Initial upload: fine-tuned tagger

.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

README.md

@@ -0,0 +1,68 @@
+---
+language:
+- ko
+- en
+tags:
+- text-generation
+- keyword-extraction
+- tag-generation
+license: other
+---
+
+# Qwen3-0.6B Float:Right Tagger (float-right.app)
+
+This repository contains a fine-tuned tag generator based on **Qwen/Qwen3-0.6B**.
+
+## What it does
+
+Given a memo/text, it returns **a JSON array of 3–10 tags**:
+
+- Prefer coarse tags (not overly detailed)
+- Keeps the same language as input (Korean -> Korean, English -> English)
+- Avoids underscores `_`
+
+> In production, parse only the first JSON array `[ ... ]` from the output.
+
+## Quick usage (Transformers)
+
+```python
+import json, re, torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MODEL_DIR = "./"  # or your HF repo id
+
+tok = AutoTokenizer.from_pretrained(MODEL_DIR, trust_remote_code=True)
+if tok.pad_token is None:
+    tok.pad_token = tok.eos_token
+
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_DIR, torch_dtype="auto", device_map="cuda", trust_remote_code=True
+)
+
+def extract_array(s: str):
+    m = re.search(r"\[[\s\S]*?\]", s)
+    if not m:
+        return None
+    return json.loads(m.group(0))
+
+text = "오늘 서울에서 AI 컨퍼런스를 다녀왔다."
+messages = [
+    {"role": "system", "content": "너는 태그 생성기다. 출력은 JSON 배열 하나만."},
+    {"role": "user", "content": f"문장: {text}\n태그 3~10개. 너무 디테일하지 않게. 언더스코어 금지. JSON 배열만."},
+]
+
+prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+enc = tok(prompt, return_tensors="pt").to("cuda")
+
+out = model.generate(**enc, max_new_tokens=64, do_sample=False)
+decoded = tok.decode(out[0], skip_special_tokens=True)
+print(extract_array(decoded))
+```
+
+Notes
+	•	Some outputs may include extra tokens (e.g., <think>). In production, extract only the first JSON array [ ... ].
+	•	Training data is intended to avoid sensitive information.
+
+Credits
+	•	Base model: Qwen/Qwen3-0.6B
+	•	Project: Float-Right

README.md”

@@ -0,0 +1 @@
+“README fixed -

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message.content is string 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.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.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' }}
+        {{- 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 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73fc41e79b036aca5e0016aabf4c30a61079cb13a234e42acbd654454339ddb1
+size 1503300328

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6ab688fe4ad89b988049d9cd73e64b3c004ff6b8d8e5c8d677ffa847a13086
+size 3006795403

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659b1cdee2219458dd84ce6a632a595465680b8080e5c44bd600ff97eca8d752
+size 15429

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
+size 15429

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
+size 15429

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
+size 15429

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394453d4186b4da42e0d5ca6a98ddc3855f23b1554cd26f3ec369ecb67591b07
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3107520198881293,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0015537600994406464,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.952500000000001e-05,
+      "loss": 1.8667953491210938,
+      "step": 20
+    },
+    {
+      "epoch": 0.003107520198881293,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.9025e-05,
+      "loss": 1.4211945533752441,
+      "step": 40
+    },
+    {
+      "epoch": 0.0046612802983219395,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.8525e-05,
+      "loss": 1.3616345405578614,
+      "step": 60
+    },
+    {
+      "epoch": 0.006215040397762586,
+      "grad_norm": 1.375,
+      "learning_rate": 9.8025e-05,
+      "loss": 1.3699079513549806,
+      "step": 80
+    },
+    {
+      "epoch": 0.007768800497203232,
+      "grad_norm": 1.265625,
+      "learning_rate": 9.7525e-05,
+      "loss": 1.326680564880371,
+      "step": 100
+    },
+    {
+      "epoch": 0.009322560596643879,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.7025e-05,
+      "loss": 1.3107091903686523,
+      "step": 120
+    },
+    {
+      "epoch": 0.010876320696084525,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.652500000000002e-05,
+      "loss": 1.3247576713562013,
+      "step": 140
+    },
+    {
+      "epoch": 0.012430080795525171,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.6025e-05,
+      "loss": 1.306673526763916,
+      "step": 160
+    },
+    {
+      "epoch": 0.013983840894965818,
+      "grad_norm": 1.2265625,
+      "learning_rate": 9.5525e-05,
+      "loss": 1.2789793014526367,
+      "step": 180
+    },
+    {
+      "epoch": 0.015537600994406464,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.5025e-05,
