Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be064a121eb29a1b3e02a14d274bce9fcd21f3bdc35e99b066b8bc4d905ab96
+size 3087467144

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1841e417bad533ee1df666ad2a8968fad7a369946be4ac5ea6ea1b4f6e195648
+size 6175147196

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6261cf01b8bbe425d34da64dd41a31c8fe03315e63aaa8045f80c24bf8d242
+size 15920

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0728b56dab7abb5ef8a0d4bae3519c5767c97467bdd886d26bf19cc8599d0312
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e481d4ef1546694da7337f6bb6c658b866dcb79b85deeb477da0d27ebe851e
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353c60be37ea56fc992fca446598ceca5d1fd002aa3bd6dbb9ad740e6f47ebb3
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9107fe964ba7205e354084b85210e5a5ea1c98cfd4d38adb9cd3926945dcae4
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d1bb1abee38b92e53f3f23549b642ce0f1edcdccf7b6129847ac61636e96d5
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd5516048e20f36959601574e29e40106085a7d3cdc7bf425ce5e84633490e6
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c13a6c57ec393828f501786fefac38cbff40dc4da546a9558ca4292532d1bf
+size 1064

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a2951d5edfa5cc0a2346ef872f8c77a2920274cfc3b503b04e3799104dee80
+size 11422060

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1233 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.27991602519244224,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 187.95238494873047,
+      "epoch": 0.0027991602519244225,
+      "grad_norm": 1.0234375,
+      "kl": 0.0,
+      "learning_rate": 1.3888888888888888e-07,
+      "loss": 0.0,
+      "reward": 0.46513424068689346,
+      "reward_std": 0.20957323536276817,
+      "rewards/check_gptzero_func": 0.46513424068689346,
+      "step": 1
+    },
+    {
+      "completion_length": 204.64286041259766,
+      "epoch": 0.005598320503848845,
+      "grad_norm": 0.859375,
+      "kl": 0.0,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 0.0,
+      "reward": 0.3453420288860798,
+      "reward_std": 0.19838641211390495,
+      "rewards/check_gptzero_func": 0.3453420288860798,
+      "step": 2
+    },
+    {
+      "completion_length": 172.09524154663086,
+      "epoch": 0.008397480755773267,
+      "grad_norm": 1.0234375,
+      "kl": 8.45193862915039e-05,
+      "learning_rate": 4.1666666666666667e-07,
+      "loss": 0.0,
+      "reward": 0.4417309910058975,
+      "reward_std": 0.15838673152029514,
+      "rewards/check_gptzero_func": 0.4417309910058975,
+      "step": 3
+    },
+    {
+      "completion_length": 182.4761962890625,
+      "epoch": 0.01119664100769769,
+      "grad_norm": 1.015625,
+      "kl": 0.00014972686767578125,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.0,
+      "reward": 0.381104938685894,
+      "reward_std": 0.18715333193540573,
+      "rewards/check_gptzero_func": 0.381104938685894,
+      "step": 4
+    },
+    {
+      "completion_length": 174.01190948486328,
+      "epoch": 0.013995801259622114,
+      "grad_norm": 1.078125,
+      "kl": 0.000102996826171875,
+      "learning_rate": 6.944444444444446e-07,
+      "loss": 0.0,
+      "reward": 0.47953247278928757,
+      "reward_std": 0.1845148727297783,
+      "rewards/check_gptzero_func": 0.47953247278928757,
+      "step": 5
+    },
+    {
+      "completion_length": 201.01190948486328,
+      "epoch": 0.016794961511546535,
+      "grad_norm": 0.91015625,
+      "kl": 0.00011652708053588867,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.0,
+      "reward": 0.42353298515081406,
+      "reward_std": 0.1985670831054449,
+      "rewards/check_gptzero_func": 0.42353298515081406,
+      "step": 6
+    },
+    {
+      "completion_length": 175.90476989746094,
+      "epoch": 0.01959412176347096,
+      "grad_norm": 1.015625,
+      "kl": 0.00013816356658935547,
+      "learning_rate": 9.722222222222224e-07,
+      "loss": 0.0,
+      "reward": 0.5062773898243904,
+      "reward_std": 0.1975775510072708,
+      "rewards/check_gptzero_func": 0.5062773898243904,
+      "step": 7
+    },
+    {
+      "completion_length": 177.42857360839844,
+      "epoch": 0.02239328201539538,
+      "grad_norm": 0.9765625,
+      "kl": 0.00012969970703125,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.0,
+      "reward": 0.3951154872775078,
+      "reward_std": 0.1862633414566517,
+      "rewards/check_gptzero_func": 0.3951154872775078,
+      "step": 8
+    },
+    {
+      "completion_length": 187.6785774230957,
+      "epoch": 0.025192442267319804,
+      "grad_norm": 1.1171875,
+      "kl": 0.00012481212615966797,
+      "learning_rate": 1.25e-06,
+      "loss": 0.0,
+      "reward": 0.5369215086102486,
+      "reward_std": 0.27992387115955353,
+      "rewards/check_gptzero_func": 0.5369215086102486,
+      "step": 9
+    },
+    {
+      "completion_length": 184.0595245361328,
+      "epoch": 0.02799160251924423,
+      "grad_norm": 0.890625,
