Instructions to use FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth")
model = AutoModelForCausalLM.from_pretrained("FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth

SGLang

How to use FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth with Docker Model Runner:
```
docker model run hf.co/FormlessAI/Qwen2.5-3B-Instruct-Math-Unsloth
```

FormlessAI commited on Jul 27

Commit

a7f9a9b

verified ·

1 Parent(s): 8a7622f

Upload folder using huggingface_hub

Browse files

Files changed (15) hide show

.gitattributes +1 -0
README.md +59 -0
added_tokens.json +24 -0
chat_template.jinja +54 -0
config.json +69 -0
generation_config.json +14 -0
merges.txt +0 -0
model-00001-of-00002.safetensors +3 -0
model-00002-of-00002.safetensors +3 -0
model.safetensors.index.json +442 -0
special_tokens_map.json +31 -0
tokenizer.json +3 -0
tokenizer_config.json +208 -0
trainer_state.json +2595 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -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

 *.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 ADDED Viewed

	@@ -0,0 +1,59 @@

+---
+base_model: unsloth/Qwen2.5-3B-Instruct
+library_name: transformers
+model_name: Qwen_Qwen2.5-3B-Instruct__project-3b-math_1785190172
+tags:
+- generated_from_trainer
+- trl
+- unsloth
+- sft
+licence: license
+---
+# Model Card for Qwen_Qwen2.5-3B-Instruct__project-3b-math_1785190172
+This model is a fine-tuned version of [unsloth/Qwen2.5-3B-Instruct](https://huggingface.co/unsloth/Qwen2.5-3B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+## Quick start
+```python
+from transformers import pipeline
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+## Training procedure
+This model was trained with SFT.
+### Framework versions
+- TRL: 0.23.1
+- Transformers: 4.57.6
+- Pytorch: 2.6.0+cu124
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+## Citations
+Cite TRL as:
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 ADDED Viewed

	@@ -0,0 +1,54 @@

+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\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>" }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

config.json ADDED Viewed

	@@ -0,0 +1,69 @@

+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_name": "unsloth/Qwen2.5-3B-Instruct",
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.7.5",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151654,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.6"
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model-00001-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8dd36ed6043c4647d8982983f64ba519804f96f875e986d0e687bfa713a72c
+size 4957789160

model-00002-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ed3861046a427b251461407cedcd31b969c29ce41e467623613251ee1566dc
+size 1214436184

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,442 @@

+{
+  "metadata": {
+    "total_parameters": 3085938688,
+    "total_size": 6172176384
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json ADDED Viewed

	@@ -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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,208 @@

