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 sha256:7318717ed1c68f510acb89d11ae502dabd001336fb37b2003a390ce9c23a510f
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b9c4aa21e6b93889b63f5f295e5c9c98cf69c89a8fcf3915e49df2cdbd1a17
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c9ac72c33c43c9a22245eacca6b7267d12b95162e499f91ca3c1a4304aaf40
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec2778a4028a52340257c07f98b931245834bdeb38122b87790426530ed925a
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ade347e400de480233e0e3ba081d238ab928e972915ab188c728ebf9908ee5
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23b217d55b7573b7f4dd169ffc3ba505a83f7de1af5b6e438d1559c4f7e2755
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c04ef8d4a6ae077862d301f613d61154d76480ee39ad9b8db0e0837e2bc1ca
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2abb61e95606c9adfb877502b35502f93ae74cb295aaa241cf8505f4218b35
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959e584d6913b374e7713cab56c03a218d6615a25be784c837b4ce09e19733dd
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59c6b0849da35b2da0162a1f69f65f02f89abd94b7ebd8b0be0987f15f047d7
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf3d1a5ead3dd9fa1c66c61b341cdf720ea0f4e3488f0ff70db6ea17cc3eac2
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55458f62a98149ffd9fa873d2b36577d5cb5d499bbf155a45ca2585850860849
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8f7e099be720ee726b9db90150c3d229e459a3807cd2f234e9c4a2ce938002
+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 +1,1133 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3333333333333333,
+  "eval_steps": 500,
+  "global_step": 157,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0021231422505307855,
+      "grad_norm": 6.233692311689662,
+      "learning_rate": 0.0,
+      "loss": 1.3677,
+      "step": 1
+    },
+    {
+      "epoch": 0.004246284501061571,
+      "grad_norm": 6.036329344230565,
+      "learning_rate": 1.2499999999999999e-06,
+      "loss": 1.4092,
+      "step": 2
+    },
+    {
+      "epoch": 0.006369426751592357,
+      "grad_norm": 6.056066195237692,
+      "learning_rate": 2.4999999999999998e-06,
+      "loss": 1.3995,
+      "step": 3
+    },
+    {
+      "epoch": 0.008492569002123142,
+      "grad_norm": 5.922965787004136,
+      "learning_rate": 3.75e-06,
+      "loss": 1.3975,
+      "step": 4
+    },
+    {
+      "epoch": 0.010615711252653927,
+      "grad_norm": 5.286633700836792,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 1.3654,
+      "step": 5
+    },
+    {
+      "epoch": 0.012738853503184714,
+      "grad_norm": 4.272128958690016,
+      "learning_rate": 6.25e-06,
+      "loss": 1.357,
+      "step": 6
+    },
+    {
+      "epoch": 0.014861995753715499,
+      "grad_norm": 3.3415834474393087,
+      "learning_rate": 7.5e-06,
+      "loss": 1.2136,
+      "step": 7
+    },
+    {
+      "epoch": 0.016985138004246284,
+      "grad_norm": 2.97877807094389,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.2796,
+      "step": 8
+    },
+    {
+      "epoch": 0.01910828025477707,
+      "grad_norm": 2.871670675310436,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 1.2221,
+      "step": 9
+    },
+    {
+      "epoch": 0.021231422505307854,
+      "grad_norm": 3.328688346998038,
+      "learning_rate": 1.125e-05,
+      "loss": 1.2234,
+      "step": 10
+    },
+    {
+      "epoch": 0.02335456475583864,
+      "grad_norm": 2.803564933108231,
+      "learning_rate": 1.25e-05,
+      "loss": 1.1813,
+      "step": 11
+    },
+    {
+      "epoch": 0.025477707006369428,
+      "grad_norm": 2.6965733342170646,
+      "learning_rate": 1.375e-05,
+      "loss": 1.1396,
+      "step": 12
+    },
