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:c4ec39b8c542dec46c584428bcc41f239ddfa2d7f5f5e01282aa8fc17cfd43f7
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:888bc516d004ed68e4d137a0425fc721f903558076e2c5eb3091f98f13c2f7d7
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9098519c5209091cdbf2ae6ad89e6f8623b2733f39415bb5e58e18a16c81182c
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98285851600cd3b86069655c14976bdd8da7e969d489bdd46d0e0b37ba6c3ad0
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05637820a3e97cbe0c767eb03e0f7d83cff36fd50d4c8bc584d936d7e068e3b
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc5f4b89fbc1cfde43a03bcbd497bc48c2e5664e8d5d0ff18b5f4f99968b881
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cdcf393112aee1f1b1979b9a8d317ecbd3f30ba04b45640981768ef8cc8641b
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0c698599c34c6ebca6bce94f7d2bf4b01ba907b12dc3687ce69cb08e302ed0
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc388c6012d6ddba57665bfe588a5c3791d0ed33a18117ef0e8fe13364a81bc
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab710fe0b2f24fffdb29679d2eb5d3224e762cb3615c74d37f405bb3c3a9b18b
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e18dc22e8b72e7a489b13911b19ccf42f66d360b823f5f92a005bdedcc827e
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94eec06606cc616588201353704c6b13b76af4a4c9631cbd86d6baa60107a32
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e617bdbabf28f382f1b6c67e6031a9e42bed1fd93899be3c91232a9ebbd627
+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 +1,832 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 114,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017543859649122806,
+      "grad_norm": 2.1737315354989266,
+      "learning_rate": 0.0,
+      "loss": 0.8483,
+      "step": 1
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 2.0657831287103607,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8763,
+      "step": 2
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 2.2705565927471225,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.019,
+      "step": 3
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 1.8847905520566954,
+      "learning_rate": 1e-05,
+      "loss": 1.0442,
+      "step": 4
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "grad_norm": 1.6215868467951315,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8301,
+      "step": 5
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 1.3337654525321527,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.967,
+      "step": 6
+    },
+    {
+      "epoch": 0.12280701754385964,
+      "grad_norm": 2.3177821608360234,
+      "learning_rate": 2e-05,
+      "loss": 0.9657,
+      "step": 7
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 1.9407807377668538,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.9063,
+      "step": 8
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 2.333688544412328,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.9327,
+      "step": 9
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.8911158364164133,
+      "learning_rate": 3e-05,
+      "loss": 0.9615,
+      "step": 10
+    },
+    {
+      "epoch": 0.19298245614035087,
+      "grad_norm": 1.559026746068459,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.9983,
+      "step": 11
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 1.0012950206512936,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.8713,
+      "step": 12
+    },
+    {
+      "epoch": 0.22807017543859648,
+      "grad_norm": 1.0896746007190306,
+      "learning_rate": 4e-05,
+      "loss": 0.9018,
+      "step": 13
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 1.1472331615890097,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.8905,
+      "step": 14
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 1.0827434164812821,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.9487,
+      "step": 15
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.8407939026078357,
+      "learning_rate": 5e-05,
+      "loss": 0.9016,
+      "step": 16
+    },
+    {
+      "epoch": 0.2982456140350877,
+      "grad_norm": 1.256351670462119,
+      "learning_rate": 4.999830770009406e-05,
+      "loss": 1.0016,
+      "step": 17
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 1.010708781438488,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.8827,
+      "step": 18
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.7503718658890081,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.9054,
+      "step": 19
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.8427918773123176,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.9468,
+      "step": 20
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.9103198542357233,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.8832,
+      "step": 21
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.743975757226857,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.7529,
+      "step": 22
+    },
+    {
+      "epoch": 0.40350877192982454,
+      "grad_norm": 0.8055578797506145,
+      "learning_rate": 4.9917122201112656e-05,
+      "loss": 0.889,
+      "step": 23
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.8546590892160185,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.7896,
+      "step": 24
+    },
+    {
+      "epoch": 0.43859649122807015,
+      "grad_norm": 0.6051439965679499,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.9219,
+      "step": 25
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 0.7522440995111975,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.8917,
+      "step": 26
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.7072008972448397,
+      "learning_rate": 4.979550878853154e-05,
+      "loss": 0.8044,
+      "step": 27
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.5952822120665937,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.8763,
+      "step": 28
+    },
+    {
+      "epoch": 0.5087719298245614,
+      "grad_norm": 0.5803355862918257,
+      "learning_rate": 4.971454298742779e-05,
+      "loss": 0.8983,
+      "step": 29
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.666437418274057,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.7866,
+      "step": 30
+    },
+    {
+      "epoch": 0.543859649122807,
+      "grad_norm": 0.6919189164588267,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.8412,
+      "step": 31
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.5772289061045422,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.7779,
+      "step": 32
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.6384456727598309,