+      "loss": 1.2699722290039062,
+      "step": 200
+    },
+    {
+      "epoch": 0.01709136109384711,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.452500000000001e-05,
+      "loss": 1.2735892295837403,
+      "step": 220
+    },
+    {
+      "epoch": 0.018645121193287758,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.402500000000001e-05,
+      "loss": 1.255952739715576,
+      "step": 240
+    },
+    {
+      "epoch": 0.020198881292728402,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.352500000000001e-05,
+      "loss": 1.2663206100463866,
+      "step": 260
+    },
+    {
+      "epoch": 0.02175264139216905,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.302500000000001e-05,
+      "loss": 1.2674468994140624,
+      "step": 280
+    },
+    {
+      "epoch": 0.023306401491609695,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.252500000000001e-05,
+      "loss": 1.2581491470336914,
+      "step": 300
+    },
+    {
+      "epoch": 0.024860161591050343,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.2025e-05,
+      "loss": 1.2293106079101563,
+      "step": 320
+    },
+    {
+      "epoch": 0.026413921690490987,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.1525e-05,
+      "loss": 1.2330900192260743,
+      "step": 340
+    },
+    {
+      "epoch": 0.027967681789931635,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.1025e-05,
+      "loss": 1.2186731338500976,
+      "step": 360
+    },
+    {
+      "epoch": 0.02952144188937228,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.0525e-05,
+      "loss": 1.2420782089233398,
+      "step": 380
+    },
+    {
+      "epoch": 0.031075201988812928,
+      "grad_norm": 0.984375,
+      "learning_rate": 9.0025e-05,
+      "loss": 1.2236801147460938,
+      "step": 400
+    },
+    {
+      "epoch": 0.032628962088253576,
+      "grad_norm": 1.0390625,
+      "learning_rate": 8.952500000000001e-05,
+      "loss": 1.2241475105285644,
+      "step": 420
+    },
+    {
+      "epoch": 0.03418272218769422,
+      "grad_norm": 0.98828125,
+      "learning_rate": 8.902500000000001e-05,
+      "loss": 1.2227598190307618,
+      "step": 440
+    },
+    {
+      "epoch": 0.035736482287134864,
+      "grad_norm": 1.0390625,
+      "learning_rate": 8.8525e-05,
+      "loss": 1.2154598236083984,
+      "step": 460
+    },
+    {
+      "epoch": 0.037290242386575516,
+      "grad_norm": 1.0859375,
+      "learning_rate": 8.8025e-05,
+      "loss": 1.20736665725708,
+      "step": 480
+    },
+    {
+      "epoch": 0.03884400248601616,
+      "grad_norm": 1.0546875,
+      "learning_rate": 8.7525e-05,
+      "loss": 1.1936758041381836,
+      "step": 500
+    },
+    {
+      "epoch": 0.040397762585456805,
+      "grad_norm": 1.09375,
+      "learning_rate": 8.7025e-05,
+      "loss": 1.1817484855651856,
+      "step": 520
+    },
+    {
+      "epoch": 0.04195152268489745,
+      "grad_norm": 1.0703125,
+      "learning_rate": 8.6525e-05,
+      "loss": 1.2060453414916992,
+      "step": 540
+    },
+    {
+      "epoch": 0.0435052827843381,
+      "grad_norm": 0.99609375,
+      "learning_rate": 8.6025e-05,
+      "loss": 1.2340307235717773,
+      "step": 560
+    },
+    {
+      "epoch": 0.045059042883778745,
+      "grad_norm": 1.0,
+      "learning_rate": 8.5525e-05,
+      "loss": 1.2149415969848634,
+      "step": 580
+    },
+    {
+      "epoch": 0.04661280298321939,
+      "grad_norm": 0.97265625,
+      "learning_rate": 8.502499999999999e-05,
+      "loss": 1.2079537391662598,
+      "step": 600
+    },
+    {
+      "epoch": 0.048166563082660034,
+      "grad_norm": 1.015625,
+      "learning_rate": 8.4525e-05,
+      "loss": 1.1671560287475586,
+      "step": 620
+    },
+    {
+      "epoch": 0.049720323182100686,
+      "grad_norm": 1.0,
+      "learning_rate": 8.402500000000001e-05,
+      "loss": 1.1967806816101074,
+      "step": 640
+    },
+    {
+      "epoch": 0.05127408328154133,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.352500000000001e-05,
+      "loss": 1.178822135925293,
+      "step": 660
+    },
+    {
+      "epoch": 0.052827843380981974,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.302500000000001e-05,
+      "loss": 1.1784405708312988,
+      "step": 680
+    },
+    {
+      "epoch": 0.054381603480422626,
+      "grad_norm": 0.9765625,
+      "learning_rate": 8.252500000000001e-05,
+      "loss": 1.1611870765686034,
+      "step": 700
+    },
+    {
+      "epoch": 0.05593536357986327,
+      "grad_norm": 1.0078125,
+      "learning_rate": 8.2025e-05,
+      "loss": 1.1876888275146484,
+      "step": 720
+    },
+    {
+      "epoch": 0.057489123679303915,
+      "grad_norm": 0.94921875,
+      "learning_rate": 8.1525e-05,
+      "loss": 1.18981876373291,
+      "step": 740
+    },
+    {