+    {
+      "epoch": 0.027600849256900213,
+      "grad_norm": 3.096481749634196,
+      "learning_rate": 1.5e-05,
+      "loss": 1.2022,
+      "step": 13
+    },
+    {
+      "epoch": 0.029723991507430998,
+      "grad_norm": 2.274249270127275,
+      "learning_rate": 1.625e-05,
+      "loss": 1.1202,
+      "step": 14
+    },
+    {
+      "epoch": 0.03184713375796178,
+      "grad_norm": 3.884266388124913,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.1371,
+      "step": 15
+    },
+    {
+      "epoch": 0.03397027600849257,
+      "grad_norm": 1.6993184946564164,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 1.1044,
+      "step": 16
+    },
+    {
+      "epoch": 0.036093418259023353,
+      "grad_norm": 1.3282225362466542,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 1.0696,
+      "step": 17
+    },
+    {
+      "epoch": 0.03821656050955414,
+      "grad_norm": 1.2132093388653153,
+      "learning_rate": 2.125e-05,
+      "loss": 1.0457,
+      "step": 18
+    },
+    {
+      "epoch": 0.040339702760084924,
+      "grad_norm": 1.2631509255285398,
+      "learning_rate": 2.25e-05,
+      "loss": 1.0374,
+      "step": 19
+    },
+    {
+      "epoch": 0.04246284501061571,
+      "grad_norm": 1.194394279683961,
+      "learning_rate": 2.3749999999999998e-05,
+      "loss": 0.9467,
+      "step": 20
+    },
+    {
+      "epoch": 0.044585987261146494,
+      "grad_norm": 1.098708611169601,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0645,
+      "step": 21
+    },
+    {
+      "epoch": 0.04670912951167728,
+      "grad_norm": 1.0283648174128268,
+      "learning_rate": 2.625e-05,
+      "loss": 1.0394,
+      "step": 22
+    },
+    {
+      "epoch": 0.04883227176220807,
+      "grad_norm": 0.9732861680373749,
+      "learning_rate": 2.75e-05,
+      "loss": 0.9515,
+      "step": 23
+    },
+    {
+      "epoch": 0.050955414012738856,
+      "grad_norm": 1.017693167952402,
+      "learning_rate": 2.875e-05,
+      "loss": 0.9749,
+      "step": 24
+    },
+    {
+      "epoch": 0.05307855626326964,
+      "grad_norm": 1.1330379055126547,
+      "learning_rate": 3e-05,
+      "loss": 1.0073,
+      "step": 25
+    },
+    {
+      "epoch": 0.055201698513800426,
+      "grad_norm": 1.0745948466977544,
+      "learning_rate": 2.9999629537566803e-05,
+      "loss": 1.0051,
+      "step": 26
+    },
+    {
+      "epoch": 0.05732484076433121,
+      "grad_norm": 0.8795447467848742,
+      "learning_rate": 2.9998518168566207e-05,
+      "loss": 1.0527,
+      "step": 27
+    },
+    {
+      "epoch": 0.059447983014861996,
+      "grad_norm": 1.1167437998178333,
+      "learning_rate": 2.999666594789427e-05,
+      "loss": 1.0584,
+      "step": 28
+    },
+    {
+      "epoch": 0.06157112526539278,
+      "grad_norm": 1.0126995680355033,
+      "learning_rate": 2.999407296704142e-05,
+      "loss": 1.0291,
+      "step": 29
+    },
+    {
+      "epoch": 0.06369426751592357,
+      "grad_norm": 0.8834749944368594,
+      "learning_rate": 2.9990739354087918e-05,
+      "loss": 1.0342,
+      "step": 30
+    },
+    {
+      "epoch": 0.06581740976645435,
+      "grad_norm": 0.980242387134944,
+      "learning_rate": 2.9986665273697548e-05,
+      "loss": 1.0209,
+      "step": 31
+    },
+    {
+      "epoch": 0.06794055201698514,
+      "grad_norm": 0.8415998788153699,
+      "learning_rate": 2.9981850927109472e-05,
+      "loss": 1.0274,
+      "step": 32
+    },
+    {
+      "epoch": 0.07006369426751592,
+      "grad_norm": 0.9010169241333265,
+      "learning_rate": 2.9976296552128305e-05,
+      "loss": 0.9844,
+      "step": 33
+    },
+    {
+      "epoch": 0.07218683651804671,
+      "grad_norm": 0.8466313083198588,
+      "learning_rate": 2.9970002423112342e-05,
