Instructions to use furproxy/9b-70 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use furproxy/9b-70 with Transformers:

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

pipe = pipeline("image-text-to-text", model="furproxy/9b-70")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("furproxy/9b-70")
model = AutoModelForImageTextToText.from_pretrained("furproxy/9b-70")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use furproxy/9b-70 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "furproxy/9b-70"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "furproxy/9b-70",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/furproxy/9b-70

SGLang

How to use furproxy/9b-70 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 "furproxy/9b-70" \
    --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": "furproxy/9b-70",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "furproxy/9b-70" \
        --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": "furproxy/9b-70",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use furproxy/9b-70 with Docker Model Runner:
```
docker model run hf.co/furproxy/9b-70
```

9b-70 / trainer_state.json

furproxy

Upload folder using huggingface_hub

042ed7b verified about 2 months ago

raw

history blame contribute delete

94 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 4.0,
	"eval_steps": 500,
	"global_step": 1004,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.00796812749003984,
	"grad_norm": 0.8687085509300232,
	"learning_rate": 3.921568627450981e-07,
	"loss": 2.0886306762695312,
	"step": 2
	},
	{
	"epoch": 0.01593625498007968,
	"grad_norm": 0.8256942629814148,
	"learning_rate": 1.1764705882352942e-06,
	"loss": 2.0069615840911865,
	"step": 4
	},
	{
	"epoch": 0.02390438247011952,
	"grad_norm": 7.175477027893066,
	"learning_rate": 1.96078431372549e-06,
	"loss": 2.1241238117218018,
	"step": 6
	},
	{
	"epoch": 0.03187250996015936,
	"grad_norm": 0.5740149617195129,
	"learning_rate": 2.7450980392156867e-06,
	"loss": 1.8192579746246338,
	"step": 8
	},
	{
	"epoch": 0.0398406374501992,
	"grad_norm": 0.9182372093200684,
	"learning_rate": 3.529411764705883e-06,
	"loss": 1.282393455505371,
	"step": 10
	},
	{
	"epoch": 0.04780876494023904,
	"grad_norm": 0.5668178796768188,
	"learning_rate": 4.313725490196079e-06,
	"loss": 1.586937665939331,
	"step": 12
	},
	{
	"epoch": 0.055776892430278883,
	"grad_norm": 0.509973406791687,
	"learning_rate": 5.098039215686274e-06,
	"loss": 1.6420693397521973,
	"step": 14
	},
	{
	"epoch": 0.06374501992031872,
	"grad_norm": 8.057994842529297,
	"learning_rate": 5.882352941176471e-06,
	"loss": 1.7643235921859741,
	"step": 16
	},
	{
	"epoch": 0.07171314741035857,
	"grad_norm": 10.05883502960205,
	"learning_rate": 6.666666666666667e-06,
	"loss": 1.5502036809921265,
	"step": 18
	},
	{
	"epoch": 0.0796812749003984,
	"grad_norm": 0.6553092002868652,
	"learning_rate": 7.450980392156863e-06,
	"loss": 1.4846529960632324,
	"step": 20
	},
	{
	"epoch": 0.08764940239043825,
	"grad_norm": 0.5488642454147339,
	"learning_rate": 8.23529411764706e-06,
	"loss": 1.144375205039978,
	"step": 22
	},
	{
	"epoch": 0.09561752988047809,
	"grad_norm": 0.6479690670967102,
	"learning_rate": 9.019607843137256e-06,
	"loss": 1.2942190170288086,
	"step": 24
	},
	{
	"epoch": 0.10358565737051793,
	"grad_norm": 0.27360522747039795,
	"learning_rate": 9.803921568627451e-06,
	"loss": 1.4014755487442017,
	"step": 26
	},
	{
	"epoch": 0.11155378486055777,
	"grad_norm": 0.4664228558540344,
	"learning_rate": 1.0588235294117648e-05,
	"loss": 1.6535426378250122,
	"step": 28
	},
	{
	"epoch": 0.11952191235059761,
	"grad_norm": 0.8422274589538574,
	"learning_rate": 1.1372549019607844e-05,
	"loss": 1.3123046159744263,
	"step": 30
	},
	{
	"epoch": 0.12749003984063745,
	"grad_norm": 0.6282227635383606,
	"learning_rate": 1.215686274509804e-05,
	"loss": 1.153808832168579,
	"step": 32
	},
	{
	"epoch": 0.13545816733067728,
	"grad_norm": 1.4378248453140259,
	"learning_rate": 1.2941176470588238e-05,
	"loss": 1.2372275590896606,
	"step": 34
	},
	{
	"epoch": 0.14342629482071714,
	"grad_norm": 0.4517601728439331,
	"learning_rate": 1.3725490196078432e-05,
	"loss": 1.3791842460632324,
	"step": 36
	},
	{
	"epoch": 0.15139442231075698,
	"grad_norm": 0.9697667360305786,
	"learning_rate": 1.4509803921568629e-05,
	"loss": 1.1730167865753174,
	"step": 38
	},
	{
	"epoch": 0.1593625498007968,
	"grad_norm": 0.3961893916130066,
	"learning_rate": 1.5294117647058822e-05,
	"loss": 1.292687177658081,
	"step": 40
	},
	{
	"epoch": 0.16733067729083664,
	"grad_norm": 1.2038718461990356,
	"learning_rate": 1.607843137254902e-05,
	"loss": 0.8232792615890503,
	"step": 42
	},
	{
	"epoch": 0.1752988047808765,
	"grad_norm": 0.4270932078361511,
	"learning_rate": 1.686274509803922e-05,
	"loss": 0.9939359426498413,
	"step": 44
	},
	{
	"epoch": 0.18326693227091634,
	"grad_norm": 0.7167245149612427,
	"learning_rate": 1.7647058823529414e-05,
	"loss": 0.9492533802986145,
	"step": 46
	},
	{
	"epoch": 0.19123505976095617,
	"grad_norm": 0.45268625020980835,
	"learning_rate": 1.843137254901961e-05,
	"loss": 1.1746896505355835,
	"step": 48
	},
	{
	"epoch": 0.199203187250996,
	"grad_norm": 0.41129186749458313,
	"learning_rate": 1.9215686274509807e-05,
	"loss": 1.3339111804962158,
	"step": 50
	},
	{
	"epoch": 0.20717131474103587,
	"grad_norm": 0.4729901850223541,
	"learning_rate": 2e-05,
	"loss": 1.2871543169021606,
	"step": 52
	},
	{
	"epoch": 0.2151394422310757,
	"grad_norm": 1.602961778640747,
	"learning_rate": 1.9999804392782173e-05,
	"loss": 1.207393765449524,
	"step": 54
	},
	{
	"epoch": 0.22310756972111553,
	"grad_norm": 0.46118712425231934,
	"learning_rate": 1.9999217579631398e-05,
	"loss": 1.5350557565689087,
	"step": 56
	},
	{
	"epoch": 0.23107569721115537,
	"grad_norm": 0.8428758382797241,
	"learning_rate": 1.9998239586055426e-05,
	"loss": 1.3389298915863037,
	"step": 58
	},
	{
	"epoch": 0.23904382470119523,
	"grad_norm": 0.30435454845428467,
	"learning_rate": 1.999687045456595e-05,
	"loss": 0.7883101105690002,
	"step": 60
	},
	{
	"epoch": 0.24701195219123506,
	"grad_norm": 0.37775376439094543,
	"learning_rate": 1.9995110244676744e-05,
	"loss": 1.3454675674438477,
	"step": 62
	},
	{
	"epoch": 0.2549800796812749,
	"grad_norm": 0.5100111365318298,
	"learning_rate": 1.999295903290109e-05,
	"loss": 1.1524405479431152,
	"step": 64
	},
	{
	"epoch": 0.26294820717131473,
	"grad_norm": 0.3763675093650818,
	"learning_rate": 1.999041691274844e-05,
	"loss": 1.2753775119781494,
	"step": 66
	},
	{
	"epoch": 0.27091633466135456,
	"grad_norm": 2.065988063812256,
	"learning_rate": 1.998748399472037e-05,
	"loss": 1.1413958072662354,
	"step": 68
	},
	{
	"epoch": 0.2788844621513944,
	"grad_norm": 0.4919253885746002,
	"learning_rate": 1.9984160406305745e-05,
	"loss": 1.6083652973175049,
	"step": 70
	},
	{
	"epoch": 0.2868525896414343,
	"grad_norm": 0.816326916217804,
