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:a6f05de92f9947d968c93fdf3a44122e9cee79164db19094fdb0317645602570
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cbb9c84583ec9fc5aeba2ad1fc30d302083fdd3b2eaa1c2861a1c4bdfade675
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b710318d2a48209496859a82aaaed1abd9b52c723a1d9b86ddbffd79860a89b4
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0884d85c73852f4b69e6521b149b7ea1eb2a4d7dc736229cd8f159d0fcb392
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17c484013abadb234dd8122dc96d57cf077188488b8d8fe8af312b9af489880
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dafb0c6085bbf3b8307a2219fa4773daed79ad499d31a4981bd3299b43a48e5
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe828ae5f83d640b8cba7084caf75fb31a26d67a6a674651cd4387dfe3e18b2e
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d447339fa4bbca5a935efa419aa2584f6385e5efd4323e638d7717d119cb3ac
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce0bf22323f467a4ce5a5cbba76c795dcdcc2e492da851e6f6203a529963f9b
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4c10f716a2a10596eff42ea572483fc19793503ba4b9dc918f8dee2cc43abd
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29aba304eb3c7fed43fcfc7760d91a3507ac867cb22cd83ec0bca62c4a91bcd
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065e360767a1dee3a4a77eb9a154a6cd649f1d9c4fd4ad230fc4c47effee30c1
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ba66c16129323a30a081d76e8b3a6fd00824408fedd54525f726b225e0277d
+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": 2.0672840185973786,
+      "learning_rate": 0.0,
+      "loss": 0.866,
+      "step": 1
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 2.2899858891181903,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.043,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 1.910333546900785,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.9429,
+      "step": 3
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 1.624979132025543,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.985,
+      "step": 4
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.3301367316845518,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.9899,
+      "step": 5
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 2.192370335122931,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.9655,
+      "step": 6
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 2.2285319009652462,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.9456,
+      "step": 7
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 2.541438185031773,
+      "learning_rate": 3e-05,
+      "loss": 0.9954,
+      "step": 8
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 2.2177826928862956,
+      "learning_rate": 2.999581555818041e-05,
+      "loss": 1.0037,
+      "step": 9
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.4333465946127133,
+      "learning_rate": 2.9983264567328756e-05,
+      "loss": 0.9675,
+      "step": 10
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 1.0448310378956214,
+      "learning_rate": 2.9962354029963835e-05,
+      "loss": 0.8559,
+      "step": 11
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.0781647166558237,
+      "learning_rate": 2.9933095612609253e-05,
+      "loss": 0.8733,
+      "step": 12
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 1.007650519854371,
+      "learning_rate": 2.989550563928436e-05,
+      "loss": 0.9403,
+      "step": 13
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.7907009024129646,
+      "learning_rate": 2.9849605082396678e-05,
+      "loss": 0.8458,
+      "step": 14
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.7042592030399148,
+      "learning_rate": 2.9795419551040836e-05,
+      "loss": 0.8727,
+      "step": 15
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.6419420174929784,
+      "learning_rate": 2.973297927671063e-05,
+      "loss": 0.8186,
+      "step": 16
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.8076296952096572,
+      "learning_rate": 2.966231909643208e-05,
+      "loss": 0.9296,
+      "step": 17
