, - 0.0, - 274.0, - 143.0, - 0.0, - 74.0, - 97.0, - 274.0, - 236.0 - ], - "step_times_ms": [ - 56644.44096497027, - 29505.720576969907, - 62939.08593803644, - 49076.82833302533, - 18123.881562962197, - 92771.2398529984, - 30032.14380296413, - 36016.123837034684, - 35705.52668598248, - 53879.347916983534 - ], - "peak_memory_gb": 55.57105255126953, - "logs_path": "logs/grpo_cb_paged_10.json" -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_cb_paged_30.json b/scripts/benchmarks/results/stats/grpo_cb_paged_30.json deleted file mode 100644 index e7fa219d9b..0000000000 --- a/scripts/benchmarks/results/stats/grpo_cb_paged_30.json +++ /dev/null @@ -1,1052 +0,0 @@ -[ - { - "step": 1, - "loss": -0.0862, - "grad_norm": 716.0, - "learning_rate": 0.0, - "num_tokens": 4262.0, - "completions/mean_length": 953.5, - "completions/min_length": 824.0, - "completions/max_length": 1092.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 953.5, - "completions/min_terminated_length": 824.0, - "completions/max_terminated_length": 1092.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 1.125, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -1.25, - "rewards/check_answer/std": 2.1794495582580566, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.625, - "reward_std": 3.4731109142303467, - "frac_reward_zero_std": 0.0, - "entropy": 0.1351587027311325, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 7.868439688409789e-05, - "time_ms": 55554.10714598838, - "memory_mb": 57451.41162109375, - "memory_gb": 56.104894161224365 - }, - { - "step": 2, - "loss": 0.041, - "grad_norm": 184.0, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 6762.0, - "completions/mean_length": 536.0, - "completions/min_length": 492.0, - "completions/max_length": 603.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 536.0, - "completions/min_terminated_length": 492.0, - "completions/max_terminated_length": 603.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -2.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.05973631516098976, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00015736879376819577, - "time_ms": 29354.5744830044, - "memory_mb": 53805.20556640625, - "memory_gb": 52.5441460609436 - }, - { - "step": 3, - "loss": 0.1442, - "grad_norm": 664.0, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 9938.0, - "completions/mean_length": 617.0, - "completions/min_length": 444.0, - "completions/max_length": 795.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 617.0, - "completions/min_terminated_length": 444.0, - "completions/max_terminated_length": 795.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -2.375, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -1.5, - "reward_std": 4.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.23810675740242004, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00023605319065229366, - "time_ms": 38962.64252299443, - "memory_mb": 55348.4404296875, - "memory_gb": 54.0512113571167 - }, - { - "step": 4, - "loss": 0.4175, - "grad_norm": 632.0, - "learning_rate": 5e-06, - "num_tokens": 15580.0, - "completions/mean_length": 1245.5, - "completions/min_length": 584.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.5, - "completions/mean_terminated_length": 645.0, - "completions/min_terminated_length": 584.0, - "completions/max_terminated_length": 706.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -1.5, - "rewards/match_format_approximately/std": 1.7320507764816284, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -5.5, - "reward_std": 2.309401035308838, - "frac_reward_zero_std": 0.0, - "entropy": 0.1256246566772461, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00031473758753639155, - "time_ms": 91278.88684801292, - "memory_mb": 63429.4716796875, - "memory_gb": 61.942843437194824 - }, - { - "step": 5, - "loss": 0.0106, - "grad_norm": 36.25, - "learning_rate": 4.814814814814815e-06, - "num_tokens": 17195.0, - "completions/mean_length": 247.75, - "completions/min_length": 246.0, - "completions/max_length": 253.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 247.75, - "completions/min_terminated_length": 246.0, - "completions/max_terminated_length": 253.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -3.0, - "rewards/check_answer/std": 1.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.0, - "reward_std": 1.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.04783342406153679, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00039342198442048943, - "time_ms": 12430.784016032703, - "memory_mb": 52261.31103515625, - "memory_gb": 51.036436557769775 - }, - { - "step": 6, - "loss": 0.0, - "grad_norm": 0.0, - "learning_rate": 4.62962962962963e-06, - "num_tokens": 24405.0, - "completions/mean_length": 1705.5, - "completions/min_length": 1284.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.75, - "completions/mean_terminated_length": 1284.0, - "completions/min_terminated_length": 1284.0, - "completions/max_terminated_length": 1284.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "entropy": 0.2811226546764374, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0004721063813045873, - "time_ms": 90694.74714196986, - "memory_mb": 63378.44287109375, - "memory_gb": 61.89301061630249 - }, - { - "step": 7, - "loss": -0.053, - "grad_norm": 78.5, - "learning_rate": 4.444444444444444e-06, - "num_tokens": 27235.0, - "completions/mean_length": 564.5, - "completions/min_length": 496.0, - "completions/max_length": 616.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 564.5, - "completions/min_terminated_length": 496.0, - "completions/max_terminated_length": 616.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.125, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -4.5, - "reward_std": 3.8297085762023926, - "frac_reward_zero_std": 0.0, - "entropy": 0.06501694023609161, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0005507907781886852, - "time_ms": 30823.07043799665, - "memory_mb": 53944.09619140625, - "memory_gb": 52.679781436920166 - }, - { - "step": 8, - "loss": -0.0433, - "grad_norm": 418.0, - "learning_rate": 4.2592592592592596e-06, - "num_tokens": 30185.0, - "completions/mean_length": 670.5, - "completions/min_length": 560.0, - "completions/max_length": 762.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 670.5, - "completions/min_terminated_length": 560.0, - "completions/max_terminated_length": 762.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -1.5, - "rewards/match_format_approximately/std": 1.7320507764816284, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": 0.5, - "rewards/check_numbers/std": 3.464101552963257, - "reward": -3.0, - "reward_std": 5.196152210235596, - "frac_reward_zero_std": 0.0, - "entropy": 0.11768585443496704, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0006294751750727831, - "time_ms": 37861.39360797824, - "memory_mb": 55010.83203125, - "memory_gb": 53.72151565551758 - }, - { - "step": 9, - "loss": 0.0257, - "grad_norm": 51.75, - "learning_rate": 4.074074074074074e-06, - "num_tokens": 32044.0, - "completions/mean_length": 367.75, - "completions/min_length": 352.0, - "completions/max_length": 386.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 367.75, - "completions/min_terminated_length": 352.0, - "completions/max_terminated_length": 386.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.125, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -4.5, - "reward_std": 3.8297085762023926, - "frac_reward_zero_std": 0.0, - "entropy": 0.04975569620728493, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007081595719568809, - "time_ms": 18964.377576019615, - "memory_mb": 52138.71337890625, - "memory_gb": 50.916712284088135 - }, - { - "step": 10, - "loss": 0.1615, - "grad_norm": 330.0, - "learning_rate": 3.88888888888889e-06, - "num_tokens": 36157.0, - "completions/mean_length": 860.25, - "completions/min_length": 741.0, - "completions/max_length": 1140.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 860.25, - "completions/min_terminated_length": 741.0, - "completions/max_terminated_length": 1140.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 2.1213202476501465, - "rewards/check_answer/mean": -3.25, - "rewards/check_answer/std": 1.4433757066726685, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -3.5, - "reward_std": 2.8284270763397217, - "frac_reward_zero_std": 0.0, - "entropy": 0.3105472922325134, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007868439688409789, - "time_ms": 55770.05596697563, - "memory_mb": 57997.91943359375, - "memory_gb": 56.6385931968689 - }, - { - "step": 11, - "loss": 0.2728, - "grad_norm": 244.0, - "learning_rate": 3.7037037037037037e-06, - "num_tokens": 39660.0, - "completions/mean_length": 763.75, - "completions/min_length": 311.0, - "completions/max_length": 1302.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 763.75, - "completions/min_terminated_length": 311.0, - "completions/max_terminated_length": 1302.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.0, - "rewards/check_numbers/std": 3.0, - "reward": -5.25, - "reward_std": 4.5, - "frac_reward_zero_std": 0.0, - "entropy": 0.26587581634521484, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0008655283657250767, - "time_ms": 63336.94338303758, - "memory_mb": 59203.02880859375, - "memory_gb": 57.815457820892334 - }, - { - "step": 12, - "loss": 0.5823, - "grad_norm": 920.0, - "learning_rate": 3.5185185185185187e-06, - "num_tokens": 42795.0, - "completions/mean_length": 654.75, - "completions/min_length": 210.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 257.66668701171875, - "completions/min_terminated_length": 210.0, - "completions/max_terminated_length": 344.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -1.5, - "rewards/match_format_approximately/std": 1.7320507764816284, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -5.5, - "reward_std": 2.309401035308838, - "frac_reward_zero_std": 0.0, - "entropy": 0.18270480632781982, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0009442127626091746, - "time_ms": 88045.46197201125, - "memory_mb": 63403.7119140625, - "memory_gb": 61.91768741607666 - }, - { - "step": 13, - "loss": 0.0, - "grad_norm": 0.0, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 45233.0, - "completions/mean_length": 466.5, - "completions/min_length": 432.0, - "completions/max_length": 513.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 466.5, - "completions/min_terminated_length": 432.0, - "completions/max_terminated_length": 513.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -3.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "entropy": 0.03867680951952934, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0010228971594932726, - "time_ms": 25137.27058301447, - "memory_mb": 53152.62451171875, - "memory_gb": 51.90685987472534 - }, - { - "step": 14, - "loss": 0.2309, - "grad_norm": 380.0, - "learning_rate": 3.1481481481481483e-06, - "num_tokens": 47795.0, - "completions/mean_length": 522.5, - "completions/min_length": 359.0, - "completions/max_length": 676.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 522.5, - "completions/min_terminated_length": 359.0, - "completions/max_terminated_length": 676.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": 0.75, - "rewards/check_numbers/std": 3.2015621662139893, - "reward": -2.0, - "reward_std": 4.358899116516113, - "frac_reward_zero_std": 0.0, - "entropy": 0.08281465619802475, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0011015815563773703, - "time_ms": 32668.75728900777, - "memory_mb": 54390.24365234375, - "memory_gb": 53.11547231674194 - }, - { - "step": 15, - "loss": 0.2529, - "grad_norm": 368.0, - "learning_rate": 2.962962962962963e-06, - "num_tokens": 52239.0, - "completions/mean_length": 953.0, - "completions/min_length": 547.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 655.3333740234375, - "completions/min_terminated_length": 547.0, - "completions/max_terminated_length": 739.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.125, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -0.25, - "rewards/check_answer/std": 3.5, - "rewards/check_numbers/mean": -0.75, - "rewards/check_numbers/std": 2.872281312942505, - "reward": -1.375, - "reward_std": 9.76707935333252, - "frac_reward_zero_std": 0.0, - "entropy": 0.15795592963695526, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0011802659532614682, - "time_ms": 89534.06670497498, - "memory_mb": 63424.408203125, - "memory_gb": 61.93789863586426 - }, - { - "step": 16, - "loss": -0.0039, - "grad_norm": 57.0, - "learning_rate": 2.7777777777777783e-06, - "num_tokens": 55300.0, - "completions/mean_length": 606.25, - "completions/min_length": 599.0, - "completions/max_length": 616.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 606.25, - "completions/min_terminated_length": 599.0, - "completions/max_terminated_length": 616.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": 1.25, - "rewards/check_answer/std": 4.330127239227295, - "rewards/check_numbers/mean": 1.0, - "rewards/check_numbers/std": 2.886751413345337, - "reward": 6.75, - "reward_std": 7.216878414154053, - "frac_reward_zero_std": 0.0, - "entropy": 0.046795804053545, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0012589503501455662, - "time_ms": 30537.121773988474, - "memory_mb": 53955.2783203125, - "memory_gb": 52.690701484680176 - }, - { - "step": 17, - "loss": 0.0829, - "grad_norm": 185.0, - "learning_rate": 2.5925925925925925e-06, - "num_tokens": 60786.0, - "completions/mean_length": 1182.5, - "completions/min_length": 841.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 961.3333740234375, - "completions/min_terminated_length": 841.0, - "completions/max_terminated_length": 1085.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 2.598076105117798, - "rewards/check_answer/mean": -0.375, - "rewards/check_answer/std": 3.5910770893096924, - "rewards/check_numbers/mean": -0.75, - "rewards/check_numbers/std": 2.872281312942505, - "reward": -0.375, - "reward_std": 9.681382179260254, - "frac_reward_zero_std": 0.0, - "entropy": 0.3588639199733734, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.001337634747029664, - "time_ms": 90275.84768499946, - "memory_mb": 63447.84521484375, - "memory_gb": 61.96078634262085 - }, - { - "step": 18, - "loss": 0.3114, - "grad_norm": 296.0, - "learning_rate": 2.4074074074074075e-06, - "num_tokens": 66174.0, - "completions/mean_length": 1204.0, - "completions/min_length": 454.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.5, - "completions/mean_terminated_length": 562.0, - "completions/min_terminated_length": 454.0, - "completions/max_terminated_length": 670.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -6.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.06863009184598923, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0014163191439137619, - "time_ms": 91312.23277695244, - "memory_mb": 63413.01708984375, - "memory_gb": 61.92677450180054 - }, - { - "step": 19, - "loss": 0.0053, - "grad_norm": 134.0, - "learning_rate": 2.222222222222222e-06, - "num_tokens": 68321.0, - "completions/mean_length": 340.75, - "completions/min_length": 232.0, - "completions/max_length": 471.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 340.75, - "completions/min_terminated_length": 232.0, - "completions/max_terminated_length": 471.