	"learning_rate": 1.9980446291975217e-05,
	"loss": 0.9345599412918091,
	"step": 72
	},
	{
	"epoch": 0.2948207171314741,
	"grad_norm": 0.6255055665969849,
	"learning_rate": 1.99763418131749e-05,
	"loss": 1.1615979671478271,
	"step": 74
	},
	{
	"epoch": 0.30278884462151395,
	"grad_norm": 0.5406404733657837,
	"learning_rate": 1.9971847148319392e-05,
	"loss": 1.4970171451568604,
	"step": 76
	},
	{
	"epoch": 0.3107569721115538,
	"grad_norm": 1.2664341926574707,
	"learning_rate": 1.9966962492784006e-05,
	"loss": 1.1129828691482544,
	"step": 78
	},
	{
	"epoch": 0.3187250996015936,
	"grad_norm": 0.3932921290397644,
	"learning_rate": 1.996168805889627e-05,
	"loss": 0.9678430557250977,
	"step": 80
	},
	{
	"epoch": 0.32669322709163345,
	"grad_norm": 0.7051851153373718,
	"learning_rate": 1.99560240759267e-05,
	"loss": 1.42896568775177,
	"step": 82
	},
	{
	"epoch": 0.3346613545816733,
	"grad_norm": 0.461885541677475,
	"learning_rate": 1.9949970790078847e-05,
	"loss": 0.9989966154098511,
	"step": 84
	},
	{
	"epoch": 0.3426294820717131,
	"grad_norm": 0.3382815718650818,
	"learning_rate": 1.9943528464478573e-05,
	"loss": 1.3530247211456299,
	"step": 86
	},
	{
	"epoch": 0.350597609561753,
	"grad_norm": 0.6359050869941711,
	"learning_rate": 1.993669737916263e-05,
	"loss": 1.0272246599197388,
	"step": 88
	},
	{
	"epoch": 0.35856573705179284,
	"grad_norm": 0.4157576560974121,
	"learning_rate": 1.9929477831066485e-05,
	"loss": 1.3488913774490356,
	"step": 90
	},
	{
	"epoch": 0.3665338645418327,
	"grad_norm": 0.5085843205451965,
	"learning_rate": 1.992187013401141e-05,
	"loss": 1.1709015369415283,
	"step": 92
	},
	{
	"epoch": 0.3745019920318725,
	"grad_norm": 0.3481963872909546,
	"learning_rate": 1.9913874618690837e-05,
	"loss": 1.2576426267623901,
	"step": 94
	},
	{
	"epoch": 0.38247011952191234,
	"grad_norm": 0.5730408430099487,
	"learning_rate": 1.9905491632655996e-05,
	"loss": 1.142296314239502,
	"step": 96
	},
	{
	"epoch": 0.3904382470119522,
	"grad_norm": 0.34298205375671387,
	"learning_rate": 1.989672154030078e-05,
	"loss": 1.2693374156951904,
	"step": 98
	},
	{
	"epoch": 0.398406374501992,
	"grad_norm": 0.34943079948425293,
	"learning_rate": 1.988756472284595e-05,
	"loss": 0.903995931148529,
	"step": 100
	},
	{
	"epoch": 0.4063745019920319,
	"grad_norm": 0.3412981927394867,
	"learning_rate": 1.9878021578322518e-05,
	"loss": 1.2715134620666504,
	"step": 102
	},
	{
	"epoch": 0.41434262948207173,
	"grad_norm": 0.29975271224975586,
	"learning_rate": 1.9868092521554478e-05,
	"loss": 1.042019248008728,
	"step": 104
	},
	{
	"epoch": 0.42231075697211157,
	"grad_norm": 2.0418882369995117,
	"learning_rate": 1.9857777984140746e-05,
	"loss": 0.7882804870605469,
	"step": 106
	},
	{
	"epoch": 0.4302788844621514,
	"grad_norm": 0.5299073457717896,
	"learning_rate": 1.9847078414436438e-05,
	"loss": 1.0833579301834106,
	"step": 108
	},
	{
	"epoch": 0.43824701195219123,
	"grad_norm": 0.335245817899704,
	"learning_rate": 1.983599427753334e-05,
	"loss": 1.2959026098251343,
	"step": 110
	},
	{
	"epoch": 0.44621513944223107,
	"grad_norm": 0.5007705688476562,
	"learning_rate": 1.9824526055239712e-05,
	"loss": 0.92479407787323,
	"step": 112
	},
	{
	"epoch": 0.4541832669322709,
	"grad_norm": 0.5642781257629395,
	"learning_rate": 1.981267424605935e-05,
	"loss": 1.1809154748916626,
	"step": 114
	},
	{
	"epoch": 0.46215139442231074,
	"grad_norm": 0.32401934266090393,
	"learning_rate": 1.98004393651699e-05,
	"loss": 1.2920209169387817,
	"step": 116
	},
	{
	"epoch": 0.4701195219123506,
	"grad_norm": 0.31211525201797485,
	"learning_rate": 1.9787821944400477e-05,
	"loss": 1.3557462692260742,
	"step": 118
	},
	{
	"epoch": 0.47808764940239046,
	"grad_norm": 0.34074831008911133,
	"learning_rate": 1.9774822532208537e-05,
	"loss": 1.2343910932540894,
	"step": 120
	},
	{
	"epoch": 0.4860557768924303,
	"grad_norm": 0.4543141722679138,
	"learning_rate": 1.9761441693656052e-05,
	"loss": 1.018692970275879,
	"step": 122
	},
	{
	"epoch": 0.4940239043824701,
	"grad_norm": 0.7025930881500244,
	"learning_rate": 1.974768001038493e-05,
	"loss": 1.0649566650390625,
	"step": 124
	},
	{
	"epoch": 0.50199203187251,
	"grad_norm": 0.3762131333351135,
	"learning_rate": 1.973353808059175e-05,
	"loss": 0.9526509642601013,
	"step": 126
	},
	{
	"epoch": 0.5099601593625498,
	"grad_norm": 0.33326825499534607,
	"learning_rate": 1.9719016519001738e-05,
	"loss": 1.2880756855010986,
	"step": 128
	},
	{
	"epoch": 0.5179282868525896,
	"grad_norm": 0.2846304774284363,
	"learning_rate": 1.9704115956842066e-05,
	"loss": 0.9497164487838745,
	"step": 130
	},
	{
	"epoch": 0.5258964143426295,
	"grad_norm": 0.4433225095272064,
	"learning_rate": 1.9688837041814396e-05,
	"loss": 0.9790914058685303,
	"step": 132
	},
	{
	"epoch": 0.5338645418326693,
	"grad_norm": 0.4545140564441681,
	"learning_rate": 1.967318043806675e-05,
	"loss": 0.9353604316711426,
	"step": 134
	},
	{
	"epoch": 0.5418326693227091,
	"grad_norm": 0.3878089189529419,
	"learning_rate": 1.965714682616461e-05,
	"loss": 1.3441240787506104,
	"step": 136
	},
	{
	"epoch": 0.549800796812749,
	"grad_norm": 2.243861436843872,
	"learning_rate": 1.9640736903061363e-05,
	"loss": 0.9743496775627136,
	"step": 138
	},
	{
	"epoch": 0.5577689243027888,
	"grad_norm": 0.9255803227424622,
	"learning_rate": 1.9623951382067983e-05,
	"loss": 1.113278865814209,
	"step": 140
	},
	{
	"epoch": 0.5657370517928287,
	"grad_norm": 0.2995326519012451,
	"learning_rate": 1.960679099282204e-05,
	"loss": 1.0455888509750366,
	"step": 142
	},
	{
	"epoch": 0.5737051792828686,
	"grad_norm": 0.29048699140548706,
	"learning_rate": 1.9589256481255984e-05,
	"loss": 1.2361657619476318,
	"step": 144
	},
	{
	"epoch": 0.5816733067729084,
	"grad_norm": 0.45288383960723877,
	"learning_rate": 1.9571348609564697e-05,
	"loss": 1.191515326499939,
	"step": 146
	},
	{
	"epoch": 0.5896414342629482,
	"grad_norm": 0.4257696270942688,
	"learning_rate": 1.9553068156172404e-05,
	"loss": 1.0653226375579834,
	"step": 148
	},
	{
	"epoch": 0.5976095617529881,
	"grad_norm": 0.8186884522438049,
	"learning_rate": 1.9534415915698793e-05,
	"loss": 0.9824154376983643,
	"step": 150
	},
	{
	"epoch": 0.6055776892430279,
	"grad_norm": 0.33720093965530396,
	"learning_rate": 1.9515392698924504e-05,
	"loss": 0.9725387096405029,
	"step": 152
	},
	{
	"epoch": 0.6135458167330677,
	"grad_norm": 0.9997106194496155,
	"learning_rate": 1.949599933275587e-05,
	"loss": 1.1494280099868774,
	"step": 154
	},
	{
	"epoch": 0.6215139442231076,
	"grad_norm": 1.5014402866363525,
	"learning_rate": 1.9476236660188982e-05,
	"loss": 1.0726919174194336,
	"step": 156
	},
	{
	"epoch": 0.6294820717131474,
	"grad_norm": 0.7345775365829468,
	"learning_rate": 1.9456105540273035e-05,
	"loss": 1.194985270500183,
	"step": 158
	},
	{
	"epoch": 0.6374501992031872,
	"grad_norm": 0.3693063259124756,
	"learning_rate": 1.9435606848073003e-05,
	"loss": 1.0574865341186523,
	"step": 160
	},
	{
	"epoch": 0.6454183266932271,
