Instructions to use pvrancx/lora-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pvrancx/lora-test with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-3-270m-it")
model = PeftModel.from_pretrained(base_model, "pvrancx/lora-test")

Transformers

How to use pvrancx/lora-test with Transformers:

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

pipe = pipeline("text-generation", model="pvrancx/lora-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pvrancx/lora-test", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pvrancx/lora-test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pvrancx/lora-test

SGLang

How to use pvrancx/lora-test 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 "pvrancx/lora-test" \
    --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": "pvrancx/lora-test",
		"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 "pvrancx/lora-test" \
        --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": "pvrancx/lora-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use pvrancx/lora-test with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for pvrancx/lora-test to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for pvrancx/lora-test to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pvrancx/lora-test to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="pvrancx/lora-test",
    max_seq_length=2048,
)

Docker Model Runner
How to use pvrancx/lora-test with Docker Model Runner:
```
docker model run hf.co/pvrancx/lora-test
```

lora-test / trainer_state.json

pvrancx

Upload 14 files

2dc8576 verified 4 months ago

Raw

History Blame Contribute Delete

94.9 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.19515368352577656,
	"eval_steps": 500,
	"global_step": 600,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.0003252561392096276,
	"grad_norm": 7.644000053405762,
	"learning_rate": 5e-05,
	"loss": 3.7348,
	"step": 1
	},
	{
	"epoch": 0.0006505122784192552,
	"grad_norm": 6.572476387023926,
	"learning_rate": 5e-05,
	"loss": 3.5202,
	"step": 2
	},
	{
	"epoch": 0.0009757684176288828,
	"grad_norm": 5.915395736694336,
	"learning_rate": 5e-05,
	"loss": 3.2423,
	"step": 3
	},
	{
	"epoch": 0.0013010245568385104,
	"grad_norm": 5.39382266998291,
	"learning_rate": 5e-05,
	"loss": 3.2308,
	"step": 4
	},
	{
	"epoch": 0.0016262806960481379,
	"grad_norm": 5.474543571472168,
	"learning_rate": 5e-05,
	"loss": 3.3753,
	"step": 5
	},
	{
	"epoch": 0.0019515368352577655,
	"grad_norm": 5.402736663818359,
	"learning_rate": 5e-05,
	"loss": 3.3042,
	"step": 6
	},
	{
	"epoch": 0.002276792974467393,
	"grad_norm": 5.727195739746094,
	"learning_rate": 5e-05,
	"loss": 3.2722,
	"step": 7
	},
	{
	"epoch": 0.002602049113677021,
	"grad_norm": 5.997256755828857,
	"learning_rate": 5e-05,
	"loss": 3.2708,
	"step": 8
	},
	{
	"epoch": 0.002927305252886648,
	"grad_norm": 8.144789695739746,
	"learning_rate": 5e-05,
	"loss": 3.4531,
	"step": 9
	},
	{
	"epoch": 0.0032525613920962758,
	"grad_norm": 11.264220237731934,
	"learning_rate": 5e-05,
	"loss": 3.3755,
	"step": 10
	},
	{
	"epoch": 0.0035778175313059034,
	"grad_norm": 10.535292625427246,
	"learning_rate": 5e-05,
	"loss": 3.5809,
	"step": 11
	},
	{
	"epoch": 0.003903073670515531,
	"grad_norm": 8.04301929473877,
	"learning_rate": 5e-05,
	"loss": 3.3787,
	"step": 12
	},
	{
	"epoch": 0.004228329809725159,
	"grad_norm": 9.441449165344238,
	"learning_rate": 5e-05,
	"loss": 3.4919,
	"step": 13
	},
	{
	"epoch": 0.004553585948934786,
	"grad_norm": 9.322367668151855,
	"learning_rate": 5e-05,
	"loss": 3.6405,
	"step": 14
	},
	{
	"epoch": 0.004878842088144414,
	"grad_norm": 10.059698104858398,
	"learning_rate": 5e-05,
	"loss": 3.425,
	"step": 15
	},
	{
	"epoch": 0.005204098227354042,
	"grad_norm": 11.285538673400879,
	"learning_rate": 5e-05,
	"loss": 3.6643,
	"step": 16
	},
	{
	"epoch": 0.0055293543665636685,
	"grad_norm": 10.433178901672363,
	"learning_rate": 5e-05,
	"loss": 3.4485,
	"step": 17
	},
	{
	"epoch": 0.005854610505773296,
	"grad_norm": 11.724845886230469,
	"learning_rate": 5e-05,
	"loss": 3.8379,
	"step": 18
	},
	{
	"epoch": 0.006179866644982924,
	"grad_norm": 11.558403968811035,
	"learning_rate": 5e-05,
	"loss": 3.8067,
	"step": 19
	},
	{
	"epoch": 0.0065051227841925515,
	"grad_norm": 9.274937629699707,
	"learning_rate": 5e-05,
	"loss": 3.5213,
	"step": 20
	},
	{
	"epoch": 0.006830378923402179,
	"grad_norm": 11.487302780151367,
	"learning_rate": 5e-05,
	"loss": 3.8464,
	"step": 21
	},
	{
	"epoch": 0.007155635062611807,
	"grad_norm": 11.910959243774414,
	"learning_rate": 5e-05,
	"loss": 3.7159,
	"step": 22
	},
	{
	"epoch": 0.0074808912018214345,
	"grad_norm": 10.441876411437988,
	"learning_rate": 5e-05,
	"loss": 4.3052,
	"step": 23
	},
	{
	"epoch": 0.007806147341031062,
	"grad_norm": 11.492648124694824,
	"learning_rate": 5e-05,
	"loss": 4.0298,
	"step": 24
	},
	{
	"epoch": 0.00813140348024069,
	"grad_norm": 11.218420028686523,
	"learning_rate": 5e-05,
	"loss": 3.9014,
	"step": 25
	},
	{
	"epoch": 0.008456659619450317,
	"grad_norm": 9.615971565246582,
	"learning_rate": 5e-05,
	"loss": 3.8972,
	"step": 26
	},
	{
	"epoch": 0.008781915758659945,
	"grad_norm": 9.325116157531738,
	"learning_rate": 5e-05,
	"loss": 4.0339,
	"step": 27
	},
	{
	"epoch": 0.009107171897869573,
	"grad_norm": 10.537034034729004,
	"learning_rate": 5e-05,
	"loss": 4.3475,
	"step": 28
	},
	{
	"epoch": 0.0094324280370792,
	"grad_norm": 9.163812637329102,
	"learning_rate": 5e-05,
	"loss": 4.4702,
	"step": 29
	},
	{
	"epoch": 0.009757684176288828,
	"grad_norm": 8.232535362243652,
	"learning_rate": 5e-05,
	"loss": 4.5234,
	"step": 30
	},
	{
	"epoch": 0.010082940315498456,
	"grad_norm": 7.85621976852417,
	"learning_rate": 5e-05,
	"loss": 4.665,
	"step": 31
	},
	{
	"epoch": 0.010408196454708083,
	"grad_norm": 7.693171501159668,
	"learning_rate": 5e-05,
	"loss": 4.5524,
	"step": 32
	},
	{
	"epoch": 0.01073345259391771,
	"grad_norm": 6.418099403381348,
	"learning_rate": 5e-05,
	"loss": 4.3471,
	"step": 33
	},
	{
	"epoch": 0.011058708733127337,
	"grad_norm": 9.231449127197266,
	"learning_rate": 5e-05,
	"loss": 4.5491,
	"step": 34
	},
	{
	"epoch": 0.011383964872336965,
	"grad_norm": 8.351770401000977,
	"learning_rate": 5e-05,
	"loss": 4.6851,
	"step": 35
	},
	{
	"epoch": 0.011709221011546592,
	"grad_norm": 8.412186622619629,
	"learning_rate": 5e-05,
	"loss": 4.4453,
	"step": 36
	},
	{
	"epoch": 0.01203447715075622,
	"grad_norm": 7.4988932609558105,
	"learning_rate": 5e-05,
	"loss": 4.2595,
	"step": 37
	},
	{
	"epoch": 0.012359733289965848,
	"grad_norm": 6.0955424308776855,
	"learning_rate": 5e-05,
	"loss": 4.1402,
	"step": 38
	},
	{
	"epoch": 0.012684989429175475,
	"grad_norm": 5.853550434112549,
	"learning_rate": 5e-05,
	"loss": 4.2133,
	"step": 39
	},
	{
	"epoch": 0.013010245568385103,
	"grad_norm": 6.071702480316162,
	"learning_rate": 5e-05,
	"loss": 3.9406,
	"step": 40
	},
	{
	"epoch": 0.01333550170759473,
	"grad_norm": 5.181666374206543,
	"learning_rate": 5e-05,
	"loss": 3.9559,
	"step": 41
	},
	{
	"epoch": 0.013660757846804358,
	"grad_norm": 5.067506313323975,
	"learning_rate": 5e-05,
	"loss": 4.0526,
	"step": 42
	},
	{
	"epoch": 0.013986013986013986,
	"grad_norm": 4.593716621398926,
	"learning_rate": 5e-05,
	"loss": 4.0814,
	"step": 43
	},
	{
	"epoch": 0.014311270125223614,
	"grad_norm": 5.379826545715332,
	"learning_rate": 5e-05,
	"loss": 4.13,
	"step": 44
	},
	{
	"epoch": 0.014636526264433241,
	"grad_norm": 6.113279819488525,
	"learning_rate": 5e-05,
	"loss": 4.0842,
	"step": 45
	},
	{
	"epoch": 0.014961782403642869,
	"grad_norm": 4.885502815246582,
	"learning_rate": 5e-05,
	"loss": 4.147,
	"step": 46
	},
	{
	"epoch": 0.015287038542852497,
	"grad_norm": 5.065276622772217,
	"learning_rate": 5e-05,
	"loss": 4.0597,
	"step": 47
	},
	{
	"epoch": 0.015612294682062124,
	"grad_norm": 5.306569576263428,
	"learning_rate": 5e-05,
	"loss": 4.4288,
	"step": 48
	},
	{
	"epoch": 0.01593755082127175,
	"grad_norm": 6.738716125488281,
	"learning_rate": 5e-05,
	"loss": 4.2153,
	"step": 49
	},
	{
	"epoch": 0.01626280696048138,
	"grad_norm": 7.264622211456299,
	"learning_rate": 5e-05,
	"loss": 4.3567,
	"step": 50
	},
	{
	"epoch": 0.016588063099691006,
	"grad_norm": 4.799393177032471,
	"learning_rate": 5e-05,
	"loss": 4.1491,
	"step": 51
	},
	{
	"epoch": 0.016913319238900635,
	"grad_norm": 4.5021071434021,
	"learning_rate": 5e-05,
	"loss": 4.0725,
	"step": 52
	},
	{
	"epoch": 0.01723857537811026,
	"grad_norm": 5.524833679199219,
	"learning_rate": 5e-05,
	"loss": 4.405,
	"step": 53
	},
	{
	"epoch": 0.01756383151731989,
	"grad_norm": 4.327210426330566,
	"learning_rate": 5e-05,
	"loss": 4.198,
	"step": 54
	},
	{
	"epoch": 0.017889087656529516,
	"grad_norm": 4.141977787017822,
	"learning_rate": 5e-05,
	"loss": 4.0445,
	"step": 55
	},
	{
	"epoch": 0.018214343795739146,
	"grad_norm": 4.746036529541016,
	"learning_rate": 5e-05,
	"loss": 4.5174,
	"step": 56
	},
	{
	"epoch": 0.01853959993494877,
	"grad_norm": 5.5715837478637695,
	"learning_rate": 5e-05,
	"loss": 4.2292,
	"step": 57
	},
	{
	"epoch": 0.0188648560741584,
	"grad_norm": 5.887129306793213,
	"learning_rate": 5e-05,
	"loss": 4.0795,
	"step": 58
	},
	{
	"epoch": 0.019190112213368027,
	"grad_norm": 4.8050150871276855,
	"learning_rate": 5e-05,
	"loss": 4.1816,
	"step": 59
	},
	{
	"epoch": 0.019515368352577656,
	"grad_norm": 4.179840564727783,
	"learning_rate": 5e-05,
	"loss": 4.337,
	"step": 60
	},
	{
	"epoch": 0.019840624491787282,
	"grad_norm": 5.042575359344482,
	"learning_rate": 5e-05,
	"loss": 4.1466,
	"step": 61
	},
	{
	"epoch": 0.02016588063099691,
	"grad_norm": 4.339786052703857,
	"learning_rate": 5e-05,
	"loss": 3.7189,
	"step": 62
	},
	{
	"epoch": 0.020491136770206538,
	"grad_norm": 8.27956771850586,
	"learning_rate": 5e-05,
