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:be092fdfdc460247662cacd4da8ff504a6a0561f4f03040b9ef347f037c3f739
+size 2384234968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed805e56c5830e1ee97f469c48c6947c0c6103c64ea445e4a9d3c8ac5f3b530
+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 sha256:4bd481860fc6c239d6ebe5da0e788d01da0ccd2a9d1d1ce20061b2fe36d8c1ec
+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": 0.3424950766332734,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0068499015326654675,
+      "grad_norm": 7.228954315185547,
+      "learning_rate": 3.0821917808219177e-06,
+      "loss": 1.9403,
+      "mean_token_accuracy": 0.6755136996507645,
+      "num_tokens": 40960.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.013699803065330935,
+      "grad_norm": 2.0438427925109863,
+      "learning_rate": 6.506849315068493e-06,
+      "loss": 0.1596,
+      "mean_token_accuracy": 0.9705234840512276,
+      "num_tokens": 81920.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.020549704597996404,
+      "grad_norm": 2.666701316833496,
+      "learning_rate": 9.931506849315069e-06,
+      "loss": 0.1364,
+      "mean_token_accuracy": 0.9744618371129036,
+      "num_tokens": 122880.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.02739960613066187,
+      "grad_norm": 1.958240032196045,
+      "learning_rate": 1.3356164383561646e-05,
+      "loss": 0.1287,
+      "mean_token_accuracy": 0.9761741667985916,
+      "num_tokens": 163840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.03424950766332734,
+      "grad_norm": 2.09761118888855,
+      "learning_rate": 1.678082191780822e-05,
+      "loss": 0.1293,
+      "mean_token_accuracy": 0.9761252395808697,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.04109940919599281,
+      "grad_norm": 2.6515567302703857,
+      "learning_rate": 2.0205479452054797e-05,
+      "loss": 0.135,
+      "mean_token_accuracy": 0.9750733785331249,
+      "num_tokens": 245760.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.047949310728658275,
+      "grad_norm": 1.7713321447372437,
+      "learning_rate": 2.363013698630137e-05,
+      "loss": 0.1296,
+      "mean_token_accuracy": 0.9753669239580631,
+      "num_tokens": 286720.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.05479921226132374,
+      "grad_norm": 2.5610976219177246,
+      "learning_rate": 2.7054794520547947e-05,
+      "loss": 0.1303,
+      "mean_token_accuracy": 0.9758806236088275,
+      "num_tokens": 327680.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.06164911379398921,
+      "grad_norm": 1.8631649017333984,
+      "learning_rate": 3.047945205479452e-05,
+      "loss": 0.1403,
+      "mean_token_accuracy": 0.9741682976484298,
+      "num_tokens": 368640.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.06849901532665469,
+      "grad_norm": 1.862723469734192,
+      "learning_rate": 3.39041095890411e-05,
+      "loss": 0.1388,
+      "mean_token_accuracy": 0.9738502882421016,
+      "num_tokens": 409600.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.07534891685932014,
+      "grad_norm": 1.824814796447754,
+      "learning_rate": 3.7328767123287675e-05,
+      "loss": 0.1386,
+      "mean_token_accuracy": 0.9734833627939224,
+      "num_tokens": 450560.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.08219881839198562,
+      "grad_norm": 1.6686910390853882,
+      "learning_rate": 4.075342465753425e-05,
+      "loss": 0.1405,
+      "mean_token_accuracy": 0.9753913849592208,
+      "num_tokens": 491520.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.08904871992465108,
+      "grad_norm": 1.7950955629348755,
+      "learning_rate": 4.417808219178082e-05,
+      "loss": 0.1371,
+      "mean_token_accuracy": 0.973972600698471,
+      "num_tokens": 532480.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.09589862145731655,
+      "grad_norm": 1.4279956817626953,
+      "learning_rate": 4.7602739726027403e-05,
+      "loss": 0.1462,
+      "mean_token_accuracy": 0.9723336577415467,
+      "num_tokens": 573440.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.10274852298998202,
+      "grad_norm": 1.1169788837432861,
+      "learning_rate": 4.988575780654989e-05,
+      "loss": 0.1489,
+      "mean_token_accuracy": 0.9726272001862526,
+      "num_tokens": 614400.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.10959842452264748,
+      "grad_norm": 1.2573721408843994,
+      "learning_rate": 4.950495049504951e-05,
+      "loss": 0.1411,
+      "mean_token_accuracy": 0.9747798435389996,
