Add files using upload-large-folder tool

Power_Area_SFT/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e279f9267e26b459d91a6eafa29d2e4de3ce28ed682edd36e8f053ce7c475393
+size 83945296

Power_Area_SFT/checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d2a2034ebb05cb71c510897f2795b31164e50f17b270bc25d2be3ad9a17b22
+size 15984

Power_Area_SFT/checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060dfdb1c49102cbdc8868a6031e68787601b4ccd782f3fb9b137e20c1fd2c7a
+size 15984

Power_Area_SFT/checkpoint-100/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af01895cb66e616591f2e4baa8dcd8151530eab133c73571ccb31c74f35422ce
+size 15984

Power_Area_SFT/checkpoint-100/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677921992b1e0cef3aee776f245975003d22f51d9bd6ed20f248ded1deb72fa9
+size 15984

Power_Area_SFT/checkpoint-100/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69353c629541c690c5471f8ec05fdab2bfecf3d37afaa436bc45939da6db68f
+size 15984

Power_Area_SFT/checkpoint-100/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e40ba6668cc03c9162c68a933d164bf38ae2d196a9a6fec03ae615491201185
+size 15984

Power_Area_SFT/checkpoint-100/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870968fea834e24b2e099cf3e4fe1e3fb8caf38d8f8e5b790d7d47386d4d05f5
+size 15984

Power_Area_SFT/checkpoint-100/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e19618bee7c6ef43256fea25abe19bca88535eb1e7dc213cde8929ae4e8180
+size 15984

Power_Area_SFT/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f649359458cb157292d9a86520c59e16f4c3ef05dbb0c452b05d500dad26a76
+size 1064

Power_Area_SFT/checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

Power_Area_SFT/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd1c55d539ebcc8ff062a4ab8fef57d8c1444eb8abb545d69197bfbf2d86131
+size 5368

Power_Area_SFT/checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b26915ef0cdd9ee619a166d4c264827ad8c04a8a72d9c019e98e1baef65df14
+size 168149074

Power_Area_SFT/checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d7e02ffb4d440dce7ab4ce0b5617578ec9ce3672acee7434ed6f1153f1ae0c
+size 15984

Power_Area_SFT/checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b40ca759e432b2688f021b81291d74a40f56a205e9842119f7e772275eebd3
+size 15984

Power_Area_SFT/checkpoint-200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdaef955ddd36d6bc1c40584113dd6205483e2aa85b02439b8b27e82e02a8359
+size 15984

Power_Area_SFT/checkpoint-200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b14ae5db356e6512538751d6b386c190754e307cc99cd652d5c6dd891e1f82
+size 15984

Power_Area_SFT/checkpoint-200/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26e28be26826eeeed244b77185c67b443ac185175f8d4bf5ba94caa8b271bc5
+size 15984

Power_Area_SFT/checkpoint-200/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847cedc1d6ca26f299a132c2ade9754887374acb9d98f26594a85d4c7742d474
+size 15984

Power_Area_SFT/checkpoint-200/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd043d1690ae0ff6991b03322799a0b28f021427b15fd9f1e5ed8b9905d9307
+size 15984

Power_Area_SFT/checkpoint-200/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772190f7e6667c865d25fc72da7bdd1b5d39f46fe03bb5c2d754aee1ad3c99c7
+size 15984

Power_Area_SFT/checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91779d753597df7ad790f335f05cf7bab32a28e97a578a59e5c83fea8efecb66
+size 1064

Power_Area_SFT/checkpoint-200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

Power_Area_SFT/checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd1c55d539ebcc8ff062a4ab8fef57d8c1444eb8abb545d69197bfbf2d86131
+size 5368

Power_Area_SFT/checkpoint-300/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4c26c615bd5830d41566fab54dc69174be292761b34514b27fbe82b45b630b
+size 15984

Power_Area_SFT/checkpoint-300/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c761d7f9b90c29c2d348a1133fd39be52c65e6bee4c2d179f6a6e564eb3a40
+size 15984

Power_Area_SFT/checkpoint-300/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccab847cc956e055fd3f9dcce06898826d065211e945b83576c8d487f87c5469
+size 15984