	"loss": 4.1767,
	"step": 63
	},
	{
	"epoch": 0.020816392909416167,
	"grad_norm": 6.273040294647217,
	"learning_rate": 5e-05,
	"loss": 4.363,
	"step": 64
	},
	{
	"epoch": 0.021141649048625793,
	"grad_norm": 7.342176914215088,
	"learning_rate": 5e-05,
	"loss": 4.3939,
	"step": 65
	},
	{
	"epoch": 0.02146690518783542,
	"grad_norm": 6.060370445251465,
	"learning_rate": 5e-05,
	"loss": 4.1033,
	"step": 66
	},
	{
	"epoch": 0.021792161327045048,
	"grad_norm": 6.683494567871094,
	"learning_rate": 5e-05,
	"loss": 3.9883,
	"step": 67
	},
	{
	"epoch": 0.022117417466254674,
	"grad_norm": 6.418432712554932,
	"learning_rate": 5e-05,
	"loss": 4.1472,
	"step": 68
	},
	{
	"epoch": 0.022442673605464303,
	"grad_norm": 6.342174053192139,
	"learning_rate": 5e-05,
	"loss": 4.414,
	"step": 69
	},
	{
	"epoch": 0.02276792974467393,
	"grad_norm": 10.055042266845703,
	"learning_rate": 5e-05,
	"loss": 4.1925,
	"step": 70
	},
	{
	"epoch": 0.02309318588388356,
	"grad_norm": 6.6624932289123535,
	"learning_rate": 5e-05,
	"loss": 4.1111,
	"step": 71
	},
	{
	"epoch": 0.023418442023093185,
	"grad_norm": 8.38736343383789,
	"learning_rate": 5e-05,
	"loss": 4.5028,
	"step": 72
	},
	{
	"epoch": 0.023743698162302814,
	"grad_norm": 8.479351997375488,
	"learning_rate": 5e-05,
	"loss": 4.2832,
	"step": 73
	},
	{
	"epoch": 0.02406895430151244,
	"grad_norm": 8.613444328308105,
	"learning_rate": 5e-05,
	"loss": 4.5189,
	"step": 74
	},
	{
	"epoch": 0.02439421044072207,
	"grad_norm": 6.932406425476074,
	"learning_rate": 5e-05,
	"loss": 4.1228,
	"step": 75
	},
	{
	"epoch": 0.024719466579931695,
	"grad_norm": 5.989908695220947,
	"learning_rate": 5e-05,
	"loss": 4.0289,
	"step": 76
	},
	{
	"epoch": 0.025044722719141325,
	"grad_norm": 5.118892192840576,
	"learning_rate": 5e-05,
	"loss": 3.8781,
	"step": 77
	},
	{
	"epoch": 0.02536997885835095,
	"grad_norm": 5.232855796813965,
	"learning_rate": 5e-05,
	"loss": 4.2731,
	"step": 78
	},
	{
	"epoch": 0.02569523499756058,
	"grad_norm": 4.9437103271484375,
	"learning_rate": 5e-05,
	"loss": 3.1985,
	"step": 79
	},
	{
	"epoch": 0.026020491136770206,
	"grad_norm": 7.929747581481934,
	"learning_rate": 5e-05,
	"loss": 4.1925,
	"step": 80
	},
	{
	"epoch": 0.026345747275979835,
	"grad_norm": 9.323763847351074,
	"learning_rate": 5e-05,
	"loss": 4.2925,
	"step": 81
	},
	{
	"epoch": 0.02667100341518946,
	"grad_norm": 6.18411111831665,
	"learning_rate": 5e-05,
	"loss": 4.0956,
	"step": 82
	},
	{
	"epoch": 0.02699625955439909,
	"grad_norm": 4.424221038818359,
	"learning_rate": 5e-05,
	"loss": 4.1803,
	"step": 83
	},
	{
	"epoch": 0.027321515693608717,
	"grad_norm": 6.044656276702881,
	"learning_rate": 5e-05,
	"loss": 4.0551,
	"step": 84
	},
	{
	"epoch": 0.027646771832818346,
	"grad_norm": 9.380243301391602,
	"learning_rate": 5e-05,
	"loss": 4.2753,
	"step": 85
	},
	{
	"epoch": 0.027972027972027972,
	"grad_norm": 10.203062057495117,
	"learning_rate": 5e-05,
	"loss": 4.5481,
	"step": 86
	},
	{
	"epoch": 0.028297284111237598,
	"grad_norm": 12.21309757232666,
	"learning_rate": 5e-05,
	"loss": 4.2921,
	"step": 87
	},
	{
	"epoch": 0.028622540250447227,
	"grad_norm": 7.666494369506836,
	"learning_rate": 5e-05,
	"loss": 4.2344,
	"step": 88
	},
	{
	"epoch": 0.028947796389656853,
	"grad_norm": 5.388767719268799,
	"learning_rate": 5e-05,
	"loss": 4.3914,
	"step": 89
	},
	{
	"epoch": 0.029273052528866483,
	"grad_norm": 7.598433971405029,
	"learning_rate": 5e-05,
	"loss": 4.242,
	"step": 90
	},
	{
	"epoch": 0.02959830866807611,
	"grad_norm": 11.387866020202637,
	"learning_rate": 5e-05,
	"loss": 4.0014,
	"step": 91
	},
	{
	"epoch": 0.029923564807285738,
	"grad_norm": 10.232786178588867,
	"learning_rate": 5e-05,
	"loss": 4.025,
	"step": 92
	},
	{
	"epoch": 0.030248820946495364,
	"grad_norm": 9.431289672851562,
	"learning_rate": 5e-05,
	"loss": 4.2743,
	"step": 93
	},
	{
	"epoch": 0.030574077085704993,
	"grad_norm": 6.723931789398193,
	"learning_rate": 5e-05,
	"loss": 4.111,
	"step": 94
	},
	{
	"epoch": 0.03089933322491462,
	"grad_norm": 5.171010971069336,
	"learning_rate": 5e-05,
	"loss": 3.8832,
	"step": 95
	},
	{
	"epoch": 0.03122458936412425,
	"grad_norm": 7.667996883392334,
	"learning_rate": 5e-05,
	"loss": 4.1839,
	"step": 96
	},
	{
	"epoch": 0.031549845503333875,
	"grad_norm": 9.853692054748535,
	"learning_rate": 5e-05,
	"loss": 4.2596,
	"step": 97
	},
	{
	"epoch": 0.0318751016425435,
	"grad_norm": 9.22080135345459,
	"learning_rate": 5e-05,
	"loss": 3.7551,
	"step": 98
	},
	{
	"epoch": 0.03220035778175313,
	"grad_norm": 8.230822563171387,
	"learning_rate": 5e-05,
	"loss": 4.1223,
	"step": 99
	},
	{
	"epoch": 0.03252561392096276,
	"grad_norm": 4.844912052154541,
	"learning_rate": 5e-05,
	"loss": 3.9264,
	"step": 100
	},
	{
	"epoch": 0.032850870060172385,
	"grad_norm": 5.341676712036133,
	"learning_rate": 5e-05,
	"loss": 4.2083,
	"step": 101
	},
	{
	"epoch": 0.03317612619938201,
	"grad_norm": 10.346305847167969,
	"learning_rate": 5e-05,
	"loss": 4.6745,
	"step": 102
	},
	{
	"epoch": 0.033501382338591644,
	"grad_norm": 5.822200298309326,
	"learning_rate": 5e-05,
	"loss": 3.9329,
	"step": 103
	},
	{
	"epoch": 0.03382663847780127,
	"grad_norm": 4.412308692932129,
	"learning_rate": 5e-05,
	"loss": 4.2581,
	"step": 104
	},
	{
	"epoch": 0.034151894617010896,
	"grad_norm": 6.643288612365723,
	"learning_rate": 5e-05,
	"loss": 4.0638,
	"step": 105
	},
	{
	"epoch": 0.03447715075622052,
	"grad_norm": 4.771259784698486,
	"learning_rate": 5e-05,
	"loss": 3.9147,
	"step": 106
	},
	{
	"epoch": 0.034802406895430155,
	"grad_norm": 4.471869945526123,
	"learning_rate": 5e-05,
	"loss": 3.8011,
	"step": 107
	},
	{
	"epoch": 0.03512766303463978,
	"grad_norm": 6.949775218963623,
	"learning_rate": 5e-05,
	"loss": 4.3229,
	"step": 108
	},
	{
	"epoch": 0.035452919173849406,
	"grad_norm": 5.095446586608887,
	"learning_rate": 5e-05,
	"loss": 3.616,
	"step": 109
	},
	{
	"epoch": 0.03577817531305903,
	"grad_norm": 6.592041015625,
	"learning_rate": 5e-05,
	"loss": 3.7697,
	"step": 110
	},
	{
	"epoch": 0.03610343145226866,
	"grad_norm": 7.455766677856445,
	"learning_rate": 5e-05,
	"loss": 4.0375,
	"step": 111
	},
	{
	"epoch": 0.03642868759147829,
	"grad_norm": 4.540219306945801,
	"learning_rate": 5e-05,
	"loss": 3.7951,
	"step": 112
	},
	{
	"epoch": 0.03675394373068792,
	"grad_norm": 5.230220794677734,
	"learning_rate": 5e-05,
	"loss": 4.0304,
	"step": 113
	},
	{
	"epoch": 0.03707919986989754,
	"grad_norm": 5.179874420166016,
	"learning_rate": 5e-05,
	"loss": 4.0191,
	"step": 114
	},
	{
	"epoch": 0.03740445600910717,
	"grad_norm": 6.374222755432129,
	"learning_rate": 5e-05,
	"loss": 4.4934,
	"step": 115
	},
	{
	"epoch": 0.0377297121483168,
	"grad_norm": 6.96058988571167,
	"learning_rate": 5e-05,
	"loss": 4.1446,
	"step": 116
	},
	{
	"epoch": 0.03805496828752643,
	"grad_norm": 6.299279689788818,
	"learning_rate": 5e-05,
	"loss": 3.9077,
	"step": 117
	},
	{
	"epoch": 0.038380224426736054,
	"grad_norm": 6.169437408447266,
	"learning_rate": 5e-05,
	"loss": 4.1457,
	"step": 118
	},
	{
	"epoch": 0.03870548056594568,
	"grad_norm": 5.159611701965332,
	"learning_rate": 5e-05,
	"loss": 3.7067,
	"step": 119
	},
	{
	"epoch": 0.03903073670515531,
	"grad_norm": 6.676630973815918,
	"learning_rate": 5e-05,
	"loss": 4.0493,
	"step": 120
	},
	{
	"epoch": 0.03935599284436494,
	"grad_norm": 6.488524436950684,
	"learning_rate": 5e-05,
	"loss": 4.109,
	"step": 121
	},
	{
	"epoch": 0.039681248983574564,
	"grad_norm": 6.670077800750732,
	"learning_rate": 5e-05,
	"loss": 3.6645,
	"step": 122
	},
	{
	"epoch": 0.04000650512278419,
	"grad_norm": 6.173693656921387,
	"learning_rate": 5e-05,
	"loss": 4.4163,
	"step": 123
	},
	{
	"epoch": 0.04033176126199382,
	"grad_norm": 6.306183815002441,
	"learning_rate": 5e-05,
	"loss": 3.9382,
	"step": 124
	},
	{
	"epoch": 0.04065701740120345,
	"grad_norm": 6.007297039031982,
	"learning_rate": 5e-05,
	"loss": 3.956,
	"step": 125
	},
	{
	"epoch": 0.040982273540413075,
	"grad_norm": 6.0243730545043945,
	"learning_rate": 5e-05,
	"loss": 3.9613,
	"step": 126
	},
	{
	"epoch": 0.0413075296796227,
	"grad_norm": 5.6909871101379395,
	"learning_rate": 5e-05,
	"loss": 3.9213,
	"step": 127
	},
	{
	"epoch": 0.041632785818832334,
	"grad_norm": 5.5652265548706055,
	"learning_rate": 5e-05,
	"loss": 3.9325,
	"step": 128
	},
	{
	"epoch": 0.04195804195804196,
	"grad_norm": 7.6173272132873535,
	"learning_rate": 5e-05,
	"loss": 4.0422,
	"step": 129
	},
	{
	"epoch": 0.042283298097251586,
	"grad_norm": 10.900376319885254,
	"learning_rate": 5e-05,
	"loss": 3.9173,
	"step": 130
	},
	{
	"epoch": 0.04260855423646121,
	"grad_norm": 12.899847984313965,
	"learning_rate": 5e-05,
	"loss": 4.0328,
	"step": 131
	},
	{
	"epoch": 0.04293381037567084,
	"grad_norm": 11.928502082824707,
	"learning_rate": 5e-05,
	"loss": 3.9763,
	"step": 132
	},
	{
	"epoch": 0.04325906651488047,
	"grad_norm": 8.4597749710083,
	"learning_rate": 5e-05,
	"loss": 4.0895,
	"step": 133
	},
	{
	"epoch": 0.043584322654090096,
	"grad_norm": 5.162694931030273,
	"learning_rate": 5e-05,
	"loss": 4.1564,
	"step": 134
	},
	{
	"epoch": 0.04390957879329972,
	"grad_norm": 13.066299438476562,
	"learning_rate": 5e-05,
	"loss": 4.1774,
	"step": 135
	},
	{
	"epoch": 0.04423483493250935,
	"grad_norm": 14.013510704040527,
	"learning_rate": 5e-05,
	"loss": 3.5203,
	"step": 136
	},
	{
	"epoch": 0.04456009107171898,
	"grad_norm": 15.885542869567871,
	"learning_rate": 5e-05,
	"loss": 4.1405,
	"step": 137
	},
	{
	"epoch": 0.04488534721092861,
	"grad_norm": 7.15226411819458,
	"learning_rate": 5e-05,
	"loss": 4.043,
	"step": 138
	},
	{
	"epoch": 0.04521060335013823,
	"grad_norm": 5.1085686683654785,
	"learning_rate": 5e-05,
	"loss": 3.7764,
	"step": 139
	},
	{
	"epoch": 0.04553585948934786,
	"grad_norm": 6.9343390464782715,
	"learning_rate": 5e-05,
