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 sha256:4adbef5233be3e3d84243beedb888b020cc4c29bd207fd9ae3fdd9df6870e8d6
+size 2384234968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a3c9aa35f41d44f954c5fd0fa1bc214b5c8f2c33d80976e177bb0b67762f24
+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:adc02dc4e44614a860545e21da563dad461cc3a594ed7ac914f55bd3f920db08
+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": 0.4917629702483403,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009835259404966806,
+      "grad_norm": 6.6343817710876465,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 1.8551,
+      "mean_token_accuracy": 0.6902152626775205,
+      "num_tokens": 40960.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.01967051880993361,
+      "grad_norm": 2.4751858711242676,
+      "learning_rate": 9.31372549019608e-06,
+      "loss": 0.2496,
+      "mean_token_accuracy": 0.9594422683119774,
+      "num_tokens": 81920.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.029505778214900417,
+      "grad_norm": 2.0798258781433105,
+      "learning_rate": 1.4215686274509804e-05,
+      "loss": 0.2178,
+      "mean_token_accuracy": 0.9631604641675949,
+      "num_tokens": 122880.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03934103761986722,
+      "grad_norm": 1.7059319019317627,
+      "learning_rate": 1.9117647058823528e-05,
+      "loss": 0.1989,
+      "mean_token_accuracy": 0.9659735761582852,
+      "num_tokens": 163840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04917629702483403,
+      "grad_norm": 2.177712917327881,
+      "learning_rate": 2.401960784313726e-05,
+      "loss": 0.2048,
+      "mean_token_accuracy": 0.9650195650756359,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.059011556429800834,
+      "grad_norm": 1.8728467226028442,
+      "learning_rate": 2.8921568627450986e-05,
+      "loss": 0.2007,
+      "mean_token_accuracy": 0.9650440283119679,
+      "num_tokens": 245760.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06884681583476764,
+      "grad_norm": 2.018501043319702,
+      "learning_rate": 3.382352941176471e-05,
+      "loss": 0.1967,
+      "mean_token_accuracy": 0.9661203466355801,
+      "num_tokens": 286720.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.07868207523973444,
+      "grad_norm": 1.6879123449325562,
+      "learning_rate": 3.872549019607844e-05,
+      "loss": 0.2068,
+      "mean_token_accuracy": 0.9635273911058903,
+      "num_tokens": 327680.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.08851733464470125,
+      "grad_norm": 1.6801401376724243,
+      "learning_rate": 4.362745098039216e-05,
+      "loss": 0.1984,
+      "mean_token_accuracy": 0.9664383515715599,
+      "num_tokens": 368640.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.09835259404966806,
+      "grad_norm": 1.5165321826934814,
+      "learning_rate": 4.8529411764705885e-05,
+      "loss": 0.1917,
+      "mean_token_accuracy": 0.9670498959720135,
+      "num_tokens": 409600.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.10818785345463487,
+      "grad_norm": 1.7143133878707886,
+      "learning_rate": 4.961706783369803e-05,
+      "loss": 0.1976,
+      "mean_token_accuracy": 0.9658023424446582,
+      "num_tokens": 450560.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.11802311285960167,
+      "grad_norm": 1.1708303689956665,
+      "learning_rate": 4.9070021881838073e-05,
+      "loss": 0.2047,
+      "mean_token_accuracy": 0.9647504858672619,
+      "num_tokens": 491520.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.12785837226456848,
+      "grad_norm": 1.330039143562317,
+      "learning_rate": 4.852297592997812e-05,
+      "loss": 0.203,
+      "mean_token_accuracy": 0.963454008102417,
+      "num_tokens": 532480.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.13769363166953527,
+      "grad_norm": 1.5339477062225342,
+      "learning_rate": 4.797592997811816e-05,
+      "loss": 0.1958,
+      "mean_token_accuracy": 0.9662671178579331,
+      "num_tokens": 573440.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.1475288910745021,
+      "grad_norm": 1.5175786018371582,
+      "learning_rate": 4.742888402625821e-05,
+      "loss": 0.1956,
+      "mean_token_accuracy": 0.9662426561117172,
+      "num_tokens": 614400.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.1573641504794689,
+      "grad_norm": 1.1754379272460938,
+      "learning_rate": 4.688183807439826e-05,
+      "loss": 0.2027,
+      "mean_token_accuracy": 0.9647504836320877,