+      "epoch": 0.05904288377874456,
+      "grad_norm": 0.93359375,
+      "learning_rate": 8.1025e-05,
+      "loss": 1.1651229858398438,
+      "step": 760
+    },
+    {
+      "epoch": 0.06059664387818521,
+      "grad_norm": 0.953125,
+      "learning_rate": 8.0525e-05,
+      "loss": 1.1725165367126464,
+      "step": 780
+    },
+    {
+      "epoch": 0.062150403977625855,
+      "grad_norm": 0.94921875,
+      "learning_rate": 8.002500000000001e-05,
+      "loss": 1.1620153427124023,
+      "step": 800
+    },
+    {
+      "epoch": 0.0637041640770665,
+      "grad_norm": 0.94921875,
+      "learning_rate": 7.952500000000001e-05,
+      "loss": 1.180180549621582,
+      "step": 820
+    },
+    {
+      "epoch": 0.06525792417650715,
+      "grad_norm": 0.953125,
+      "learning_rate": 7.902500000000001e-05,
+      "loss": 1.169425106048584,
+      "step": 840
+    },
+    {
+      "epoch": 0.06681168427594779,
+      "grad_norm": 0.96875,
+      "learning_rate": 7.8525e-05,
+      "loss": 1.1701436996459962,
+      "step": 860
+    },
+    {
+      "epoch": 0.06836544437538844,
+      "grad_norm": 0.98828125,
+      "learning_rate": 7.8025e-05,
+      "loss": 1.1514653205871581,
+      "step": 880
+    },
+    {
+      "epoch": 0.06991920447482909,
+      "grad_norm": 0.9453125,
+      "learning_rate": 7.7525e-05,
+      "loss": 1.166794776916504,
+      "step": 900
+    },
+    {
+      "epoch": 0.07147296457426973,
+      "grad_norm": 0.98828125,
+      "learning_rate": 7.7025e-05,
+      "loss": 1.1640316009521485,
+      "step": 920
+    },
+    {
+      "epoch": 0.07302672467371038,
+      "grad_norm": 1.0,
+      "learning_rate": 7.6525e-05,
+      "loss": 1.1756441116333007,
+      "step": 940
+    },
+    {
+      "epoch": 0.07458048477315103,
+      "grad_norm": 0.921875,
+      "learning_rate": 7.6025e-05,
+      "loss": 1.1775863647460938,
+      "step": 960
+    },
+    {
+      "epoch": 0.07613424487259167,
+      "grad_norm": 0.94140625,
+      "learning_rate": 7.5525e-05,
+      "loss": 1.1620708465576173,
+      "step": 980
+    },
+    {
+      "epoch": 0.07768800497203232,
+      "grad_norm": 0.93359375,
+      "learning_rate": 7.502500000000001e-05,
+      "loss": 1.1424921989440917,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07924176507147296,
+      "grad_norm": 0.94140625,
+      "learning_rate": 7.4525e-05,
+      "loss": 1.1636884689331055,
+      "step": 1020
+    },
+    {
+      "epoch": 0.08079552517091361,
+      "grad_norm": 0.96875,
+      "learning_rate": 7.4025e-05,
+      "loss": 1.1640792846679688,
+      "step": 1040
+    },
+    {
+      "epoch": 0.08234928527035426,
+      "grad_norm": 0.96875,
+      "learning_rate": 7.3525e-05,
+      "loss": 1.1577949523925781,
+      "step": 1060
+    },
+    {
+      "epoch": 0.0839030453697949,
+      "grad_norm": 0.9375,
+      "learning_rate": 7.3025e-05,
+      "loss": 1.1563040733337402,
+      "step": 1080
+    },
+    {
+      "epoch": 0.08545680546923555,
+      "grad_norm": 0.9296875,
+      "learning_rate": 7.2525e-05,
+      "loss": 1.1314552307128907,
+      "step": 1100
+    },
+    {
+      "epoch": 0.0870105655686762,
+      "grad_norm": 0.953125,
+      "learning_rate": 7.2025e-05,
+      "loss": 1.1430686950683593,
+      "step": 1120
+    },
+    {
+      "epoch": 0.08856432566811684,
+      "grad_norm": 0.921875,
+      "learning_rate": 7.1525e-05,
+      "loss": 1.1624882698059082,
+      "step": 1140
+    },
+    {
+      "epoch": 0.09011808576755749,
+      "grad_norm": 0.9375,
+      "learning_rate": 7.1025e-05,
+      "loss": 1.1404618263244628,
+      "step": 1160
+    },
+    {
+      "epoch": 0.09167184586699814,
+      "grad_norm": 0.94921875,
+      "learning_rate": 7.0525e-05,
+      "loss": 1.142820453643799,
+      "step": 1180
+    },
+    {
+      "epoch": 0.09322560596643878,
+      "grad_norm": 0.9296875,
+      "learning_rate": 7.002500000000001e-05,
+      "loss": 1.1361354827880858,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09477936606587943,
+      "grad_norm": 0.91796875,
+      "learning_rate": 6.952500000000001e-05,
+      "loss": 1.141007137298584,
+      "step": 1220
+    },
+    {
+      "epoch": 0.09633312616532007,
+      "grad_norm": 0.93359375,
+      "learning_rate": 6.902500000000001e-05,
+      "loss": 1.140983772277832,
+      "step": 1240
+    },
+    {
+      "epoch": 0.09788688626476072,
+      "grad_norm": 0.94921875,
+      "learning_rate": 6.852500000000001e-05,
+      "loss": 1.1491514205932618,
+      "step": 1260
+    },
+    {
+      "epoch": 0.09944064636420137,
+      "grad_norm": 0.953125,
+      "learning_rate": 6.8025e-05,
+      "loss": 1.1248952865600585,
+      "step": 1280
+    },
+    {
+      "epoch": 0.10099440646364201,
+      "grad_norm": 0.9296875,
+      "learning_rate": 6.7525e-05,