	"grad_norm": 0.16802608966827393,
	"learning_rate": 1.9414741474631586e-05,
	"loss": 0.7915345430374146,
	"step": 162
	},
	{
	"epoch": 0.6533864541832669,
	"grad_norm": 0.24361276626586914,
	"learning_rate": 1.939351032693048e-05,
	"loss": 1.1572449207305908,
	"step": 164
	},
	{
	"epoch": 0.6613545816733067,
	"grad_norm": 0.2987329065799713,
	"learning_rate": 1.9371914327850958e-05,
	"loss": 0.880090057849884,
	"step": 166
	},
	{
	"epoch": 0.6693227091633466,
	"grad_norm": 0.757393479347229,
	"learning_rate": 1.934995441613376e-05,
	"loss": 1.2498260736465454,
	"step": 168
	},
	{
	"epoch": 0.6772908366533864,
	"grad_norm": 1.6156872510910034,
	"learning_rate": 1.9327631546338263e-05,
	"loss": 1.065740704536438,
	"step": 170
	},
	{
	"epoch": 0.6852589641434262,
	"grad_norm": 0.285990446805954,
	"learning_rate": 1.9304946688801014e-05,
	"loss": 0.9508867859840393,
	"step": 172
	},
	{
	"epoch": 0.6932270916334662,
	"grad_norm": 0.2722166180610657,
	"learning_rate": 1.9281900829593544e-05,
	"loss": 1.246326208114624,
	"step": 174
	},
	{
	"epoch": 0.701195219123506,
	"grad_norm": 0.6919268369674683,
	"learning_rate": 1.9258494970479494e-05,
	"loss": 0.8008362054824829,
	"step": 176
	},
	{
	"epoch": 0.7091633466135459,
	"grad_norm": 0.7445635795593262,
	"learning_rate": 1.923473012887109e-05,
	"loss": 0.9828277826309204,
	"step": 178
	},
	{
	"epoch": 0.7171314741035857,
	"grad_norm": 0.55351722240448,
	"learning_rate": 1.9210607337784885e-05,
	"loss": 1.158448576927185,
	"step": 180
	},
	{
	"epoch": 0.7250996015936255,
	"grad_norm": 0.13257816433906555,
	"learning_rate": 1.9186127645796902e-05,
	"loss": 0.5361558198928833,
	"step": 182
	},
	{
	"epoch": 0.7330677290836654,
	"grad_norm": 0.24445906281471252,
	"learning_rate": 1.916129211699701e-05,
	"loss": 1.3766955137252808,
	"step": 184
	},
	{
	"epoch": 0.7410358565737052,
	"grad_norm": 0.4627974033355713,
	"learning_rate": 1.91361018309427e-05,
	"loss": 1.304077386856079,
	"step": 186
	},
	{
	"epoch": 0.749003984063745,
	"grad_norm": 0.26658743619918823,
	"learning_rate": 1.911055788261214e-05,
	"loss": 1.151049256324768,
	"step": 188
	},
	{
	"epoch": 0.7569721115537849,
	"grad_norm": 0.3607999086380005,
	"learning_rate": 1.9084661382356592e-05,
	"loss": 0.9221289157867432,
	"step": 190
	},
	{
	"epoch": 0.7649402390438247,
	"grad_norm": 1.0667331218719482,
	"learning_rate": 1.9058413455852142e-05,
	"loss": 1.2540066242218018,
	"step": 192
	},
	{
	"epoch": 0.7729083665338645,
	"grad_norm": 0.35192084312438965,
	"learning_rate": 1.9031815244050752e-05,
	"loss": 0.9460887908935547,
	"step": 194
	},
	{
	"epoch": 0.7808764940239044,
	"grad_norm": 0.39151957631111145,
	"learning_rate": 1.9004867903130694e-05,
	"loss": 0.6812059283256531,
	"step": 196
	},
	{
	"epoch": 0.7888446215139442,
	"grad_norm": 0.4794232249259949,
	"learning_rate": 1.897757260444628e-05,
	"loss": 0.7969710826873779,
	"step": 198
	},
	{
	"epoch": 0.796812749003984,
	"grad_norm": 0.4055477976799011,
	"learning_rate": 1.8949930534476938e-05,
	"loss": 1.0776989459991455,
	"step": 200
	},
	{
	"epoch": 0.8047808764940239,
	"grad_norm": 0.13282935321331024,
	"learning_rate": 1.892194289477565e-05,
	"loss": 1.0324515104293823,
	"step": 202
	},
	{
	"epoch": 0.8127490039840638,
	"grad_norm": 0.31035351753234863,
	"learning_rate": 1.8893610901916707e-05,
	"loss": 1.5635279417037964,
	"step": 204
	},
	{
	"epoch": 0.8207171314741036,
	"grad_norm": 0.34337109327316284,
	"learning_rate": 1.886493578744284e-05,
	"loss": 1.242823600769043,
	"step": 206
	},
	{
	"epoch": 0.8286852589641435,
	"grad_norm": 0.1983502358198166,
	"learning_rate": 1.8835918797811693e-05,
	"loss": 0.6256985068321228,
	"step": 208
	},
	{
	"epoch": 0.8366533864541833,
	"grad_norm": 0.34944215416908264,
	"learning_rate": 1.880656119434162e-05,
	"loss": 1.284050464630127,
	"step": 210
	},
	{
	"epoch": 0.8446215139442231,
	"grad_norm": 0.22934027016162872,
	"learning_rate": 1.8776864253156875e-05,
	"loss": 1.2318283319473267,
	"step": 212
	},
	{
	"epoch": 0.852589641434263,
	"grad_norm": 0.2371150404214859,
	"learning_rate": 1.874682926513213e-05,
	"loss": 0.9791166186332703,
	"step": 214
	},
	{
	"epoch": 0.8605577689243028,
	"grad_norm": 1.4798812866210938,
	"learning_rate": 1.871645753583638e-05,
	"loss": 1.452410340309143,
	"step": 216
	},
	{
	"epoch": 0.8685258964143426,
	"grad_norm": 0.7958971858024597,
	"learning_rate": 1.8685750385476166e-05,
	"loss": 0.916776716709137,
	"step": 218
	},
	{
	"epoch": 0.8764940239043825,
	"grad_norm": 1.7680853605270386,
	"learning_rate": 1.8654709148838218e-05,
	"loss": 1.2467654943466187,
	"step": 220
	},
	{
	"epoch": 0.8844621513944223,
	"grad_norm": 0.6561282873153687,
	"learning_rate": 1.8623335175231402e-05,
	"loss": 1.5111079216003418,
	"step": 222
	},
	{
	"epoch": 0.8924302788844621,
	"grad_norm": 1.2204989194869995,
	"learning_rate": 1.85916298284281e-05,
	"loss": 0.7252726554870605,
	"step": 224
	},
	{
	"epoch": 0.900398406374502,
	"grad_norm": 0.29036325216293335,
	"learning_rate": 1.8559594486604905e-05,
	"loss": 1.0382778644561768,
	"step": 226
	},
	{
	"epoch": 0.9083665338645418,
	"grad_norm": 0.6182889938354492,
	"learning_rate": 1.8527230542282724e-05,
	"loss": 1.1135358810424805,
	"step": 228
	},
	{
	"epoch": 0.9163346613545816,
	"grad_norm": 0.3456054925918579,
	"learning_rate": 1.849453940226625e-05,
	"loss": 1.1879663467407227,
	"step": 230
	},
	{
	"epoch": 0.9243027888446215,
	"grad_norm": 0.5696732401847839,
	"learning_rate": 1.8461522487582803e-05,
	"loss": 1.3329076766967773,
	"step": 232
	},
	{
	"epoch": 0.9322709163346613,
	"grad_norm": 0.38616132736206055,
	"learning_rate": 1.8428181233420565e-05,
	"loss": 0.8451637029647827,
	"step": 234
	},
	{
	"epoch": 0.9402390438247012,
	"grad_norm": 0.25511351227760315,
	"learning_rate": 1.8394517089066197e-05,
	"loss": 0.8644623756408691,
	"step": 236
	},
	{
	"epoch": 0.9482071713147411,
	"grad_norm": 0.2771114408969879,
	"learning_rate": 1.8360531517841832e-05,
	"loss": 0.5260741114616394,
	"step": 238
	},
	{
	"epoch": 0.9561752988047809,
	"grad_norm": 1.012864589691162,
	"learning_rate": 1.8326225997041482e-05,
	"loss": 0.9196873903274536,
	"step": 240
	},
	{
	"epoch": 0.9641434262948207,
	"grad_norm": 0.35297006368637085,
	"learning_rate": 1.8291602017866806e-05,
	"loss": 1.1390161514282227,
	"step": 242
	},
	{
	"epoch": 0.9721115537848606,
	"grad_norm": 0.30612561106681824,
	"learning_rate": 1.8256661085362308e-05,
	"loss": 1.2218761444091797,
	"step": 244
	},
	{
	"epoch": 0.9800796812749004,
	"grad_norm": 0.6584000587463379,
	"learning_rate": 1.8221404718349888e-05,
	"loss": 0.9740089774131775,
	"step": 246
	},
	{
	"epoch": 0.9880478087649402,
	"grad_norm": 0.4018401801586151,
	"learning_rate": 1.8185834449362855e-05,
	"loss": 1.025275468826294,
	"step": 248
	},
	{
	"epoch": 0.9960159362549801,
	"grad_norm": 1.4323194026947021,
	"learning_rate": 1.8149951824579283e-05,