+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,2595 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 25,
+  "global_step": 248,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00808080808080808,
+      "grad_norm": 34.29597854614258,
+      "learning_rate": 0.0,
+      "loss": 0.9949,
+      "num_input_tokens_seen": 24048,
+      "step": 1,
+      "train_runtime": 17.3014,
+      "train_tokens_per_second": 1389.947
+    },
+    {
+      "epoch": 0.01616161616161616,
+      "grad_norm": 35.52030944824219,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.0553,
+      "num_input_tokens_seen": 48096,
+      "step": 2,
+      "train_runtime": 19.429,
+      "train_tokens_per_second": 2475.474
+    },
+    {
+      "epoch": 0.024242424242424242,
+      "grad_norm": 25.08833122253418,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8931,
+      "num_input_tokens_seen": 68416,
+      "step": 3,
+      "train_runtime": 21.2655,
+      "train_tokens_per_second": 3217.224
+    },
+    {
+      "epoch": 0.03232323232323232,
+      "grad_norm": 15.185912132263184,
+      "learning_rate": 1.2e-05,
+      "loss": 0.6129,
+      "num_input_tokens_seen": 90432,
+      "step": 4,
+      "train_runtime": 23.2211,
+      "train_tokens_per_second": 3894.39
+    },
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 15.486276626586914,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.5151,
+      "num_input_tokens_seen": 110544,
+      "step": 5,
+      "train_runtime": 25.0374,
+      "train_tokens_per_second": 4415.159
+    },
+    {
+      "epoch": 0.048484848484848485,
+      "grad_norm": 6.518914699554443,
+      "learning_rate": 2e-05,
+      "loss": 0.3906,
+      "num_input_tokens_seen": 135584,
+      "step": 6,
+      "train_runtime": 27.2726,
+      "train_tokens_per_second": 4971.445
+    },
+    {
+      "epoch": 0.05656565656565657,
+      "grad_norm": 3.689831256866455,
+      "learning_rate": 1.991769547325103e-05,
+      "loss": 0.3707,
+      "num_input_tokens_seen": 159200,
+      "step": 7,
+      "train_runtime": 29.3859,
+      "train_tokens_per_second": 5417.559
+    },
+    {
+      "epoch": 0.06464646464646465,
+      "grad_norm": 2.442633867263794,
+      "learning_rate": 1.983539094650206e-05,
+      "loss": 0.361,
+      "num_input_tokens_seen": 182224,
+      "step": 8,
+      "train_runtime": 31.4524,
+      "train_tokens_per_second": 5793.636
+    },
+    {
+      "epoch": 0.07272727272727272,
+      "grad_norm": 2.300377368927002,
+      "learning_rate": 1.9753086419753087e-05,
+      "loss": 0.3582,
+      "num_input_tokens_seen": 205472,
+      "step": 9,
+      "train_runtime": 33.5262,
+      "train_tokens_per_second": 6128.691
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 1.9368574619293213,
+      "learning_rate": 1.9670781893004115e-05,
+      "loss": 0.3134,
+      "num_input_tokens_seen": 230400,
+      "step": 10,
+      "train_runtime": 36.915,
+      "train_tokens_per_second": 6241.36
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 2.0495376586914062,
+      "learning_rate": 1.9588477366255147e-05,
+      "loss": 0.3375,
+      "num_input_tokens_seen": 252736,
+      "step": 11,
+      "train_runtime": 38.9446,
+      "train_tokens_per_second": 6489.625
+    },
+    {
+      "epoch": 0.09696969696969697,
+      "grad_norm": 2.28267502784729,
+      "learning_rate": 1.9506172839506175e-05,
+      "loss": 0.3242,
+      "num_input_tokens_seen": 273584,
+      "step": 12,
+      "train_runtime": 40.8507,
+      "train_tokens_per_second": 6697.174
+    },
+    {
+      "epoch": 0.10505050505050505,
+      "grad_norm": 2.2189362049102783,
+      "learning_rate": 1.9423868312757203e-05,
+      "loss": 0.3666,
+      "num_input_tokens_seen": 299968,
+      "step": 13,
+      "train_runtime": 43.2004,
+      "train_tokens_per_second": 6943.636
+    },
+    {
+      "epoch": 0.11313131313131314,
+      "grad_norm": 2.0740907192230225,
+      "learning_rate": 1.934156378600823e-05,
+      "loss": 0.3772,
+      "num_input_tokens_seen": 322480,
+      "step": 14,
+      "train_runtime": 45.2552,
+      "train_tokens_per_second": 7125.818
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 2.38155460357666,
+      "learning_rate": 1.925925925925926e-05,
+      "loss": 0.362,
+      "num_input_tokens_seen": 344864,
+      "step": 15,
+      "train_runtime": 47.2767,
+      "train_tokens_per_second": 7294.584
+    },
+    {
+      "epoch": 0.1292929292929293,
+      "grad_norm": 1.8321378231048584,
+      "learning_rate": 1.9176954732510288e-05,
+      "loss": 0.3286,
+      "num_input_tokens_seen": 369296,
+      "step": 16,
+      "train_runtime": 49.4673,
+      "train_tokens_per_second": 7465.459
+    },
+    {
+      "epoch": 0.13737373737373737,
+      "grad_norm": 2.0253713130950928,
+      "learning_rate": 1.9094650205761317e-05,
+      "loss": 0.3555,
+      "num_input_tokens_seen": 390944,
+      "step": 17,
+      "train_runtime": 51.4481,
+      "train_tokens_per_second": 7598.811
+    },
+    {
+      "epoch": 0.14545454545454545,
+      "grad_norm": 1.9212645292282104,
+      "learning_rate": 1.901234567901235e-05,
+      "loss": 0.3191,
+      "num_input_tokens_seen": 414144,
+      "step": 18,
+      "train_runtime": 53.5341,
+      "train_tokens_per_second": 7736.071
+    },
+    {
+      "epoch": 0.15353535353535352,
+      "grad_norm": 1.9833357334136963,
+      "learning_rate": 1.8930041152263377e-05,
+      "loss": 0.3033,
+      "num_input_tokens_seen": 435840,
+      "step": 19,
+      "train_runtime": 55.4996,
+      "train_tokens_per_second": 7853.023
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 1.8135859966278076,
+      "learning_rate": 1.8847736625514405e-05,
+      "loss": 0.3375,
+      "num_input_tokens_seen": 459808,
+      "step": 20,
+      "train_runtime": 57.6671,
+      "train_tokens_per_second": 7973.49
+    },
+    {
+      "epoch": 0.1696969696969697,
+      "grad_norm": 1.9057047367095947,
+      "learning_rate": 1.8765432098765433e-05,
+      "loss": 0.3338,
+      "num_input_tokens_seen": 479504,
+      "step": 21,
+      "train_runtime": 59.4876,
+      "train_tokens_per_second": 8060.567
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.8097015619277954,
+      "learning_rate": 1.868312757201646e-05,
+      "loss": 0.3333,
+      "num_input_tokens_seen": 505712,
+      "step": 22,
+      "train_runtime": 61.8524,
+      "train_tokens_per_second": 8176.108
+    },
+    {
+      "epoch": 0.18585858585858586,
+      "grad_norm": 2.087014675140381,
+      "learning_rate": 1.860082304526749e-05,
+      "loss": 0.3309,
+      "num_input_tokens_seen": 525456,
+      "step": 23,
+      "train_runtime": 63.693,
+      "train_tokens_per_second": 8249.829
+    },
+    {
+      "epoch": 0.19393939393939394,
+      "grad_norm": 2.135472536087036,
+      "learning_rate": 1.851851851851852e-05,
+      "loss": 0.3742,
+      "num_input_tokens_seen": 548928,
+      "step": 24,
+      "train_runtime": 65.8153,
+      "train_tokens_per_second": 8340.436
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 2.068189859390259,
+      "learning_rate": 1.843621399176955e-05,
+      "loss": 0.3191,
+      "num_input_tokens_seen": 568608,
+      "step": 25,
+      "train_runtime": 67.6509,
+      "train_tokens_per_second": 8405.03
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "eval_loss": 0.30983325839042664,
+      "eval_runtime": 10.55,
+      "eval_samples_per_second": 83.318,
+      "eval_steps_per_second": 5.213,
+      "num_input_tokens_seen": 568608,
+      "step": 25
+    },
+    {
+      "epoch": 0.2101010101010101,
+      "grad_norm": 2.005445718765259,
+      "learning_rate": 1.835390946502058e-05,
+      "loss": 0.3055,
+      "num_input_tokens_seen": 592240,
+      "step": 26,
+      "train_runtime": 81.0864,
+      "train_tokens_per_second": 7303.813
+    },
+    {
+      "epoch": 0.21818181818181817,
+      "grad_norm": 1.9169626235961914,
+      "learning_rate": 1.8271604938271607e-05,
+      "loss": 0.2896,
+      "num_input_tokens_seen": 613168,
+      "step": 27,
+      "train_runtime": 83.0241,
+      "train_tokens_per_second": 7385.42
+    },
+    {
+      "epoch": 0.22626262626262628,
+      "grad_norm": 1.8428266048431396,
+      "learning_rate": 1.8189300411522635e-05,
+      "loss": 0.3012,
+      "num_input_tokens_seen": 637552,
+      "step": 28,
+      "train_runtime": 85.2155,
+      "train_tokens_per_second": 7481.643
+    },
+    {
+      "epoch": 0.23434343434343435,
+      "grad_norm": 1.9976342916488647,
+      "learning_rate": 1.8106995884773663e-05,
+      "loss": 0.3314,
+      "num_input_tokens_seen": 661184,
+      "step": 29,
+      "train_runtime": 87.3748,
+      "train_tokens_per_second": 7567.217
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 1.928344964981079,
+      "learning_rate": 1.802469135802469e-05,
+      "loss": 0.3567,
+      "num_input_tokens_seen": 683072,
+      "step": 30,
+      "train_runtime": 89.3764,
+      "train_tokens_per_second": 7642.645
+    },
+    {
+      "epoch": 0.2505050505050505,
+      "grad_norm": 1.8772201538085938,
+      "learning_rate": 1.7942386831275723e-05,
+      "loss": 0.3105,
+      "num_input_tokens_seen": 703776,
+      "step": 31,
+      "train_runtime": 107.296,
+      "train_tokens_per_second": 6559.199
+    },
+    {
+      "epoch": 0.2585858585858586,
+      "grad_norm": 1.742013692855835,
+      "learning_rate": 1.786008230452675e-05,
+      "loss": 0.3078,
+      "num_input_tokens_seen": 729584,
+      "step": 32,
+      "train_runtime": 109.5875,
+      "train_tokens_per_second": 6657.545
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 2.0742855072021484,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.3568,
+      "num_input_tokens_seen": 752672,
+      "step": 33,
+      "train_runtime": 111.6837,
+      "train_tokens_per_second": 6739.321
+    },
+    {
+      "epoch": 0.27474747474747474,
+      "grad_norm": 2.038970947265625,
+      "learning_rate": 1.769547325102881e-05,
+      "loss": 0.3193,
+      "num_input_tokens_seen": 776672,
+      "step": 34,
+      "train_runtime": 113.8655,
+      "train_tokens_per_second": 6820.962
+    },
+    {
+      "epoch": 0.2828282828282828,
+      "grad_norm": 1.8307162523269653,
+      "learning_rate": 1.7613168724279837e-05,
+      "loss": 0.3426,
+      "num_input_tokens_seen": 801296,
+      "step": 35,
+      "train_runtime": 116.0796,
+      "train_tokens_per_second": 6902.987
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 2.0113823413848877,
+      "learning_rate": 1.7530864197530865e-05,
+      "loss": 0.3058,
+      "num_input_tokens_seen": 822368,
+      "step": 36,
+      "train_runtime": 117.9981,
