Training in progress, step 500, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

last-checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543c01ec2228fb2ba44250ef67c10491417bb2af81d7bf9fab335938c4948e5e
+size 2384234968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe5cb03139112001a3d49ce1fb075dda67282b061031040c354fa78f99639b2
+size 4768662910

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20343d345ab4506d850d027127c440e50f1e76aeb80866fae355fdd527297de3
+size 1064

last-checkpoint/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
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
+size 11422932

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "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
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,484 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.23312740412635505,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004662548082527101,
+      "grad_norm": 11.413495063781738,
+      "learning_rate": 2.0930232558139536e-06,
+      "loss": 2.1997,
+      "mean_token_accuracy": 0.6332681007683277,
+      "num_tokens": 40960.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.009325096165054203,
+      "grad_norm": 3.026613235473633,
+      "learning_rate": 4.418604651162791e-06,
+      "loss": 0.2202,
+      "mean_token_accuracy": 0.9591976493597031,
+      "num_tokens": 81920.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.013987644247581303,
+      "grad_norm": 3.188910484313965,
+      "learning_rate": 6.744186046511629e-06,
+      "loss": 0.1552,
+      "mean_token_accuracy": 0.9727005831897259,
+      "num_tokens": 122880.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.018650192330108405,
+      "grad_norm": 2.405056953430176,
+      "learning_rate": 9.069767441860467e-06,
+      "loss": 0.1617,
+      "mean_token_accuracy": 0.970401169359684,
+      "num_tokens": 163840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.023312740412635504,
+      "grad_norm": 1.8522473573684692,
+      "learning_rate": 1.1395348837209304e-05,
+      "loss": 0.1483,
+      "mean_token_accuracy": 0.9725293517112732,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.027975288495162606,
+      "grad_norm": 2.335966110229492,
+      "learning_rate": 1.372093023255814e-05,
+      "loss": 0.162,
+      "mean_token_accuracy": 0.9705968640744687,
+      "num_tokens": 245760.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.032637836577689705,
+      "grad_norm": 1.632568120956421,
+      "learning_rate": 1.6046511627906977e-05,
+      "loss": 0.15,
+      "mean_token_accuracy": 0.9726516589522362,
+      "num_tokens": 286720.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.03730038466021681,
+      "grad_norm": 2.076934814453125,
+      "learning_rate": 1.8372093023255815e-05,
+      "loss": 0.15,
+      "mean_token_accuracy": 0.9726027354598046,
+      "num_tokens": 327680.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.04196293274274391,
+      "grad_norm": 1.8859127759933472,
+      "learning_rate": 2.069767441860465e-05,
+      "loss": 0.1511,
+      "mean_token_accuracy": 0.9725048892199993,
+      "num_tokens": 368640.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.04662548082527101,
+      "grad_norm": 1.4506077766418457,
+      "learning_rate": 2.302325581395349e-05,
+      "loss": 0.1525,
+      "mean_token_accuracy": 0.9715508803725242,
+      "num_tokens": 409600.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.051288028907798114,
+      "grad_norm": 2.4370200634002686,
+      "learning_rate": 2.5348837209302327e-05,
+      "loss": 0.1562,
+      "mean_token_accuracy": 0.9715753376483918,
+      "num_tokens": 450560.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.05595057699032521,
+      "grad_norm": 1.9207055568695068,
+      "learning_rate": 2.7674418604651166e-05,
+      "loss": 0.1674,
+      "mean_token_accuracy": 0.9695450030267239,
+      "num_tokens": 491520.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.06061312507285231,
+      "grad_norm": 1.4174894094467163,
+      "learning_rate": 3e-05,
+      "loss": 0.1588,
+      "mean_token_accuracy": 0.9711594931781292,
+      "num_tokens": 532480.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.06527567315537941,
+      "grad_norm": 1.8064192533493042,
+      "learning_rate": 3.2325581395348836e-05,
+      "loss": 0.148,
+      "mean_token_accuracy": 0.9740459866821766,
+      "num_tokens": 573440.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.06993822123790652,
+      "grad_norm": 1.877570390701294,
+      "learning_rate": 3.465116279069768e-05,
+      "loss": 0.1688,
+      "mean_token_accuracy": 0.9682485282421112,
+      "num_tokens": 614400.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.07460076932043362,
+      "grad_norm": 1.4343609809875488,
+      "learning_rate": 3.697674418604651e-05,
+      "loss": 0.1563,
+      "mean_token_accuracy": 0.9713551811873913,
+      "num_tokens": 655360.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.07926331740296072,
+      "grad_norm": 1.804133653640747,
+      "learning_rate": 3.930232558139535e-05,
+      "loss": 0.1554,
+      "mean_token_accuracy": 0.9715264171361924,
+      "num_tokens": 696320.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.08392586548548782,
+      "grad_norm": 1.6452622413635254,
+      "learning_rate": 4.162790697674418e-05,
+      "loss": 0.1582,
+      "mean_token_accuracy": 0.9704745568335056,
+      "num_tokens": 737280.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.08858841356801492,
+      "grad_norm": 1.8188875913619995,
+      "learning_rate": 4.395348837209303e-05,
+      "loss": 0.1712,
+      "mean_token_accuracy": 0.9682240694761276,
+      "num_tokens": 778240.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.09325096165054202,
+      "grad_norm": 1.1670570373535156,
+      "learning_rate": 4.627906976744186e-05,
+      "loss": 0.1601,
+      "mean_token_accuracy": 0.9712084129452705,
+      "num_tokens": 819200.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.09791350973306913,
+      "grad_norm": 1.4625047445297241,
+      "learning_rate": 4.86046511627907e-05,
+      "loss": 0.1783,
+      "mean_token_accuracy": 0.9678082153201103,
+      "num_tokens": 860160.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.10257605781559623,
+      "grad_norm": 1.5419492721557617,
+      "learning_rate": 4.9896319336443754e-05,
+      "loss": 0.1683,
+      "mean_token_accuracy": 0.9691291511058807,
+      "num_tokens": 901120.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.10723860589812333,
+      "grad_norm": 1.2325941324234009,
+      "learning_rate": 4.963711767755314e-05,
+      "loss": 0.1699,
+      "mean_token_accuracy": 0.9690313078463078,
+      "num_tokens": 942080.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.11190115398065043,
+      "grad_norm": 1.3551839590072632,
+      "learning_rate": 4.9377916018662525e-05,
+      "loss": 0.1711,
+      "mean_token_accuracy": 0.9692270018160343,
+      "num_tokens": 983040.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.11656370206317752,
+      "grad_norm": 0.9003294110298157,
+      "learning_rate": 4.9118714359771904e-05,
+      "loss": 0.1642,
+      "mean_token_accuracy": 0.9703767098486423,
+      "num_tokens": 1024000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.12122625014570462,
+      "grad_norm": 1.07398521900177,
+      "learning_rate": 4.885951270088129e-05,
+      "loss": 0.1796,
+      "mean_token_accuracy": 0.9677592895925045,
+      "num_tokens": 1064960.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.12588879822823174,
+      "grad_norm": 0.9522043466567993,
+      "learning_rate": 4.860031104199067e-05,
+      "loss": 0.1711,
+      "mean_token_accuracy": 0.9692025415599346,
+      "num_tokens": 1105920.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.13055134631075882,
+      "grad_norm": 1.098105549812317,
+      "learning_rate": 4.8341109383100054e-05,
+      "loss": 0.1644,
+      "mean_token_accuracy": 0.9703033231198788,
+      "num_tokens": 1146880.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.13521389439328593,
+      "grad_norm": 1.0333844423294067,
+      "learning_rate": 4.808190772420943e-05,
+      "loss": 0.1635,
+      "mean_token_accuracy": 0.9702788636088371,
+      "num_tokens": 1187840.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.13987644247581305,
+      "grad_norm": 1.0744949579238892,
+      "learning_rate": 4.7822706065318826e-05,
+      "loss": 0.1773,
+      "mean_token_accuracy": 0.967441288381815,
+      "num_tokens": 1228800.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.14453899055834013,
+      "grad_norm": 1.3253214359283447,
+      "learning_rate": 4.7563504406428204e-05,
+      "loss": 0.1693,
+      "mean_token_accuracy": 0.9699119344353676,
+      "num_tokens": 1269760.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.14920153864086724,
+      "grad_norm": 0.9514919519424438,
+      "learning_rate": 4.730430274753759e-05,
+      "loss": 0.1644,
+      "mean_token_accuracy": 0.9707191742956638,
+      "num_tokens": 1310720.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.15386408672339433,
+      "grad_norm": 0.8925274610519409,
+      "learning_rate": 4.704510108864697e-05,
+      "loss": 0.1725,
+      "mean_token_accuracy": 0.9697651624679565,
+      "num_tokens": 1351680.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.15852663480592144,
+      "grad_norm": 1.496803641319275,
+      "learning_rate": 4.6785899429756355e-05,
+      "loss": 0.1786,
+      "mean_token_accuracy": 0.96783267557621,
+      "num_tokens": 1392640.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.16318918288844853,
+      "grad_norm": 1.119128704071045,
+      "learning_rate": 4.6526697770865733e-05,
+      "loss": 0.1732,
+      "mean_token_accuracy": 0.9690068483352661,
+      "num_tokens": 1433600.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.16785173097097564,
+      "grad_norm": 0.8431158661842346,
+      "learning_rate": 4.626749611197512e-05,
+      "loss": 0.1762,
+      "mean_token_accuracy": 0.9682729922235012,
+      "num_tokens": 1474560.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.17251427905350275,
+      "grad_norm": 1.0234483480453491,
+      "learning_rate": 4.60082944530845e-05,
+      "loss": 0.1573,
+      "mean_token_accuracy": 0.9715019583702087,
+      "num_tokens": 1515520.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.17717682713602984,
+      "grad_norm": 0.8898618817329407,
+      "learning_rate": 4.574909279419389e-05,
+      "loss": 0.1765,
+      "mean_token_accuracy": 0.9686399199068546,
+      "num_tokens": 1556480.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.18183937521855695,
+      "grad_norm": 0.7379114627838135,
+      "learning_rate": 4.548989113530327e-05,
+      "loss": 0.166,
+      "mean_token_accuracy": 0.9697896264493465,
+      "num_tokens": 1597440.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.18650192330108403,
+      "grad_norm": 1.0399589538574219,
+      "learning_rate": 4.5230689476412655e-05,
+      "loss": 0.1745,
+      "mean_token_accuracy": 0.9686154551804066,
+      "num_tokens": 1638400.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.19116447138361115,
+      "grad_norm": 1.3671499490737915,
+      "learning_rate": 4.4971487817522034e-05,
+      "loss": 0.1887,
+      "mean_token_accuracy": 0.9650684870779515,
+      "num_tokens": 1679360.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.19582701946613826,
+      "grad_norm": 1.037642002105713,
+      "learning_rate": 4.471228615863142e-05,
+      "loss": 0.1781,
+      "mean_token_accuracy": 0.9675146743655205,
+      "num_tokens": 1720320.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.20048956754866534,
+      "grad_norm": 1.0587457418441772,
+      "learning_rate": 4.44530844997408e-05,
+      "loss": 0.168,
+      "mean_token_accuracy": 0.9690557658672333,
+      "num_tokens": 1761280.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.20515211563119246,
+      "grad_norm": 0.9384447336196899,
+      "learning_rate": 4.4193882840850184e-05,
+      "loss": 0.1777,
+      "mean_token_accuracy": 0.9680772960186005,
+      "num_tokens": 1802240.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.20981466371371954,
+      "grad_norm": 0.9823533296585083,
+      "learning_rate": 4.393468118195957e-05,
+      "loss": 0.1753,
+      "mean_token_accuracy": 0.9683463744819164,
+      "num_tokens": 1843200.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.21447721179624665,
+      "grad_norm": 0.6335959434509277,
+      "learning_rate": 4.367547952306895e-05,
+      "loss": 0.1682,
+      "mean_token_accuracy": 0.96954500451684,
+      "num_tokens": 1884160.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.21913975987877374,
+      "grad_norm": 1.4692820310592651,
+      "learning_rate": 4.3416277864178334e-05,
+      "loss": 0.1766,
+      "mean_token_accuracy": 0.9676614463329315,
+      "num_tokens": 1925120.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.22380230796130085,
+      "grad_norm": 0.973223865032196,
+      "learning_rate": 4.315707620528772e-05,
+      "loss": 0.1768,
+      "mean_token_accuracy": 0.9680039100348949,
+      "num_tokens": 1966080.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.22846485604382796,
+      "grad_norm": 0.924390435218811,
+      "learning_rate": 4.28978745463971e-05,
+      "loss": 0.1748,
+      "mean_token_accuracy": 0.968713304400444,
+      "num_tokens": 2007040.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.23312740412635505,
+      "grad_norm": 0.9293317198753357,
+      "learning_rate": 4.2638672887506484e-05,
+      "loss": 0.1946,
+      "mean_token_accuracy": 0.9643835619091987,
+      "num_tokens": 2048000.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2144,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5412464099328000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb813fb05789abd9bb3026e3ed71e9943229113479e527e21360eea8a63e5e1
+size 5624