	"loss": 4.2056,
	"step": 140
	},
	{
	"epoch": 0.04586111562855749,
	"grad_norm": 11.624869346618652,
	"learning_rate": 5e-05,
	"loss": 3.7097,
	"step": 141
	},
	{
	"epoch": 0.04618637176776712,
	"grad_norm": 12.546487808227539,
	"learning_rate": 5e-05,
	"loss": 4.2067,
	"step": 142
	},
	{
	"epoch": 0.046511627906976744,
	"grad_norm": 5.573001861572266,
	"learning_rate": 5e-05,
	"loss": 3.6916,
	"step": 143
	},
	{
	"epoch": 0.04683688404618637,
	"grad_norm": 6.0869140625,
	"learning_rate": 5e-05,
	"loss": 4.1239,
	"step": 144
	},
	{
	"epoch": 0.047162140185396,
	"grad_norm": 7.625162124633789,
	"learning_rate": 5e-05,
	"loss": 3.9154,
	"step": 145
	},
	{
	"epoch": 0.04748739632460563,
	"grad_norm": 5.8476762771606445,
	"learning_rate": 5e-05,
	"loss": 3.9673,
	"step": 146
	},
	{
	"epoch": 0.047812652463815254,
	"grad_norm": 6.097865104675293,
	"learning_rate": 5e-05,
	"loss": 3.994,
	"step": 147
	},
	{
	"epoch": 0.04813790860302488,
	"grad_norm": 5.200497150421143,
	"learning_rate": 5e-05,
	"loss": 4.1332,
	"step": 148
	},
	{
	"epoch": 0.04846316474223451,
	"grad_norm": 8.92606258392334,
	"learning_rate": 5e-05,
	"loss": 4.1005,
	"step": 149
	},
	{
	"epoch": 0.04878842088144414,
	"grad_norm": 5.433960437774658,
	"learning_rate": 5e-05,
	"loss": 4.099,
	"step": 150
	},
	{
	"epoch": 0.049113677020653765,
	"grad_norm": 4.350966453552246,
	"learning_rate": 5e-05,
	"loss": 3.7492,
	"step": 151
	},
	{
	"epoch": 0.04943893315986339,
	"grad_norm": 8.3677978515625,
	"learning_rate": 5e-05,
	"loss": 3.8048,
	"step": 152
	},
	{
	"epoch": 0.04976418929907302,
	"grad_norm": 10.74728012084961,
	"learning_rate": 5e-05,
	"loss": 4.3122,
	"step": 153
	},
	{
	"epoch": 0.05008944543828265,
	"grad_norm": 8.89576530456543,
	"learning_rate": 5e-05,
	"loss": 4.432,
	"step": 154
	},
	{
	"epoch": 0.050414701577492275,
	"grad_norm": 6.710874080657959,
	"learning_rate": 5e-05,
	"loss": 3.9353,
	"step": 155
	},
	{
	"epoch": 0.0507399577167019,
	"grad_norm": 10.725092887878418,
	"learning_rate": 5e-05,
	"loss": 4.2776,
	"step": 156
	},
	{
	"epoch": 0.05106521385591153,
	"grad_norm": 11.6733980178833,
	"learning_rate": 5e-05,
	"loss": 4.1354,
	"step": 157
	},
	{
	"epoch": 0.05139046999512116,
	"grad_norm": 9.846784591674805,
	"learning_rate": 5e-05,
	"loss": 3.9646,
	"step": 158
	},
	{
	"epoch": 0.051715726134330786,
	"grad_norm": 8.646893501281738,
	"learning_rate": 5e-05,
	"loss": 3.9413,
	"step": 159
	},
	{
	"epoch": 0.05204098227354041,
	"grad_norm": 7.0959062576293945,
	"learning_rate": 5e-05,
	"loss": 4.0745,
	"step": 160
	},
	{
	"epoch": 0.05236623841275004,
	"grad_norm": 7.378256797790527,
	"learning_rate": 5e-05,
	"loss": 4.1712,
	"step": 161
	},
	{
	"epoch": 0.05269149455195967,
	"grad_norm": 7.3625640869140625,
	"learning_rate": 5e-05,
	"loss": 3.9466,
	"step": 162
	},
	{
	"epoch": 0.0530167506911693,
	"grad_norm": 4.918821811676025,
	"learning_rate": 5e-05,
	"loss": 3.8243,
	"step": 163
	},
	{
	"epoch": 0.05334200683037892,
	"grad_norm": 6.653145790100098,
	"learning_rate": 5e-05,
	"loss": 3.8895,
	"step": 164
	},
	{
	"epoch": 0.05366726296958855,
	"grad_norm": 8.699049949645996,
	"learning_rate": 5e-05,
	"loss": 4.1705,
	"step": 165
	},
	{
	"epoch": 0.05399251910879818,
	"grad_norm": 7.855594158172607,
	"learning_rate": 5e-05,
	"loss": 3.6343,
	"step": 166
	},
	{
	"epoch": 0.05431777524800781,
	"grad_norm": 5.597055435180664,
	"learning_rate": 5e-05,
	"loss": 3.7043,
	"step": 167
	},
	{
	"epoch": 0.05464303138721743,
	"grad_norm": 9.524121284484863,
	"learning_rate": 5e-05,
	"loss": 3.8942,
	"step": 168
	},
	{
	"epoch": 0.05496828752642706,
	"grad_norm": 5.389048099517822,
	"learning_rate": 5e-05,
	"loss": 3.4256,
	"step": 169
	},
	{
	"epoch": 0.05529354366563669,
	"grad_norm": 5.568866729736328,
	"learning_rate": 5e-05,
	"loss": 3.9784,
	"step": 170
	},
	{
	"epoch": 0.05561879980484632,
	"grad_norm": 12.199308395385742,
	"learning_rate": 5e-05,
	"loss": 3.7894,
	"step": 171
	},
	{
	"epoch": 0.055944055944055944,
	"grad_norm": 15.115793228149414,
	"learning_rate": 5e-05,
	"loss": 3.6162,
	"step": 172
	},
	{
	"epoch": 0.05626931208326557,
	"grad_norm": 5.6520538330078125,
	"learning_rate": 5e-05,
	"loss": 3.8633,
	"step": 173
	},
	{
	"epoch": 0.056594568222475196,
	"grad_norm": 5.969440937042236,
	"learning_rate": 5e-05,
	"loss": 4.0392,
	"step": 174
	},
	{
	"epoch": 0.05691982436168483,
	"grad_norm": 8.82860279083252,
	"learning_rate": 5e-05,
	"loss": 4.1596,
	"step": 175
	},
	{
	"epoch": 0.057245080500894455,
	"grad_norm": 8.133511543273926,
	"learning_rate": 5e-05,
	"loss": 4.3075,
	"step": 176
	},
	{
	"epoch": 0.05757033664010408,
	"grad_norm": 5.794802665710449,
	"learning_rate": 5e-05,
	"loss": 3.7082,
	"step": 177
	},
	{
	"epoch": 0.057895592779313707,
	"grad_norm": 6.0018744468688965,
	"learning_rate": 5e-05,
	"loss": 3.67,
	"step": 178
	},
	{
	"epoch": 0.05822084891852334,
	"grad_norm": 9.123400688171387,
	"learning_rate": 5e-05,
	"loss": 3.6293,
	"step": 179
	},
	{
	"epoch": 0.058546105057732965,
	"grad_norm": 12.262410163879395,
	"learning_rate": 5e-05,
	"loss": 4.0337,
	"step": 180
	},
	{
	"epoch": 0.05887136119694259,
	"grad_norm": 5.367374897003174,
	"learning_rate": 5e-05,
	"loss": 3.7243,
	"step": 181
	},
	{
	"epoch": 0.05919661733615222,
	"grad_norm": 5.942975997924805,
	"learning_rate": 5e-05,
	"loss": 3.691,
	"step": 182
	},
	{
	"epoch": 0.05952187347536185,
	"grad_norm": 5.772192001342773,
	"learning_rate": 5e-05,
	"loss": 3.8556,
	"step": 183
	},
	{
	"epoch": 0.059847129614571476,
	"grad_norm": 6.091885566711426,
	"learning_rate": 5e-05,
	"loss": 3.8396,
	"step": 184
	},
	{
	"epoch": 0.0601723857537811,
	"grad_norm": 6.4458231925964355,
	"learning_rate": 5e-05,
	"loss": 4.3947,
	"step": 185
	},
	{
	"epoch": 0.06049764189299073,
	"grad_norm": 6.378884315490723,
	"learning_rate": 5e-05,
	"loss": 4.375,
	"step": 186
	},
	{
	"epoch": 0.06082289803220036,
	"grad_norm": 7.179290294647217,
	"learning_rate": 5e-05,
	"loss": 3.6237,
	"step": 187
	},
	{
	"epoch": 0.06114815417140999,
	"grad_norm": 5.786200046539307,
	"learning_rate": 5e-05,
	"loss": 4.2066,
	"step": 188
	},
	{
	"epoch": 0.06147341031061961,
	"grad_norm": 5.186939239501953,
	"learning_rate": 5e-05,
	"loss": 3.9935,
	"step": 189
	},
	{
	"epoch": 0.06179866644982924,
	"grad_norm": 4.02333402633667,
	"learning_rate": 5e-05,
	"loss": 3.6273,
	"step": 190
	},
	{
	"epoch": 0.06212392258903887,
	"grad_norm": 6.622715473175049,
	"learning_rate": 5e-05,
	"loss": 4.2028,
	"step": 191
	},
	{
	"epoch": 0.0624491787282485,
	"grad_norm": 9.464071273803711,
	"learning_rate": 5e-05,
	"loss": 4.0506,
	"step": 192
	},
	{
	"epoch": 0.06277443486745812,
	"grad_norm": 6.995242595672607,
	"learning_rate": 5e-05,
	"loss": 4.1047,
	"step": 193
	},
	{
	"epoch": 0.06309969100666775,
	"grad_norm": 9.435445785522461,
	"learning_rate": 5e-05,
	"loss": 3.8718,
	"step": 194
	},
	{
	"epoch": 0.06342494714587738,
	"grad_norm": 7.273919582366943,
	"learning_rate": 5e-05,
	"loss": 3.9176,
	"step": 195
	},
	{
	"epoch": 0.063750203285087,
	"grad_norm": 6.896090030670166,
	"learning_rate": 5e-05,
	"loss": 3.8408,
	"step": 196
	},
	{
	"epoch": 0.06407545942429663,
	"grad_norm": 7.282253265380859,
	"learning_rate": 5e-05,
	"loss": 3.6903,
	"step": 197
	},
	{
	"epoch": 0.06440071556350627,
	"grad_norm": 9.39031982421875,
	"learning_rate": 5e-05,
	"loss": 3.9139,
	"step": 198
	},
	{
	"epoch": 0.06472597170271589,
	"grad_norm": 7.485379695892334,
	"learning_rate": 5e-05,
	"loss": 3.8522,
	"step": 199
	},
	{
	"epoch": 0.06505122784192552,
	"grad_norm": 7.848803997039795,
	"learning_rate": 5e-05,
	"loss": 3.879,
	"step": 200
	},
	{
	"epoch": 0.06537648398113514,
	"grad_norm": 7.829058647155762,
	"learning_rate": 5e-05,
	"loss": 4.0283,
	"step": 201
	},
	{
	"epoch": 0.06570174012034477,
	"grad_norm": 8.984028816223145,
	"learning_rate": 5e-05,
	"loss": 3.8663,
	"step": 202
	},
	{
	"epoch": 0.0660269962595544,
	"grad_norm": 7.604732513427734,
	"learning_rate": 5e-05,
	"loss": 3.7871,
	"step": 203
	},
	{
	"epoch": 0.06635225239876402,
	"grad_norm": 6.779748916625977,
	"learning_rate": 5e-05,
	"loss": 3.9423,
	"step": 204
	},
	{
	"epoch": 0.06667750853797365,
	"grad_norm": 8.93659782409668,
	"learning_rate": 5e-05,
	"loss": 4.0208,
	"step": 205
	},
	{
	"epoch": 0.06700276467718329,
	"grad_norm": 6.093626022338867,
	"learning_rate": 5e-05,
	"loss": 3.8828,
	"step": 206
	},
	{
	"epoch": 0.06732802081639291,
	"grad_norm": 6.105995178222656,
	"learning_rate": 5e-05,
	"loss": 4.0983,
	"step": 207
	},
	{
	"epoch": 0.06765327695560254,
	"grad_norm": 7.379316329956055,
	"learning_rate": 5e-05,
	"loss": 4.0493,
	"step": 208
	},
	{
	"epoch": 0.06797853309481217,
	"grad_norm": 6.404873847961426,
	"learning_rate": 5e-05,
	"loss": 3.9271,
	"step": 209
	},
	{
	"epoch": 0.06830378923402179,
	"grad_norm": 7.560967445373535,
	"learning_rate": 5e-05,
	"loss": 3.8633,
	"step": 210
	},
	{
	"epoch": 0.06862904537323142,
	"grad_norm": 6.042522430419922,
	"learning_rate": 5e-05,
	"loss": 3.7389,
	"step": 211
	},
	{
	"epoch": 0.06895430151244104,
	"grad_norm": 6.4881367683410645,
	"learning_rate": 5e-05,
	"loss": 3.8196,
	"step": 212
	},
	{
	"epoch": 0.06927955765165067,
	"grad_norm": 6.52613639831543,
	"learning_rate": 5e-05,
	"loss": 3.7737,
	"step": 213
	},
	{
	"epoch": 0.06960481379086031,
	"grad_norm": 4.999444007873535,
	"learning_rate": 5e-05,
	"loss": 3.8722,
	"step": 214
	},
	{
	"epoch": 0.06993006993006994,
	"grad_norm": 7.060845851898193,
	"learning_rate": 5e-05,
	"loss": 3.774,
	"step": 215
	},
	{
	"epoch": 0.07025532606927956,
	"grad_norm": 8.545415878295898,
	"learning_rate": 5e-05,
	"loss": 3.8479,
	"step": 216
	},
	{
	"epoch": 0.07058058220848919,
	"grad_norm": 7.625663757324219,
	"learning_rate": 5e-05,
	"loss": 3.5068,