+      "loss": 0.9862,
+      "step": 34
+    },
+    {
+      "epoch": 0.07430997876857749,
+      "grad_norm": 3.0775818765498997,
+      "learning_rate": 2.996296885096003e-05,
+      "loss": 0.9921,
+      "step": 35
+    },
+    {
+      "epoch": 0.07643312101910828,
+      "grad_norm": 0.9668150868467069,
+      "learning_rate": 2.9955196183094604e-05,
+      "loss": 1.0312,
+      "step": 36
+    },
+    {
+      "epoch": 0.07855626326963906,
+      "grad_norm": 0.8491853067637553,
+      "learning_rate": 2.9946684803446928e-05,
+      "loss": 0.9704,
+      "step": 37
+    },
+    {
+      "epoch": 0.08067940552016985,
+      "grad_norm": 1.4205641764205312,
+      "learning_rate": 2.9937435132436517e-05,
+      "loss": 0.9659,
+      "step": 38
+    },
+    {
+      "epoch": 0.08280254777070063,
+      "grad_norm": 0.9441030271305156,
+      "learning_rate": 2.9927447626950795e-05,
+      "loss": 0.9507,
+      "step": 39
+    },
+    {
+      "epoch": 0.08492569002123142,
+      "grad_norm": 1.2675209983159783,
+      "learning_rate": 2.9916722780322504e-05,
+      "loss": 1.002,
+      "step": 40
+    },
+    {
+      "epoch": 0.0870488322717622,
+      "grad_norm": 1.6463034987153113,
+      "learning_rate": 2.9905261122305344e-05,
+      "loss": 0.9619,
+      "step": 41
+    },
+    {
+      "epoch": 0.08917197452229299,
+      "grad_norm": 0.9187757905390965,
+      "learning_rate": 2.9893063219047815e-05,
+      "loss": 0.9691,
+      "step": 42
+    },
+    {
+      "epoch": 0.09129511677282377,
+      "grad_norm": 0.9018029010217173,
+      "learning_rate": 2.988012967306524e-05,
+      "loss": 0.9658,
+      "step": 43
+    },
+    {
+      "epoch": 0.09341825902335456,
+      "grad_norm": 0.7942951837701693,
+      "learning_rate": 2.9866461123210005e-05,
+      "loss": 1.036,
+      "step": 44
+    },
+    {
+      "epoch": 0.09554140127388536,
+      "grad_norm": 0.7920942774535104,
+      "learning_rate": 2.985205824464001e-05,
+      "loss": 1.0362,
+      "step": 45
+    },
+    {
+      "epoch": 0.09766454352441614,
+      "grad_norm": 1.1538568110872267,
+      "learning_rate": 2.983692174878531e-05,
+      "loss": 1.0226,
+      "step": 46
+    },
+    {
+      "epoch": 0.09978768577494693,
+      "grad_norm": 0.8728667083119837,
+      "learning_rate": 2.9821052383312987e-05,
+      "loss": 0.9848,
+      "step": 47
+    },
+    {
+      "epoch": 0.10191082802547771,
+      "grad_norm": 0.9041523514230781,
+      "learning_rate": 2.980445093209021e-05,
+      "loss": 0.9875,
+      "step": 48
+    },
+    {
+      "epoch": 0.1040339702760085,
+      "grad_norm": 1.0596951962405752,
+      "learning_rate": 2.9787118215145502e-05,
+      "loss": 0.9708,
+      "step": 49
+    },
+    {
+      "epoch": 0.10615711252653928,
+      "grad_norm": 0.9427913699014273,
+      "learning_rate": 2.976905508862828e-05,
+      "loss": 1.009,
+      "step": 50
+    },
+    {
+      "epoch": 0.10828025477707007,
+      "grad_norm": 0.8275899758352401,
+      "learning_rate": 2.9750262444766502e-05,
+      "loss": 0.9985,
+      "step": 51
+    },
+    {
+      "epoch": 0.11040339702760085,
+      "grad_norm": 0.975852608473361,
+      "learning_rate": 2.9730741211822654e-05,
+      "loss": 1.0062,
+      "step": 52
+    },
+    {
+      "epoch": 0.11252653927813164,
+      "grad_norm": 0.8051301886044567,
+      "learning_rate": 2.9710492354047857e-05,
+      "loss": 0.9339,
+      "step": 53
+    },
+    {
+      "epoch": 0.11464968152866242,
+      "grad_norm": 0.8707635236666643,
+      "learning_rate": 2.968951687163426e-05,
+      "loss": 0.9955,
+      "step": 54
+    },
+    {
+      "epoch": 0.11677282377919321,
+      "grad_norm": 0.8254929493091868,
