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:b1527b36f322772ceed414a72fdaab86725572b37db9c497d13237d6e28c42b7
+size 2384234968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85fd8c515f5e316201b0cf42627973016f759269b41b78e6a8a92757f02ff58
+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:df5d3a70c0852d4db63cc457d8b0a5e781ff9531b1d36f260607cfb207306039
+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": 0.8069396812588259,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016138793625176517,
+      "grad_norm": 3.143124580383301,
+      "learning_rate": 7.258064516129033e-06,
+      "loss": 1.6561,
+      "mean_token_accuracy": 0.7124999972060323,
+      "num_tokens": 40960.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.03227758725035303,
+      "grad_norm": 2.3436570167541504,
+      "learning_rate": 1.5322580645161292e-05,
+      "loss": 0.1926,
+      "mean_token_accuracy": 0.966169273853302,
+      "num_tokens": 81920.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.048416380875529554,
+      "grad_norm": 3.512237071990967,
+      "learning_rate": 2.338709677419355e-05,
+      "loss": 0.1742,
+      "mean_token_accuracy": 0.9685420736670494,
+      "num_tokens": 122880.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06455517450070607,
+      "grad_norm": 2.72192645072937,
+      "learning_rate": 3.1451612903225806e-05,
+      "loss": 0.1687,
+      "mean_token_accuracy": 0.9700342424213886,
+      "num_tokens": 163840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.08069396812588259,
+      "grad_norm": 2.1354479789733887,
+      "learning_rate": 3.951612903225806e-05,
+      "loss": 0.1726,
+      "mean_token_accuracy": 0.9692270033061504,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09683276175105911,
+      "grad_norm": 3.7211921215057373,
+      "learning_rate": 4.7580645161290326e-05,
+      "loss": 0.1884,
+      "mean_token_accuracy": 0.9661448106169701,
+      "num_tokens": 245760.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.11297155537623563,
+      "grad_norm": 1.5104479789733887,
+      "learning_rate": 4.937163375224417e-05,
+      "loss": 0.1869,
+      "mean_token_accuracy": 0.9675391376018524,
+      "num_tokens": 286720.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12911034900141213,
+      "grad_norm": 2.113689422607422,
+      "learning_rate": 4.847396768402155e-05,
+      "loss": 0.1815,
+      "mean_token_accuracy": 0.9682729855179787,
+      "num_tokens": 327680.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.14524914262658867,
+      "grad_norm": 1.308586597442627,
+      "learning_rate": 4.7576301615798926e-05,
+      "loss": 0.1955,
+      "mean_token_accuracy": 0.9657534204423428,
+      "num_tokens": 368640.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.16138793625176517,
+      "grad_norm": 1.7842236757278442,
+      "learning_rate": 4.667863554757631e-05,
+      "loss": 0.1893,
+      "mean_token_accuracy": 0.9666340447962284,
+      "num_tokens": 409600.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1775267298769417,
+      "grad_norm": 1.172074556350708,
+      "learning_rate": 4.578096947935368e-05,
+      "loss": 0.1849,
+      "mean_token_accuracy": 0.9681262239813805,
+      "num_tokens": 450560.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.19366552350211821,
+      "grad_norm": 1.2354941368103027,
+      "learning_rate": 4.488330341113106e-05,
+      "loss": 0.1884,
+      "mean_token_accuracy": 0.9675146743655205,
+      "num_tokens": 491520.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.20980431712729475,
+      "grad_norm": 1.0571320056915283,
+      "learning_rate": 4.398563734290844e-05,
+      "loss": 0.1968,
+      "mean_token_accuracy": 0.9660469628870487,
+      "num_tokens": 532480.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.22594311075247125,
+      "grad_norm": 1.255366563796997,
+      "learning_rate": 4.308797127468582e-05,
+      "loss": 0.1882,
+      "mean_token_accuracy": 0.9669765122234821,
+      "num_tokens": 573440.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.24208190437764776,
+      "grad_norm": 0.7935602068901062,
+      "learning_rate": 4.21903052064632e-05,
+      "loss": 0.189,
+      "mean_token_accuracy": 0.9665362000465393,
+      "num_tokens": 614400.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.25822069800282427,
+      "grad_norm": 1.0346981287002563,
+      "learning_rate": 4.129263913824057e-05,
+      "loss": 0.1911,
+      "mean_token_accuracy": 0.9670254394412041,
