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:fe657aded3f7cd32cbc6e5a95cc0038a86186a6f19246857934cf5b4de1aaf96
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52b092a414f9587bebf44d0de09b12e2e3696d6f20f3e7494b5146d6e5715d9
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2dbec41f3aa9ac0f81a3487701c3ac27aee33c17d0b66df2c238f7fdb08a25
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b94eda4b556ee13fc56454e67b9b9032971f97d2c1e39d22ed3b7945495f403
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f21711cd89c0d208024b01b9304a1f5bb085c0796337e28f80b57f3859ea92f
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deaff088a4ab05b7ed8cc0a0ff398a05d70a12c931de72bc1ed69e7e954aeeaa
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ce0ca4487080196f363ccc5e0f9168449257e560c480f4ee79c4500971c527
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc811f39a312b851932af70237beb537b583c05bbb7a59d9beabf2510c21a6c
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c591de2562bdce357de7db4eefc42e390595e9299e0bb633432508224177d631
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9f034f59d2532b953bfea5bbf4b01731d912f10f0f3bb3e3242c612cf708bb
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e295c78794565e4a5d63257e381f4460f7806b60abf60652f88ce08a67d3974e
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f694fd78b49df68afa81ee7efb7658487cec4e1d986973e0a39366a1c5c409a
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12b44924237cef2c1f4c302174ce1cf2eb7353f80a4976343b6373ff08093dd
+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 +1,1357 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 189,
+  "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
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.7921009597496743,
+      "learning_rate": 9.67890959377418e-06,
+      "loss": 0.8141,
+      "step": 64
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.5263404719063407,
+      "learning_rate": 9.658762842283343e-06,
+      "loss": 0.8,
+      "step": 65
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.6027486092631968,
+      "learning_rate": 9.638025403873939e-06,
+      "loss": 0.8869,
+      "step": 66
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.5040803182249076,
+      "learning_rate": 9.616699907856368e-06,
+      "loss": 0.7434,
+      "step": 67
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.4794307353380867,
+      "learning_rate": 9.594789058101154e-06,
+      "loss": 0.7162,
+      "step": 68
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.519708365022811,
+      "learning_rate": 9.57229563269612e-06,
+      "loss": 0.9109,
+      "step": 69
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5405956328678668,
+      "learning_rate": 9.549222483594154e-06,
+      "loss": 0.7813,
+      "step": 70
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.5713243651929747,
+      "learning_rate": 9.525572536251608e-06,
+      "loss": 0.7776,
+      "step": 71
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.7593604265555369,
+      "learning_rate": 9.501348789257373e-06,
+      "loss": 0.7817,
+      "step": 72
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.5104218019933199,
+      "learning_rate": 9.476554313952697e-06,
+      "loss": 0.7754,
+      "step": 73
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.4357678519578492,
+      "learning_rate": 9.451192254041759e-06,
+      "loss": 0.7828,
+      "step": 74
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.48992867265594076,
+      "learning_rate": 9.425265825193077e-06,
+      "loss": 0.7823,
+      "step": 75
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.4744625173124652,
+      "learning_rate": 9.398778314631801e-06,
+      "loss": 0.7303,
+      "step": 76
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.5598627796833753,
+      "learning_rate": 9.371733080722911e-06,
+      "loss": 0.7444,
+      "step": 77
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.4312343972662455,
+      "learning_rate": 9.34413355254542e-06,
+      "loss": 0.836,
+      "step": 78
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.624677329344369,
+      "learning_rate": 9.31598322945759e-06,
+      "loss": 0.8577,
+      "step": 79
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.49859023374542194,
+      "learning_rate": 9.287285680653254e-06,
+      "loss": 0.7683,
+      "step": 80
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6015424998788388,
+      "learning_rate": 9.258044544709276e-06,
+      "loss": 0.8227,
+      "step": 81
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.44003554877608686,
+      "learning_rate": 9.228263529124199e-06,
+      "loss": 0.7863,
+      "step": 82
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.5609641970743867,
+      "learning_rate": 9.197946409848196e-06,
+      "loss": 0.8774,
+      "step": 83
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.43143646632622484,
+      "learning_rate": 9.167097030804289e-06,
+      "loss": 0.8157,
+      "step": 84
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.43142249232413526,
+      "learning_rate": 9.135719303400995e-06,
+      "loss": 0.7508,
+      "step": 85
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.4657223032122722,
+      "learning_rate": 9.103817206036383e-06,
+      "loss": 0.6509,
+      "step": 86
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.48523334387177774,
+      "learning_rate": 9.071394783593664e-06,
+      "loss": 0.8359,