	"step": 217
	},
	{
	"epoch": 0.07090583834769881,
	"grad_norm": 7.191437244415283,
	"learning_rate": 5e-05,
	"loss": 3.7885,
	"step": 218
	},
	{
	"epoch": 0.07123109448690844,
	"grad_norm": 7.386499881744385,
	"learning_rate": 5e-05,
	"loss": 3.9494,
	"step": 219
	},
	{
	"epoch": 0.07155635062611806,
	"grad_norm": 5.616601943969727,
	"learning_rate": 5e-05,
	"loss": 3.8093,
	"step": 220
	},
	{
	"epoch": 0.07188160676532769,
	"grad_norm": 6.17822265625,
	"learning_rate": 5e-05,
	"loss": 3.8981,
	"step": 221
	},
	{
	"epoch": 0.07220686290453732,
	"grad_norm": 6.138426303863525,
	"learning_rate": 5e-05,
	"loss": 4.0091,
	"step": 222
	},
	{
	"epoch": 0.07253211904374696,
	"grad_norm": 6.6297831535339355,
	"learning_rate": 5e-05,
	"loss": 3.9291,
	"step": 223
	},
	{
	"epoch": 0.07285737518295658,
	"grad_norm": 6.557385444641113,
	"learning_rate": 5e-05,
	"loss": 3.8338,
	"step": 224
	},
	{
	"epoch": 0.07318263132216621,
	"grad_norm": 6.9579291343688965,
	"learning_rate": 5e-05,
	"loss": 3.8158,
	"step": 225
	},
	{
	"epoch": 0.07350788746137583,
	"grad_norm": 7.129207611083984,
	"learning_rate": 5e-05,
	"loss": 4.1731,
	"step": 226
	},
	{
	"epoch": 0.07383314360058546,
	"grad_norm": 6.645360946655273,
	"learning_rate": 5e-05,
	"loss": 3.6926,
	"step": 227
	},
	{
	"epoch": 0.07415839973979509,
	"grad_norm": 8.101895332336426,
	"learning_rate": 5e-05,
	"loss": 4.3064,
	"step": 228
	},
	{
	"epoch": 0.07448365587900471,
	"grad_norm": 7.812802791595459,
	"learning_rate": 5e-05,
	"loss": 3.7983,
	"step": 229
	},
	{
	"epoch": 0.07480891201821434,
	"grad_norm": 7.278988838195801,
	"learning_rate": 5e-05,
	"loss": 3.9539,
	"step": 230
	},
	{
	"epoch": 0.07513416815742398,
	"grad_norm": 7.909803867340088,
	"learning_rate": 5e-05,
	"loss": 3.5888,
	"step": 231
	},
	{
	"epoch": 0.0754594242966336,
	"grad_norm": 5.668457984924316,
	"learning_rate": 5e-05,
	"loss": 3.8219,
	"step": 232
	},
	{
	"epoch": 0.07578468043584323,
	"grad_norm": 6.159639358520508,
	"learning_rate": 5e-05,
	"loss": 4.0184,
	"step": 233
	},
	{
	"epoch": 0.07610993657505286,
	"grad_norm": 6.18869161605835,
	"learning_rate": 5e-05,
	"loss": 3.7595,
	"step": 234
	},
	{
	"epoch": 0.07643519271426248,
	"grad_norm": 5.471868991851807,
	"learning_rate": 5e-05,
	"loss": 3.9409,
	"step": 235
	},
	{
	"epoch": 0.07676044885347211,
	"grad_norm": 7.921130180358887,
	"learning_rate": 5e-05,
	"loss": 4.1452,
	"step": 236
	},
	{
	"epoch": 0.07708570499268173,
	"grad_norm": 6.49941349029541,
	"learning_rate": 5e-05,
	"loss": 3.8261,
	"step": 237
	},
	{
	"epoch": 0.07741096113189136,
	"grad_norm": 10.190372467041016,
	"learning_rate": 5e-05,
	"loss": 3.6134,
	"step": 238
	},
	{
	"epoch": 0.07773621727110099,
	"grad_norm": 5.995229244232178,
	"learning_rate": 5e-05,
	"loss": 3.7563,
	"step": 239
	},
	{
	"epoch": 0.07806147341031063,
	"grad_norm": 8.94497299194336,
	"learning_rate": 5e-05,
	"loss": 3.5379,
	"step": 240
	},
	{
	"epoch": 0.07838672954952025,
	"grad_norm": 10.990089416503906,
	"learning_rate": 5e-05,
	"loss": 3.9176,
	"step": 241
	},
	{
	"epoch": 0.07871198568872988,
	"grad_norm": 7.899653434753418,
	"learning_rate": 5e-05,
	"loss": 3.7961,
	"step": 242
	},
	{
	"epoch": 0.0790372418279395,
	"grad_norm": 7.264082908630371,
	"learning_rate": 5e-05,
	"loss": 3.5957,
	"step": 243
	},
	{
	"epoch": 0.07936249796714913,
	"grad_norm": 5.855433940887451,
	"learning_rate": 5e-05,
	"loss": 3.5913,
	"step": 244
	},
	{
	"epoch": 0.07968775410635875,
	"grad_norm": 6.854794979095459,
	"learning_rate": 5e-05,
	"loss": 3.6167,
	"step": 245
	},
	{
	"epoch": 0.08001301024556838,
	"grad_norm": 7.06243896484375,
	"learning_rate": 5e-05,
	"loss": 3.7909,
	"step": 246
	},
	{
	"epoch": 0.080338266384778,
	"grad_norm": 8.033863067626953,
	"learning_rate": 5e-05,
	"loss": 4.046,
	"step": 247
	},
	{
	"epoch": 0.08066352252398765,
	"grad_norm": 6.078402519226074,
	"learning_rate": 5e-05,
	"loss": 3.3269,
	"step": 248
	},
	{
	"epoch": 0.08098877866319727,
	"grad_norm": 9.511942863464355,
	"learning_rate": 5e-05,
	"loss": 3.5749,
	"step": 249
	},
	{
	"epoch": 0.0813140348024069,
	"grad_norm": 9.74225902557373,
	"learning_rate": 5e-05,
	"loss": 3.9162,
	"step": 250
	},
	{
	"epoch": 0.08163929094161652,
	"grad_norm": 6.432509422302246,
	"learning_rate": 5e-05,
	"loss": 3.8754,
	"step": 251
	},
	{
	"epoch": 0.08196454708082615,
	"grad_norm": 7.885379314422607,
	"learning_rate": 5e-05,
	"loss": 3.7214,
	"step": 252
	},
	{
	"epoch": 0.08228980322003578,
	"grad_norm": 11.552560806274414,
	"learning_rate": 5e-05,
	"loss": 3.7367,
	"step": 253
	},
	{
	"epoch": 0.0826150593592454,
	"grad_norm": 9.054500579833984,
	"learning_rate": 5e-05,
	"loss": 3.5476,
	"step": 254
	},
	{
	"epoch": 0.08294031549845503,
	"grad_norm": 5.916128635406494,
	"learning_rate": 5e-05,
	"loss": 3.695,
	"step": 255
	},
	{
	"epoch": 0.08326557163766467,
	"grad_norm": 10.65311050415039,
	"learning_rate": 5e-05,
	"loss": 4.1597,
	"step": 256
	},
	{
	"epoch": 0.0835908277768743,
	"grad_norm": 13.63244342803955,
	"learning_rate": 5e-05,
	"loss": 3.5796,
	"step": 257
	},
	{
	"epoch": 0.08391608391608392,
	"grad_norm": 10.830595970153809,
	"learning_rate": 5e-05,
	"loss": 3.4825,
	"step": 258
	},
	{
	"epoch": 0.08424134005529355,
	"grad_norm": 5.9953718185424805,
	"learning_rate": 5e-05,
	"loss": 3.792,
	"step": 259
	},
	{
	"epoch": 0.08456659619450317,
	"grad_norm": 12.76282787322998,
	"learning_rate": 5e-05,
	"loss": 3.5532,
	"step": 260
	},
	{
	"epoch": 0.0848918523337128,
	"grad_norm": 18.605255126953125,
	"learning_rate": 5e-05,
	"loss": 3.7788,
	"step": 261
	},
	{
	"epoch": 0.08521710847292242,
	"grad_norm": 12.753776550292969,
	"learning_rate": 5e-05,
	"loss": 3.7542,
	"step": 262
	},
	{
	"epoch": 0.08554236461213205,
	"grad_norm": 7.8098673820495605,
	"learning_rate": 5e-05,
	"loss": 4.4529,
	"step": 263
	},
	{
	"epoch": 0.08586762075134168,
	"grad_norm": 9.642732620239258,
	"learning_rate": 5e-05,
	"loss": 3.8515,
	"step": 264
	},
	{
	"epoch": 0.08619287689055131,
	"grad_norm": 5.820125102996826,
	"learning_rate": 5e-05,
	"loss": 4.3286,
	"step": 265
	},
	{
	"epoch": 0.08651813302976094,
	"grad_norm": 9.613585472106934,
	"learning_rate": 5e-05,
	"loss": 3.9569,
	"step": 266
	},
	{
	"epoch": 0.08684338916897057,
	"grad_norm": 9.211997985839844,
	"learning_rate": 5e-05,
	"loss": 3.9244,
	"step": 267
	},
	{
	"epoch": 0.08716864530818019,
	"grad_norm": 6.351746559143066,
	"learning_rate": 5e-05,
	"loss": 3.6584,
	"step": 268
	},
	{
	"epoch": 0.08749390144738982,
	"grad_norm": 6.802426815032959,
	"learning_rate": 5e-05,
	"loss": 3.8361,
	"step": 269
	},
	{
	"epoch": 0.08781915758659944,
	"grad_norm": 7.498976707458496,
	"learning_rate": 5e-05,
	"loss": 3.6589,
	"step": 270
	},
	{
	"epoch": 0.08814441372580907,
	"grad_norm": 6.058091163635254,
	"learning_rate": 5e-05,
	"loss": 3.6699,
	"step": 271
	},
	{
	"epoch": 0.0884696698650187,
	"grad_norm": 5.347617149353027,
	"learning_rate": 5e-05,
	"loss": 3.586,
	"step": 272
	},
	{
	"epoch": 0.08879492600422834,
	"grad_norm": 6.720355033874512,
	"learning_rate": 5e-05,
	"loss": 3.9508,
	"step": 273
	},
	{
	"epoch": 0.08912018214343796,
	"grad_norm": 5.8187174797058105,
	"learning_rate": 5e-05,
	"loss": 4.1922,
	"step": 274
	},
	{
	"epoch": 0.08944543828264759,
	"grad_norm": 4.981271743774414,
	"learning_rate": 5e-05,
	"loss": 3.5997,
	"step": 275
	},
	{
	"epoch": 0.08977069442185721,
	"grad_norm": 6.238826751708984,
	"learning_rate": 5e-05,
	"loss": 3.6929,
	"step": 276
	},
	{
	"epoch": 0.09009595056106684,
	"grad_norm": 7.073620796203613,
	"learning_rate": 5e-05,
	"loss": 3.7813,
	"step": 277
	},
	{
	"epoch": 0.09042120670027647,
	"grad_norm": 7.445998668670654,
	"learning_rate": 5e-05,
	"loss": 3.5475,
	"step": 278
	},
	{
	"epoch": 0.09074646283948609,
	"grad_norm": 6.120103359222412,
	"learning_rate": 5e-05,
	"loss": 3.7499,
	"step": 279
	},
	{
	"epoch": 0.09107171897869572,
	"grad_norm": 8.138337135314941,
	"learning_rate": 5e-05,
	"loss": 3.8753,
	"step": 280
	},
	{
	"epoch": 0.09139697511790534,
	"grad_norm": 7.516664981842041,
	"learning_rate": 5e-05,
	"loss": 3.6093,
	"step": 281
	},
	{
	"epoch": 0.09172223125711498,
	"grad_norm": 5.630866050720215,
	"learning_rate": 5e-05,
	"loss": 3.7269,
	"step": 282
	},
	{
	"epoch": 0.09204748739632461,
	"grad_norm": 5.958463668823242,
	"learning_rate": 5e-05,
	"loss": 3.7448,
	"step": 283
	},
	{
	"epoch": 0.09237274353553424,
	"grad_norm": 6.990318298339844,
	"learning_rate": 5e-05,
	"loss": 3.6994,
	"step": 284
	},
	{
	"epoch": 0.09269799967474386,
	"grad_norm": 6.364505767822266,
	"learning_rate": 5e-05,
	"loss": 3.5316,
	"step": 285
	},
	{
	"epoch": 0.09302325581395349,
	"grad_norm": 6.308237552642822,
	"learning_rate": 5e-05,
	"loss": 4.1899,
	"step": 286
	},
	{
	"epoch": 0.09334851195316311,
	"grad_norm": 8.585831642150879,
	"learning_rate": 5e-05,
	"loss": 3.7078,
	"step": 287
	},
	{
	"epoch": 0.09367376809237274,
	"grad_norm": 6.02251672744751,
	"learning_rate": 5e-05,
	"loss": 3.7081,
	"step": 288
	},
	{
	"epoch": 0.09399902423158236,
	"grad_norm": 6.891519546508789,
	"learning_rate": 5e-05,
	"loss": 3.9432,
	"step": 289
	},
	{
	"epoch": 0.094324280370792,
	"grad_norm": 8.65449047088623,
	"learning_rate": 5e-05,
	"loss": 3.4704,
	"step": 290
	},
	{
	"epoch": 0.09464953651000163,
	"grad_norm": 6.133912563323975,
	"learning_rate": 5e-05,
	"loss": 3.8847,
	"step": 291
	},
	{
	"epoch": 0.09497479264921126,
	"grad_norm": 6.619656085968018,
	"learning_rate": 5e-05,
	"loss": 3.5818,
	"step": 292
	},
	{
	"epoch": 0.09530004878842088,
	"grad_norm": 9.706931114196777,
	"learning_rate": 5e-05,
	"loss": 3.6839,
	"step": 293
	},
	{
	"epoch": 0.09562530492763051,
	"grad_norm": 6.43947172164917,
	"learning_rate": 5e-05,
	"loss": 4.0691,