+      "train_tokens_per_second": 6969.331
+    },
+    {
+      "epoch": 0.298989898989899,
+      "grad_norm": 1.922239899635315,
+      "learning_rate": 1.7448559670781893e-05,
+      "loss": 0.2951,
+      "num_input_tokens_seen": 848928,
+      "step": 37,
+      "train_runtime": 120.382,
+      "train_tokens_per_second": 7051.954
+    },
+    {
+      "epoch": 0.30707070707070705,
+      "grad_norm": 1.8546710014343262,
+      "learning_rate": 1.7366255144032925e-05,
+      "loss": 0.2751,
+      "num_input_tokens_seen": 870672,
+      "step": 38,
+      "train_runtime": 122.3477,
+      "train_tokens_per_second": 7116.372
+    },
+    {
+      "epoch": 0.3151515151515151,
+      "grad_norm": 2.022054433822632,
+      "learning_rate": 1.728395061728395e-05,
+      "loss": 0.3516,
+      "num_input_tokens_seen": 892064,
+      "step": 39,
+      "train_runtime": 124.3075,
+      "train_tokens_per_second": 7176.271
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 1.8261455297470093,
+      "learning_rate": 1.720164609053498e-05,
+      "loss": 0.3178,
+      "num_input_tokens_seen": 915680,
+      "step": 40,
+      "train_runtime": 126.4529,
+      "train_tokens_per_second": 7241.273
+    },
+    {
+      "epoch": 0.33131313131313134,
+      "grad_norm": 2.0345096588134766,
+      "learning_rate": 1.711934156378601e-05,
+      "loss": 0.3142,
+      "num_input_tokens_seen": 935216,
+      "step": 41,
+      "train_runtime": 128.2566,
+      "train_tokens_per_second": 7291.759
+    },
+    {
+      "epoch": 0.3393939393939394,
+      "grad_norm": 1.9947233200073242,
+      "learning_rate": 1.7037037037037038e-05,
+      "loss": 0.3049,
+      "num_input_tokens_seen": 956864,
+      "step": 42,
+      "train_runtime": 130.2476,
+      "train_tokens_per_second": 7346.5
+    },
+    {
+      "epoch": 0.3474747474747475,
+      "grad_norm": 2.135382652282715,
+      "learning_rate": 1.6954732510288067e-05,
+      "loss": 0.3233,
+      "num_input_tokens_seen": 981440,
+      "step": 43,
+      "train_runtime": 132.4658,
+      "train_tokens_per_second": 7409.008
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 2.0088696479797363,
+      "learning_rate": 1.68724279835391e-05,
+      "loss": 0.297,
+      "num_input_tokens_seen": 1001232,
+      "step": 44,
+      "train_runtime": 134.324,
+      "train_tokens_per_second": 7453.858
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.9240626096725464,
+      "learning_rate": 1.6790123456790123e-05,
+      "loss": 0.2836,
+      "num_input_tokens_seen": 1027680,
+      "step": 45,
+      "train_runtime": 136.7055,
+      "train_tokens_per_second": 7517.473
+    },
+    {
+      "epoch": 0.3717171717171717,
+      "grad_norm": 1.9892817735671997,
+      "learning_rate": 1.670781893004115e-05,
+      "loss": 0.3567,
+      "num_input_tokens_seen": 1049968,
+      "step": 46,
+      "train_runtime": 138.7457,
+      "train_tokens_per_second": 7567.57
+    },
+    {
+      "epoch": 0.3797979797979798,
+      "grad_norm": 2.067185401916504,
+      "learning_rate": 1.6625514403292183e-05,
+      "loss": 0.3299,
+      "num_input_tokens_seen": 1071840,
+      "step": 47,
+      "train_runtime": 140.7519,
+      "train_tokens_per_second": 7615.101
+    },
+    {
+      "epoch": 0.3878787878787879,
+      "grad_norm": 1.953230619430542,
+      "learning_rate": 1.654320987654321e-05,
+      "loss": 0.2794,
+      "num_input_tokens_seen": 1092864,
+      "step": 48,
+      "train_runtime": 142.7001,
+      "train_tokens_per_second": 7658.469
+    },
+    {
+      "epoch": 0.39595959595959596,
+      "grad_norm": 1.9437150955200195,
+      "learning_rate": 1.646090534979424e-05,
+      "loss": 0.3269,
+      "num_input_tokens_seen": 1117040,
+      "step": 49,
+      "train_runtime": 144.8716,
+      "train_tokens_per_second": 7710.55
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 1.921739101409912,
+      "learning_rate": 1.6378600823045268e-05,
+      "loss": 0.3297,
+      "num_input_tokens_seen": 1140240,
+      "step": 50,
+      "train_runtime": 146.9806,
+      "train_tokens_per_second": 7757.759
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "eval_loss": 0.30039629340171814,
+      "eval_runtime": 7.062,
+      "eval_samples_per_second": 124.469,
+      "eval_steps_per_second": 7.788,
+      "num_input_tokens_seen": 1140240,
+      "step": 50
+    },
+    {
+      "epoch": 0.4121212121212121,
+      "grad_norm": 2.030803918838501,
+      "learning_rate": 1.6296296296296297e-05,
+      "loss": 0.317,
+      "num_input_tokens_seen": 1161104,
+      "step": 51,
+      "train_runtime": 155.9849,
+      "train_tokens_per_second": 7443.696
+    },
+    {
+      "epoch": 0.4202020202020202,
+      "grad_norm": 1.6810036897659302,
+      "learning_rate": 1.6213991769547325e-05,
+      "loss": 0.3059,
+      "num_input_tokens_seen": 1189328,
+      "step": 52,
+      "train_runtime": 158.5167,
+      "train_tokens_per_second": 7502.855
+    },
+    {
+      "epoch": 0.42828282828282827,
+      "grad_norm": 1.7849842309951782,
+      "learning_rate": 1.6131687242798357e-05,
+      "loss": 0.2731,
+      "num_input_tokens_seen": 1211120,
+      "step": 53,
+      "train_runtime": 160.4993,
+      "train_tokens_per_second": 7545.95
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 1.7593951225280762,
+      "learning_rate": 1.6049382716049385e-05,
+      "loss": 0.2982,
+      "num_input_tokens_seen": 1234080,
+      "step": 54,
+      "train_runtime": 162.5873,
+      "train_tokens_per_second": 7590.26
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.9831680059432983,
+      "learning_rate": 1.5967078189300413e-05,
+      "loss": 0.3024,
+      "num_input_tokens_seen": 1256880,
+      "step": 55,
+      "train_runtime": 164.6649,
+      "train_tokens_per_second": 7632.957
+    },
+    {
+      "epoch": 0.45252525252525255,
+      "grad_norm": 1.9270755052566528,
+      "learning_rate": 1.588477366255144e-05,
+      "loss": 0.3484,
+      "num_input_tokens_seen": 1281376,
+      "step": 56,
+      "train_runtime": 166.8926,
+      "train_tokens_per_second": 7677.849
+    },
+    {
+      "epoch": 0.46060606060606063,
+      "grad_norm": 1.7645379304885864,
+      "learning_rate": 1.580246913580247e-05,
+      "loss": 0.2909,
+      "num_input_tokens_seen": 1309216,
+      "step": 57,
+      "train_runtime": 169.4269,
+      "train_tokens_per_second": 7727.323
+    },
+    {
+      "epoch": 0.4686868686868687,
+      "grad_norm": 2.019009590148926,
+      "learning_rate": 1.5720164609053498e-05,
+      "loss": 0.37,
+      "num_input_tokens_seen": 1331120,
+      "step": 58,
+      "train_runtime": 171.4602,
+      "train_tokens_per_second": 7763.433
+    },
+    {
+      "epoch": 0.4767676767676768,
+      "grad_norm": 1.8868393898010254,
+      "learning_rate": 1.5637860082304527e-05,
+      "loss": 0.2952,
+      "num_input_tokens_seen": 1354976,
+      "step": 59,
+      "train_runtime": 173.6145,
+      "train_tokens_per_second": 7804.51
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 2.1054604053497314,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.3012,
+      "num_input_tokens_seen": 1376976,
+      "step": 60,
+      "train_runtime": 175.6397,
+      "train_tokens_per_second": 7839.778
+    },
+    {
+      "epoch": 0.49292929292929294,
+      "grad_norm": 1.8059983253479004,
+      "learning_rate": 1.5473251028806587e-05,
+      "loss": 0.3007,
+      "num_input_tokens_seen": 1397952,
+      "step": 61,
+      "train_runtime": 193.5698,
+      "train_tokens_per_second": 7221.952
+    },
+    {
+      "epoch": 0.501010101010101,
+      "grad_norm": 1.8705294132232666,
+      "learning_rate": 1.5390946502057615e-05,
+      "loss": 0.2984,
+      "num_input_tokens_seen": 1417712,
+      "step": 62,
+      "train_runtime": 195.3895,
+      "train_tokens_per_second": 7255.825
+    },
+    {
+      "epoch": 0.509090909090909,
+      "grad_norm": 1.9110565185546875,
+      "learning_rate": 1.5308641975308643e-05,
+      "loss": 0.2868,
+      "num_input_tokens_seen": 1438544,
+      "step": 63,
+      "train_runtime": 197.311,
+      "train_tokens_per_second": 7290.746
+    },
+    {
+      "epoch": 0.5171717171717172,
+      "grad_norm": 1.8605395555496216,
+      "learning_rate": 1.5226337448559672e-05,
+      "loss": 0.2894,
+      "num_input_tokens_seen": 1461776,
+      "step": 64,
+      "train_runtime": 199.4092,
+      "train_tokens_per_second": 7330.533
+    },
+    {
+      "epoch": 0.5252525252525253,
+      "grad_norm": 1.9197546243667603,
+      "learning_rate": 1.51440329218107e-05,
+      "loss": 0.3344,
+      "num_input_tokens_seen": 1483600,
+      "step": 65,
+      "train_runtime": 201.3793,
+      "train_tokens_per_second": 7367.193
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.8143887519836426,
+      "learning_rate": 1.506172839506173e-05,
+      "loss": 0.3272,
+      "num_input_tokens_seen": 1507280,
+      "step": 66,
+      "train_runtime": 203.5195,
+      "train_tokens_per_second": 7406.072
+    },
+    {
+      "epoch": 0.5414141414141415,
+      "grad_norm": 1.9554014205932617,
+      "learning_rate": 1.4979423868312758e-05,
+      "loss": 0.3072,
+      "num_input_tokens_seen": 1530176,
+      "step": 67,
+      "train_runtime": 205.5865,
+      "train_tokens_per_second": 7442.978
+    },
+    {
+      "epoch": 0.5494949494949495,
+      "grad_norm": 1.8135331869125366,
+      "learning_rate": 1.4897119341563788e-05,
+      "loss": 0.2907,
+      "num_input_tokens_seen": 1553520,
+      "step": 68,
+      "train_runtime": 207.7058,
+      "train_tokens_per_second": 7479.424
+    },
+    {
+      "epoch": 0.5575757575757576,
+      "grad_norm": 1.7284748554229736,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.3004,
+      "num_input_tokens_seen": 1577728,
+      "step": 69,
+      "train_runtime": 209.9215,
+      "train_tokens_per_second": 7515.801
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 1.9973853826522827,
+      "learning_rate": 1.4732510288065845e-05,
+      "loss": 0.2774,
+      "num_input_tokens_seen": 1598448,
+      "step": 70,
+      "train_runtime": 211.8265,
+      "train_tokens_per_second": 7546.025
+    },
+    {
+      "epoch": 0.5737373737373738,
+      "grad_norm": 1.867518663406372,
+      "learning_rate": 1.4650205761316873e-05,
+      "loss": 0.2953,
+      "num_input_tokens_seen": 1619616,
+      "step": 71,
+      "train_runtime": 213.7737,
+      "train_tokens_per_second": 7576.311
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 1.87697172164917,
+      "learning_rate": 1.4567901234567903e-05,
+      "loss": 0.3165,
+      "num_input_tokens_seen": 1647504,
+      "step": 72,
+      "train_runtime": 216.2825,