+      "step": 87
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.46496551627210725,
+      "learning_rate": 9.038456146928325e-06,
+      "loss": 0.864,
+      "step": 88
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.4440780678769445,
+      "learning_rate": 9.005005472346923e-06,
+      "loss": 0.7902,
+      "step": 89
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.561826912899574,
+      "learning_rate": 8.971047001077561e-06,
+      "loss": 0.8076,
+      "step": 90
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.4900358752234758,
+      "learning_rate": 8.936585038732143e-06,
+      "loss": 0.6602,
+      "step": 91
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.4606489965356049,
+      "learning_rate": 8.90162395476046e-06,
+      "loss": 0.8151,
+      "step": 92
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.5359817129085576,
+      "learning_rate": 8.866168181896198e-06,
+      "loss": 0.8108,
+      "step": 93
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.4099923668319849,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.7473,
+      "step": 94
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.46662939848509505,
+      "learning_rate": 8.793790613463956e-06,
+      "loss": 0.8871,
+      "step": 95
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.6601471838069068,
+      "learning_rate": 8.756877994684818e-06,
+      "loss": 0.8559,
+      "step": 96
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.45387042686918283,
+      "learning_rate": 8.719489039427256e-06,
+      "loss": 0.7211,
+      "step": 97
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.39658772389509284,
+      "learning_rate": 8.681628488255986e-06,
+      "loss": 0.8225,
+      "step": 98
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.48808248239123686,
+      "learning_rate": 8.643301141529619e-06,
+      "loss": 0.7259,
+      "step": 99
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.5005912376865987,
+      "learning_rate": 8.604511858792006e-06,
+      "loss": 0.8113,
+      "step": 100
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.39380103997630306,
+      "learning_rate": 8.565265558156101e-06,
+      "loss": 0.782,
+      "step": 101
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5511984663976129,
+      "learning_rate": 8.525567215680397e-06,
+      "loss": 0.8738,
+      "step": 102
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.4456656598175722,
+      "learning_rate": 8.485421864737997e-06,
+      "loss": 0.7922,
+      "step": 103
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.4908529752157155,
+      "learning_rate": 8.444834595378434e-06,
+      "loss": 0.8487,
+      "step": 104
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.4428491434503844,
+      "learning_rate": 8.403810553682307e-06,
+      "loss": 0.8335,
+      "step": 105
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.5044508101327926,
+      "learning_rate": 8.362354941108803e-06,
+      "loss": 0.7921,
+      "step": 106
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.5179814826203967,
+      "learning_rate": 8.320473013836197e-06,
+      "loss": 0.8403,
+      "step": 107
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5470226099168956,
+      "learning_rate": 8.278170082095422e-06,
+      "loss": 0.8999,
+      "step": 108
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.41030649187861784,
+      "learning_rate": 8.23545150949679e-06,
+      "loss": 0.8033,
+      "step": 109
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5622265643432103,
+      "learning_rate": 8.192322712349917e-06,
+      "loss": 0.7425,
+      "step": 110
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5223132208572823,
+      "learning_rate": 8.148789158977012e-06,
+      "loss": 0.7316,
+      "step": 111
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.475126333442523,
+      "learning_rate": 8.104856369019525e-06,
+      "loss": 0.7683,
+      "step": 112
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.4948572562329079,
+      "learning_rate": 8.060529912738316e-06,
+      "loss": 0.7647,
+      "step": 113
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.531807251361054,
+      "learning_rate": 8.0158154103074e-06,
+      "loss": 0.7611,
+      "step": 114
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.47670080587998737,
+      "learning_rate": 7.970718531101365e-06,
+      "loss": 0.8092,
+      "step": 115
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.4114578657588441,
+      "learning_rate": 7.925244992976538e-06,
+      "loss": 0.8859,
+      "step": 116
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.5115548644684491,
+      "learning_rate": 7.879400561546033e-06,
+      "loss": 0.8891,
+      "step": 117
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.5853821031130237,
+      "learning_rate": 7.833191049448706e-06,
+      "loss": 0.6497,
+      "step": 118
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.3798635295552685,
+      "learning_rate": 7.786622315612182e-06,
+      "loss": 0.8151,
+      "step": 119
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 0.4971866098065484,
+      "learning_rate": 7.739700264509993e-06,
+      "loss": 0.7809,
+      "step": 120
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.4980674292423549,
+      "learning_rate": 7.692430845412946e-06,
+      "loss": 0.7679,
+      "step": 121
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.4324290073091459,