Power_Area_SFT/checkpoint-300/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5f1dbdcf6ec820c22fd1e4258fcd7af2a2bce65c480988d3f111aa574c9c06
+size 15984

Power_Area_SFT/checkpoint-300/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a23184c3e806d2649776427d1da2c0c9137f9b23a84468f3bdd5bbc75f696c9
+size 15984

Power_Area_SFT/checkpoint-300/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382fc01b809542bf6f5e26742e3e19e80a1f189ac5de24cf8cd822e303916b83
+size 15984

Power_Area_SFT/checkpoint-300/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b178265c7d2ae07bff10b7312e5e49b9f5b4914c38969d2f64a6ca006296bca
+size 15984

Power_Area_SFT/checkpoint-300/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668825a859126c4cf32afb883895c91004130b6aee02178736ca2840e5429ad0
+size 15984

Power_Area_SFT/checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b47f004eb04e7696b54e7cc0fbeb90f37c253591ea075c818122b3642c678b6
+size 1064

Power_Area_SFT/checkpoint-300/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

Power_Area_SFT/checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd1c55d539ebcc8ff062a4ab8fef57d8c1444eb8abb545d69197bfbf2d86131
+size 5368

Power_Area_SFT/checkpoint-400/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

Power_Area_SFT/checkpoint-400/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7891ffa7c7dae99113aa986d67278b52b8c57db55001dc3547a61f24569a34ee
+size 15984

Power_Area_SFT/checkpoint-400/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b92875cb04deec367605433847d1bda444b178b643d2da7ed9aaf738d232b4
+size 15984

Power_Area_SFT/checkpoint-400/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f5f3338a05e325b5408a1cd0b6f5e5b10fad05fe479d63f44bec4cf18107d6
+size 15984

Power_Area_SFT/checkpoint-400/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be749fea477a3867d44010631937e0d8f071ca5f9614f9795c92c7fa68833a6
+size 15984

Power_Area_SFT/checkpoint-400/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc4a5ea4532c621f4c8e9891117b2e597a7f005001e8b4f2a1b4da8c82bf964
+size 15984

Power_Area_SFT/checkpoint-400/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480f9fe7dd71b54d915b46162e34b780ba2467d5542115cc809dbca60b394c0e
+size 15984

Power_Area_SFT/checkpoint-400/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11d982dcd813e82c2d97a5491ce9624cff2dd22e8655ea617ccef1fc1474470
+size 15984

Power_Area_SFT/checkpoint-400/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73494fac3a001cba7cedd097b97f028d4c1d136ee6709214b0a7fe305e5b9089
+size 15984

Power_Area_SFT/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b06b3faa61578a09d2f6b68679e7fd51d8d191703edc2524c8658dd1149ada0
+size 1064

Power_Area_SFT/checkpoint-400/special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[PAD]"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Power_Area_SFT/checkpoint-400/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

