Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.0.dev0"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f1ef1f254dbd2f0e620f99ec22d8e4124af702fec5385d926f399438317a63
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb7aeced16f99227df2b9c0a3d310feb186b1ad187101785e40782d9b4babc0
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454d3186239acc517fc2f205f23446c8f289a565034a8ae550d1a5ece30f9555
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c19670082d7c19107327bea92d3f5452e44c350ad707ca5621ae88ed283ff33
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b63a07a3ed0fc24f3569f6799a8fc7ce09bbab06b5f0674875af5ee0185638
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104f763f12b259727afc549b6cab5f4ad4c4d36cd0d9bc51d21cfcd00e97d986
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f6549b87ab0c5d8f8a1f235934399b2f1b603dfdb39e17df5e3c8f156eb4b6
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca32f663fab48c69cd53014ae070f80a0e8a49dd811e3df3c4fe26dabadfaa3
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98cbf69cb87e9c759397d5096a123113814e4c7efdd89279ebbb798c72fb929
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59164717dfa56608e532f93a29d232fca3cc6389f5ea6159a35910a8b2869447
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef444d75a357b1a8a3df392e20e5e1d4aa4fc272e4d889fcfa10cab8b1f851b8
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62aaa4c665b9a620f1148b863cb9398a4f63955bc494cf41f4dd6a713febd472
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7af8f8a54a3ba3e812063476a1dd5a12edb330b7d4445fdc5b893ad5b2b4e9
+size 1094220288

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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1014 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.842105263157895,
+  "eval_steps": 500,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 2.0673070244813063,
+      "learning_rate": 0.0,
+      "loss": 0.866,
+      "step": 1
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 2.290645149886701,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.043,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.0384407294665747,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.9475,
+      "step": 3
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 2.0751386251214314,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.0015,
+      "step": 4
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.8611754309476487,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.0106,
+      "step": 5
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 1.5605070320275363,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.9839,
+      "step": 6
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 1.323817282105345,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.9658,
+      "step": 7
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 1.1766396808562414,
+      "learning_rate": 1e-05,
+      "loss": 0.9877,
+      "step": 8
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 1.920335999253467,
+      "learning_rate": 9.998605186060138e-06,
+      "loss": 1.0056,
+      "step": 9
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.8982677371348105,
+      "learning_rate": 9.99442152244292e-06,
+      "loss": 0.9781,
+      "step": 10
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 1.7435846632830103,
+      "learning_rate": 9.98745134332128e-06,
+      "loss": 0.8702,
+      "step": 11
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.8684092704303354,
+      "learning_rate": 9.97769853753642e-06,
+      "loss": 0.8934,
+      "step": 12
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 1.761909365090902,
+      "learning_rate": 9.965168546428122e-06,
+      "loss": 0.9624,
+      "step": 13
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 1.3688611326166515,
+      "learning_rate": 9.949868360798893e-06,
+      "loss": 0.8695,
+      "step": 14
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.1087321036703561,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 0.8931,
+      "step": 15
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.8075436412081172,
+      "learning_rate": 9.910993092236878e-06,
+      "loss": 0.8353,
+      "step": 16
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.836233225723369,
+      "learning_rate": 9.887439698810694e-06,
+      "loss": 0.9445,
+      "step": 17
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.715862149797478,
+      "learning_rate": 9.861159477775653e-06,
+      "loss": 0.8434,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.7888763860979434,
+      "learning_rate": 9.832167091539215e-06,
+      "loss": 0.9075,
+      "step": 19
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.7782919163094735,
+      "learning_rate": 9.800478715695165e-06,
+      "loss": 0.9018,
+      "step": 20
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.8319523753602327,
+      "learning_rate": 9.766112029998847e-06,
+      "loss": 0.869,