+      "learning_rate": 2.9667815800665637e-05,
+      "loss": 1.0298,
+      "step": 55
+    },
+    {
+      "epoch": 0.11889596602972399,
+      "grad_norm": 0.7562926195663171,
+      "learning_rate": 2.9645390213066193e-05,
+      "loss": 1.0611,
+      "step": 56
+    },
+    {
+      "epoch": 0.12101910828025478,
+      "grad_norm": 0.8226232019747459,
+      "learning_rate": 2.9622241216547623e-05,
+      "loss": 0.9991,
+      "step": 57
+    },
+    {
+      "epoch": 0.12314225053078556,
+      "grad_norm": 0.7982200631080218,
+      "learning_rate": 2.9598369954554405e-05,
+      "loss": 0.9991,
+      "step": 58
+    },
+    {
+      "epoch": 0.12526539278131635,
+      "grad_norm": 0.6963466420104463,
+      "learning_rate": 2.957377760620732e-05,
+      "loss": 0.9941,
+      "step": 59
+    },
+    {
+      "epoch": 0.12738853503184713,
+      "grad_norm": 0.7408513127997496,
+      "learning_rate": 2.9548465386245185e-05,
+      "loss": 0.9874,
+      "step": 60
+    },
+    {
+      "epoch": 0.12951167728237792,
+      "grad_norm": 0.8271991090411744,
+      "learning_rate": 2.952243454496488e-05,
+      "loss": 0.9139,
+      "step": 61
+    },
+    {
+      "epoch": 0.1316348195329087,
+      "grad_norm": 1.0499980155535253,
+      "learning_rate": 2.9495686368159592e-05,
+      "loss": 0.9768,
+      "step": 62
+    },
+    {
+      "epoch": 0.1337579617834395,
+      "grad_norm": 0.7840493370566994,
+      "learning_rate": 2.946822217705526e-05,
+      "loss": 0.999,
+      "step": 63
+    },
+    {
+      "epoch": 0.13588110403397027,
+      "grad_norm": 0.7806728112401357,
+      "learning_rate": 2.9440043328245366e-05,
+      "loss": 1.0215,
+      "step": 64
+    },
+    {
+      "epoch": 0.13800424628450106,
+      "grad_norm": 0.7631865352856676,
+      "learning_rate": 2.9411151213623894e-05,
+      "loss": 1.0313,
+      "step": 65
+    },
+    {
+      "epoch": 0.14012738853503184,
+      "grad_norm": 0.7125983390885618,
+      "learning_rate": 2.938154726031659e-05,
+      "loss": 0.9669,
+      "step": 66
+    },
+    {
+      "epoch": 0.14225053078556263,
+      "grad_norm": 0.7130914703890735,
+      "learning_rate": 2.9351232930610473e-05,
+      "loss": 0.9745,
+      "step": 67
+    },
+    {
+      "epoch": 0.14437367303609341,
+      "grad_norm": 0.7946605985222294,
+      "learning_rate": 2.932020972188157e-05,
+      "loss": 0.9708,
+      "step": 68
+    },
+    {
+      "epoch": 0.1464968152866242,
+      "grad_norm": 0.6811138210740744,
+      "learning_rate": 2.9288479166521014e-05,
+      "loss": 0.9494,
+      "step": 69
+    },
+    {
+      "epoch": 0.14861995753715498,
+      "grad_norm": 0.772893213577846,
+      "learning_rate": 2.9256042831859295e-05,
+      "loss": 1.0612,
+      "step": 70
+    },
+    {
+      "epoch": 0.15074309978768577,
+      "grad_norm": 0.7592068515404989,
+      "learning_rate": 2.9222902320088882e-05,
+      "loss": 1.0019,
+      "step": 71
+    },
+    {
+      "epoch": 0.15286624203821655,
+      "grad_norm": 0.7696389426407971,
+      "learning_rate": 2.9189059268185057e-05,
+      "loss": 1.0222,
+      "step": 72
+    },
+    {
+      "epoch": 0.15498938428874734,
+      "grad_norm": 0.7196168653178467,
+      "learning_rate": 2.9154515347825065e-05,
+      "loss": 0.9702,
+      "step": 73
+    },
+    {
+      "epoch": 0.15711252653927812,
+      "grad_norm": 0.8084046623013887,
+      "learning_rate": 2.9119272265305546e-05,
+      "loss": 0.9476,
+      "step": 74
+    },
+    {
+      "epoch": 0.1592356687898089,
+      "grad_norm": 0.7666084490813502,
+      "learning_rate": 2.9083331761458247e-05,
+      "loss": 0.9927,
+      "step": 75
+    },
+    {
+      "epoch": 0.1613588110403397,