	"step": 294
	},
	{
	"epoch": 0.09595056106684013,
	"grad_norm": 7.45628547668457,
	"learning_rate": 5e-05,
	"loss": 3.9546,
	"step": 295
	},
	{
	"epoch": 0.09627581720604976,
	"grad_norm": 9.464739799499512,
	"learning_rate": 5e-05,
	"loss": 3.8893,
	"step": 296
	},
	{
	"epoch": 0.09660107334525939,
	"grad_norm": 9.263232231140137,
	"learning_rate": 5e-05,
	"loss": 4.3718,
	"step": 297
	},
	{
	"epoch": 0.09692632948446903,
	"grad_norm": 6.793147087097168,
	"learning_rate": 5e-05,
	"loss": 3.7036,
	"step": 298
	},
	{
	"epoch": 0.09725158562367865,
	"grad_norm": 12.16869831085205,
	"learning_rate": 5e-05,
	"loss": 4.2924,
	"step": 299
	},
	{
	"epoch": 0.09757684176288828,
	"grad_norm": 10.058348655700684,
	"learning_rate": 5e-05,
	"loss": 3.852,
	"step": 300
	},
	{
	"epoch": 0.0979020979020979,
	"grad_norm": 5.966858386993408,
	"learning_rate": 5e-05,
	"loss": 3.7514,
	"step": 301
	},
	{
	"epoch": 0.09822735404130753,
	"grad_norm": 9.075318336486816,
	"learning_rate": 5e-05,
	"loss": 3.6808,
	"step": 302
	},
	{
	"epoch": 0.09855261018051716,
	"grad_norm": 11.372644424438477,
	"learning_rate": 5e-05,
	"loss": 4.0671,
	"step": 303
	},
	{
	"epoch": 0.09887786631972678,
	"grad_norm": 12.080697059631348,
	"learning_rate": 5e-05,
	"loss": 3.2312,
	"step": 304
	},
	{
	"epoch": 0.09920312245893641,
	"grad_norm": 5.336820125579834,
	"learning_rate": 5e-05,
	"loss": 3.5947,
	"step": 305
	},
	{
	"epoch": 0.09952837859814603,
	"grad_norm": 7.266972064971924,
	"learning_rate": 5e-05,
	"loss": 3.1227,
	"step": 306
	},
	{
	"epoch": 0.09985363473735567,
	"grad_norm": 6.334729194641113,
	"learning_rate": 5e-05,
	"loss": 3.6156,
	"step": 307
	},
	{
	"epoch": 0.1001788908765653,
	"grad_norm": 5.643017768859863,
	"learning_rate": 5e-05,
	"loss": 3.6258,
	"step": 308
	},
	{
	"epoch": 0.10050414701577493,
	"grad_norm": 5.640905380249023,
	"learning_rate": 5e-05,
	"loss": 3.9051,
	"step": 309
	},
	{
	"epoch": 0.10082940315498455,
	"grad_norm": 6.985749244689941,
	"learning_rate": 5e-05,
	"loss": 3.6725,
	"step": 310
	},
	{
	"epoch": 0.10115465929419418,
	"grad_norm": 6.893199443817139,
	"learning_rate": 5e-05,
	"loss": 3.4541,
	"step": 311
	},
	{
	"epoch": 0.1014799154334038,
	"grad_norm": 6.803256511688232,
	"learning_rate": 5e-05,
	"loss": 3.0762,
	"step": 312
	},
	{
	"epoch": 0.10180517157261343,
	"grad_norm": 8.491405487060547,
	"learning_rate": 5e-05,
	"loss": 3.719,
	"step": 313
	},
	{
	"epoch": 0.10213042771182305,
	"grad_norm": 5.912895202636719,
	"learning_rate": 5e-05,
	"loss": 3.6613,
	"step": 314
	},
	{
	"epoch": 0.1024556838510327,
	"grad_norm": 6.211380958557129,
	"learning_rate": 5e-05,
	"loss": 3.632,
	"step": 315
	},
	{
	"epoch": 0.10278093999024232,
	"grad_norm": 8.083343505859375,
	"learning_rate": 5e-05,
	"loss": 3.5327,
	"step": 316
	},
	{
	"epoch": 0.10310619612945195,
	"grad_norm": 8.091614723205566,
	"learning_rate": 5e-05,
	"loss": 3.8166,
	"step": 317
	},
	{
	"epoch": 0.10343145226866157,
	"grad_norm": 5.631373405456543,
	"learning_rate": 5e-05,
	"loss": 3.6482,
	"step": 318
	},
	{
	"epoch": 0.1037567084078712,
	"grad_norm": 12.532264709472656,
	"learning_rate": 5e-05,
	"loss": 3.5283,
	"step": 319
	},
	{
	"epoch": 0.10408196454708082,
	"grad_norm": 5.990050315856934,
	"learning_rate": 5e-05,
	"loss": 3.9679,
	"step": 320
	},
	{
	"epoch": 0.10440722068629045,
	"grad_norm": 6.2988667488098145,
	"learning_rate": 5e-05,
	"loss": 3.8285,
	"step": 321
	},
	{
	"epoch": 0.10473247682550008,
	"grad_norm": 8.320550918579102,
	"learning_rate": 5e-05,
	"loss": 4.0295,
	"step": 322
	},
	{
	"epoch": 0.10505773296470972,
	"grad_norm": 6.640725612640381,
	"learning_rate": 5e-05,
	"loss": 3.5094,
	"step": 323
	},
	{
	"epoch": 0.10538298910391934,
	"grad_norm": 6.340143203735352,
	"learning_rate": 5e-05,
	"loss": 3.6144,
	"step": 324
	},
	{
	"epoch": 0.10570824524312897,
	"grad_norm": 7.403520584106445,
	"learning_rate": 5e-05,
	"loss": 3.9676,
	"step": 325
	},
	{
	"epoch": 0.1060335013823386,
	"grad_norm": 7.462515354156494,
	"learning_rate": 5e-05,
	"loss": 3.7215,
	"step": 326
	},
	{
	"epoch": 0.10635875752154822,
	"grad_norm": 5.612910747528076,
	"learning_rate": 5e-05,
	"loss": 3.5211,
	"step": 327
	},
	{
	"epoch": 0.10668401366075785,
	"grad_norm": 7.502828598022461,
	"learning_rate": 5e-05,
	"loss": 4.0133,
	"step": 328
	},
	{
	"epoch": 0.10700926979996747,
	"grad_norm": 8.6078462600708,
	"learning_rate": 5e-05,
	"loss": 4.1303,
	"step": 329
	},
	{
	"epoch": 0.1073345259391771,
	"grad_norm": 9.176727294921875,
	"learning_rate": 5e-05,
	"loss": 3.8978,
	"step": 330
	},
	{
	"epoch": 0.10765978207838672,
	"grad_norm": 10.041065216064453,
	"learning_rate": 5e-05,
	"loss": 4.0287,
	"step": 331
	},
	{
	"epoch": 0.10798503821759636,
	"grad_norm": 9.741332054138184,
	"learning_rate": 5e-05,
	"loss": 3.5463,
	"step": 332
	},
	{
	"epoch": 0.10831029435680599,
	"grad_norm": 7.8142499923706055,
	"learning_rate": 5e-05,
	"loss": 3.7777,
	"step": 333
	},
	{
	"epoch": 0.10863555049601561,
	"grad_norm": 8.65985107421875,
	"learning_rate": 5e-05,
	"loss": 3.7169,
	"step": 334
	},
	{
	"epoch": 0.10896080663522524,
	"grad_norm": 9.955862998962402,
	"learning_rate": 5e-05,
	"loss": 3.4762,
	"step": 335
	},
	{
	"epoch": 0.10928606277443487,
	"grad_norm": 8.422538757324219,
	"learning_rate": 5e-05,
	"loss": 3.8524,
	"step": 336
	},
	{
	"epoch": 0.10961131891364449,
	"grad_norm": 6.849399089813232,
	"learning_rate": 5e-05,
	"loss": 3.5617,
	"step": 337
	},
	{
	"epoch": 0.10993657505285412,
	"grad_norm": 10.709142684936523,
	"learning_rate": 5e-05,
	"loss": 3.8691,
	"step": 338
	},
	{
	"epoch": 0.11026183119206374,
	"grad_norm": 6.636946678161621,
	"learning_rate": 5e-05,
	"loss": 3.9301,
	"step": 339
	},
	{
	"epoch": 0.11058708733127338,
	"grad_norm": 7.364269256591797,
	"learning_rate": 5e-05,
	"loss": 3.485,
	"step": 340
	},
	{
	"epoch": 0.11091234347048301,
	"grad_norm": 12.705086708068848,
	"learning_rate": 5e-05,
	"loss": 3.8413,
	"step": 341
	},
	{
	"epoch": 0.11123759960969264,
	"grad_norm": 6.6930928230285645,
	"learning_rate": 5e-05,
	"loss": 3.8912,
	"step": 342
	},
	{
	"epoch": 0.11156285574890226,
	"grad_norm": 6.823209285736084,
	"learning_rate": 5e-05,
	"loss": 4.2082,
	"step": 343
	},
	{
	"epoch": 0.11188811188811189,
	"grad_norm": 9.133801460266113,
	"learning_rate": 5e-05,
	"loss": 4.0229,
	"step": 344
	},
	{
	"epoch": 0.11221336802732151,
	"grad_norm": 7.471242904663086,
	"learning_rate": 5e-05,
	"loss": 3.6206,
	"step": 345
	},
	{
	"epoch": 0.11253862416653114,
	"grad_norm": 7.450990676879883,
	"learning_rate": 5e-05,
	"loss": 3.7254,
	"step": 346
	},
	{
	"epoch": 0.11286388030574077,
	"grad_norm": 7.53968620300293,
	"learning_rate": 5e-05,
	"loss": 4.0496,
	"step": 347
	},
	{
	"epoch": 0.11318913644495039,
	"grad_norm": 12.383916854858398,
	"learning_rate": 5e-05,
	"loss": 3.6815,
	"step": 348
	},
	{
	"epoch": 0.11351439258416003,
	"grad_norm": 8.754898071289062,
	"learning_rate": 5e-05,
	"loss": 3.5597,
	"step": 349
	},
	{
	"epoch": 0.11383964872336966,
	"grad_norm": 7.65074348449707,
	"learning_rate": 5e-05,
	"loss": 4.0558,
	"step": 350
	},
	{
	"epoch": 0.11416490486257928,
	"grad_norm": 6.735880374908447,
	"learning_rate": 5e-05,
	"loss": 3.5702,
	"step": 351
	},
	{
	"epoch": 0.11449016100178891,
	"grad_norm": 6.371280670166016,
	"learning_rate": 5e-05,
	"loss": 3.7325,
	"step": 352
	},
	{
	"epoch": 0.11481541714099854,
	"grad_norm": 6.2961745262146,
	"learning_rate": 5e-05,
	"loss": 3.8299,
	"step": 353
	},
	{
	"epoch": 0.11514067328020816,
	"grad_norm": 8.073019027709961,
	"learning_rate": 5e-05,
	"loss": 3.77,
	"step": 354
	},
	{
	"epoch": 0.11546592941941779,
	"grad_norm": 7.552728176116943,
	"learning_rate": 5e-05,
	"loss": 3.6974,
	"step": 355
	},
	{
	"epoch": 0.11579118555862741,
	"grad_norm": 6.595133304595947,
	"learning_rate": 5e-05,
	"loss": 3.6737,
	"step": 356
	},
	{
	"epoch": 0.11611644169783705,
	"grad_norm": 7.287491321563721,
	"learning_rate": 5e-05,
	"loss": 3.5135,
	"step": 357
	},
	{
	"epoch": 0.11644169783704668,
	"grad_norm": 8.068704605102539,
	"learning_rate": 5e-05,
	"loss": 3.9036,
	"step": 358
	},
	{
	"epoch": 0.1167669539762563,
	"grad_norm": 6.8040618896484375,
	"learning_rate": 5e-05,
	"loss": 3.8034,
	"step": 359
	},
	{
	"epoch": 0.11709221011546593,
	"grad_norm": 9.113652229309082,
	"learning_rate": 5e-05,
	"loss": 3.4709,
	"step": 360
	},
	{
	"epoch": 0.11741746625467556,
	"grad_norm": 8.15011978149414,
	"learning_rate": 5e-05,
	"loss": 4.111,
	"step": 361
	},
	{
	"epoch": 0.11774272239388518,
	"grad_norm": 6.63869047164917,
	"learning_rate": 5e-05,
	"loss": 3.8713,
	"step": 362
	},
	{
	"epoch": 0.11806797853309481,
	"grad_norm": 6.785707473754883,
	"learning_rate": 5e-05,
	"loss": 3.1996,
	"step": 363
	},
	{
	"epoch": 0.11839323467230443,
	"grad_norm": 7.099983215332031,
	"learning_rate": 5e-05,
	"loss": 3.4236,
	"step": 364
	},
	{
	"epoch": 0.11871849081151407,
	"grad_norm": 7.014822006225586,
	"learning_rate": 5e-05,
	"loss": 3.7598,
	"step": 365
	},
	{
	"epoch": 0.1190437469507237,
	"grad_norm": 7.138816833496094,
	"learning_rate": 5e-05,
	"loss": 3.6681,
	"step": 366
	},
	{
	"epoch": 0.11936900308993333,
	"grad_norm": 6.563411235809326,
	"learning_rate": 5e-05,
	"loss": 3.82,
	"step": 367
	},
	{
	"epoch": 0.11969425922914295,
	"grad_norm": 6.389061450958252,
	"learning_rate": 5e-05,
	"loss": 3.7305,
	"step": 368
	},
	{
	"epoch": 0.12001951536835258,
	"grad_norm": 8.009288787841797,
	"learning_rate": 5e-05,
	"loss": 3.9673,
	"step": 369
	},
	{
	"epoch": 0.1203447715075622,
	"grad_norm": 6.436244964599609,
	"learning_rate": 5e-05,
	"loss": 3.6934,
	"step": 370
	},
	{
	"epoch": 0.12067002764677183,
	"grad_norm": 7.818999767303467,
	"learning_rate": 5e-05,
	"loss": 3.8564,
	"step": 371
	},
	{