+      "step": 21
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.7124372949071385,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 0.822,
+      "step": 22
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.7500909047451202,
+      "learning_rate": 9.689421908860928e-06,
+      "loss": 0.8867,
+      "step": 23
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.5886562659462773,
+      "learning_rate": 9.64714126079933e-06,
+      "loss": 0.8565,
+      "step": 24
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.5469375245913981,
+      "learning_rate": 9.602267853773301e-06,
+      "loss": 0.8436,
+      "step": 25
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.48742789244387086,
+      "learning_rate": 9.554826723804304e-06,
+      "loss": 0.91,
+      "step": 26
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.481986089398419,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.808,
+      "step": 27
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.5338814362033426,
+      "learning_rate": 9.452348587347224e-06,
+      "loss": 0.8373,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5338814362033426,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 0.7497,
+      "step": 29
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.9216087684021367,
+      "learning_rate": 9.339935520221816e-06,
+      "loss": 0.8368,
+      "step": 30
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.5517402285558708,
+      "learning_rate": 9.280080923386501e-06,
+      "loss": 0.803,
+      "step": 31
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.4780695144971756,
+      "learning_rate": 9.217838359936914e-06,
+      "loss": 0.8483,
+      "step": 32
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.4352106079609395,
+      "learning_rate": 9.153242556591115e-06,
+      "loss": 0.8255,
+      "step": 33
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 0.41608709718428166,
+      "learning_rate": 9.08632955299989e-06,
+      "loss": 0.7893,
+      "step": 34
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.39539913867385906,
+      "learning_rate": 9.017136681639307e-06,
+      "loss": 0.8458,
+      "step": 35
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.4147873782216342,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 0.8336,
+      "step": 36
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 0.4859811666166825,
+      "learning_rate": 8.872067003958597e-06,
+      "loss": 0.8216,
+      "step": 37
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.3825847458202985,
+      "learning_rate": 8.796271135721944e-06,
+      "loss": 0.7914,
+      "step": 38
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 0.38418403992840294,
+      "learning_rate": 8.71835723072545e-06,
+      "loss": 0.7468,
+      "step": 39
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.37144282673439744,
+      "learning_rate": 8.638368759129433e-06,
+      "loss": 0.8526,
+      "step": 40
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.4263001257500465,
+      "learning_rate": 8.556350348547978e-06,
+      "loss": 0.7826,
+      "step": 41
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 0.3725947130107881,
+      "learning_rate": 8.472347759150044e-06,
+      "loss": 0.7509,
+      "step": 42
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.35479611609977757,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 0.7388,
+      "step": 43
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.3523727317535909,
+      "learning_rate": 8.298578593552737e-06,
+      "loss": 0.8733,
+      "step": 44
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.35090923069349866,
+      "learning_rate": 8.208908967615159e-06,
+      "loss": 0.8275,
+      "step": 45
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.3363022296982819,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.7592,
+      "step": 46
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.33371096186357996,
+      "learning_rate": 8.024249746438189e-06,
+      "loss": 0.7492,
+      "step": 47
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3503795383305235,
+      "learning_rate": 7.929363177301124e-06,
+      "loss": 0.8032,
+      "step": 48
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 0.31772810586348393,
+      "learning_rate": 7.832842241526212e-06,
+      "loss": 0.8147,
+      "step": 49
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.34558444572109065,
+      "learning_rate": 7.734740790612137e-06,
+      "loss": 0.8039,
+      "step": 50
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 0.3683078602862912,
+      "learning_rate": 7.635113557867395e-06,
+      "loss": 0.821,
+      "step": 51
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.3779532923279179,
+      "learning_rate": 7.5340161278732e-06,
+      "loss": 0.8398,
+      "step": 52
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.34514628086251675,