+      "loss": 1.1090205192565918,
+      "step": 1300
+    },
+    {
+      "epoch": 0.10254816656308266,
+      "grad_norm": 0.9765625,
+      "learning_rate": 6.7025e-05,
+      "loss": 1.1208727836608887,
+      "step": 1320
+    },
+    {
+      "epoch": 0.10410192666252331,
+      "grad_norm": 0.9375,
+      "learning_rate": 6.6525e-05,
+      "loss": 1.1511701583862304,
+      "step": 1340
+    },
+    {
+      "epoch": 0.10565568676196395,
+      "grad_norm": 0.8828125,
+      "learning_rate": 6.6025e-05,
+      "loss": 1.1259963989257813,
+      "step": 1360
+    },
+    {
+      "epoch": 0.1072094468614046,
+      "grad_norm": 0.921875,
+      "learning_rate": 6.552500000000001e-05,
+      "loss": 1.1311534881591796,
+      "step": 1380
+    },
+    {
+      "epoch": 0.10876320696084525,
+      "grad_norm": 0.9375,
+      "learning_rate": 6.502500000000001e-05,
+      "loss": 1.1099111557006835,
+      "step": 1400
+    },
+    {
+      "epoch": 0.11031696706028589,
+      "grad_norm": 0.953125,
+      "learning_rate": 6.4525e-05,
+      "loss": 1.126076602935791,
+      "step": 1420
+    },
+    {
+      "epoch": 0.11187072715972654,
+      "grad_norm": 0.8984375,
+      "learning_rate": 6.4025e-05,
+      "loss": 1.1338358879089356,
+      "step": 1440
+    },
+    {
+      "epoch": 0.11342448725916718,
+      "grad_norm": 0.91796875,
+      "learning_rate": 6.3525e-05,
+      "loss": 1.1149433135986329,
+      "step": 1460
+    },
+    {
+      "epoch": 0.11497824735860783,
+      "grad_norm": 0.96484375,
+      "learning_rate": 6.3025e-05,
+      "loss": 1.1221566200256348,
+      "step": 1480
+    },
+    {
+      "epoch": 0.11653200745804848,
+      "grad_norm": 0.921875,
+      "learning_rate": 6.2525e-05,
+      "loss": 1.1223237991333008,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11808576755748912,
+      "grad_norm": 0.90234375,
+      "learning_rate": 6.2025e-05,
+      "loss": 1.1033407211303712,
+      "step": 1520
+    },
+    {
+      "epoch": 0.11963952765692977,
+      "grad_norm": 0.90234375,
+      "learning_rate": 6.1525e-05,
+      "loss": 1.1114818572998046,
+      "step": 1540
+    },
+    {
+      "epoch": 0.12119328775637042,
+      "grad_norm": 0.91796875,
+      "learning_rate": 6.1025e-05,
+      "loss": 1.1105637550354004,
+      "step": 1560
+    },
+    {
+      "epoch": 0.12274704785581106,
+      "grad_norm": 0.90625,
+      "learning_rate": 6.0525e-05,
+      "loss": 1.1189040184020995,
+      "step": 1580
+    },
+    {
+      "epoch": 0.12430080795525171,
+      "grad_norm": 0.921875,
+      "learning_rate": 6.0024999999999995e-05,
+      "loss": 1.1234063148498534,
+      "step": 1600
+    },
+    {
+      "epoch": 0.12585456805469236,
+      "grad_norm": 0.953125,
+      "learning_rate": 5.9525e-05,
+      "loss": 1.1020179748535157,
+      "step": 1620
+    },
+    {
+      "epoch": 0.127408328154133,
+      "grad_norm": 0.921875,
+      "learning_rate": 5.9025000000000005e-05,
+      "loss": 1.1260129928588867,
+      "step": 1640
+    },
+    {
+      "epoch": 0.12896208825357364,
+      "grad_norm": 0.87890625,
+      "learning_rate": 5.8525000000000006e-05,
+      "loss": 1.1067705154418945,
+      "step": 1660
+    },
+    {
+      "epoch": 0.1305158483530143,
+      "grad_norm": 0.94140625,
+      "learning_rate": 5.802500000000001e-05,
+      "loss": 1.115440273284912,
+      "step": 1680
+    },
+    {
+      "epoch": 0.13206960845245494,
+      "grad_norm": 0.91796875,
+      "learning_rate": 5.752500000000001e-05,
+      "loss": 1.1169689178466797,
+      "step": 1700
+    },
+    {
+      "epoch": 0.13362336855189558,
+      "grad_norm": 0.921875,
+      "learning_rate": 5.7025000000000004e-05,
+      "loss": 1.1162803649902344,
+      "step": 1720
+    },
+    {
+      "epoch": 0.13517712865133624,
+      "grad_norm": 0.8984375,
+      "learning_rate": 5.6525000000000005e-05,
+      "loss": 1.1266037940979003,
+      "step": 1740
+    },
+    {
+      "epoch": 0.13673088875077688,
+      "grad_norm": 0.953125,
+      "learning_rate": 5.6025000000000007e-05,
+      "loss": 1.1090587615966796,
+      "step": 1760
+    },
+    {
+      "epoch": 0.13828464885021752,
+      "grad_norm": 0.8828125,
+      "learning_rate": 5.552500000000001e-05,
+      "loss": 1.1141853332519531,
+      "step": 1780
+    },
+    {
+      "epoch": 0.13983840894965818,
+      "grad_norm": 0.88671875,
+      "learning_rate": 5.5025e-05,
+      "loss": 1.1379024505615234,
+      "step": 1800
+    },
+    {
+      "epoch": 0.14139216904909882,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.4525000000000004e-05,
+      "loss": 1.110361099243164,
+      "step": 1820
+    },
+    {
+      "epoch": 0.14294592914853946,
+      "grad_norm": 0.8984375,
+      "learning_rate": 5.4025000000000005e-05,