+      "train_tokens_per_second": 7617.373
+    },
+    {
+      "epoch": 0.5898989898989899,
+      "grad_norm": 2.0404067039489746,
+      "learning_rate": 1.4485596707818932e-05,
+      "loss": 0.325,
+      "num_input_tokens_seen": 1669600,
+      "step": 73,
+      "train_runtime": 218.3171,
+      "train_tokens_per_second": 7647.592
+    },
+    {
+      "epoch": 0.597979797979798,
+      "grad_norm": 1.9081746339797974,
+      "learning_rate": 1.4403292181069962e-05,
+      "loss": 0.3295,
+      "num_input_tokens_seen": 1692464,
+      "step": 74,
+      "train_runtime": 220.4059,
+      "train_tokens_per_second": 7678.851
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 1.9184836149215698,
+      "learning_rate": 1.4320987654320988e-05,
+      "loss": 0.3046,
+      "num_input_tokens_seen": 1714544,
+      "step": 75,
+      "train_runtime": 222.438,
+      "train_tokens_per_second": 7707.964
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "eval_loss": 0.2966873049736023,
+      "eval_runtime": 7.0993,
+      "eval_samples_per_second": 123.814,
+      "eval_steps_per_second": 7.747,
+      "num_input_tokens_seen": 1714544,
+      "step": 75
+    },
+    {
+      "epoch": 0.6141414141414141,
+      "grad_norm": 1.9091130495071411,
+      "learning_rate": 1.4238683127572017e-05,
+      "loss": 0.3117,
+      "num_input_tokens_seen": 1734992,
+      "step": 76,
+      "train_runtime": 231.4507,
+      "train_tokens_per_second": 7496.164
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.8281859159469604,
+      "learning_rate": 1.4156378600823047e-05,
+      "loss": 0.3165,
+      "num_input_tokens_seen": 1758528,
+      "step": 77,
+      "train_runtime": 233.6112,
+      "train_tokens_per_second": 7527.584
+    },
+    {
+      "epoch": 0.6303030303030303,
+      "grad_norm": 2.0086405277252197,
+      "learning_rate": 1.4074074074074075e-05,
+      "loss": 0.3239,
+      "num_input_tokens_seen": 1782768,
+      "step": 78,
+      "train_runtime": 235.7867,
+      "train_tokens_per_second": 7560.935
+    },
+    {
+      "epoch": 0.6383838383838384,
+      "grad_norm": 1.9040608406066895,
+      "learning_rate": 1.3991769547325105e-05,
+      "loss": 0.3269,
+      "num_input_tokens_seen": 1806000,
+      "step": 79,
+      "train_runtime": 237.8964,
+      "train_tokens_per_second": 7591.539
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 1.8077948093414307,
+      "learning_rate": 1.3909465020576133e-05,
+      "loss": 0.3069,
+      "num_input_tokens_seen": 1833264,
+      "step": 80,
+      "train_runtime": 240.3427,
+      "train_tokens_per_second": 7627.708
+    },
+    {
+      "epoch": 0.6545454545454545,
+      "grad_norm": 2.132566452026367,
+      "learning_rate": 1.3827160493827162e-05,
+      "loss": 0.3564,
+      "num_input_tokens_seen": 1855920,
+      "step": 81,
+      "train_runtime": 242.4326,
+      "train_tokens_per_second": 7655.407
+    },
+    {
+      "epoch": 0.6626262626262627,
+      "grad_norm": 1.9666991233825684,
+      "learning_rate": 1.374485596707819e-05,
+      "loss": 0.3299,
+      "num_input_tokens_seen": 1877664,
+      "step": 82,
+      "train_runtime": 244.4539,
+      "train_tokens_per_second": 7681.055
+    },
+    {
+      "epoch": 0.6707070707070707,
+      "grad_norm": 1.7784312963485718,
+      "learning_rate": 1.366255144032922e-05,
+      "loss": 0.2704,
+      "num_input_tokens_seen": 1901152,
+      "step": 83,
+      "train_runtime": 246.5816,
+      "train_tokens_per_second": 7710.033
+    },
+    {
+      "epoch": 0.6787878787878788,
+      "grad_norm": 1.9089895486831665,
+      "learning_rate": 1.3580246913580248e-05,
+      "loss": 0.3071,
+      "num_input_tokens_seen": 1927440,
+      "step": 84,
+      "train_runtime": 248.9261,
+      "train_tokens_per_second": 7743.02
+    },
+    {
+      "epoch": 0.6868686868686869,
+      "grad_norm": 2.1388967037200928,
+      "learning_rate": 1.3497942386831278e-05,
+      "loss": 0.3121,
+      "num_input_tokens_seen": 1951408,
+      "step": 85,
+      "train_runtime": 251.0849,
+      "train_tokens_per_second": 7771.906
+    },
+    {
+      "epoch": 0.694949494949495,
+      "grad_norm": 1.9663597345352173,
+      "learning_rate": 1.3415637860082307e-05,
+      "loss": 0.3255,
+      "num_input_tokens_seen": 1973200,
+      "step": 86,
+      "train_runtime": 253.071,
+      "train_tokens_per_second": 7797.022
+    },
+    {
+      "epoch": 0.703030303030303,
+      "grad_norm": 1.8622767925262451,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3316,
+      "num_input_tokens_seen": 1994528,
+      "step": 87,
+      "train_runtime": 255.0392,
+      "train_tokens_per_second": 7820.476
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 2.091785430908203,
+      "learning_rate": 1.3251028806584363e-05,
+      "loss": 0.29,
+      "num_input_tokens_seen": 2019248,
+      "step": 88,
+      "train_runtime": 257.2586,
+      "train_tokens_per_second": 7849.097
+    },
+    {
+      "epoch": 0.7191919191919192,
+      "grad_norm": 1.9802072048187256,
+      "learning_rate": 1.3168724279835392e-05,
+      "loss": 0.3108,
+      "num_input_tokens_seen": 2040592,
+      "step": 89,
+      "train_runtime": 259.2297,
+      "train_tokens_per_second": 7871.751
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 1.8566641807556152,
+      "learning_rate": 1.3086419753086422e-05,
+      "loss": 0.2818,
+      "num_input_tokens_seen": 2062032,
+      "step": 90,
+      "train_runtime": 261.2082,
+      "train_tokens_per_second": 7894.21
+    },
+    {
+      "epoch": 0.7353535353535353,
+      "grad_norm": 2.006922960281372,
+      "learning_rate": 1.300411522633745e-05,
+      "loss": 0.2786,
+      "num_input_tokens_seen": 2082368,
+      "step": 91,
+      "train_runtime": 279.7434,
+      "train_tokens_per_second": 7443.85
+    },
+    {
+      "epoch": 0.7434343434343434,
+      "grad_norm": 1.9318790435791016,
+      "learning_rate": 1.2921810699588477e-05,
+      "loss": 0.2882,
+      "num_input_tokens_seen": 2104976,
+      "step": 92,
+      "train_runtime": 281.7953,
+      "train_tokens_per_second": 7469.876
+    },
+    {
+      "epoch": 0.7515151515151515,
+      "grad_norm": 2.0379955768585205,
+      "learning_rate": 1.2839506172839507e-05,
+      "loss": 0.3164,
+      "num_input_tokens_seen": 2125664,
+      "step": 93,
+      "train_runtime": 283.6716,
+      "train_tokens_per_second": 7493.396
+    },
+    {
+      "epoch": 0.7595959595959596,
+      "grad_norm": 1.7655056715011597,
+      "learning_rate": 1.2757201646090535e-05,
+      "loss": 0.2632,
+      "num_input_tokens_seen": 2151216,
+      "step": 94,
+      "train_runtime": 285.9821,
+      "train_tokens_per_second": 7522.204
+    },
+    {
+      "epoch": 0.7676767676767676,
+      "grad_norm": 2.0078585147857666,
+      "learning_rate": 1.2674897119341565e-05,
+      "loss": 0.3138,
+      "num_input_tokens_seen": 2174480,
+      "step": 95,
+      "train_runtime": 288.0796,
+      "train_tokens_per_second": 7548.192
+    },
+    {
+      "epoch": 0.7757575757575758,
+      "grad_norm": 1.8399180173873901,
+      "learning_rate": 1.2592592592592593e-05,
+      "loss": 0.2765,
+      "num_input_tokens_seen": 2198048,
+      "step": 96,
+      "train_runtime": 290.2011,
+      "train_tokens_per_second": 7574.225
+    },
+    {
+      "epoch": 0.7838383838383839,
+      "grad_norm": 2.049941301345825,
+      "learning_rate": 1.2510288065843623e-05,
+      "loss": 0.3136,
+      "num_input_tokens_seen": 2218944,
+      "step": 97,
+      "train_runtime": 292.1183,
+      "train_tokens_per_second": 7596.047
+    },
+    {
+      "epoch": 0.7919191919191919,
+      "grad_norm": 1.8334540128707886,
+      "learning_rate": 1.242798353909465e-05,
+      "loss": 0.3265,
+      "num_input_tokens_seen": 2244752,
+      "step": 98,
+      "train_runtime": 294.4345,
+      "train_tokens_per_second": 7623.944
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.317540168762207,
+      "learning_rate": 1.234567901234568e-05,
+      "loss": 0.3505,
+      "num_input_tokens_seen": 2267728,
+      "step": 99,
+      "train_runtime": 296.5099,
+      "train_tokens_per_second": 7648.068
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 1.9731619358062744,
+      "learning_rate": 1.2263374485596708e-05,
+      "loss": 0.2984,
+      "num_input_tokens_seen": 2289328,
+      "step": 100,
+      "train_runtime": 298.4904,
+      "train_tokens_per_second": 7669.686
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "eval_loss": 0.29423120617866516,
+      "eval_runtime": 7.029,
+      "eval_samples_per_second": 125.053,
+      "eval_steps_per_second": 7.825,
+      "num_input_tokens_seen": 2289328,
+      "step": 100
+    },
+    {
+      "epoch": 0.8161616161616162,
+      "grad_norm": 2.0644495487213135,
+      "learning_rate": 1.2181069958847738e-05,
+      "loss": 0.326,
+      "num_input_tokens_seen": 2313216,
+      "step": 101,
+      "train_runtime": 307.6926,
+      "train_tokens_per_second": 7517.945
+    },
+    {
+      "epoch": 0.8242424242424242,
+      "grad_norm": 1.9370036125183105,
+      "learning_rate": 1.2098765432098767e-05,
+      "loss": 0.2865,
+      "num_input_tokens_seen": 2333152,
+      "step": 102,
+      "train_runtime": 309.5355,
+      "train_tokens_per_second": 7537.591
+    },
+    {
+      "epoch": 0.8323232323232324,
+      "grad_norm": 1.9265321493148804,
+      "learning_rate": 1.2016460905349797e-05,
+      "loss": 0.3275,
+      "num_input_tokens_seen": 2355744,
+      "step": 103,
+      "train_runtime": 311.5913,
+      "train_tokens_per_second": 7560.365
+    },
+    {
+      "epoch": 0.8404040404040404,
+      "grad_norm": 1.9668643474578857,
+      "learning_rate": 1.1934156378600823e-05,
+      "loss": 0.3592,
+      "num_input_tokens_seen": 2376560,
+      "step": 104,
+      "train_runtime": 313.4969,
+      "train_tokens_per_second": 7580.81
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 1.9941215515136719,
+      "learning_rate": 1.1851851851851852e-05,
+      "loss": 0.2986,
+      "num_input_tokens_seen": 2400896,
+      "step": 105,
+      "train_runtime": 315.6988,
+      "train_tokens_per_second": 7605.02
+    },
+    {
+      "epoch": 0.8565656565656565,
+      "grad_norm": 2.070256233215332,
+      "learning_rate": 1.1769547325102882e-05,
+      "loss": 0.3146,
+      "num_input_tokens_seen": 2423632,
+      "step": 106,
+      "train_runtime": 317.7728,
+      "train_tokens_per_second": 7626.933
+    },
+    {
+      "epoch": 0.8646464646464647,
+      "grad_norm": 1.929892659187317,
+      "learning_rate": 1.168724279835391e-05,
+      "loss": 0.33,
+      "num_input_tokens_seen": 2448432,
+      "step": 107,
+      "train_runtime": 320.0049,