	"loss": 1.0199095010757446,
	"step": 250
	},
	{
	"epoch": 1.00398406374502,
	"grad_norm": 0.341948926448822,
	"learning_rate": 1.8113758403754823e-05,
	"loss": 0.9343042373657227,
	"step": 252
	},
	{
	"epoch": 1.0119521912350598,
	"grad_norm": 0.38058942556381226,
	"learning_rate": 1.8077255760154883e-05,
	"loss": 0.7046458721160889,
	"step": 254
	},
	{
	"epoch": 1.0199203187250996,
	"grad_norm": 0.5085623860359192,
	"learning_rate": 1.8040445480486254e-05,
	"loss": 1.0890356302261353,
	"step": 256
	},
	{
	"epoch": 1.0278884462151394,
	"grad_norm": 0.4822426438331604,
	"learning_rate": 1.8003329164828133e-05,
	"loss": 1.0524687767028809,
	"step": 258
	},
	{
	"epoch": 1.0358565737051793,
	"grad_norm": 0.38201844692230225,
	"learning_rate": 1.7965908426562582e-05,
	"loss": 0.9374608993530273,
	"step": 260
	},
	{
	"epoch": 1.043824701195219,
	"grad_norm": 0.4644787311553955,
	"learning_rate": 1.7928184892304366e-05,
	"loss": 0.9212496876716614,
	"step": 262
	},
	{
	"epoch": 1.051792828685259,
	"grad_norm": 0.721108078956604,
	"learning_rate": 1.789016020183029e-05,
	"loss": 1.007407546043396,
	"step": 264
	},
	{
	"epoch": 1.0597609561752988,
	"grad_norm": 0.7453786730766296,
	"learning_rate": 1.7851836008007883e-05,
	"loss": 0.75822514295578,
	"step": 266
	},
	{
	"epoch": 1.0677290836653386,
	"grad_norm": 1.0901387929916382,
	"learning_rate": 1.781321397672358e-05,
	"loss": 0.8778277039527893,
	"step": 268
	},
	{
	"epoch": 1.0756972111553784,
	"grad_norm": 0.289546400308609,
	"learning_rate": 1.777429578681029e-05,
	"loss": 0.5031875371932983,
	"step": 270
	},
	{
	"epoch": 1.0836653386454183,
	"grad_norm": 0.48452669382095337,
	"learning_rate": 1.7735083129974423e-05,
	"loss": 1.1954156160354614,
	"step": 272
	},
	{
	"epoch": 1.091633466135458,
	"grad_norm": 0.5753158330917358,
	"learning_rate": 1.769557771072236e-05,
	"loss": 0.6099209189414978,
	"step": 274
	},
	{
	"epoch": 1.099601593625498,
	"grad_norm": 0.4469282329082489,
	"learning_rate": 1.7655781246286345e-05,
	"loss": 0.8086526989936829,
	"step": 276
	},
	{
	"epoch": 1.1075697211155378,
	"grad_norm": 0.8727370500564575,
	"learning_rate": 1.761569546654988e-05,
	"loss": 0.7694612741470337,
	"step": 278
	},
	{
	"epoch": 1.1155378486055776,
	"grad_norm": 0.4654983580112457,
	"learning_rate": 1.7575322113972472e-05,
	"loss": 0.9192116260528564,
	"step": 280
	},
	{
	"epoch": 1.1235059760956174,
	"grad_norm": 0.31477856636047363,
	"learning_rate": 1.753466294351395e-05,
	"loss": 1.049499750137329,
	"step": 282
	},
	{
	"epoch": 1.1314741035856573,
	"grad_norm": 0.4698004126548767,
	"learning_rate": 1.7493719722558135e-05,
	"loss": 1.1166934967041016,
	"step": 284
	},
	{
	"epoch": 1.139442231075697,
	"grad_norm": 0.20743758976459503,
	"learning_rate": 1.7452494230836034e-05,
	"loss": 0.3405384123325348,
	"step": 286
	},
	{
	"epoch": 1.1474103585657371,
	"grad_norm": 0.21572747826576233,
	"learning_rate": 1.741098826034848e-05,
	"loss": 0.6110213994979858,
	"step": 288
	},
	{
	"epoch": 1.155378486055777,
	"grad_norm": 0.9294064044952393,
	"learning_rate": 1.7369203615288227e-05,
	"loss": 0.86930912733078,
	"step": 290
	},
	{
	"epoch": 1.1633466135458168,
	"grad_norm": 0.9067952036857605,
	"learning_rate": 1.7327142111961537e-05,
	"loss": 0.7051547169685364,
	"step": 292
	},
	{
	"epoch": 1.1713147410358566,
	"grad_norm": 0.3776642382144928,
	"learning_rate": 1.7284805578709218e-05,
	"loss": 1.1381611824035645,
	"step": 294
	},
	{
	"epoch": 1.1792828685258965,
	"grad_norm": 0.20979639887809753,
	"learning_rate": 1.724219585582716e-05,
	"loss": 1.2165122032165527,
	"step": 296
	},
	{
	"epoch": 1.1872509960159363,
	"grad_norm": 0.3244563043117523,
	"learning_rate": 1.7199314795486325e-05,
	"loss": 1.2280006408691406,
	"step": 298
	},
	{
	"epoch": 1.1952191235059761,
	"grad_norm": 0.7252885699272156,
	"learning_rate": 1.7156164261652247e-05,
	"loss": 0.6707150340080261,
	"step": 300
	},
	{
	"epoch": 1.203187250996016,
	"grad_norm": 0.3757059574127197,
	"learning_rate": 1.711274613000401e-05,
	"loss": 0.8710638880729675,
	"step": 302
	},
	{
	"epoch": 1.2111553784860558,
	"grad_norm": 0.30097636580467224,
	"learning_rate": 1.7069062287852717e-05,
	"loss": 0.5094844102859497,
	"step": 304
	},
	{
	"epoch": 1.2191235059760956,
	"grad_norm": 0.48242101073265076,
	"learning_rate": 1.702511463405943e-05,
	"loss": 1.133294701576233,
	"step": 306
	},
	{
	"epoch": 1.2270916334661355,
	"grad_norm": 0.7108588814735413,
	"learning_rate": 1.698090507895266e-05,
	"loss": 0.9296752214431763,
	"step": 308
	},
	{
	"epoch": 1.2350597609561753,
	"grad_norm": 0.41015177965164185,
	"learning_rate": 1.693643554424532e-05,
	"loss": 1.068943738937378,
	"step": 310
	},
	{
	"epoch": 1.2430278884462151,
	"grad_norm": 0.34054386615753174,
	"learning_rate": 1.6891707962951173e-05,
	"loss": 1.0081392526626587,
	"step": 312
	},
	{
	"epoch": 1.250996015936255,
	"grad_norm": 2.2303950786590576,
	"learning_rate": 1.684672427930083e-05,
	"loss": 0.8653253316879272,
	"step": 314
	},
	{
	"epoch": 1.2589641434262948,
	"grad_norm": 0.3943715989589691,
	"learning_rate": 1.680148644865722e-05,
	"loss": 0.7365275621414185,
	"step": 316
	},
	{
	"epoch": 1.2669322709163346,
	"grad_norm": 0.33673974871635437,
	"learning_rate": 1.6755996437430622e-05,
	"loss": 0.6356416344642639,
	"step": 318
	},
	{
	"epoch": 1.2749003984063745,
	"grad_norm": 0.9208086729049683,
	"learning_rate": 1.6710256222993137e-05,
	"loss": 0.5271879434585571,
	"step": 320
	},
	{
	"epoch": 1.2828685258964143,
	"grad_norm": 0.45602428913116455,
	"learning_rate": 1.6664267793592797e-05,
	"loss": 0.9226617217063904,
	"step": 322
	},
	{
	"epoch": 1.2908366533864541,
	"grad_norm": 0.5400494337081909,
	"learning_rate": 1.661803314826709e-05,
	"loss": 0.8759934902191162,
	"step": 324
	},
	{
	"epoch": 1.298804780876494,
	"grad_norm": 1.4296598434448242,
	"learning_rate": 1.65715542967561e-05,
	"loss": 1.1430692672729492,
	"step": 326
	},
	{
	"epoch": 1.3067729083665338,
	"grad_norm": 0.3259183168411255,
	"learning_rate": 1.652483325941511e-05,
	"loss": 0.7194448709487915,
	"step": 328
	},
	{
	"epoch": 1.3147410358565736,
	"grad_norm": 0.40675562620162964,
	"learning_rate": 1.647787206712683e-05,
	"loss": 0.7846541404724121,
	"step": 330
	},
	{
	"epoch": 1.3227091633466135,
	"grad_norm": 0.5686507821083069,
	"learning_rate": 1.6430672761213065e-05,
	"loss": 0.8795408010482788,
	"step": 332
	},
	{
	"epoch": 1.3306772908366533,
	"grad_norm": 0.5391749739646912,
	"learning_rate": 1.6383237393346025e-05,
	"loss": 0.5901771187782288,
	"step": 334
	},
	{
	"epoch": 1.3386454183266931,
	"grad_norm": 1.5842124223709106,
	"learning_rate": 1.633556802545911e-05,
	"loss": 0.8455764651298523,
	"step": 336
	},
	{
	"epoch": 1.3466135458167332,
	"grad_norm": 0.6567497253417969,
	"learning_rate": 1.628766672965731e-05,
	"loss": 1.0685632228851318,
	"step": 338
	},
	{
	"epoch": 1.354581673306773,
	"grad_norm": 0.28743740916252136,