+      "num_tokens": 655360.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.11644832605531295,
+      "grad_norm": 1.3669424057006836,
+      "learning_rate": 4.912414318354912e-05,
+      "loss": 0.1376,
+      "mean_token_accuracy": 0.9747553795576096,
+      "num_tokens": 696320.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.12329822758797843,
+      "grad_norm": 1.292544960975647,
+      "learning_rate": 4.8743335872048744e-05,
+      "loss": 0.1616,
+      "mean_token_accuracy": 0.9711105652153492,
+      "num_tokens": 737280.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.13014812912064389,
+      "grad_norm": 1.3793798685073853,
+      "learning_rate": 4.8362528560548366e-05,
+      "loss": 0.1436,
+      "mean_token_accuracy": 0.9736790612339974,
+      "num_tokens": 778240.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.13699803065330937,
+      "grad_norm": 1.4192166328430176,
+      "learning_rate": 4.798172124904798e-05,
+      "loss": 0.1508,
+      "mean_token_accuracy": 0.9721379615366459,
+      "num_tokens": 819200.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.14384793218597483,
+      "grad_norm": 0.9240191578865051,
+      "learning_rate": 4.76009139375476e-05,
+      "loss": 0.1504,
+      "mean_token_accuracy": 0.9727739751338959,
+      "num_tokens": 860160.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.1506978337186403,
+      "grad_norm": 1.2324212789535522,
+      "learning_rate": 4.7220106626047223e-05,
+      "loss": 0.1478,
+      "mean_token_accuracy": 0.9731898196041584,
+      "num_tokens": 901120.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.15754773525130578,
+      "grad_norm": 0.9403596520423889,
+      "learning_rate": 4.6839299314546845e-05,
+      "loss": 0.1505,
+      "mean_token_accuracy": 0.9722358077764511,
+      "num_tokens": 942080.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.16439763678397123,
+      "grad_norm": 1.3236258029937744,
+      "learning_rate": 4.645849200304646e-05,
+      "loss": 0.1581,
+      "mean_token_accuracy": 0.9712084129452705,
+      "num_tokens": 983040.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.1712475383166367,
+      "grad_norm": 0.9371373653411865,
+      "learning_rate": 4.607768469154608e-05,
+      "loss": 0.1465,
+      "mean_token_accuracy": 0.9727005869150162,
+      "num_tokens": 1024000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.17809743984930215,
+      "grad_norm": 1.0923305749893188,
+      "learning_rate": 4.56968773800457e-05,
+      "loss": 0.147,
+      "mean_token_accuracy": 0.9735812105238437,
+      "num_tokens": 1064960.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.18494734138196764,
+      "grad_norm": 1.3869222402572632,
+      "learning_rate": 4.531607006854532e-05,
+      "loss": 0.1525,
+      "mean_token_accuracy": 0.9721379593014717,
+      "num_tokens": 1105920.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.1917972429146331,
+      "grad_norm": 0.9886603951454163,
+      "learning_rate": 4.493526275704494e-05,
+      "loss": 0.154,
+      "mean_token_accuracy": 0.9713551826775074,
+      "num_tokens": 1146880.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.19864714444729856,
+      "grad_norm": 0.9658203721046448,
+      "learning_rate": 4.455445544554456e-05,
+      "loss": 0.1495,
+      "mean_token_accuracy": 0.9729207411408425,
+      "num_tokens": 1187840.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.20549704597996404,
+      "grad_norm": 0.9130630493164062,
+      "learning_rate": 4.4173648134044175e-05,
+      "loss": 0.1514,
+      "mean_token_accuracy": 0.9714774928987027,
+      "num_tokens": 1228800.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.2123469475126295,
+      "grad_norm": 0.7772193551063538,
+      "learning_rate": 4.3792840822543796e-05,
+      "loss": 0.146,
+      "mean_token_accuracy": 0.9719911932945251,
+      "num_tokens": 1269760.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.21919684904529496,
+      "grad_norm": 0.8756822347640991,
+      "learning_rate": 4.341203351104342e-05,
+      "loss": 0.1518,
+      "mean_token_accuracy": 0.9728718154132366,
+      "num_tokens": 1310720.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.22604675057796045,
+      "grad_norm": 0.7406238913536072,
+      "learning_rate": 4.303122619954303e-05,
+      "loss": 0.1447,
+      "mean_token_accuracy": 0.9732876688241958,
+      "num_tokens": 1351680.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.2328966521106259,