+      "train_tokens_per_second": 7651.233
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 1.7959911823272705,
+      "learning_rate": 1.160493827160494e-05,
+      "loss": 0.3109,
+      "num_input_tokens_seen": 2470768,
+      "step": 108,
+      "train_runtime": 322.0228,
+      "train_tokens_per_second": 7672.65
+    },
+    {
+      "epoch": 0.8808080808080808,
+      "grad_norm": 1.8385419845581055,
+      "learning_rate": 1.1522633744855968e-05,
+      "loss": 0.2902,
+      "num_input_tokens_seen": 2494944,
+      "step": 109,
+      "train_runtime": 324.2378,
+      "train_tokens_per_second": 7694.798
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.9622164964675903,
+      "learning_rate": 1.1440329218106997e-05,
+      "loss": 0.3503,
+      "num_input_tokens_seen": 2515760,
+      "step": 110,
+      "train_runtime": 326.16,
+      "train_tokens_per_second": 7713.268
+    },
+    {
+      "epoch": 0.896969696969697,
+      "grad_norm": 1.9579459428787231,
+      "learning_rate": 1.1358024691358025e-05,
+      "loss": 0.2731,
+      "num_input_tokens_seen": 2537792,
+      "step": 111,
+      "train_runtime": 328.183,
+      "train_tokens_per_second": 7732.857
+    },
+    {
+      "epoch": 0.9050505050505051,
+      "grad_norm": 1.8197929859161377,
+      "learning_rate": 1.1275720164609055e-05,
+      "loss": 0.2742,
+      "num_input_tokens_seen": 2562032,
+      "step": 112,
+      "train_runtime": 330.3793,
+      "train_tokens_per_second": 7754.819
+    },
+    {
+      "epoch": 0.9131313131313131,
+      "grad_norm": 2.2101240158081055,
+      "learning_rate": 1.1193415637860083e-05,
+      "loss": 0.3154,
+      "num_input_tokens_seen": 2583760,
+      "step": 113,
+      "train_runtime": 332.3672,
+      "train_tokens_per_second": 7773.81
+    },
+    {
+      "epoch": 0.9212121212121213,
+      "grad_norm": 1.961485743522644,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.2789,
+      "num_input_tokens_seen": 2607776,
+      "step": 114,
+      "train_runtime": 334.5191,
+      "train_tokens_per_second": 7795.596
+    },
+    {
+      "epoch": 0.9292929292929293,
+      "grad_norm": 2.0995683670043945,
+      "learning_rate": 1.1028806584362142e-05,
+      "loss": 0.3263,
+      "num_input_tokens_seen": 2630208,
+      "step": 115,
+      "train_runtime": 336.587,
+      "train_tokens_per_second": 7814.349
+    },
+    {
+      "epoch": 0.9373737373737374,
+      "grad_norm": 2.0641095638275146,
+      "learning_rate": 1.0946502057613168e-05,
+      "loss": 0.2851,
+      "num_input_tokens_seen": 2650208,
+      "step": 116,
+      "train_runtime": 338.4264,
+      "train_tokens_per_second": 7830.972
+    },
+    {
+      "epoch": 0.9454545454545454,
+      "grad_norm": 2.0057430267333984,
+      "learning_rate": 1.0864197530864198e-05,
+      "loss": 0.3165,
+      "num_input_tokens_seen": 2672592,
+      "step": 117,
+      "train_runtime": 340.4808,
+      "train_tokens_per_second": 7849.464
+    },
+    {
+      "epoch": 0.9535353535353536,
+      "grad_norm": 1.996042251586914,
+      "learning_rate": 1.0781893004115227e-05,
+      "loss": 0.2761,
+      "num_input_tokens_seen": 2698064,
+      "step": 118,
+      "train_runtime": 342.8571,
+      "train_tokens_per_second": 7869.354
+    },
+    {
+      "epoch": 0.9616161616161616,
+      "grad_norm": 1.9719218015670776,
+      "learning_rate": 1.0699588477366257e-05,
+      "loss": 0.3056,
+      "num_input_tokens_seen": 2719680,
+      "step": 119,
+      "train_runtime": 344.8444,
+      "train_tokens_per_second": 7886.688
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 1.7962714433670044,
+      "learning_rate": 1.0617283950617285e-05,
+      "loss": 0.2745,
+      "num_input_tokens_seen": 2742400,
+      "step": 120,
+      "train_runtime": 346.9298,
+      "train_tokens_per_second": 7904.768
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.91484797000885,
+      "learning_rate": 1.0534979423868315e-05,
+      "loss": 0.2906,
+      "num_input_tokens_seen": 2766112,
+      "step": 121,
+      "train_runtime": 365.0207,
+      "train_tokens_per_second": 7577.96
+    },
+    {
+      "epoch": 0.9858585858585859,
+      "grad_norm": 1.9865151643753052,
+      "learning_rate": 1.0452674897119342e-05,
+      "loss": 0.291,
+      "num_input_tokens_seen": 2787952,
+      "step": 122,
+      "train_runtime": 366.9952,
+      "train_tokens_per_second": 7596.699
+    },
+    {
+      "epoch": 0.9939393939393939,
+      "grad_norm": 2.03933048248291,
+      "learning_rate": 1.037037037037037e-05,
+      "loss": 0.3486,
+      "num_input_tokens_seen": 2811632,
+      "step": 123,
+      "train_runtime": 369.1409,
+      "train_tokens_per_second": 7616.69
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.3509812355041504,
+      "learning_rate": 1.02880658436214e-05,
+      "loss": 0.2723,
+      "num_input_tokens_seen": 2825206,
+      "step": 124,
+      "train_runtime": 372.5555,
+      "train_tokens_per_second": 7583.315
+    },
+    {
+      "epoch": 1.0080808080808081,
+      "grad_norm": 2.5542423725128174,
+      "learning_rate": 1.0205761316872428e-05,
+      "loss": 0.271,
+      "num_input_tokens_seen": 2847206,
+      "step": 125,
+      "train_runtime": 374.5469,
+      "train_tokens_per_second": 7601.734
+    },
+    {
+      "epoch": 1.0080808080808081,
+      "eval_loss": 0.2926430106163025,
+      "eval_runtime": 7.026,
+      "eval_samples_per_second": 125.107,
+      "eval_steps_per_second": 7.828,
+      "num_input_tokens_seen": 2847206,
+      "step": 125
+    },
+    {
+      "epoch": 1.0161616161616163,
+      "grad_norm": 2.485454797744751,
+      "learning_rate": 1.0123456790123458e-05,
+      "loss": 0.2351,
+      "num_input_tokens_seen": 2867190,
+      "step": 126,
+      "train_runtime": 383.4417,
+      "train_tokens_per_second": 7477.513
+    },
+    {
+      "epoch": 1.0242424242424242,
+      "grad_norm": 1.870703101158142,
+      "learning_rate": 1.0041152263374487e-05,
+      "loss": 0.2432,
+      "num_input_tokens_seen": 2888710,
+      "step": 127,
+      "train_runtime": 385.4176,
+      "train_tokens_per_second": 7495.014
+    },
+    {
+      "epoch": 1.0323232323232323,
+      "grad_norm": 1.9022161960601807,
+      "learning_rate": 9.958847736625515e-06,
+      "loss": 0.2415,
+      "num_input_tokens_seen": 2913990,
+      "step": 128,
+      "train_runtime": 387.7088,
+      "train_tokens_per_second": 7515.925
+    },
+    {
+      "epoch": 1.0404040404040404,
+      "grad_norm": 2.121541738510132,
+      "learning_rate": 9.876543209876543e-06,
+      "loss": 0.2421,
+      "num_input_tokens_seen": 2938246,
+      "step": 129,
+      "train_runtime": 389.9127,
+      "train_tokens_per_second": 7535.65
+    },
+    {
+      "epoch": 1.0484848484848486,
+      "grad_norm": 1.8283259868621826,
+      "learning_rate": 9.794238683127573e-06,
+      "loss": 0.2525,
+      "num_input_tokens_seen": 2962326,
+      "step": 130,
+      "train_runtime": 392.1155,
+      "train_tokens_per_second": 7554.729
+    },
+    {
+      "epoch": 1.0565656565656565,
+      "grad_norm": 2.0393452644348145,
+      "learning_rate": 9.711934156378602e-06,
+      "loss": 0.2636,
+      "num_input_tokens_seen": 2983126,
+      "step": 131,
+      "train_runtime": 394.0236,
+      "train_tokens_per_second": 7570.933
+    },
+    {
+      "epoch": 1.0646464646464646,
+      "grad_norm": 2.0195391178131104,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 0.2488,
+      "num_input_tokens_seen": 3005606,
+      "step": 132,
+      "train_runtime": 396.0787,
+      "train_tokens_per_second": 7588.405
+    },
+    {
+      "epoch": 1.0727272727272728,
+      "grad_norm": 2.2477834224700928,
+      "learning_rate": 9.547325102880658e-06,
+      "loss": 0.2564,
+      "num_input_tokens_seen": 3027926,
+      "step": 133,
+      "train_runtime": 398.1422,
+      "train_tokens_per_second": 7605.138
+    },
+    {
+      "epoch": 1.0808080808080809,
+      "grad_norm": 2.251457691192627,
+      "learning_rate": 9.465020576131688e-06,
+      "loss": 0.2514,
+      "num_input_tokens_seen": 3052294,
+      "step": 134,
+      "train_runtime": 400.3525,
+      "train_tokens_per_second": 7624.016
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 2.3457224369049072,
+      "learning_rate": 9.382716049382717e-06,
+      "loss": 0.2447,
+      "num_input_tokens_seen": 3073014,
+      "step": 135,
+      "train_runtime": 402.2692,
+      "train_tokens_per_second": 7639.198
+    },
+    {
+      "epoch": 1.096969696969697,
+      "grad_norm": 2.5215225219726562,
+      "learning_rate": 9.300411522633745e-06,
+      "loss": 0.2123,
+      "num_input_tokens_seen": 3095126,
+      "step": 136,
+      "train_runtime": 404.2858,
+      "train_tokens_per_second": 7655.786
+    },
+    {
+      "epoch": 1.105050505050505,
+      "grad_norm": 2.9330391883850098,
+      "learning_rate": 9.218106995884775e-06,
+      "loss": 0.2813,
+      "num_input_tokens_seen": 3116438,
+      "step": 137,
+      "train_runtime": 406.2489,
+      "train_tokens_per_second": 7671.252
+    },
+    {
+      "epoch": 1.1131313131313132,
+      "grad_norm": 2.4419281482696533,
+      "learning_rate": 9.135802469135803e-06,
+      "loss": 0.2355,
+      "num_input_tokens_seen": 3139174,
+      "step": 138,
+      "train_runtime": 408.3028,
+      "train_tokens_per_second": 7688.348
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 2.1203596591949463,
+      "learning_rate": 9.053497942386832e-06,
+      "loss": 0.2362,
+      "num_input_tokens_seen": 3165206,
+      "step": 139,
+      "train_runtime": 410.6277,
+      "train_tokens_per_second": 7708.214
+    },
+    {
+      "epoch": 1.1292929292929292,
+      "grad_norm": 2.388300657272339,
+      "learning_rate": 8.971193415637862e-06,
+      "loss": 0.2683,
+      "num_input_tokens_seen": 3189942,
+      "step": 140,
+      "train_runtime": 412.8585,
+      "train_tokens_per_second": 7726.478
+    },
+    {
+      "epoch": 1.1373737373737374,
+      "grad_norm": 2.1845967769622803,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.2414,
+      "num_input_tokens_seen": 3213878,
+      "step": 141,
+      "train_runtime": 415.0261,
+      "train_tokens_per_second": 7743.798
+    },
+    {
+      "epoch": 1.1454545454545455,
+      "grad_norm": 1.9687696695327759,
+      "learning_rate": 8.806584362139918e-06,
+      "loss": 0.2828,
+      "num_input_tokens_seen": 3236806,
+      "step": 142,
+      "train_runtime": 417.1211,
+      "train_tokens_per_second": 7759.872
+    },
+    {
+      "epoch": 1.1535353535353536,
+      "grad_norm": 2.1155526638031006,
+      "learning_rate": 8.724279835390947e-06,
+      "loss": 0.2821,