+      "learning_rate": 4.951251239389948e-05,
+      "loss": 0.8722,
+      "step": 33
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.7003155529960633,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.9772,
+      "step": 34
+    },
+    {
+      "epoch": 0.6140350877192983,
+      "grad_norm": 0.5892482774139678,
+      "learning_rate": 4.939155700460536e-05,
+      "loss": 0.8181,
+      "step": 35
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.7141350627505272,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.8379,
+      "step": 36
+    },
+    {
+      "epoch": 0.6491228070175439,
+      "grad_norm": 0.6685379755417092,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 0.876,
+      "step": 37
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5887972405354546,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.8834,
+      "step": 38
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.6547850047970274,
+      "learning_rate": 4.9110093502873476e-05,
+      "loss": 0.9068,
+      "step": 39
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.5095372843368391,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.871,
+      "step": 40
+    },
+    {
+      "epoch": 0.7192982456140351,
+      "grad_norm": 0.5803092931334194,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.8804,
+      "step": 41
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.5157094405208372,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.8112,
+      "step": 42
+    },
+    {
+      "epoch": 0.7543859649122807,
+      "grad_norm": 0.5763799658576816,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.8485,
+      "step": 43
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.5206239155896253,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.7658,
+      "step": 44
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.5163119284367372,
+      "learning_rate": 4.859021265983959e-05,
+      "loss": 0.8806,
+      "step": 45
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.5555872744357858,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.8559,
+      "step": 46
+    },
+    {
+      "epoch": 0.8245614035087719,
+      "grad_norm": 0.670329020537153,
+      "learning_rate": 4.839123789598829e-05,
+      "loss": 0.8667,
+      "step": 47
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.5517318833150326,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.8424,
+      "step": 48
+    },
+    {
+      "epoch": 0.8596491228070176,
+      "grad_norm": 0.6399166130889407,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.9417,
+      "step": 49
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.460883037522045,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.6751,
+      "step": 50
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.6278603703151171,
+      "learning_rate": 4.7955402672006854e-05,
+      "loss": 0.9086,
+      "step": 51
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.5482062880943421,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.8832,
+      "step": 52
+    },
+    {
+      "epoch": 0.9298245614035088,
+      "grad_norm": 0.5538960900799985,
+      "learning_rate": 4.771877822433911e-05,
+      "loss": 0.8332,
+      "step": 53
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.5020357523197391,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 0.7833,
+      "step": 54
+    },
+    {
+      "epoch": 0.9649122807017544,
+      "grad_norm": 0.5299810912852558,
+      "learning_rate": 4.7469851157479177e-05,
+      "loss": 0.8219,
+      "step": 55
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.48572413576489937,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.8327,
+      "step": 56
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7694567676131596,
+      "learning_rate": 4.7208756269825104e-05,
+      "loss": 0.6932,
+      "step": 57
+    },
+    {
+      "epoch": 1.0175438596491229,
+      "grad_norm": 0.8079734171770722,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.7363,
+      "step": 58
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.647606443516366,
+      "learning_rate": 4.693563494886455e-05,
+      "loss": 0.628,
+      "step": 59
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 1.0392055903524327,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.7284,
+      "step": 60
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.8936107628035881,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.6199,
+      "step": 61
+    },
+    {
+      "epoch": 1.087719298245614,
+      "grad_norm": 0.8579847990954221,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.6542,
+      "step": 62
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 1.2135497198079113,
+      "learning_rate": 4.6353911039513145e-05,
+      "loss": 0.7282,
+      "step": 63
+    },
+    {
+      "epoch": 1.1228070175438596,
+      "grad_norm": 0.8104073129740915,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.6731,
+      "step": 64
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.6601313754612921,
+      "learning_rate": 4.604562346488144e-05,
+      "loss": 0.6216,
+      "step": 65
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.7521560385174539,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.6368,
+      "step": 66
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 0.6696118869453084,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.6243,
+      "step": 67
+    },
+    {
+      "epoch": 1.1929824561403508,
+      "grad_norm": 0.7323191679088321,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.6631,
+      "step": 68
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.7881911923428006,
+      "learning_rate": 4.539503170110431e-05,
+      "loss": 0.702,
+      "step": 69
+    },
+    {
+      "epoch": 1.2280701754385965,
+      "grad_norm": 0.5443171520898024,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.6556,
+      "step": 70
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.7465685103291306,
+      "learning_rate": 4.50530798188761e-05,
+      "loss": 0.7226,
+      "step": 71
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 1.531802448485134,
+      "learning_rate": 4.48780199123712e-05,
+      "loss": 0.6821,
+      "step": 72
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 0.624551106382425,
+      "learning_rate": 4.4700268840168045e-05,
+      "loss": 0.6704,
+      "step": 73
+    },
+    {
+      "epoch": 1.2982456140350878,
+      "grad_norm": 0.5646709447787752,
+      "learning_rate": 4.4519850666916484e-05,
+      "loss": 0.6031,
+      "step": 74