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.6598191860375567,
+      "learning_rate": 2.958347843332696e-05,
+      "loss": 0.8284,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5560706149108875,
+      "learning_rate": 2.949650127461764e-05,
+      "loss": 0.8931,
+      "step": 19
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.5418452815767641,
+      "learning_rate": 2.940143614708549e-05,
+      "loss": 0.8911,
+      "step": 20
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.6442251215106719,
+      "learning_rate": 2.9298336089996538e-05,
+      "loss": 0.857,
+      "step": 21
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.5601338870306712,
+      "learning_rate": 2.9187258625509518e-05,
+      "loss": 0.8112,
+      "step": 22
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.5147949384274566,
+      "learning_rate": 2.906826572658278e-05,
+      "loss": 0.8752,
+      "step": 23
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.414227052576231,
+      "learning_rate": 2.8941423782397987e-05,
+      "loss": 0.8455,
+      "step": 24
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.4724293164215497,
+      "learning_rate": 2.8806803561319903e-05,
+      "loss": 0.8332,
+      "step": 25
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.5244546146099837,
+      "learning_rate": 2.866448017141291e-05,
+      "loss": 0.8992,
+      "step": 26
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.49846452691797277,
+      "learning_rate": 2.8514533018536286e-05,
+      "loss": 0.7989,
+      "step": 27
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.5139730942456431,
+      "learning_rate": 2.835704576204167e-05,
+      "loss": 0.8281,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5139730942456431,
+      "learning_rate": 2.8192106268097336e-05,
+      "loss": 0.7089,
+      "step": 29
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.8522153801917955,
+      "learning_rate": 2.801980656066545e-05,
+      "loss": 0.7715,
+      "step": 30
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.48621319476048247,
+      "learning_rate": 2.78402427701595e-05,
+      "loss": 0.7326,
+      "step": 31
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.4931003602154137,
+      "learning_rate": 2.7653515079810744e-05,
+      "loss": 0.7796,
+      "step": 32
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.6820149173810659,
+      "learning_rate": 2.7459727669773344e-05,
+      "loss": 0.7558,
+      "step": 33
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 0.6039546286330506,
+      "learning_rate": 2.725898865899967e-05,
+      "loss": 0.7164,
+      "step": 34
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.49413279486249445,
+      "learning_rate": 2.705141004491792e-05,
+      "loss": 0.771,
+      "step": 35
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.46540726916290787,
+      "learning_rate": 2.6837107640945904e-05,
+      "loss": 0.7745,
+      "step": 36
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 0.7142115362037698,
+      "learning_rate": 2.6616201011875792e-05,
+      "loss": 0.7457,
+      "step": 37
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.5357068778365942,
+      "learning_rate": 2.638881340716583e-05,
+      "loss": 0.7222,
+      "step": 38
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 0.46939662640391816,
+      "learning_rate": 2.6155071692176348e-05,
+      "loss": 0.6748,
+      "step": 39
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.537500418669669,
+      "learning_rate": 2.5915106277388293e-05,
+      "loss": 0.7777,
+      "step": 40
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.59073194769042,
+      "learning_rate": 2.566905104564393e-05,
+      "loss": 0.7173,
+      "step": 41
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 0.42637743115128474,
+      "learning_rate": 2.541704327745013e-05,
+      "loss": 0.6769,
+      "step": 42
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.4344573872029452,
+      "learning_rate": 2.5159223574386117e-05,
+      "loss": 0.6656,