	"learning_rate": 1.6239535588127107e-05,
	"loss": 1.0498569011688232,
	"step": 340
	},
	{
	"epoch": 1.3625498007968129,
	"grad_norm": 0.24235428869724274,
	"learning_rate": 1.6191176693046e-05,
	"loss": 1.1290383338928223,
	"step": 342
	},
	{
	"epoch": 1.3705179282868527,
	"grad_norm": 0.27160707116127014,
	"learning_rate": 1.6142592146491517e-05,
	"loss": 1.0615555047988892,
	"step": 344
	},
	{
	"epoch": 1.3784860557768925,
	"grad_norm": 0.5951285362243652,
	"learning_rate": 1.6093784060349876e-05,
	"loss": 0.6895939111709595,
	"step": 346
	},
	{
	"epoch": 1.3864541832669324,
	"grad_norm": 0.267936646938324,
	"learning_rate": 1.6044754556224178e-05,
	"loss": 1.1047388315200806,
	"step": 348
	},
	{
	"epoch": 1.3944223107569722,
	"grad_norm": 0.2702598571777344,
	"learning_rate": 1.5995505765342176e-05,
	"loss": 0.6365596055984497,
	"step": 350
	},
	{
	"epoch": 1.402390438247012,
	"grad_norm": 0.3268156051635742,
	"learning_rate": 1.594603982846364e-05,
	"loss": 1.1005016565322876,
	"step": 352
	},
	{
	"epoch": 1.4103585657370519,
	"grad_norm": 0.49795475602149963,
	"learning_rate": 1.5896358895787304e-05,
	"loss": 1.080939769744873,
	"step": 354
	},
	{
	"epoch": 1.4183266932270917,
	"grad_norm": 0.6326602101325989,
	"learning_rate": 1.5846465126857386e-05,
	"loss": 0.8446483612060547,
	"step": 356
	},
	{
	"epoch": 1.4262948207171315,
	"grad_norm": 0.3423049747943878,
	"learning_rate": 1.579636069046975e-05,
	"loss": 1.112828016281128,
	"step": 358
	},
	{
	"epoch": 1.4342629482071714,
	"grad_norm": 0.331617534160614,
	"learning_rate": 1.5746047764577586e-05,
	"loss": 0.556983470916748,
	"step": 360
	},
	{
	"epoch": 1.4422310756972112,
	"grad_norm": 0.7952442169189453,
	"learning_rate": 1.5695528536196774e-05,
	"loss": 0.7050241827964783,
	"step": 362
	},
	{
	"epoch": 1.450199203187251,
	"grad_norm": 0.49163997173309326,
	"learning_rate": 1.564480520131081e-05,
	"loss": 1.011673927307129,
	"step": 364
	},
	{
	"epoch": 1.4581673306772909,
	"grad_norm": 0.5051209330558777,
	"learning_rate": 1.559387996477534e-05,
	"loss": 1.0447050333023071,
	"step": 366
	},
	{
	"epoch": 1.4661354581673307,
	"grad_norm": 0.4506257474422455,
	"learning_rate": 1.5542755040222325e-05,
	"loss": 0.5882746577262878,
	"step": 368
	},
	{
	"epoch": 1.4741035856573705,
	"grad_norm": 0.3848789930343628,
	"learning_rate": 1.5491432649963823e-05,
	"loss": 0.6615412831306458,
	"step": 370
	},
	{
	"epoch": 1.4820717131474104,
	"grad_norm": 1.171698808670044,
	"learning_rate": 1.543991502489538e-05,
	"loss": 1.2864530086517334,
	"step": 372
	},
	{
	"epoch": 1.4900398406374502,
	"grad_norm": 0.4419739544391632,
	"learning_rate": 1.5388204404399073e-05,
	"loss": 1.0378817319869995,
	"step": 374
	},
	{
	"epoch": 1.49800796812749,
	"grad_norm": 0.23308596014976501,
	"learning_rate": 1.533630303624614e-05,
	"loss": 1.0560197830200195,
	"step": 376
	},
	{
	"epoch": 1.5059760956175299,
	"grad_norm": 0.8023196458816528,
	"learning_rate": 1.5284213176499302e-05,
	"loss": 0.8570104241371155,
	"step": 378
	},
	{
	"epoch": 1.5139442231075697,
	"grad_norm": 0.3250346779823303,
	"learning_rate": 1.5231937089414675e-05,
	"loss": 1.092508316040039,
	"step": 380
	},
	{
	"epoch": 1.5219123505976095,
	"grad_norm": 0.25869283080101013,
	"learning_rate": 1.517947704734337e-05,
	"loss": 0.6813873648643494,
	"step": 382
	},
	{
	"epoch": 1.5298804780876494,
	"grad_norm": 0.28996741771698,
	"learning_rate": 1.5126835330632677e-05,
	"loss": 0.6645854115486145,
	"step": 384
	},
	{
	"epoch": 1.5378486055776892,
	"grad_norm": 1.5717236995697021,
	"learning_rate": 1.5074014227526997e-05,
	"loss": 0.9236294031143188,
	"step": 386
	},
	{
	"epoch": 1.545816733067729,
	"grad_norm": 0.32109910249710083,
	"learning_rate": 1.502101603406833e-05,
	"loss": 1.0823489427566528,
	"step": 388
	},
	{
	"epoch": 1.5537848605577689,
	"grad_norm": 0.7276486158370972,
	"learning_rate": 1.4967843053996494e-05,
	"loss": 0.5451988577842712,
	"step": 390
	},
	{
	"epoch": 1.5617529880478087,
	"grad_norm": 0.3085494041442871,
	"learning_rate": 1.4914497598648973e-05,
	"loss": 0.5751717686653137,
	"step": 392
	},
	{
	"epoch": 1.5697211155378485,
	"grad_norm": 1.1126803159713745,
	"learning_rate": 1.4860981986860464e-05,
	"loss": 1.058145523071289,
	"step": 394
	},
	{
	"epoch": 1.5776892430278884,
	"grad_norm": 0.6459108591079712,
	"learning_rate": 1.4807298544862054e-05,
	"loss": 0.9958094358444214,
	"step": 396
	},
	{
	"epoch": 1.5856573705179282,
	"grad_norm": 0.20127789676189423,
	"learning_rate": 1.4753449606180137e-05,
	"loss": 1.0852116346359253,
	"step": 398
	},
	{
	"epoch": 1.593625498007968,
	"grad_norm": 0.3237609565258026,
	"learning_rate": 1.4699437511534947e-05,
	"loss": 0.6027621030807495,
	"step": 400
	},
	{
	"epoch": 1.6015936254980079,
	"grad_norm": 0.4658999443054199,
	"learning_rate": 1.4645264608738832e-05,
	"loss": 1.0461393594741821,
	"step": 402
	},
	{
	"epoch": 1.6095617529880477,
	"grad_norm": 0.22849686443805695,
	"learning_rate": 1.4590933252594193e-05,
	"loss": 1.1783668994903564,
	"step": 404
	},
	{
	"epoch": 1.6175298804780875,
	"grad_norm": 0.464072585105896,
	"learning_rate": 1.4536445804791125e-05,
	"loss": 0.699569582939148,
	"step": 406
	},
	{
	"epoch": 1.6254980079681274,
	"grad_norm": 0.18738897144794464,
	"learning_rate": 1.4481804633804746e-05,
	"loss": 0.5158436894416809,
	"step": 408
	},
	{
	"epoch": 1.6334661354581672,
	"grad_norm": 0.4792879521846771,
	"learning_rate": 1.4427012114792269e-05,
	"loss": 0.7027358412742615,
	"step": 410
	},
	{
	"epoch": 1.641434262948207,
	"grad_norm": 0.2847132980823517,
	"learning_rate": 1.4372070629489744e-05,
	"loss": 0.4589526355266571,
	"step": 412
	},
	{
	"epoch": 1.6494023904382469,
	"grad_norm": 0.16233396530151367,
	"learning_rate": 1.4316982566108515e-05,
	"loss": 0.7499012351036072,
	"step": 414
	},
	{
	"epoch": 1.6573705179282867,
	"grad_norm": 0.34753382205963135,
	"learning_rate": 1.4261750319231432e-05,
	"loss": 0.7557674050331116,
	"step": 416
	},
	{
	"epoch": 1.6653386454183265,
	"grad_norm": 0.5319584608078003,
	"learning_rate": 1.4206376289708752e-05,
	"loss": 0.8566523194313049,
	"step": 418
	},
	{
	"epoch": 1.6733067729083664,
	"grad_norm": 0.291802316904068,
	"learning_rate": 1.4150862884553776e-05,
	"loss": 1.1130759716033936,
	"step": 420
	},
	{
	"epoch": 1.6812749003984062,
	"grad_norm": 0.19954712688922882,
	"learning_rate": 1.4095212516838216e-05,
	"loss": 0.9514334201812744,
	"step": 422
	},
	{
	"epoch": 1.6892430278884463,
	"grad_norm": 0.3112265467643738,
	"learning_rate": 1.4039427605587326e-05,
	"loss": 0.5233280062675476,
	"step": 424
	},
	{
	"epoch": 1.697211155378486,
	"grad_norm": 0.20384936034679413,
	"learning_rate": 1.398351057567472e-05,
	"loss": 1.1268967390060425,
	"step": 426
	},
	{
	"epoch": 1.705179282868526,
	"grad_norm": 0.21102385222911835,
	"learning_rate": 1.392746385771699e-05,
	"loss": 1.063062071800232,
	"step": 428
	},