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.6162637626547116,
+      "learning_rate": 4.43367898183491e-05,
+      "loss": 0.7309,
+      "step": 75
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.484728084443174,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.6089,
+      "step": 76
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 0.5348661093893772,
+      "learning_rate": 4.396283958372173e-05,
+      "loss": 0.6013,
+      "step": 77
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.6972365743462106,
+      "learning_rate": 4.377200082453749e-05,
+      "loss": 0.7103,
+      "step": 78
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.6386714887467159,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 0.6876,
+      "step": 79
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 0.6068938883006068,
+      "learning_rate": 4.3382725201495723e-05,
+      "loss": 0.6655,
+      "step": 80
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.5578279802500624,
+      "learning_rate": 4.318434103932622e-05,
+      "loss": 0.6688,
+      "step": 81
+    },
+    {
+      "epoch": 1.4385964912280702,
+      "grad_norm": 0.5450559810011418,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.6545,
+      "step": 82
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 0.549555813592061,
+      "learning_rate": 4.278021430025343e-05,
+      "loss": 0.5803,
+      "step": 83
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.44599243421537427,
+      "learning_rate": 4.257452643564155e-05,
+      "loss": 0.5056,
+      "step": 84
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.6512205627641299,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.6704,
+      "step": 85
+    },
+    {
+      "epoch": 1.5087719298245614,
+      "grad_norm": 0.5031784031963774,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.6411,
+      "step": 86
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.5371693274835859,
+      "learning_rate": 4.194329997864331e-05,
+      "loss": 0.7647,
+      "step": 87
+    },
+    {
+      "epoch": 1.543859649122807,
+      "grad_norm": 0.5952220323734707,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.6663,
+      "step": 88
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.5194062067573968,
+      "learning_rate": 4.1510965599975196e-05,
+      "loss": 0.7005,
+      "step": 89
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.5666524807032483,
+      "learning_rate": 4.129143072053638e-05,
+      "loss": 0.604,
+      "step": 90
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.5389713669315125,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.6349,
+      "step": 91
+    },
+    {
+      "epoch": 1.6140350877192984,
+      "grad_norm": 0.5311149694642213,
+      "learning_rate": 4.0845774184967754e-05,
+      "loss": 0.652,
+      "step": 92
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.5012325622032431,
+      "learning_rate": 4.0619712863599e-05,
+      "loss": 0.5946,
+      "step": 93
+    },
+    {
+      "epoch": 1.6491228070175439,
+      "grad_norm": 0.4814283230741368,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.6008,
+      "step": 94
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5273571145503247,
+      "learning_rate": 4.0161277134970345e-05,
+      "loss": 0.6998,
+      "step": 95
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.6037954834513913,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.6152,
+      "step": 96
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 0.5375890783535183,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.7677,
+      "step": 97
+    },
+    {
+      "epoch": 1.719298245614035,
+      "grad_norm": 0.6267427489443681,
+      "learning_rate": 3.945830840419966e-05,
+      "loss": 0.6621,
+      "step": 98
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.5070654701641488,
+      "learning_rate": 3.9220028077571295e-05,
+      "loss": 0.679,
+      "step": 99
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 0.49591448977957925,
+      "learning_rate": 3.897982258676867e-05,
+      "loss": 0.6153,
+      "step": 100
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 0.5563015062976071,
+      "learning_rate": 3.873772445177015e-05,
+      "loss": 0.7054,
+      "step": 101
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.4874896431926999,
+      "learning_rate": 3.8493766448787825e-05,
+      "loss": 0.6942,
+      "step": 102
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.6557911386705954,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 0.695,
+      "step": 103
+    },
+    {
+      "epoch": 1.8245614035087718,
+      "grad_norm": 0.5154404737450541,
+      "learning_rate": 3.8000403198230387e-05,
+      "loss": 0.5788,
+      "step": 104
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.4665270737354506,
+      "learning_rate": 3.775106474414188e-05,
+      "loss": 0.5437,
+      "step": 105
+    },
+    {
+      "epoch": 1.8596491228070176,
+      "grad_norm": 0.7148660834996573,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.758,
+      "step": 106
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.7335976271467938,
+      "learning_rate": 3.7247242955952175e-05,
+      "loss": 0.6691,
+      "step": 107
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.5963174425512796,
+      "learning_rate": 3.699282783125616e-05,
+      "loss": 0.668,
+      "step": 108
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.5791219305747107,
+      "learning_rate": 3.673678906964727e-05,
+      "loss": 0.5826,
+      "step": 109
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 0.5583303920187029,
+      "learning_rate": 3.6479161334675296e-05,
+      "loss": 0.7001,
+      "step": 110
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.6110054211158291,
+      "learning_rate": 3.621997950501156e-05,
+      "loss": 0.7133,
+      "step": 111
+    },
+    {
+      "epoch": 1.9649122807017543,
+      "grad_norm": 0.617058874054503,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.6776,
+      "step": 112
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 0.5818691639875067,
+      "learning_rate": 3.569709412354136e-05,
+      "loss": 0.7395,
+      "step": 113
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7383826511530396,
+      "learning_rate": 3.543346136204545e-05,
+      "loss": 0.5666,
+      "step": 114
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 285,
+  "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": 26112855638016.0,
+  "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:d83b4df5d706e4c8bc431f088d2170998a3a8eafe51554ccb621ba77c95afe02
+size 8017