+      "learning_rate": 7.644820051634813e-06,
+      "loss": 0.8501,
+      "step": 122
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.47176687932737493,
+      "learning_rate": 7.596873919772438e-06,
+      "loss": 0.8027,
+      "step": 123
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.43463683245782003,
+      "learning_rate": 7.548598528940354e-06,
+      "loss": 0.7492,
+      "step": 124
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.49151296507554265,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7126,
+      "step": 125
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7056512813119306,
+      "learning_rate": 7.451084494783668e-06,
+      "loss": 0.9934,
+      "step": 126
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8222112850756275,
+      "learning_rate": 7.401858215313228e-06,
+      "loss": 0.7107,
+      "step": 127
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.578857909730416,
+      "learning_rate": 7.352327403013779e-06,
+      "loss": 0.7626,
+      "step": 128
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.6947157428046444,
+      "learning_rate": 7.302498337922293e-06,
+      "loss": 0.8212,
+      "step": 129
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 1.3653434931121922,
+      "learning_rate": 7.2523773378913655e-06,
+      "loss": 0.7474,
+      "step": 130
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8976124611811842,
+      "learning_rate": 7.201970757788172e-06,
+      "loss": 0.6376,
+      "step": 131
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.5152408942741,
+      "learning_rate": 7.151284988688731e-06,
+      "loss": 0.6641,
+      "step": 132
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.6830633595485539,
+      "learning_rate": 7.100326457067576e-06,
+      "loss": 0.7996,
+      "step": 133
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.5496861285450714,
+      "learning_rate": 7.049101623982938e-06,
+      "loss": 0.7581,
+      "step": 134
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.6403401425933127,
+      "learning_rate": 6.9976169842575526e-06,
+      "loss": 0.7457,
+      "step": 135
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.44381400078067595,
+      "learning_rate": 6.945879065655164e-06,
+      "loss": 0.6706,
+      "step": 136
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.607564640506437,
+      "learning_rate": 6.893894428052881e-06,
+      "loss": 0.7532,
+      "step": 137
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.5370083889151855,
+      "learning_rate": 6.841669662609437e-06,
+      "loss": 0.723,
+      "step": 138
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.503787140696792,
+      "learning_rate": 6.789211390929497e-06,
+      "loss": 0.6432,
+      "step": 139
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.48811253497835444,
+      "learning_rate": 6.736526264224101e-06,
+      "loss": 0.7416,
+      "step": 140
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.5393544740145144,
+      "learning_rate": 6.6836209624673575e-06,
+      "loss": 0.6972,
+      "step": 141
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.5146295742117404,
+      "learning_rate": 6.6305021935494755e-06,
+      "loss": 0.7735,
+      "step": 142
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.5354676350111098,
+      "learning_rate": 6.5771766924262795e-06,
+      "loss": 0.7254,
+      "step": 143
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 0.48957997280536275,
+      "learning_rate": 6.523651220265269e-06,
+      "loss": 0.6449,
+      "step": 144
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.6260723291086323,
+      "learning_rate": 6.469932563588386e-06,
+      "loss": 0.6024,
+      "step": 145
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.6277559902277917,
+      "learning_rate": 6.41602753341152e-06,
+      "loss": 0.7118,
+      "step": 146
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.5654085188913539,
+      "learning_rate": 6.361942964380967e-06,
+      "loss": 0.7289,
+      "step": 147
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 0.5511085996838134,
+      "learning_rate": 6.307685713906835e-06,
+      "loss": 0.7078,
+      "step": 148
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.48643046392503236,
+      "learning_rate": 6.2532626612936035e-06,
+      "loss": 0.6913,
+      "step": 149
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.4251201514104161,
+      "learning_rate": 6.1986807068678926e-06,
+      "loss": 0.8129,
+      "step": 150
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4957551218147004,
+      "learning_rate": 6.143946771103561e-06,
+      "loss": 0.7541,
+      "step": 151
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 0.5337634201089703,
+      "learning_rate": 6.089067793744258e-06,
+      "loss": 0.7421,
+      "step": 152
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.45135282751579137,
+      "learning_rate": 6.034050732923538e-06,
+      "loss": 0.7623,
+      "step": 153
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 0.40984798370772846,
+      "learning_rate": 5.978902564282616e-06,
+      "loss": 0.8119,
+      "step": 154
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.42530164890628464,
+      "learning_rate": 5.923630280085948e-06,
+      "loss": 0.7985,
+      "step": 155
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.390559143940863,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.6778,