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 1.4361406564712524, - "rewards/check_answer/mean": -2.25, - "rewards/check_answer/std": 0.28867512941360474, - "rewards/check_numbers/mean": -0.75, - "rewards/check_numbers/std": 0.8660253882408142, - "reward": -1.125, - "reward_std": 1.973786473274231, - "frac_reward_zero_std": 0.0, - "entropy": 0.12558427453041077, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0014950035407978598, - "time_ms": 22925.990092975553, - "memory_mb": 53074.19970703125, - "memory_gb": 51.830273151397705 - }, - { - "step": 20, - "loss": 0.0803, - "grad_norm": 252.0, - "learning_rate": 2.037037037037037e-06, - "num_tokens": 71085.0, - "completions/mean_length": 593.0, - "completions/min_length": 486.0, - "completions/max_length": 810.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 593.0, - "completions/min_terminated_length": 486.0, - "completions/max_terminated_length": 810.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.75, - "rewards/match_format_approximately/std": 0.8660253882408142, - "rewards/check_answer/mean": -2.25, - "rewards/check_answer/std": 0.28867512941360474, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -1.5, - "reward_std": 2.309401035308838, - "frac_reward_zero_std": 0.0, - "entropy": 0.3193286061286926, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0015736879376819577, - "time_ms": 39714.41951999441, - "memory_mb": 55404.677734375, - "memory_gb": 54.106130599975586 - }, - { - "step": 21, - "loss": 0.0498, - "grad_norm": 326.0, - "learning_rate": 1.8518518518518519e-06, - "num_tokens": 73899.0, - "completions/mean_length": 617.5, - "completions/min_length": 567.0, - "completions/max_length": 721.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 617.5, - "completions/min_terminated_length": 567.0, - "completions/max_terminated_length": 721.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.75, - "rewards/match_format_approximately/std": 0.8660253882408142, - "rewards/check_answer/mean": 0.625, - "rewards/check_answer/std": 3.350994825363159, - "rewards/check_numbers/mean": 2.25, - "rewards/check_numbers/std": 2.5, - "reward": 5.125, - "reward_std": 5.437140941619873, - "frac_reward_zero_std": 0.0, - "entropy": 0.17848895490169525, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0016523723345660555, - "time_ms": 35041.47868498694, - "memory_mb": 54711.2119140625, - "memory_gb": 53.42891788482666 - }, - { - "step": 22, - "loss": -0.0079, - "grad_norm": 101.0, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 76046.0, - "completions/mean_length": 424.75, - "completions/min_length": 383.0, - "completions/max_length": 471.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 424.75, - "completions/min_terminated_length": 383.0, - "completions/max_terminated_length": 471.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": 3.125, - "rewards/check_answer/std": 0.75, - "rewards/check_numbers/mean": 2.25, - "rewards/check_numbers/std": 2.5, - "reward": 9.875, - "reward_std": 3.25, - "frac_reward_zero_std": 0.0, - "entropy": 0.059299319982528687, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0017310567314501534, - "time_ms": 22683.228761015926, - "memory_mb": 52805.021484375, - "memory_gb": 51.56740379333496 - }, - { - "step": 23, - "loss": -0.0559, - "grad_norm": 213.0, - "learning_rate": 1.4814814814814815e-06, - "num_tokens": 78477.0, - "completions/mean_length": 489.75, - "completions/min_length": 450.0, - "completions/max_length": 569.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 489.75, - "completions/min_terminated_length": 450.0, - "completions/max_terminated_length": 569.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -0.375, - "rewards/check_answer/std": 2.462214469909668, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 2.625, - "reward_std": 2.462214469909668, - "frac_reward_zero_std": 0.0, - "entropy": 0.08941338956356049, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0018097411283342513, - "time_ms": 29075.48440602841, - "memory_mb": 53564.72998046875, - "memory_gb": 52.309306621551514 - }, - { - "step": 24, - "loss": 0.0286, - "grad_norm": 128.0, - "learning_rate": 1.2962962962962962e-06, - "num_tokens": 82025.0, - "completions/mean_length": 717.0, - "completions/min_length": 623.0, - "completions/max_length": 785.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 717.0, - "completions/min_terminated_length": 623.0, - "completions/max_terminated_length": 785.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.875, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -1.125, - "rewards/check_answer/std": 1.75, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -4.5, - "reward_std": 6.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.130662202835083, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0018884255252183493, - "time_ms": 39820.741517003626, - "memory_mb": 55265.95751953125, - "memory_gb": 53.970661640167236 - }, - { - "step": 25, - "loss": 0.1726, - "grad_norm": 78.0, - "learning_rate": 1.111111111111111e-06, - "num_tokens": 83908.0, - "completions/mean_length": 394.75, - "completions/min_length": 286.0, - "completions/max_length": 531.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 394.75, - "completions/min_terminated_length": 286.0, - "completions/max_terminated_length": 531.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": 3.125, - "rewards/check_answer/std": 3.75, - "rewards/check_numbers/mean": 2.25, - "rewards/check_numbers/std": 2.5, - "reward": 9.875, - "reward_std": 6.25, - "frac_reward_zero_std": 0.0, - "entropy": 0.04741385951638222, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0019671099221024472, - "time_ms": 25694.13814501604, - "memory_mb": 53241.78662109375, - "memory_gb": 51.993932247161865 - }, - { - "step": 26, - "loss": 0.4091, - "grad_norm": 276.0, - "learning_rate": 9.259259259259259e-07, - "num_tokens": 89379.0, - "completions/mean_length": 1253.75, - "completions/min_length": 644.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.5, - "completions/mean_terminated_length": 661.5, - "completions/min_terminated_length": 644.0, - "completions/max_terminated_length": 679.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 2.598076105117798, - "rewards/check_answer/mean": -2.75, - "rewards/check_answer/std": 1.190238118171692, - "rewards/check_numbers/mean": -1.625, - "rewards/check_numbers/std": 1.1814539432525635, - "reward": -3.625, - "reward_std": 4.479118347167969, - "frac_reward_zero_std": 0.0, - "entropy": 0.22006553411483765, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.002045794318986545, - "time_ms": 90294.3110250053, - "memory_mb": 63390.86669921875, - "memory_gb": 61.90514326095581 - }, - { - "step": 27, - "loss": -0.102, - "grad_norm": 290.0, - "learning_rate": 7.407407407407407e-07, - "num_tokens": 93739.0, - "completions/mean_length": 946.0, - "completions/min_length": 807.0, - "completions/max_length": 1139.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 946.0, - "completions/min_terminated_length": 807.0, - "completions/max_terminated_length": 1139.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -6.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.15364356338977814, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0021244787158706427, - "time_ms": 56216.15647501312, - "memory_mb": 57971.0712890625, - "memory_gb": 56.6123743057251 - }, - { - "step": 28, - "loss": -0.0477, - "grad_norm": 752.0, - "learning_rate": 5.555555555555555e-07, - "num_tokens": 97665.0, - "completions/mean_length": 837.5, - "completions/min_length": 748.0, - "completions/max_length": 967.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 837.5, - "completions/min_terminated_length": 748.0, - "completions/max_terminated_length": 967.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.125, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -2.625, - "rewards/check_answer/std": 1.25, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -5.0, - "reward_std": 3.0, - "frac_reward_zero_std": 0.0, - "entropy": 0.24837817251682281, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0022031631127547406, - "time_ms": 47257.37831299193, - "memory_mb": 56647.58935546875, - "memory_gb": 55.31991147994995 - }, - { - "step": 29, - "loss": 0.1184, - "grad_norm": 576.0, - "learning_rate": 3.7037037037037036e-07, - "num_tokens": 103868.0, - "completions/mean_length": 1354.75, - "completions/min_length": 1124.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 1191.0, - "completions/min_terminated_length": 1124.0, - "completions/max_terminated_length": 1322.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -0.375, - "rewards/match_format_approximately/std": 1.8874585628509521, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -3.5, - "reward_std": 3.265986442565918, - "frac_reward_zero_std": 0.0, - "entropy": 0.4512600004673004, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0022818475096388386, - "time_ms": 90669.61020795861, - "memory_mb": 63452.36083984375, - "memory_gb": 61.96519613265991 - }, - { - "step": 30, - "loss": 0.2766, - "grad_norm": 800.0, - "learning_rate": 1.8518518518518518e-07, - "num_tokens": 109818.0, - "completions/mean_length": 1391.5, - "completions/min_length": 666.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 1240.0, - "completions/min_terminated_length": 666.0, - "completions/max_terminated_length": 1654.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 1.9364917278289795, - "rewards/check_answer/mean": -0.25, - "rewards/check_answer/std": 3.5, - "rewards/check_numbers/mean": -0.375, - "rewards/check_numbers/std": 2.839454174041748, - "reward": -0.625, - "reward_std": 9.375277519226074, - "frac_reward_zero_std": 0.0, - "entropy": 0.15001536905765533, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0023605319065229365, - "time_ms": 91291.07107501477, - "memory_mb": 63377.84716796875, - "memory_gb": 61.89242887496948 - } -] \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_cb_paged_30.summary.json b/scripts/benchmarks/results/stats/grpo_cb_paged_30.summary.json deleted file mode 100644 index 475c455100..0000000000 --- a/scripts/benchmarks/results/stats/grpo_cb_paged_30.summary.json +++ /dev/null @@ -1,144 +0,0 @@ -{ - "backend": "cb_paged", - "max_steps": 30, - "train_wall_s": 1564.461075181025, - "median_step_ms_post_warmup": 39820.741517003626, - "n_logged_steps": 30, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - }, - "losses": [ - -0.0862, - 0.041, - 0.1442, - 0.4175, - 0.0106, - 0.0, - -0.053, - -0.0433, - 0.0257, - 0.1615, - 0.2728, - 0.5823, - 0.0, - 0.2309, - 0.2529, - -0.0039, - 0.0829, - 0.3114, - 0.0053, - 0.0803, - 0.0498, - -0.0079, - -0.0559, - 0.0286, - 0.1726, - 0.4091, - -0.102, - -0.0477, - 0.1184, - 0.2766 - ], - "rewards": [ - 0.625, - -2.5, - -1.5, - -5.5, - 0.0, - -7.5, - -4.5, - -3.0, - -4.5, - -3.5, - -5.25, - -5.5, - -3.5, - -2.0, - -1.375, - 6.75, - -0.375, - -6.5, - -1.125, - -1.5, - 5.125, - 9.875, - 2.625, - -4.5, - 9.875, - -3.625, - -6.5, - -5.0, - -3.5, - -0.625 - ], - "kls": [], - "grad_norms": [ - 716.0, - 184.0, - 664.0, - 632.0, - 36.25, - 0.0, - 78.5, - 418.0, - 51.75, - 330.0, - 244.0, - 920.0, - 0.0, - 380.0, - 368.0, - 57.0, - 185.0, - 296.0, - 134.0, - 252.0, - 326.0, - 101.0, - 213.0, - 128.0, - 78.0, - 276.0, - 290.0, - 752.0, - 576.0, - 800.0 - ], - "step_times_ms": [ - 55554.10714598838, - 29354.5744830044, - 38962.64252299443, - 91278.88684801292, - 12430.784016032703, - 90694.74714196986, - 30823.07043799665, - 37861.39360797824, - 18964.377576019615, - 55770.05596697563, - 63336.94338303758, - 88045.46197201125, - 25137.27058301447, - 32668.75728900777, - 89534.06670497498, - 30537.121773988474, - 90275.84768499946, - 91312.23277695244, - 22925.990092975553, - 39714.41951999441, - 35041.47868498694, - 22683.228761015926, - 29075.48440602841, - 39820.741517003626, - 25694.13814501604, - 90294.3110250053, - 56216.15647501312, - 47257.37831299193, - 90669.61020795861, - 91291.07107501477 - ], - "peak_memory_gb": 61.89242887496948, - "logs_path": "logs/grpo_cb_paged_30.json" -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_fi_false_30.json b/scripts/benchmarks/results/stats/grpo_fi_false_30.json deleted file mode 100644 index 6bf92cd2d0..0000000000 --- a/scripts/benchmarks/results/stats/grpo_fi_false_30.json +++ /dev/null @@ -1,1082 +0,0 @@ -[ - { - "step": 1, - "loss": 0.0, - "grad_norm": 0.0, - "learning_rate": 0.0, - "num_tokens": 3693.0, - "completions/mean_length": 811.25, - "completions/min_length": 779.0, - "completions/max_length": 856.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 811.25, - "completions/min_terminated_length": 779.0, - "completions/max_terminated_length": 856.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.5, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 811.25, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 7.868439688409789e-05, - "time_ms": 47513.93520901911, - "memory_mb": 9253.59765625, - "memory_gb": 9.03671646118164 - }, - { - "step": 2, - "loss": -0.0893, - "grad_norm": 0.6121569275856018, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 6238.0, - "completions/mean_length": 547.25, - "completions/min_length": 487.0, - "completions/max_length": 645.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 547.25, - "completions/min_terminated_length": 487.0, - "completions/max_terminated_length": 645.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -6.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 547.25, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00015736879376819577, - "time_ms": 26899.73210898461, - "memory_mb": 9076.26025390625, - "memory_gb": 8.863535404205322 - }, - { - "step": 3, - "loss": -0.1912, - "grad_norm": 0.5873263478279114, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 9665.0, - "completions/mean_length": 679.75, - "completions/min_length": 533.0, - "completions/max_length": 1002.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 679.75, - "completions/min_terminated_length": 533.0, - "completions/max_terminated_length": 1002.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.5, - "rewards/match_format_approximately/std": 2.1213202476501465, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.625, - "rewards/check_numbers/std": 1.1814539432525635, - "reward": -4.5, - "reward_std": 3.8297085762023926, - "frac_reward_zero_std": 0.0, - "completion_length": 679.75, - "kl": 0.006437055766582489, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00023605319065229366, - "time_ms": 41262.48180796392, - "memory_mb": 9628.142578125, - "memory_gb": 9.402482986450195 - }, - { - "step": 4, - "loss": 0.4302, - "grad_norm": 0.4428107738494873, - "learning_rate": 5e-06, - "num_tokens": 14294.0, - "completions/mean_length": 992.25, - "completions/min_length": 572.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 707.6666870117188, - "completions/min_terminated_length": 572.0, - "completions/max_terminated_length": 797.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -4.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 992.25, - "kl": 0.007001329679042101, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00031473758753639155, - "time_ms": 66495.43262599036, - "memory_mb": 10919.0859375, - "memory_gb": 10.663169860839844 - }, - { - "step": 5, - "loss": -0.0144, - "grad_norm": 0.9299039244651794, - "learning_rate": 4.814814814814815e-06, - "num_tokens": 16166.0, - "completions/mean_length": 312.0, - "completions/min_length": 303.0, - "completions/max_length": 315.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 312.0, - "completions/min_terminated_length": 303.0, - "completions/max_terminated_length": 315.