+      "loss": 1.1104223251342773,
+      "step": 1840
+    },
+    {
+      "epoch": 0.14449968924798012,
+      "grad_norm": 0.953125,
+      "learning_rate": 5.3525e-05,
+      "loss": 1.0993282318115234,
+      "step": 1860
+    },
+    {
+      "epoch": 0.14605344934742076,
+      "grad_norm": 0.88671875,
+      "learning_rate": 5.3025e-05,
+      "loss": 1.1151838302612305,
+      "step": 1880
+    },
+    {
+      "epoch": 0.1476072094468614,
+      "grad_norm": 0.91796875,
+      "learning_rate": 5.2525e-05,
+      "loss": 1.1184428215026856,
+      "step": 1900
+    },
+    {
+      "epoch": 0.14916096954630206,
+      "grad_norm": 0.921875,
+      "learning_rate": 5.2025000000000004e-05,
+      "loss": 1.1321413040161132,
+      "step": 1920
+    },
+    {
+      "epoch": 0.1507147296457427,
+      "grad_norm": 0.875,
+      "learning_rate": 5.1525e-05,
+      "loss": 1.1035722732543944,
+      "step": 1940
+    },
+    {
+      "epoch": 0.15226848974518334,
+      "grad_norm": 0.92578125,
+      "learning_rate": 5.1025e-05,
+      "loss": 1.0843469619750976,
+      "step": 1960
+    },
+    {
+      "epoch": 0.153822249844624,
+      "grad_norm": 0.89453125,
+      "learning_rate": 5.0525e-05,
+      "loss": 1.102191162109375,
+      "step": 1980
+    },
+    {
+      "epoch": 0.15537600994406464,
+      "grad_norm": 0.93359375,
+      "learning_rate": 5.0025e-05,
+      "loss": 1.1058999061584474,
+      "step": 2000
+    },
+    {
+      "epoch": 0.15692977004350528,
+      "grad_norm": 0.8984375,
+      "learning_rate": 4.9525000000000004e-05,
+      "loss": 1.1077130317687989,
+      "step": 2020
+    },
+    {
+      "epoch": 0.15848353014294592,
+      "grad_norm": 0.91796875,
+      "learning_rate": 4.9025000000000006e-05,
+      "loss": 1.0922195434570312,
+      "step": 2040
+    },
+    {
+      "epoch": 0.16003729024238658,
+      "grad_norm": 0.92578125,
+      "learning_rate": 4.8525e-05,
+      "loss": 1.130363941192627,
+      "step": 2060
+    },
+    {
+      "epoch": 0.16159105034182722,
+      "grad_norm": 0.8984375,
+      "learning_rate": 4.8025e-05,
+      "loss": 1.0666452407836915,
+      "step": 2080
+    },
+    {
+      "epoch": 0.16314481044126786,
+      "grad_norm": 0.91015625,
+      "learning_rate": 4.7525e-05,
+      "loss": 1.096773052215576,
+      "step": 2100
+    },
+    {
+      "epoch": 0.16469857054070852,
+      "grad_norm": 0.9296875,
+      "learning_rate": 4.7025000000000005e-05,
+      "loss": 1.0890857696533203,
+      "step": 2120
+    },
+    {
+      "epoch": 0.16625233064014916,
+      "grad_norm": 0.91015625,
+      "learning_rate": 4.6525e-05,
+      "loss": 1.1071590423583983,
+      "step": 2140
+    },
+    {
+      "epoch": 0.1678060907395898,
+      "grad_norm": 0.87890625,
+      "learning_rate": 4.6025e-05,
+      "loss": 1.1148256301879882,
+      "step": 2160
+    },
+    {
+      "epoch": 0.16935985083903046,
+      "grad_norm": 0.92578125,
+      "learning_rate": 4.5525e-05,
+      "loss": 1.090849018096924,
+      "step": 2180
+    },
+    {
+      "epoch": 0.1709136109384711,
+      "grad_norm": 0.921875,
+      "learning_rate": 4.5025000000000003e-05,
+      "loss": 1.1214483261108399,
+      "step": 2200
+    },
+    {
+      "epoch": 0.17246737103791174,
+      "grad_norm": 0.89453125,
+      "learning_rate": 4.4525e-05,
+      "loss": 1.099250030517578,
+      "step": 2220
+    },
+    {
+      "epoch": 0.1740211311373524,
+      "grad_norm": 0.90234375,
+      "learning_rate": 4.4025e-05,
+      "loss": 1.0906652450561523,
+      "step": 2240
+    },
+    {
+      "epoch": 0.17557489123679304,
+      "grad_norm": 0.875,
+      "learning_rate": 4.352500000000001e-05,
+      "loss": 1.0940235137939454,
+      "step": 2260
+    },
+    {
+      "epoch": 0.17712865133623368,
+      "grad_norm": 0.875,
+      "learning_rate": 4.3025e-05,
+      "loss": 1.0771520614624024,
+      "step": 2280
+    },
+    {
+      "epoch": 0.17868241143567434,
+      "grad_norm": 0.875,
+      "learning_rate": 4.2525000000000004e-05,
+      "loss": 1.0870559692382813,
+      "step": 2300
+    },
+    {
+      "epoch": 0.18023617153511498,
+      "grad_norm": 0.90625,
+      "learning_rate": 4.2025000000000005e-05,
+      "loss": 1.0863205909729003,
+      "step": 2320
+    },
+    {
+      "epoch": 0.18178993163455562,
+      "grad_norm": 0.9296875,
+      "learning_rate": 4.1525e-05,
+      "loss": 1.0996931076049805,
+      "step": 2340
+    },
+    {
+      "epoch": 0.18334369173399628,
+      "grad_norm": 0.875,
+      "learning_rate": 4.1025e-05,
+      "loss": 1.0987712860107421,
+      "step": 2360
+    },
+    {
+      "epoch": 0.18489745183343692,
+      "grad_norm": 0.9296875,
+      "learning_rate": 4.0525e-05,
+      "loss": 1.1171295166015625,