+      "learning_rate": 7.431504905471407e-06,
+      "loss": 0.6881,
+      "step": 53
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.3766820846229699,
+      "learning_rate": 7.327637084294818e-06,
+      "loss": 0.8313,
+      "step": 54
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.3715998928933267,
+      "learning_rate": 7.22247061485738e-06,
+      "loss": 0.7854,
+      "step": 55
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.3507736964447335,
+      "learning_rate": 7.1160641722221255e-06,
+      "loss": 0.8326,
+      "step": 56
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 0.34806693367183694,
+      "learning_rate": 7.008477123264849e-06,
+      "loss": 0.8366,
+      "step": 57
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5059705893154623,
+      "learning_rate": 6.8997694935518e-06,
+      "loss": 0.8023,
+      "step": 58
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.36732538969218886,
+      "learning_rate": 6.7900019338499005e-06,
+      "loss": 0.7269,
+      "step": 59
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.38816138679916923,
+      "learning_rate": 6.6792356862881144e-06,
+      "loss": 0.8553,
+      "step": 60
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.2980417664812599,
+      "learning_rate": 6.567532550188908e-06,
+      "loss": 0.7446,
+      "step": 61
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 0.33750149488854814,
+      "learning_rate": 6.454954847588824e-06,
+      "loss": 0.7341,
+      "step": 62
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.3235359591643424,
+      "learning_rate": 6.341565388467425e-06,
+      "loss": 0.7762,
+      "step": 63
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.3188121927886282,
+      "learning_rate": 6.227427435703997e-06,
+      "loss": 0.7962,
+      "step": 64
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.3250154832460792,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.691,
+      "step": 65
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.34832993543964275,
+      "learning_rate": 5.997161153257963e-06,
+      "loss": 0.7472,
+      "step": 66
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.3346266356546261,
+      "learning_rate": 5.88116129502361e-06,
+      "loss": 0.7332,
+      "step": 67
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.3380898664917708,
+      "learning_rate": 5.764669814366231e-06,
+      "loss": 0.7963,
+      "step": 68
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.2938364946133426,
+      "learning_rate": 5.647751704862263e-06,
+      "loss": 0.7254,
+      "step": 69
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.33097036890842274,
+      "learning_rate": 5.530472198115291e-06,
+      "loss": 0.8319,
+      "step": 70
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.3203526720947049,
+      "learning_rate": 5.412896727361663e-06,
+      "loss": 0.759,
+      "step": 71
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.30349016859987393,
+      "learning_rate": 5.2950908909636144e-06,
+      "loss": 0.7713,
+      "step": 72
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.3129174721997617,
+      "learning_rate": 5.177120415810271e-06,
+      "loss": 0.701,
+      "step": 73
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.311973264845113,
+      "learning_rate": 5.059051120646924e-06,
+      "loss": 0.7475,
+      "step": 74
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.3229947499800019,
+      "learning_rate": 4.940948879353078e-06,
+      "loss": 0.7584,
+      "step": 75
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.5066103233489299,
+      "learning_rate": 4.822879584189732e-06,
+      "loss": 0.7755,
+      "step": 76
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.31244071017364927,
+      "learning_rate": 4.704909109036387e-06,
+      "loss": 0.7986,
+      "step": 77
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 0.32284665228956844,
+      "learning_rate": 4.587103272638339e-06,
+      "loss": 0.7757,
+      "step": 78
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.3186010169256378,
+      "learning_rate": 4.46952780188471e-06,
+      "loss": 0.7521,
+      "step": 79
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.28846269969958793,
+      "learning_rate": 4.352248295137739e-06,
+      "loss": 0.7074,
+      "step": 80
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.3048547667354007,
+      "learning_rate": 4.23533018563377e-06,
+      "loss": 0.6802,
+      "step": 81
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.3386181101278266,
+      "learning_rate": 4.118838704976392e-06,
+      "loss": 0.7647,
+      "step": 82
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 0.3271528578378757,
+      "learning_rate": 4.002838846742039e-06,
+      "loss": 0.7617,
+      "step": 83
+    },
+    {
+      "epoch": 2.912280701754386,
+      "grad_norm": 0.32075888680959214,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.7706,