	"epoch": 0.12099528378598146,
	"grad_norm": 7.891193866729736,
	"learning_rate": 5e-05,
	"loss": 3.9254,
	"step": 372
	},
	{
	"epoch": 0.12132053992519108,
	"grad_norm": 8.381048202514648,
	"learning_rate": 5e-05,
	"loss": 3.8966,
	"step": 373
	},
	{
	"epoch": 0.12164579606440072,
	"grad_norm": 7.328115940093994,
	"learning_rate": 5e-05,
	"loss": 3.4804,
	"step": 374
	},
	{
	"epoch": 0.12197105220361035,
	"grad_norm": 7.0525922775268555,
	"learning_rate": 5e-05,
	"loss": 4.0177,
	"step": 375
	},
	{
	"epoch": 0.12229630834281997,
	"grad_norm": 7.212350845336914,
	"learning_rate": 5e-05,
	"loss": 3.4131,
	"step": 376
	},
	{
	"epoch": 0.1226215644820296,
	"grad_norm": 6.808897972106934,
	"learning_rate": 5e-05,
	"loss": 3.5174,
	"step": 377
	},
	{
	"epoch": 0.12294682062123923,
	"grad_norm": 7.094473838806152,
	"learning_rate": 5e-05,
	"loss": 3.7852,
	"step": 378
	},
	{
	"epoch": 0.12327207676044885,
	"grad_norm": 6.998628616333008,
	"learning_rate": 5e-05,
	"loss": 3.8094,
	"step": 379
	},
	{
	"epoch": 0.12359733289965848,
	"grad_norm": 7.043560028076172,
	"learning_rate": 5e-05,
	"loss": 3.6862,
	"step": 380
	},
	{
	"epoch": 0.1239225890388681,
	"grad_norm": 6.198429107666016,
	"learning_rate": 5e-05,
	"loss": 3.5462,
	"step": 381
	},
	{
	"epoch": 0.12424784517807774,
	"grad_norm": 6.5926513671875,
	"learning_rate": 5e-05,
	"loss": 3.9851,
	"step": 382
	},
	{
	"epoch": 0.12457310131728737,
	"grad_norm": 5.893482208251953,
	"learning_rate": 5e-05,
	"loss": 3.6685,
	"step": 383
	},
	{
	"epoch": 0.124898357456497,
	"grad_norm": 5.886164665222168,
	"learning_rate": 5e-05,
	"loss": 3.7367,
	"step": 384
	},
	{
	"epoch": 0.1252236135957066,
	"grad_norm": 7.275190353393555,
	"learning_rate": 5e-05,
	"loss": 3.4105,
	"step": 385
	},
	{
	"epoch": 0.12554886973491625,
	"grad_norm": 8.864086151123047,
	"learning_rate": 5e-05,
	"loss": 4.0736,
	"step": 386
	},
	{
	"epoch": 0.1258741258741259,
	"grad_norm": 9.517216682434082,
	"learning_rate": 5e-05,
	"loss": 3.6961,
	"step": 387
	},
	{
	"epoch": 0.1261993820133355,
	"grad_norm": 8.437984466552734,
	"learning_rate": 5e-05,
	"loss": 4.1894,
	"step": 388
	},
	{
	"epoch": 0.12652463815254514,
	"grad_norm": 9.38377571105957,
	"learning_rate": 5e-05,
	"loss": 3.9029,
	"step": 389
	},
	{
	"epoch": 0.12684989429175475,
	"grad_norm": 8.621910095214844,
	"learning_rate": 5e-05,
	"loss": 3.9334,
	"step": 390
	},
	{
	"epoch": 0.1271751504309644,
	"grad_norm": 7.772785186767578,
	"learning_rate": 5e-05,
	"loss": 3.4678,
	"step": 391
	},
	{
	"epoch": 0.127500406570174,
	"grad_norm": 8.752019882202148,
	"learning_rate": 5e-05,
	"loss": 3.62,
	"step": 392
	},
	{
	"epoch": 0.12782566270938364,
	"grad_norm": 7.4593706130981445,
	"learning_rate": 5e-05,
	"loss": 3.907,
	"step": 393
	},
	{
	"epoch": 0.12815091884859325,
	"grad_norm": 7.014523983001709,
	"learning_rate": 5e-05,
	"loss": 3.7242,
	"step": 394
	},
	{
	"epoch": 0.1284761749878029,
	"grad_norm": 7.254335403442383,
	"learning_rate": 5e-05,
	"loss": 3.8927,
	"step": 395
	},
	{
	"epoch": 0.12880143112701253,
	"grad_norm": 7.555474281311035,
	"learning_rate": 5e-05,
	"loss": 4.3168,
	"step": 396
	},
	{
	"epoch": 0.12912668726622215,
	"grad_norm": 11.899949073791504,
	"learning_rate": 5e-05,
	"loss": 3.6753,
	"step": 397
	},
	{
	"epoch": 0.12945194340543179,
	"grad_norm": 11.901144027709961,
	"learning_rate": 5e-05,
	"loss": 3.7524,
	"step": 398
	},
	{
	"epoch": 0.1297771995446414,
	"grad_norm": 9.584845542907715,
	"learning_rate": 5e-05,
	"loss": 3.4015,
	"step": 399
	},
	{
	"epoch": 0.13010245568385104,
	"grad_norm": 12.348978042602539,
	"learning_rate": 5e-05,
	"loss": 3.6966,
	"step": 400
	},
	{
	"epoch": 0.13042771182306065,
	"grad_norm": 12.886831283569336,
	"learning_rate": 5e-05,
	"loss": 4.5981,
	"step": 401
	},
	{
	"epoch": 0.1307529679622703,
	"grad_norm": 7.066255569458008,
	"learning_rate": 5e-05,
	"loss": 3.6408,
	"step": 402
	},
	{
	"epoch": 0.13107822410147993,
	"grad_norm": 7.1310014724731445,
	"learning_rate": 5e-05,
	"loss": 3.7652,
	"step": 403
	},
	{
	"epoch": 0.13140348024068954,
	"grad_norm": 7.658654689788818,
	"learning_rate": 5e-05,
	"loss": 3.9908,
	"step": 404
	},
	{
	"epoch": 0.13172873637989918,
	"grad_norm": 9.139669418334961,
	"learning_rate": 5e-05,
	"loss": 3.7055,
	"step": 405
	},
	{
	"epoch": 0.1320539925191088,
	"grad_norm": 7.406591892242432,
	"learning_rate": 5e-05,
	"loss": 3.9435,
	"step": 406
	},
	{
	"epoch": 0.13237924865831843,
	"grad_norm": 7.888886451721191,
	"learning_rate": 5e-05,
	"loss": 3.7047,
	"step": 407
	},
	{
	"epoch": 0.13270450479752804,
	"grad_norm": 6.58457088470459,
	"learning_rate": 5e-05,
	"loss": 3.5882,
	"step": 408
	},
	{
	"epoch": 0.13302976093673768,
	"grad_norm": 6.361485958099365,
	"learning_rate": 5e-05,
	"loss": 3.6571,
	"step": 409
	},
	{
	"epoch": 0.1333550170759473,
	"grad_norm": 10.977415084838867,
	"learning_rate": 5e-05,
	"loss": 3.9192,
	"step": 410
	},
	{
	"epoch": 0.13368027321515694,
	"grad_norm": 8.509581565856934,
	"learning_rate": 5e-05,
	"loss": 3.7566,
	"step": 411
	},
	{
	"epoch": 0.13400552935436658,
	"grad_norm": 7.781307220458984,
	"learning_rate": 5e-05,
	"loss": 4.1816,
	"step": 412
	},
	{
	"epoch": 0.1343307854935762,
	"grad_norm": 7.275979518890381,
	"learning_rate": 5e-05,
	"loss": 3.2031,
	"step": 413
	},
	{
	"epoch": 0.13465604163278583,
	"grad_norm": 7.543152332305908,
	"learning_rate": 5e-05,
	"loss": 3.9525,
	"step": 414
	},
	{
	"epoch": 0.13498129777199544,
	"grad_norm": 9.093851089477539,
	"learning_rate": 5e-05,
	"loss": 3.9126,
	"step": 415
	},
	{
	"epoch": 0.13530655391120508,
	"grad_norm": 12.760071754455566,
	"learning_rate": 5e-05,
	"loss": 3.7383,
	"step": 416
	},
	{
	"epoch": 0.1356318100504147,
	"grad_norm": 8.025795936584473,
	"learning_rate": 5e-05,
	"loss": 3.5959,
	"step": 417
	},
	{
	"epoch": 0.13595706618962433,
	"grad_norm": 7.363426685333252,
	"learning_rate": 5e-05,
	"loss": 3.7238,
	"step": 418
	},
	{
	"epoch": 0.13628232232883394,
	"grad_norm": 8.554017066955566,
	"learning_rate": 5e-05,
	"loss": 3.3142,
	"step": 419
	},
	{
	"epoch": 0.13660757846804358,
	"grad_norm": 7.679929256439209,
	"learning_rate": 5e-05,
	"loss": 3.6632,
	"step": 420
	},
	{
	"epoch": 0.13693283460725322,
	"grad_norm": 7.977594375610352,
	"learning_rate": 5e-05,
	"loss": 3.3469,
	"step": 421
	},
	{
	"epoch": 0.13725809074646284,
	"grad_norm": 7.612384796142578,
	"learning_rate": 5e-05,
	"loss": 3.6385,
	"step": 422
	},
	{
	"epoch": 0.13758334688567248,
	"grad_norm": 9.067974090576172,
	"learning_rate": 5e-05,
	"loss": 3.7935,
	"step": 423
	},
	{
	"epoch": 0.1379086030248821,
	"grad_norm": 9.513571739196777,
	"learning_rate": 5e-05,
	"loss": 4.0498,
	"step": 424
	},
	{
	"epoch": 0.13823385916409173,
	"grad_norm": 10.234723091125488,
	"learning_rate": 5e-05,
	"loss": 3.9196,
	"step": 425
	},
	{
	"epoch": 0.13855911530330134,
	"grad_norm": 8.635189056396484,
	"learning_rate": 5e-05,
	"loss": 3.8482,
	"step": 426
	},
	{
	"epoch": 0.13888437144251098,
	"grad_norm": 10.970733642578125,
	"learning_rate": 5e-05,
	"loss": 3.765,
	"step": 427
	},
	{
	"epoch": 0.13920962758172062,
	"grad_norm": 9.9661226272583,
	"learning_rate": 5e-05,
	"loss": 3.939,
	"step": 428
	},
	{
	"epoch": 0.13953488372093023,
	"grad_norm": 9.381548881530762,
	"learning_rate": 5e-05,
	"loss": 3.749,
	"step": 429
	},
	{
	"epoch": 0.13986013986013987,
	"grad_norm": 8.287264823913574,
	"learning_rate": 5e-05,
	"loss": 3.7818,
	"step": 430
	},
	{
	"epoch": 0.14018539599934948,
	"grad_norm": 8.97390365600586,
	"learning_rate": 5e-05,
	"loss": 4.0317,
	"step": 431
	},
	{
	"epoch": 0.14051065213855912,
	"grad_norm": 7.877195835113525,
	"learning_rate": 5e-05,
	"loss": 3.5584,
	"step": 432
	},
	{
	"epoch": 0.14083590827776873,
	"grad_norm": 9.581697463989258,
	"learning_rate": 5e-05,
	"loss": 3.4095,
	"step": 433
	},
	{
	"epoch": 0.14116116441697837,
	"grad_norm": 17.695627212524414,
	"learning_rate": 5e-05,
	"loss": 4.3531,
	"step": 434
	},
	{
	"epoch": 0.141486420556188,
	"grad_norm": 8.333785057067871,
	"learning_rate": 5e-05,
	"loss": 3.3827,
	"step": 435
	},
	{
	"epoch": 0.14181167669539763,
	"grad_norm": 7.970407009124756,
	"learning_rate": 5e-05,
	"loss": 3.5483,
	"step": 436
	},
	{
	"epoch": 0.14213693283460727,
	"grad_norm": 9.061053276062012,
	"learning_rate": 5e-05,
	"loss": 3.7439,
	"step": 437
	},
	{
	"epoch": 0.14246218897381688,
	"grad_norm": 6.50039005279541,
	"learning_rate": 5e-05,
	"loss": 3.9181,
	"step": 438
	},
	{
	"epoch": 0.14278744511302652,
	"grad_norm": 9.928549766540527,
	"learning_rate": 5e-05,
	"loss": 3.5832,
	"step": 439
	},
	{
	"epoch": 0.14311270125223613,
	"grad_norm": 12.250447273254395,
	"learning_rate": 5e-05,
	"loss": 3.4639,
	"step": 440
	},
	{
	"epoch": 0.14343795739144577,
	"grad_norm": 8.427464485168457,
	"learning_rate": 5e-05,
	"loss": 3.4289,
	"step": 441
	},
	{
	"epoch": 0.14376321353065538,
	"grad_norm": 12.150249481201172,
	"learning_rate": 5e-05,
	"loss": 3.8382,
	"step": 442
	},
	{
	"epoch": 0.14408846966986502,
	"grad_norm": 7.406175136566162,
	"learning_rate": 5e-05,
	"loss": 3.9814,
	"step": 443
	},
	{
	"epoch": 0.14441372580907463,
	"grad_norm": 6.988471031188965,
	"learning_rate": 5e-05,
	"loss": 4.0547,
	"step": 444
	},
	{
	"epoch": 0.14473898194828427,
	"grad_norm": 12.318148612976074,
	"learning_rate": 5e-05,
	"loss": 3.9433,
	"step": 445
	},
	{
	"epoch": 0.1450642380874939,
	"grad_norm": 10.347890853881836,
	"learning_rate": 5e-05,
	"loss": 3.7052,
	"step": 446
	},
	{
	"epoch": 0.14538949422670353,
	"grad_norm": 9.213937759399414,
	"learning_rate": 5e-05,
	"loss": 3.9906,
	"step": 447
	},
	{
	"epoch": 0.14571475036591316,
	"grad_norm": 10.614618301391602,
	"learning_rate": 5e-05,
	"loss": 3.276,
	"step": 448
	},
	{