+      "num_tokens": 655360.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.1671994098844357,
+      "grad_norm": 0.958105206489563,
+      "learning_rate": 4.63347921225383e-05,
+      "loss": 0.1961,
+      "mean_token_accuracy": 0.9655332624912262,
+      "num_tokens": 696320.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.1770346692894025,
+      "grad_norm": 1.1706628799438477,
+      "learning_rate": 4.578774617067834e-05,
+      "loss": 0.1868,
+      "mean_token_accuracy": 0.967563596367836,
+      "num_tokens": 737280.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.1868699286943693,
+      "grad_norm": 1.4143725633621216,
+      "learning_rate": 4.524070021881838e-05,
+      "loss": 0.1947,
+      "mean_token_accuracy": 0.9658023461699485,
+      "num_tokens": 778240.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.19670518809933613,
+      "grad_norm": 0.9401776194572449,
+      "learning_rate": 4.469365426695843e-05,
+      "loss": 0.2035,
+      "mean_token_accuracy": 0.9653375715017318,
+      "num_tokens": 819200.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.20654044750430292,
+      "grad_norm": 0.9780746698379517,
+      "learning_rate": 4.414660831509847e-05,
+      "loss": 0.1877,
+      "mean_token_accuracy": 0.967000974714756,
+      "num_tokens": 860160.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.21637570690926974,
+      "grad_norm": 1.2982661724090576,
+      "learning_rate": 4.359956236323852e-05,
+      "loss": 0.1831,
+      "mean_token_accuracy": 0.9679060593247414,
+      "num_tokens": 901120.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.22621096631423654,
+      "grad_norm": 0.9432095885276794,
+      "learning_rate": 4.305251641137856e-05,
+      "loss": 0.1869,
+      "mean_token_accuracy": 0.9667318977415562,
+      "num_tokens": 942080.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.23604622571920333,
+      "grad_norm": 1.0005096197128296,
+      "learning_rate": 4.2505470459518606e-05,
+      "loss": 0.1882,
+      "mean_token_accuracy": 0.9674412846565247,
+      "num_tokens": 983040.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.24588148512417016,
+      "grad_norm": 0.8945526480674744,
+      "learning_rate": 4.1958424507658647e-05,
+      "loss": 0.1861,
+      "mean_token_accuracy": 0.9670498959720135,
+      "num_tokens": 1024000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.25571674452913695,
+      "grad_norm": 0.7671024799346924,
+      "learning_rate": 4.1411378555798694e-05,
+      "loss": 0.1843,
+      "mean_token_accuracy": 0.9678082145750523,
+      "num_tokens": 1064960.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.2655520039341038,
+      "grad_norm": 1.0006589889526367,
+      "learning_rate": 4.0864332603938735e-05,
+      "loss": 0.1948,
+      "mean_token_accuracy": 0.9665361948311328,
+      "num_tokens": 1105920.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.27538726333907054,
+      "grad_norm": 0.854852020740509,
+      "learning_rate": 4.0317286652078776e-05,
+      "loss": 0.1815,
+      "mean_token_accuracy": 0.9685909926891327,
+      "num_tokens": 1146880.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.28522252274403737,
+      "grad_norm": 1.1041579246520996,
+      "learning_rate": 3.977024070021882e-05,
+      "loss": 0.1897,
+      "mean_token_accuracy": 0.9675146728754044,
+      "num_tokens": 1187840.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.2950577821490042,
+      "grad_norm": 0.838715136051178,
+      "learning_rate": 3.9223194748358865e-05,
+      "loss": 0.1874,
+      "mean_token_accuracy": 0.9673434391617775,
+      "num_tokens": 1228800.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.304893041553971,
+      "grad_norm": 0.809256911277771,
+      "learning_rate": 3.8676148796498906e-05,
+      "loss": 0.1887,
+      "mean_token_accuracy": 0.9662915796041489,
+      "num_tokens": 1269760.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.3147283009589378,
+      "grad_norm": 0.9318556785583496,
+      "learning_rate": 3.8129102844638954e-05,
+      "loss": 0.1806,
+      "mean_token_accuracy": 0.9675391353666782,
+      "num_tokens": 1310720.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.3245635603639046,
+      "grad_norm": 0.9607388377189636,
+      "learning_rate": 3.7582056892778995e-05,
+      "loss": 0.1803,
+      "mean_token_accuracy": 0.9687866866588593,
+      "num_tokens": 1351680.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.3343988197688714,