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": 2.625, - "rewards/check_answer/std": 4.75, - "rewards/check_numbers/mean": 2.25, - "rewards/check_numbers/std": 2.5, - "reward": 9.375, - "reward_std": 7.25, - "frac_reward_zero_std": 0.0, - "completion_length": 312.0, - "kl": 0.0032435881439596415, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00039342198442048943, - "time_ms": 10969.204296008684, - "memory_mb": 8791.23876953125, - "memory_gb": 8.585194110870361 - }, - { - "step": 6, - "loss": 0.0, - "grad_norm": 0.0014747647801414132, - "learning_rate": 4.62962962962963e-06, - "num_tokens": 23938.0, - "completions/mean_length": 1846.0, - "completions/min_length": 1846.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 1.0, - "completions/mean_terminated_length": 0.0, - "completions/min_terminated_length": 0.0, - "completions/max_terminated_length": 0.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 1846.0, - "kl": 0.00288483127951622, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0004721063813045873, - "time_ms": 60708.51903402945, - "memory_mb": 10914.98193359375, - "memory_gb": 10.659162044525146 - }, - { - "step": 7, - "loss": 0.0036, - "grad_norm": 0.6682185530662537, - "learning_rate": 4.444444444444444e-06, - "num_tokens": 26669.0, - "completions/mean_length": 539.75, - "completions/min_length": 505.0, - "completions/max_length": 570.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 539.75, - "completions/min_terminated_length": 505.0, - "completions/max_terminated_length": 570.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 2.598076105117798, - "rewards/check_answer/mean": -2.25, - "rewards/check_answer/std": 0.28867512941360474, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -3.5, - "reward_std": 4.618802070617676, - "frac_reward_zero_std": 0.0, - "completion_length": 539.75, - "kl": 0.0062899235635995865, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0005507907781886852, - "time_ms": 19134.767919022124, - "memory_mb": 8999.23828125, - "memory_gb": 8.788318634033203 - }, - { - "step": 8, - "loss": 0.0, - "grad_norm": 0.00014817823830526322, - "learning_rate": 4.2592592592592596e-06, - "num_tokens": 30907.0, - "completions/mean_length": 992.5, - "completions/min_length": 739.0, - "completions/max_length": 1246.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 992.5, - "completions/min_terminated_length": 739.0, - "completions/max_terminated_length": 1246.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 992.5, - "kl": 0.0008946225862018764, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0006294751750727831, - "time_ms": 41297.174014966, - "memory_mb": 10005.82177734375, - "memory_gb": 9.771310329437256 - }, - { - "step": 9, - "loss": -0.1558, - "grad_norm": 0.2690228223800659, - "learning_rate": 4.074074074074074e-06, - "num_tokens": 35749.0, - "completions/mean_length": 1113.5, - "completions/min_length": 380.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.5, - "completions/mean_terminated_length": 381.0, - "completions/min_terminated_length": 380.0, - "completions/max_terminated_length": 382.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": -0.375, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -2.75, - "rewards/check_answer/std": 1.190238118171692, - "rewards/check_numbers/mean": -1.0, - "rewards/check_numbers/std": 1.2247449159622192, - "reward": -2.625, - "reward_std": 3.705289125442505, - "frac_reward_zero_std": 0.0, - "completion_length": 1113.5, - "kl": 0.0027981880120933056, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007081595719568809, - "time_ms": 61718.76015001908, - "memory_mb": 10914.98193359375, - "memory_gb": 10.659162044525146 - }, - { - "step": 10, - "loss": 0.018, - "grad_norm": 0.4899609088897705, - "learning_rate": 3.88888888888889e-06, - "num_tokens": 40357.0, - "completions/mean_length": 984.0, - "completions/min_length": 770.0, - "completions/max_length": 1157.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 984.0, - "completions/min_terminated_length": 770.0, - "completions/max_terminated_length": 1157.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 2.598076105117798, - "rewards/check_answer/mean": -3.25, - "rewards/check_answer/std": 1.4433757066726685, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -4.5, - "reward_std": 3.464101552963257, - "frac_reward_zero_std": 0.0, - "completion_length": 984.0, - "kl": 0.0029807849787175655, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007868439688409789, - "time_ms": 46218.60432100948, - "memory_mb": 9873.21826171875, - "memory_gb": 9.641814708709717 - }, - { - "step": 11, - "loss": 0.1468, - "grad_norm": 0.46429336071014404, - "learning_rate": 3.7037037037037037e-06, - "num_tokens": 44529.0, - "completions/mean_length": 931.0, - "completions/min_length": 453.0, - "completions/max_length": 1518.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 931.0, - "completions/min_terminated_length": 453.0, - "completions/max_terminated_length": 1518.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 2.598076105117798, - "rewards/check_answer/mean": 0.625, - "rewards/check_answer/std": 3.350994825363159, - "rewards/check_numbers/mean": -0.75, - "rewards/check_numbers/std": 2.872281312942505, - "reward": 0.625, - "reward_std": 10.003124237060547, - "frac_reward_zero_std": 0.0, - "completion_length": 931.0, - "kl": 0.00796814076602459, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0008655283657250767, - "time_ms": 63510.61685796594, - "memory_mb": 10419.21240234375, - "memory_gb": 10.175012111663818 - }, - { - "step": 12, - "loss": 0.0, - "grad_norm": 0.0002485642035026103, - "learning_rate": 3.5185185185185187e-06, - "num_tokens": 45912.0, - "completions/mean_length": 216.75, - "completions/min_length": 212.0, - "completions/max_length": 231.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 216.75, - "completions/min_terminated_length": 212.0, - "completions/max_terminated_length": 231.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -3.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 216.75, - "kl": 0.001598043367266655, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0009442127626091746, - "time_ms": 10268.670362012926, - "memory_mb": 8757.7900390625, - "memory_gb": 8.552529335021973 - }, - { - "step": 13, - "loss": -0.2741, - "grad_norm": 0.4754463732242584, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 49277.0, - "completions/mean_length": 698.25, - "completions/min_length": 512.0, - "completions/max_length": 1081.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 698.25, - "completions/min_terminated_length": 512.0, - "completions/max_terminated_length": 1081.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -6.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 698.25, - "kl": 0.003610937623307109, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0010228971594932726, - "time_ms": 43201.109810965136, - "memory_mb": 9757.1708984375, - "memory_gb": 9.528487205505371 - }, - { - "step": 14, - "loss": 0.096, - "grad_norm": 0.7229195237159729, - "learning_rate": 3.1481481481481483e-06, - "num_tokens": 51514.0, - "completions/mean_length": 441.25, - "completions/min_length": 348.0, - "completions/max_length": 674.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 441.25, - "completions/min_terminated_length": 348.0, - "completions/max_terminated_length": 674.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.75, - "rewards/match_format_approximately/std": 0.8660253882408142, - "rewards/check_answer/mean": -0.375, - "rewards/check_answer/std": 3.5910770893096924, - "rewards/check_numbers/mean": 2.25, - "rewards/check_numbers/std": 2.5, - "reward": 4.125, - "reward_std": 5.935416221618652, - "frac_reward_zero_std": 0.0, - "completion_length": 441.25, - "kl": 0.0050869532860815525, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0011015815563773703, - "time_ms": 22460.022343031596, - "memory_mb": 9146.40673828125, - "memory_gb": 8.932037830352783 - }, - { - "step": 15, - "loss": 0.0103, - "grad_norm": 0.49645838141441345, - "learning_rate": 2.962962962962963e-06, - "num_tokens": 54580.0, - "completions/mean_length": 608.5, - "completions/min_length": 576.0, - "completions/max_length": 657.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 608.5, - "completions/min_terminated_length": 576.0, - "completions/max_terminated_length": 657.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": 3.125, - "rewards/check_answer/std": 3.75, - "rewards/check_numbers/mean": 2.25, - "rewards/check_numbers/std": 2.5, - "reward": 9.875, - "reward_std": 6.25, - "frac_reward_zero_std": 0.0, - "completion_length": 608.5, - "kl": 0.0019661628175526857, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0011802659532614682, - "time_ms": 21824.53149399953, - "memory_mb": 9118.775390625, - "memory_gb": 8.905054092407227 - }, - { - "step": 16, - "loss": 0.0398, - "grad_norm": 0.3055652379989624, - "learning_rate": 2.7777777777777783e-06, - "num_tokens": 58204.0, - "completions/mean_length": 747.0, - "completions/min_length": 595.0, - "completions/max_length": 834.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 747.0, - "completions/min_terminated_length": 595.0, - "completions/max_terminated_length": 834.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": 1.0, - "rewards/check_numbers/std": 2.886751413345337, - "reward": 0.0, - "reward_std": 2.3804759979248047, - "frac_reward_zero_std": 0.0, - "completion_length": 747.0, - "kl": 0.0062008751556277275, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0012589503501455662, - "time_ms": 27588.505985040683, - "memory_mb": 9391.25830078125, - "memory_gb": 9.17115068435669 - }, - { - "step": 17, - "loss": 0.0139, - "grad_norm": 0.3895750939846039, - "learning_rate": 2.5925925925925925e-06, - "num_tokens": 63202.0, - "completions/mean_length": 1060.5, - "completions/min_length": 932.0, - "completions/max_length": 1344.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 1060.5, - "completions/min_terminated_length": 932.0, - "completions/max_terminated_length": 1344.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.875, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -5.5, - "reward_std": 4.0, - "frac_reward_zero_std": 0.0, - "completion_length": 1060.5, - "kl": 0.003240604419261217, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.001337634747029664, - "time_ms": 44275.010473967995, - "memory_mb": 10169.431640625, - "memory_gb": 9.931085586547852 - }, - { - "step": 18, - "loss": 0.3858, - "grad_norm": 0.5219303369522095, - "learning_rate": 2.4074074074074075e-06, - "num_tokens": 67625.0, - "completions/mean_length": 962.75, - "completions/min_length": 633.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 668.3333740234375, - "completions/min_terminated_length": 633.0, - "completions/max_terminated_length": 686.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -0.375, - "rewards/match_format_approximately/std": 1.8874585628509521, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -3.5, - "reward_std": 3.265986442565918, - "frac_reward_zero_std": 0.0, - "completion_length": 962.75, - "kl": 0.00907122902572155, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0014163191439137619, - "time_ms": 60585.87563998299, - "memory_mb": 10917.68017578125, - "memory_gb": 10.661797046661377 - }, - { - "step": 19, - "loss": 0.9674, - "grad_norm": 0.3664180636405945, - "learning_rate": 2.222222222222222e-06, - "num_tokens": 70925.0, - "completions/mean_length": 629.0, - "completions/min_length": 136.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 223.33334350585938, - "completions/min_terminated_length": 136.0, - "completions/max_terminated_length": 302.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 2.1213202476501465, - "rewards/check_answer/mean": -3.875, - "rewards/check_answer/std": 1.25, - "rewards/check_numbers/mean": -0.75, - "rewards/check_numbers/std": 0.8660253882408142, - "reward": -2.375, - "reward_std": 1.75, - "frac_reward_zero_std": 0.0, - "completion_length": 629.0, - "kl": 0.00969112291932106, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0014950035407978598, - "time_ms": 60958.746705029625, - "memory_mb": 10921.3955078125, - "memory_gb": 10.665425300598145 - }, - { - "step": 20, - "loss": 0.2627, - "grad_norm": 0.453957200050354, - "learning_rate": 2.037037037037037e-06, - "num_tokens": 75362.0, - "completions/mean_length": 1011.25, - "completions/min_length": 359.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 733.0, - "completions/min_terminated_length": 359.0, - "completions/max_terminated_length": 920.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 2.1213202476501465, - "rewards/check_answer/mean": -2.25, - "rewards/check_answer/std": 0.28867512941360474, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -2.5, - "reward_std": 3.8297085762023926, - "frac_reward_zero_std": 0.0, - "completion_length": 1011.25, - "kl": 0.006743168458342552, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0015736879376819577, - "time_ms": 60960.08875203552, - "memory_mb": 10915.64599609375, - "memory_gb": 10.659810543060303 - }, - { - "step": 21, - "loss": 0.0582, - "grad_norm": 0.5753984451293945, - "learning_rate": 1.8518518518518519e-06, - "num_tokens": 77971.0, - "completions/mean_length": 566.25, - "completions/min_length": 499.0, - "completions/max_length": 631.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 566.25, - "completions/min_terminated_length": 499.0, - "completions/max_terminated_length": 631.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 1.125, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": 2.375, - "rewards/check_answer/std": 3.350994825363159, - "rewards/check_numbers/mean": 2.25, - "rewards/check_numbers/std": 2.5, - "reward": 8.0, - "reward_std": 5.901977062225342, - "frac_reward_zero_std": 0.0, - "completion_length": 566.25, - "kl": 0.00867636501789093, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0016523723345660555, - "time_ms": 20987.195259018335, - "memory_mb": 9084.64697265625, - "memory_gb": 8.87172555923462 - }, - { - "step": 22, - "loss": 0.0, - "grad_norm": 0.001453780336305499, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 79903.0, - "completions/mean_length": 371.0, - "completions/min_length": 345.0, - "completions/max_length": 412.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 371.0, - "completions/min_terminated_length": 345.0, - "completions/max_terminated_length": 412.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": 3.5, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": 3.5, - "rewards/check_numbers/std": 0.0, - "reward": 11.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 371.0, - "kl": 0.004581788554787636, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0017310567314501534, - "time_ms": 13986.805958964396, - "memory_mb": 8760.32666015625, - "memory_gb": 8.555006504058838 - }, - { - "step": 23, - "loss": 0.6477, - "grad_norm": 0.45908382534980774, - "learning_rate": 1.4814814814814815e-06, - "num_tokens": 83416.0, - "completions/mean_length": 760.25, - "completions/min_length": 308.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 398.3333435058594, - "completions/min_terminated_length": 308.0, - "completions/max_terminated_length": 450.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -1.875, - "rewards/check_answer/std": 2.4958298206329346, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -1.0, - "reward_std": 5.0, - "frac_reward_zero_std": 0.0, - "completion_length": 760.25, - "kl": 0.007497473154217005, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0018097411283342513, - "time_ms": 60834.94512201287, - "memory_mb": 10916.8193359375, - "memory_gb": 10.660956382751465 - }, - { - "step": 24, - "loss": -0.109, - "grad_norm": 1.2539762258529663, - "learning_rate": 1.2962962962962962e-06, - "num_tokens": 87039.0, - "completions/mean_length": 735.75, - "completions/min_length": 625.0, - "completions/max_length": 835.