+      "step": 43
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.5018768196524176,
+      "learning_rate": 2.489573578065821e-05,
+      "loss": 0.802,
+      "step": 44
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.4529698728985265,
+      "learning_rate": 2.4626726902845477e-05,
+      "loss": 0.7586,
+      "step": 45
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.48235341277848787,
+      "learning_rate": 2.4352347027881003e-05,
+      "loss": 0.6852,
+      "step": 46
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.3627100867848393,
+      "learning_rate": 2.4072749239314565e-05,
+      "loss": 0.6858,
+      "step": 47
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.38664865341383037,
+      "learning_rate": 2.3788089531903372e-05,
+      "loss": 0.7365,
+      "step": 48
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 0.4545364316322588,
+      "learning_rate": 2.3498526724578637e-05,
+      "loss": 0.7538,
+      "step": 49
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.518944898034962,
+      "learning_rate": 2.320422237183641e-05,
+      "loss": 0.7454,
+      "step": 50
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 0.4067307322789782,
+      "learning_rate": 2.2905340673602184e-05,
+      "loss": 0.7482,
+      "step": 51
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.4862538497731571,
+      "learning_rate": 2.26020483836196e-05,
+      "loss": 0.7729,
+      "step": 52
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.46087867219067935,
+      "learning_rate": 2.229451471641422e-05,
+      "loss": 0.6216,
+      "step": 53
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.5430309866121377,
+      "learning_rate": 2.198291125288445e-05,
+      "loss": 0.7631,
+      "step": 54
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.5141331795467418,
+      "learning_rate": 2.166741184457214e-05,
+      "loss": 0.7101,
+      "step": 55
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.39081537987082116,
+      "learning_rate": 2.1348192516666376e-05,
+      "loss": 0.7608,
+      "step": 56
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 0.4994585530441829,
+      "learning_rate": 2.1025431369794546e-05,
+      "loss": 0.7654,
+      "step": 57
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8215961436633803,
+      "learning_rate": 2.0699308480655397e-05,
+      "loss": 0.674,
+      "step": 58
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.7120328127826715,
+      "learning_rate": 2.03700058015497e-05,
+      "loss": 0.6013,
+      "step": 59
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.8161065595108032,
+      "learning_rate": 2.0037707058864343e-05,
+      "loss": 0.7149,
+      "step": 60
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 1.8952005651095847,
+      "learning_rate": 1.9702597650566723e-05,
+      "loss": 0.6234,
+      "step": 61
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 0.5215133657210498,
+      "learning_rate": 1.936486454276647e-05,
+      "loss": 0.6001,
+      "step": 62
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.8401793670285913,
+      "learning_rate": 1.9024696165402272e-05,
+      "loss": 0.6392,
+      "step": 63
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.7463732624054893,
+      "learning_rate": 1.8682282307111988e-05,
+      "loss": 0.6392,
+      "step": 64
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.449660878951785,
+      "learning_rate": 1.8337814009344716e-05,
+      "loss": 0.5725,
+      "step": 65
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.6166851563782507,
+      "learning_rate": 1.7991483459773887e-05,
+      "loss": 0.6117,
+      "step": 66
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.4765184980194071,
+      "learning_rate": 1.7643483885070827e-05,
+      "loss": 0.5877,
+      "step": 67
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.539140038588759,
+      "learning_rate": 1.729400944309869e-05,
+      "loss": 0.6497,
+      "step": 68
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.48435908336158434,