+      "num_tokens": 655360.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.27435949162800083,
+      "grad_norm": 1.0733519792556763,
+      "learning_rate": 4.0394973070017954e-05,
+      "loss": 0.1945,
+      "mean_token_accuracy": 0.9651418760418892,
+      "num_tokens": 696320.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.29049828525317734,
+      "grad_norm": 1.1686853170394897,
+      "learning_rate": 3.9497307001795335e-05,
+      "loss": 0.1883,
+      "mean_token_accuracy": 0.9680283769965172,
+      "num_tokens": 737280.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.30663707887835384,
+      "grad_norm": 1.4509366750717163,
+      "learning_rate": 3.859964093357271e-05,
+      "loss": 0.1815,
+      "mean_token_accuracy": 0.9682240642607212,
+      "num_tokens": 778240.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.32277587250353035,
+      "grad_norm": 1.7541567087173462,
+      "learning_rate": 3.770197486535009e-05,
+      "loss": 0.1799,
+      "mean_token_accuracy": 0.9676614426076412,
+      "num_tokens": 819200.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.33891466612870685,
+      "grad_norm": 0.8904175162315369,
+      "learning_rate": 3.6804308797127465e-05,
+      "loss": 0.1789,
+      "mean_token_accuracy": 0.9690802305936813,
+      "num_tokens": 860160.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3550534597538834,
+      "grad_norm": 1.066307783126831,
+      "learning_rate": 3.5906642728904846e-05,
+      "loss": 0.1884,
+      "mean_token_accuracy": 0.967025438696146,
+      "num_tokens": 901120.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3711922533790599,
+      "grad_norm": 0.8745315670967102,
+      "learning_rate": 3.500897666068223e-05,
+      "loss": 0.1873,
+      "mean_token_accuracy": 0.9678571395576,
+      "num_tokens": 942080.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.38733104700423643,
+      "grad_norm": 1.2400248050689697,
+      "learning_rate": 3.411131059245961e-05,
+      "loss": 0.1843,
+      "mean_token_accuracy": 0.9680772952735424,
+      "num_tokens": 983040.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.40346984062941293,
+      "grad_norm": 0.9607365131378174,
+      "learning_rate": 3.321364452423699e-05,
+      "loss": 0.2003,
+      "mean_token_accuracy": 0.9650195680558682,
+      "num_tokens": 1024000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4196086342545895,
+      "grad_norm": 1.288979172706604,
+      "learning_rate": 3.231597845601436e-05,
+      "loss": 0.1874,
+      "mean_token_accuracy": 0.9666095845401287,
+      "num_tokens": 1064960.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.435747427879766,
+      "grad_norm": 1.0444912910461426,
+      "learning_rate": 3.1418312387791744e-05,
+      "loss": 0.2023,
+      "mean_token_accuracy": 0.9641144774854183,
+      "num_tokens": 1105920.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.4518862215049425,
+      "grad_norm": 1.1588054895401,
+      "learning_rate": 3.0520646319569125e-05,
+      "loss": 0.1824,
+      "mean_token_accuracy": 0.9674902133643627,
+      "num_tokens": 1146880.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.468025015130119,
+      "grad_norm": 1.1021692752838135,
+      "learning_rate": 2.96229802513465e-05,
+      "loss": 0.1845,
+      "mean_token_accuracy": 0.9678815990686417,
+      "num_tokens": 1187840.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.4841638087552955,
+      "grad_norm": 1.2420721054077148,
+      "learning_rate": 2.872531418312388e-05,
+      "loss": 0.1975,
+      "mean_token_accuracy": 0.9652152620255947,
+      "num_tokens": 1228800.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.5003026023804721,
+      "grad_norm": 1.1611697673797607,
+      "learning_rate": 2.7827648114901255e-05,
+      "loss": 0.1798,
+      "mean_token_accuracy": 0.9679794535040855,
+      "num_tokens": 1269760.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.5164413960056485,
+      "grad_norm": 0.9205463528633118,
+      "learning_rate": 2.6929982046678636e-05,
+      "loss": 0.1881,
+      "mean_token_accuracy": 0.9673923663794994,
+      "num_tokens": 1310720.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5325801896308251,
+      "grad_norm": 1.0037810802459717,
+      "learning_rate": 2.6032315978456017e-05,
+      "loss": 0.1788,
+      "mean_token_accuracy": 0.9688356101512909,
+      "num_tokens": 1351680.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5487189832560017,