+      "num_input_tokens_seen": 3258822,
+      "step": 143,
+      "train_runtime": 419.1343,
+      "train_tokens_per_second": 7775.127
+    },
+    {
+      "epoch": 1.1616161616161615,
+      "grad_norm": 2.031667947769165,
+      "learning_rate": 8.641975308641975e-06,
+      "loss": 0.2472,
+      "num_input_tokens_seen": 3280694,
+      "step": 144,
+      "train_runtime": 421.1299,
+      "train_tokens_per_second": 7790.219
+    },
+    {
+      "epoch": 1.1696969696969697,
+      "grad_norm": 2.065946340560913,
+      "learning_rate": 8.559670781893005e-06,
+      "loss": 0.24,
+      "num_input_tokens_seen": 3305894,
+      "step": 145,
+      "train_runtime": 423.386,
+      "train_tokens_per_second": 7808.226
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 2.0876126289367676,
+      "learning_rate": 8.477366255144033e-06,
+      "loss": 0.2466,
+      "num_input_tokens_seen": 3327526,
+      "step": 146,
+      "train_runtime": 425.3809,
+      "train_tokens_per_second": 7822.462
+    },
+    {
+      "epoch": 1.185858585858586,
+      "grad_norm": 1.9692819118499756,
+      "learning_rate": 8.395061728395062e-06,
+      "loss": 0.2462,
+      "num_input_tokens_seen": 3349414,
+      "step": 147,
+      "train_runtime": 427.3897,
+      "train_tokens_per_second": 7836.909
+    },
+    {
+      "epoch": 1.1939393939393939,
+      "grad_norm": 2.186434030532837,
+      "learning_rate": 8.312757201646092e-06,
+      "loss": 0.3039,
+      "num_input_tokens_seen": 3373782,
+      "step": 148,
+      "train_runtime": 429.5935,
+      "train_tokens_per_second": 7853.429
+    },
+    {
+      "epoch": 1.202020202020202,
+      "grad_norm": 2.0272040367126465,
+      "learning_rate": 8.23045267489712e-06,
+      "loss": 0.2476,
+      "num_input_tokens_seen": 3397254,
+      "step": 149,
+      "train_runtime": 431.7412,
+      "train_tokens_per_second": 7868.729
+    },
+    {
+      "epoch": 1.2101010101010101,
+      "grad_norm": 1.9289153814315796,
+      "learning_rate": 8.148148148148148e-06,
+      "loss": 0.2371,
+      "num_input_tokens_seen": 3420102,
+      "step": 150,
+      "train_runtime": 433.8468,
+      "train_tokens_per_second": 7883.202
+    },
+    {
+      "epoch": 1.2101010101010101,
+      "eval_loss": 0.2959754765033722,
+      "eval_runtime": 7.0833,
+      "eval_samples_per_second": 124.095,
+      "eval_steps_per_second": 7.765,
+      "num_input_tokens_seen": 3420102,
+      "step": 150
+    },
+    {
+      "epoch": 1.2181818181818183,
+      "grad_norm": 2.1007144451141357,
+      "learning_rate": 8.065843621399178e-06,
+      "loss": 0.265,
+      "num_input_tokens_seen": 3440438,
+      "step": 151,
+      "train_runtime": 461.0146,
+      "train_tokens_per_second": 7462.752
+    },
+    {
+      "epoch": 1.2262626262626264,
+      "grad_norm": 2.0250070095062256,
+      "learning_rate": 7.983539094650207e-06,
+      "loss": 0.2486,
+      "num_input_tokens_seen": 3466054,
+      "step": 152,
+      "train_runtime": 463.3174,
+      "train_tokens_per_second": 7480.949
+    },
+    {
+      "epoch": 1.2343434343434343,
+      "grad_norm": 1.7474883794784546,
+      "learning_rate": 7.901234567901235e-06,
+      "loss": 0.2172,
+      "num_input_tokens_seen": 3492278,
+      "step": 153,
+      "train_runtime": 465.6949,
+      "train_tokens_per_second": 7499.068
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 1.8963685035705566,
+      "learning_rate": 7.818930041152263e-06,
+      "loss": 0.2187,
+      "num_input_tokens_seen": 3512582,
+      "step": 154,
+      "train_runtime": 467.5775,
+      "train_tokens_per_second": 7512.299
+    },
+    {
+      "epoch": 1.2505050505050506,
+      "grad_norm": 1.9363595247268677,
+      "learning_rate": 7.736625514403293e-06,
+      "loss": 0.2594,
+      "num_input_tokens_seen": 3535750,
+      "step": 155,
+      "train_runtime": 469.6918,
+      "train_tokens_per_second": 7527.809
+    },
+    {
+      "epoch": 1.2585858585858585,
+      "grad_norm": 2.0793097019195557,
+      "learning_rate": 7.654320987654322e-06,
+      "loss": 0.2463,
+      "num_input_tokens_seen": 3559894,
+      "step": 156,
+      "train_runtime": 471.8957,
+      "train_tokens_per_second": 7543.816
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 2.071737289428711,
+      "learning_rate": 7.57201646090535e-06,
+      "loss": 0.2553,
+      "num_input_tokens_seen": 3580390,
+      "step": 157,
+      "train_runtime": 473.7908,
+      "train_tokens_per_second": 7556.901
+    },
+    {
+      "epoch": 1.2747474747474747,
+      "grad_norm": 1.9994101524353027,
+      "learning_rate": 7.489711934156379e-06,
+      "loss": 0.2189,
+      "num_input_tokens_seen": 3601750,
+      "step": 158,
+      "train_runtime": 475.7442,
+      "train_tokens_per_second": 7570.77
+    },
+    {
+      "epoch": 1.2828282828282829,
+      "grad_norm": 2.021566867828369,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.2453,
+      "num_input_tokens_seen": 3629030,
+      "step": 159,
+      "train_runtime": 478.1887,
+      "train_tokens_per_second": 7589.117
+    },
+    {
+      "epoch": 1.290909090909091,
+      "grad_norm": 2.1607470512390137,
+      "learning_rate": 7.325102880658437e-06,
+      "loss": 0.2541,
+      "num_input_tokens_seen": 3654358,
+      "step": 160,
+      "train_runtime": 480.4853,
+      "train_tokens_per_second": 7605.556
+    },
+    {
+      "epoch": 1.298989898989899,
+      "grad_norm": 2.1245932579040527,
+      "learning_rate": 7.242798353909466e-06,
+      "loss": 0.2361,
+      "num_input_tokens_seen": 3680758,
+      "step": 161,
+      "train_runtime": 482.8693,
+      "train_tokens_per_second": 7622.68
+    },
+    {
+      "epoch": 1.307070707070707,
+      "grad_norm": 2.2660951614379883,
+      "learning_rate": 7.160493827160494e-06,
+      "loss": 0.2438,
+      "num_input_tokens_seen": 3704022,
+      "step": 162,
+      "train_runtime": 485.004,
+      "train_tokens_per_second": 7637.096
+    },
+    {
+      "epoch": 1.3151515151515152,
+      "grad_norm": 2.2035646438598633,
+      "learning_rate": 7.078189300411523e-06,
+      "loss": 0.2482,
+      "num_input_tokens_seen": 3727814,
+      "step": 163,
+      "train_runtime": 487.1455,
+      "train_tokens_per_second": 7652.362
+    },
+    {
+      "epoch": 1.3232323232323233,
+      "grad_norm": 2.1511008739471436,
+      "learning_rate": 6.9958847736625525e-06,
+      "loss": 0.2547,
+      "num_input_tokens_seen": 3749606,
+      "step": 164,
+      "train_runtime": 489.1325,
+      "train_tokens_per_second": 7665.828
+    },
+    {
+      "epoch": 1.3313131313131312,
+      "grad_norm": 2.249523878097534,
+      "learning_rate": 6.913580246913581e-06,
+      "loss": 0.2968,
+      "num_input_tokens_seen": 3774710,
+      "step": 165,
+      "train_runtime": 491.419,
+      "train_tokens_per_second": 7681.245
+    },
+    {
+      "epoch": 1.3393939393939394,
+      "grad_norm": 2.0948562622070312,
+      "learning_rate": 6.83127572016461e-06,
+      "loss": 0.2359,
+      "num_input_tokens_seen": 3793814,
+      "step": 166,
+      "train_runtime": 493.2079,
+      "train_tokens_per_second": 7692.119
+    },
+    {
+      "epoch": 1.3474747474747475,
+      "grad_norm": 2.107844591140747,
+      "learning_rate": 6.748971193415639e-06,
+      "loss": 0.2737,
+      "num_input_tokens_seen": 3818662,
+      "step": 167,
+      "train_runtime": 495.4635,
+      "train_tokens_per_second": 7707.251
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 2.3334641456604004,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.2596,
+      "num_input_tokens_seen": 3841606,
+      "step": 168,
+      "train_runtime": 497.5542,
+      "train_tokens_per_second": 7720.98
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 2.0350282192230225,
+      "learning_rate": 6.584362139917696e-06,
+      "loss": 0.2443,
+      "num_input_tokens_seen": 3863830,
+      "step": 169,
+      "train_runtime": 499.6021,
+      "train_tokens_per_second": 7733.815
+    },
+    {
+      "epoch": 1.3717171717171717,
+      "grad_norm": 2.1754233837127686,
+      "learning_rate": 6.502057613168725e-06,
+      "loss": 0.2618,
+      "num_input_tokens_seen": 3886230,
+      "step": 170,
+      "train_runtime": 501.6397,
+      "train_tokens_per_second": 7747.055
+    },
+    {
+      "epoch": 1.3797979797979798,
+      "grad_norm": 2.145559072494507,
+      "learning_rate": 6.419753086419753e-06,
+      "loss": 0.2353,
+      "num_input_tokens_seen": 3908982,
+      "step": 171,
+      "train_runtime": 503.6986,
+      "train_tokens_per_second": 7760.557
+    },
+    {
+      "epoch": 1.387878787878788,
+      "grad_norm": 2.020923376083374,
+      "learning_rate": 6.3374485596707825e-06,
+      "loss": 0.2178,
+      "num_input_tokens_seen": 3936150,
+      "step": 172,
+      "train_runtime": 506.1611,
+      "train_tokens_per_second": 7776.477
+    },
+    {
+      "epoch": 1.3959595959595958,
+      "grad_norm": 2.0729899406433105,
+      "learning_rate": 6.255144032921812e-06,
+      "loss": 0.2592,
+      "num_input_tokens_seen": 3959430,
+      "step": 173,
+      "train_runtime": 508.2944,
+      "train_tokens_per_second": 7789.639
+    },
+    {
+      "epoch": 1.404040404040404,
+      "grad_norm": 2.098947525024414,
+      "learning_rate": 6.17283950617284e-06,
+      "loss": 0.2497,
+      "num_input_tokens_seen": 3981126,
+      "step": 174,
+      "train_runtime": 510.3129,
+      "train_tokens_per_second": 7801.344
+    },
+    {
+      "epoch": 1.412121212121212,
+      "grad_norm": 2.200272560119629,
+      "learning_rate": 6.090534979423869e-06,
+      "loss": 0.2587,
+      "num_input_tokens_seen": 4006118,
+      "step": 175,
+      "train_runtime": 512.5647,
+      "train_tokens_per_second": 7815.829
+    },
+    {
+      "epoch": 1.412121212121212,
+      "eval_loss": 0.29883837699890137,
+      "eval_runtime": 7.1029,
+      "eval_samples_per_second": 123.753,
+      "eval_steps_per_second": 7.743,
+      "num_input_tokens_seen": 4006118,
+      "step": 175
+    },
+    {
+      "epoch": 1.4202020202020202,
+      "grad_norm": 2.150625228881836,
+      "learning_rate": 6.008230452674898e-06,
+      "loss": 0.2508,
+      "num_input_tokens_seen": 4034054,
+      "step": 176,
+      "train_runtime": 522.2099,
+      "train_tokens_per_second": 7724.967
+    },
+    {
+      "epoch": 1.4282828282828284,
+      "grad_norm": 2.0687313079833984,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 0.2393,
+      "num_input_tokens_seen": 4058646,
+      "step": 177,
+      "train_runtime": 524.4627,
+      "train_tokens_per_second": 7738.674
+    },
+    {
+      "epoch": 1.4363636363636363,
+      "grad_norm": 2.018831253051758,