+      "step": 84
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.29833302106635273,
+      "learning_rate": 3.7725725642960047e-06,
+      "loss": 0.7099,
+      "step": 85
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 0.3062957423483349,
+      "learning_rate": 3.658434611532578e-06,
+      "loss": 0.7638,
+      "step": 86
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3062957423483349,
+      "learning_rate": 3.545045152411178e-06,
+      "loss": 0.6088,
+      "step": 87
+    },
+    {
+      "epoch": 3.0350877192982457,
+      "grad_norm": 0.5482814905537367,
+      "learning_rate": 3.4324674498110956e-06,
+      "loss": 0.7223,
+      "step": 88
+    },
+    {
+      "epoch": 3.0701754385964914,
+      "grad_norm": 0.41862251591120203,
+      "learning_rate": 3.3207643137118872e-06,
+      "loss": 0.7913,
+      "step": 89
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.3244934215825421,
+      "learning_rate": 3.2099980661501016e-06,
+      "loss": 0.7557,
+      "step": 90
+    },
+    {
+      "epoch": 3.1403508771929824,
+      "grad_norm": 0.3969196085560306,
+      "learning_rate": 3.1002305064482006e-06,
+      "loss": 0.7263,
+      "step": 91
+    },
+    {
+      "epoch": 3.175438596491228,
+      "grad_norm": 0.43992957203194183,
+      "learning_rate": 2.991522876735154e-06,
+      "loss": 0.7216,
+      "step": 92
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.41651928918050923,
+      "learning_rate": 2.8839358277778758e-06,
+      "loss": 0.8204,
+      "step": 93
+    },
+    {
+      "epoch": 3.245614035087719,
+      "grad_norm": 0.2986644588563747,
+      "learning_rate": 2.7775293851426233e-06,
+      "loss": 0.6971,
+      "step": 94
+    },
+    {
+      "epoch": 3.280701754385965,
+      "grad_norm": 0.2802522062222716,
+      "learning_rate": 2.6723629157051844e-06,
+      "loss": 0.6917,
+      "step": 95
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.40318713749421614,
+      "learning_rate": 2.5684950945285937e-06,
+      "loss": 0.7642,
+      "step": 96
+    },
+    {
+      "epoch": 3.3508771929824563,
+      "grad_norm": 0.3425889553518609,
+      "learning_rate": 2.4659838721268005e-06,
+      "loss": 0.7384,
+      "step": 97
+    },
+    {
+      "epoch": 3.3859649122807016,
+      "grad_norm": 0.30677645652568974,
+      "learning_rate": 2.364886442132606e-06,
+      "loss": 0.6411,
+      "step": 98
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.30070095711232125,
+      "learning_rate": 2.265259209387867e-06,
+      "loss": 0.6619,
+      "step": 99
+    },
+    {
+      "epoch": 3.456140350877193,
+      "grad_norm": 0.3218588836728724,
+      "learning_rate": 2.16715775847379e-06,
+      "loss": 0.6622,
+      "step": 100
+    },
+    {
+      "epoch": 3.4912280701754383,
+      "grad_norm": 0.2879660334650254,
+      "learning_rate": 2.0706368226988772e-06,
+      "loss": 0.6959,
+      "step": 101
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.34066475296129334,
+      "learning_rate": 1.9757502535618137e-06,
+      "loss": 0.6848,
+      "step": 102
+    },
+    {
+      "epoch": 3.56140350877193,
+      "grad_norm": 0.2796823907822852,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.6986,
+      "step": 103
+    },
+    {
+      "epoch": 3.5964912280701755,
+      "grad_norm": 0.34218464755974587,
+      "learning_rate": 1.7910910323848435e-06,
+      "loss": 0.6903,
+      "step": 104
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.3201128199990079,
+      "learning_rate": 1.7014214064472646e-06,
+      "loss": 0.614,
+      "step": 105
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.30125374157139934,
+      "learning_rate": 1.6135921418712959e-06,
+      "loss": 0.6915,
+      "step": 106
+    },
+    {
+      "epoch": 3.7017543859649122,
+      "grad_norm": 0.304680180290739,
+      "learning_rate": 1.5276522408499567e-06,
+      "loss": 0.6943,
+      "step": 107
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.3621378255456493,
+      "learning_rate": 1.4436496514520253e-06,
+      "loss": 0.7568,
+      "step": 108
+    },
+    {
+      "epoch": 3.7719298245614032,
+      "grad_norm": 0.30215239608253547,
+      "learning_rate": 1.361631240870569e-06,
+      "loss": 0.7791,
+      "step": 109
+    },
+    {
+      "epoch": 3.807017543859649,
+      "grad_norm": 0.2989892612179986,
+      "learning_rate": 1.281642769274552e-06,
+      "loss": 0.7399,
+      "step": 110
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.31314273131226966,
+      "learning_rate": 1.2037288642780575e-06,
+      "loss": 0.7435,
+      "step": 111
+    },
+    {
+      "epoch": 3.8771929824561404,
+      "grad_norm": 0.3142500922087154,
+      "learning_rate": 1.1279329960414047e-06,
+      "loss": 0.6847,
+      "step": 112
+    },
+    {
+      "epoch": 3.912280701754386,
+      "grad_norm": 0.29926703136108684,
+      "learning_rate": 1.0542974530180327e-06,