+      "grad_norm": 0.8464390116357674,
+      "learning_rate": 2.904669561156404e-05,
+      "loss": 0.909,
+      "step": 76
+    },
+    {
+      "epoch": 0.16348195329087048,
+      "grad_norm": 0.6443641909940253,
+      "learning_rate": 2.9009365625265215e-05,
+      "loss": 0.9603,
+      "step": 77
+    },
+    {
+      "epoch": 0.16560509554140126,
+      "grad_norm": 0.7599832914924824,
+      "learning_rate": 2.8971343646476114e-05,
+      "loss": 0.9786,
+      "step": 78
+    },
+    {
+      "epoch": 0.16772823779193205,
+      "grad_norm": 0.806592225804777,
+      "learning_rate": 2.893263155329204e-05,
+      "loss": 0.9774,
+      "step": 79
+    },
+    {
+      "epoch": 0.16985138004246284,
+      "grad_norm": 0.7338345781204999,
+      "learning_rate": 2.8893231257896502e-05,
+      "loss": 1.076,
+      "step": 80
+    },
+    {
+      "epoch": 0.17197452229299362,
+      "grad_norm": 0.7256977111670229,
+      "learning_rate": 2.8853144706466725e-05,
+      "loss": 1.0003,
+      "step": 81
+    },
+    {
+      "epoch": 0.1740976645435244,
+      "grad_norm": 0.9486924335177603,
+      "learning_rate": 2.881237387907757e-05,
+      "loss": 1.061,
+      "step": 82
+    },
+    {
+      "epoch": 0.1762208067940552,
+      "grad_norm": 0.7245363724222085,
+      "learning_rate": 2.8770920789603687e-05,
+      "loss": 0.9772,
+      "step": 83
+    },
+    {
+      "epoch": 0.17834394904458598,
+      "grad_norm": 0.8462340519151804,
+      "learning_rate": 2.8728787485620068e-05,
+      "loss": 1.0097,
+      "step": 84
+    },
+    {
+      "epoch": 0.18046709129511676,
+      "grad_norm": 0.7351160195293913,
+      "learning_rate": 2.868597604830088e-05,
+      "loss": 0.99,
+      "step": 85
+    },
+    {
+      "epoch": 0.18259023354564755,
+      "grad_norm": 0.7346962642071149,
+      "learning_rate": 2.864248859231669e-05,
+      "loss": 1.0185,
+      "step": 86
+    },
+    {
+      "epoch": 0.18471337579617833,
+      "grad_norm": 0.7264358663319485,
+      "learning_rate": 2.859832726573e-05,
+      "loss": 1.018,
+      "step": 87
+    },
+    {
+      "epoch": 0.18683651804670912,
+      "grad_norm": 0.6502521161134233,
+      "learning_rate": 2.855349424988915e-05,
+      "loss": 0.9539,
+      "step": 88
+    },
+    {
+      "epoch": 0.18895966029723993,
+      "grad_norm": 0.7429051973625352,
+      "learning_rate": 2.8507991759320545e-05,
+      "loss": 0.932,
+      "step": 89
+    },
+    {
+      "epoch": 0.1910828025477707,
+      "grad_norm": 0.7337271359665005,
+      "learning_rate": 2.8461822041619312e-05,
+      "loss": 1.0024,
+      "step": 90
+    },
+    {
+      "epoch": 0.1932059447983015,
+      "grad_norm": 0.696436735871088,
+      "learning_rate": 2.841498737733824e-05,
+      "loss": 0.9241,
+      "step": 91
+    },
+    {
+      "epoch": 0.19532908704883228,
+      "grad_norm": 0.8367022783932109,
+      "learning_rate": 2.8367490079875154e-05,
+      "loss": 0.9643,
+      "step": 92
+    },
+    {
+      "epoch": 0.19745222929936307,
+      "grad_norm": 0.7508090587584874,
+      "learning_rate": 2.831933249535865e-05,
+      "loss": 0.9753,
+      "step": 93
+    },
+    {
+      "epoch": 0.19957537154989385,
+      "grad_norm": 0.7462348768378886,
+      "learning_rate": 2.827051700253217e-05,
+      "loss": 0.958,
+      "step": 94
+    },
+    {
+      "epoch": 0.20169851380042464,
+      "grad_norm": 0.7525272193363061,
+      "learning_rate": 2.8221046012636558e-05,
+      "loss": 1.0095,
+      "step": 95
+    },
+    {
+      "epoch": 0.20382165605095542,
+      "grad_norm": 0.6809918403435731,
+      "learning_rate": 2.817092196929091e-05,
+      "loss": 0.9593,
+      "step": 96
+    },
+    {
+      "epoch": 0.2059447983014862,