+      "learning_rate": 5.843621399176955e-06,
+      "loss": 0.2712,
+      "num_input_tokens_seen": 4083414,
+      "step": 178,
+      "train_runtime": 526.7043,
+      "train_tokens_per_second": 7752.764
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 2.097909450531006,
+      "learning_rate": 5.761316872427984e-06,
+      "loss": 0.2601,
+      "num_input_tokens_seen": 4107190,
+      "step": 179,
+      "train_runtime": 528.9031,
+      "train_tokens_per_second": 7765.487
+    },
+    {
+      "epoch": 1.4525252525252526,
+      "grad_norm": 2.1564548015594482,
+      "learning_rate": 5.6790123456790125e-06,
+      "loss": 0.3076,
+      "num_input_tokens_seen": 4129958,
+      "step": 180,
+      "train_runtime": 531.0094,
+      "train_tokens_per_second": 7777.561
+    },
+    {
+      "epoch": 1.4606060606060607,
+      "grad_norm": 2.1547343730926514,
+      "learning_rate": 5.596707818930042e-06,
+      "loss": 0.2285,
+      "num_input_tokens_seen": 4153302,
+      "step": 181,
+      "train_runtime": 551.2055,
+      "train_tokens_per_second": 7534.943
+    },
+    {
+      "epoch": 1.4686868686868686,
+      "grad_norm": 2.0703673362731934,
+      "learning_rate": 5.514403292181071e-06,
+      "loss": 0.237,
+      "num_input_tokens_seen": 4175222,
+      "step": 182,
+      "train_runtime": 553.2018,
+      "train_tokens_per_second": 7547.375
+    },
+    {
+      "epoch": 1.4767676767676767,
+      "grad_norm": 1.8771171569824219,
+      "learning_rate": 5.432098765432099e-06,
+      "loss": 0.2437,
+      "num_input_tokens_seen": 4196966,
+      "step": 183,
+      "train_runtime": 555.2016,
+      "train_tokens_per_second": 7559.355
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 2.054640293121338,
+      "learning_rate": 5.349794238683128e-06,
+      "loss": 0.259,
+      "num_input_tokens_seen": 4222630,
+      "step": 184,
+      "train_runtime": 557.5348,
+      "train_tokens_per_second": 7573.752
+    },
+    {
+      "epoch": 1.492929292929293,
+      "grad_norm": 2.0560507774353027,
+      "learning_rate": 5.2674897119341575e-06,
+      "loss": 0.2397,
+      "num_input_tokens_seen": 4243798,
+      "step": 185,
+      "train_runtime": 559.4718,
+      "train_tokens_per_second": 7585.365
+    },
+    {
+      "epoch": 1.5010101010101011,
+      "grad_norm": 2.1618330478668213,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.254,
+      "num_input_tokens_seen": 4265174,
+      "step": 186,
+      "train_runtime": 561.4461,
+      "train_tokens_per_second": 7596.765
+    },
+    {
+      "epoch": 1.509090909090909,
+      "grad_norm": 1.9395222663879395,
+      "learning_rate": 5.102880658436214e-06,
+      "loss": 0.2269,
+      "num_input_tokens_seen": 4286374,
+      "step": 187,
+      "train_runtime": 563.42,
+      "train_tokens_per_second": 7607.777
+    },
+    {
+      "epoch": 1.5171717171717172,
+      "grad_norm": 1.9343959093093872,
+      "learning_rate": 5.020576131687243e-06,
+      "loss": 0.2284,
+      "num_input_tokens_seen": 4314534,
+      "step": 188,
+      "train_runtime": 565.9536,
+      "train_tokens_per_second": 7623.477
+    },
+    {
+      "epoch": 1.5252525252525253,
+      "grad_norm": 2.2199180126190186,
+      "learning_rate": 4.938271604938272e-06,
+      "loss": 0.2729,
+      "num_input_tokens_seen": 4334726,
+      "step": 189,
+      "train_runtime": 567.8322,
+      "train_tokens_per_second": 7633.815
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 2.422062397003174,
+      "learning_rate": 4.855967078189301e-06,
+      "loss": 0.2577,
+      "num_input_tokens_seen": 4357238,
+      "step": 190,
+      "train_runtime": 569.9123,
+      "train_tokens_per_second": 7645.453
+    },
+    {
+      "epoch": 1.5414141414141413,
+      "grad_norm": 2.182530641555786,
+      "learning_rate": 4.773662551440329e-06,
+      "loss": 0.2506,
+      "num_input_tokens_seen": 4380310,
+      "step": 191,
+      "train_runtime": 572.0127,
+      "train_tokens_per_second": 7657.714
+    },
+    {
+      "epoch": 1.5494949494949495,
+      "grad_norm": 1.9306634664535522,
+      "learning_rate": 4.691358024691358e-06,
+      "loss": 0.2492,
+      "num_input_tokens_seen": 4402598,
+      "step": 192,
+      "train_runtime": 574.0447,
+      "train_tokens_per_second": 7669.434
+    },
+    {
+      "epoch": 1.5575757575757576,
+      "grad_norm": 2.064788818359375,
+      "learning_rate": 4.6090534979423875e-06,
+      "loss": 0.2417,
+      "num_input_tokens_seen": 4426854,
+      "step": 193,
+      "train_runtime": 576.2391,
+      "train_tokens_per_second": 7682.321
+    },
+    {
+      "epoch": 1.5656565656565657,
+      "grad_norm": 2.1123790740966797,
+      "learning_rate": 4.526748971193416e-06,
+      "loss": 0.2702,
+      "num_input_tokens_seen": 4452422,
+      "step": 194,
+      "train_runtime": 578.5618,
+      "train_tokens_per_second": 7695.673
+    },
+    {
+      "epoch": 1.5737373737373739,
+      "grad_norm": 2.039179563522339,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.2523,
+      "num_input_tokens_seen": 4479574,
+      "step": 195,
+      "train_runtime": 581.0195,
+      "train_tokens_per_second": 7709.852
+    },
+    {
+      "epoch": 1.5818181818181818,
+      "grad_norm": 2.136936664581299,
+      "learning_rate": 4.362139917695473e-06,
+      "loss": 0.2797,
+      "num_input_tokens_seen": 4499862,
+      "step": 196,
+      "train_runtime": 582.8938,
+      "train_tokens_per_second": 7719.867
+    },
+    {
+      "epoch": 1.58989898989899,
+      "grad_norm": 2.0336132049560547,
+      "learning_rate": 4.2798353909465025e-06,
+      "loss": 0.2496,
+      "num_input_tokens_seen": 4522614,
+      "step": 197,
+      "train_runtime": 584.992,
+      "train_tokens_per_second": 7731.07
+    },
+    {
+      "epoch": 1.5979797979797978,
+      "grad_norm": 1.997153639793396,
+      "learning_rate": 4.197530864197531e-06,
+      "loss": 0.2318,
+      "num_input_tokens_seen": 4544022,
+      "step": 198,
+      "train_runtime": 586.9586,
+      "train_tokens_per_second": 7741.64
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 1.994828224182129,
+      "learning_rate": 4.11522633744856e-06,
+      "loss": 0.2436,
+      "num_input_tokens_seen": 4566198,
+      "step": 199,
+      "train_runtime": 588.9959,
+      "train_tokens_per_second": 7752.512
+    },
+    {
+      "epoch": 1.614141414141414,
+      "grad_norm": 2.174928665161133,
+      "learning_rate": 4.032921810699589e-06,
+      "loss": 0.2769,
+      "num_input_tokens_seen": 4588070,
+      "step": 200,
+      "train_runtime": 590.9965,
+      "train_tokens_per_second": 7763.277
+    },
+    {
+      "epoch": 1.614141414141414,
+      "eval_loss": 0.2970900535583496,
+      "eval_runtime": 7.1151,
+      "eval_samples_per_second": 123.539,
+      "eval_steps_per_second": 7.73,
+      "num_input_tokens_seen": 4588070,
+      "step": 200
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 2.186704158782959,
+      "learning_rate": 3.9506172839506175e-06,
+      "loss": 0.2691,
+      "num_input_tokens_seen": 4612646,
+      "step": 201,
+      "train_runtime": 600.3639,
+      "train_tokens_per_second": 7683.084
+    },
+    {
+      "epoch": 1.6303030303030304,
+      "grad_norm": 2.1499741077423096,
+      "learning_rate": 3.868312757201647e-06,
+      "loss": 0.2562,
+      "num_input_tokens_seen": 4633446,
+      "step": 202,
+      "train_runtime": 602.3025,
+      "train_tokens_per_second": 7692.889
+    },
+    {
+      "epoch": 1.6383838383838385,
+      "grad_norm": 2.155334711074829,
+      "learning_rate": 3.786008230452675e-06,
+      "loss": 0.2389,
+      "num_input_tokens_seen": 4656278,
+      "step": 203,
+      "train_runtime": 604.4073,
+      "train_tokens_per_second": 7703.875
+    },
+    {
+      "epoch": 1.6464646464646466,
+      "grad_norm": 2.1553854942321777,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.2447,
+      "num_input_tokens_seen": 4678006,
+      "step": 204,
+      "train_runtime": 606.4147,
+      "train_tokens_per_second": 7714.203
+    },
+    {
+      "epoch": 1.6545454545454545,
+      "grad_norm": 2.211529493331909,
+      "learning_rate": 3.621399176954733e-06,
+      "loss": 0.2673,
+      "num_input_tokens_seen": 4701206,
+      "step": 205,
+      "train_runtime": 608.5378,
+      "train_tokens_per_second": 7725.414
+    },
+    {
+      "epoch": 1.6626262626262627,
+      "grad_norm": 1.99440336227417,
+      "learning_rate": 3.5390946502057617e-06,
+      "loss": 0.2631,
+      "num_input_tokens_seen": 4724646,
+      "step": 206,
+      "train_runtime": 610.695,
+      "train_tokens_per_second": 7736.507
+    },
+    {
+      "epoch": 1.6707070707070706,
+      "grad_norm": 2.078808307647705,
+      "learning_rate": 3.4567901234567904e-06,
+      "loss": 0.2474,
+      "num_input_tokens_seen": 4748998,
+      "step": 207,
+      "train_runtime": 612.9302,
+      "train_tokens_per_second": 7748.025
+    },
+    {
+      "epoch": 1.6787878787878787,
+      "grad_norm": 2.2216312885284424,
+      "learning_rate": 3.3744855967078196e-06,
+      "loss": 0.2523,
+      "num_input_tokens_seen": 4768294,
+      "step": 208,
+      "train_runtime": 614.7311,
+      "train_tokens_per_second": 7756.715
+    },
+    {
+      "epoch": 1.6868686868686869,
+      "grad_norm": 2.1256401538848877,
+      "learning_rate": 3.292181069958848e-06,
+      "loss": 0.2799,
+      "num_input_tokens_seen": 4792550,
+      "step": 209,
+      "train_runtime": 616.9493,
+      "train_tokens_per_second": 7768.143
+    },
+    {
+      "epoch": 1.694949494949495,
+      "grad_norm": 2.0942769050598145,
+      "learning_rate": 3.2098765432098767e-06,
+      "loss": 0.259,
+      "num_input_tokens_seen": 4816006,
+      "step": 210,
+      "train_runtime": 619.088,
+      "train_tokens_per_second": 7779.194
+    },
+    {
+      "epoch": 1.7030303030303031,
+      "grad_norm": 1.9659632444381714,
+      "learning_rate": 3.127572016460906e-06,
+      "loss": 0.271,
+      "num_input_tokens_seen": 4839222,
+      "step": 211,
+      "train_runtime": 639.404,
+      "train_tokens_per_second": 7568.332
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 1.9326211214065552,
+      "learning_rate": 3.0452674897119346e-06,
+      "loss": 0.2437,
+      "num_input_tokens_seen": 4862822,
+      "step": 212,
+      "train_runtime": 641.5123,
+      "train_tokens_per_second": 7580.247
+    },
+    {
+      "epoch": 1.7191919191919192,
+      "grad_norm": 2.3900415897369385,
+      "learning_rate": 2.962962962962963e-06,
+      "loss": 0.3026,
+      "num_input_tokens_seen": 4884582,
+      "step": 213,
+      "train_runtime": 643.5091,
+      "train_tokens_per_second": 7590.541