+      "step": 2380
+    },
+    {
+      "epoch": 0.18645121193287756,
+      "grad_norm": 0.9296875,
+      "learning_rate": 4.0025000000000004e-05,
+      "loss": 1.103907012939453,
+      "step": 2400
+    },
+    {
+      "epoch": 0.18800497203231822,
+      "grad_norm": 0.94140625,
+      "learning_rate": 3.9525e-05,
+      "loss": 1.090281867980957,
+      "step": 2420
+    },
+    {
+      "epoch": 0.18955873213175886,
+      "grad_norm": 0.9140625,
+      "learning_rate": 3.9025e-05,
+      "loss": 1.0880367279052734,
+      "step": 2440
+    },
+    {
+      "epoch": 0.1911124922311995,
+      "grad_norm": 0.90625,
+      "learning_rate": 3.8525e-05,
+      "loss": 1.0839120864868164,
+      "step": 2460
+    },
+    {
+      "epoch": 0.19266625233064014,
+      "grad_norm": 0.9375,
+      "learning_rate": 3.8025e-05,
+      "loss": 1.1069268226623534,
+      "step": 2480
+    },
+    {
+      "epoch": 0.1942200124300808,
+      "grad_norm": 0.87109375,
+      "learning_rate": 3.7525e-05,
+      "loss": 1.0701780319213867,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19577377252952144,
+      "grad_norm": 0.921875,
+      "learning_rate": 3.7025000000000005e-05,
+      "loss": 1.1017258644104004,
+      "step": 2520
+    },
+    {
+      "epoch": 0.19732753262896208,
+      "grad_norm": 0.9140625,
+      "learning_rate": 3.652500000000001e-05,
+      "loss": 1.1134037017822265,
+      "step": 2540
+    },
+    {
+      "epoch": 0.19888129272840274,
+      "grad_norm": 0.9453125,
+      "learning_rate": 3.6025e-05,
+      "loss": 1.0741355895996094,
+      "step": 2560
+    },
+    {
+      "epoch": 0.20043505282784338,
+      "grad_norm": 0.890625,
+      "learning_rate": 3.5525e-05,
+      "loss": 1.0729135513305663,
+      "step": 2580
+    },
+    {
+      "epoch": 0.20198881292728402,
+      "grad_norm": 0.921875,
+      "learning_rate": 3.5025000000000004e-05,
+      "loss": 1.0833280563354493,
+      "step": 2600
+    },
+    {
+      "epoch": 0.20354257302672468,
+      "grad_norm": 0.8984375,
+      "learning_rate": 3.4525e-05,
+      "loss": 1.1003621101379395,
+      "step": 2620
+    },
+    {
+      "epoch": 0.20509633312616532,
+      "grad_norm": 0.8984375,
+      "learning_rate": 3.4025e-05,
+      "loss": 1.0958992004394532,
+      "step": 2640
+    },
+    {
+      "epoch": 0.20665009322560596,
+      "grad_norm": 0.90625,
+      "learning_rate": 3.3525e-05,
+      "loss": 1.098832893371582,
+      "step": 2660
+    },
+    {
+      "epoch": 0.20820385332504662,
+      "grad_norm": 0.89453125,
+      "learning_rate": 3.3025e-05,
+      "loss": 1.0823541641235352,
+      "step": 2680
+    },
+    {
+      "epoch": 0.20975761342448726,
+      "grad_norm": 0.91015625,
+      "learning_rate": 3.2525e-05,
+      "loss": 1.0849027633666992,
+      "step": 2700
+    },
+    {
+      "epoch": 0.2113113735239279,
+      "grad_norm": 0.890625,
+      "learning_rate": 3.2025e-05,
+      "loss": 1.0959321975708007,
+      "step": 2720
+    },
+    {
+      "epoch": 0.21286513362336856,
+      "grad_norm": 0.88671875,
+      "learning_rate": 3.1525e-05,
+      "loss": 1.083869743347168,
+      "step": 2740
+    },
+    {
+      "epoch": 0.2144188937228092,
+      "grad_norm": 0.8984375,
+      "learning_rate": 3.1025e-05,
+      "loss": 1.0912399291992188,
+      "step": 2760
+    },
+    {
+      "epoch": 0.21597265382224984,
+      "grad_norm": 0.9140625,
+      "learning_rate": 3.0525e-05,
+      "loss": 1.088266944885254,
+      "step": 2780
+    },
+    {
+      "epoch": 0.2175264139216905,
+      "grad_norm": 0.86328125,
+      "learning_rate": 3.0025000000000005e-05,
+      "loss": 1.0917407035827638,
+      "step": 2800
+    },
+    {
+      "epoch": 0.21908017402113114,
+      "grad_norm": 0.88671875,
+      "learning_rate": 2.9525000000000003e-05,
+      "loss": 1.088615608215332,
+      "step": 2820
+    },
+    {
+      "epoch": 0.22063393412057178,
+      "grad_norm": 0.89453125,
+      "learning_rate": 2.9025e-05,
+      "loss": 1.0885720252990723,
+      "step": 2840
+    },
+    {
+      "epoch": 0.22218769422001244,
+      "grad_norm": 0.8828125,
+      "learning_rate": 2.8525000000000002e-05,
+      "loss": 1.072688388824463,
+      "step": 2860
+    },
+    {
+      "epoch": 0.22374145431945308,
+      "grad_norm": 0.89453125,
+      "learning_rate": 2.8025e-05,
+      "loss": 1.0892706871032716,
+      "step": 2880
+    },
+    {
+      "epoch": 0.22529521441889372,
+      "grad_norm": 0.93359375,
+      "learning_rate": 2.7525e-05,
+      "loss": 1.083917236328125,
+      "step": 2900
+    },
+    {
+      "epoch": 0.22684897451833436,
+      "grad_norm": 0.921875,
+      "learning_rate": 2.7025e-05,
+      "loss": 1.1079219818115233,
+      "step": 2920
+    },
+    {
+      "epoch": 0.22840273461777502,