+      "grad_norm": 0.6932971348903458,
+      "learning_rate": 2.8120147348371912e-05,
+      "loss": 0.9581,
+      "step": 97
+    },
+    {
+      "epoch": 0.208067940552017,
+      "grad_norm": 0.7197887059084126,
+      "learning_rate": 2.8068724657891507e-05,
+      "loss": 0.9432,
+      "step": 98
+    },
+    {
+      "epoch": 0.21019108280254778,
+      "grad_norm": 0.7347184474062712,
+      "learning_rate": 2.801665643787303e-05,
+      "loss": 1.0137,
+      "step": 99
+    },
+    {
+      "epoch": 0.21231422505307856,
+      "grad_norm": 0.673328010924802,
+      "learning_rate": 2.7963945260225748e-05,
+      "loss": 1.0148,
+      "step": 100
+    },
+    {
+      "epoch": 0.21443736730360935,
+      "grad_norm": 0.7214998628963789,
+      "learning_rate": 2.7910593728617813e-05,
+      "loss": 1.0484,
+      "step": 101
+    },
+    {
+      "epoch": 0.21656050955414013,
+      "grad_norm": 0.6722704514414892,
+      "learning_rate": 2.7856604478347655e-05,
+      "loss": 0.9654,
+      "step": 102
+    },
+    {
+      "epoch": 0.21868365180467092,
+      "grad_norm": 0.6556980159522945,
+      "learning_rate": 2.7801980176213798e-05,
+      "loss": 0.9148,
+      "step": 103
+    },
+    {
+      "epoch": 0.2208067940552017,
+      "grad_norm": 0.7796844299678404,
+      "learning_rate": 2.7746723520383174e-05,
+      "loss": 0.9803,
+      "step": 104
+    },
+    {
+      "epoch": 0.2229299363057325,
+      "grad_norm": 0.69615473393741,
+      "learning_rate": 2.76908372402578e-05,
+      "loss": 0.9389,
+      "step": 105
+    },
+    {
+      "epoch": 0.22505307855626328,
+      "grad_norm": 0.665149808571595,
+      "learning_rate": 2.763432409633998e-05,
+      "loss": 0.9407,
+      "step": 106
+    },
+    {
+      "epoch": 0.22717622080679406,
+      "grad_norm": 0.6679067532269544,
+      "learning_rate": 2.7577186880095966e-05,
+      "loss": 0.9864,
+      "step": 107
+    },
+    {
+      "epoch": 0.22929936305732485,
+      "grad_norm": 0.717736772052187,
+      "learning_rate": 2.7519428413818034e-05,
+      "loss": 0.9568,
+      "step": 108
+    },
+    {
+      "epoch": 0.23142250530785563,
+      "grad_norm": 0.7365137124208776,
+      "learning_rate": 2.7461051550485116e-05,
+      "loss": 1.0027,
+      "step": 109
+    },
+    {
+      "epoch": 0.23354564755838642,
+      "grad_norm": 0.7060692871299123,
+      "learning_rate": 2.740205917362186e-05,
+      "loss": 1.0176,
+      "step": 110
+    },
+    {
+      "epoch": 0.2356687898089172,
+      "grad_norm": 0.6086155886816632,
+      "learning_rate": 2.7342454197156194e-05,
+      "loss": 0.9614,
+      "step": 111
+    },
+    {
+      "epoch": 0.23779193205944799,
+      "grad_norm": 0.6391029724554078,
+      "learning_rate": 2.728223956527539e-05,
+      "loss": 0.979,
+      "step": 112
+    },
+    {
+      "epoch": 0.23991507430997877,
+      "grad_norm": 0.7225858742160614,
+      "learning_rate": 2.722141825228066e-05,
+      "loss": 0.9522,
+      "step": 113
+    },
+    {
+      "epoch": 0.24203821656050956,
+      "grad_norm": 0.6685886845969267,
+      "learning_rate": 2.7159993262440228e-05,
+      "loss": 0.9574,
+      "step": 114
+    },
+    {
+      "epoch": 0.24416135881104034,
+      "grad_norm": 0.6648088183213471,
+      "learning_rate": 2.7097967629840906e-05,
+      "loss": 1.008,
+      "step": 115
+    },
+    {
+      "epoch": 0.24628450106157113,
+      "grad_norm": 0.7204962333279492,
+      "learning_rate": 2.703534441823827e-05,
+      "loss": 0.9785,
+      "step": 116
+    },
+    {
+      "epoch": 0.2484076433121019,
+      "grad_norm": 0.6804549324723432,
+      "learning_rate": 2.6972126720905293e-05,
+      "loss": 0.9816,
+      "step": 117
+    },
+    {