+      "step": 156
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.45694185479460997,
+      "learning_rate": 5.8127414118779825e-06,
+      "loss": 0.7597,
+      "step": 157
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.4952633583203359,
+      "learning_rate": 5.757138887522884e-06,
+      "loss": 0.7168,
+      "step": 158
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.4342497218363157,
+      "learning_rate": 5.701440365141799e-06,
+      "loss": 0.6564,
+      "step": 159
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 0.4718029081715289,
+      "learning_rate": 5.645652906778808e-06,
+      "loss": 0.66,
+      "step": 160
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.5236548730626042,
+      "learning_rate": 5.5897835857542315e-06,
+      "loss": 0.7189,
+      "step": 161
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.4217271822666547,
+      "learning_rate": 5.533839485767795e-06,
+      "loss": 0.6501,
+      "step": 162
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.51236732912632,
+      "learning_rate": 5.477827700000492e-06,
+      "loss": 0.5564,
+      "step": 163
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 0.5794935429954644,
+      "learning_rate": 5.421755330215223e-06,
+      "loss": 0.7193,
+      "step": 164
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.43579809758377336,
+      "learning_rate": 5.365629485856381e-06,
+      "loss": 0.782,
+      "step": 165
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.4273541248432265,
+      "learning_rate": 5.30945728314841e-06,
+      "loss": 0.6904,
+      "step": 166
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.5127404572609707,
+      "learning_rate": 5.253245844193564e-06,
+      "loss": 0.7756,
+      "step": 167
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 0.4502193208238627,
+      "learning_rate": 5.197002296068878e-06,
+      "loss": 0.7199,
+      "step": 168
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.6522139082928684,
+      "learning_rate": 5.140733769922525e-06,
+      "loss": 0.7523,
+      "step": 169
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.4604865675922319,
+      "learning_rate": 5.084447400069656e-06,
+      "loss": 0.658,
+      "step": 170
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.47189630919959746,
+      "learning_rate": 5.0281503230878304e-06,
+      "loss": 0.7168,
+      "step": 171
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 0.45853515734923483,
+      "learning_rate": 4.971849676912172e-06,
+      "loss": 0.59,
+      "step": 172
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.6617371663600603,
+      "learning_rate": 4.915552599930345e-06,
+      "loss": 0.7154,
+      "step": 173
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.4581535675670496,
+      "learning_rate": 4.859266230077474e-06,
+      "loss": 0.8279,
+      "step": 174
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.44995006651439057,
+      "learning_rate": 4.802997703931124e-06,
+      "loss": 0.7029,
+      "step": 175
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.6247080166668746,
+      "learning_rate": 4.746754155806437e-06,
+      "loss": 0.6663,
+      "step": 176
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.43343619400050193,
+      "learning_rate": 4.6905427168515914e-06,
+      "loss": 0.7364,
+      "step": 177
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.6592346345644005,
+      "learning_rate": 4.63437051414362e-06,
+      "loss": 0.7337,
+      "step": 178
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.464552230592377,
+      "learning_rate": 4.5782446697847775e-06,
+      "loss": 0.7164,
+      "step": 179
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 0.47084386707640963,
+      "learning_rate": 4.52217229999951e-06,
+      "loss": 0.7538,
+      "step": 180
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.49465152130409273,
+      "learning_rate": 4.466160514232206e-06,
+      "loss": 0.6193,
+      "step": 181
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 0.7463104607291,
+      "learning_rate": 4.410216414245771e-06,
+      "loss": 0.6887,
+      "step": 182
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.5311673012762305,
+      "learning_rate": 4.354347093221194e-06,
+      "loss": 0.8275,
+      "step": 183
+    },
+    {
+      "epoch": 2.928,
+      "grad_norm": 0.4765968349930382,
+      "learning_rate": 4.298559634858202e-06,
+      "loss": 0.709,
+      "step": 184
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.4041073627021218,
+      "learning_rate": 4.2428611124771184e-06,
+      "loss": 0.7103,
+      "step": 185
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.5090780248152671,
+      "learning_rate": 4.187258588122019e-06,
+      "loss": 0.7976,
+      "step": 186
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.6082158511853922,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.7694,
+      "step": 187
+    },
+    {
+      "epoch": 2.992,
+      "grad_norm": 0.5727874160786263,
+      "learning_rate": 4.076369719914055e-06,
+      "loss": 0.7123,
+      "step": 188
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5727874160786263,
+      "learning_rate": 4.021097435717386e-06,
+      "loss": 0.5299,
+      "step": 189
+    }
+  ],
+  "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": 37970102255616.0,
+  "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