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 735.75, - "completions/min_terminated_length": 625.0, - "completions/max_terminated_length": 835.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": 1.375, - "rewards/check_answer/std": 4.190763473510742, - "rewards/check_numbers/mean": 0.75, - "rewards/check_numbers/std": 3.2015621662139893, - "reward": 4.75, - "reward_std": 10.070584297180176, - "frac_reward_zero_std": 0.0, - "completion_length": 735.75, - "kl": 0.007104712072759867, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0018884255252183493, - "time_ms": 27714.821267989464, - "memory_mb": 9397.89501953125, - "memory_gb": 9.177631855010986 - }, - { - "step": 25, - "loss": 0.0296, - "grad_norm": 0.6490684747695923, - "learning_rate": 1.111111111111111e-06, - "num_tokens": 89065.0, - "completions/mean_length": 430.5, - "completions/min_length": 286.0, - "completions/max_length": 490.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 430.5, - "completions/min_terminated_length": 286.0, - "completions/max_terminated_length": 490.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 1.125, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": 3.25, - "rewards/check_answer/std": 3.5, - "rewards/check_numbers/mean": 3.5, - "rewards/check_numbers/std": 0.0, - "reward": 10.125, - "reward_std": 5.75, - "frac_reward_zero_std": 0.0, - "completion_length": 430.5, - "kl": 0.00291788624599576, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0019671099221024472, - "time_ms": 16654.144487984013, - "memory_mb": 8867.1201171875, - "memory_gb": 8.659296989440918 - }, - { - "step": 26, - "loss": 0.0185, - "grad_norm": 0.6853195428848267, - "learning_rate": 9.259259259259259e-07, - "num_tokens": 91688.0, - "completions/mean_length": 541.75, - "completions/min_length": 415.0, - "completions/max_length": 697.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 541.75, - "completions/min_terminated_length": 415.0, - "completions/max_terminated_length": 697.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 1.125, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -1.75, - "rewards/check_answer/std": 2.723355770111084, - "rewards/check_numbers/mean": -1.125, - "rewards/check_numbers/std": 0.75, - "reward": 0.5, - "reward_std": 3.488075017929077, - "frac_reward_zero_std": 0.0, - "completion_length": 541.75, - "kl": 0.011633609421551228, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.002045794318986545, - "time_ms": 23337.049510038923, - "memory_mb": 9177.7041015625, - "memory_gb": 8.962601661682129 - }, - { - "step": 27, - "loss": 0.0, - "grad_norm": 0.0011842504609376192, - "learning_rate": 7.407407407407407e-07, - "num_tokens": 95560.0, - "completions/mean_length": 824.0, - "completions/min_length": 745.0, - "completions/max_length": 873.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 824.0, - "completions/min_terminated_length": 745.0, - "completions/max_terminated_length": 873.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 824.0, - "kl": 0.0014683930203318596, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0021244787158706427, - "time_ms": 29055.362954968587, - "memory_mb": 9451.98291015625, - "memory_gb": 9.230452060699463 - }, - { - "step": 28, - "loss": 0.014, - "grad_norm": 0.6820011734962463, - "learning_rate": 5.555555555555555e-07, - "num_tokens": 99037.0, - "completions/mean_length": 725.25, - "completions/min_length": 590.0, - "completions/max_length": 856.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 725.25, - "completions/min_terminated_length": 590.0, - "completions/max_terminated_length": 856.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -3.375, - "rewards/check_answer/std": 1.3149778842926025, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -2.5, - "reward_std": 3.464101552963257, - "frac_reward_zero_std": 0.0, - "completion_length": 725.25, - "kl": 0.006795317865908146, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0022031631127547406, - "time_ms": 28389.59298102418, - "memory_mb": 9432.56787109375, - "memory_gb": 9.21149206161499 - }, - { - "step": 29, - "loss": -0.0851, - "grad_norm": 0.42553478479385376, - "learning_rate": 3.7037037037037036e-07, - "num_tokens": 103436.0, - "completions/mean_length": 903.75, - "completions/min_length": 750.0, - "completions/max_length": 1323.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 903.75, - "completions/min_terminated_length": 750.0, - "completions/max_terminated_length": 1323.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.75, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.375, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -1.125, - "reward_std": 3.25, - "frac_reward_zero_std": 0.0, - "completion_length": 903.75, - "kl": 0.005157058592885733, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0022818475096388386, - "time_ms": 43584.85947694862, - "memory_mb": 10134.4453125, - "memory_gb": 9.896919250488281 - }, - { - "step": 30, - "loss": 0.0898, - "grad_norm": 0.259000688791275, - "learning_rate": 1.8518518518518518e-07, - "num_tokens": 108757.0, - "completions/mean_length": 1234.25, - "completions/min_length": 527.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 1030.3333740234375, - "completions/min_terminated_length": 527.0, - "completions/max_terminated_length": 1642.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 2.1213202476501465, - "rewards/check_answer/mean": 1.5, - "rewards/check_answer/std": 4.041451930999756, - "rewards/check_numbers/mean": 2.0, - "rewards/check_numbers/std": 3.0, - "reward": 5.0, - "reward_std": 9.941495895385742, - "frac_reward_zero_std": 0.0, - "completion_length": 1234.25, - "kl": 0.003586029401049018, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0023605319065229365, - "time_ms": 60590.078279026784, - "memory_mb": 10915.52783203125, - "memory_gb": 10.659695148468018 - } -] \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_fi_false_30.summary.json b/scripts/benchmarks/results/stats/grpo_fi_false_30.summary.json deleted file mode 100644 index 55d4059673..0000000000 --- a/scripts/benchmarks/results/stats/grpo_fi_false_30.summary.json +++ /dev/null @@ -1,175 +0,0 @@ -{ - "backend": "unsloth_fi_false", - "max_steps": 30, - "train_wall_s": 1165.377411015972, - "median_step_ms_post_warmup": 41297.174014966, - "n_logged_steps": 30, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - }, - "losses": [ - 0.0, - -0.0893, - -0.1912, - 0.4302, - -0.0144, - 0.0, - 0.0036, - 0.0, - -0.1558, - 0.018, - 0.1468, - 0.0, - -0.2741, - 0.096, - 0.0103, - 0.0398, - 0.0139, - 0.3858, - 0.9674, - 0.2627, - 0.0582, - 0.0, - 0.6477, - -0.109, - 0.0296, - 0.0185, - 0.0, - 0.014, - -0.0851, - 0.0898 - ], - "rewards": [ - 0.5, - -6.5, - -4.5, - -4.5, - 9.375, - -7.5, - -3.5, - -7.5, - -2.625, - -4.5, - 0.625, - -3.5, - -6.5, - 4.125, - 9.875, - 0.0, - -5.5, - -3.5, - -2.375, - -2.5, - 8.0, - 11.5, - -1.0, - 4.75, - 10.125, - 0.5, - -7.5, - -2.5, - -1.125, - 5.0 - ], - "kls": [ - 0.0, - 0.0, - 0.006437055766582489, - 0.007001329679042101, - 0.0032435881439596415, - 0.00288483127951622, - 0.0062899235635995865, - 0.0008946225862018764, - 0.0027981880120933056, - 0.0029807849787175655, - 0.00796814076602459, - 0.001598043367266655, - 0.003610937623307109, - 0.0050869532860815525, - 0.0019661628175526857, - 0.0062008751556277275, - 0.003240604419261217, - 0.00907122902572155, - 0.00969112291932106, - 0.006743168458342552, - 0.00867636501789093, - 0.004581788554787636, - 0.007497473154217005, - 0.007104712072759867, - 0.00291788624599576, - 0.011633609421551228, - 0.0014683930203318596, - 0.006795317865908146, - 0.005157058592885733, - 0.003586029401049018 - ], - "grad_norms": [ - 0.0, - 0.6121569275856018, - 0.5873263478279114, - 0.4428107738494873, - 0.9299039244651794, - 0.0014747647801414132, - 0.6682185530662537, - 0.00014817823830526322, - 0.2690228223800659, - 0.4899609088897705, - 0.46429336071014404, - 0.0002485642035026103, - 0.4754463732242584, - 0.7229195237159729, - 0.49645838141441345, - 0.3055652379989624, - 0.3895750939846039, - 0.5219303369522095, - 0.3664180636405945, - 0.453957200050354, - 0.5753984451293945, - 0.001453780336305499, - 0.45908382534980774, - 1.2539762258529663, - 0.6490684747695923, - 0.6853195428848267, - 0.0011842504609376192, - 0.6820011734962463, - 0.42553478479385376, - 0.259000688791275 - ], - "step_times_ms": [ - 47513.93520901911, - 26899.73210898461, - 41262.48180796392, - 66495.43262599036, - 10969.204296008684, - 60708.51903402945, - 19134.767919022124, - 41297.174014966, - 61718.76015001908, - 46218.60432100948, - 63510.61685796594, - 10268.670362012926, - 43201.109810965136, - 22460.022343031596, - 21824.53149399953, - 27588.505985040683, - 44275.010473967995, - 60585.87563998299, - 60958.746705029625, - 60960.08875203552, - 20987.195259018335, - 13986.805958964396, - 60834.94512201287, - 27714.821267989464, - 16654.144487984013, - 23337.049510038923, - 29055.362954968587, - 28389.59298102418, - 43584.85947694862, - 60590.078279026784 - ], - "peak_memory_gb": 10.659695148468018, - "logs_path": "logs/grpo_fi_false_30.json" -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_unsloth_fi_false_10.json b/scripts/benchmarks/results/stats/grpo_unsloth_fi_false_10.json deleted file mode 100644 index c777419a15..0000000000 --- a/scripts/benchmarks/results/stats/grpo_unsloth_fi_false_10.json +++ /dev/null @@ -1,362 +0,0 @@ -[ - { - "step": 1, - "loss": 0.0, - "grad_norm": 0.0, - "learning_rate": 0.0, - "num_tokens": 3693.0, - "completions/mean_length": 811.25, - "completions/min_length": 779.0, - "completions/max_length": 856.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 811.25, - "completions/min_terminated_length": 779.0, - "completions/max_terminated_length": 856.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.5, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 811.25, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 7.868439688409789e-05, - "time_ms": 77897.29859499494, - "memory_mb": 9442.14013671875, - "memory_gb": 9.220839977264404 - }, - { - "step": 2, - "loss": -0.0893, - "grad_norm": 0.6125104427337646, - "learning_rate": 5e-06, - "num_tokens": 6238.0, - "completions/mean_length": 547.25, - "completions/min_length": 487.0, - "completions/max_length": 645.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 547.25, - "completions/min_terminated_length": 487.0, - "completions/max_terminated_length": 645.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -6.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 547.25, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00015736879376819577, - "time_ms": 21634.983669035137, - "memory_mb": 9076.26025390625, - "memory_gb": 8.863535404205322 - }, - { - "step": 3, - "loss": -0.1386, - "grad_norm": 0.5993297696113586, - "learning_rate": 4.444444444444444e-06, - "num_tokens": 10165.0, - "completions/mean_length": 804.75, - "completions/min_length": 605.0, - "completions/max_length": 1214.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 804.75, - "completions/min_terminated_length": 605.0, - "completions/max_terminated_length": 1214.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 2.598076105117798, - "rewards/check_answer/mean": -1.25, - "rewards/check_answer/std": 1.8484227657318115, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -2.5, - "reward_std": 6.0, - "frac_reward_zero_std": 0.0, - "completion_length": 804.75, - "kl": 0.008573448285460472, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00023605319065229366, - "time_ms": 40298.14357904252, - "memory_mb": 9952.80322265625, - "memory_gb": 9.719534397125244 - }, - { - "step": 4, - "loss": -0.1236, - "grad_norm": 0.5647851228713989, - "learning_rate": 3.88888888888889e-06, - "num_tokens": 13320.0, - "completions/mean_length": 623.75, - "completions/min_length": 421.0, - "completions/max_length": 789.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 623.75, - "completions/min_terminated_length": 421.0, - "completions/max_terminated_length": 789.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -2.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 623.75, - "kl": 0.009312103502452374, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00031473758753639155, - "time_ms": 26193.765547999647, - "memory_mb": 9306.09326171875, - "memory_gb": 9.087981700897217 - }, - { - "step": 5, - "loss": 0.0, - "grad_norm": 0.0010538548231124878, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 14970.0, - "completions/mean_length": 256.5, - "completions/min_length": 246.0, - "completions/max_length": 260.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 256.5, - "completions/min_terminated_length": 246.0, - "completions/max_terminated_length": 260.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.5, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 256.5, - "kl": 0.002130241831764579, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00039342198442048943, - "time_ms": 9324.433026020415, - "memory_mb": 8777.982421875, - "memory_gb": 8.572248458862305 - }, - { - "step": 6, - "loss": 0.0, - "grad_norm": 0.00012166703527327627, - "learning_rate": 2.7777777777777783e-06, - "num_tokens": 21841.0, - "completions/mean_length": 1620.75, - "completions/min_length": 1214.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.5, - "completions/mean_terminated_length": 1395.5, - "completions/min_terminated_length": 1214.0, - "completions/max_terminated_length": 1577.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 1620.75, - "kl": 0.0007094849133864045, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0004721063813045873, - "time_ms": 61652.94101298787, - "memory_mb": 10914.11279296875, - "memory_gb": 10.658313274383545 - }, - { - "step": 7, - "loss": -0.0097, - "grad_norm": 0.9194015860557556, - "learning_rate": 2.222222222222222e-06, - "num_tokens": 24587.0, - "completions/mean_length": 543.5, - "completions/min_length": 511.0, - "completions/max_length": 562.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 543.5, - "completions/min_terminated_length": 511.0, - "completions/max_terminated_length": 562.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.875, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -5.5, - "reward_std": 4.0, - "frac_reward_zero_std": 0.0, - "completion_length": 543.5, - "kl": 0.005215016193687916, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0005507907781886852, - "time_ms": 18906.7719859886, - "memory_mb": 8996.00390625, - "memory_gb": 8.785160064697266 - }, - { - "step": 8, - "loss": 0.0338, - "grad_norm": 0.5346357822418213, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 27519.0, - "completions/mean_length": 666.0, - "completions/min_length": 615.0, - "completions/max_length": 714.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 666.0, - "completions/min_terminated_length": 615.0, - "completions/max_terminated_length": 714.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.0, - "rewards/check_numbers/std": 3.0, - "reward": -5.25, - "reward_std": 4.5, - "frac_reward_zero_std": 0.0, - "completion_length": 666.0, - "kl": 0.0001442090724594891, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0006294751750727831, - "time_ms": 23948.13355000224, - "memory_mb": 9202.39306640625, - "memory_gb": 8.986711978912354 - }, - { - "step": 9, - "loss": 0.0, - "grad_norm": 0.0033828848972916603, - "learning_rate": 1.111111111111111e-06, - "num_tokens": 29207.0, - "completions/mean_length": 325.0, - "completions/min_length": 310.0, - "completions/max_length": 334.