	{
	"epoch": 1.7131474103585658,
	"grad_norm": 0.3036285936832428,
	"learning_rate": 1.3871289887968034e-05,
	"loss": 0.6780144572257996,
	"step": 430
	},
	{
	"epoch": 1.7211155378486056,
	"grad_norm": 0.7043957114219666,
	"learning_rate": 1.3814991108213173e-05,
	"loss": 0.8546534776687622,
	"step": 432
	},
	{
	"epoch": 1.7290836653386454,
	"grad_norm": 0.360525518655777,
	"learning_rate": 1.3758569965663011e-05,
	"loss": 0.6243395805358887,
	"step": 434
	},
	{
	"epoch": 1.7370517928286853,
	"grad_norm": 0.8308858871459961,
	"learning_rate": 1.370202891284703e-05,
	"loss": 0.43398115038871765,
	"step": 436
	},
	{
	"epoch": 1.745019920318725,
	"grad_norm": 0.3703770935535431,
	"learning_rate": 1.3645370407507017e-05,
	"loss": 0.738655149936676,
	"step": 438
	},
	{
	"epoch": 1.752988047808765,
	"grad_norm": 2.820668935775757,
	"learning_rate": 1.3588596912490222e-05,
	"loss": 0.7261440753936768,
	"step": 440
	},
	{
	"epoch": 1.7609561752988048,
	"grad_norm": 0.43590405583381653,
	"learning_rate": 1.3531710895642288e-05,
	"loss": 1.3262492418289185,
	"step": 442
	},
	{
	"epoch": 1.7689243027888446,
	"grad_norm": 0.34120041131973267,
	"learning_rate": 1.3474714829699987e-05,
	"loss": 0.7070552706718445,
	"step": 444
	},
	{
	"epoch": 1.7768924302788844,
	"grad_norm": 0.18316373229026794,
	"learning_rate": 1.341761119218374e-05,
	"loss": 1.004502773284912,
	"step": 446
	},
	{
	"epoch": 1.7848605577689243,
	"grad_norm": 0.3774756193161011,
	"learning_rate": 1.3360402465289916e-05,
	"loss": 1.0533740520477295,
	"step": 448
	},
	{
	"epoch": 1.792828685258964,
	"grad_norm": 0.21326151490211487,
	"learning_rate": 1.3303091135782942e-05,
	"loss": 0.8273346424102783,
	"step": 450
	},
	{
	"epoch": 1.800796812749004,
	"grad_norm": 0.2267659306526184,
	"learning_rate": 1.3245679694887192e-05,
	"loss": 0.42468857765197754,
	"step": 452
	},
	{
	"epoch": 1.8087649402390438,
	"grad_norm": 0.5060834288597107,
	"learning_rate": 1.318817063817872e-05,
	"loss": 0.8974787592887878,
	"step": 454
	},
	{
	"epoch": 1.8167330677290838,
	"grad_norm": 0.48161670565605164,
	"learning_rate": 1.3130566465476773e-05,
	"loss": 0.6163372993469238,
	"step": 456
	},
	{
	"epoch": 1.8247011952191237,
	"grad_norm": 0.2777350842952728,
	"learning_rate": 1.307286968073511e-05,
	"loss": 0.9941050410270691,
	"step": 458
	},
	{
	"epoch": 1.8326693227091635,
	"grad_norm": 0.488695353269577,
	"learning_rate": 1.3015082791933182e-05,
	"loss": 0.7475647926330566,
	"step": 460
	},
	{
	"epoch": 1.8406374501992033,
	"grad_norm": 0.24865223467350006,
	"learning_rate": 1.295720831096712e-05,
	"loss": 0.8023468255996704,
	"step": 462
	},
	{
	"epoch": 1.8486055776892432,
	"grad_norm": 0.17197415232658386,
	"learning_rate": 1.2899248753540518e-05,
	"loss": 0.1325809210538864,
	"step": 464
	},
	{
	"epoch": 1.856573705179283,
	"grad_norm": 1.5523875951766968,
	"learning_rate": 1.2841206639055108e-05,
	"loss": 1.1007118225097656,
	"step": 466
	},
	{
	"epoch": 1.8645418326693228,
	"grad_norm": 0.5094614624977112,
	"learning_rate": 1.2783084490501229e-05,
	"loss": 0.514072060585022,
	"step": 468
	},
	{
	"epoch": 1.8725099601593627,
	"grad_norm": 0.35147467255592346,
	"learning_rate": 1.2724884834348163e-05,
	"loss": 1.0952625274658203,
	"step": 470
	},
	{
	"epoch": 1.8804780876494025,
	"grad_norm": 0.36751729249954224,
	"learning_rate": 1.266661020043432e-05,
	"loss": 0.9377644658088684,
	"step": 472
	},
	{
	"epoch": 1.8884462151394423,
	"grad_norm": 0.4373418092727661,
	"learning_rate": 1.2608263121857244e-05,
	"loss": 0.9737136960029602,
	"step": 474
	},
	{
	"epoch": 1.8964143426294822,
	"grad_norm": 0.19097857177257538,
	"learning_rate": 1.254984613486355e-05,
	"loss": 0.9451252222061157,
	"step": 476
	},
	{
	"epoch": 1.904382470119522,
	"grad_norm": 0.42185327410697937,
	"learning_rate": 1.2491361778738631e-05,
	"loss": 0.7926995158195496,
	"step": 478
	},
	{
	"epoch": 1.9123505976095618,
	"grad_norm": 0.5808318257331848,
	"learning_rate": 1.243281259569631e-05,
	"loss": 0.5798477530479431,
	"step": 480
	},
	{
	"epoch": 1.9203187250996017,
	"grad_norm": 0.5500463247299194,
	"learning_rate": 1.2374201130768325e-05,
	"loss": 0.7669761180877686,
	"step": 482
	},
	{
	"epoch": 1.9282868525896415,
	"grad_norm": 0.21460963785648346,
	"learning_rate": 1.2315529931693682e-05,
	"loss": 1.054688811302185,
	"step": 484
	},
	{
	"epoch": 1.9362549800796813,
	"grad_norm": 0.2985857129096985,
	"learning_rate": 1.2256801548807948e-05,
	"loss": 0.9884510040283203,
	"step": 486
	},
	{
	"epoch": 1.9442231075697212,
	"grad_norm": 0.22740538418293,
	"learning_rate": 1.2198018534932367e-05,
	"loss": 1.0773851871490479,
	"step": 488
	},
	{
	"epoch": 1.952191235059761,
	"grad_norm": 0.1833743005990982,
	"learning_rate": 1.2139183445262892e-05,
	"loss": 1.0440764427185059,
	"step": 490
	},
	{
	"epoch": 1.9601593625498008,
	"grad_norm": 0.26161497831344604,
	"learning_rate": 1.2080298837259124e-05,
	"loss": 0.7149063348770142,
	"step": 492
	},
	{
	"epoch": 1.9681274900398407,
	"grad_norm": 2.253765821456909,
	"learning_rate": 1.2021367270533138e-05,
	"loss": 0.7989740967750549,
	"step": 494
	},
	{
	"epoch": 1.9760956175298805,
	"grad_norm": 0.28019073605537415,
	"learning_rate": 1.1962391306738226e-05,
	"loss": 1.0134761333465576,
	"step": 496
	},
	{
	"epoch": 1.9840637450199203,
	"grad_norm": 0.6458740234375,
	"learning_rate": 1.190337350945754e-05,
	"loss": 0.823985755443573,
	"step": 498
	},
	{
	"epoch": 1.9920318725099602,
	"grad_norm": 0.298125684261322,
	"learning_rate": 1.1844316444092667e-05,
	"loss": 1.132564902305603,
	"step": 500
	},
	{
	"epoch": 2.0,
	"grad_norm": 0.3069063127040863,
	"learning_rate": 1.1785222677752105e-05,
	"loss": 0.6213638782501221,
	"step": 502
	},
	{
	"epoch": 2.00796812749004,
	"grad_norm": 0.2165108621120453,
	"learning_rate": 1.1726094779139685e-05,
	"loss": 0.5043126344680786,
	"step": 504
	},
	{
	"epoch": 2.0159362549800797,
	"grad_norm": 0.4651063084602356,
	"learning_rate": 1.1666935318442905e-05,
	"loss": 0.44121354818344116,
	"step": 506
	},
	{
	"epoch": 2.0239043824701195,
	"grad_norm": 0.08969016373157501,
	"learning_rate": 1.1607746867221208e-05,
	"loss": 0.4672836661338806,
	"step": 508
	},
	{
	"epoch": 2.0318725099601593,
	"grad_norm": 0.38188546895980835,
	"learning_rate": 1.1548531998294217e-05,
	"loss": 0.7249612808227539,
	"step": 510
	},
	{
	"epoch": 2.039840637450199,
	"grad_norm": 0.2776472866535187,
	"learning_rate": 1.148929328562987e-05,
	"loss": 0.6245005130767822,
	"step": 512
	},
	{
	"epoch": 2.047808764940239,
	"grad_norm": 0.6827823519706726,
	"learning_rate": 1.1430033304232569e-05,
	"loss": 0.3463484048843384,
	"step": 514
	},
	{
	"epoch": 2.055776892430279,
	"grad_norm": 0.4058661162853241,
	"learning_rate": 1.137075463003122e-05,
	"loss": 0.7836011052131653,
	"step": 516
	},
	{
	"epoch": 2.0637450199203187,
	"grad_norm": 12.217242240905762,
	"learning_rate": 1.1311459839767278e-05,