Power_Area_SFT/checkpoint-400/trainer_state.json

@@ -0,0 +1,633 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.50210970464135,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33755274261603374,
+      "grad_norm": 4.021343231201172,
+      "learning_rate": 8.620689655172415e-07,
+      "logits/chosen": -2.3571667671203613,
+      "logits/rejected": -2.3413684368133545,
+      "logps/chosen": -66.12004852294922,
+      "logps/rejected": -75.67423248291016,
+      "loss": 0.6916,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 0.002384235616773367,
+      "rewards/margins": 0.0006812589708715677,
+      "rewards/rejected": 0.00170297606382519,
+      "step": 10
+    },
+    {
+      "epoch": 0.6751054852320675,
+      "grad_norm": 4.169963359832764,
+      "learning_rate": 1.724137931034483e-06,
+      "logits/chosen": -2.2970731258392334,
+      "logits/rejected": -2.3126332759857178,
+      "logps/chosen": -75.44676208496094,
+      "logps/rejected": -91.96070861816406,
+      "loss": 0.695,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.004610966891050339,
+      "rewards/margins": -0.0035776779986917973,
+      "rewards/rejected": -0.0010332881938666105,
+      "step": 20
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "grad_norm": 3.956296682357788,
+      "learning_rate": 2.5862068965517246e-06,
+      "logits/chosen": -2.323883056640625,
+      "logits/rejected": -2.360252857208252,
+      "logps/chosen": -82.34379577636719,
+      "logps/rejected": -76.72650146484375,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.0038711726665496826,
+      "rewards/margins": -0.002081885002553463,
+      "rewards/rejected": -0.001789287431165576,
+      "step": 30
+    },
+    {
+      "epoch": 1.350210970464135,
+      "grad_norm": 3.930093765258789,
+      "learning_rate": 3.448275862068966e-06,
+      "logits/chosen": -2.3154587745666504,
+      "logits/rejected": -2.3474326133728027,
+      "logps/chosen": -65.43012237548828,
+      "logps/rejected": -73.15928649902344,
+      "loss": 0.691,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.005101156421005726,
+      "rewards/margins": 0.008008326403796673,
+      "rewards/rejected": -0.0029071702156215906,
+      "step": 40
+    },
+    {
+      "epoch": 1.6877637130801688,
+      "grad_norm": 4.285252094268799,
+      "learning_rate": 4.310344827586207e-06,
+      "logits/chosen": -2.3710691928863525,
+      "logits/rejected": -2.371490478515625,
+      "logps/chosen": -71.6757583618164,
+      "logps/rejected": -70.73356628417969,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": 0.0005036738002672791,
+      "rewards/margins": 0.01000114344060421,
+      "rewards/rejected": -0.009497471153736115,
+      "step": 50
+    },
+    {
+      "epoch": 2.0253164556962027,
+      "grad_norm": 4.272525787353516,
+      "learning_rate": 4.999818897894192e-06,
+      "logits/chosen": -2.3313004970550537,
+      "logits/rejected": -2.3659963607788086,
+      "logps/chosen": -76.61670684814453,
+      "logps/rejected": -83.35383605957031,
+      "loss": 0.6826,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.0012120052706450224,
+      "rewards/margins": 0.0215681791305542,
+      "rewards/rejected": -0.020356174558401108,
+      "step": 60
+    },
+    {
+      "epoch": 2.3628691983122363,
+      "grad_norm": 3.9699583053588867,
+      "learning_rate": 4.9934830787948756e-06,
+      "logits/chosen": -2.335836172103882,
+      "logits/rejected": -2.346723794937134,
+      "logps/chosen": -77.20027923583984,
+      "logps/rejected": -76.7348403930664,
+      "loss": 0.668,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.01467165071517229,
+      "rewards/margins": 0.05109705403447151,
+      "rewards/rejected": -0.036425404250621796,
+      "step": 70
+    },
+    {
+      "epoch": 2.70042194092827,
+      "grad_norm": 4.201504230499268,
+      "learning_rate": 4.978118375700895e-06,
+      "logits/chosen": -2.3483119010925293,
+      "logits/rejected": -2.314948320388794,
+      "logps/chosen": -86.64659881591797,
+      "logps/rejected": -73.74983215332031,
+      "loss": 0.6543,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.015483448281884193,
+      "rewards/margins": 0.07252755016088486,