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 325.0, - "completions/min_terminated_length": 310.0, - "completions/max_terminated_length": 334.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.5, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 325.0, - "kl": 0.010901343077421188, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007081595719568809, - "time_ms": 11388.401818985585, - "memory_mb": 8705.7236328125, - "memory_gb": 8.501683235168457 - }, - { - "step": 10, - "loss": 0.2036, - "grad_norm": 0.22472381591796875, - "learning_rate": 5.555555555555555e-07, - "num_tokens": 34891.0, - "completions/mean_length": 1253.0, - "completions/min_length": 1044.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 1055.3333740234375, - "completions/min_terminated_length": 1044.0, - "completions/max_terminated_length": 1067.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 2.1213202476501465, - "rewards/check_answer/mean": -2.25, - "rewards/check_answer/std": 0.28867512941360474, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -2.5, - "reward_std": 3.8297085762023926, - "frac_reward_zero_std": 0.0, - "completion_length": 1253.0, - "kl": 0.00215436820872128, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007868439688409789, - "time_ms": 61737.33338096645, - "memory_mb": 10919.5498046875, - "memory_gb": 10.663622856140137 - } -] \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_unsloth_fi_false_10.summary.json b/scripts/benchmarks/results/stats/grpo_unsloth_fi_false_10.summary.json deleted file mode 100644 index aba12f1486..0000000000 --- a/scripts/benchmarks/results/stats/grpo_unsloth_fi_false_10.summary.json +++ /dev/null @@ -1,75 +0,0 @@ -{ - "backend": "unsloth_fi_false", - "max_steps": 10, - "train_wall_s": 355.41431403998286, - "median_step_ms_post_warmup": 23948.13355000224, - "n_logged_steps": 10, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - }, - "losses": [ - 0.0, - -0.0893, - -0.1386, - -0.1236, - 0.0, - 0.0, - -0.0097, - 0.0338, - 0.0, - 0.2036 - ], - "rewards": [ - 0.5, - -6.5, - -2.5, - -2.5, - 0.5, - -7.5, - -5.5, - -5.25, - 0.5, - -2.5 - ], - "kls": [ - 0.0, - 0.0, - 0.008573448285460472, - 0.009312103502452374, - 0.002130241831764579, - 0.0007094849133864045, - 0.005215016193687916, - 0.0001442090724594891, - 0.010901343077421188, - 0.00215436820872128 - ], - "grad_norms": [ - 0.0, - 0.6125104427337646, - 0.5993297696113586, - 0.5647851228713989, - 0.0010538548231124878, - 0.00012166703527327627, - 0.9194015860557556, - 0.5346357822418213, - 0.0033828848972916603, - 0.22472381591796875 - ], - "step_times_ms": [ - 77897.29859499494, - 21634.983669035137, - 40298.14357904252, - 26193.765547999647, - 9324.433026020415, - 61652.94101298787, - 18906.7719859886, - 23948.13355000224, - 11388.401818985585, - 61737.33338096645 - ], - "peak_memory_gb": 10.663622856140137, - "logs_path": "logs/grpo_unsloth_fi_false_10.json" -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_vllm_10.json b/scripts/benchmarks/results/stats/grpo_vllm_10.json deleted file mode 100644 index 0b7390a1b4..0000000000 --- a/scripts/benchmarks/results/stats/grpo_vllm_10.json +++ /dev/null @@ -1,362 +0,0 @@ -[ - { - "step": 1, - "loss": 0.0305, - "grad_norm": 0.4133029878139496, - "learning_rate": 0.0, - "num_tokens": 3705.0, - "completions/mean_length": 814.25, - "completions/min_length": 781.0, - "completions/max_length": 864.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 814.25, - "completions/min_terminated_length": 781.0, - "completions/max_terminated_length": 864.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -3.0, - "rewards/check_answer/std": 1.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.0, - "reward_std": 1.0, - "frac_reward_zero_std": 0.0, - "completion_length": 814.25, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 7.868439688409789e-05, - "time_ms": 17984.56621397054, - "memory_mb": 161170.2099609375, - "memory_gb": 157.39278316497803 - }, - { - "step": 2, - "loss": -0.1941, - "grad_norm": 0.8333088159561157, - "learning_rate": 5e-06, - "num_tokens": 7167.0, - "completions/mean_length": 776.5, - "completions/min_length": 525.0, - "completions/max_length": 1078.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 776.5, - "completions/min_terminated_length": 525.0, - "completions/max_terminated_length": 1078.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -2.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 776.5, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00015736879376819577, - "time_ms": 6704.717919987161, - "memory_mb": 161638.7705078125, - "memory_gb": 157.85036182403564 - }, - { - "step": 3, - "loss": 0.2632, - "grad_norm": 0.4677680730819702, - "learning_rate": 4.444444444444444e-06, - "num_tokens": 11596.0, - "completions/mean_length": 930.25, - "completions/min_length": 445.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 625.0, - "completions/min_terminated_length": 445.0, - "completions/max_terminated_length": 863.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 2.598076105117798, - "rewards/check_answer/mean": -2.75, - "rewards/check_answer/std": 1.190238118171692, - "rewards/check_numbers/mean": -1.625, - "rewards/check_numbers/std": 1.1814539432525635, - "reward": -3.625, - "reward_std": 4.479118347167969, - "frac_reward_zero_std": 0.0, - "completion_length": 930.25, - "kl": 0.011923530139029026, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00023605319065229366, - "time_ms": 12108.133931003977, - "memory_mb": 162822.73876953125, - "memory_gb": 159.00658082962036 - }, - { - "step": 4, - "loss": -0.2013, - "grad_norm": 0.5163940191268921, - "learning_rate": 3.88888888888889e-06, - "num_tokens": 14365.0, - "completions/mean_length": 527.25, - "completions/min_length": 315.0, - "completions/max_length": 598.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 527.25, - "completions/min_terminated_length": 315.0, - "completions/max_terminated_length": 598.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -3.0, - "rewards/check_answer/std": 1.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.0, - "reward_std": 1.0, - "frac_reward_zero_std": 0.0, - "completion_length": 527.25, - "kl": 0.004221913404762745, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00031473758753639155, - "time_ms": 4019.3081409670413, - "memory_mb": 160943.57275390625, - "memory_gb": 157.17145776748657 - }, - { - "step": 5, - "loss": 0.2093, - "grad_norm": 1.160618782043457, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 16176.0, - "completions/mean_length": 296.75, - "completions/min_length": 246.0, - "completions/max_length": 421.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 296.75, - "completions/min_terminated_length": 246.0, - "completions/max_terminated_length": 421.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -3.0, - "rewards/check_answer/std": 1.0, - "rewards/check_numbers/mean": -1.125, - "rewards/check_numbers/std": 0.75, - "reward": 0.375, - "reward_std": 0.25, - "frac_reward_zero_std": 0.0, - "completion_length": 296.75, - "kl": 0.003692739875987172, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00039342198442048943, - "time_ms": 3241.851194994524, - "memory_mb": 160665.36376953125, - "memory_gb": 156.89976930618286 - }, - { - "step": 6, - "loss": 0.0, - "grad_norm": 0.0007444396032951772, - "learning_rate": 2.7777777777777783e-06, - "num_tokens": 23948.0, - "completions/mean_length": 1846.0, - "completions/min_length": 1846.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 1.0, - "completions/mean_terminated_length": 0.0, - "completions/min_terminated_length": 0.0, - "completions/max_terminated_length": 0.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 1846.0, - "kl": 0.0025038770399987698, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0004721063813045873, - "time_ms": 10860.668059962336, - "memory_mb": 162817.607421875, - "memory_gb": 159.0015697479248 - }, - { - "step": 7, - "loss": 0.0371, - "grad_norm": 2.262518882751465, - "learning_rate": 2.222222222222222e-06, - "num_tokens": 26728.0, - "completions/mean_length": 552.0, - "completions/min_length": 506.0, - "completions/max_length": 627.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 552.0, - "completions/min_terminated_length": 506.0, - "completions/max_terminated_length": 627.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -1.5, - "rewards/check_answer/std": 2.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 1.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 552.0, - "kl": 0.006138760130852461, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0005507907781886852, - "time_ms": 4138.088690000586, - "memory_mb": 160989.1611328125, - "memory_gb": 157.2159776687622 - }, - { - "step": 8, - "loss": 0.0, - "grad_norm": 0.001562082557938993, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 29420.0, - "completions/mean_length": 606.0, - "completions/min_length": 560.0, - "completions/max_length": 636.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 606.0, - "completions/min_terminated_length": 560.0, - "completions/max_terminated_length": 636.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 606.0, - "kl": 0.004652692936360836, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0006294751750727831, - "time_ms": 4177.52773797838, - "memory_mb": 160996.86376953125, - "memory_gb": 157.22349977493286 - }, - { - "step": 9, - "loss": 0.0, - "grad_norm": 0.00027447607135400176, - "learning_rate": 1.111111111111111e-06, - "num_tokens": 31353.0, - "completions/mean_length": 386.25, - "completions/min_length": 334.0, - "completions/max_length": 464.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 386.25, - "completions/min_terminated_length": 334.0, - "completions/max_terminated_length": 464.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.5, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 386.25, - "kl": 0.0017617446137592196, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007081595719568809, - "time_ms": 3263.2006779895164, - "memory_mb": 160745.5380859375, - "memory_gb": 156.97806453704834 - }, - { - "step": 10, - "loss": 0.2052, - "grad_norm": 0.4320540428161621, - "learning_rate": 5.555555555555555e-07, - "num_tokens": 35257.0, - "completions/mean_length": 808.0, - "completions/min_length": 650.0, - "completions/max_length": 1119.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 808.0, - "completions/min_terminated_length": 650.0, - "completions/max_terminated_length": 1119.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 2.1213202476501465, - "rewards/check_answer/mean": -3.25, - "rewards/check_answer/std": 1.4433757066726685, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -3.5, - "reward_std": 2.8284270763397217, - "frac_reward_zero_std": 0.0, - "completion_length": 808.0, - "kl": 0.001998987514525652, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007868439688409789, - "time_ms": 6874.866564990953, - "memory_mb": 161736.77734375, - "memory_gb": 157.94607162475586 - } -] \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_vllm_10.summary.json b/scripts/benchmarks/results/stats/grpo_vllm_10.summary.json deleted file mode 100644 index e827daa75b..0000000000 --- a/scripts/benchmarks/results/stats/grpo_vllm_10.summary.json +++ /dev/null @@ -1,75 +0,0 @@ -{ - "backend": "vllm", - "max_steps": 10, - "train_wall_s": 74.41919421299826, - "median_step_ms_post_warmup": 4138.088690000586, - "n_logged_steps": 10, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - }, - "losses": [ - 0.0305, - -0.1941, - 0.2632, - -0.2013, - 0.2093, - 0.0, - 0.0371, - 0.0, - 0.0, - 0.2052 - ], - "rewards": [ - 0.0, - -2.5, - -3.625, - 0.0, - 0.375, - -7.5, - 1.5, - -7.5, - 0.5, - -3.5 - ], - "kls": [ - 0.0, - 0.0, - 0.011923530139029026, - 0.004221913404762745, - 0.003692739875987172, - 0.0025038770399987698, - 0.006138760130852461, - 0.004652692936360836, - 0.0017617446137592196, - 0.001998987514525652 - ], - "grad_norms": [ - 0.4133029878139496, - 0.8333088159561157, - 0.4677680730819702, - 0.5163940191268921, - 1.160618782043457, - 0.0007444396032951772, - 2.262518882751465, - 0.001562082557938993, - 0.00027447607135400176, - 0.4320540428161621 - ], - "step_times_ms": [ - 17984.56621397054, - 6704.717919987161, - 12108.133931003977, - 4019.3081409670413, - 3241.851194994524, - 10860.668059962336, - 4138.088690000586, - 4177.52773797838, - 3263.2006779895164, - 6874.866564990953 - ], - "peak_memory_gb": 157.94607162475586, - "logs_path": "logs/grpo_vllm_10.json" -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_vllm_30.json b/scripts/benchmarks/results/stats/grpo_vllm_30.json deleted file mode 100644 index d43f2ab1ee..0000000000 --- a/scripts/benchmarks/results/stats/grpo_vllm_30.json +++ /dev/null @@ -1,1082 +0,0 @@ -[ - { - "step": 1, - "loss": 0.0305, - "grad_norm": 0.41349539160728455, - "learning_rate": 0.0, - "num_tokens": 3705.0, - "completions/mean_length": 814.25, - "completions/min_length": 781.0, - "completions/max_length": 864.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 814.25, - "completions/min_terminated_length": 781.0, - "completions/max_terminated_length": 864.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -3.0, - "rewards/check_answer/std": 1.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.0, - "reward_std": 1.0, - "frac_reward_zero_std": 0.0, - "completion_length": 814.25, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 7.868439688409789e-05, - "time_ms": 17866.63037497783, - "memory_mb": 161170.2099609375, - "memory_gb": 157.39278316497803 - }, - { - "step": 2, - "loss": -0.1941, - "grad_norm": 0.8339279294013977, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 7167.0, - "completions/mean_length": 776.5, - "completions/min_length": 525.0, - "completions/max_length": 1078.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 776.5, - "completions/min_terminated_length": 525.0, - "completions/max_terminated_length": 1078.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -2.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 776.5, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00015736879376819577, - "time_ms": 6304.458727012388, - "memory_mb": 161638.7705078125, - "memory_gb": 157.85036182403564 - }, - { - "step": 3, - "loss": 0.2006, - "grad_norm": 0.6402159929275513, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 9959.0, - "completions/mean_length": 521.0, - "completions/min_length": 445.0, - "completions/max_length": 730.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 521.0, - "completions/min_terminated_length": 445.0, - "completions/max_terminated_length": 730.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -3.0, - "rewards/check_answer/std": 1.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.0, - "reward_std": 1.0, - "frac_reward_zero_std": 0.0, - "completion_length": 521.0, - "kl": 0.0024282929953187704, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00023605319065229366, - "time_ms": 4510.530841012951, - "memory_mb": 161131.90673828125, - "memory_gb": 157.35537767410278 - }, - { - "step": 4, - "loss": 0.2437, - "grad_norm": 0.2846885919570923, - "learning_rate": 5e-06, - "num_tokens": 15286.0, - "completions/mean_length": 1166.75, - "completions/min_length": 598.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 940.3333740234375, - "completions/min_terminated_length": 598.0, - "completions/max_terminated_length": 1266.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -6.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 1166.75, - "kl": 0.005713047459721565, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00031473758753639155, - "time_ms": 11239.92098000599, - "memory_mb": 162822.2685546875, - "memory_gb": 159.006121635437 - }, - { - "step": 5, - "loss": 0.0, - "grad_norm": 0.00401803245767951, - "learning_rate": 4.814814814814815e-06, - "num_tokens": 17067.0, - "completions/mean_length": 289.25, - "completions/min_length": 246.0, - "completions/max_length": 391.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 289.25, - "completions/min_terminated_length": 246.0, - "completions/max_terminated_length": 391.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.5, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": 0.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 289.25, - "kl": 0.011252232827246189, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00039342198442048943, - "time_ms": 2776.7173860338517, - "memory_mb": 160628.82666015625, - "memory_gb": 156.86408853530884 - }, - { - "step": 6, - "loss": 0.0, - "grad_norm": 0.00014282428310252726, - "learning_rate": 4.62962962962963e-06, - "num_tokens": 23546.0, - "completions/mean_length": 1522.75, - "completions/min_length": 1208.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 1415.0, - "completions/min_terminated_length": 1208.0, - "completions/max_terminated_length": 1822.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 1522.75, - "kl": 0.0008392990566790104, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0004721063813045873, - "time_ms": 10157.209870987572, - "memory_mb": 162817.607421875, - "memory_gb": 159.0015697479248 - }, - { - "step": 7, - "loss": 0.0, - "grad_norm": 0.0015061397571116686, - "learning_rate": 4.444444444444444e-06, - "num_tokens": 26672.0, - "completions/mean_length": 638.5, - "completions/min_length": 513.0, - "completions/max_length": 749.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 638.5, - "completions/min_terminated_length": 513.0, - "completions/max_terminated_length": 749.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 638.5, - "kl": 0.0047083343379199505, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0005507907781886852, - "time_ms": 4554.909924976528, - "memory_mb": 161159.95166015625, - "memory_gb": 157.38276529312134 - }, - { - "step": 8, - "loss": 0.2403, - "grad_norm": 0.44619685411453247, - "learning_rate": 4.2592592592592596e-06, - "num_tokens": 30793.0, - "completions/mean_length": 963.25, - "completions/min_length": 615.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 669.0, - "completions/min_terminated_length": 615.0, - "completions/max_terminated_length": 714.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -1.5, - "rewards/match_format_approximately/std": 1.7320507764816284, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -5.5, - "reward_std": 2.309401035308838, - "frac_reward_zero_std": 0.0, - "completion_length": 963.25, - "kl": 0.004438905976712704, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0006294751750727831, - "time_ms": 10537.410682998598, - "memory_mb": 162816.43310546875, - "memory_gb": 159.00042295455933 - }, - { - "step": 9, - "loss": 0.0251, - "grad_norm": 0.7223323583602905, - "learning_rate": 4.074074074074074e-06, - "num_tokens": 32595.0, - "completions/mean_length": 353.5, - "completions/min_length": 327.0, - "completions/max_length": 380.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 353.5, - "completions/min_terminated_length": 327.0, - "completions/max_terminated_length": 380.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -0.375, - "rewards/match_format_approximately/std": 1.8874585628509521, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -3.5, - "reward_std": 3.265986442565918, - "frac_reward_zero_std": 0.0, - "completion_length": 353.5, - "kl": 0.002922436688095331, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007081595719568809, - "time_ms": 2670.8698750007898, - "memory_mb": 160619.87939453125, - "memory_gb": 156.85535097122192 - }, - { - "step": 10, - "loss": 0.0, - "grad_norm": 0.0002955764648504555, - "learning_rate": 3.88888888888889e-06, - "num_tokens": 37082.0, - "completions/mean_length": 953.75, - "completions/min_length": 894.0, - "completions/max_length": 1133.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 953.75, - "completions/min_terminated_length": 894.0, - "completions/max_terminated_length": 1133.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 953.75, - "kl": 0.001744209323078394, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007868439688409789, - "time_ms": 6595.109536021482, - "memory_mb": 161739.52294921875, - "memory_gb": 157.94875288009644 - }, - { - "step": 11, - "loss": 0.0, - "grad_norm": 0.0008108518086373806, - "learning_rate": 3.7037037037037037e-06, - "num_tokens": 42411.0, - "completions/mean_length": 1220.25, - "completions/min_length": 402.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.5, - "completions/mean_terminated_length": 594.5, - "completions/min_terminated_length": 402.0, - "completions/max_terminated_length": 787.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 1220.25, - "kl": 0.002685483079403639, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0008655283657250767, - "time_ms": 10160.135700018145, - "memory_mb": 162818.43603515625, - "memory_gb": 159.00237894058228 - }, - { - "step": 12, - "loss": 0.331, - "grad_norm": 0.9407532215118408, - "learning_rate": 3.5185185185185187e-06, - "num_tokens": 44358.0, - "completions/mean_length": 357.75, - "completions/min_length": 212.0, - "completions/max_length": 537.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 357.75, - "completions/min_terminated_length": 212.0, - "completions/max_terminated_length": 537.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -1.5, - "rewards/match_format_approximately/std": 1.7320507764816284, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -5.5, - "reward_std": 2.309401035308838, - "frac_reward_zero_std": 0.0, - "completion_length": 357.75, - "kl": 0.007562238723039627, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0009442127626091746, - "time_ms": 3498.259258980397, - "memory_mb": 160852.2197265625, - "memory_gb": 157.0822458267212 - }, - { - "step": 13, - "loss": 0.0298, - "grad_norm": 0.6642693281173706, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 46878.0, - "completions/mean_length": 487.0, - "completions/min_length": 450.0, - "completions/max_length": 521.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 487.0, - "completions/min_terminated_length": 450.0, - "completions/max_terminated_length": 521.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -6.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 487.0, - "kl": 0.01840771734714508, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0010228971594932726, - "time_ms": 3411.464748030994, - "memory_mb": 160815.06787109375, - "memory_gb": 157.045964717865 - }, - { - "step": 14, - "loss": 0.1561, - "grad_norm": 0.5970175266265869, - "learning_rate": 3.1481481481481483e-06, - "num_tokens": 49277.0, - "completions/mean_length": 481.75, - "completions/min_length": 314.0, - "completions/max_length": 636.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 481.75, - "completions/min_terminated_length": 314.0, - "completions/max_terminated_length": 636.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.75, - "rewards/match_format_approximately/std": 0.8660253882408142, - "rewards/check_answer/mean": -0.375, - "rewards/check_answer/std": 3.5910770893096924, - "rewards/check_numbers/mean": 1.0, - "rewards/check_numbers/std": 2.886751413345337, - "reward": 2.875, - "reward_std": 7.087254047393799, - "frac_reward_zero_std": 0.0, - "completion_length": 481.75, - "kl": 0.00663342559710145, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0011015815563773703, - "time_ms": 3980.731577030383, - "memory_mb": 160999.58642578125, - "memory_gb": 157.226158618927 - }, - { - "step": 15, - "loss": 0.4028, - "grad_norm": 0.2463085651397705, - "learning_rate": 2.962962962962963e-06, - "num_tokens": 54006.0, - "completions/mean_length": 1024.25, - "completions/min_length": 576.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 750.3333740234375, - "completions/min_terminated_length": 576.0, - "completions/max_terminated_length": 1006.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": 1.375, - "rewards/check_answer/std": 4.190763473510742, - "rewards/check_numbers/mean": 0.75, - "rewards/check_numbers/std": 3.2015621662139893, - "reward": 4.75, - "reward_std": 10.070584297180176, - "frac_reward_zero_std": 0.0, - "completion_length": 1024.25, - "kl": 0.004423078149557114, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0011802659532614682, - "time_ms": 10481.332287017722, - "memory_mb": 162821.994140625, - "memory_gb": 159.0058536529541 - }, - { - "step": 16, - "loss": 0.0184, - "grad_norm": 0.4361814856529236, - "learning_rate": 2.7777777777777783e-06, - "num_tokens": 57142.0, - "completions/mean_length": 625.0, - "completions/min_length": 523.0, - "completions/max_length": 847.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 625.0, - "completions/min_terminated_length": 523.0, - "completions/max_terminated_length": 847.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -0.25, - "rewards/check_answer/std": 3.5, - "rewards/check_numbers/mean": -0.25, - "rewards/check_numbers/std": 2.5, - "reward": 0.625, - "reward_std": 8.25, - "frac_reward_zero_std": 0.0, - "completion_length": 625.0, - "kl": 0.004664436914026737, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0012589503501455662, - "time_ms": 5105.93488701852, - "memory_mb": 161322.53271484375, - "memory_gb": 157.5415358543396 - }, - { - "step": 17, - "loss": 0.1807, - "grad_norm": 0.25606873631477356, - "learning_rate": 2.5925925925925925e-06, - "num_tokens": 64007.0, - "completions/mean_length": 1527.25, - "completions/min_length": 1190.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.5, - "completions/mean_terminated_length": 1208.5, - "completions/min_terminated_length": 1190.0, - "completions/max_terminated_length": 1227.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 2.598076105117798, - "rewards/check_answer/mean": 1.5, - "rewards/check_answer/std": 4.041451930999756, - "rewards/check_numbers/mean": 0.5, - "rewards/check_numbers/std": 3.464101552963257, - "reward": 2.75, - "reward_std": 11.83568000793457, - "frac_reward_zero_std": 0.0, - "completion_length": 1527.25, - "kl": 0.002878781408071518, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.001337634747029664, - "time_ms": 10356.32998100482, - "memory_mb": 162823.20751953125, - "memory_gb": 159.00703859329224 - }, - { - "step": 18, - "loss": 0.2383, - "grad_norm": 0.38782942295074463, - "learning_rate": 2.4074074074074075e-06, - "num_tokens": 68993.0, - "completions/mean_length": 1103.5, - "completions/min_length": 669.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 856.0, - "completions/min_terminated_length": 669.0, - "completions/max_terminated_length": 987.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -0.375, - "rewards/match_format_approximately/std": 1.8874585628509521, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -3.5, - "reward_std": 3.265986442565918, - "frac_reward_zero_std": 0.0, - "completion_length": 1103.5, - "kl": 0.00984956230968237, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0014163191439137619, - "time_ms": 10494.073983980343, - "memory_mb": 162820.2548828125, - "memory_gb": 159.00415515899658 - }, - { - "step": 19, - "loss": 0.8338, - "grad_norm": 0.2885834872722626, - "learning_rate": 2.222222222222222e-06, - "num_tokens": 72545.0, - "completions/mean_length": 692.0, - "completions/min_length": 280.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 307.3333435058594, - "completions/min_terminated_length": 280.0, - "completions/max_terminated_length": 359.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -0.625, - "rewards/check_numbers/std": 1.25, - "reward": -3.375, - "reward_std": 2.75, - "frac_reward_zero_std": 0.0, - "completion_length": 692.0, - "kl": 0.0006688942667096853, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0014950035407978598, - "time_ms": 10833.778033033013, - "memory_mb": 162823.48193359375, - "memory_gb": 159.00730657577515 - }, - { - "step": 20, - "loss": 0.0, - "grad_norm": 0.0024749308358877897, - "learning_rate": 2.037037037037037e-06, - "num_tokens": 74488.0, - "completions/mean_length": 387.75, - "completions/min_length": 311.0, - "completions/max_length": 467.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 387.75, - "completions/min_terminated_length": 311.0, - "completions/max_terminated_length": 467.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 0.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -3.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 387.75, - "kl": 0.013835551217198372, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0015736879376819577, - "time_ms": 3094.477139005903, - "memory_mb": 160741.390625, - "memory_gb": 156.97401428222656 - }, - { - "step": 21, - "loss": -0.0037, - "grad_norm": 0.6102232336997986, - "learning_rate": 1.8518518518518519e-06, - "num_tokens": 77105.0, - "completions/mean_length": 568.25, - "completions/min_length": 530.0, - "completions/max_length": 617.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 568.25, - "completions/min_terminated_length": 530.0, - "completions/max_terminated_length": 617.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.75, - "rewards/match_format_approximately/std": 0.8660253882408142, - "rewards/check_answer/mean": 1.5, - "rewards/check_answer/std": 4.041451930999756, - "rewards/check_numbers/mean": 2.25, - "rewards/check_numbers/std": 2.5, - "reward": 6.0, - "reward_std": 8.336666107177734, - "frac_reward_zero_std": 0.0, - "completion_length": 568.25, - "kl": 0.0076245637610554695, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0016523723345660555, - "time_ms": 3840.9026580047794, - "memory_mb": 160956.8515625, - "memory_gb": 157.1844253540039 - }, - { - "step": 22, - "loss": 0.0379, - "grad_norm": 0.8350751996040344, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 79148.0, - "completions/mean_length": 398.75, - "completions/min_length": 352.0, - "completions/max_length": 429.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 398.75, - "completions/min_terminated_length": 352.0, - "completions/max_terminated_length": 429.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": 1.5, - "rewards/check_answer/std": 4.0, - "rewards/check_numbers/mean": 2.25, - "rewards/check_numbers/std": 2.5, - "reward": 8.25, - "reward_std": 6.5, - "frac_reward_zero_std": 0.0, - "completion_length": 398.75, - "kl": 0.011878136545419693, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0017310567314501534, - "time_ms": 2903.038158954587, - "memory_mb": 160683.75, - "memory_gb": 156.917724609375 - }, - { - "step": 23, - "loss": 0.3886, - "grad_norm": 0.28949517011642456, - "learning_rate": 1.4814814814814815e-06, - "num_tokens": 83401.0, - "completions/mean_length": 945.25, - "completions/min_length": 472.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 645.0, - "completions/min_terminated_length": 472.0, - "completions/max_terminated_length": 898.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -1.375, - "rewards/check_answer/std": 1.9311050176620483, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -0.5, - "reward_std": 5.0332231521606445, - "frac_reward_zero_std": 0.0, - "completion_length": 945.25, - "kl": 0.010346058756113052, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0018097411283342513, - "time_ms": 10495.372234028764, - "memory_mb": 162818.78857421875, - "memory_gb": 159.0027232170105 - }, - { - "step": 24, - "loss": 0.1431, - "grad_norm": 0.5029579401016235, - "learning_rate": 1.2962962962962962e-06, - "num_tokens": 87768.0, - "completions/mean_length": 921.75, - "completions/min_length": 524.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 613.6666870117188, - "completions/min_terminated_length": 524.0, - "completions/max_terminated_length": 659.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.875, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -1.125, - "rewards/check_answer/std": 1.75, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -4.5, - "reward_std": 6.0, - "frac_reward_zero_std": 0.0, - "completion_length": 921.75, - "kl": 0.009395054541528225, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0018884255252183493, - "time_ms": 10606.634334020782, - "memory_mb": 162822.4638671875, - "memory_gb": 159.0063123703003 - }, - { - "step": 25, - "loss": 0.1063, - "grad_norm": 0.3104912340641022, - "learning_rate": 1.111111111111111e-06, - "num_tokens": 90028.0, - "completions/mean_length": 489.0, - "completions/min_length": 385.0, - "completions/max_length": 531.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 489.0, - "completions/min_terminated_length": 385.0, - "completions/max_terminated_length": 531.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -0.625, - "rewards/check_answer/std": 3.75, - "rewards/check_numbers/mean": -0.25, - "rewards/check_numbers/std": 2.5, - "reward": 3.625, - "reward_std": 6.25, - "frac_reward_zero_std": 0.0, - "completion_length": 489.0, - "kl": 0.0016164245316758752, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0019671099221024472, - "time_ms": 3563.0593819660135, - "memory_mb": 160835.37353515625, - "memory_gb": 157.06579446792603 - }, - { - "step": 26, - "loss": -0.0821, - "grad_norm": 0.4499339461326599, - "learning_rate": 9.259259259259259e-07, - "num_tokens": 92568.0, - "completions/mean_length": 521.0, - "completions/min_length": 410.0, - "completions/max_length": 671.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 521.0, - "completions/min_terminated_length": 410.0, - "completions/max_terminated_length": 671.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -1.0, - "rewards/check_answer/std": 2.0, - "rewards/check_numbers/mean": 0.125, - "rewards/check_numbers/std": 2.3584952354431152, - "reward": 0.25, - "reward_std": 3.796928644180298, - "frac_reward_zero_std": 0.0, - "completion_length": 521.0, - "kl": 0.005659917835146189, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.002045794318986545, - "time_ms": 4147.492960037198, - "memory_mb": 161050.13818359375, - "memory_gb": 157.27552556991577 - }, - { - "step": 27, - "loss": 0.0, - "grad_norm": 7.777348946547136e-05, - "learning_rate": 7.407407407407407e-07, - "num_tokens": 96438.0, - "completions/mean_length": 823.5, - "completions/min_length": 807.0, - "completions/max_length": 873.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 823.5, - "completions/min_terminated_length": 807.0, - "completions/max_terminated_length": 873.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 823.5, - "kl": 7.657324022147804e-05, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0021244787158706427, - "time_ms": 5140.9110790118575, - "memory_mb": 161351.87939453125, - "memory_gb": 157.57019472122192 - }, - { - "step": 28, - "loss": 0.0, - "grad_norm": 0.00013634964125230908, - "learning_rate": 5.555555555555555e-07, - "num_tokens": 102122.0, - "completions/mean_length": 1277.0, - "completions/min_length": 690.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.5, - "completions/mean_terminated_length": 708.0, - "completions/min_terminated_length": 690.0, - "completions/max_terminated_length": 726.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 1277.0, - "kl": 0.001502353698015213, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0022031631127547406, - "time_ms": 10219.65475397883, - "memory_mb": 162820.3134765625, - "memory_gb": 159.00421237945557 - }, - { - "step": 29, - "loss": 0.0181, - "grad_norm": 0.419629842042923, - "learning_rate": 3.7037037037037036e-07, - "num_tokens": 106026.0, - "completions/mean_length": 780.0, - "completions/min_length": 730.0, - "completions/max_length": 808.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 780.0, - "completions/min_terminated_length": 730.0, - "completions/max_terminated_length": 808.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 1.125, - "rewards/match_format_approximately/std": 0.75, - "rewards/check_answer/mean": -2.875, - "rewards/check_answer/std": 1.1086779832839966, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -1.0, - "reward_std": 1.9148542881011963, - "frac_reward_zero_std": 0.0, - "completion_length": 780.0, - "kl": 0.009886534884572029, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0022818475096388386, - "time_ms": 4818.701309966855, - "memory_mb": 161265.3359375, - "memory_gb": 157.48567962646484 - }, - { - "step": 30, - "loss": 0.2357, - "grad_norm": 0.22457966208457947, - "learning_rate": 1.8518518518518518e-07, - "num_tokens": 111428.0, - "completions/mean_length": 1254.5, - "completions/min_length": 634.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 1057.3333740234375, - "completions/min_terminated_length": 634.0, - "completions/max_terminated_length": 1269.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": 2.0, - "rewards/check_numbers/std": 3.0, - "reward": -0.75, - "reward_std": 4.5, - "frac_reward_zero_std": 0.0, - "completion_length": 1254.5, - "kl": 0.0031997335609048605, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0023605319065229365, - "time_ms": 10382.734156039078, - "memory_mb": 162817.5673828125, - "memory_gb": 159.00153064727783 - } -] \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/grpo_vllm_30.summary.json b/scripts/benchmarks/results/stats/grpo_vllm_30.summary.json deleted file mode 100644 index 88b38a2839..0000000000 --- a/scripts/benchmarks/results/stats/grpo_vllm_30.summary.json +++ /dev/null @@ -1,175 +0,0 @@ -{ - "backend": "vllm", - "max_steps": 30, - "train_wall_s": 215.93619061401114, - "median_step_ms_post_warmup": 5140.9110790118575, - "n_logged_steps": 30, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - }, - "losses": [ - 0.0305, - -0.1941, - 0.2006, - 0.2437, - 0.0, - 0.0, - 0.0, - 0.2403, - 0.0251, - 0.0, - 0.0, - 0.331, - 0.0298, - 0.1561, - 0.4028, - 0.0184, - 0.1807, - 0.2383, - 0.8338, - 0.0, - -0.0037, - 0.0379, - 0.3886, - 0.1431, - 0.1063, - -0.0821, - 0.0, - 0.0, - 0.0181, - 0.2357 - ], - "rewards": [ - 0.0, - -2.5, - 0.0, - -6.5, - 0.5, - -7.5, - -7.5, - -5.5, - -3.5, - -7.5, - -7.5, - -5.5, - -6.5, - 2.875, - 4.75, - 0.625, - 2.75, - -3.5, - -3.375, - -3.5, - 6.0, - 8.25, - -0.5, - -4.5, - 3.625, - 0.25, - -7.5, - -7.5, - -1.0, - -0.75 - ], - "kls": [ - 0.0, - 0.0, - 0.0024282929953187704, - 0.005713047459721565, - 0.011252232827246189, - 0.0008392990566790104, - 0.0047083343379199505, - 0.004438905976712704, - 0.002922436688095331, - 0.001744209323078394, - 0.002685483079403639, - 0.007562238723039627, - 0.01840771734714508, - 0.00663342559710145, - 0.004423078149557114, - 0.004664436914026737, - 0.002878781408071518, - 0.00984956230968237, - 0.0006688942667096853, - 0.013835551217198372, - 0.0076245637610554695, - 0.011878136545419693, - 0.010346058756113052, - 0.009395054541528225, - 0.0016164245316758752, - 0.005659917835146189, - 7.657324022147804e-05, - 0.001502353698015213, - 0.009886534884572029, - 0.0031997335609048605 - ], - "grad_norms": [ - 0.41349539160728455, - 0.8339279294013977, - 0.6402159929275513, - 0.2846885919570923, - 0.00401803245767951, - 0.00014282428310252726, - 0.0015061397571116686, - 0.44619685411453247, - 0.7223323583602905, - 0.0002955764648504555, - 0.0008108518086373806, - 0.9407532215118408, - 0.6642693281173706, - 0.5970175266265869, - 0.2463085651397705, - 0.4361814856529236, - 0.25606873631477356, - 0.38782942295074463, - 0.2885834872722626, - 0.0024749308358877897, - 0.6102232336997986, - 0.8350751996040344, - 0.28949517011642456, - 0.5029579401016235, - 0.3104912340641022, - 0.4499339461326599, - 7.777348946547136e-05, - 0.00013634964125230908, - 0.419629842042923, - 0.22457966208457947 - ], - "step_times_ms": [ - 17866.63037497783, - 6304.458727012388, - 4510.530841012951, - 11239.92098000599, - 2776.7173860338517, - 10157.209870987572, - 4554.909924976528, - 10537.410682998598, - 2670.8698750007898, - 6595.109536021482, - 10160.135700018145, - 3498.259258980397, - 3411.464748030994, - 3980.731577030383, - 10481.332287017722, - 5105.93488701852, - 10356.32998100482, - 10494.073983980343, - 10833.778033033013, - 3094.477139005903, - 3840.9026580047794, - 2903.038158954587, - 10495.372234028764, - 10606.634334020782, - 3563.0593819660135, - 4147.492960037198, - 5140.9110790118575, - 10219.65475397883, - 4818.701309966855, - 10382.734156039078 - ], - "peak_memory_gb": 159.00153064727783, - "logs_path": "logs/grpo_vllm_30.json" -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/lora_cb_paged_fa4_gen.json b/scripts/benchmarks/results/stats/lora_cb_paged_fa4_gen.json deleted file mode 100644 index 6034e8755b..0000000000 --- a/scripts/benchmarks/results/stats/lora_cb_paged_fa4_gen.json +++ /dev/null @@ -1,29 +0,0 @@ -{ - "backend": "tpaged", - "lora_adapter": "outputs/lora_rank32_fresh", - "attn_impl": "paged_attention", - "persistent_cb": true, - "n_prompts": 32, - "n_prompt_tokens": 4847, - "n_decoded_tokens": 14750, - "wall_times_s": [ - 34.991439365025144, - 33.211731680028606 - ], - "median_wall_s": 34.991439365025144, - "prompt_tps": 138.5195947339252, - "decode_tps": 421.53167367967745, - "max_new_tokens": 512, - "sample_completions": [ - "First, we can factor the quadratic expression $n^2-3n+2$ as $(n-1)(n-2)$. For this expression to be a prime number, one of the factors must be equal to 1 and the other factor must be a prime number. \n", - "First, we need to determine how many $4 \\times 5$ rectangles can fit into a $20 \\times 24$ rectangle. To do this, we divide the dimensions of the larger rectangle by the dimensions of the smaller rect", - " \nTo find the area of the smaller square, we need to determine its side length. Let's denote the side length of the smaller square as \\( s \\).\n\nFrom the diagram, we can see that the larger square has " - ], - "peak_memory_gb": 103.81339406967163, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/lora_cb_sdpa_paged_gen.json b/scripts/benchmarks/results/stats/lora_cb_sdpa_paged_gen.json deleted file mode 100644 index 0da44b9423..0000000000 --- a/scripts/benchmarks/results/stats/lora_cb_sdpa_paged_gen.json +++ /dev/null @@ -1,29 +0,0 @@ -{ - "backend": "tpaged", - "lora_adapter": "outputs/lora_rank32_fresh", - "attn_impl": "sdpa_paged", - "persistent_cb": true, - "n_prompts": 32, - "n_prompt_tokens": 4847, - "n_decoded_tokens": 14785, - "wall_times_s": [ - 33.532237556006294, - 34.068173120962456 - ], - "median_wall_s": 34.068173120962456, - "prompt_tps": 142.27355199793783, - "decode_tps": 433.9827658942667, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to understand the structure of a cube. A cube has 12 edges and 8 vertices. Each vertex is connected to 3 edges. \n\nNow, let's consider the pairs of parallel edges. Since a cube has 12 ed", - "First, we need to determine how many $4 \\times 5$ rectangles can fit into a $20 \\times 24$ rectangle. We can do this by dividing the dimensions of the larger rectangle by the dimensions of the smaller", - "First, let's count the total number of letters in the word \"FLUFFY\". There are 6 letters in total.\n\nNext, we need to determine how many of these letters are repeated. In this case, the letter \"F\" appe" - ], - "peak_memory_gb": 111.93839406967163, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/lora_unsloth_fi_false_gen.json b/scripts/benchmarks/results/stats/lora_unsloth_fi_false_gen.json deleted file mode 100644 index 0e6f58a400..0000000000 --- a/scripts/benchmarks/results/stats/lora_unsloth_fi_false_gen.json +++ /dev/null @@ -1,27 +0,0 @@ -{ - "backend": "unsloth_fi_false", - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 32, - "n_prompt_tokens": 4847, - "n_decoded_tokens": 16384, - "wall_times_s": [ - 25.54396249598358, - 25.480999241000973 - ], - "median_wall_s": 25.54396249598358, - "prompt_tps": 189.75129644674828, - "decode_tps": 641.4040109311994, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$. We can use the Pythagorean theore", - "Let $Q(x) = P(x) - x^{2023}P(1-\\frac{1}{x})$. Then $Q(k) = 0$ for every positive integer $1 \\leq k \\leq 2023$. Since $P(x)$ is a monic polynomial of degree $2023$, $Q(x)$ is also a monic polynomial of", - " To solve this problem, we need to determine the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n" - ], - "peak_memory_gb": 15.8363037109375, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/lora_vllm_gen.json b/scripts/benchmarks/results/stats/lora_vllm_gen.json deleted file mode 100644 index f2b9b3fa86..0000000000 --- a/scripts/benchmarks/results/stats/lora_vllm_gen.json +++ /dev/null @@ -1,27 +0,0 @@ -{ - "backend": "vllm", - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 32, - "n_prompt_tokens": 4847, - "n_decoded_tokens": 15140, - "wall_times_s": [ - 3.304712440993171, - 3.2573561430326663 - ], - "median_wall_s": 3.304712440993171, - "prompt_tps": 1466.6934223612275, - "decode_tps": 4581.336582329066, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$. We can use the Pythagorean theore", - "Let $Q(x) = P(x) - x^{2023}P(1-\\frac{1}{x})$. Then $Q(k) = 0$ for every positive integer $1 \\leq k \\leq 2023$. Since $P(x)$ is a monic polynomial of degree $2023$, $Q(x)$ is also a monic polynomial of", - " To solve this problem, we need to find the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirs" - ], - "peak_memory_gb": 156.21798133850098, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/notebook_ref_10.json b/scripts/benchmarks/results/stats/notebook_ref_10.json deleted file mode 100644 index 3adee77566..0000000000 --- a/scripts/benchmarks/results/stats/notebook_ref_10.json +++ /dev/null @@ -1,362 +0,0 @@ -[ - { - "step": 1, - "loss": 0.2423, - "grad_norm": 0.24541568756103516, - "learning_rate": 0.0, - "num_tokens": 5422.0, - "completions/mean_length": 1243.5, - "completions/min_length": 1019.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 1042.666748046875, - "completions/min_terminated_length": 1019.0, - "completions/max_terminated_length": 1089.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.75, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.375, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -0.875, - "reward_std": 2.75, - "frac_reward_zero_std": 0.0, - "completion_length": 1243.5, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 7.868439688409789e-05, - "time_ms": 60626.65366800502, - "memory_mb": 162696.66357421875, - "memory_gb": 158.883460521698 - }, - { - "step": 2, - "loss": 0.1559, - "grad_norm": 0.7674608826637268, - "learning_rate": 5e-06, - "num_tokens": 7690.0, - "completions/mean_length": 478.0, - "completions/min_length": 329.0, - "completions/max_length": 553.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 478.0, - "completions/min_terminated_length": 329.0, - "completions/max_terminated_length": 553.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -1.875, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -5.5, - "reward_std": 4.0, - "frac_reward_zero_std": 0.0, - "completion_length": 478.0, - "kl": 0.0, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00015736879376819577, - "time_ms": 3893.7715340289287, - "memory_mb": 160786.34130859375, - "memory_gb": 157.01791143417358 - }, - { - "step": 3, - "loss": -0.165, - "grad_norm": 0.47987309098243713, - "learning_rate": 4.444444444444444e-06, - "num_tokens": 12437.0, - "completions/mean_length": 1009.75, - "completions/min_length": 745.0, - "completions/max_length": 1319.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 1009.75, - "completions/min_terminated_length": 745.0, - "completions/max_terminated_length": 1319.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -1.375, - "rewards/check_answer/std": 1.9311050176620483, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -0.5, - "reward_std": 5.0332231521606445, - "frac_reward_zero_std": 0.0, - "completion_length": 1009.75, - "kl": 0.0038291513919830322, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00023605319065229366, - "time_ms": 7929.127738985699, - "memory_mb": 161959.54833984375, - "memory_gb": 158.16362142562866 - }, - { - "step": 4, - "loss": 0.3177, - "grad_norm": 0.37925368547439575, - "learning_rate": 3.88888888888889e-06, - "num_tokens": 17403.0, - "completions/mean_length": 1076.5, - "completions/min_length": 546.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.25, - "completions/mean_terminated_length": 820.0, - "completions/min_terminated_length": 546.0, - "completions/max_terminated_length": 1192.0, - "rewards/match_format_exactly/mean": 0.75, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": -0.75, - "rewards/match_format_approximately/std": 1.9364917278289795, - "rewards/check_answer/mean": -2.125, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -2.0, - "rewards/check_numbers/std": 0.5773502588272095, - "reward": -4.125, - "reward_std": 3.4970226287841797, - "frac_reward_zero_std": 0.0, - "completion_length": 1076.5, - "kl": 0.005913741886615753, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00031473758753639155, - "time_ms": 11084.477900003549, - "memory_mb": 162749.5458984375, - "memory_gb": 158.93510341644287 - }, - { - "step": 5, - "loss": -0.02, - "grad_norm": 0.6089861989021301, - "learning_rate": 3.3333333333333333e-06, - "num_tokens": 19235.0, - "completions/mean_length": 302.0, - "completions/min_length": 256.0, - "completions/max_length": 334.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 302.0, - "completions/min_terminated_length": 256.0, - "completions/max_terminated_length": 334.0, - "rewards/match_format_exactly/mean": 3.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": 1.5, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -1.125, - "rewards/check_answer/std": 4.190763473510742, - "rewards/check_numbers/mean": -0.25, - "rewards/check_numbers/std": 2.5, - "reward": 3.125, - "reward_std": 6.650501251220703, - "frac_reward_zero_std": 0.0, - "completion_length": 302.0, - "kl": 0.015983864665031433, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.00039342198442048943, - "time_ms": 2679.084858042188, - "memory_mb": 160465.05859375, - "memory_gb": 156.70415878295898 - }, - { - "step": 6, - "loss": 0.0, - "grad_norm": 0.002889552852138877, - "learning_rate": 2.7777777777777783e-06, - "num_tokens": 26958.0, - "completions/mean_length": 1833.75, - "completions/min_length": 1797.0, - "completions/max_length": 1846.0, - "completions/clipped_ratio": 0.75, - "completions/mean_terminated_length": 1797.0, - "completions/min_terminated_length": 1797.0, - "completions/max_terminated_length": 1797.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 1833.75, - "kl": 0.003961368463933468, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0004721063813045873, - "time_ms": 10652.5042289868, - "memory_mb": 162744.833984375, - "memory_gb": 158.9305019378662 - }, - { - "step": 7, - "loss": 0.0, - "grad_norm": 0.003148352960124612, - "learning_rate": 2.222222222222222e-06, - "num_tokens": 29616.0, - "completions/mean_length": 521.5, - "completions/min_length": 452.0, - "completions/max_length": 675.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 521.5, - "completions/min_terminated_length": 452.0, - "completions/max_terminated_length": 675.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -3.0, - "rewards/match_format_approximately/std": 0.0, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.5, - "rewards/check_numbers/std": 0.0, - "reward": -7.5, - "reward_std": 0.0, - "frac_reward_zero_std": 1.0, - "completion_length": 521.5, - "kl": 0.009647021070122719, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0005507907781886852, - "time_ms": 4468.553012993652, - "memory_mb": 160983.70361328125, - "memory_gb": 157.21064805984497 - }, - { - "step": 8, - "loss": 0.0613, - "grad_norm": 0.4861072301864624, - "learning_rate": 1.6666666666666667e-06, - "num_tokens": 32984.0, - "completions/mean_length": 775.0, - "completions/min_length": 671.0, - "completions/max_length": 933.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 775.0, - "completions/min_terminated_length": 671.0, - "completions/max_terminated_length": 933.0, - "rewards/match_format_exactly/mean": 0.0, - "rewards/match_format_exactly/std": 0.0, - "rewards/match_format_approximately/mean": -2.25, - "rewards/match_format_approximately/std": 1.5, - "rewards/check_answer/mean": -2.0, - "rewards/check_answer/std": 0.0, - "rewards/check_numbers/mean": -2.25, - "rewards/check_numbers/std": 0.5, - "reward": -6.5, - "reward_std": 2.0, - "frac_reward_zero_std": 0.0, - "completion_length": 775.0, - "kl": 0.003189136739820242, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0006294751750727831, - "time_ms": 5805.1959190052, - "memory_mb": 161361.3447265625, - "memory_gb": 157.5794382095337 - }, - { - "step": 9, - "loss": 0.006, - "grad_norm": 0.5726504921913147, - "learning_rate": 1.111111111111111e-06, - "num_tokens": 35116.0, - "completions/mean_length": 436.0, - "completions/min_length": 237.0, - "completions/max_length": 635.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 436.0, - "completions/min_terminated_length": 237.0, - "completions/max_terminated_length": 635.0, - "rewards/match_format_exactly/mean": 1.5, - "rewards/match_format_exactly/std": 1.7320507764816284, - "rewards/match_format_approximately/mean": 0.75, - "rewards/match_format_approximately/std": 0.8660253882408142, - "rewards/check_answer/mean": -1.25, - "rewards/check_answer/std": 1.8484227657318115, - "rewards/check_numbers/mean": -1.5, - "rewards/check_numbers/std": 0.0, - "reward": -0.5, - "reward_std": 3.8297085762023926, - "frac_reward_zero_std": 0.0, - "completion_length": 436.0, - "kl": 0.0023976736702024937, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007081595719568809, - "time_ms": 4304.089896031655, - "memory_mb": 160920.1044921875, - "memory_gb": 157.14853954315186 - }, - { - "step": 10, - "loss": 0.1582, - "grad_norm": 0.3651980459690094, - "learning_rate": 5.555555555555555e-07, - "num_tokens": 39155.0, - "completions/mean_length": 841.75, - "completions/min_length": 729.0, - "completions/max_length": 1108.0, - "completions/clipped_ratio": 0.0, - "completions/mean_terminated_length": 841.75, - "completions/min_terminated_length": 729.0, - "completions/max_terminated_length": 1108.0, - "rewards/match_format_exactly/mean": 2.25, - "rewards/match_format_exactly/std": 1.5, - "rewards/match_format_approximately/mean": 0.375, - "rewards/match_format_approximately/std": 2.25, - "rewards/check_answer/mean": -2.375, - "rewards/check_answer/std": 0.25, - "rewards/check_numbers/mean": -1.75, - "rewards/check_numbers/std": 0.5, - "reward": -1.5, - "reward_std": 4.0, - "frac_reward_zero_std": 0.0, - "completion_length": 841.75, - "kl": 0.00485160993412137, - "clip_ratio/low_mean": 0.0, - "clip_ratio/low_min": 0.0, - "clip_ratio/high_mean": 0.0, - "clip_ratio/high_max": 0.0, - "clip_ratio/region_mean": 0.0, - "epoch": 0.0007868439688409789, - "time_ms": 6777.490795007907, - "memory_mb": 161641.44970703125, - "memory_gb": 157.8529782295227 - } -] \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/vllm_128x512.json b/scripts/benchmarks/results/stats/vllm_128x512.json deleted file mode 100644 index a3ee1d9e0c..0000000000 --- a/scripts/benchmarks/results/stats/vllm_128x512.json +++ /dev/null @@ -1,28 +0,0 @@ -{ - "backend": "vllm", - "lora_adapter": null, - "n_prompts": 128, - "n_prompt_tokens": 18551, - "n_decoded_tokens": 60123, - "wall_times_s": [ - 4.089218033012003, - 4.009195051970892, - 3.9967994149774313 - ], - "median_wall_s": 4.009195051970892, - "prompt_tps": 4627.1133630379145, - "decode_tps": 14996.277113143688, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$. We can use the Pythagorean theore", - " \nTo solve this problem, we need to analyze the given conditions and derive the form of the polynomial \\( P(x) \\). The key condition is that \\( P(k) = k^{2023} P\\left(1 - \\frac{1}{k}\\right) \\) for eve", - " To solve this problem, we need to find the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirs" - ], - "peak_memory_gb": 156.63964891433716, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/vllm_16.json b/scripts/benchmarks/results/stats/vllm_16.json deleted file mode 100644 index b49b45cf58..0000000000 --- a/scripts/benchmarks/results/stats/vllm_16.json +++ /dev/null @@ -1,28 +0,0 @@ -{ - "backend": "vllm", - "lora_adapter": null, - "n_prompts": 16, - "n_prompt_tokens": 2061, - "n_decoded_tokens": 7259, - "wall_times_s": [ - 1.9610779809881933, - 1.9720804590033367, - 1.962739369017072 - ], - "median_wall_s": 1.962739369017072, - "prompt_tps": 1050.0630050703758, - "decode_tps": 3698.4024035933326, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$. We can use the Pythagorean theore", - " \nTo solve this problem, we need to analyze the given conditions and derive the form of the polynomial \\( P(x) \\). The key condition is that \\( P(k) = k^{2023} P\\left(1 - \\frac{1}{k}\\right) \\) for eve", - " To solve this problem, we need to find the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirs" - ], - "peak_memory_gb": 156.21798133850098, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/vllm_256x512.json b/scripts/benchmarks/results/stats/vllm_256x512.json deleted file mode 100644 index 8fca1ac6d9..0000000000 --- a/scripts/benchmarks/results/stats/vllm_256x512.json +++ /dev/null @@ -1,28 +0,0 @@ -{ - "backend": "vllm", - "lora_adapter": null, - "n_prompts": 256, - "n_prompt_tokens": 36963, - "n_decoded_tokens": 120774, - "wall_times_s": [ - 5.908074813021813, - 5.705008256016299, - 5.693635127041489 - ], - "median_wall_s": 5.705008256016299, - "prompt_tps": 6479.044085697884, - "decode_tps": 21169.82037188746, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$. We can use the Pythagorean theore", - " \nTo solve this problem, we need to analyze the given conditions and derive the form of the polynomial \\( P(x) \\). The key condition is that \\( P(k) = k^{2023} P\\left(1 - \\frac{1}{k}\\right) \\) for eve", - " To solve this problem, we need to find the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirs" - ], - "peak_memory_gb": 157.12996101379395, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/vllm_32.json b/scripts/benchmarks/results/stats/vllm_32.json deleted file mode 100644 index 8ac29f2b4c..0000000000 --- a/scripts/benchmarks/results/stats/vllm_32.json +++ /dev/null @@ -1,28 +0,0 @@ -{ - "backend": "vllm", - "lora_adapter": null, - "n_prompts": 32, - "n_prompt_tokens": 4847, - "n_decoded_tokens": 15097, - "wall_times_s": [ - 2.422758528031409, - 2.3895113189937547, - 2.388265542977024 - ], - "median_wall_s": 2.3895113189937547, - "prompt_tps": 2028.4482276656954, - "decode_tps": 6318.028242844854, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$. We can use the Pythagorean theore", - " \nTo solve this problem, we need to analyze the given conditions and derive the form of the polynomial \\( P(x) \\). The key condition is that \\( P(k) = k^{2023} P\\left(1 - \\frac{1}{k}\\right) \\) for eve", - " To solve this problem, we need to find the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirs" - ], - "peak_memory_gb": 156.21798133850098, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/vllm_64.json b/scripts/benchmarks/results/stats/vllm_64.json deleted file mode 100644 index a13dbf7f69..0000000000 --- a/scripts/benchmarks/results/stats/vllm_64.json +++ /dev/null @@ -1,28 +0,0 @@ -{ - "backend": "vllm", - "lora_adapter": null, - "n_prompts": 64, - "n_prompt_tokens": 9129, - "n_decoded_tokens": 30300, - "wall_times_s": [ - 2.916221586987376, - 2.8970531829982065, - 2.8907751629594713 - ], - "median_wall_s": 2.8970531829982065, - "prompt_tps": 3151.13303876329, - "decode_tps": 10458.9036120635, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$. We can use the Pythagorean theore", - " \nTo solve this problem, we need to analyze the given conditions and derive the form of the polynomial \\( P(x) \\). The key condition is that \\( P(k) = k^{2023} P\\left(1 - \\frac{1}{k}\\right) \\) for eve", - " To solve this problem, we need to find the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirs" - ], - "peak_memory_gb": 156.2349009513855, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/vllm_64x512_lora.json b/scripts/benchmarks/results/stats/vllm_64x512_lora.json deleted file mode 100644 index 47065a7751..0000000000 --- a/scripts/benchmarks/results/stats/vllm_64x512_lora.json +++ /dev/null @@ -1,28 +0,0 @@ -{ - "backend": "vllm", - "lora_adapter": "outputs/lora_rank32_fresh", - "n_prompts": 64, - "n_prompt_tokens": 9129, - "n_decoded_tokens": 30163, - "wall_times_s": [ - 3.911774954001885, - 3.8794285799958743, - 3.8696357629960403 - ], - "median_wall_s": 3.8794285799958743, - "prompt_tps": 2353.181612125389, - "decode_tps": 7775.114138080634, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$. We can use the Pythagorean theore", - "Let $Q(x) = P(x) - x^{2023}P(1-\\frac{1}{x})$. Then $Q(k) = 0$ for every positive integer $1 \\leq k \\leq 2023$. Since $P(x)$ is a monic polynomial of degree $2023$, $Q(x)$ is also a monic polynomial of", - " To solve this problem, we need to find the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirs" - ], - "peak_memory_gb": 156.2349009513855, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file diff --git a/scripts/benchmarks/results/stats/vllm_8.json b/scripts/benchmarks/results/stats/vllm_8.json deleted file mode 100644 index 4148a8bf95..0000000000 --- a/scripts/benchmarks/results/stats/vllm_8.json +++ /dev/null @@ -1,28 +0,0 @@ -{ - "backend": "vllm", - "lora_adapter": null, - "n_prompts": 8, - "n_prompt_tokens": 1009, - "n_decoded_tokens": 3961, - "wall_times_s": [ - 2.087421328993514, - 2.0852316500386223, - 2.084826519014314 - ], - "median_wall_s": 2.0852316500386223, - "prompt_tps": 483.87909323230895, - "decode_tps": 1899.5491459793616, - "max_new_tokens": 512, - "sample_completions": [ - "First, we need to find the length of the legs of the trapezoid. Since the trapezoid is isosceles, the legs are equal in length. Let's call the length of each leg $x$.\n\nWe can use the Pythagorean theor", - " \nTo solve this problem, we need to analyze the given conditions and derive the form of the polynomial \\( P(x) \\). Let's start by examining the functional equation provided:\n\n\\[ P(k) = k^{2023} P\\left", - " To solve this problem, we need to find the maximum value of \\(a\\) such that the line \\(y = mx + 2\\) does not pass through any lattice points for \\(0 < x \\leq 100\\) when \\(\\frac{1}{2} < m < a\\).\n\nFirs" - ], - "peak_memory_gb": 156.21798133850098, - "sampling": { - "temperature": 0.1, - "top_p": 0.97, - "min_p": 0.5, - "top_k": 5 - } -} \ No newline at end of file