	"loss": 0.4506489038467407,
	"step": 518
	},
	{
	"epoch": 2.0717131474103585,
	"grad_norm": 3.7635204792022705,
	"learning_rate": 1.1252151510882731e-05,
	"loss": 0.6491232514381409,
	"step": 520
	},
	{
	"epoch": 2.0796812749003983,
	"grad_norm": 0.39710062742233276,
	"learning_rate": 1.1192832221408068e-05,
	"loss": 0.8215765953063965,
	"step": 522
	},
	{
	"epoch": 2.087649402390438,
	"grad_norm": 0.4940469563007355,
	"learning_rate": 1.1133504549850218e-05,
	"loss": 0.7698899507522583,
	"step": 524
	},
	{
	"epoch": 2.095617529880478,
	"grad_norm": 0.536239504814148,
	"learning_rate": 1.1074171075080469e-05,
	"loss": 0.36201098561286926,
	"step": 526
	},
	{
	"epoch": 2.103585657370518,
	"grad_norm": 0.8106605410575867,
	"learning_rate": 1.1014834376222351e-05,
	"loss": 0.5792776942253113,
	"step": 528
	},
	{
	"epoch": 2.1115537848605577,
	"grad_norm": 0.15770025551319122,
	"learning_rate": 1.0955497032539557e-05,
	"loss": 0.44848746061325073,
	"step": 530
	},
	{
	"epoch": 2.1195219123505975,
	"grad_norm": 0.24326692521572113,
	"learning_rate": 1.0896161623323795e-05,
	"loss": 0.1985977292060852,
	"step": 532
	},
	{
	"epoch": 2.1274900398406373,
	"grad_norm": 1.5041277408599854,
	"learning_rate": 1.0836830727782692e-05,
	"loss": 0.612493634223938,
	"step": 534
	},
	{
	"epoch": 2.135458167330677,
	"grad_norm": 1.0610326528549194,
	"learning_rate": 1.0777506924927667e-05,
	"loss": 0.6036497950553894,
	"step": 536
	},
	{
	"epoch": 2.143426294820717,
	"grad_norm": 0.6076405644416809,
	"learning_rate": 1.0718192793461849e-05,
	"loss": 0.6230844855308533,
	"step": 538
	},
	{
	"epoch": 2.151394422310757,
	"grad_norm": 0.36088430881500244,
	"learning_rate": 1.065889091166795e-05,
	"loss": 0.7613107562065125,
	"step": 540
	},
	{
	"epoch": 2.1593625498007967,
	"grad_norm": 0.3054327964782715,
	"learning_rate": 1.059960385729621e-05,
	"loss": 0.6941779851913452,
	"step": 542
	},
	{
	"epoch": 2.1673306772908365,
	"grad_norm": 0.24954797327518463,
	"learning_rate": 1.0540334207452363e-05,
	"loss": 0.47066619992256165,
	"step": 544
	},
	{
	"epoch": 2.1752988047808763,
	"grad_norm": 0.2986539900302887,
	"learning_rate": 1.0481084538485589e-05,
	"loss": 0.5359241366386414,
	"step": 546
	},
	{
	"epoch": 2.183266932270916,
	"grad_norm": 0.3956416845321655,
	"learning_rate": 1.0421857425876524e-05,
	"loss": 0.7813495397567749,
	"step": 548
	},
	{
	"epoch": 2.191235059760956,
	"grad_norm": 0.3207624852657318,
	"learning_rate": 1.0362655444125334e-05,
	"loss": 0.8096965551376343,
	"step": 550
	},
	{
	"epoch": 2.199203187250996,
	"grad_norm": 0.4274860620498657,
	"learning_rate": 1.0303481166639784e-05,
	"loss": 0.509590208530426,
	"step": 552
	},
	{
	"epoch": 2.2071713147410357,
	"grad_norm": 0.5321890711784363,
	"learning_rate": 1.0244337165623378e-05,
	"loss": 0.453169047832489,
	"step": 554
	},
	{
	"epoch": 2.2151394422310755,
	"grad_norm": 0.5689948797225952,
	"learning_rate": 1.0185226011963563e-05,
	"loss": 0.6031365990638733,
	"step": 556
	},
	{
	"epoch": 2.2231075697211153,
	"grad_norm": 2.9450175762176514,
	"learning_rate": 1.0126150275119958e-05,
	"loss": 0.8096473813056946,
	"step": 558
	},
	{
	"epoch": 2.231075697211155,
	"grad_norm": 0.4231691062450409,
	"learning_rate": 1.0067112523012686e-05,
	"loss": 0.7732781767845154,
	"step": 560
	},
	{
	"epoch": 2.239043824701195,
	"grad_norm": 0.31910139322280884,
	"learning_rate": 1.0008115321910729e-05,
	"loss": 0.8720684051513672,
	"step": 562
	},
	{
	"epoch": 2.247011952191235,
	"grad_norm": 6.204998016357422,
	"learning_rate": 9.949161236320388e-06,
	"loss": 0.5987430214881897,
	"step": 564
	},
	{
	"epoch": 2.2549800796812747,
	"grad_norm": 0.29381808638572693,
	"learning_rate": 9.890252828873816e-06,
	"loss": 0.4853253960609436,
	"step": 566
	},
	{
	"epoch": 2.2629482071713145,
	"grad_norm": 0.2391190379858017,
	"learning_rate": 9.831392660217608e-06,
	"loss": 0.6356629729270935,
	"step": 568
	},
	{
	"epoch": 2.2709163346613543,
	"grad_norm": 0.35715413093566895,
	"learning_rate": 9.772583288901502e-06,
	"loss": 0.7994184494018555,
	"step": 570
	},
	{
	"epoch": 2.278884462151394,
	"grad_norm": 0.8083705306053162,
	"learning_rate": 9.713827271267169e-06,
	"loss": 0.5638254284858704,
	"step": 572
	},
	{
	"epoch": 2.2868525896414345,
	"grad_norm": 0.25096696615219116,
	"learning_rate": 9.655127161337088e-06,
	"loss": 0.5889987349510193,
	"step": 574
	},
	{
	"epoch": 2.2948207171314743,
	"grad_norm": 0.2611815333366394,
	"learning_rate": 9.59648551070351e-06,
	"loss": 0.2555178701877594,
	"step": 576
	},
	{
	"epoch": 2.302788844621514,
	"grad_norm": 0.5718734264373779,
	"learning_rate": 9.53790486841759e-06,
	"loss": 0.5340811014175415,
	"step": 578
	},
	{
	"epoch": 2.310756972111554,
	"grad_norm": 0.3825013339519501,
	"learning_rate": 9.479387780878531e-06,
	"loss": 0.5315930247306824,
	"step": 580
	},
	{
	"epoch": 2.318725099601594,
	"grad_norm": 0.685142457485199,
	"learning_rate": 9.42093679172294e-06,
	"loss": 0.4931807219982147,
	"step": 582
	},
	{
	"epoch": 2.3266932270916336,
	"grad_norm": 0.657268762588501,
	"learning_rate": 9.362554441714216e-06,
	"loss": 0.624793529510498,
	"step": 584
	},
	{
	"epoch": 2.3346613545816735,
	"grad_norm": 0.36978161334991455,
	"learning_rate": 9.304243268632165e-06,
	"loss": 0.5345178842544556,
	"step": 586
	},
	{
	"epoch": 2.3426294820717133,
	"grad_norm": 0.6148081421852112,
	"learning_rate": 9.246005807162632e-06,
	"loss": 0.6727567911148071,
	"step": 588
	},
	{
	"epoch": 2.350597609561753,
	"grad_norm": 0.299528568983078,
	"learning_rate": 9.187844588787354e-06,
	"loss": 0.7979969382286072,
	"step": 590
	},
	{
	"epoch": 2.358565737051793,
	"grad_norm": 0.37552663683891296,
	"learning_rate": 9.12976214167391e-06,
	"loss": 0.8545841574668884,
	"step": 592
	},
	{
	"epoch": 2.366533864541833,
	"grad_norm": 0.31660106778144836,
	"learning_rate": 9.071760990565832e-06,
	"loss": 0.5427640676498413,
	"step": 594
	},
	{
	"epoch": 2.3745019920318726,
	"grad_norm": 0.2705290913581848,
	"learning_rate": 9.013843656672854e-06,
	"loss": 0.7104488015174866,
	"step": 596
	},
	{
	"epoch": 2.3824701195219125,
	"grad_norm": 0.27716466784477234,
	"learning_rate": 8.956012657561314e-06,
	"loss": 0.5637896060943604,
	"step": 598
	},
	{
	"epoch": 2.3904382470119523,
	"grad_norm": 2.9362845420837402,
	"learning_rate": 8.89827050704474e-06,
	"loss": 0.6183806657791138,
	"step": 600
	},
	{
	"epoch": 2.398406374501992,
	"grad_norm": 0.2689732313156128,
	"learning_rate": 8.840619715074553e-06,
	"loss": 0.7946896553039551,
	"step": 602
	},
	{
	"epoch": 2.406374501992032,
	"grad_norm": 0.23491685092449188,
	"learning_rate": 8.78306278763098e-06,
	"loss": 0.4485781192779541,
	"step": 604
	},
	{
	"epoch": 2.414342629482072,
	"grad_norm": 0.9759865999221802,
	"learning_rate": 8.725602226614121e-06,
	"loss": 0.2319762110710144,
	"step": 606
	},
	{
	"epoch": 2.4223107569721116,
	"grad_norm": 0.15988869965076447,
