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 sha256:6004518858dd47923085a686e83eeac59ce66a86b1b38f9d7f5cf7a3f4c1f3af
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:162449c2609895d15f3a4430b3244855e446a70d75ad4462d1530e25304e81e0
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b3e5a9e00c7c49e40b3e04f1aee7062609a151dd048ef704787405dfd0006f
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f0f28087ebb1f93ea2fd846843cb629dcad08698aff0c3170ea59286ce2d27
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0787c69725df734c1f833b93727a3cdd45475a36e6c1aa65b8f9480964fc07
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe4ca6398d259d9ed10e0326592108fa47922641036885c91bea92af7a01f68
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58395aaf9fa99306875360f01206090973f35cc5e417db5a3a5b9ad0098921b0
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c338be253c9947423967e587c8b40404698ee27ea16ae8914ec21751800170
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207813464df8e2277ec2f531dffbab79992012b0f57151d5fe610232e906f8a2
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73a9c120c59ad5305d4c31d175a324104a03c37857b722f53b086e410da75b3
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf80e6d153dc41232e869d37dcc5175f19c4560e8f29efe769896b56ed31bbe
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3718527ea8bc382e6dd575e8fab1329fdb9d3482046531a8044eb156f62b8ce
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed22c7351cbfcfc4b2e68bf36c9a1e84920534bec607da3f757a86f85fa90ac3
+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 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.18066847335140018,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018066847335140017,
+      "grad_norm": 2.8330458831358536,
+      "learning_rate": 0.0,
+      "loss": 0.8251,
+      "step": 1
+    },
+    {
+      "epoch": 0.0036133694670280035,
+      "grad_norm": 2.881506507345633,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.8284,
+      "step": 2
+    },
+    {
+      "epoch": 0.005420054200542005,
+      "grad_norm": 2.864957143736817,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.8427,
+      "step": 3
+    },
+    {
+      "epoch": 0.007226738934056007,
+      "grad_norm": 2.789658157036283,
+      "learning_rate": 3.2142857142857143e-06,
+      "loss": 0.8378,
+      "step": 4
+    },
+    {
+      "epoch": 0.009033423667570008,
+      "grad_norm": 2.5748296264473147,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.8226,
+      "step": 5
+    },
+    {
+      "epoch": 0.01084010840108401,
+      "grad_norm": 2.1226324001162262,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.8096,
+      "step": 6
+    },
+    {
+      "epoch": 0.012646793134598013,
+      "grad_norm": 1.4591614339485137,
+      "learning_rate": 6.428571428571429e-06,
+      "loss": 0.7738,
+      "step": 7
+    },
+    {
+      "epoch": 0.014453477868112014,
+      "grad_norm": 1.3910404074529026,
+      "learning_rate": 7.5e-06,
+      "loss": 0.7731,
+      "step": 8
+    },
+    {
+      "epoch": 0.016260162601626018,
+      "grad_norm": 1.2975941991178286,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.7653,
+      "step": 9
+    },
+    {
+      "epoch": 0.018066847335140017,
+      "grad_norm": 2.39949931335525,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 0.7503,
+      "step": 10
+    },
+    {
+      "epoch": 0.01987353206865402,
+      "grad_norm": 2.339166039208163,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.7353,
+      "step": 11
+    },
+    {
+      "epoch": 0.02168021680216802,
+      "grad_norm": 2.2235135720121253,
+      "learning_rate": 1.1785714285714286e-05,
+      "loss": 0.7488,
+      "step": 12
+    },
+    {
+      "epoch": 0.023486901535682024,
+      "grad_norm": 1.8641369164869521,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.7252,
+      "step": 13
+    },
+    {
+      "epoch": 0.025293586269196026,
+      "grad_norm": 1.7375311366152815,
+      "learning_rate": 1.3928571428571429e-05,
+      "loss": 0.7282,
+      "step": 14
+    },
+    {
+      "epoch": 0.02710027100271003,
+      "grad_norm": 1.4297603171733615,
+      "learning_rate": 1.5e-05,
+      "loss": 0.7175,
+      "step": 15
+    },
+    {
+      "epoch": 0.028906955736224028,
+      "grad_norm": 1.1151402205703254,
+      "learning_rate": 1.6071428571428572e-05,
+      "loss": 0.7016,
+      "step": 16
+    },
+    {
+      "epoch": 0.03071364046973803,
+      "grad_norm": 0.8024202349277224,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.6998,
+      "step": 17
+    },
+    {
+      "epoch": 0.032520325203252036,
+      "grad_norm": 0.7606508999595812,
+      "learning_rate": 1.8214285714285712e-05,
+      "loss": 0.6884,
+      "step": 18
+    },
+    {
+      "epoch": 0.03432700993676603,
+      "grad_norm": 0.7625534222641119,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 0.6829,
+      "step": 19
+    },
+    {
+      "epoch": 0.036133694670280034,
+      "grad_norm": 0.6694670087645954,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 0.6597,
+      "step": 20
+    },
+    {
+      "epoch": 0.037940379403794036,
+      "grad_norm": 0.5962751724140051,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.6656,
+      "step": 21
+    },
+    {
+      "epoch": 0.03974706413730804,
+      "grad_norm": 0.574939617107255,
+      "learning_rate": 2.25e-05,
+      "loss": 0.6544,
+      "step": 22
+    },
+    {
+      "epoch": 0.04155374887082204,
+      "grad_norm": 0.5740495615931904,
+      "learning_rate": 2.357142857142857e-05,
+      "loss": 0.655,
+      "step": 23
+    },
+    {
+      "epoch": 0.04336043360433604,
+      "grad_norm": 0.5401386924725768,
+      "learning_rate": 2.464285714285714e-05,
+      "loss": 0.6603,
+      "step": 24
+    },
+    {
+      "epoch": 0.045167118337850046,
+      "grad_norm": 0.5411734137719719,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.6417,
+      "step": 25
+    },
+    {
+      "epoch": 0.04697380307136405,
+      "grad_norm": 0.4707448281296468,
+      "learning_rate": 2.6785714285714288e-05,
+      "loss": 0.6565,
+      "step": 26
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 0.4601634980551412,
+      "learning_rate": 2.7857142857142858e-05,
+      "loss": 0.6344,
+      "step": 27
+    },
+    {
+      "epoch": 0.05058717253839205,
+      "grad_norm": 0.4576924664211419,
+      "learning_rate": 2.892857142857143e-05,
+      "loss": 0.637,
+      "step": 28
+    },
+    {
+      "epoch": 0.052393857271906055,
+      "grad_norm": 0.44420515620753975,
+      "learning_rate": 3e-05,
+      "loss": 0.6484,
+      "step": 29
+    },
+    {
+      "epoch": 0.05420054200542006,
+      "grad_norm": 0.41258566428029175,
+      "learning_rate": 2.9999731440137413e-05,
+      "loss": 0.6488,
+      "step": 30
+    },
+    {
+      "epoch": 0.05600722673893405,
+      "grad_norm": 0.3492774187256118,
+      "learning_rate": 2.9998925770166232e-05,
+      "loss": 0.6377,
+      "step": 31
+    },
+    {
+      "epoch": 0.057813911472448055,
+      "grad_norm": 0.38161813042837406,
+      "learning_rate": 2.9997583018935875e-05,
+      "loss": 0.6262,
+      "step": 32
+    },
+    {
+      "epoch": 0.05962059620596206,
+      "grad_norm": 0.3667873345432628,
+      "learning_rate": 2.9995703234527553e-05,
+      "loss": 0.6358,
+      "step": 33
+    },
+    {
+      "epoch": 0.06142728093947606,
+      "grad_norm": 0.3431907596759456,
+      "learning_rate": 2.999328648425255e-05,
+      "loss": 0.6233,
+      "step": 34
+    },
+    {
+      "epoch": 0.06323396567299007,
+      "grad_norm": 0.36189091112235033,
+      "learning_rate": 2.999033285464982e-05,
+      "loss": 0.6288,
+      "step": 35
+    },
+    {
+      "epoch": 0.06504065040650407,
+      "grad_norm": 0.3804643814225747,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 0.6248,
+      "step": 36
+    },
+    {
+      "epoch": 0.06684733514001806,
+      "grad_norm": 0.35830891965133377,
+      "learning_rate": 2.9982815399736008e-05,
+      "loss": 0.6297,
+      "step": 37
+    },
+    {
+      "epoch": 0.06865401987353206,
+      "grad_norm": 0.349837532228719,
+      "learning_rate": 2.9978251843609816e-05,
+      "loss": 0.6219,
+      "step": 38
+    },
+    {
+      "epoch": 0.07046070460704607,
+      "grad_norm": 0.40406566853435366,
+      "learning_rate": 2.9973151946516027e-05,
+      "loss": 0.6243,
+      "step": 39
+    },
+    {
+      "epoch": 0.07226738934056007,
+      "grad_norm": 0.30908023037541016,
+      "learning_rate": 2.996751589107167e-05,
+      "loss": 0.6123,
+      "step": 40
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.3499175700089795,
+      "learning_rate": 2.9961343879092512e-05,
+      "loss": 0.6186,
+      "step": 41
+    },
+    {
+      "epoch": 0.07588075880758807,
+      "grad_norm": 0.29453754657609377,
+      "learning_rate": 2.9954636131585845e-05,
+      "loss": 0.6117,
+      "step": 42
+    },
+    {
+      "epoch": 0.07768744354110207,
+      "grad_norm": 0.31600841861885537,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 0.6117,
+      "step": 43
+    },
+    {
+      "epoch": 0.07949412827461608,
+      "grad_norm": 0.3022084890043788,
+      "learning_rate": 2.993961440992859e-05,
+      "loss": 0.6056,
+      "step": 44
+    },
+    {
+      "epoch": 0.08130081300813008,
+      "grad_norm": 0.3192692448247662,
+      "learning_rate": 2.993130097367553e-05,
+      "loss": 0.613,
+      "step": 45
+    },
+    {
+      "epoch": 0.08310749774164408,
+      "grad_norm": 0.2995609365814746,
+      "learning_rate": 2.9922452877670775e-05,
+      "loss": 0.6145,
+      "step": 46
+    },
+    {
+      "epoch": 0.08491418247515808,
+      "grad_norm": 0.28359568489888487,
+      "learning_rate": 2.991307043874677e-05,
+      "loss": 0.6171,
+      "step": 47
+    },
+    {
+      "epoch": 0.08672086720867209,
+      "grad_norm": 0.2763705613050705,
+      "learning_rate": 2.9903153992869734e-05,
+      "loss": 0.6031,
+      "step": 48
+    },
+    {
+      "epoch": 0.08852755194218609,
+      "grad_norm": 0.3024771650885143,
+      "learning_rate": 2.989270389512756e-05,
+      "loss": 0.6108,
+      "step": 49
+    },
+    {
+      "epoch": 0.09033423667570009,
+      "grad_norm": 0.2961191333250206,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.61,
+      "step": 50
+    },
+    {
+      "epoch": 0.0921409214092141,
+      "grad_norm": 0.2832954078297925,
+      "learning_rate": 2.9870204259931062e-05,
+      "loss": 0.5999,
+      "step": 51
+    },
+    {
+      "epoch": 0.0939476061427281,
+      "grad_norm": 0.28528145590927906,
+      "learning_rate": 2.9858155528143256e-05,
+      "loss": 0.617,
+      "step": 52
+    },
+    {
+      "epoch": 0.0957542908762421,
+      "grad_norm": 0.31958273903448986,
+      "learning_rate": 2.9845574755794522e-05,
+      "loss": 0.6027,
+      "step": 53
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.2721806575699711,
+      "learning_rate": 2.9832462393376926e-05,
+      "loss": 0.5922,
+      "step": 54
+    },
+    {
+      "epoch": 0.0993676603432701,
+      "grad_norm": 0.345845783610871,
+      "learning_rate": 2.9818818910417706e-05,
+      "loss": 0.6081,
+      "step": 55
+    },
+    {
+      "epoch": 0.1011743450767841,
+      "grad_norm": 0.29580862920928147,
+      "learning_rate": 2.9804644795462437e-05,
+      "loss": 0.6121,
+      "step": 56
+    },
+    {
+      "epoch": 0.10298102981029811,
+      "grad_norm": 0.3175507142787931,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.5976,
+      "step": 57
+    },
+    {
+      "epoch": 0.10478771454381211,
+      "grad_norm": 0.3374272189572956,
+      "learning_rate": 2.9774706718732255e-05,
+      "loss": 0.6061,
+      "step": 58
+    },
+    {
+      "epoch": 0.10659439927732611,
+      "grad_norm": 0.27546053233166856,
+      "learning_rate": 2.9758943828979444e-05,
+      "loss": 0.5922,
+      "step": 59
+    },
+    {
+      "epoch": 0.10840108401084012,
+      "grad_norm": 0.3657689574287652,
+      "learning_rate": 2.9742652451236414e-05,
+      "loss": 0.5934,
+      "step": 60
+    },
+    {
+      "epoch": 0.1102077687443541,
+      "grad_norm": 0.2986956716963071,
+      "learning_rate": 2.972583316886451e-05,
+      "loss": 0.5971,
+      "step": 61
+    },
+    {
+      "epoch": 0.1120144534778681,
+      "grad_norm": 0.3448276185716925,
+      "learning_rate": 2.9708486584128303e-05,
+      "loss": 0.6017,
+      "step": 62
+    },
+    {
+      "epoch": 0.11382113821138211,
+      "grad_norm": 0.3163562156051723,
+      "learning_rate": 2.9690613318173966e-05,
+      "loss": 0.6018,
+      "step": 63
+    },
+    {
+      "epoch": 0.11562782294489611,
+      "grad_norm": 0.2891799826775374,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.6001,
+      "step": 64
+    },
+    {
+      "epoch": 0.11743450767841011,
+      "grad_norm": 0.3052917388689653,
+      "learning_rate": 2.9653289321469715e-05,
+      "loss": 0.5941,
+      "step": 65
+    },
+    {
+      "epoch": 0.11924119241192412,
+      "grad_norm": 0.27037779234686826,
+      "learning_rate": 2.9633839927216793e-05,
+      "loss": 0.5971,
+      "step": 66
+    },
+    {
+      "epoch": 0.12104787714543812,
+      "grad_norm": 0.2837154841373324,
+      "learning_rate": 2.9613866524691867e-05,
+      "loss": 0.5873,
+      "step": 67
+    },
+    {
+      "epoch": 0.12285456187895212,
+      "grad_norm": 0.29318973292150885,
+      "learning_rate": 2.9593369829102173e-05,
+      "loss": 0.6033,
+      "step": 68
+    },
+    {
+      "epoch": 0.12466124661246612,
+      "grad_norm": 0.27320922800225206,
+      "learning_rate": 2.957235057439301e-05,
+      "loss": 0.6043,
+      "step": 69
+    },
+    {
+      "epoch": 0.12646793134598014,
+      "grad_norm": 0.2888792462126571,
+      "learning_rate": 2.955080951322147e-05,
+      "loss": 0.609,
+      "step": 70
+    },
+    {
+      "epoch": 0.12827461607949414,
+      "grad_norm": 0.3010426601423717,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.5817,
+      "step": 71
+    },
+    {
+      "epoch": 0.13008130081300814,
+      "grad_norm": 0.29363653670708806,
+      "learning_rate": 2.9506165075516148e-05,
+      "loss": 0.599,
+      "step": 72
+    },
+    {
+      "epoch": 0.13188798554652212,
+      "grad_norm": 0.3695495205161594,
+      "learning_rate": 2.9483063297609577e-05,
+      "loss": 0.5979,
+      "step": 73
+    },
+    {
+      "epoch": 0.13369467028003612,
+      "grad_norm": 0.312283280850037,
+      "learning_rate": 2.9459442910437798e-05,
+      "loss": 0.5894,
+      "step": 74
+    },
+    {
+      "epoch": 0.13550135501355012,
+      "grad_norm": 0.34410257132188554,
+      "learning_rate": 2.94353047597992e-05,
+      "loss": 0.5887,
+      "step": 75
+    },
+    {
+      "epoch": 0.13730803974706413,
+      "grad_norm": 0.2913822090159289,
+      "learning_rate": 2.941064971003224e-05,
+      "loss": 0.5844,
+      "step": 76
+    },
+    {
+      "epoch": 0.13911472448057813,
+      "grad_norm": 0.34659905630109983,
+      "learning_rate": 2.9385478643984484e-05,
+      "loss": 0.5796,
+      "step": 77
+    },
+    {
+      "epoch": 0.14092140921409213,
+      "grad_norm": 0.3690502006189352,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.591,
+      "step": 78
+    },
+    {
+      "epoch": 0.14272809394760613,
+      "grad_norm": 0.3032664893630925,
+      "learning_rate": 2.9333592086792113e-05,
+      "loss": 0.5986,
+      "step": 79
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "grad_norm": 0.34886668595229536,
+      "learning_rate": 2.9306878453600382e-05,
+      "loss": 0.6077,
+      "step": 80
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.3308668167904688,
+      "learning_rate": 2.9279652519967105e-05,
+      "loss": 0.5927,
+      "step": 81
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.34561229364377843,
+      "learning_rate": 2.9251915260798024e-05,
+      "loss": 0.585,
+      "step": 82
+    },
+    {
+      "epoch": 0.14995483288166214,
+      "grad_norm": 0.3315517031152509,
+      "learning_rate": 2.9223667669308395e-05,
+      "loss": 0.5951,
+      "step": 83
+    },
+    {
+      "epoch": 0.15176151761517614,
+      "grad_norm": 0.26853290095208654,
+      "learning_rate": 2.9194910756987464e-05,
+      "loss": 0.5885,
+      "step": 84
+    },
+    {
+      "epoch": 0.15356820234869015,
+      "grad_norm": 0.29448765107140906,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.5914,
+      "step": 85
+    },
+    {
+      "epoch": 0.15537488708220415,
+      "grad_norm": 0.2806586567612587,
+      "learning_rate": 2.9135873106960525e-05,
+      "loss": 0.5905,
+      "step": 86
+    },
+    {
+      "epoch": 0.15718157181571815,
+      "grad_norm": 0.3083804198003563,
+      "learning_rate": 2.9105594483273603e-05,
+      "loss": 0.5933,
+      "step": 87
+    },
+    {
+      "epoch": 0.15898825654923215,
+      "grad_norm": 0.29100169406971965,
+      "learning_rate": 2.9074810766717865e-05,
+      "loss": 0.5971,
+      "step": 88
+    },
+    {
+      "epoch": 0.16079494128274616,
+      "grad_norm": 0.3123482151135741,
+      "learning_rate": 2.904352305959606e-05,
+      "loss": 0.594,
+      "step": 89
+    },
+    {
+      "epoch": 0.16260162601626016,
+      "grad_norm": 0.29086528776110065,
+      "learning_rate": 2.9011732482257835e-05,
+      "loss": 0.5858,
+      "step": 90
+    },
+    {
+      "epoch": 0.16440831074977416,
+      "grad_norm": 0.32777518300425235,
+      "learning_rate": 2.89794401730596e-05,
+      "loss": 0.5838,
+      "step": 91
+    },
+    {
+      "epoch": 0.16621499548328816,
+      "grad_norm": 0.31282829577117277,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.5878,
+      "step": 92
+    },
+    {
+      "epoch": 0.16802168021680217,
+      "grad_norm": 0.30591224241436143,
+      "learning_rate": 2.8913355002297367e-05,
+      "loss": 0.5943,
+      "step": 93
+    },
+    {
+      "epoch": 0.16982836495031617,
+      "grad_norm": 0.3454363395865153,
+      "learning_rate": 2.887956450710995e-05,
+      "loss": 0.5939,
+      "step": 94
+    },
+    {
+      "epoch": 0.17163504968383017,
+      "grad_norm": 0.3119824836679083,
+      "learning_rate": 2.8845277012730963e-05,
+      "loss": 0.5859,
+      "step": 95
+    },
+    {
+      "epoch": 0.17344173441734417,
+      "grad_norm": 0.29451741781860913,
+      "learning_rate": 2.8810493746926364e-05,
+      "loss": 0.5853,
+      "step": 96
+    },
+    {
+      "epoch": 0.17524841915085818,
+      "grad_norm": 0.3034863549374876,
+      "learning_rate": 2.87752159552147e-05,
+      "loss": 0.591,
+      "step": 97
+    },
+    {
+      "epoch": 0.17705510388437218,
+      "grad_norm": 0.28746917797897076,
+      "learning_rate": 2.87394449008225e-05,
+      "loss": 0.5841,
+      "step": 98
+    },
+    {
+      "epoch": 0.17886178861788618,
+      "grad_norm": 0.30996182677103346,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.5969,
+      "step": 99
+    },
+    {
+      "epoch": 0.18066847335140018,
+      "grad_norm": 0.29091619146077263,
+      "learning_rate": 2.8666428145170385e-05,
+      "loss": 0.5702,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 553,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 115440686923776.0,
+  "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:e17e9ef49452dfbb88bdb398539e0416fca0be014460bc3a0231be831d4c7664
+size 8017