+      "learning_rate": 1.6943255114586788e-05,
+      "loss": 0.6004,
+      "step": 69
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 1.0565779360065954,
+      "learning_rate": 1.659141659434587e-05,
+      "loss": 0.6898,
+      "step": 70
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.44520837075665026,
+      "learning_rate": 1.623869018208499e-05,
+      "loss": 0.6189,
+      "step": 71
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.5141213138770342,
+      "learning_rate": 1.5885272672890842e-05,
+      "loss": 0.6262,
+      "step": 72
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.5046502197354534,
+      "learning_rate": 1.553136124743081e-05,
+      "loss": 0.5617,
+      "step": 73
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.47228102896457386,
+      "learning_rate": 1.517715336194077e-05,
+      "loss": 0.6288,
+      "step": 74
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.3945749736245955,
+      "learning_rate": 1.4822846638059234e-05,
+      "loss": 0.6189,
+      "step": 75
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.47554210947045383,
+      "learning_rate": 1.4468638752569193e-05,
+      "loss": 0.6187,
+      "step": 76
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.4168918402865985,
+      "learning_rate": 1.411472732710916e-05,
+      "loss": 0.6511,
+      "step": 77
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 0.3784629074937835,
+      "learning_rate": 1.3761309817915017e-05,
+      "loss": 0.6384,
+      "step": 78
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.3766919801894043,
+      "learning_rate": 1.340858340565413e-05,
+      "loss": 0.6241,
+      "step": 79
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.3304739692544291,
+      "learning_rate": 1.3056744885413216e-05,
+      "loss": 0.5765,
+      "step": 80
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.3593006941475982,
+      "learning_rate": 1.2705990556901311e-05,
+      "loss": 0.5384,
+      "step": 81
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.3790675720863581,
+      "learning_rate": 1.2356516114929176e-05,
+      "loss": 0.6123,
+      "step": 82
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 0.38906936709954903,
+      "learning_rate": 1.2008516540226115e-05,
+      "loss": 0.6196,
+      "step": 83
+    },
+    {
+      "epoch": 2.912280701754386,
+      "grad_norm": 0.38879375158868906,
+      "learning_rate": 1.1662185990655285e-05,
+      "loss": 0.6376,
+      "step": 84
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.37164660785811104,
+      "learning_rate": 1.1317717692888014e-05,
+      "loss": 0.5652,
+      "step": 85
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 0.3398419044284849,
+      "learning_rate": 1.0975303834597734e-05,
+      "loss": 0.6338,
+      "step": 86
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3398419044284849,
+      "learning_rate": 1.0635135457233533e-05,
+      "loss": 0.4196,
+      "step": 87
+    },
+    {
+      "epoch": 3.0350877192982457,
+      "grad_norm": 1.0137232981739484,
+      "learning_rate": 1.0297402349433286e-05,
+      "loss": 0.5244,
+      "step": 88
+    },
+    {
+      "epoch": 3.0701754385964914,
+      "grad_norm": 1.00282256056707,
+      "learning_rate": 9.96229294113566e-06,
+      "loss": 0.5768,
+      "step": 89
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.7359804333242452,
+      "learning_rate": 9.629994198450305e-06,
+      "loss": 0.5524,
+      "step": 90
+    },
+    {
+      "epoch": 3.1403508771929824,
+      "grad_norm": 2.2445121599018316,
+      "learning_rate": 9.300691519344602e-06,
+      "loss": 0.5148,
+      "step": 91
+    },
+    {
+      "epoch": 3.175438596491228,
+      "grad_norm": 1.8476077615083395,
+      "learning_rate": 8.974568630205462e-06,
+      "loss": 0.5253,
+      "step": 92
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.9919680932647257,
+      "learning_rate": 8.651807483333627e-06,
+      "loss": 0.5889,
+      "step": 93
+    },
+    {
+      "epoch": 3.245614035087719,
+      "grad_norm": 0.6006306613920271,