+      "grad_norm": 0.91796875,
+      "learning_rate": 2.6525e-05,
+      "loss": 1.0851898193359375,
+      "step": 2940
+    },
+    {
+      "epoch": 0.22995649471721566,
+      "grad_norm": 0.91015625,
+      "learning_rate": 2.6025e-05,
+      "loss": 1.0698064804077148,
+      "step": 2960
+    },
+    {
+      "epoch": 0.2315102548166563,
+      "grad_norm": 0.8828125,
+      "learning_rate": 2.5525e-05,
+      "loss": 1.0661302566528321,
+      "step": 2980
+    },
+    {
+      "epoch": 0.23306401491609696,
+      "grad_norm": 0.9140625,
+      "learning_rate": 2.5025e-05,
+      "loss": 1.0647387504577637,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2346177750155376,
+      "grad_norm": 0.8984375,
+      "learning_rate": 2.4525e-05,
+      "loss": 1.074313259124756,
+      "step": 3020
+    },
+    {
+      "epoch": 0.23617153511497824,
+      "grad_norm": 0.9140625,
+      "learning_rate": 2.4025e-05,
+      "loss": 1.0964820861816407,
+      "step": 3040
+    },
+    {
+      "epoch": 0.2377252952144189,
+      "grad_norm": 0.89453125,
+      "learning_rate": 2.3525e-05,
+      "loss": 1.0810314178466798,
+      "step": 3060
+    },
+    {
+      "epoch": 0.23927905531385954,
+      "grad_norm": 0.9296875,
+      "learning_rate": 2.3025e-05,
+      "loss": 1.078106689453125,
+      "step": 3080
+    },
+    {
+      "epoch": 0.24083281541330018,
+      "grad_norm": 0.90234375,
+      "learning_rate": 2.2525000000000002e-05,
+      "loss": 1.0860605239868164,
+      "step": 3100
+    },
+    {
+      "epoch": 0.24238657551274084,
+      "grad_norm": 0.88671875,
+      "learning_rate": 2.2025e-05,
+      "loss": 1.0743337631225587,
+      "step": 3120
+    },
+    {
+      "epoch": 0.24394033561218148,
+      "grad_norm": 0.88671875,
+      "learning_rate": 2.1525e-05,
+      "loss": 1.0778118133544923,
+      "step": 3140
+    },
+    {
+      "epoch": 0.24549409571162212,
+      "grad_norm": 0.9296875,
+      "learning_rate": 2.1025e-05,
+      "loss": 1.0981425285339355,
+      "step": 3160
+    },
+    {
+      "epoch": 0.24704785581106278,
+      "grad_norm": 0.91015625,
+      "learning_rate": 2.0525e-05,
+      "loss": 1.0836584091186523,
+      "step": 3180
+    },
+    {
+      "epoch": 0.24860161591050342,
+      "grad_norm": 0.8671875,
+      "learning_rate": 2.0025000000000002e-05,
+      "loss": 1.089561367034912,
+      "step": 3200
+    },
+    {
+      "epoch": 0.2501553760099441,
+      "grad_norm": 0.9296875,
+      "learning_rate": 1.9525e-05,
+      "loss": 1.0788454055786132,
+      "step": 3220
+    },
+    {
+      "epoch": 0.2517091361093847,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.9025e-05,
+      "loss": 1.078543758392334,
+      "step": 3240
+    },
+    {
+      "epoch": 0.25326289620882536,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.8525e-05,
+      "loss": 1.1045896530151367,
+      "step": 3260
+    },
+    {
+      "epoch": 0.254816656308266,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.8025e-05,
+      "loss": 1.0857179641723633,
+      "step": 3280
+    },
+    {
+      "epoch": 0.25637041640770664,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.7525e-05,
+      "loss": 1.0980566024780274,
+      "step": 3300
+    },
+    {
+      "epoch": 0.2579241765071473,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.7025e-05,
+      "loss": 1.0898794174194335,
+      "step": 3320
+    },
+    {
+      "epoch": 0.25947793660658797,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.6525000000000002e-05,
+      "loss": 1.0813383102416991,
+      "step": 3340
+    },
+    {
+      "epoch": 0.2610316967060286,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.6025e-05,
+      "loss": 1.0852994918823242,
+      "step": 3360
+    },
+    {
+      "epoch": 0.26258545680546924,
+      "grad_norm": 0.9296875,
+      "learning_rate": 1.5525e-05,
+      "loss": 1.0736425399780274,
+      "step": 3380
+    },
+    {
+      "epoch": 0.2641392169049099,
+      "grad_norm": 0.87890625,
+      "learning_rate": 1.5025000000000001e-05,
+      "loss": 1.0873353004455566,
+      "step": 3400
+    },
+    {
+      "epoch": 0.2656929770043505,
+      "grad_norm": 0.90625,
+      "learning_rate": 1.4524999999999999e-05,
+      "loss": 1.0847795486450196,
+      "step": 3420
+    },
+    {
+      "epoch": 0.26724673710379115,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.4025000000000002e-05,
+      "loss": 1.0983787536621095,
+      "step": 3440
+    },
+    {
+      "epoch": 0.26880049720323185,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1.3525000000000002e-05,
+      "loss": 1.0719210624694824,
+      "step": 3460
+    },
+    {
+      "epoch": 0.2703542573026725,
+      "grad_norm": 0.87890625,
+      "learning_rate": 1.3025000000000002e-05,