+      "epoch": 0.2505307855626327,
+      "grad_norm": 0.6837624060695675,
+      "learning_rate": 2.6908317660479583e-05,
+      "loss": 0.9813,
+      "step": 118
+    },
+    {
+      "epoch": 0.2526539278131635,
+      "grad_norm": 0.6706972759019354,
+      "learning_rate": 2.68439203888091e-05,
+      "loss": 1.0129,
+      "step": 119
+    },
+    {
+      "epoch": 0.25477707006369427,
+      "grad_norm": 0.7603607267519649,
+      "learning_rate": 2.6778938086796512e-05,
+      "loss": 1.0785,
+      "step": 120
+    },
+    {
+      "epoch": 0.25690021231422505,
+      "grad_norm": 0.701884945821394,
+      "learning_rate": 2.6713373964242043e-05,
+      "loss": 0.9629,
+      "step": 121
+    },
+    {
+      "epoch": 0.25902335456475584,
+      "grad_norm": 0.7096804682790832,
+      "learning_rate": 2.6647231259684946e-05,
+      "loss": 0.9646,
+      "step": 122
+    },
+    {
+      "epoch": 0.2611464968152866,
+      "grad_norm": 0.6445523205552592,
+      "learning_rate": 2.6580513240243524e-05,
+      "loss": 1.0163,
+      "step": 123
+    },
+    {
+      "epoch": 0.2632696390658174,
+      "grad_norm": 0.6863246456533727,
+      "learning_rate": 2.651322320145375e-05,
+      "loss": 0.9842,
+      "step": 124
+    },
+    {
+      "epoch": 0.2653927813163482,
+      "grad_norm": 0.691665965346161,
+      "learning_rate": 2.6445364467106494e-05,
+      "loss": 0.9421,
+      "step": 125
+    },
+    {
+      "epoch": 0.267515923566879,
+      "grad_norm": 0.7584893620552549,
+      "learning_rate": 2.637694038908333e-05,
+      "loss": 1.0348,
+      "step": 126
+    },
+    {
+      "epoch": 0.26963906581740976,
+      "grad_norm": 0.6613598336840398,
+      "learning_rate": 2.630795434719099e-05,
+      "loss": 0.9464,
+      "step": 127
+    },
+    {
+      "epoch": 0.27176220806794055,
+      "grad_norm": 0.6713699116927843,
+      "learning_rate": 2.623840974899439e-05,
+      "loss": 0.8904,
+      "step": 128
+    },
+    {
+      "epoch": 0.27388535031847133,
+      "grad_norm": 0.816037128777881,
+      "learning_rate": 2.616831002964834e-05,
+      "loss": 0.9743,
+      "step": 129
+    },
+    {
+      "epoch": 0.2760084925690021,
+      "grad_norm": 0.7338762748040034,
+      "learning_rate": 2.609765865172786e-05,
+      "loss": 0.9847,
+      "step": 130
+    },
+    {
+      "epoch": 0.2781316348195329,
+      "grad_norm": 0.6161573010385878,
+      "learning_rate": 2.6026459105057127e-05,
+      "loss": 0.9607,
+      "step": 131
+    },
+    {
+      "epoch": 0.2802547770700637,
+      "grad_norm": 0.6784919139990105,
+      "learning_rate": 2.5954714906537116e-05,
+      "loss": 0.9833,
+      "step": 132
+    },
+    {
+      "epoch": 0.2823779193205945,
+      "grad_norm": 0.7455868873904333,
+      "learning_rate": 2.5882429599971872e-05,
+      "loss": 0.9333,
+      "step": 133
+    },
+    {
+      "epoch": 0.28450106157112526,
+      "grad_norm": 0.6606022069654393,
+      "learning_rate": 2.580960675589347e-05,
+      "loss": 1.0049,
+      "step": 134
+    },
+    {
+      "epoch": 0.28662420382165604,
+      "grad_norm": 0.6870029740052253,
+      "learning_rate": 2.573624997138565e-05,
+      "loss": 1.0137,
+      "step": 135
+    },
+    {
+      "epoch": 0.28874734607218683,
+      "grad_norm": 0.6822500856445419,
+      "learning_rate": 2.5662362869906123e-05,
+      "loss": 1.0007,
+      "step": 136
+    },
+    {
+      "epoch": 0.2908704883227176,
+      "grad_norm": 0.6035427107718914,
+      "learning_rate": 2.558794910110761e-05,
+      "loss": 0.937,
+      "step": 137
+    },
+    {
+      "epoch": 0.2929936305732484,
+      "grad_norm": 0.6041202314277974,
+      "learning_rate": 2.5513012340657557e-05,
+      "loss": 0.9461,