+      "rewards/rejected": -0.057044100016355515,
+      "step": 80
+    },
+    {
+      "epoch": 3.037974683544304,
+      "grad_norm": 4.158086776733398,
+      "learning_rate": 4.953780424089803e-06,
+      "logits/chosen": -2.353440523147583,
+      "logits/rejected": -2.3548269271850586,
+      "logps/chosen": -66.6883773803711,
+      "logps/rejected": -70.85858917236328,
+      "loss": 0.6434,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.027489716187119484,
+      "rewards/margins": 0.11177561432123184,
+      "rewards/rejected": -0.08428589999675751,
+      "step": 90
+    },
+    {
+      "epoch": 3.3755274261603376,
+      "grad_norm": 4.082221031188965,
+      "learning_rate": 4.920557351506409e-06,
+      "logits/chosen": -2.341866970062256,
+      "logits/rejected": -2.364499092102051,
+      "logps/chosen": -129.14761352539062,
+      "logps/rejected": -73.15742492675781,
+      "loss": 0.6058,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.4784974157810211,
+      "rewards/margins": 0.6413174867630005,
+      "rewards/rejected": -0.16281995177268982,
+      "step": 100
+    },
+    {
+      "epoch": 3.7130801687763713,
+      "grad_norm": 4.832098007202148,
+      "learning_rate": 4.878569458453592e-06,
+      "logits/chosen": -2.345391035079956,
+      "logits/rejected": -2.348513603210449,
+      "logps/chosen": -77.12025451660156,
+      "logps/rejected": -87.58562469482422,
+      "loss": 0.583,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.005122403614223003,
+      "rewards/margins": 0.2564489245414734,
+      "rewards/rejected": -0.26157131791114807,
+      "step": 110
+    },
+    {
+      "epoch": 4.050632911392405,
+      "grad_norm": 4.12258243560791,
+      "learning_rate": 4.827968782785062e-06,
+      "logits/chosen": -2.373936176300049,
+      "logits/rejected": -2.4137730598449707,
+      "logps/chosen": -75.44515228271484,
+      "logps/rejected": -93.63223266601562,
+      "loss": 0.5739,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.009799259714782238,
+      "rewards/margins": 0.2614334523677826,
+      "rewards/rejected": -0.2712326943874359,
+      "step": 120
+    },
+    {
+      "epoch": 4.3881856540084385,
+      "grad_norm": 4.568253993988037,
+      "learning_rate": 4.7689385491773934e-06,
+      "logits/chosen": -2.3857738971710205,
+      "logits/rejected": -2.3939366340637207,
+      "logps/chosen": -75.08316802978516,
+      "logps/rejected": -85.54856872558594,
+      "loss": 0.5264,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.057138361036777496,
+      "rewards/margins": 0.4834250807762146,
+      "rewards/rejected": -0.5405634641647339,
+      "step": 130
+    },
+    {
+      "epoch": 4.725738396624473,
+      "grad_norm": 5.059521675109863,
+      "learning_rate": 4.70169250567482e-06,
+      "logits/chosen": -2.403332471847534,
+      "logits/rejected": -2.4016706943511963,
+      "logps/chosen": -77.38340759277344,
+      "logps/rejected": -77.5801010131836,
+      "loss": 0.5097,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.15228016674518585,
+      "rewards/margins": 0.39201101660728455,
+      "rewards/rejected": -0.5442911982536316,
+      "step": 140
+    },
+    {
+      "epoch": 5.063291139240507,
+      "grad_norm": 4.922734260559082,
+      "learning_rate": 4.626474149709127e-06,
+      "logits/chosen": -2.400696039199829,
+      "logits/rejected": -2.3924992084503174,
+      "logps/chosen": -65.39146423339844,
+      "logps/rejected": -72.46720886230469,
+      "loss": 0.5004,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.16622374951839447,
+      "rewards/margins": 0.5306353569030762,
+      "rewards/rejected": -0.6968590617179871,
+      "step": 150
+    },
+    {
+      "epoch": 5.40084388185654,
+      "grad_norm": 4.739672660827637,
+      "learning_rate": 4.54355584639723e-06,
+      "logits/chosen": -2.426323413848877,
+      "logits/rejected": -2.4180703163146973,
+      "logps/chosen": -89.33406066894531,
+      "logps/rejected": -86.6529541015625,
+      "loss": 0.4472,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.2703530192375183,
+      "rewards/margins": 0.723961353302002,
+      "rewards/rejected": -0.9943143725395203,
+      "step": 160
+    },
+    {