+      "kl": 0.00013375282287597656,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 0.0,
+      "reward": 0.4447266310453415,
+      "reward_std": 0.25660283863544464,
+      "rewards/check_gptzero_func": 0.4447266310453415,
+      "step": 10
+    },
+    {
+      "completion_length": 178.57143020629883,
+      "epoch": 0.03079076277116865,
+      "grad_norm": 1.109375,
+      "kl": 0.00011909008026123047,
+      "learning_rate": 1.527777777777778e-06,
+      "loss": 0.0,
+      "reward": 0.4782513678073883,
+      "reward_std": 0.19694043323397636,
+      "rewards/check_gptzero_func": 0.4782513678073883,
+      "step": 11
+    },
+    {
+      "completion_length": 166.57143020629883,
+      "epoch": 0.03358992302309307,
+      "grad_norm": 1.078125,
+      "kl": 0.00013256072998046875,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.0,
+      "reward": 0.2991659436374903,
+      "reward_std": 0.2037220150232315,
+      "rewards/check_gptzero_func": 0.2991659436374903,
+      "step": 12
+    },
+    {
+      "completion_length": 179.64286422729492,
+      "epoch": 0.0363890832750175,
+      "grad_norm": 0.921875,
+      "kl": 0.00010061264038085938,
+      "learning_rate": 1.8055555555555557e-06,
+      "loss": 0.0,
+      "reward": 0.35697006061673164,
+      "reward_std": 0.16125616803765297,
+      "rewards/check_gptzero_func": 0.35697006061673164,
+      "step": 13
+    },
+    {
+      "completion_length": 195.26191329956055,
+      "epoch": 0.03918824352694192,
+      "grad_norm": 1.0078125,
+      "kl": 0.00013875961303710938,
+      "learning_rate": 1.944444444444445e-06,
+      "loss": 0.0,
+      "reward": 0.5023506954312325,
+      "reward_std": 0.2251712903380394,
+      "rewards/check_gptzero_func": 0.5023506954312325,
+      "step": 14
+    },
+    {
+      "completion_length": 163.0952377319336,
+      "epoch": 0.04198740377886634,
+      "grad_norm": 1.15625,
+      "kl": 0.00012624263763427734,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.0,
+      "reward": 0.5686202421784401,
+      "reward_std": 0.16065805964171886,
+      "rewards/check_gptzero_func": 0.5686202421784401,
+      "step": 15
+    },
+    {
+      "completion_length": 180.0714340209961,
+      "epoch": 0.04478656403079076,
+      "grad_norm": 1.03125,
+      "kl": 0.00016486644744873047,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.0,
+      "reward": 0.4932379499077797,
+      "reward_std": 0.2570475209504366,
+      "rewards/check_gptzero_func": 0.4932379499077797,
+      "step": 16
+    },
+    {
+      "completion_length": 193.03571701049805,
+      "epoch": 0.04758572428271519,
+      "grad_norm": 1.0078125,
+      "kl": 0.00022602081298828125,
+      "learning_rate": 2.361111111111111e-06,
+      "loss": 0.0,
+      "reward": 0.34498296678066254,
+      "reward_std": 0.23837541788816452,
+      "rewards/check_gptzero_func": 0.34498296678066254,
+      "step": 17
+    },
+    {
+      "completion_length": 179.34524536132812,
+      "epoch": 0.05038488453463961,
+      "grad_norm": 0.94921875,
+      "kl": 0.00022101402282714844,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0,
+      "reward": 0.5981053188443184,
+      "reward_std": 0.16939585842192173,
+      "rewards/check_gptzero_func": 0.5981053188443184,
+      "step": 18
+    },
+    {
+      "completion_length": 182.52381134033203,
+      "epoch": 0.05318404478656403,
+      "grad_norm": 0.91796875,
+      "kl": 0.00026416778564453125,
+      "learning_rate": 2.6388888888888893e-06,
+      "loss": 0.0,
+      "reward": 0.4666922390460968,
+      "reward_std": 0.19714651349931955,
+      "rewards/check_gptzero_func": 0.4666922390460968,
+      "step": 19
+    },
+    {
+      "completion_length": 172.7023811340332,
+      "epoch": 0.05598320503848846,
+      "grad_norm": 0.98828125,
+      "kl": 0.0003151893615722656,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.0,
+      "reward": 0.5293586701154709,
+      "reward_std": 0.1787981353700161,
+      "rewards/check_gptzero_func": 0.5293586701154709,
+      "step": 20
+    },
+    {
+      "completion_length": 199.94047927856445,
+      "epoch": 0.05878236529041288,
+      "grad_norm": 1.0546875,
+      "kl": 0.00033283233642578125,
+      "learning_rate": 2.916666666666667e-06,
+      "loss": 0.0,
+      "reward": 0.4446847140789032,
+      "reward_std": 0.18958063051104546,
+      "rewards/check_gptzero_func": 0.4446847140789032,
+      "step": 21
+    },
+    {
+      "completion_length": 198.52381134033203,
+      "epoch": 0.0615815255423373,
+      "grad_norm": 0.8359375,
+      "kl": 0.00037479400634765625,
+      "learning_rate": 3.055555555555556e-06,
+      "loss": 0.0,
+      "reward": 0.5041225850582123,
+      "reward_std": 0.1401257887482643,
+      "rewards/check_gptzero_func": 0.5041225850582123,
+      "step": 22
+    },
+    {
+      "completion_length": 177.72619247436523,
+      "epoch": 0.06438068579426172,
+      "grad_norm": 0.99609375,