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 2.0574638843536377,
+      "learning_rate": 2.880658436213992e-06,
+      "loss": 0.2525,
+      "num_input_tokens_seen": 4909174,
+      "step": 214,
+      "train_runtime": 645.7213,
+      "train_tokens_per_second": 7602.62
+    },
+    {
+      "epoch": 1.7353535353535352,
+      "grad_norm": 2.039299726486206,
+      "learning_rate": 2.798353909465021e-06,
+      "loss": 0.2637,
+      "num_input_tokens_seen": 4933798,
+      "step": 215,
+      "train_runtime": 647.9549,
+      "train_tokens_per_second": 7614.416
+    },
+    {
+      "epoch": 1.7434343434343433,
+      "grad_norm": 2.1611974239349365,
+      "learning_rate": 2.7160493827160496e-06,
+      "loss": 0.2601,
+      "num_input_tokens_seen": 4952742,
+      "step": 216,
+      "train_runtime": 649.7285,
+      "train_tokens_per_second": 7622.787
+    },
+    {
+      "epoch": 1.7515151515151515,
+      "grad_norm": 1.8820812702178955,
+      "learning_rate": 2.6337448559670788e-06,
+      "loss": 0.2407,
+      "num_input_tokens_seen": 4976246,
+      "step": 217,
+      "train_runtime": 651.852,
+      "train_tokens_per_second": 7634.012
+    },
+    {
+      "epoch": 1.7595959595959596,
+      "grad_norm": 2.016808271408081,
+      "learning_rate": 2.551440329218107e-06,
+      "loss": 0.2237,
+      "num_input_tokens_seen": 4995798,
+      "step": 218,
+      "train_runtime": 653.6727,
+      "train_tokens_per_second": 7642.66
+    },
+    {
+      "epoch": 1.7676767676767677,
+      "grad_norm": 2.027350902557373,
+      "learning_rate": 2.469135802469136e-06,
+      "loss": 0.2408,
+      "num_input_tokens_seen": 5018838,
+      "step": 219,
+      "train_runtime": 655.7795,
+      "train_tokens_per_second": 7653.241
+    },
+    {
+      "epoch": 1.7757575757575759,
+      "grad_norm": 2.164444923400879,
+      "learning_rate": 2.3868312757201646e-06,
+      "loss": 0.2154,
+      "num_input_tokens_seen": 5041782,
+      "step": 220,
+      "train_runtime": 657.8444,
+      "train_tokens_per_second": 7664.094
+    },
+    {
+      "epoch": 1.783838383838384,
+      "grad_norm": 2.082343339920044,
+      "learning_rate": 2.3045267489711937e-06,
+      "loss": 0.2569,
+      "num_input_tokens_seen": 5063478,
+      "step": 221,
+      "train_runtime": 659.8611,
+      "train_tokens_per_second": 7673.552
+    },
+    {
+      "epoch": 1.791919191919192,
+      "grad_norm": 2.043057680130005,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.2536,
+      "num_input_tokens_seen": 5085526,
+      "step": 222,
+      "train_runtime": 661.8702,
+      "train_tokens_per_second": 7683.57
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.9899940490722656,
+      "learning_rate": 2.1399176954732512e-06,
+      "loss": 0.2755,
+      "num_input_tokens_seen": 5109430,
+      "step": 223,
+      "train_runtime": 664.0648,
+      "train_tokens_per_second": 7694.173
+    },
+    {
+      "epoch": 1.808080808080808,
+      "grad_norm": 2.1286203861236572,
+      "learning_rate": 2.05761316872428e-06,
+      "loss": 0.2391,
+      "num_input_tokens_seen": 5132182,
+      "step": 224,
+      "train_runtime": 666.1433,
+      "train_tokens_per_second": 7704.321
+    },
+    {
+      "epoch": 1.816161616161616,
+      "grad_norm": 1.9586842060089111,
+      "learning_rate": 1.9753086419753087e-06,
+      "loss": 0.2511,
+      "num_input_tokens_seen": 5153622,
+      "step": 225,
+      "train_runtime": 668.1036,
+      "train_tokens_per_second": 7713.807
+    },
+    {
+      "epoch": 1.816161616161616,
+      "eval_loss": 0.29719212651252747,
+      "eval_runtime": 7.0733,
+      "eval_samples_per_second": 124.27,
+      "eval_steps_per_second": 7.776,
+      "num_input_tokens_seen": 5153622,
+      "step": 225
+    },
+    {
+      "epoch": 1.8242424242424242,
+      "grad_norm": 2.056194543838501,
+      "learning_rate": 1.8930041152263375e-06,
+      "loss": 0.239,
+      "num_input_tokens_seen": 5178470,
+      "step": 226,
+      "train_runtime": 677.4315,
+      "train_tokens_per_second": 7644.27
+    },
+    {
+      "epoch": 1.8323232323232324,
+      "grad_norm": 2.03861403465271,
+      "learning_rate": 1.8106995884773665e-06,
+      "loss": 0.2453,
+      "num_input_tokens_seen": 5199062,
+      "step": 227,
+      "train_runtime": 679.3306,
+      "train_tokens_per_second": 7653.214
+    },
+    {
+      "epoch": 1.8404040404040405,
+      "grad_norm": 2.454902410507202,
+      "learning_rate": 1.7283950617283952e-06,
+      "loss": 0.2815,
+      "num_input_tokens_seen": 5218134,
+      "step": 228,
+      "train_runtime": 681.1112,
+      "train_tokens_per_second": 7661.207
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 2.0664114952087402,
+      "learning_rate": 1.646090534979424e-06,
+      "loss": 0.2481,
+      "num_input_tokens_seen": 5242054,
+      "step": 229,
+      "train_runtime": 683.2902,
+      "train_tokens_per_second": 7671.783
+    },
+    {
+      "epoch": 1.8565656565656565,
+      "grad_norm": 2.1586387157440186,
+      "learning_rate": 1.563786008230453e-06,
+      "loss": 0.2255,
+      "num_input_tokens_seen": 5264518,
+      "step": 230,
+      "train_runtime": 685.3446,
+      "train_tokens_per_second": 7681.564
+    },
+    {
+      "epoch": 1.8646464646464647,
+      "grad_norm": 2.2115135192871094,
+      "learning_rate": 1.4814814814814815e-06,
+      "loss": 0.2941,
+      "num_input_tokens_seen": 5284374,
+      "step": 231,
+      "train_runtime": 687.1947,
+      "train_tokens_per_second": 7689.777
+    },
+    {
+      "epoch": 1.8727272727272726,
+      "grad_norm": 1.9213886260986328,
+      "learning_rate": 1.3991769547325104e-06,
+      "loss": 0.2309,
+      "num_input_tokens_seen": 5303622,
+      "step": 232,
+      "train_runtime": 688.9977,
+      "train_tokens_per_second": 7697.591
+    },
+    {
+      "epoch": 1.8808080808080807,
+      "grad_norm": 1.919615387916565,
+      "learning_rate": 1.3168724279835394e-06,
+      "loss": 0.2332,
+      "num_input_tokens_seen": 5329718,
+      "step": 233,
+      "train_runtime": 691.3575,
+      "train_tokens_per_second": 7709.062
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 1.9546780586242676,
+      "learning_rate": 1.234567901234568e-06,
+      "loss": 0.2468,
+      "num_input_tokens_seen": 5349718,
+      "step": 234,
+      "train_runtime": 693.227,
+      "train_tokens_per_second": 7717.123
+    },
+    {
+      "epoch": 1.896969696969697,
+      "grad_norm": 2.1279263496398926,
+      "learning_rate": 1.1522633744855969e-06,
+      "loss": 0.2711,
+      "num_input_tokens_seen": 5369638,
+      "step": 235,
+      "train_runtime": 695.0864,
+      "train_tokens_per_second": 7725.137
+    },
+    {
+      "epoch": 1.905050505050505,
+      "grad_norm": 2.0568149089813232,
+      "learning_rate": 1.0699588477366256e-06,
+      "loss": 0.262,
+      "num_input_tokens_seen": 5392726,
+      "step": 236,
+      "train_runtime": 697.1851,
+      "train_tokens_per_second": 7734.999
+    },
+    {
+      "epoch": 1.9131313131313132,
+      "grad_norm": 2.307243824005127,
+      "learning_rate": 9.876543209876544e-07,
+      "loss": 0.2773,
+      "num_input_tokens_seen": 5412470,
+      "step": 237,
+      "train_runtime": 699.0602,
+      "train_tokens_per_second": 7742.495
+    },
+    {
+      "epoch": 1.9212121212121214,
+      "grad_norm": 2.0928726196289062,
+      "learning_rate": 9.053497942386832e-07,
+      "loss": 0.2715,
+      "num_input_tokens_seen": 5437894,
+      "step": 238,
+      "train_runtime": 701.3562,
+      "train_tokens_per_second": 7753.398
+    },
+    {
+      "epoch": 1.9292929292929293,
+      "grad_norm": 2.1170663833618164,
+      "learning_rate": 8.23045267489712e-07,
+      "loss": 0.2814,
+      "num_input_tokens_seen": 5461686,
+      "step": 239,
+      "train_runtime": 703.5235,
+      "train_tokens_per_second": 7763.331
+    },
+    {
+      "epoch": 1.9373737373737374,
+      "grad_norm": 1.9261893033981323,
+      "learning_rate": 7.407407407407407e-07,
+      "loss": 0.2426,
+      "num_input_tokens_seen": 5486054,
+      "step": 240,
+      "train_runtime": 705.7339,
+      "train_tokens_per_second": 7773.545
+    },
+    {
+      "epoch": 1.9454545454545453,
+      "grad_norm": 2.053776741027832,
+      "learning_rate": 6.584362139917697e-07,
+      "loss": 0.2712,
+      "num_input_tokens_seen": 5509142,
+      "step": 241,
+      "train_runtime": 726.1192,
+      "train_tokens_per_second": 7587.104
+    },
+    {
+      "epoch": 1.9535353535353535,
+      "grad_norm": 1.9918407201766968,
+      "learning_rate": 5.761316872427984e-07,
+      "loss": 0.2019,
+      "num_input_tokens_seen": 5528598,
+      "step": 242,
+      "train_runtime": 727.9519,
+      "train_tokens_per_second": 7594.73
+    },
+    {
+      "epoch": 1.9616161616161616,
+      "grad_norm": 1.8533083200454712,
+      "learning_rate": 4.938271604938272e-07,
+      "loss": 0.2358,
+      "num_input_tokens_seen": 5551926,
+      "step": 243,
+      "train_runtime": 730.0608,
+      "train_tokens_per_second": 7604.744
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 1.9955955743789673,
+      "learning_rate": 4.11522633744856e-07,
+      "loss": 0.2237,
+      "num_input_tokens_seen": 5574326,
+      "step": 244,
+      "train_runtime": 732.1133,
+      "train_tokens_per_second": 7614.021
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 2.0239830017089844,
+      "learning_rate": 3.2921810699588484e-07,
+      "loss": 0.2742,
+      "num_input_tokens_seen": 5598310,
+      "step": 245,
+      "train_runtime": 734.2562,
+      "train_tokens_per_second": 7624.464
+    },
+    {
+      "epoch": 1.985858585858586,
+      "grad_norm": 2.1352379322052,
+      "learning_rate": 2.469135802469136e-07,
+      "loss": 0.2701,
+      "num_input_tokens_seen": 5620534,
+      "step": 246,
+      "train_runtime": 736.283,
+      "train_tokens_per_second": 7633.66
+    },
+    {
+      "epoch": 1.993939393939394,
+      "grad_norm": 2.292893171310425,
+      "learning_rate": 1.6460905349794242e-07,
+      "loss": 0.2626,
+      "num_input_tokens_seen": 5640982,
+      "step": 247,
+      "train_runtime": 738.169,
+      "train_tokens_per_second": 7641.857
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.7160730361938477,
+      "learning_rate": 8.230452674897121e-08,
+      "loss": 0.2577,
+      "num_input_tokens_seen": 5653442,
+      "step": 248,
+      "train_runtime": 739.3962,
+      "train_tokens_per_second": 7646.025
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 248,
+  "num_input_tokens_seen": 5653442,
+  "num_train_epochs": 2,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.412213509169152e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff