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 sha256:6c1d50f0ec75755b6371fa0cee03e270ad831ffb66a8285750a3220d2816f413
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1c242250eeff1cbf8db46609b19027d21d423fc507802aa74311d75ce2cf66
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28ef1e9636ea28deac7d1064026acb83b828aabddb11df34ce50e05e89ebd69
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adf227c2b9ff735137325514e76e9abd250c4ef620e944165339f48eb9f5c4d
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344c23a15dde4fdce112365c0b319f51d2c4f02c726e8b81e9c3593e96cab236
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ebbbb70dc9053f0c01d75cdef03854b357ba0f52550b0eaf281d03ba9f7b5d
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae7470adc6eabc9f06b2131f7dc3ec3f8621387eb9a258bff381bd3af3832d1
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e5dee8862b76aa2167d05fe8a6eaa82c1668f7058dee496d6c7f04f21458d4
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14353dc0f6ab88d002f9087912e79dc82f7e8461335a9ae37366449037bf49f2
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff95c6c86e2710e0936bf41e797be42797ca7f1afe3836a1854b1ce2bedc29b
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9054ff396ba7813042b68f4a093cd21576ec6edfe9f9512c31f5fb7151836e01
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590510e1a168bbd04879645c5b83fd527113bfa464786b1bf04d5fbb93ec1580
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9736c01729a7ed5086edc8d73c5ff06c01de626eb5b589d63b51789b5a59fa0
+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 +1,475 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016,
+      "grad_norm": 2.3387899124656393,
+      "learning_rate": 0.0,
+      "loss": 1.1321,
+      "step": 1
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 2.2739175729395282,
+      "learning_rate": 3.2258064516129035e-07,
+      "loss": 0.9759,
+      "step": 2
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 3.2333006230979437,
+      "learning_rate": 6.451612903225807e-07,
+      "loss": 1.0141,
+      "step": 3
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.350357276823565,
+      "learning_rate": 9.67741935483871e-07,
+      "loss": 0.9947,
+      "step": 4
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.1839271581694755,
+      "learning_rate": 1.2903225806451614e-06,
+      "loss": 1.023,
+      "step": 5
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.153599307977408,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 0.9609,
+      "step": 6
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 2.1555129140427067,
+      "learning_rate": 1.935483870967742e-06,
+      "loss": 0.9622,
+      "step": 7
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 2.008278114649717,
+      "learning_rate": 2.2580645161290324e-06,
+      "loss": 0.9711,
+      "step": 8
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 1.9242182990110015,
+      "learning_rate": 2.580645161290323e-06,
+      "loss": 0.9673,
+      "step": 9
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.750252408219067,
+      "learning_rate": 2.903225806451613e-06,
+      "loss": 0.9438,
+      "step": 10
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 1.6939070396617073,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 0.8756,
+      "step": 11
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 1.2834939133740737,
+      "learning_rate": 3.548387096774194e-06,
+      "loss": 0.9823,
+      "step": 12
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 1.4367519479529964,
+      "learning_rate": 3.870967741935484e-06,
+      "loss": 0.9596,
+      "step": 13
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 1.3144994907230427,
+      "learning_rate": 4.193548387096774e-06,
+      "loss": 1.0521,
+      "step": 14
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.0689628463958285,
+      "learning_rate": 4.516129032258065e-06,
+      "loss": 0.938,
+      "step": 15
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 1.2021712620582392,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 1.0955,
+      "step": 16
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 1.2539951248917753,
+      "learning_rate": 5.161290322580646e-06,
+      "loss": 0.9417,
+      "step": 17
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 1.4053233581800462,
+      "learning_rate": 5.483870967741935e-06,
+      "loss": 0.9956,
+      "step": 18
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 1.0278616263126648,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 0.7439,
+      "step": 19
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.256128877382818,
+      "learning_rate": 6.129032258064517e-06,
+      "loss": 0.9542,
+      "step": 20
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.9487549369343321,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.9816,
+      "step": 21
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 1.0891896971338342,
+      "learning_rate": 6.774193548387097e-06,
+      "loss": 1.0704,
+      "step": 22
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 1.1660258370107575,
+      "learning_rate": 7.096774193548388e-06,
+      "loss": 0.8931,
+      "step": 23
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.9415137340919071,
+      "learning_rate": 7.4193548387096784e-06,
+      "loss": 0.8683,
+      "step": 24
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0798354285638785,
+      "learning_rate": 7.741935483870968e-06,
+      "loss": 1.0478,
+      "step": 25
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.8096142802637235,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 0.8466,
+      "step": 26
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7447999799600428,
+      "learning_rate": 8.387096774193549e-06,
+      "loss": 0.7486,
+      "step": 27
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.8621800122661538,
+      "learning_rate": 8.70967741935484e-06,
+      "loss": 0.9581,
+      "step": 28
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.7940321530754582,
+      "learning_rate": 9.03225806451613e-06,
+      "loss": 0.8867,
+      "step": 29
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.8496750615573763,
+      "learning_rate": 9.35483870967742e-06,
+      "loss": 0.9179,
+      "step": 30
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.8798601594137285,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 0.8834,
+      "step": 31
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.8818390794513048,
+      "learning_rate": 1e-05,
+      "loss": 0.8952,
+      "step": 32
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.8322934845468171,
+      "learning_rate": 9.999683023724021e-06,
+      "loss": 1.029,
+      "step": 33
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.7007834456821566,
+      "learning_rate": 9.998732135085665e-06,
+      "loss": 0.8438,
+      "step": 34
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6137020406246253,
+      "learning_rate": 9.99714745464859e-06,
+      "loss": 0.8435,
+      "step": 35
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.7231796555332799,
+      "learning_rate": 9.994929183335237e-06,
+      "loss": 0.9646,
+      "step": 36
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.6180598082755802,
+      "learning_rate": 9.992077602401358e-06,
+      "loss": 0.9616,
+      "step": 37
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.6567886708960547,
+      "learning_rate": 9.988593073400354e-06,
+      "loss": 0.8522,
+      "step": 38
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.7454067800699115,
+      "learning_rate": 9.984476038137437e-06,
+      "loss": 0.9052,
+      "step": 39
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.6714316518124167,
+      "learning_rate": 9.979727018613607e-06,
+      "loss": 0.8103,
+      "step": 40
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.6229146249540587,
+      "learning_rate": 9.974346616959476e-06,
+      "loss": 0.8401,
+      "step": 41
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.6448840489157996,
+      "learning_rate": 9.968335515358916e-06,
+      "loss": 0.9144,
+      "step": 42
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.528060268374605,
+      "learning_rate": 9.961694475962562e-06,
+      "loss": 0.8348,
+      "step": 43
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.5902102953939741,
+      "learning_rate": 9.954424340791195e-06,
+      "loss": 0.7721,
+      "step": 44
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5526442876969153,
+      "learning_rate": 9.94652603162896e-06,
+      "loss": 0.8438,
+      "step": 45
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.5331236922634145,
+      "learning_rate": 9.938000549906509e-06,
+      "loss": 0.8023,
+      "step": 46
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.6339240906385807,
+      "learning_rate": 9.92884897657402e-06,
+      "loss": 0.894,
+      "step": 47
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5283804877111584,
+      "learning_rate": 9.919072471964146e-06,
+      "loss": 0.9069,
+      "step": 48
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.5170169653511614,
+      "learning_rate": 9.908672275644898e-06,
+      "loss": 0.8051,
+      "step": 49
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4763529065504662,
+      "learning_rate": 9.897649706262474e-06,
+      "loss": 0.8301,
+      "step": 50
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.4890239660294139,
+      "learning_rate": 9.88600616137407e-06,
+      "loss": 0.8629,
+      "step": 51
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.37392633165922323,
+      "learning_rate": 9.873743117270691e-06,
+      "loss": 0.8343,
+      "step": 52
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5097372006252004,
+      "learning_rate": 9.860862128789954e-06,
+      "loss": 0.9025,
+      "step": 53
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.5331140780823508,
+      "learning_rate": 9.847364829118963e-06,
+      "loss": 0.7832,
+      "step": 54
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.5371583880849503,
+      "learning_rate": 9.833252929587231e-06,
+      "loss": 0.7241,
+      "step": 55
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.45993890737280607,
+      "learning_rate": 9.818528219449705e-06,
+      "loss": 0.8964,
+      "step": 56
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.4715847632418153,
+      "learning_rate": 9.803192565659898e-06,
+      "loss": 0.8623,
+      "step": 57
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.4942244137822645,
+      "learning_rate": 9.78724791263318e-06,
+      "loss": 0.7657,
+      "step": 58
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.45536932211394177,
+      "learning_rate": 9.770696282000245e-06,
+      "loss": 0.8766,
+      "step": 59
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.4891485391099054,
+      "learning_rate": 9.753539772350792e-06,
+      "loss": 0.8621,
+      "step": 60
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.45887131278496746,
+      "learning_rate": 9.735780558967434e-06,
+      "loss": 0.7718,
+      "step": 61
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.5002555111850944,
+      "learning_rate": 9.717420893549902e-06,
+      "loss": 0.8746,
+      "step": 62
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5002555111850944,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.7591,
+      "step": 63
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 310,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 12613769428992.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c1028dc3622e720731c6412f8963725b6a7cc32a4ba1fa24bca1f33df7d5c1
+size 8081