+      "loss": 1.0850942611694336,
+      "step": 3480
+    },
+    {
+      "epoch": 0.2719080174021131,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.2525000000000001e-05,
+      "loss": 1.0767460823059083,
+      "step": 3500
+    },
+    {
+      "epoch": 0.27346177750155376,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.2025000000000001e-05,
+      "loss": 1.0981364250183105,
+      "step": 3520
+    },
+    {
+      "epoch": 0.2750155376009944,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.1525e-05,
+      "loss": 1.0713367462158203,
+      "step": 3540
+    },
+    {
+      "epoch": 0.27656929770043504,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.1025e-05,
+      "loss": 1.074637222290039,
+      "step": 3560
+    },
+    {
+      "epoch": 0.2781230577998757,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.0525e-05,
+      "loss": 1.0917478561401368,
+      "step": 3580
+    },
+    {
+      "epoch": 0.27967681789931637,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1.0025000000000001e-05,
+      "loss": 1.0934381484985352,
+      "step": 3600
+    },
+    {
+      "epoch": 0.281230577998757,
+      "grad_norm": 0.953125,
+      "learning_rate": 9.525000000000001e-06,
+      "loss": 1.0998394966125489,
+      "step": 3620
+    },
+    {
+      "epoch": 0.28278433809819764,
+      "grad_norm": 0.8828125,
+      "learning_rate": 9.025e-06,
+      "loss": 1.087621021270752,
+      "step": 3640
+    },
+    {
+      "epoch": 0.2843380981976383,
+      "grad_norm": 0.91015625,
+      "learning_rate": 8.525e-06,
+      "loss": 1.091860866546631,
+      "step": 3660
+    },
+    {
+      "epoch": 0.2858918582970789,
+      "grad_norm": 0.9375,
+      "learning_rate": 8.025e-06,
+      "loss": 1.072180938720703,
+      "step": 3680
+    },
+    {
+      "epoch": 0.28744561839651955,
+      "grad_norm": 0.8828125,
+      "learning_rate": 7.525e-06,
+      "loss": 1.0778998374938964,
+      "step": 3700
+    },
+    {
+      "epoch": 0.28899937849596025,
+      "grad_norm": 0.875,
+      "learning_rate": 7.025000000000001e-06,
+      "loss": 1.0709803581237793,
+      "step": 3720
+    },
+    {
+      "epoch": 0.2905531385954009,
+      "grad_norm": 0.91015625,
+      "learning_rate": 6.525e-06,
+      "loss": 1.1010093688964844,
+      "step": 3740
+    },
+    {
+      "epoch": 0.2921068986948415,
+      "grad_norm": 0.91015625,
+      "learning_rate": 6.025e-06,
+      "loss": 1.0703121185302735,
+      "step": 3760
+    },
+    {
+      "epoch": 0.29366065879428216,
+      "grad_norm": 0.88671875,
+      "learning_rate": 5.5250000000000005e-06,
+      "loss": 1.0773000717163086,
+      "step": 3780
+    },
+    {
+      "epoch": 0.2952144188937228,
+      "grad_norm": 0.91796875,
+      "learning_rate": 5.025e-06,
+      "loss": 1.0894964218139649,
+      "step": 3800
+    },
+    {
+      "epoch": 0.29676817899316343,
+      "grad_norm": 0.87890625,
+      "learning_rate": 4.525e-06,
+      "loss": 1.060502815246582,
+      "step": 3820
+    },
+    {
+      "epoch": 0.2983219390926041,
+      "grad_norm": 0.890625,
+      "learning_rate": 4.0250000000000004e-06,
+      "loss": 1.0844976425170898,
+      "step": 3840
+    },
+    {
+      "epoch": 0.29987569919204476,
+      "grad_norm": 0.90625,
+      "learning_rate": 3.5249999999999997e-06,
+      "loss": 1.068390464782715,
+      "step": 3860
+    },
+    {
+      "epoch": 0.3014294592914854,
+      "grad_norm": 0.8828125,
+      "learning_rate": 3.0250000000000003e-06,
+      "loss": 1.0733464241027832,
+      "step": 3880
+    },
+    {
+      "epoch": 0.30298321939092604,
+      "grad_norm": 0.92578125,
+      "learning_rate": 2.5250000000000004e-06,
+      "loss": 1.0655000686645508,
+      "step": 3900
+    },
+    {
+      "epoch": 0.3045369794903667,
+      "grad_norm": 0.88671875,
+      "learning_rate": 2.025e-06,
+      "loss": 1.0655412673950195,
+      "step": 3920
+    },
+    {
+      "epoch": 0.3060907395898073,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.525e-06,
+      "loss": 1.0558664321899414,
+      "step": 3940
+    },
+    {
+      "epoch": 0.307644499689248,
+      "grad_norm": 0.94140625,
+      "learning_rate": 1.0250000000000001e-06,
+      "loss": 1.1024866104125977,
+      "step": 3960
+    },
+    {
+      "epoch": 0.30919825978868865,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.250000000000001e-07,
+      "loss": 1.0651491165161133,
+      "step": 3980
+    },
+    {
+      "epoch": 0.3107520198881293,
+      "grad_norm": 0.9609375,
+      "learning_rate": 2.5000000000000002e-08,
+      "loss": 1.0959912300109864,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.3750546137088e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989fbd47b6a05e982f81abdb2d6ae79f41c2a90d7a85b4c5f217a5a1b2edad8c
+size 5201