+      "step": 138
+    },
+    {
+      "epoch": 0.2951167728237792,
+      "grad_norm": 0.6390470706425474,
+      "learning_rate": 2.5437556290056575e-05,
+      "loss": 0.9358,
+      "step": 139
+    },
+    {
+      "epoch": 0.29723991507430997,
+      "grad_norm": 0.7195254765489666,
+      "learning_rate": 2.5361584676455627e-05,
+      "loss": 0.9976,
+      "step": 140
+    },
+    {
+      "epoch": 0.29936305732484075,
+      "grad_norm": 0.6521311999355591,
+      "learning_rate": 2.5285101252471874e-05,
+      "loss": 0.9377,
+      "step": 141
+    },
+    {
+      "epoch": 0.30148619957537154,
+      "grad_norm": 0.6409749095351458,
+      "learning_rate": 2.5208109796003364e-05,
+      "loss": 1.0104,
+      "step": 142
+    },
+    {
+      "epoch": 0.3036093418259023,
+      "grad_norm": 0.6315495351185857,
+      "learning_rate": 2.5130614110042415e-05,
+      "loss": 1.0316,
+      "step": 143
+    },
+    {
+      "epoch": 0.3057324840764331,
+      "grad_norm": 0.6737333438485361,
+      "learning_rate": 2.5052618022487733e-05,
+      "loss": 0.9078,
+      "step": 144
+    },
+    {
+      "epoch": 0.3078556263269639,
+      "grad_norm": 0.6808606797582761,
+      "learning_rate": 2.4974125385955374e-05,
+      "loss": 0.9745,
+      "step": 145
+    },
+    {
+      "epoch": 0.3099787685774947,
+      "grad_norm": 0.6728298363507792,
+      "learning_rate": 2.4895140077588412e-05,
+      "loss": 0.9231,
+      "step": 146
+    },
+    {
+      "epoch": 0.31210191082802546,
+      "grad_norm": 0.737270504862064,
+      "learning_rate": 2.481566599886546e-05,
+      "loss": 0.9499,
+      "step": 147
+    },
+    {
+      "epoch": 0.31422505307855625,
+      "grad_norm": 0.6659360676868527,
+      "learning_rate": 2.473570707540793e-05,
+      "loss": 1.036,
+      "step": 148
+    },
+    {
+      "epoch": 0.31634819532908703,
+      "grad_norm": 0.6279327692414004,
+      "learning_rate": 2.4655267256786126e-05,
+      "loss": 1.0277,
+      "step": 149
+    },
+    {
+      "epoch": 0.3184713375796178,
+      "grad_norm": 0.6827718930790617,
+      "learning_rate": 2.4574350516324176e-05,
+      "loss": 0.9544,
+      "step": 150
+    },
+    {
+      "epoch": 0.3205944798301486,
+      "grad_norm": 0.6764712245297005,
+      "learning_rate": 2.4492960850903757e-05,
+      "loss": 0.9915,
+      "step": 151
+    },
+    {
+      "epoch": 0.3227176220806794,
+      "grad_norm": 0.6118211254231126,
+      "learning_rate": 2.4411102280766658e-05,
+      "loss": 0.9918,
+      "step": 152
+    },
+    {
+      "epoch": 0.3248407643312102,
+      "grad_norm": 0.6445432947438029,
+      "learning_rate": 2.432877884931623e-05,
+      "loss": 1.0199,
+      "step": 153
+    },
+    {
+      "epoch": 0.32696390658174096,
+      "grad_norm": 0.6555286244268101,
+      "learning_rate": 2.4245994622917636e-05,
+      "loss": 1.0144,
+      "step": 154
+    },
+    {
+      "epoch": 0.32908704883227174,
+      "grad_norm": 0.5747726408332037,
+      "learning_rate": 2.4162753690696998e-05,
+      "loss": 1.0059,
+      "step": 155
+    },
+    {
+      "epoch": 0.33121019108280253,
+      "grad_norm": 0.6633624122819982,
+      "learning_rate": 2.4079060164339427e-05,
+      "loss": 0.9892,
+      "step": 156
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.624099565922787,
+      "learning_rate": 2.3994918177885906e-05,
+      "loss": 1.0363,
+      "step": 157
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 471,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 157,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 23254277554176.0,
+  "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:cd681504643138a679e55133a50cd258b4e3cf9ca5f57dfb9fcdc5045782b5d3
+size 8017