+      "loss": 0.6994,
+      "step": 113
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.27501540645654055,
+      "learning_rate": 9.82863318360695e-07,
+      "loss": 0.7181,
+      "step": 114
+    },
+    {
+      "epoch": 3.982456140350877,
+      "grad_norm": 0.2895489612529346,
+      "learning_rate": 9.136704470001101e-07,
+      "loss": 0.7339,
+      "step": 115
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.49026129635730115,
+      "learning_rate": 8.46757443408886e-07,
+      "loss": 0.6741,
+      "step": 116
+    },
+    {
+      "epoch": 4.035087719298246,
+      "grad_norm": 0.3178598574719659,
+      "learning_rate": 7.821616400630866e-07,
+      "loss": 0.6855,
+      "step": 117
+    },
+    {
+      "epoch": 4.0701754385964914,
+      "grad_norm": 0.363536923752346,
+      "learning_rate": 7.199190766135001e-07,
+      "loss": 0.6937,
+      "step": 118
+    },
+    {
+      "epoch": 4.105263157894737,
+      "grad_norm": 0.3170276756005372,
+      "learning_rate": 6.600644797781847e-07,
+      "loss": 0.7208,
+      "step": 119
+    },
+    {
+      "epoch": 4.140350877192983,
+      "grad_norm": 0.31066860165653054,
+      "learning_rate": 6.026312439675553e-07,
+      "loss": 0.6932,
+      "step": 120
+    },
+    {
+      "epoch": 4.175438596491228,
+      "grad_norm": 0.31518476145134705,
+      "learning_rate": 5.476514126527771e-07,
+      "loss": 0.6702,
+      "step": 121
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 0.2992971948787984,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.6438,
+      "step": 122
+    },
+    {
+      "epoch": 4.245614035087719,
+      "grad_norm": 0.4156443389342463,
+      "learning_rate": 4.4517327619569784e-07,
+      "loss": 0.6876,
+      "step": 123
+    },
+    {
+      "epoch": 4.280701754385965,
+      "grad_norm": 0.3213893768577189,
+      "learning_rate": 3.9773214622669974e-07,
+      "loss": 0.7109,
+      "step": 124
+    },
+    {
+      "epoch": 4.315789473684211,
+      "grad_norm": 0.29988541816282643,
+      "learning_rate": 3.528587392006716e-07,
+      "loss": 0.7561,
+      "step": 125
+    },
+    {
+      "epoch": 4.350877192982456,
+      "grad_norm": 0.3129487444676496,
+      "learning_rate": 3.105780911390738e-07,
+      "loss": 0.7051,
+      "step": 126
+    },
+    {
+      "epoch": 4.385964912280702,
+      "grad_norm": 0.3592055992496657,
+      "learning_rate": 2.7091379149682683e-07,
+      "loss": 0.7052,
+      "step": 127
+    },
+    {
+      "epoch": 4.421052631578947,
+      "grad_norm": 0.2912336365524275,
+      "learning_rate": 2.3388797000115427e-07,
+      "loss": 0.7159,
+      "step": 128
+    },
+    {
+      "epoch": 4.456140350877193,
+      "grad_norm": 0.28213898200794857,
+      "learning_rate": 1.9952128430483718e-07,
+      "loss": 0.7201,
+      "step": 129
+    },
+    {
+      "epoch": 4.491228070175438,
+      "grad_norm": 0.287153447612373,
+      "learning_rate": 1.6783290846078714e-07,
+      "loss": 0.772,
+      "step": 130
+    },
+    {
+      "epoch": 4.526315789473684,
+      "grad_norm": 0.2975453038642912,
+      "learning_rate": 1.388405222243472e-07,
+      "loss": 0.6801,
+      "step": 131
+    },
+    {
+      "epoch": 4.56140350877193,
+      "grad_norm": 0.30216919034385753,
+      "learning_rate": 1.1256030118930727e-07,
+      "loss": 0.7095,
+      "step": 132
+    },
+    {
+      "epoch": 4.5964912280701755,
+      "grad_norm": 0.33725665688405765,
+      "learning_rate": 8.900690776312282e-08,
+      "loss": 0.6186,
+      "step": 133
+    },
+    {
+      "epoch": 4.631578947368421,
+      "grad_norm": 0.2885141464272949,
+      "learning_rate": 6.819348298638839e-08,
+      "loss": 0.618,
+      "step": 134
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.3151545606250234,
+      "learning_rate": 5.013163920110864e-08,
+      "loss": 0.6912,
+      "step": 135
+    },
+    {
+      "epoch": 4.701754385964913,
+      "grad_norm": 0.3210608790204161,
+      "learning_rate": 3.483145357187967e-08,
+      "loss": 0.6663,
+      "step": 136
+    },
+    {
+      "epoch": 4.7368421052631575,
+      "grad_norm": 0.29638656127915125,
+      "learning_rate": 2.230146246358256e-08,
+      "loss": 0.7137,
+      "step": 137
+    },
+    {
+      "epoch": 4.771929824561403,
+      "grad_norm": 0.2842147099084156,
+      "learning_rate": 1.2548656678721404e-08,
+      "loss": 0.7475,
+      "step": 138
+    },
+    {
+      "epoch": 4.807017543859649,
+      "grad_norm": 0.33549357153059817,
+      "learning_rate": 5.578477557081074e-09,
+      "loss": 0.6913,
+      "step": 139
+    },
+    {
+      "epoch": 4.842105263157895,
+      "grad_norm": 0.28359612174705795,
+      "learning_rate": 1.3948139398628492e-09,
+      "loss": 0.6749,
+      "step": 140
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 63037458677760.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03c89a0c46bbc2f859dda7c08486ce064945cfa951262e9d8324e88d6b9f4d7
+size 8017