	"epoch": 0.14604000650512278,
	"grad_norm": 11.268338203430176,
	"learning_rate": 5e-05,
	"loss": 3.5563,
	"step": 449
	},
	{
	"epoch": 0.14636526264433242,
	"grad_norm": 8.418384552001953,
	"learning_rate": 5e-05,
	"loss": 3.4222,
	"step": 450
	},
	{
	"epoch": 0.14669051878354203,
	"grad_norm": 12.904454231262207,
	"learning_rate": 5e-05,
	"loss": 3.7737,
	"step": 451
	},
	{
	"epoch": 0.14701577492275167,
	"grad_norm": 9.767146110534668,
	"learning_rate": 5e-05,
	"loss": 4.0424,
	"step": 452
	},
	{
	"epoch": 0.1473410310619613,
	"grad_norm": 8.333344459533691,
	"learning_rate": 5e-05,
	"loss": 3.7574,
	"step": 453
	},
	{
	"epoch": 0.14766628720117092,
	"grad_norm": 11.907800674438477,
	"learning_rate": 5e-05,
	"loss": 3.7266,
	"step": 454
	},
	{
	"epoch": 0.14799154334038056,
	"grad_norm": 9.306441307067871,
	"learning_rate": 5e-05,
	"loss": 3.8885,
	"step": 455
	},
	{
	"epoch": 0.14831679947959017,
	"grad_norm": 10.486589431762695,
	"learning_rate": 5e-05,
	"loss": 3.7777,
	"step": 456
	},
	{
	"epoch": 0.1486420556187998,
	"grad_norm": 12.291946411132812,
	"learning_rate": 5e-05,
	"loss": 3.6718,
	"step": 457
	},
	{
	"epoch": 0.14896731175800942,
	"grad_norm": 12.743392944335938,
	"learning_rate": 5e-05,
	"loss": 3.6533,
	"step": 458
	},
	{
	"epoch": 0.14929256789721906,
	"grad_norm": 9.82790470123291,
	"learning_rate": 5e-05,
	"loss": 3.8719,
	"step": 459
	},
	{
	"epoch": 0.14961782403642868,
	"grad_norm": 11.749984741210938,
	"learning_rate": 5e-05,
	"loss": 3.495,
	"step": 460
	},
	{
	"epoch": 0.14994308017563832,
	"grad_norm": 11.35322380065918,
	"learning_rate": 5e-05,
	"loss": 4.0119,
	"step": 461
	},
	{
	"epoch": 0.15026833631484796,
	"grad_norm": 7.1181159019470215,
	"learning_rate": 5e-05,
	"loss": 3.6675,
	"step": 462
	},
	{
	"epoch": 0.15059359245405757,
	"grad_norm": 11.3037109375,
	"learning_rate": 5e-05,
	"loss": 3.5125,
	"step": 463
	},
	{
	"epoch": 0.1509188485932672,
	"grad_norm": 10.003439903259277,
	"learning_rate": 5e-05,
	"loss": 3.2109,
	"step": 464
	},
	{
	"epoch": 0.15124410473247682,
	"grad_norm": 7.561882019042969,
	"learning_rate": 5e-05,
	"loss": 3.566,
	"step": 465
	},
	{
	"epoch": 0.15156936087168646,
	"grad_norm": 7.8044586181640625,
	"learning_rate": 5e-05,
	"loss": 3.5393,
	"step": 466
	},
	{
	"epoch": 0.15189461701089607,
	"grad_norm": 11.766450881958008,
	"learning_rate": 5e-05,
	"loss": 3.7168,
	"step": 467
	},
	{
	"epoch": 0.1522198731501057,
	"grad_norm": 7.827965259552002,
	"learning_rate": 5e-05,
	"loss": 3.7292,
	"step": 468
	},
	{
	"epoch": 0.15254512928931532,
	"grad_norm": 9.4542236328125,
	"learning_rate": 5e-05,
	"loss": 3.4709,
	"step": 469
	},
	{
	"epoch": 0.15287038542852496,
	"grad_norm": 8.595137596130371,
	"learning_rate": 5e-05,
	"loss": 4.3444,
	"step": 470
	},
	{
	"epoch": 0.1531956415677346,
	"grad_norm": 8.952139854431152,
	"learning_rate": 5e-05,
	"loss": 4.3924,
	"step": 471
	},
	{
	"epoch": 0.15352089770694421,
	"grad_norm": 9.41843318939209,
	"learning_rate": 5e-05,
	"loss": 3.7794,
	"step": 472
	},
	{
	"epoch": 0.15384615384615385,
	"grad_norm": 7.201237201690674,
	"learning_rate": 5e-05,
	"loss": 3.3527,
	"step": 473
	},
	{
	"epoch": 0.15417140998536347,
	"grad_norm": 9.496088981628418,
	"learning_rate": 5e-05,
	"loss": 3.3554,
	"step": 474
	},
	{
	"epoch": 0.1544966661245731,
	"grad_norm": 8.370413780212402,
	"learning_rate": 5e-05,
	"loss": 3.8943,
	"step": 475
	},
	{
	"epoch": 0.15482192226378272,
	"grad_norm": 8.910099029541016,
	"learning_rate": 5e-05,
	"loss": 3.5867,
	"step": 476
	},
	{
	"epoch": 0.15514717840299236,
	"grad_norm": 7.085155963897705,
	"learning_rate": 5e-05,
	"loss": 3.3267,
	"step": 477
	},
	{
	"epoch": 0.15547243454220197,
	"grad_norm": 8.49357795715332,
	"learning_rate": 5e-05,
	"loss": 3.5925,
	"step": 478
	},
	{
	"epoch": 0.1557976906814116,
	"grad_norm": 7.811654567718506,
	"learning_rate": 5e-05,
	"loss": 3.9464,
	"step": 479
	},
	{
	"epoch": 0.15612294682062125,
	"grad_norm": 9.111326217651367,
	"learning_rate": 5e-05,
	"loss": 3.5547,
	"step": 480
	},
	{
	"epoch": 0.15644820295983086,
	"grad_norm": 7.44144344329834,
	"learning_rate": 5e-05,
	"loss": 3.9226,
	"step": 481
	},
	{
	"epoch": 0.1567734590990405,
	"grad_norm": 9.64633846282959,
	"learning_rate": 5e-05,
	"loss": 3.887,
	"step": 482
	},
	{
	"epoch": 0.15709871523825011,
	"grad_norm": 11.60362720489502,
	"learning_rate": 5e-05,
	"loss": 3.7125,
	"step": 483
	},
	{
	"epoch": 0.15742397137745975,
	"grad_norm": 7.746142864227295,
	"learning_rate": 5e-05,
	"loss": 3.9722,
	"step": 484
	},
	{
	"epoch": 0.15774922751666937,
	"grad_norm": 7.080160140991211,
	"learning_rate": 5e-05,
	"loss": 3.1951,
	"step": 485
	},
	{
	"epoch": 0.158074483655879,
	"grad_norm": 17.081741333007812,
	"learning_rate": 5e-05,
	"loss": 3.7901,
	"step": 486
	},
	{
	"epoch": 0.15839973979508865,
	"grad_norm": 7.917695999145508,
	"learning_rate": 5e-05,
	"loss": 3.5357,
	"step": 487
	},
	{
	"epoch": 0.15872499593429826,
	"grad_norm": 8.854647636413574,
	"learning_rate": 5e-05,
	"loss": 3.7515,
	"step": 488
	},
	{
	"epoch": 0.1590502520735079,
	"grad_norm": 9.028191566467285,
	"learning_rate": 5e-05,
	"loss": 3.5516,
	"step": 489
	},
	{
	"epoch": 0.1593755082127175,
	"grad_norm": 10.008574485778809,
	"learning_rate": 5e-05,
	"loss": 3.6189,
	"step": 490
	},
	{
	"epoch": 0.15970076435192715,
	"grad_norm": 10.596325874328613,
	"learning_rate": 5e-05,
	"loss": 3.4306,
	"step": 491
	},
	{
	"epoch": 0.16002602049113676,
	"grad_norm": 12.258661270141602,
	"learning_rate": 5e-05,
	"loss": 3.5577,
	"step": 492
	},
	{
	"epoch": 0.1603512766303464,
	"grad_norm": 11.506673812866211,
	"learning_rate": 5e-05,
	"loss": 3.9079,
	"step": 493
	},
	{
	"epoch": 0.160676532769556,
	"grad_norm": 7.967488765716553,
	"learning_rate": 5e-05,
	"loss": 3.6066,
	"step": 494
	},
	{
	"epoch": 0.16100178890876565,
	"grad_norm": 11.729570388793945,
	"learning_rate": 5e-05,
	"loss": 3.9043,
	"step": 495
	},
	{
	"epoch": 0.1613270450479753,
	"grad_norm": 8.846243858337402,
	"learning_rate": 5e-05,
	"loss": 3.8228,
	"step": 496
	},
	{
	"epoch": 0.1616523011871849,
	"grad_norm": 12.016153335571289,
	"learning_rate": 5e-05,
	"loss": 3.9159,
	"step": 497
	},
	{
	"epoch": 0.16197755732639454,
	"grad_norm": 8.154533386230469,
	"learning_rate": 5e-05,
	"loss": 3.7158,
	"step": 498
	},
	{
	"epoch": 0.16230281346560416,
	"grad_norm": 11.766820907592773,
	"learning_rate": 5e-05,
	"loss": 3.5189,
	"step": 499
	},
	{
	"epoch": 0.1626280696048138,
	"grad_norm": 11.467671394348145,
	"learning_rate": 5e-05,
	"loss": 3.8887,
	"step": 500
	},
	{
	"epoch": 0.1629533257440234,
	"grad_norm": 7.477685451507568,
	"learning_rate": 5e-05,
	"loss": 4.0159,
	"step": 501
	},
	{
	"epoch": 0.16327858188323305,
	"grad_norm": 6.95028018951416,
	"learning_rate": 5e-05,
	"loss": 3.7446,
	"step": 502
	},
	{
	"epoch": 0.16360383802244266,
	"grad_norm": 11.298054695129395,
	"learning_rate": 5e-05,
	"loss": 3.692,
	"step": 503
	},
	{
	"epoch": 0.1639290941616523,
	"grad_norm": 7.807789325714111,
	"learning_rate": 5e-05,
	"loss": 3.6819,
	"step": 504
	},
	{
	"epoch": 0.16425435030086194,
	"grad_norm": 7.94120454788208,
	"learning_rate": 5e-05,
	"loss": 3.6853,
	"step": 505
	},
	{
	"epoch": 0.16457960644007155,
	"grad_norm": 8.74360466003418,
	"learning_rate": 5e-05,
	"loss": 3.5674,
	"step": 506
	},
	{
	"epoch": 0.1649048625792812,
	"grad_norm": 8.877306938171387,
	"learning_rate": 5e-05,
	"loss": 3.5393,
	"step": 507
	},
	{
	"epoch": 0.1652301187184908,
	"grad_norm": 7.502864837646484,
	"learning_rate": 5e-05,
	"loss": 3.6376,
	"step": 508
	},
	{
	"epoch": 0.16555537485770044,
	"grad_norm": 11.325250625610352,
	"learning_rate": 5e-05,
	"loss": 3.7114,
	"step": 509
	},
	{
	"epoch": 0.16588063099691006,
	"grad_norm": 9.918580055236816,
	"learning_rate": 5e-05,
	"loss": 3.783,
	"step": 510
	},
	{
	"epoch": 0.1662058871361197,
	"grad_norm": 8.940899848937988,
	"learning_rate": 5e-05,
	"loss": 3.707,
	"step": 511
	},
	{
	"epoch": 0.16653114327532934,
	"grad_norm": 17.020418167114258,
	"learning_rate": 5e-05,
	"loss": 4.319,
	"step": 512
	},
	{
	"epoch": 0.16685639941453895,
	"grad_norm": 10.722935676574707,
	"learning_rate": 5e-05,
	"loss": 3.4215,
	"step": 513
	},
	{
	"epoch": 0.1671816555537486,
	"grad_norm": 9.579489707946777,
	"learning_rate": 5e-05,
	"loss": 2.835,
	"step": 514
	},
	{
	"epoch": 0.1675069116929582,
	"grad_norm": 8.158295631408691,
	"learning_rate": 5e-05,
	"loss": 2.78,
	"step": 515
	},
	{
	"epoch": 0.16783216783216784,
	"grad_norm": 8.238765716552734,
	"learning_rate": 5e-05,
	"loss": 3.4628,
	"step": 516
	},
	{
	"epoch": 0.16815742397137745,
	"grad_norm": 8.580034255981445,
	"learning_rate": 5e-05,
	"loss": 3.9686,
	"step": 517
	},
	{
	"epoch": 0.1684826801105871,
	"grad_norm": 8.966435432434082,
	"learning_rate": 5e-05,
	"loss": 3.4936,
	"step": 518
	},
	{
	"epoch": 0.1688079362497967,
	"grad_norm": 6.970677375793457,
	"learning_rate": 5e-05,
	"loss": 3.4287,
	"step": 519
	},
	{
	"epoch": 0.16913319238900634,
	"grad_norm": 7.750168323516846,
	"learning_rate": 5e-05,
	"loss": 3.3396,
	"step": 520
	},
	{
	"epoch": 0.16945844852821598,
	"grad_norm": 7.394572734832764,
	"learning_rate": 5e-05,
	"loss": 3.6622,
	"step": 521
	},
	{
	"epoch": 0.1697837046674256,
	"grad_norm": 6.781547546386719,
	"learning_rate": 5e-05,
	"loss": 3.5704,
	"step": 522
	},
	{
	"epoch": 0.17010896080663523,
	"grad_norm": 11.887150764465332,
	"learning_rate": 5e-05,
	"loss": 3.4968,
	"step": 523
	},
	{
	"epoch": 0.17043421694584485,
	"grad_norm": 7.665548324584961,
	"learning_rate": 5e-05,
	"loss": 3.6475,
	"step": 524
	},
	{
	"epoch": 0.1707594730850545,
	"grad_norm": 8.977829933166504,
	"learning_rate": 5e-05,
	"loss": 2.6397,
	"step": 525
	},
	{
	"epoch": 0.1710847292242641,