+      "learning_rate": 8.332588155427869e-06,
+      "loss": 0.4976,
+      "step": 94
+    },
+    {
+      "epoch": 3.280701754385965,
+      "grad_norm": 0.8381288364191982,
+      "learning_rate": 8.017088747115554e-06,
+      "loss": 0.4911,
+      "step": 95
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 1.019844749447574,
+      "learning_rate": 7.70548528358578e-06,
+      "loss": 0.545,
+      "step": 96
+    },
+    {
+      "epoch": 3.3508771929824563,
+      "grad_norm": 0.686676528584022,
+      "learning_rate": 7.397951616380401e-06,
+      "loss": 0.5178,
+      "step": 97
+    },
+    {
+      "epoch": 3.3859649122807016,
+      "grad_norm": 0.44425862963385576,
+      "learning_rate": 7.094659326397818e-06,
+      "loss": 0.4589,
+      "step": 98
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.5838625291964793,
+      "learning_rate": 6.795777628163599e-06,
+      "loss": 0.458,
+      "step": 99
+    },
+    {
+      "epoch": 3.456140350877193,
+      "grad_norm": 0.5930203797342937,
+      "learning_rate": 6.50147327542137e-06,
+      "loss": 0.446,
+      "step": 100
+    },
+    {
+      "epoch": 3.4912280701754383,
+      "grad_norm": 0.5269168747999409,
+      "learning_rate": 6.211910468096631e-06,
+      "loss": 0.4934,
+      "step": 101
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.5670642434002793,
+      "learning_rate": 5.927250760685441e-06,
+      "loss": 0.4873,
+      "step": 102
+    },
+    {
+      "epoch": 3.56140350877193,
+      "grad_norm": 0.4247200179986956,
+      "learning_rate": 5.647652972118998e-06,
+      "loss": 0.5014,
+      "step": 103
+    },
+    {
+      "epoch": 3.5964912280701755,
+      "grad_norm": 0.4430935108406106,
+      "learning_rate": 5.37327309715453e-06,
+      "loss": 0.4655,
+      "step": 104
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.5635679456028786,
+      "learning_rate": 5.104264219341793e-06,
+      "loss": 0.4347,
+      "step": 105
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.5287787974058867,
+      "learning_rate": 4.840776425613887e-06,
+      "loss": 0.4702,
+      "step": 106
+    },
+    {
+      "epoch": 3.7017543859649122,
+      "grad_norm": 0.39061619403610864,
+      "learning_rate": 4.5829567225498696e-06,
+      "loss": 0.4811,
+      "step": 107
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.460388428002953,
+      "learning_rate": 4.330948954356076e-06,
+      "loss": 0.5509,
+      "step": 108
+    },
+    {
+      "epoch": 3.7719298245614032,
+      "grad_norm": 0.4278739474644464,
+      "learning_rate": 4.084893722611706e-06,
+      "loss": 0.5717,
+      "step": 109
+    },
+    {
+      "epoch": 3.807017543859649,
+      "grad_norm": 0.45200972992342586,
+      "learning_rate": 3.844928307823655e-06,
+      "loss": 0.5056,
+      "step": 110
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.4253590718408458,
+      "learning_rate": 3.6111865928341723e-06,
+      "loss": 0.5168,
+      "step": 111
+    },
+    {
+      "epoch": 3.8771929824561404,
+      "grad_norm": 0.32918346887072003,
+      "learning_rate": 3.3837989881242142e-06,
+      "loss": 0.4625,
+      "step": 112
+    },
+    {
+      "epoch": 3.912280701754386,
+      "grad_norm": 0.3745055783395016,
+      "learning_rate": 3.162892359054098e-06,
+      "loss": 0.4761,
+      "step": 113
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.4208498044542645,
+      "learning_rate": 2.948589955082085e-06,
+      "loss": 0.501,
+      "step": 114
+    },
+    {
+      "epoch": 3.982456140350877,
+      "grad_norm": 0.35518617384373624,
+      "learning_rate": 2.74101134100033e-06,
+      "loss": 0.518,
+      "step": 115
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6359258653193457,
+      "learning_rate": 2.540272330226658e-06,
+      "loss": 0.4388,
+      "step": 116
+    },
+    {
+      "epoch": 4.035087719298246,
+      "grad_norm": 0.9344007231992887,
+      "learning_rate": 2.3464849201892596e-06,
+      "loss": 0.4476,
+      "step": 117
+    },
+    {
+      "epoch": 4.0701754385964914,
+      "grad_norm": 0.7231074120032394,