+      "kl": 0.0007195472717285156,
+      "learning_rate": 3.1944444444444443e-06,
+      "loss": 0.0001,
+      "reward": 0.472538560628891,
+      "reward_std": 0.25678203627467155,
+      "rewards/check_gptzero_func": 0.472538560628891,
+      "step": 23
+    },
+    {
+      "completion_length": 201.9761962890625,
+      "epoch": 0.06717984604618614,
+      "grad_norm": 0.8984375,
+      "kl": 0.0009317398071289062,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0001,
+      "reward": 0.5138305872678757,
+      "reward_std": 0.19977859780192375,
+      "rewards/check_gptzero_func": 0.5138305872678757,
+      "step": 24
+    },
+    {
+      "completion_length": 211.83333587646484,
+      "epoch": 0.06997900629811056,
+      "grad_norm": 0.78125,
+      "kl": 0.0008678436279296875,
+      "learning_rate": 3.4722222222222224e-06,
+      "loss": 0.0001,
+      "reward": 0.4136114977300167,
+      "reward_std": 0.1939336434006691,
+      "rewards/check_gptzero_func": 0.4136114977300167,
+      "step": 25
+    },
+    {
+      "completion_length": 173.82143020629883,
+      "epoch": 0.072778166550035,
+      "grad_norm": 0.9375,
+      "kl": 0.0014667510986328125,
+      "learning_rate": 3.6111111111111115e-06,
+      "loss": 0.0001,
+      "reward": 0.5154794007539749,
+      "reward_std": 0.22610028088092804,
+      "rewards/check_gptzero_func": 0.5154794007539749,
+      "step": 26
+    },
+    {
+      "completion_length": 190.48809814453125,
+      "epoch": 0.07557732680195942,
+      "grad_norm": 0.87890625,
+      "kl": 0.00168609619140625,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0002,
+      "reward": 0.5691990107297897,
+      "reward_std": 0.1696779690682888,
+      "rewards/check_gptzero_func": 0.5691990107297897,
+      "step": 27
+    },
+    {
+      "completion_length": 188.2738151550293,
+      "epoch": 0.07837648705388384,
+      "grad_norm": 0.9375,
+      "kl": 0.00185394287109375,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.0002,
+      "reward": 0.5436510145664215,
+      "reward_std": 0.24924885854125023,
+      "rewards/check_gptzero_func": 0.5436510145664215,
+      "step": 28
+    },
+    {
+      "completion_length": 205.52381134033203,
+      "epoch": 0.08117564730580826,
+      "grad_norm": 0.765625,
+      "kl": 0.001617431640625,
+      "learning_rate": 4.027777777777779e-06,
+      "loss": 0.0002,
+      "reward": 0.4470183253288269,
+      "reward_std": 0.20528827793896198,
+      "rewards/check_gptzero_func": 0.4470183253288269,
+      "step": 29
+    },
+    {
+      "completion_length": 171.84524154663086,
+      "epoch": 0.08397480755773268,
+      "grad_norm": 0.9609375,
+      "kl": 0.003101348876953125,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.0003,
+      "reward": 0.46852748841047287,
+      "reward_std": 0.16202964074909687,
+      "rewards/check_gptzero_func": 0.46852748841047287,
+      "step": 30
+    },
+    {
+      "completion_length": 180.92857360839844,
+      "epoch": 0.0867739678096571,
+      "grad_norm": 1.34375,
+      "kl": 0.003253936767578125,
+      "learning_rate": 4.305555555555556e-06,
+      "loss": 0.0003,
+      "reward": 0.43846940994262695,
+      "reward_std": 0.16219847835600376,
+      "rewards/check_gptzero_func": 0.43846940994262695,
+      "step": 31
+    },
+    {
+      "completion_length": 200.4285774230957,
+      "epoch": 0.08957312806158152,
+      "grad_norm": 0.8125,
+      "kl": 0.00244140625,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0003,
+      "reward": 0.5283855870366096,
+      "reward_std": 0.20884095132350922,
+      "rewards/check_gptzero_func": 0.5283855870366096,
+      "step": 32
+    },
+    {
+      "completion_length": 178.6190528869629,
+      "epoch": 0.09237228831350595,
+      "grad_norm": 0.83984375,
+      "kl": 0.00383758544921875,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 0.0004,
+      "reward": 0.5132240653038025,
+      "reward_std": 0.15939988382160664,
+      "rewards/check_gptzero_func": 0.5132240653038025,
+      "step": 33
+    },
+    {
+      "completion_length": 195.8095245361328,
+      "epoch": 0.09517144856543037,
+      "grad_norm": 0.9609375,
+      "kl": 0.0034942626953125,
+      "learning_rate": 4.722222222222222e-06,
+      "loss": 0.0003,
+      "reward": 0.4721037596464157,
+      "reward_std": 0.22807539626955986,
+      "rewards/check_gptzero_func": 0.4721037596464157,
+      "step": 34
+    },
+    {
+      "completion_length": 187.72619247436523,
+      "epoch": 0.0979706088173548,
+      "grad_norm": 0.78515625,
+      "kl": 0.004547119140625,
+      "learning_rate": 4.861111111111111e-06,
+      "loss": 0.0005,
+      "reward": 0.4753117114305496,
+      "reward_std": 0.21822157502174377,
+      "rewards/check_gptzero_func": 0.4753117114305496,
+      "step": 35
+    },
+    {
+      "completion_length": 189.3452377319336,
+      "epoch": 0.10076976906927922,
+      "grad_norm": 1.015625,
+      "kl": 0.005115509033203125,
+      "learning_rate": 5e-06,
+      "loss": 0.0005,
+      "reward": 0.5079967528581619,
+      "reward_std": 0.1728131715208292,
+      "rewards/check_gptzero_func": 0.5079967528581619,
+      "step": 36
+    },
+    {
+      "completion_length": 182.50000381469727,
+      "epoch": 0.10356892932120364,
+      "grad_norm": 0.859375,
+      "kl": 0.006103515625,
+      "learning_rate": 4.999880271862381e-06,
+      "loss": 0.0006,
+      "reward": 0.5491276457905769,
+      "reward_std": 0.29580989107489586,
+      "rewards/check_gptzero_func": 0.5491276457905769,
+      "step": 37
+    },
+    {
+      "completion_length": 201.61904907226562,
+      "epoch": 0.10636808957312806,
+      "grad_norm": 0.7890625,
+      "kl": 0.00431060791015625,
+      "learning_rate": 4.999521098917384e-06,
+      "loss": 0.0005,
+      "reward": 0.7083312571048737,
+      "reward_std": 0.17898299172520638,
+      "rewards/check_gptzero_func": 0.7083312571048737,
+      "step": 38
+    },
+    {
+      "completion_length": 183.6904754638672,
+      "epoch": 0.10916724982505248,
+      "grad_norm": 0.828125,
+      "kl": 0.00653076171875,
+      "learning_rate": 4.998922515567496e-06,
+      "loss": 0.0007,
+      "reward": 0.5663967505097389,
+      "reward_std": 0.21669673547148705,
+      "rewards/check_gptzero_func": 0.5663967505097389,
+      "step": 39
+    },
+    {
+      "completion_length": 176.16667556762695,
+      "epoch": 0.11196641007697691,
+      "grad_norm": 0.83984375,
+      "kl": 0.007232666015625,
+      "learning_rate": 4.998084579146533e-06,
+      "loss": 0.0007,
+      "reward": 0.592326283454895,
+      "reward_std": 0.1653369516134262,
+      "rewards/check_gptzero_func": 0.592326283454895,
+      "step": 40
+    },
+    {
+      "completion_length": 191.34524154663086,
+      "epoch": 0.11476557032890133,
+      "grad_norm": 0.78515625,
+      "kl": 0.006866455078125,
+      "learning_rate": 4.997007369914149e-06,
+      "loss": 0.0007,
+      "reward": 0.5438110902905464,
+      "reward_std": 0.150531854480505,
+      "rewards/check_gptzero_func": 0.5438110902905464,
+      "step": 41
+    },
+    {
+      "completion_length": 173.26190567016602,
+      "epoch": 0.11756473058082575,
+      "grad_norm": 0.90234375,
+      "kl": 0.00835418701171875,
+      "learning_rate": 4.9956909910481465e-06,
+      "loss": 0.0008,
+      "reward": 0.496019683778286,
+      "reward_std": 0.13957532681524754,
+      "rewards/check_gptzero_func": 0.496019683778286,
+      "step": 42
+    },
+    {
+      "completion_length": 197.21428680419922,
+      "epoch": 0.12036389083275018,
+      "grad_norm": 0.7578125,
+      "kl": 0.00658416748046875,
+      "learning_rate": 4.994135568634598e-06,
+      "loss": 0.0007,
+      "reward": 0.5706812366843224,
+      "reward_std": 0.22384651005268097,
+      "rewards/check_gptzero_func": 0.5706812366843224,
+      "step": 43
+    },
+    {
+      "completion_length": 195.50000381469727,
+      "epoch": 0.1231630510846746,
+      "grad_norm": 0.8046875,
+      "kl": 0.0059814453125,
+      "learning_rate": 4.992341251655768e-06,
+      "loss": 0.0006,
+      "reward": 0.49248379468917847,
+      "reward_std": 0.1679957453161478,
+      "rewards/check_gptzero_func": 0.49248379468917847,
+      "step": 44
+    },
+    {
+      "completion_length": 174.83333206176758,
+      "epoch": 0.12596221133659902,
+      "grad_norm": 0.83984375,
+      "kl": 0.00934600830078125,
+      "learning_rate": 4.99030821197584e-06,
+      "loss": 0.001,
+      "reward": 0.5782680213451385,
+      "reward_std": 0.18842186219990253,
+      "rewards/check_gptzero_func": 0.5782680213451385,
+      "step": 45
+    },
+    {
+      "completion_length": 180.71428680419922,
+      "epoch": 0.12876137158852344,
+      "grad_norm": 0.83203125,
+      "kl": 0.009490966796875,
+      "learning_rate": 4.988036644324457e-06,
+      "loss": 0.001,
+      "reward": 0.5191970095038414,
+      "reward_std": 0.2319345511496067,
+      "rewards/check_gptzero_func": 0.5191970095038414,
+      "step": 46
+    },
+    {
+      "completion_length": 185.46429061889648,
+      "epoch": 0.13156053184044786,
+      "grad_norm": 0.8125,
+      "kl": 0.00946044921875,
+      "learning_rate": 4.9855267662780715e-06,
+      "loss": 0.0009,
+      "reward": 0.6461608409881592,
+      "reward_std": 0.1471536885946989,
+      "rewards/check_gptzero_func": 0.6461608409881592,
+      "step": 47
+    },
+    {
+      "completion_length": 176.53571701049805,
+      "epoch": 0.13435969209237228,
+      "grad_norm": 0.82421875,
+      "kl": 0.01032257080078125,
+      "learning_rate": 4.982778818239101e-06,
+      "loss": 0.001,
+      "reward": 0.49297887086868286,
+      "reward_std": 0.1380300959572196,
+      "rewards/check_gptzero_func": 0.49297887086868286,
+      "step": 48
+    },
+    {
+      "completion_length": 189.15476608276367,
+      "epoch": 0.1371588523442967,
+      "grad_norm": 0.9765625,
+      "kl": 0.01055145263671875,
+      "learning_rate": 4.979793063412909e-06,
+      "loss": 0.0011,
+      "reward": 0.5546858608722687,
+      "reward_std": 0.20936554670333862,
+      "rewards/check_gptzero_func": 0.5546858608722687,
+      "step": 49
+    },
+    {
+      "completion_length": 175.32143020629883,
+      "epoch": 0.13995801259622112,
+      "grad_norm": 0.80859375,
+      "kl": 0.0104827880859375,
+      "learning_rate": 4.9765697877825844e-06,
+      "loss": 0.001,
+      "reward": 0.5866354256868362,
+      "reward_std": 0.1675815749913454,
+      "rewards/check_gptzero_func": 0.5866354256868362,
+      "step": 50
+    },
+    {
+      "completion_length": 178.88095092773438,
+      "epoch": 0.14275717284814557,
+      "grad_norm": 0.921875,
+      "kl": 0.01032257080078125,
+      "learning_rate": 4.97310930008156e-06,
+      "loss": 0.001,
+      "reward": 0.6669622659683228,
+      "reward_std": 0.21926475502550602,
+      "rewards/check_gptzero_func": 0.6669622659683228,
+      "step": 51
+    },
+    {
+      "completion_length": 180.7738151550293,
+      "epoch": 0.14555633310007,
+      "grad_norm": 0.83984375,
+      "kl": 0.0123748779296875,
+      "learning_rate": 4.969411931764033e-06,
+      "loss": 0.0012,
+      "reward": 0.567020371556282,
+      "reward_std": 0.17968417704105377,
+      "rewards/check_gptzero_func": 0.567020371556282,
+      "step": 52
+    },
+    {
+      "completion_length": 195.5357208251953,
+      "epoch": 0.1483554933519944,
+      "grad_norm": 0.796875,
+      "kl": 0.0104827880859375,
+      "learning_rate": 4.965478036973221e-06,
+      "loss": 0.001,
+      "reward": 0.6985915303230286,
+      "reward_std": 0.17377906665205956,
+      "rewards/check_gptzero_func": 0.6985915303230286,
+      "step": 53
+    },
+    {
+      "completion_length": 178.00000381469727,
+      "epoch": 0.15115465360391883,
+      "grad_norm": 1.0234375,
+      "kl": 0.01174163818359375,
+      "learning_rate": 4.9613079925074435e-06,
+      "loss": 0.0012,
+      "reward": 0.6754837036132812,
+      "reward_std": 0.2185358963906765,
+      "rewards/check_gptzero_func": 0.6754837036132812,
+      "step": 54
+    },
+    {
+      "completion_length": 172.64286041259766,
+      "epoch": 0.15395381385584325,
+      "grad_norm": 0.8203125,
+      "kl": 0.0126953125,
+      "learning_rate": 4.956902197784025e-06,
+      "loss": 0.0013,
+      "reward": 0.5507477447390556,
+      "reward_std": 0.12427662499248981,
+      "rewards/check_gptzero_func": 0.5507477447390556,
+      "step": 55
+    },
+    {
+      "completion_length": 178.40476608276367,
+      "epoch": 0.15675297410776767,
+      "grad_norm": 0.83984375,
+      "kl": 0.01100921630859375,
+      "learning_rate": 4.952261074801043e-06,
+      "loss": 0.0011,
+      "reward": 0.7200377136468887,
+      "reward_std": 0.1754942275583744,
+      "rewards/check_gptzero_func": 0.7200377136468887,
+      "step": 56
+    },
+    {
+      "completion_length": 177.02381134033203,
+      "epoch": 0.1595521343596921,
+      "grad_norm": 0.859375,
+      "kl": 0.01055908203125,
+      "learning_rate": 4.947385068096907e-06,
+      "loss": 0.0011,
+      "reward": 0.7536474019289017,
+      "reward_std": 0.12843344174325466,
+      "rewards/check_gptzero_func": 0.7536474019289017,
+      "step": 57
+    },
+    {
+      "completion_length": 197.3571434020996,
+      "epoch": 0.16235129461161651,
+      "grad_norm": 0.8515625,
+      "kl": 0.00899505615234375,
+      "learning_rate": 4.942274644707778e-06,
+      "loss": 0.0009,
+      "reward": 0.5334034785628319,
+      "reward_std": 0.22946524992585182,
+      "rewards/check_gptzero_func": 0.5334034785628319,
+      "step": 58
+    },
+    {
+      "completion_length": 182.14286041259766,
+      "epoch": 0.16515045486354094,
+      "grad_norm": 0.921875,
+      "kl": 0.01129150390625,
+      "learning_rate": 4.936930294122838e-06,
+      "loss": 0.0011,
+      "reward": 0.5683771669864655,
+      "reward_std": 0.1916387351229787,
+      "rewards/check_gptzero_func": 0.5683771669864655,
+      "step": 59
+    },
+    {
+      "completion_length": 173.2023811340332,
+      "epoch": 0.16794961511546536,
+      "grad_norm": 0.92578125,
+      "kl": 0.01171875,
+      "learning_rate": 4.931352528237398e-06,
+      "loss": 0.0012,
+      "reward": 0.6447094231843948,
+      "reward_std": 0.19410214200615883,
+      "rewards/check_gptzero_func": 0.6447094231843948,
+      "step": 60
+    },
+    {
+      "completion_length": 185.6428565979004,
+      "epoch": 0.17074877536738978,
+      "grad_norm": 0.8515625,
+      "kl": 0.00968170166015625,
+      "learning_rate": 4.925541881303876e-06,
+      "loss": 0.001,
+      "reward": 0.6383133828639984,
+      "reward_std": 0.18484976701438427,
+      "rewards/check_gptzero_func": 0.6383133828639984,
+      "step": 61
+    },
+    {
+      "completion_length": 189.1785774230957,
+      "epoch": 0.1735479356193142,
+      "grad_norm": 1.0078125,
+      "kl": 0.008331298828125,
+      "learning_rate": 4.919498909880621e-06,
+      "loss": 0.0008,
+      "reward": 0.6155931651592255,
+      "reward_std": 0.18777143955230713,
+      "rewards/check_gptzero_func": 0.6155931651592255,
+      "step": 62
+    },
+    {
+      "completion_length": 191.80952835083008,
+      "epoch": 0.17634709587123862,
+      "grad_norm": 0.8046875,
+      "kl": 0.00836181640625,
+      "learning_rate": 4.913224192778604e-06,
+      "loss": 0.0008,
+      "reward": 0.6793939918279648,
+      "reward_std": 0.09720544703304768,
+      "rewards/check_gptzero_func": 0.6793939918279648,
+      "step": 63
+    },
+    {
+      "completion_length": 171.97619247436523,
+      "epoch": 0.17914625612316304,
+      "grad_norm": 0.88671875,
+      "kl": 0.00908660888671875,
+      "learning_rate": 4.906718331005979e-06,
+      "loss": 0.0009,
+      "reward": 0.44309166073799133,
+      "reward_std": 0.2190867941826582,
+      "rewards/check_gptzero_func": 0.44309166073799133,
+      "step": 64
+    },
+    {
+      "completion_length": 175.59524154663086,
+      "epoch": 0.1819454163750875,
+      "grad_norm": 0.9140625,
+      "kl": 0.00946044921875,
+      "learning_rate": 4.899981947710518e-06,
+      "loss": 0.0009,
+      "reward": 0.5109639540314674,
+      "reward_std": 0.15947622060775757,
+      "rewards/check_gptzero_func": 0.5109639540314674,
+      "step": 65
+    },
+    {
+      "completion_length": 184.76190948486328,
+      "epoch": 0.1847445766270119,
+      "grad_norm": 0.90234375,
+      "kl": 0.009246826171875,
+      "learning_rate": 4.893015688119921e-06,
+      "loss": 0.0009,
+      "reward": 0.5143184289336205,
+      "reward_std": 0.2525811605155468,
+      "rewards/check_gptzero_func": 0.5143184289336205,
+      "step": 66
+    },
+    {
+      "completion_length": 174.76191329956055,
+      "epoch": 0.18754373687893633,
+      "grad_norm": 0.890625,
+      "kl": 0.0095367431640625,
+      "learning_rate": 4.885820219480018e-06,
+      "loss": 0.001,
+      "reward": 0.6203874498605728,
+      "reward_std": 0.20078162848949432,
+      "rewards/check_gptzero_func": 0.6203874498605728,
+      "step": 67
+    },
+    {
+      "completion_length": 184.2738151550293,
+      "epoch": 0.19034289713086075,
+      "grad_norm": 0.98046875,
+      "kl": 0.008697509765625,
+      "learning_rate": 4.8783962309908564e-06,
+      "loss": 0.0009,
+      "reward": 0.5816539227962494,
+      "reward_std": 0.23236144706606865,
+      "rewards/check_gptzero_func": 0.5816539227962494,
+      "step": 68
+    },
+    {
+      "completion_length": 184.0,
+      "epoch": 0.19314205738278517,
+      "grad_norm": 0.8984375,
+      "kl": 0.00894927978515625,
+      "learning_rate": 4.870744433740688e-06,
+      "loss": 0.0009,
+      "reward": 0.6825973987579346,
+      "reward_std": 0.17790008522570133,
+      "rewards/check_gptzero_func": 0.6825973987579346,
+      "step": 69
+    },
+    {
+      "completion_length": 204.1785774230957,
+      "epoch": 0.1959412176347096,
+      "grad_norm": 0.8203125,
+      "kl": 0.00753021240234375,
+      "learning_rate": 4.8628655606378625e-06,
+      "loss": 0.0008,
+      "reward": 0.6512226462364197,
+      "reward_std": 0.22282536327838898,
+      "rewards/check_gptzero_func": 0.6512226462364197,
+      "step": 70
+    },
+    {
+      "completion_length": 188.47619247436523,
+      "epoch": 0.198740377886634,
+      "grad_norm": 0.96875,
+      "kl": 0.00823974609375,
+      "learning_rate": 4.854760366340619e-06,
+      "loss": 0.0008,
+      "reward": 0.6291620433330536,
+      "reward_std": 0.18235865235328674,
+      "rewards/check_gptzero_func": 0.6291620433330536,
+      "step": 71
+    },
+    {
+      "completion_length": 191.6428565979004,
+      "epoch": 0.20153953813855843,
+      "grad_norm": 1.0078125,
+      "kl": 0.00788116455078125,
+      "learning_rate": 4.846429627184816e-06,
+      "loss": 0.0008,
+      "reward": 0.5630831271409988,
+      "reward_std": 0.20192383974790573,
+      "rewards/check_gptzero_func": 0.5630831271409988,
+      "step": 72
+    },
+    {
+      "completion_length": 186.39286422729492,
+      "epoch": 0.20433869839048285,
+      "grad_norm": 1.0078125,
+      "kl": 0.0083770751953125,
+      "learning_rate": 4.837874141109557e-06,
+      "loss": 0.0008,
+      "reward": 0.566518671810627,
+      "reward_std": 0.2747541069984436,
+      "rewards/check_gptzero_func": 0.566518671810627,
+      "step": 73
+    },
+    {
+      "completion_length": 197.75000381469727,
+      "epoch": 0.20713785864240727,
+      "grad_norm": 0.9140625,
+      "kl": 0.0078887939453125,
+      "learning_rate": 4.829094727580775e-06,
+      "loss": 0.0008,
+      "reward": 0.6935234069824219,
+      "reward_std": 0.12828794866800308,
+      "rewards/check_gptzero_func": 0.6935234069824219,
+      "step": 74
+    },
+    {
+      "completion_length": 182.94047927856445,
+      "epoch": 0.2099370188943317,
+      "grad_norm": 1.0859375,
+      "kl": 0.0101470947265625,
+      "learning_rate": 4.820092227512736e-06,
+      "loss": 0.001,
+      "reward": 0.5632592514157295,
+      "reward_std": 0.20659778825938702,
+      "rewards/check_gptzero_func": 0.5632592514157295,
+      "step": 75
+    },
+    {
+      "completion_length": 189.26190948486328,
+      "epoch": 0.21273617914625612,
+      "grad_norm": 0.97265625,
+      "kl": 0.0099639892578125,
+      "learning_rate": 4.810867503187492e-06,
+      "loss": 0.001,
+      "reward": 0.6693995073437691,
+      "reward_std": 0.15574552537873387,
+      "rewards/check_gptzero_func": 0.6693995073437691,
+      "step": 76
+    },
+    {
+      "completion_length": 202.20238494873047,
+      "epoch": 0.21553533939818054,
+      "grad_norm": 1.046875,
+      "kl": 0.0087127685546875,
+      "learning_rate": 4.8014214381722945e-06,
+      "loss": 0.0009,
+      "reward": 0.6062769070267677,
+      "reward_std": 0.269734937697649,
+      "rewards/check_gptzero_func": 0.6062769070267677,
+      "step": 77
+    },
+    {
+      "completion_length": 201.22619247436523,
+      "epoch": 0.21833449965010496,
+      "grad_norm": 0.953125,
+      "kl": 0.00868988037109375,
+      "learning_rate": 4.791754937234962e-06,
+      "loss": 0.0009,
+      "reward": 0.5902510657906532,
+      "reward_std": 0.20445209927856922,
+      "rewards/check_gptzero_func": 0.5902510657906532,
+      "step": 78
+    },
+    {
+      "completion_length": 191.41666793823242,
+      "epoch": 0.22113365990202938,
+      "grad_norm": 0.859375,
+      "kl": 0.0099029541015625,
+      "learning_rate": 4.781868926257216e-06,
+      "loss": 0.001,
+      "reward": 0.7119332551956177,
+      "reward_std": 0.1272009308449924,
+      "rewards/check_gptzero_func": 0.7119332551956177,
+      "step": 79
+    },
+    {
+      "completion_length": 201.95238494873047,
+      "epoch": 0.22393282015395383,
+      "grad_norm": 0.9609375,
+      "kl": 0.01006317138671875,
+      "learning_rate": 4.771764352146005e-06,
+      "loss": 0.001,
+      "reward": 0.6730313450098038,
+      "reward_std": 0.23449595272541046,
+      "rewards/check_gptzero_func": 0.6730313450098038,
+      "step": 80
+    },
+    {
+      "completion_length": 181.53571701049805,
+      "epoch": 0.22673198040587825,
+      "grad_norm": 1.15625,
+      "kl": 0.0106964111328125,
+      "learning_rate": 4.761442182742799e-06,
+      "loss": 0.0011,
+      "reward": 0.5613239407539368,
+      "reward_std": 0.21234364807605743,
+      "rewards/check_gptzero_func": 0.5613239407539368,
+      "step": 81
+    },
+    {
+      "completion_length": 184.67857360839844,
+      "epoch": 0.22953114065780267,
+      "grad_norm": 0.9765625,
+      "kl": 0.0101776123046875,
+      "learning_rate": 4.750903406730895e-06,
+      "loss": 0.001,
+      "reward": 0.5844283923506737,
+      "reward_std": 0.21481262892484665,
+      "rewards/check_gptzero_func": 0.5844283923506737,
+      "step": 82
+    },
+    {
+      "completion_length": 169.38095474243164,
+      "epoch": 0.2323303009097271,
+      "grad_norm": 1.1484375,
+      "kl": 0.0128021240234375,
+      "learning_rate": 4.740149033540711e-06,
+      "loss": 0.0013,
+      "reward": 0.6525488644838333,
+      "reward_std": 0.19818515330553055,
+      "rewards/check_gptzero_func": 0.6525488644838333,
+      "step": 83
+    },
+    {
+      "completion_length": 178.3809585571289,
+      "epoch": 0.2351294611616515,
+      "grad_norm": 1.0859375,
+      "kl": 0.010101318359375,
+      "learning_rate": 4.729180093253106e-06,
+      "loss": 0.001,
+      "reward": 0.6054461151361465,
+      "reward_std": 0.22233787178993225,
+      "rewards/check_gptzero_func": 0.6054461151361465,
+      "step": 84
+    },
+    {
+      "completion_length": 185.47619247436523,
+      "epoch": 0.23792862141357593,
+      "grad_norm": 0.93359375,
+      "kl": 0.0096588134765625,
+      "learning_rate": 4.717997636500715e-06,
+      "loss": 0.001,
+      "reward": 0.5751017481088638,
+      "reward_std": 0.19414596632122993,
+      "rewards/check_gptzero_func": 0.5751017481088638,
+      "step": 85
+    },
+    {
+      "completion_length": 176.61904907226562,
+      "epoch": 0.24072778166550035,
+      "grad_norm": 0.90234375,
+      "kl": 0.0117034912109375,
+      "learning_rate": 4.706602734367314e-06,
+      "loss": 0.0012,
+      "reward": 0.6652742102742195,
+      "reward_std": 0.1461728010326624,
+      "rewards/check_gptzero_func": 0.6652742102742195,
+      "step": 86
+    },
+    {
+      "completion_length": 204.6785774230957,
+      "epoch": 0.24352694191742477,
+      "grad_norm": 0.8203125,
+      "kl": 0.00868988037109375,
+      "learning_rate": 4.694996478285232e-06,
+      "loss": 0.0009,
+      "reward": 0.5329968556761742,
+      "reward_std": 0.23187025263905525,
+      "rewards/check_gptzero_func": 0.5329968556761742,
+      "step": 87
+    },
+    {
+      "completion_length": 191.7738151550293,
+      "epoch": 0.2463261021693492,
+      "grad_norm": 0.9140625,
+      "kl": 0.0092010498046875,
+      "learning_rate": 4.683179979930808e-06,
+      "loss": 0.0009,
+      "reward": 0.660212829709053,
+      "reward_std": 0.17499383352696896,
+      "rewards/check_gptzero_func": 0.660212829709053,
+      "step": 88
+    },
+    {
+      "completion_length": 188.29762268066406,
+      "epoch": 0.2491252624212736,
+      "grad_norm": 0.85546875,
+      "kl": 0.01043701171875,
+      "learning_rate": 4.6711543711179155e-06,
+      "loss": 0.001,
+      "reward": 0.6105453222990036,
+      "reward_std": 0.1719030626118183,
+      "rewards/check_gptzero_func": 0.6105453222990036,
+      "step": 89
+    },
+    {
+      "completion_length": 185.86904907226562,
+      "epoch": 0.25192442267319803,
+      "grad_norm": 1.0234375,
+      "kl": 0.01029205322265625,
+      "learning_rate": 4.658920803689553e-06,
+      "loss": 0.001,
+      "reward": 0.6307502388954163,
+      "reward_std": 0.26598427444696426,
+      "rewards/check_gptzero_func": 0.6307502388954163,
+      "step": 90
+    },
+    {
+      "completion_length": 180.8571434020996,
+      "epoch": 0.2547235829251225,
+      "grad_norm": 0.9765625,
+      "kl": 0.0113525390625,
+      "learning_rate": 4.646480449407516e-06,
+      "loss": 0.0011,
+      "reward": 0.661887601017952,
+      "reward_std": 0.17039467580616474,
+      "rewards/check_gptzero_func": 0.661887601017952,
+      "step": 91
+    },
+    {
+      "completion_length": 175.97619247436523,
+      "epoch": 0.2575227431770469,
+      "grad_norm": 1.09375,
+      "kl": 0.0103912353515625,
+      "learning_rate": 4.633834499840164e-06,
+      "loss": 0.001,
+      "reward": 0.6470509469509125,
+      "reward_std": 0.11666383501142263,
+      "rewards/check_gptzero_func": 0.6470509469509125,
+      "step": 92
+    },
+    {
+      "completion_length": 196.95238494873047,
+      "epoch": 0.2603219034289713,
+      "grad_norm": 0.87890625,
+      "kl": 0.00783538818359375,
+      "learning_rate": 4.620984166248288e-06,
+      "loss": 0.0008,
+      "reward": 0.645782083272934,
+      "reward_std": 0.16378989815711975,
+      "rewards/check_gptzero_func": 0.645782083272934,
+      "step": 93
+    },
+    {
+      "completion_length": 184.09524536132812,
+      "epoch": 0.2631210636808957,
+      "grad_norm": 0.92578125,
+      "kl": 0.00963592529296875,
+      "learning_rate": 4.607930679469096e-06,
+      "loss": 0.001,
+      "reward": 0.6375631093978882,
+      "reward_std": 0.12679122015833855,
+      "rewards/check_gptzero_func": 0.6375631093978882,
+      "step": 94
+    },
+    {
+      "completion_length": 187.78571701049805,
+      "epoch": 0.26592022393282017,
+      "grad_norm": 0.84375,
+      "kl": 0.009124755859375,
+      "learning_rate": 4.594675289798317e-06,
+      "loss": 0.0009,
+      "reward": 0.6679813116788864,
+      "reward_std": 0.19044114090502262,
+      "rewards/check_gptzero_func": 0.6679813116788864,
+      "step": 95
+    },
+    {
+      "completion_length": 174.94048309326172,
+      "epoch": 0.26871938418474456,
+      "grad_norm": 0.9609375,
+      "kl": 0.01029205322265625,
+      "learning_rate": 4.5812192668704454e-06,
+      "loss": 0.001,
+      "reward": 0.5234083607792854,
+      "reward_std": 0.2531973347067833,
+      "rewards/check_gptzero_func": 0.5234083607792854,
+      "step": 96
+    },
+    {
+      "completion_length": 183.19048309326172,
+      "epoch": 0.271518544436669,
+      "grad_norm": 0.90234375,
+      "kl": 0.00909423828125,
+      "learning_rate": 4.5675638995371355e-06,
+      "loss": 0.0009,
+      "reward": 0.5966005846858025,
+      "reward_std": 0.22473083063960075,
+      "rewards/check_gptzero_func": 0.5966005846858025,
+      "step": 97
+    },
+    {
+      "completion_length": 183.14286041259766,
+      "epoch": 0.2743177046885934,
+      "grad_norm": 0.85546875,
+      "kl": 0.0090484619140625,
+      "learning_rate": 4.553710495743744e-06,
+      "loss": 0.0009,
+      "reward": 0.5813074707984924,
+      "reward_std": 0.1640096753835678,
+      "rewards/check_gptzero_func": 0.5813074707984924,
+      "step": 98
+    },
+    {
+      "completion_length": 198.46429061889648,
+      "epoch": 0.27711686494051785,
+      "grad_norm": 0.88671875,
+      "kl": 0.0083465576171875,
+      "learning_rate": 4.53966038240406e-06,
+      "loss": 0.0008,
+      "reward": 0.48446883261203766,
+      "reward_std": 0.14858301915228367,
+      "rewards/check_gptzero_func": 0.48446883261203766,
+      "step": 99
+    },
+    {
+      "completion_length": 158.04762268066406,
+      "epoch": 0.27991602519244224,
+      "grad_norm": 1.0625,
+      "kl": 0.0104522705078125,
+      "learning_rate": 4.525414905273208e-06,
+      "loss": 0.001,
+      "reward": 0.6134350448846817,
+      "reward_std": 0.15003260038793087,
+      "rewards/check_gptzero_func": 0.6134350448846817,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 357,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11767c9c1a86e9069ef349f062d3c4d431840ae62e6be3f9118a165fd4e018dd
+size 5560