+      "grad_norm": 0.8166679739952087,
+      "learning_rate": 4.2650418888042654e-05,
+      "loss": 0.1528,
+      "mean_token_accuracy": 0.9725782759487629,
+      "num_tokens": 1392640.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.23974655364329137,
+      "grad_norm": 0.8173955082893372,
+      "learning_rate": 4.2269611576542275e-05,
+      "loss": 0.1504,
+      "mean_token_accuracy": 0.9733365930616855,
+      "num_tokens": 1433600.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.24659645517595685,
+      "grad_norm": 1.621888518333435,
+      "learning_rate": 4.188880426504189e-05,
+      "loss": 0.1505,
+      "mean_token_accuracy": 0.972700584679842,
+      "num_tokens": 1474560.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.2534463567086223,
+      "grad_norm": 0.9569937586784363,
+      "learning_rate": 4.150799695354151e-05,
+      "loss": 0.1499,
+      "mean_token_accuracy": 0.9727495074272156,
+      "num_tokens": 1515520.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.26029625824128777,
+      "grad_norm": 0.85816490650177,
+      "learning_rate": 4.112718964204113e-05,
+      "loss": 0.1391,
+      "mean_token_accuracy": 0.9745596811175347,
+      "num_tokens": 1556480.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.26714615977395323,
+      "grad_norm": 0.9886700510978699,
+      "learning_rate": 4.074638233054075e-05,
+      "loss": 0.1501,
+      "mean_token_accuracy": 0.9725048922002315,
+      "num_tokens": 1597440.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.27399606130661874,
+      "grad_norm": 1.0124937295913696,
+      "learning_rate": 4.036557501904037e-05,
+      "loss": 0.1468,
+      "mean_token_accuracy": 0.973581213504076,
+      "num_tokens": 1638400.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.2808459628392842,
+      "grad_norm": 0.8479059934616089,
+      "learning_rate": 3.998476770753999e-05,
+      "loss": 0.1485,
+      "mean_token_accuracy": 0.9728962764143944,
+      "num_tokens": 1679360.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.28769586437194966,
+      "grad_norm": 0.7756571173667908,
+      "learning_rate": 3.9603960396039605e-05,
+      "loss": 0.1455,
+      "mean_token_accuracy": 0.9734344355762005,
+      "num_tokens": 1720320.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.2945457659046151,
+      "grad_norm": 1.327717900276184,
+      "learning_rate": 3.922315308453923e-05,
+      "loss": 0.1355,
+      "mean_token_accuracy": 0.9750244557857514,
+      "num_tokens": 1761280.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.3013956674372806,
+      "grad_norm": 0.7622424960136414,
+      "learning_rate": 3.884234577303885e-05,
+      "loss": 0.1576,
+      "mean_token_accuracy": 0.970841483771801,
+      "num_tokens": 1802240.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.30824556896994604,
+      "grad_norm": 0.8018739819526672,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 0.1443,
+      "mean_token_accuracy": 0.9734099790453911,
+      "num_tokens": 1843200.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.31509547050261155,
+      "grad_norm": 0.7922894358634949,
+      "learning_rate": 3.8080731150038084e-05,
+      "loss": 0.1413,
+      "mean_token_accuracy": 0.9735322877764702,
+      "num_tokens": 1884160.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.321945372035277,
+      "grad_norm": 1.5768623352050781,
+      "learning_rate": 3.7699923838537706e-05,
+      "loss": 0.1447,
+      "mean_token_accuracy": 0.9738502897322178,
+      "num_tokens": 1925120.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.32879527356794247,
+      "grad_norm": 1.3384929895401,
+      "learning_rate": 3.731911652703732e-05,
+      "loss": 0.1421,
+      "mean_token_accuracy": 0.9732142813503742,
+      "num_tokens": 1966080.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.33564517510060793,
+      "grad_norm": 0.6923882365226746,
+      "learning_rate": 3.693830921553694e-05,
+      "loss": 0.1521,
+      "mean_token_accuracy": 0.9728228941559791,
+      "num_tokens": 2007040.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.3424950766332734,
+      "grad_norm": 0.9716359376907349,
+      "learning_rate": 3.655750190403656e-05,
+      "loss": 0.1446,
+      "mean_token_accuracy": 0.973679056763649,
+      "num_tokens": 2048000.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1459,
+  "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 sha256:98363cee36ba7d96c31ce6bb8d6006adba3095cc09bec2b564b23681afdeae90
+size 5624