+      "learning_rate": 2.1597572298405e-06,
+      "loss": 0.4268,
+      "step": 118
+    },
+    {
+      "epoch": 4.105263157894737,
+      "grad_norm": 0.4903922122084103,
+      "learning_rate": 1.980193439334554e-06,
+      "loss": 0.4815,
+      "step": 119
+    },
+    {
+      "epoch": 4.140350877192983,
+      "grad_norm": 0.5916262133643917,
+      "learning_rate": 1.8078937319026655e-06,
+      "loss": 0.4353,
+      "step": 120
+    },
+    {
+      "epoch": 4.175438596491228,
+      "grad_norm": 0.34841237956938415,
+      "learning_rate": 1.6429542379583313e-06,
+      "loss": 0.4176,
+      "step": 121
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 0.4947947773800059,
+      "learning_rate": 1.4854669814637145e-06,
+      "loss": 0.4334,
+      "step": 122
+    },
+    {
+      "epoch": 4.245614035087719,
+      "grad_norm": 0.4962400757050512,
+      "learning_rate": 1.3355198285870935e-06,
+      "loss": 0.4354,
+      "step": 123
+    },
+    {
+      "epoch": 4.280701754385965,
+      "grad_norm": 0.6480795706970779,
+      "learning_rate": 1.1931964386800991e-06,
+      "loss": 0.4221,
+      "step": 124
+    },
+    {
+      "epoch": 4.315789473684211,
+      "grad_norm": 0.5789623920753147,
+      "learning_rate": 1.0585762176020148e-06,
+      "loss": 0.4818,
+      "step": 125
+    },
+    {
+      "epoch": 4.350877192982456,
+      "grad_norm": 0.515709293090189,
+      "learning_rate": 9.317342734172213e-07,
+      "loss": 0.4548,
+      "step": 126
+    },
+    {
+      "epoch": 4.385964912280702,
+      "grad_norm": 0.6538071676655299,
+      "learning_rate": 8.127413744904805e-07,
+      "loss": 0.4475,
+      "step": 127
+    },
+    {
+      "epoch": 4.421052631578947,
+      "grad_norm": 0.41858161288361395,
+      "learning_rate": 7.016639100034627e-07,
+      "loss": 0.4535,
+      "step": 128
+    },
+    {
+      "epoch": 4.456140350877193,
+      "grad_norm": 0.38988164233302713,
+      "learning_rate": 5.985638529145115e-07,
+      "loss": 0.4714,
+      "step": 129
+    },
+    {
+      "epoch": 4.491228070175438,
+      "grad_norm": 0.4008059598246354,
+      "learning_rate": 5.034987253823614e-07,
+      "loss": 0.5021,
+      "step": 130
+    },
+    {
+      "epoch": 4.526315789473684,
+      "grad_norm": 0.3728752330965698,
+      "learning_rate": 4.165215666730415e-07,
+      "loss": 0.4285,
+      "step": 131
+    },
+    {
+      "epoch": 4.56140350877193,
+      "grad_norm": 0.33158568625741724,
+      "learning_rate": 3.376809035679218e-07,
+      "loss": 0.4621,
+      "step": 132
+    },
+    {
+      "epoch": 4.5964912280701755,
+      "grad_norm": 0.30943024786404216,
+      "learning_rate": 2.670207232893684e-07,
+      "loss": 0.3947,
+      "step": 133
+    },
+    {
+      "epoch": 4.631578947368421,
+      "grad_norm": 0.3543355424963944,
+      "learning_rate": 2.0458044895916516e-07,
+      "loss": 0.3815,
+      "step": 134
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.3281884846876981,
+      "learning_rate": 1.503949176033259e-07,
+      "loss": 0.437,
+      "step": 135
+    },
+    {
+      "epoch": 4.701754385964913,
+      "grad_norm": 0.32730709189350027,
+      "learning_rate": 1.04494360715639e-07,
+      "loss": 0.4172,
+      "step": 136
+    },
+    {
+      "epoch": 4.7368421052631575,
+      "grad_norm": 0.34332536619087617,
+      "learning_rate": 6.690438739074767e-08,
+      "loss": 0.4577,
+      "step": 137
+    },
+    {
+      "epoch": 4.771929824561403,
+      "grad_norm": 0.32103263244796076,
+      "learning_rate": 3.764597003616421e-08,
+      "loss": 0.4919,
+      "step": 138
+    },
+    {
+      "epoch": 4.807017543859649,
+      "grad_norm": 0.3426179471144698,
+      "learning_rate": 1.6735432671243223e-08,
+      "loss": 0.4387,
+      "step": 139
+    },
+    {
+      "epoch": 4.842105263157895,
+      "grad_norm": 0.3081417797666205,
+      "learning_rate": 4.184441819588547e-09,
+      "loss": 0.4253,
+      "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 sha256:868e0c9aa3d1c77999ea8d9ae84c869b30a3ed6d0b7f102e2ddaf05c2139b612
+size 8017