+      "grad_norm": 1.1759089231491089,
+      "learning_rate": 3.703501094091904e-05,
+      "loss": 0.1853,
+      "mean_token_accuracy": 0.9683219142258167,
+      "num_tokens": 1392640.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.3442340791738382,
+      "grad_norm": 0.8875013589859009,
+      "learning_rate": 3.648796498905908e-05,
+      "loss": 0.1798,
+      "mean_token_accuracy": 0.9690557658672333,
+      "num_tokens": 1433600.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.354069338578805,
+      "grad_norm": 0.5948426127433777,
+      "learning_rate": 3.594091903719913e-05,
+      "loss": 0.1717,
+      "mean_token_accuracy": 0.9697162359952927,
+      "num_tokens": 1474560.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.36390459798377184,
+      "grad_norm": 1.2609747648239136,
+      "learning_rate": 3.539387308533917e-05,
+      "loss": 0.1713,
+      "mean_token_accuracy": 0.9699119322001934,
+      "num_tokens": 1515520.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.3737398573887386,
+      "grad_norm": 0.7272819876670837,
+      "learning_rate": 3.484682713347921e-05,
+      "loss": 0.175,
+      "mean_token_accuracy": 0.969153618067503,
+      "num_tokens": 1556480.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.38357511679370543,
+      "grad_norm": 0.7384645938873291,
+      "learning_rate": 3.4299781181619254e-05,
+      "loss": 0.1687,
+      "mean_token_accuracy": 0.969373769313097,
+      "num_tokens": 1597440.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.39341037619867225,
+      "grad_norm": 1.0476771593093872,
+      "learning_rate": 3.37527352297593e-05,
+      "loss": 0.1707,
+      "mean_token_accuracy": 0.969740702956915,
+      "num_tokens": 1638400.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.403245635603639,
+      "grad_norm": 0.9195008277893066,
+      "learning_rate": 3.320568927789934e-05,
+      "loss": 0.1692,
+      "mean_token_accuracy": 0.9701076246798038,
+      "num_tokens": 1679360.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.41308089500860584,
+      "grad_norm": 0.9223462343215942,
+      "learning_rate": 3.265864332603939e-05,
+      "loss": 0.1809,
+      "mean_token_accuracy": 0.968713303655386,
+      "num_tokens": 1720320.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.42291615441357266,
+      "grad_norm": 0.9247675538063049,
+      "learning_rate": 3.211159737417943e-05,
+      "loss": 0.1728,
+      "mean_token_accuracy": 0.9698140874505043,
+      "num_tokens": 1761280.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.4327514138185395,
+      "grad_norm": 0.7341080904006958,
+      "learning_rate": 3.156455142231948e-05,
+      "loss": 0.1724,
+      "mean_token_accuracy": 0.969716239720583,
+      "num_tokens": 1802240.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.44258667322350626,
+      "grad_norm": 0.6656466126441956,
+      "learning_rate": 3.101750547045952e-05,
+      "loss": 0.1669,
+      "mean_token_accuracy": 0.9707191735506058,
+      "num_tokens": 1843200.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.4524219326284731,
+      "grad_norm": 1.0469170808792114,
+      "learning_rate": 3.0470459518599564e-05,
+      "loss": 0.1678,
+      "mean_token_accuracy": 0.9706457875669002,
+      "num_tokens": 1884160.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.4622571920334399,
+      "grad_norm": 0.8678417801856995,
+      "learning_rate": 2.9923413566739605e-05,
+      "loss": 0.1742,
+      "mean_token_accuracy": 0.9697651587426662,
+      "num_tokens": 1925120.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.47209245143840667,
+      "grad_norm": 0.9280726313591003,
+      "learning_rate": 2.9376367614879653e-05,
+      "loss": 0.1706,
+      "mean_token_accuracy": 0.9689089976251125,
+      "num_tokens": 1966080.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 1.031360387802124,
+      "learning_rate": 2.8829321663019694e-05,
+      "loss": 0.1674,
+      "mean_token_accuracy": 0.97010762616992,
+      "num_tokens": 2007040.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.4917629702483403,
+      "grad_norm": 1.0764884948730469,
+      "learning_rate": 2.828227571115974e-05,
+      "loss": 0.1761,
+      "mean_token_accuracy": 0.9694471597671509,
+      "num_tokens": 2048000.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1016,
+  "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 sha256:2bf73865ec4fc5b6eb60f5807398b998b49ba98cf43e5b3b38354b0b812ca9f5
+size 5624