+      "epoch": 5.738396624472574,
+      "grad_norm": 5.088452339172363,
+      "learning_rate": 4.45323784230908e-06,
+      "logits/chosen": -2.371295690536499,
+      "logits/rejected": -2.4007980823516846,
+      "logps/chosen": -74.7086410522461,
+      "logps/rejected": -110.96791076660156,
+      "loss": 0.4337,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.19489821791648865,
+      "rewards/margins": 0.838965117931366,
+      "rewards/rejected": -1.0338633060455322,
+      "step": 170
+    },
+    {
+      "epoch": 6.075949367088608,
+      "grad_norm": 4.700001239776611,
+      "learning_rate": 4.355847178277025e-06,
+      "logits/chosen": -2.408874750137329,
+      "logits/rejected": -2.433443546295166,
+      "logps/chosen": -73.986083984375,
+      "logps/rejected": -92.54002380371094,
+      "loss": 0.4201,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.3620097041130066,
+      "rewards/margins": 0.8090314865112305,
+      "rewards/rejected": -1.1710412502288818,
+      "step": 180
+    },
+    {
+      "epoch": 6.413502109704641,
+      "grad_norm": 5.745143890380859,
+      "learning_rate": 4.2517365051833564e-06,
+      "logits/chosen": -2.413661479949951,
+      "logits/rejected": -2.4319045543670654,
+      "logps/chosen": -61.93586349487305,
+      "logps/rejected": -87.93816375732422,
+      "loss": 0.3822,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.3493840992450714,
+      "rewards/margins": 1.0286495685577393,
+      "rewards/rejected": -1.3780337572097778,
+      "step": 190
+    },
+    {
+      "epoch": 6.751054852320675,
+      "grad_norm": 14.167346000671387,
+      "learning_rate": 4.141282807014034e-06,
+      "logits/chosen": -2.376776695251465,
+      "logits/rejected": -2.386939287185669,
+      "logps/chosen": -78.03498840332031,
+      "logps/rejected": -103.80584716796875,
+      "loss": 0.3533,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.5522706508636475,
+      "rewards/margins": 1.1880146265029907,
+      "rewards/rejected": -1.7402851581573486,
+      "step": 200
+    },
+    {
+      "epoch": 7.0886075949367084,
+      "grad_norm": 5.238346576690674,
+      "learning_rate": 4.024886035802432e-06,
+      "logits/chosen": -2.399014711380005,
+      "logits/rejected": -2.4000418186187744,
+      "logps/chosen": -91.64801025390625,
+      "logps/rejected": -88.77143096923828,
+      "loss": 0.3512,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -0.6410180330276489,
+      "rewards/margins": 1.2458090782165527,
+      "rewards/rejected": -1.8868271112442017,
+      "step": 210
+    },
+    {
+      "epoch": 7.4261603375527425,
+      "grad_norm": 4.895415306091309,
+      "learning_rate": 3.9029676634059565e-06,
+      "logits/chosen": -2.38824725151062,
+      "logits/rejected": -2.390937328338623,
+      "logps/chosen": -76.24591064453125,
+      "logps/rejected": -109.47352600097656,
+      "loss": 0.3182,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -0.6207951307296753,
+      "rewards/margins": 1.5345582962036133,
+      "rewards/rejected": -2.155353546142578,
+      "step": 220
+    },
+    {
+      "epoch": 7.763713080168777,
+      "grad_norm": 7.413693904876709,
+      "learning_rate": 3.7759691553595214e-06,
+      "logits/chosen": -2.399376153945923,
+      "logits/rejected": -2.3986117839813232,
+      "logps/chosen": -90.97004699707031,
+      "logps/rejected": -98.67308807373047,
+      "loss": 0.2989,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.7282214760780334,
+      "rewards/margins": 1.5992071628570557,
+      "rewards/rejected": -2.3274283409118652,
+      "step": 230
+    },
+    {
+      "epoch": 8.10126582278481,
+      "grad_norm": 4.8047990798950195,
+      "learning_rate": 3.6443503723320837e-06,
+      "logits/chosen": -2.3746752738952637,
+      "logits/rejected": -2.3904380798339844,
+      "logps/chosen": -81.03557586669922,
+      "logps/rejected": -98.62934112548828,
+      "loss": 0.2891,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.0007418394088745,
+      "rewards/margins": 1.6062211990356445,
+      "rewards/rejected": -2.6069629192352295,
+      "step": 240
+    },
+    {
+      "epoch": 8.438818565400844,
+      "grad_norm": 5.075074672698975,
+      "learning_rate": 3.508587904974522e-06,