+      "grad_norm": 1.0601574182510376,
+      "learning_rate": 2.5134649910233395e-05,
+      "loss": 0.1839,
+      "mean_token_accuracy": 0.9674412839114666,
+      "num_tokens": 1392640.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5648577768811781,
+      "grad_norm": 1.083649754524231,
+      "learning_rate": 2.4236983842010776e-05,
+      "loss": 0.1866,
+      "mean_token_accuracy": 0.9668052822351456,
+      "num_tokens": 1433600.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5809965705063547,
+      "grad_norm": 0.9604955315589905,
+      "learning_rate": 2.3339317773788153e-05,
+      "loss": 0.1792,
+      "mean_token_accuracy": 0.9675391390919685,
+      "num_tokens": 1474560.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5971353641315311,
+      "grad_norm": 1.1074978113174438,
+      "learning_rate": 2.244165170556553e-05,
+      "loss": 0.19,
+      "mean_token_accuracy": 0.966560660302639,
+      "num_tokens": 1515520.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.6132741577567077,
+      "grad_norm": 1.0041981935501099,
+      "learning_rate": 2.154398563734291e-05,
+      "loss": 0.1958,
+      "mean_token_accuracy": 0.9653864920139312,
+      "num_tokens": 1556480.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6294129513818842,
+      "grad_norm": 0.9702057838439941,
+      "learning_rate": 2.0646319569120286e-05,
+      "loss": 0.1776,
+      "mean_token_accuracy": 0.9691046938300133,
+      "num_tokens": 1597440.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6455517450070607,
+      "grad_norm": 0.767419159412384,
+      "learning_rate": 1.9748653500897668e-05,
+      "loss": 0.1626,
+      "mean_token_accuracy": 0.9722602725028991,
+      "num_tokens": 1638400.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6616905386322373,
+      "grad_norm": 1.132580041885376,
+      "learning_rate": 1.8850987432675045e-05,
+      "loss": 0.1807,
+      "mean_token_accuracy": 0.9676369808614254,
+      "num_tokens": 1679360.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6778293322574137,
+      "grad_norm": 1.1673997640609741,
+      "learning_rate": 1.7953321364452423e-05,
+      "loss": 0.1911,
+      "mean_token_accuracy": 0.9661203488707543,
+      "num_tokens": 1720320.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6939681258825903,
+      "grad_norm": 1.094133734703064,
+      "learning_rate": 1.7055655296229804e-05,
+      "loss": 0.1811,
+      "mean_token_accuracy": 0.9679305233061314,
+      "num_tokens": 1761280.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.7101069195077668,
+      "grad_norm": 0.9924063086509705,
+      "learning_rate": 1.615798922800718e-05,
+      "loss": 0.1657,
+      "mean_token_accuracy": 0.9702054776251317,
+      "num_tokens": 1802240.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.7262457131329433,
+      "grad_norm": 1.4084646701812744,
+      "learning_rate": 1.5260323159784563e-05,
+      "loss": 0.181,
+      "mean_token_accuracy": 0.9674412921071053,
+      "num_tokens": 1843200.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7423845067581198,
+      "grad_norm": 1.202055811882019,
+      "learning_rate": 1.436265709156194e-05,
+      "loss": 0.1733,
+      "mean_token_accuracy": 0.9695694677531719,
+      "num_tokens": 1884160.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7585233003832963,
+      "grad_norm": 0.8700960278511047,
+      "learning_rate": 1.3464991023339318e-05,
+      "loss": 0.1799,
+      "mean_token_accuracy": 0.9682240679860115,
+      "num_tokens": 1925120.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7746620940084729,
+      "grad_norm": 0.9524367451667786,
+      "learning_rate": 1.2567324955116697e-05,
+      "loss": 0.1843,
+      "mean_token_accuracy": 0.9665117390453816,
+      "num_tokens": 1966080.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7908008876336494,
+      "grad_norm": 0.836246132850647,
+      "learning_rate": 1.1669658886894077e-05,
+      "loss": 0.1835,
+      "mean_token_accuracy": 0.9679794497787952,
+      "num_tokens": 2007040.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.8069396812588259,
+      "grad_norm": 0.9284518361091614,
+      "learning_rate": 1.0771992818671454e-05,
+      "loss": 0.1762,
+      "mean_token_accuracy": 0.9691536143422127,
+      "num_tokens": 2048000.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 619,
+  "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 sha256:2cae0e43984705df6456ee4792a79c7338f2cba809541fd7ca92dfab14c7843b
+size 5688