	"grad_norm": 9.76028060913086,
	"learning_rate": 5e-05,
	"loss": 3.6625,
	"step": 526
	},
	{
	"epoch": 0.17140998536347374,
	"grad_norm": 9.248437881469727,
	"learning_rate": 5e-05,
	"loss": 3.5199,
	"step": 527
	},
	{
	"epoch": 0.17173524150268335,
	"grad_norm": 9.724522590637207,
	"learning_rate": 5e-05,
	"loss": 3.7095,
	"step": 528
	},
	{
	"epoch": 0.172060497641893,
	"grad_norm": 8.21666431427002,
	"learning_rate": 5e-05,
	"loss": 3.6802,
	"step": 529
	},
	{
	"epoch": 0.17238575378110263,
	"grad_norm": 7.362802505493164,
	"learning_rate": 5e-05,
	"loss": 3.6511,
	"step": 530
	},
	{
	"epoch": 0.17271100992031224,
	"grad_norm": 7.2599334716796875,
	"learning_rate": 5e-05,
	"loss": 3.1097,
	"step": 531
	},
	{
	"epoch": 0.17303626605952188,
	"grad_norm": 9.250597953796387,
	"learning_rate": 5e-05,
	"loss": 3.608,
	"step": 532
	},
	{
	"epoch": 0.1733615221987315,
	"grad_norm": 8.88681411743164,
	"learning_rate": 5e-05,
	"loss": 3.8212,
	"step": 533
	},
	{
	"epoch": 0.17368677833794113,
	"grad_norm": 11.290247917175293,
	"learning_rate": 5e-05,
	"loss": 3.3286,
	"step": 534
	},
	{
	"epoch": 0.17401203447715075,
	"grad_norm": 10.88404369354248,
	"learning_rate": 5e-05,
	"loss": 3.5241,
	"step": 535
	},
	{
	"epoch": 0.17433729061636039,
	"grad_norm": 9.20648193359375,
	"learning_rate": 5e-05,
	"loss": 3.6005,
	"step": 536
	},
	{
	"epoch": 0.17466254675557003,
	"grad_norm": 8.10119342803955,
	"learning_rate": 5e-05,
	"loss": 3.5739,
	"step": 537
	},
	{
	"epoch": 0.17498780289477964,
	"grad_norm": 10.661712646484375,
	"learning_rate": 5e-05,
	"loss": 3.4837,
	"step": 538
	},
	{
	"epoch": 0.17531305903398928,
	"grad_norm": 10.739490509033203,
	"learning_rate": 5e-05,
	"loss": 3.6787,
	"step": 539
	},
	{
	"epoch": 0.1756383151731989,
	"grad_norm": 9.183284759521484,
	"learning_rate": 5e-05,
	"loss": 3.6174,
	"step": 540
	},
	{
	"epoch": 0.17596357131240853,
	"grad_norm": 8.37816047668457,
	"learning_rate": 5e-05,
	"loss": 3.5964,
	"step": 541
	},
	{
	"epoch": 0.17628882745161814,
	"grad_norm": 10.69176959991455,
	"learning_rate": 5e-05,
	"loss": 3.8804,
	"step": 542
	},
	{
	"epoch": 0.17661408359082778,
	"grad_norm": 8.007463455200195,
	"learning_rate": 5e-05,
	"loss": 3.8485,
	"step": 543
	},
	{
	"epoch": 0.1769393397300374,
	"grad_norm": 8.839487075805664,
	"learning_rate": 5e-05,
	"loss": 3.6356,
	"step": 544
	},
	{
	"epoch": 0.17726459586924703,
	"grad_norm": 11.773893356323242,
	"learning_rate": 5e-05,
	"loss": 3.8846,
	"step": 545
	},
	{
	"epoch": 0.17758985200845667,
	"grad_norm": 11.021324157714844,
	"learning_rate": 5e-05,
	"loss": 3.8369,
	"step": 546
	},
	{
	"epoch": 0.17791510814766628,
	"grad_norm": 10.33259391784668,
	"learning_rate": 5e-05,
	"loss": 3.392,
	"step": 547
	},
	{
	"epoch": 0.17824036428687592,
	"grad_norm": 8.52408504486084,
	"learning_rate": 5e-05,
	"loss": 3.8102,
	"step": 548
	},
	{
	"epoch": 0.17856562042608554,
	"grad_norm": 9.792526245117188,
	"learning_rate": 5e-05,
	"loss": 3.9087,
	"step": 549
	},
	{
	"epoch": 0.17889087656529518,
	"grad_norm": 9.989365577697754,
	"learning_rate": 5e-05,
	"loss": 3.8268,
	"step": 550
	},
	{
	"epoch": 0.1792161327045048,
	"grad_norm": 9.42458438873291,
	"learning_rate": 5e-05,
	"loss": 3.7863,
	"step": 551
	},
	{
	"epoch": 0.17954138884371443,
	"grad_norm": 8.195592880249023,
	"learning_rate": 5e-05,
	"loss": 3.7507,
	"step": 552
	},
	{
	"epoch": 0.17986664498292404,
	"grad_norm": 9.999628067016602,
	"learning_rate": 5e-05,
	"loss": 3.742,
	"step": 553
	},
	{
	"epoch": 0.18019190112213368,
	"grad_norm": 8.54041576385498,
	"learning_rate": 5e-05,
	"loss": 4.4209,
	"step": 554
	},
	{
	"epoch": 0.18051715726134332,
	"grad_norm": 8.870122909545898,
	"learning_rate": 5e-05,
	"loss": 3.2489,
	"step": 555
	},
	{
	"epoch": 0.18084241340055293,
	"grad_norm": 10.103729248046875,
	"learning_rate": 5e-05,
	"loss": 3.5182,
	"step": 556
	},
	{
	"epoch": 0.18116766953976257,
	"grad_norm": 9.698139190673828,
	"learning_rate": 5e-05,
	"loss": 3.7934,
	"step": 557
	},
	{
	"epoch": 0.18149292567897218,
	"grad_norm": 9.132758140563965,
	"learning_rate": 5e-05,
	"loss": 3.3561,
	"step": 558
	},
	{
	"epoch": 0.18181818181818182,
	"grad_norm": 8.661752700805664,
	"learning_rate": 5e-05,
	"loss": 3.5775,
	"step": 559
	},
	{
	"epoch": 0.18214343795739144,
	"grad_norm": 9.332806587219238,
	"learning_rate": 5e-05,
	"loss": 3.0548,
	"step": 560
	},
	{
	"epoch": 0.18246869409660108,
	"grad_norm": 9.24280071258545,
	"learning_rate": 5e-05,
	"loss": 4.0208,
	"step": 561
	},
	{
	"epoch": 0.1827939502358107,
	"grad_norm": 9.924572944641113,
	"learning_rate": 5e-05,
	"loss": 3.6914,
	"step": 562
	},
	{
	"epoch": 0.18311920637502033,
	"grad_norm": 9.362936973571777,
	"learning_rate": 5e-05,
	"loss": 3.9219,
	"step": 563
	},
	{
	"epoch": 0.18344446251422997,
	"grad_norm": 12.603287696838379,
	"learning_rate": 5e-05,
	"loss": 3.4585,
	"step": 564
	},
	{
	"epoch": 0.18376971865343958,
	"grad_norm": 10.904036521911621,
	"learning_rate": 5e-05,
	"loss": 3.3266,
	"step": 565
	},
	{
	"epoch": 0.18409497479264922,
	"grad_norm": 9.598895072937012,
	"learning_rate": 5e-05,
	"loss": 3.6607,
	"step": 566
	},
	{
	"epoch": 0.18442023093185883,
	"grad_norm": 8.842279434204102,
	"learning_rate": 5e-05,
	"loss": 3.5674,
	"step": 567
	},
	{
	"epoch": 0.18474548707106847,
	"grad_norm": 9.379899024963379,
	"learning_rate": 5e-05,
	"loss": 3.6743,
	"step": 568
	},
	{
	"epoch": 0.18507074321027808,
	"grad_norm": 9.745834350585938,
	"learning_rate": 5e-05,
	"loss": 4.0652,
	"step": 569
	},
	{
	"epoch": 0.18539599934948772,
	"grad_norm": 8.990086555480957,
	"learning_rate": 5e-05,
	"loss": 3.637,
	"step": 570
	},
	{
	"epoch": 0.18572125548869736,
	"grad_norm": 8.382301330566406,
	"learning_rate": 5e-05,
	"loss": 3.967,
	"step": 571
	},
	{
	"epoch": 0.18604651162790697,
	"grad_norm": 8.533965110778809,
	"learning_rate": 5e-05,
	"loss": 3.4941,
	"step": 572
	},
	{
	"epoch": 0.18637176776711661,
	"grad_norm": 9.823786735534668,
	"learning_rate": 5e-05,
	"loss": 3.7345,
	"step": 573
	},
	{
	"epoch": 0.18669702390632623,
	"grad_norm": 7.766260147094727,
	"learning_rate": 5e-05,
	"loss": 3.6831,
	"step": 574
	},
	{
	"epoch": 0.18702228004553587,
	"grad_norm": 8.095032691955566,
	"learning_rate": 5e-05,
	"loss": 3.4701,
	"step": 575
	},
	{
	"epoch": 0.18734753618474548,
	"grad_norm": 11.641885757446289,
	"learning_rate": 5e-05,
	"loss": 4.0934,
	"step": 576
	},
	{
	"epoch": 0.18767279232395512,
	"grad_norm": 9.155062675476074,
	"learning_rate": 5e-05,
	"loss": 3.5356,
	"step": 577
	},
	{
	"epoch": 0.18799804846316473,
	"grad_norm": 8.703105926513672,
	"learning_rate": 5e-05,
	"loss": 3.8144,
	"step": 578
	},
	{
	"epoch": 0.18832330460237437,
	"grad_norm": 9.528350830078125,
	"learning_rate": 5e-05,
	"loss": 3.2073,
	"step": 579
	},
	{
	"epoch": 0.188648560741584,
	"grad_norm": 9.156220436096191,
	"learning_rate": 5e-05,
	"loss": 3.777,
	"step": 580
	},
	{
	"epoch": 0.18897381688079362,
	"grad_norm": 8.443305015563965,
	"learning_rate": 5e-05,
	"loss": 3.7239,
	"step": 581
	},
	{
	"epoch": 0.18929907302000326,
	"grad_norm": 7.838225841522217,
	"learning_rate": 5e-05,
	"loss": 3.4467,
	"step": 582
	},
	{
	"epoch": 0.18962432915921287,
	"grad_norm": 7.3834757804870605,
	"learning_rate": 5e-05,
	"loss": 3.5151,
	"step": 583
	},
	{
	"epoch": 0.1899495852984225,
	"grad_norm": 9.460673332214355,
	"learning_rate": 5e-05,
	"loss": 3.4287,
	"step": 584
	},
	{
	"epoch": 0.19027484143763213,
	"grad_norm": 8.232035636901855,
	"learning_rate": 5e-05,
	"loss": 4.2533,
	"step": 585
	},
	{
	"epoch": 0.19060009757684176,
	"grad_norm": 12.586129188537598,
	"learning_rate": 5e-05,
	"loss": 3.7747,
	"step": 586
	},
	{
	"epoch": 0.19092535371605138,
	"grad_norm": 8.150300979614258,
	"learning_rate": 5e-05,
	"loss": 3.9724,
	"step": 587
	},
	{
	"epoch": 0.19125060985526102,
	"grad_norm": 8.529426574707031,
	"learning_rate": 5e-05,
	"loss": 4.6377,
	"step": 588
	},
	{
	"epoch": 0.19157586599447066,
	"grad_norm": 7.794090747833252,
	"learning_rate": 5e-05,
	"loss": 3.2597,
	"step": 589
	},
	{
	"epoch": 0.19190112213368027,
	"grad_norm": 8.038799285888672,
	"learning_rate": 5e-05,
	"loss": 3.9826,
	"step": 590
	},
	{
	"epoch": 0.1922263782728899,
	"grad_norm": 7.855754852294922,
	"learning_rate": 5e-05,
	"loss": 3.7777,
	"step": 591
	},
	{
	"epoch": 0.19255163441209952,
	"grad_norm": 8.140380859375,
	"learning_rate": 5e-05,
	"loss": 3.443,
	"step": 592
	},
	{
	"epoch": 0.19287689055130916,
	"grad_norm": 9.79352855682373,
	"learning_rate": 5e-05,
	"loss": 3.7066,
	"step": 593
	},
	{
	"epoch": 0.19320214669051877,
	"grad_norm": 13.119344711303711,
	"learning_rate": 5e-05,
	"loss": 3.9336,
	"step": 594
	},
	{
	"epoch": 0.1935274028297284,
	"grad_norm": 8.955309867858887,
	"learning_rate": 5e-05,
	"loss": 3.3643,
	"step": 595
	},
	{
	"epoch": 0.19385265896893805,
	"grad_norm": 8.016314506530762,
	"learning_rate": 5e-05,
	"loss": 3.7039,
	"step": 596
	},
	{
	"epoch": 0.19417791510814766,
	"grad_norm": 8.888792991638184,
	"learning_rate": 5e-05,
	"loss": 3.6356,
	"step": 597
	},
	{
	"epoch": 0.1945031712473573,
	"grad_norm": 9.017245292663574,
	"learning_rate": 5e-05,
	"loss": 3.6173,
	"step": 598
	},
	{
	"epoch": 0.19482842738656692,
	"grad_norm": 9.05187702178955,
	"learning_rate": 5e-05,
	"loss": 3.7156,
	"step": 599
	},
	{
	"epoch": 0.19515368352577656,
	"grad_norm": 8.980157852172852,
	"learning_rate": 5e-05,
	"loss": 3.5519,
	"step": 600
	}
	],
	"logging_steps": 1,
	"max_steps": 1000,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 1,
	"save_steps": 200,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": false
	},
	"attributes": {}
	}
	},
	"total_flos": 2792420391095808.0,
	"train_batch_size": 2,
	"trial_name": null,
	"trial_params": null
	}