+      "logits/chosen": -2.3420817852020264,
+      "logits/rejected": -2.3538601398468018,
+      "logps/chosen": -86.0930404663086,
+      "logps/rejected": -113.33358001708984,
+      "loss": 0.2451,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -0.8170707821846008,
+      "rewards/margins": 1.765887975692749,
+      "rewards/rejected": -2.582958698272705,
+      "step": 250
+    },
+    {
+      "epoch": 8.776371308016877,
+      "grad_norm": 5.683614730834961,
+      "learning_rate": 3.3691733481883693e-06,
+      "logits/chosen": -2.3793487548828125,
+      "logits/rejected": -2.376232862472534,
+      "logps/chosen": -82.44889831542969,
+      "logps/rejected": -100.43474578857422,
+      "loss": 0.2561,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -1.052356481552124,
+      "rewards/margins": 1.7894868850708008,
+      "rewards/rejected": -2.841843605041504,
+      "step": 260
+    },
+    {
+      "epoch": 9.113924050632912,
+      "grad_norm": 5.043191909790039,
+      "learning_rate": 3.226611521064278e-06,
+      "logits/chosen": -2.3715972900390625,
+      "logits/rejected": -2.3901712894439697,
+      "logps/chosen": -78.08219909667969,
+      "logps/rejected": -101.30404663085938,
+      "loss": 0.2135,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -1.124599575996399,
+      "rewards/margins": 1.955810546875,
+      "rewards/rejected": -3.0804100036621094,
+      "step": 270
+    },
+    {
+      "epoch": 9.451476793248945,
+      "grad_norm": 4.911313533782959,
+      "learning_rate": 3.0814186389357765e-06,
+      "logits/chosen": -2.365330696105957,
+      "logits/rejected": -2.3815040588378906,
+      "logps/chosen": -74.75053405761719,
+      "logps/rejected": -96.59932708740234,
+      "loss": 0.2016,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -1.2124760150909424,
+      "rewards/margins": 2.1574602127075195,
+      "rewards/rejected": -3.369936466217041,
+      "step": 280
+    },
+    {
+      "epoch": 9.789029535864978,
+      "grad_norm": 5.809771537780762,
+      "learning_rate": 2.9341204441673267e-06,
+      "logits/chosen": -2.349513292312622,
+      "logits/rejected": -2.362490653991699,
+      "logps/chosen": -82.00188446044922,
+      "logps/rejected": -115.06053161621094,
+      "loss": 0.1873,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -1.5614944696426392,
+      "rewards/margins": 2.464742660522461,
+      "rewards/rejected": -4.0262370109558105,
+      "step": 290
+    },
+    {
+      "epoch": 10.126582278481013,
+      "grad_norm": 5.956116676330566,
+      "learning_rate": 2.785250302445062e-06,
+      "logits/chosen": -2.3490607738494873,
+      "logits/rejected": -2.3738341331481934,
+      "logps/chosen": -96.7169418334961,
+      "logps/rejected": -125.81837463378906,
+      "loss": 0.1794,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -1.4949434995651245,
+      "rewards/margins": 2.48805832862854,
+      "rewards/rejected": -3.983001708984375,
+      "step": 300
+    },
+    {
+      "epoch": 10.464135021097047,
+      "grad_norm": 5.315141201019287,
+      "learning_rate": 2.6353472714635443e-06,
+      "logits/chosen": -2.3448591232299805,
+      "logits/rejected": -2.3330416679382324,
+      "logps/chosen": -77.31942749023438,
+      "logps/rejected": -108.85356140136719,
+      "loss": 0.1444,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -1.4829410314559937,
+      "rewards/margins": 2.6632163524627686,
+      "rewards/rejected": -4.146157264709473,
+      "step": 310
+    },
+    {
+      "epoch": 10.80168776371308,
+      "grad_norm": 5.832997798919678,
+      "learning_rate": 2.4849541490017868e-06,
+      "logits/chosen": -2.3063769340515137,
+      "logits/rejected": -2.31026029586792,
+      "logps/chosen": -89.78933715820312,
+      "logps/rejected": -124.50910949707031,
+      "loss": 0.1507,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -1.8659601211547852,
+      "rewards/margins": 2.7945058345794678,
+      "rewards/rejected": -4.660466194152832,
+      "step": 320
+    },
+    {
+      "epoch": 11.139240506329115,
+      "grad_norm": 5.006984233856201,
+      "learning_rate": 2.3346155074564712e-06,
+      "logits/chosen": -2.3069465160369873,
+      "logits/rejected": -2.3103697299957275,
