Upload checkpoint checkpoint-100

.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
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-100/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
+}

checkpoint-100/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/a23chand/projects/def-sfischme/a23chand/synthetic_questions/Qwen/Qwen2.5-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "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": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-100/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae7a67a70f040cec791cd4641866ba41d8e28d957ed42521f8dca8cfd22cafc
+size 3087467144

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c223685611eb8ca66172e98a5ae4d95e91d096b50c87d5ac51cf3a20f20698f0
+size 15024

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ecb9f981bc1cea06513b87be9861bad9289cd33d5bc89c8c1d83bebf350e5a
+size 15024

checkpoint-100/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b78f34e8919a0955c52fa2192994cab8b958695edae102824ebf7fb17e0c11e
+size 15024

checkpoint-100/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497903fb965e5819817c1bcae461581db9a95d72adb9e86baf55fc2dc3a38323
+size 15024

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7967c800915392f068addf34faf7da41da15c33263c318384d9786f5f7cc88
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-100/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 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 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.4437333333333333,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034133333333333335,
+      "grad_norm": 1.625,
+      "learning_rate": 3.448275862068965e-08,
+      "loss": 0.6812,
+      "step": 1
+    },
+    {
+      "epoch": 0.06826666666666667,
+      "grad_norm": 1.6953125,
+      "learning_rate": 6.89655172413793e-08,
+      "loss": 0.6715,
+      "step": 2
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.0344827586206897e-07,
+      "loss": 0.635,
+      "step": 3
+    },
+    {
+      "epoch": 0.13653333333333334,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.379310344827586e-07,
+      "loss": 0.6077,
+      "step": 4
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.7241379310344828e-07,
+      "loss": 0.6327,
+      "step": 5
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 1.6640625,
+      "learning_rate": 2.0689655172413793e-07,
+      "loss": 0.6415,
+      "step": 6
+    },
+    {
+      "epoch": 0.23893333333333333,
+      "grad_norm": 1.4609375,
+      "learning_rate": 2.413793103448276e-07,
+      "loss": 0.6325,
+      "step": 7
+    },
+    {
+      "epoch": 0.2730666666666667,
+      "grad_norm": 1.71875,
+      "learning_rate": 2.758620689655172e-07,
+      "loss": 0.6588,
+      "step": 8
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 1.71875,
+      "learning_rate": 3.103448275862069e-07,
+      "loss": 0.6164,
+      "step": 9
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 1.78125,
+      "learning_rate": 3.4482758620689656e-07,
+      "loss": 0.6437,
+      "step": 10
+    },
+    {
+      "epoch": 0.37546666666666667,
+      "grad_norm": 1.578125,
+      "learning_rate": 3.793103448275862e-07,
+      "loss": 0.6496,
+      "step": 11
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 1.5859375,
+      "learning_rate": 4.1379310344827586e-07,
+      "loss": 0.6255,
+      "step": 12
+    },
+    {
+      "epoch": 0.4437333333333333,
+      "grad_norm": 1.6953125,
+      "learning_rate": 4.482758620689655e-07,
+      "loss": 0.6657,
+      "step": 13
+    },
+    {
+      "epoch": 0.47786666666666666,
+      "grad_norm": 1.53125,
+      "learning_rate": 4.827586206896552e-07,
+      "loss": 0.6664,
+      "step": 14
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 1.7265625,
+      "learning_rate": 5.172413793103448e-07,
+      "loss": 0.6579,
+      "step": 15
+    },
+    {
+      "epoch": 0.5461333333333334,
+      "grad_norm": 1.671875,
+      "learning_rate": 5.517241379310344e-07,
+      "loss": 0.6361,
+      "step": 16
+    },
+    {
+      "epoch": 0.5802666666666667,
+      "grad_norm": 1.703125,
+      "learning_rate": 5.86206896551724e-07,
+      "loss": 0.6719,
+      "step": 17
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 1.59375,
+      "learning_rate": 6.206896551724138e-07,
+      "loss": 0.6339,
+      "step": 18
+    },
+    {
+      "epoch": 0.6485333333333333,
+      "grad_norm": 1.765625,
+      "learning_rate": 6.551724137931034e-07,
+      "loss": 0.6607,
+      "step": 19
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 1.7421875,
+      "learning_rate": 6.896551724137931e-07,
+      "loss": 0.6302,
+      "step": 20
+    },
+    {
+      "epoch": 0.7168,
+      "grad_norm": 1.6796875,
+      "learning_rate": 7.241379310344827e-07,
+      "loss": 0.6656,
+      "step": 21
+    },
+    {
+      "epoch": 0.7509333333333333,
+      "grad_norm": 1.5625,
+      "learning_rate": 7.586206896551724e-07,
+      "loss": 0.6384,
+      "step": 22
+    },
+    {
+      "epoch": 0.7850666666666667,
+      "grad_norm": 1.6328125,
+      "learning_rate": 7.931034482758621e-07,
+      "loss": 0.629,
+      "step": 23
+    },
+    {
+      "epoch": 0.8192,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.275862068965517e-07,
+      "loss": 0.6668,
+      "step": 24
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.6875,
+      "learning_rate": 8.620689655172412e-07,
+      "loss": 0.6722,
+      "step": 25
+    },
+    {
+      "epoch": 0.8874666666666666,
+      "grad_norm": 1.6640625,
+      "learning_rate": 8.96551724137931e-07,
+      "loss": 0.6246,
+      "step": 26
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 1.734375,
+      "learning_rate": 9.310344827586206e-07,
+      "loss": 0.6597,
+      "step": 27
+    },
+    {
+      "epoch": 0.9557333333333333,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.655172413793103e-07,
+      "loss": 0.6172,
+      "step": 28
+    },
+    {
+      "epoch": 0.9898666666666667,
+      "grad_norm": 1.59375,
+      "learning_rate": 1e-06,
+      "loss": 0.6329,
+      "step": 29
+    },
+    {
+      "epoch": 1.0341333333333333,
+      "grad_norm": 3.46875,
+      "learning_rate": 9.961685823754787e-07,
+      "loss": 1.1453,
+      "step": 30
+    },
+    {
+      "epoch": 1.0682666666666667,
+      "grad_norm": 1.734375,
+      "learning_rate": 9.92337164750958e-07,
+      "loss": 0.6728,
+      "step": 31
+    },
+    {
+      "epoch": 1.1024,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.885057471264367e-07,
+      "loss": 0.6488,
+      "step": 32
+    },
+    {
+      "epoch": 1.1365333333333334,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.846743295019157e-07,
+      "loss": 0.6498,
+      "step": 33
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.808429118773945e-07,
+      "loss": 0.6179,
+      "step": 34
+    },
+    {
+      "epoch": 1.2048,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.770114942528735e-07,
+      "loss": 0.6519,
+      "step": 35
+    },
+    {
+      "epoch": 1.2389333333333332,
+      "grad_norm": 1.6796875,
+      "learning_rate": 9.731800766283525e-07,
+      "loss": 0.6306,
+      "step": 36
+    },
+    {
+      "epoch": 1.2730666666666668,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.693486590038313e-07,
+      "loss": 0.6343,
+      "step": 37
+    },
+    {
+      "epoch": 1.3072,
+      "grad_norm": 1.5,
+      "learning_rate": 9.655172413793103e-07,
+      "loss": 0.6397,
+      "step": 38
+    },
+    {
+      "epoch": 1.3413333333333333,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.616858237547893e-07,
+      "loss": 0.6536,
+      "step": 39
+    },
+    {
+      "epoch": 1.3754666666666666,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.578544061302681e-07,
+      "loss": 0.6857,
+      "step": 40
+    },
+    {
+      "epoch": 1.4096,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.540229885057471e-07,
+      "loss": 0.6381,
+      "step": 41
+    },
+    {
+      "epoch": 1.4437333333333333,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.50191570881226e-07,
+      "loss": 0.6301,
+      "step": 42
+    },
+    {
+      "epoch": 1.4778666666666667,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.463601532567049e-07,
+      "loss": 0.6432,
+      "step": 43
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.425287356321838e-07,
+      "loss": 0.6236,
+      "step": 44
+    },
+    {
+      "epoch": 1.5461333333333334,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.386973180076628e-07,
+      "loss": 0.6525,
+      "step": 45
+    },
+    {
+      "epoch": 1.5802666666666667,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.348659003831417e-07,
+      "loss": 0.6455,
+      "step": 46
+    },
+    {
+      "epoch": 1.6143999999999998,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.310344827586206e-07,
+      "loss": 0.6134,
+      "step": 47
+    },
+    {
+      "epoch": 1.6485333333333334,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.272030651340996e-07,
+      "loss": 0.674,
+      "step": 48
+    },
+    {
+      "epoch": 1.6826666666666665,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.233716475095785e-07,
+      "loss": 0.6919,
+      "step": 49
+    },
+    {
+      "epoch": 1.7168,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.195402298850574e-07,
+      "loss": 0.6323,
+      "step": 50
+    },
+    {
+      "epoch": 1.7509333333333332,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.157088122605363e-07,
+      "loss": 0.6359,
+      "step": 51
+    },
+    {
+      "epoch": 1.7850666666666668,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.118773946360153e-07,
+      "loss": 0.6329,
+      "step": 52
+    },
+    {
+      "epoch": 1.8192,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.080459770114942e-07,
+      "loss": 0.6481,
+      "step": 53
+    },
+    {
+      "epoch": 1.8533333333333335,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.042145593869731e-07,
+      "loss": 0.6458,
+      "step": 54
+    },
+    {
+      "epoch": 1.8874666666666666,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.003831417624521e-07,
+      "loss": 0.6262,
+      "step": 55
+    },
+    {
+      "epoch": 1.9216,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.96551724137931e-07,
+      "loss": 0.5932,
+      "step": 56
+    },
+    {
+      "epoch": 1.9557333333333333,
+      "grad_norm": 1.5546875,
+      "learning_rate": 8.927203065134099e-07,
+      "loss": 0.639,
+      "step": 57
+    },
+    {
+      "epoch": 1.9898666666666667,
+      "grad_norm": 1.578125,
+      "learning_rate": 8.888888888888888e-07,
+      "loss": 0.6974,
+      "step": 58
+    },
+    {
+      "epoch": 2.034133333333333,
+      "grad_norm": 3.15625,
+      "learning_rate": 8.850574712643678e-07,
+      "loss": 1.278,
+      "step": 59
+    },
+    {
+      "epoch": 2.0682666666666667,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.812260536398467e-07,
+      "loss": 0.6448,
+      "step": 60
+    },
+    {
+      "epoch": 2.1024,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.773946360153256e-07,
+      "loss": 0.6189,
+      "step": 61
+    },
+    {
+      "epoch": 2.1365333333333334,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.735632183908046e-07,
+      "loss": 0.6928,
+      "step": 62
+    },
+    {
+      "epoch": 2.1706666666666665,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.697318007662835e-07,
+      "loss": 0.6655,
+      "step": 63
+    },
+    {
+      "epoch": 2.2048,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.659003831417624e-07,
+      "loss": 0.5869,
+      "step": 64
+    },
+    {
+      "epoch": 2.238933333333333,
+      "grad_norm": 1.5703125,
+      "learning_rate": 8.620689655172412e-07,
+      "loss": 0.6216,
+      "step": 65
+    },
+    {
+      "epoch": 2.273066666666667,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.582375478927202e-07,
+      "loss": 0.6275,
+      "step": 66
+    },
+    {
+      "epoch": 2.3072,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.544061302681991e-07,
+      "loss": 0.6295,
+      "step": 67
+    },
+    {
+      "epoch": 2.3413333333333335,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.50574712643678e-07,
+      "loss": 0.6624,
+      "step": 68
+    },
+    {
+      "epoch": 2.3754666666666666,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.46743295019157e-07,
+      "loss": 0.6656,
+      "step": 69
+    },
+    {
+      "epoch": 2.4096,
+      "grad_norm": 1.6015625,
+      "learning_rate": 8.429118773946359e-07,
+      "loss": 0.6347,
+      "step": 70
+    },
+    {
+      "epoch": 2.4437333333333333,
+      "grad_norm": 1.4375,
+      "learning_rate": 8.390804597701148e-07,
+      "loss": 0.6198,
+      "step": 71
+    },
+    {
+      "epoch": 2.4778666666666664,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.352490421455939e-07,
+      "loss": 0.6345,
+      "step": 72
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 1.4375,
+      "learning_rate": 8.314176245210728e-07,
+      "loss": 0.6262,
+      "step": 73
+    },
+    {
+      "epoch": 2.5461333333333336,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.275862068965517e-07,
+      "loss": 0.6306,
+      "step": 74
+    },
+    {
+      "epoch": 2.5802666666666667,
+      "grad_norm": 1.5,
+      "learning_rate": 8.237547892720306e-07,
+      "loss": 0.6323,
+      "step": 75
+    },
+    {
+      "epoch": 2.6144,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.199233716475096e-07,
+      "loss": 0.6105,
+      "step": 76
+    },
+    {
+      "epoch": 2.6485333333333334,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.160919540229885e-07,
+      "loss": 0.6483,
+      "step": 77
+    },
+    {
+      "epoch": 2.6826666666666665,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.122605363984674e-07,
+      "loss": 0.6103,
+      "step": 78
+    },
+    {
+      "epoch": 2.7168,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.084291187739464e-07,
+      "loss": 0.6399,
+      "step": 79
+    },
+    {
+      "epoch": 2.7509333333333332,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.045977011494253e-07,
+      "loss": 0.6818,
+      "step": 80
+    },
+    {
+      "epoch": 2.785066666666667,
+      "grad_norm": 1.4140625,
+      "learning_rate": 8.007662835249042e-07,
+      "loss": 0.6503,
+      "step": 81
+    },
+    {
+      "epoch": 2.8192,
+      "grad_norm": 1.4765625,
+      "learning_rate": 7.969348659003831e-07,
+      "loss": 0.6264,
+      "step": 82
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.931034482758621e-07,
+      "loss": 0.6276,
+      "step": 83
+    },
+    {
+      "epoch": 2.8874666666666666,
+      "grad_norm": 1.5390625,
+      "learning_rate": 7.89272030651341e-07,
+      "loss": 0.6959,
+      "step": 84
+    },
+    {
+      "epoch": 2.9215999999999998,
+      "grad_norm": 1.3671875,
+      "learning_rate": 7.854406130268199e-07,
+      "loss": 0.6187,
+      "step": 85
+    },
+    {
+      "epoch": 2.9557333333333333,
+      "grad_norm": 1.3359375,
+      "learning_rate": 7.816091954022989e-07,
+      "loss": 0.6249,
+      "step": 86
+    },
+    {
+      "epoch": 2.989866666666667,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.777777777777778e-07,
+      "loss": 0.6371,
+      "step": 87
+    },
+    {
+      "epoch": 3.034133333333333,
+      "grad_norm": 3.171875,
+      "learning_rate": 7.739463601532567e-07,
+      "loss": 1.3335,
+      "step": 88
+    },
+    {
+      "epoch": 3.0682666666666667,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.701149425287356e-07,
+      "loss": 0.6225,
+      "step": 89
+    },
+    {
+      "epoch": 3.1024,
+      "grad_norm": 1.3984375,
+      "learning_rate": 7.662835249042146e-07,
+      "loss": 0.6191,
+      "step": 90
+    },
+    {
+      "epoch": 3.1365333333333334,
+      "grad_norm": 1.4140625,
+      "learning_rate": 7.624521072796935e-07,
+      "loss": 0.6146,
+      "step": 91
+    },
+    {
+      "epoch": 3.1706666666666665,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.586206896551724e-07,
+      "loss": 0.6388,
+      "step": 92
+    },
+    {
+      "epoch": 3.2048,
+      "grad_norm": 1.515625,
+      "learning_rate": 7.547892720306514e-07,
+      "loss": 0.6625,
+      "step": 93
+    },
+    {
+      "epoch": 3.238933333333333,
+      "grad_norm": 1.28125,
+      "learning_rate": 7.509578544061303e-07,
+      "loss": 0.632,
+      "step": 94
+    },
+    {
+      "epoch": 3.273066666666667,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.471264367816092e-07,
+      "loss": 0.6503,
+      "step": 95
+    },
+    {
+      "epoch": 3.3072,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.432950191570882e-07,
+      "loss": 0.6422,
+      "step": 96
+    },
+    {
+      "epoch": 3.3413333333333335,
+      "grad_norm": 1.421875,
+      "learning_rate": 7.394636015325671e-07,
+      "loss": 0.6298,
+      "step": 97
+    },
+    {
+      "epoch": 3.3754666666666666,
+      "grad_norm": 1.3984375,
+      "learning_rate": 7.35632183908046e-07,
+      "loss": 0.6569,
+      "step": 98
+    },
+    {
+      "epoch": 3.4096,
+      "grad_norm": 1.4921875,
+      "learning_rate": 7.318007662835249e-07,
+      "loss": 0.6449,
+      "step": 99
+    },
+    {
+      "epoch": 3.4437333333333333,
+      "grad_norm": 1.3984375,
+      "learning_rate": 7.279693486590039e-07,
+      "loss": 0.6673,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 290,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.588607272209613e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1663b29e6a330e700089ce4e183600526d393875623a97e080b5ca64c90a8dee
+size 5752