+      "logps/chosen": -94.30183410644531,
+      "logps/rejected": -111.3757553100586,
+      "loss": 0.1389,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -1.8566234111785889,
+      "rewards/margins": 2.650669574737549,
+      "rewards/rejected": -4.507293701171875,
+      "step": 330
+    },
+    {
+      "epoch": 11.476793248945148,
+      "grad_norm": 5.461178302764893,
+      "learning_rate": 2.184875721949277e-06,
+      "logits/chosen": -2.307982921600342,
+      "logits/rejected": -2.2805938720703125,
+      "logps/chosen": -95.00460815429688,
+      "logps/rejected": -130.14364624023438,
+      "loss": 0.1192,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.095489025115967,
+      "rewards/margins": 3.2359142303466797,
+      "rewards/rejected": -5.331402778625488,
+      "step": 340
+    },
+    {
+      "epoch": 11.814345991561181,
+      "grad_norm": 5.430806636810303,
+      "learning_rate": 2.0362769991485514e-06,
+      "logits/chosen": -2.305732488632202,
+      "logits/rejected": -2.325230360031128,
+      "logps/chosen": -85.6950454711914,
+      "logps/rejected": -129.57199096679688,
+      "loss": 0.1168,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -1.912523865699768,
+      "rewards/margins": 3.0515921115875244,
+      "rewards/rejected": -4.964116096496582,
+      "step": 350
+    },
+    {
+      "epoch": 12.151898734177216,
+      "grad_norm": 4.317180156707764,
+      "learning_rate": 1.8893574139429226e-06,
+      "logits/chosen": -2.29160737991333,
+      "logits/rejected": -2.3020012378692627,
+      "logps/chosen": -88.52080535888672,
+      "logps/rejected": -132.19122314453125,
+      "loss": 0.0974,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -2.399042844772339,
+      "rewards/margins": 3.41259503364563,
+      "rewards/rejected": -5.811637878417969,
+      "step": 360
+    },
+    {
+      "epoch": 12.48945147679325,
+      "grad_norm": 4.4959611892700195,
+      "learning_rate": 1.744648961076068e-06,
+      "logits/chosen": -2.2502753734588623,
+      "logits/rejected": -2.26035737991333,
+      "logps/chosen": -100.68859100341797,
+      "logps/rejected": -137.6667938232422,
+      "loss": 0.084,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -2.559737205505371,
+      "rewards/margins": 3.8113670349121094,
+      "rewards/rejected": -6.3711042404174805,
+      "step": 370
+    },
+    {
+      "epoch": 12.827004219409282,
+      "grad_norm": 5.346553802490234,
+      "learning_rate": 1.602675628797636e-06,
+      "logits/chosen": -2.2998809814453125,
+      "logits/rejected": -2.2750256061553955,
+      "logps/chosen": -100.53385925292969,
+      "logps/rejected": -129.20062255859375,
+      "loss": 0.0921,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -2.7617571353912354,
+      "rewards/margins": 3.2644877433776855,
+      "rewards/rejected": -6.0262451171875,
+      "step": 380
+    },
+    {
+      "epoch": 13.164556962025316,
+      "grad_norm": 4.991717338562012,
+      "learning_rate": 1.4639515015056205e-06,
+      "logits/chosen": -2.249573230743408,
+      "logits/rejected": -2.265824556350708,
+      "logps/chosen": -104.0100326538086,
+      "logps/rejected": -141.9222869873047,
+      "loss": 0.09,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.6467862129211426,
+      "rewards/margins": 3.3599770069122314,
+      "rewards/rejected": -6.006763458251953,
+      "step": 390
+    },
+    {
+      "epoch": 13.50210970464135,
+      "grad_norm": 5.525568962097168,
+      "learning_rate": 1.328978898250525e-06,
+      "logits/chosen": -2.304884672164917,
+      "logits/rejected": -2.2955222129821777,
+      "logps/chosen": -99.25491333007812,
+      "logps/rejected": -142.86819458007812,
+      "loss": 0.0758,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.675879955291748,
+      "rewards/margins": 3.701845645904541,
+      "rewards/rejected": -6.377726078033447,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 580,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4823507575449846e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Power_Area_SFT/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd1c55d539ebcc8ff062a4ab8fef57d8c1444eb8abb545d69197bfbf2d86131
+size 5368