	"learning_rate": 8.668240529735192e-06,
	"loss": 0.3493569493293762,
	"step": 608
	},
	{
	"epoch": 2.4302788844621515,
	"grad_norm": 0.17206406593322754,
	"learning_rate": 8.610980190407958e-06,
	"loss": 0.6467002630233765,
	"step": 610
	},
	{
	"epoch": 2.4382470119521913,
	"grad_norm": 0.25553181767463684,
	"learning_rate": 8.55382369764034e-06,
	"loss": 0.583063006401062,
	"step": 612
	},
	{
	"epoch": 2.446215139442231,
	"grad_norm": 0.3950878381729126,
	"learning_rate": 8.496773535926242e-06,
	"loss": 0.46504709124565125,
	"step": 614
	},
	{
	"epoch": 2.454183266932271,
	"grad_norm": 0.26962918043136597,
	"learning_rate": 8.439832185137529e-06,
	"loss": 0.6895124912261963,
	"step": 616
	},
	{
	"epoch": 2.462151394422311,
	"grad_norm": 0.41879427433013916,
	"learning_rate": 8.383002120416241e-06,
	"loss": 0.5566327571868896,
	"step": 618
	},
	{
	"epoch": 2.4701195219123506,
	"grad_norm": 1.4798431396484375,
	"learning_rate": 8.326285812067023e-06,
	"loss": 0.6534566879272461,
	"step": 620
	},
	{
	"epoch": 2.4780876494023905,
	"grad_norm": 0.307312548160553,
	"learning_rate": 8.269685725449708e-06,
	"loss": 0.6504800915718079,
	"step": 622
	},
	{
	"epoch": 2.4860557768924303,
	"grad_norm": 0.5427370071411133,
	"learning_rate": 8.213204320872176e-06,
	"loss": 0.6383635997772217,
	"step": 624
	},
	{
	"epoch": 2.49402390438247,
	"grad_norm": 0.26320162415504456,
	"learning_rate": 8.156844053483412e-06,
	"loss": 0.4011181890964508,
	"step": 626
	},
	{
	"epoch": 2.50199203187251,
	"grad_norm": 0.37865692377090454,
	"learning_rate": 8.100607373166773e-06,
	"loss": 0.7987120151519775,
	"step": 628
	},
	{
	"epoch": 2.50996015936255,
	"grad_norm": 0.4195093512535095,
	"learning_rate": 8.044496724433493e-06,
	"loss": 0.2998882532119751,
	"step": 630
	},
	{
	"epoch": 2.5179282868525896,
	"grad_norm": 0.9238357543945312,
	"learning_rate": 7.988514546316437e-06,
	"loss": 0.34079158306121826,
	"step": 632
	},
	{
	"epoch": 2.5258964143426295,
	"grad_norm": 0.27209165692329407,
	"learning_rate": 7.932663272264079e-06,
	"loss": 0.8152284622192383,
	"step": 634
	},
	{
	"epoch": 2.5338645418326693,
	"grad_norm": 0.3044971227645874,
	"learning_rate": 7.87694533003471e-06,
	"loss": 0.7516045570373535,
	"step": 636
	},
	{
	"epoch": 2.541832669322709,
	"grad_norm": 0.5729214549064636,
	"learning_rate": 7.82136314159092e-06,
	"loss": 0.8303281664848328,
	"step": 638
	},
	{
	"epoch": 2.549800796812749,
	"grad_norm": 0.19276340305805206,
	"learning_rate": 7.765919122994319e-06,
	"loss": 0.29311320185661316,
	"step": 640
	},
	{
	"epoch": 2.557768924302789,
	"grad_norm": 0.4937683045864105,
	"learning_rate": 7.710615684300518e-06,
	"loss": 0.7855862379074097,
	"step": 642
	},
	{
	"epoch": 2.5657370517928286,
	"grad_norm": 0.2187207043170929,
	"learning_rate": 7.655455229454354e-06,
	"loss": 0.7239468097686768,
	"step": 644
	},
	{
	"epoch": 2.5737051792828685,
	"grad_norm": 1.5033259391784668,
	"learning_rate": 7.6004401561854e-06,
	"loss": 0.5276362299919128,
	"step": 646
	},
	{
	"epoch": 2.5816733067729083,
	"grad_norm": 0.33054134249687195,
	"learning_rate": 7.545572855903756e-06,
	"loss": 0.7969309687614441,
	"step": 648
	},
	{
	"epoch": 2.589641434262948,
	"grad_norm": 0.3152036666870117,
	"learning_rate": 7.490855713596081e-06,
	"loss": 0.6026449203491211,
	"step": 650
	},
	{
	"epoch": 2.597609561752988,
	"grad_norm": 0.33109569549560547,
	"learning_rate": 7.4362911077219155e-06,
	"loss": 0.5262701511383057,
	"step": 652
	},
	{
	"epoch": 2.605577689243028,
	"grad_norm": 0.29034096002578735,
	"learning_rate": 7.381881410110326e-06,
	"loss": 0.6021281480789185,
	"step": 654
	},
	{
	"epoch": 2.6135458167330676,
	"grad_norm": 0.25865310430526733,
	"learning_rate": 7.327628985856765e-06,
	"loss": 0.25670185685157776,
	"step": 656
	},
	{
	"epoch": 2.6215139442231075,
	"grad_norm": 0.39587166905403137,
	"learning_rate": 7.2735361932202965e-06,
	"loss": 0.47300997376441956,
	"step": 658
	},
	{
	"epoch": 2.6294820717131473,
	"grad_norm": 0.32333165407180786,
	"learning_rate": 7.219605383521067e-06,
	"loss": 0.6984432935714722,
	"step": 660
	},
	{
	"epoch": 2.637450199203187,
	"grad_norm": 0.8259761929512024,
	"learning_rate": 7.165838901038107e-06,
	"loss": 0.5749056935310364,
	"step": 662
	},
	{
	"epoch": 2.645418326693227,
	"grad_norm": 1.1761703491210938,
	"learning_rate": 7.112239082907433e-06,
	"loss": 0.452744722366333,
	"step": 664
	},
	{
	"epoch": 2.653386454183267,
	"grad_norm": 0.3080389201641083,
	"learning_rate": 7.058808259020442e-06,
	"loss": 0.7340803146362305,
	"step": 666
	},
	{
	"epoch": 2.6613545816733066,
	"grad_norm": 0.13718551397323608,
	"learning_rate": 7.005548751922642e-06,
	"loss": 0.5631315112113953,
	"step": 668
	},
	{
	"epoch": 2.6693227091633465,
	"grad_norm": 0.48113957047462463,
	"learning_rate": 6.952462876712707e-06,
	"loss": 0.5454351305961609,
	"step": 670
	},
	{
	"epoch": 2.6772908366533863,
	"grad_norm": 0.10773833841085434,
	"learning_rate": 6.899552940941829e-06,
	"loss": 0.27837103605270386,
	"step": 672
	},
	{
	"epoch": 2.685258964143426,
	"grad_norm": 0.22576193511486053,
	"learning_rate": 6.846821244513411e-06,
	"loss": 0.8114858865737915,
	"step": 674
	},
	{
	"epoch": 2.6932270916334664,
	"grad_norm": 0.784417450428009,
	"learning_rate": 6.794270079583101e-06,
	"loss": 0.5748249292373657,
	"step": 676
	},
	{
	"epoch": 2.7011952191235062,
	"grad_norm": 0.3679204285144806,
	"learning_rate": 6.741901730459166e-06,
	"loss": 0.4891148507595062,
	"step": 678
	},
	{
	"epoch": 2.709163346613546,
	"grad_norm": 0.29442018270492554,
	"learning_rate": 6.68971847350317e-06,
	"loss": 0.8089858293533325,
	"step": 680
	},
	{
	"epoch": 2.717131474103586,
	"grad_norm": 0.22440965473651886,
	"learning_rate": 6.6377225770310514e-06,
	"loss": 0.8312827348709106,
	"step": 682
	},
	{
	"epoch": 2.7250996015936257,
	"grad_norm": 0.8225514888763428,
	"learning_rate": 6.585916301214519e-06,
	"loss": 0.5896182656288147,
	"step": 684
	},
	{
	"epoch": 2.7330677290836656,
	"grad_norm": 3.1597442626953125,
	"learning_rate": 6.534301897982774e-06,
	"loss": 0.3686487376689911,
	"step": 686
	},
	{
	"epoch": 2.7410358565737054,
	"grad_norm": 0.24462340772151947,
	"learning_rate": 6.482881610924674e-06,
	"loss": 0.8054239749908447,
	"step": 688
	},
	{
	"epoch": 2.7490039840637452,
	"grad_norm": 1.4142591953277588,
	"learning_rate": 6.43165767519117e-06,
	"loss": 0.4302287697792053,
	"step": 690
	},
	{
	"epoch": 2.756972111553785,
	"grad_norm": 0.3220599293708801,
	"learning_rate": 6.380632317398168e-06,
	"loss": 0.9143630862236023,
	"step": 692
	},
	{
	"epoch": 2.764940239043825,
	"grad_norm": 0.6856467723846436,
	"learning_rate": 6.3298077555297245e-06,
	"loss": 0.6507794857025146,
	"step": 694
	},
	{
	"epoch": 2.7729083665338647,
	"grad_norm": 0.4382452070713043,
	"learning_rate": 6.279186198841647e-06,
	"loss": 0.3969390094280243,
	"step": 696
	},
	{
	"epoch": 2.7808764940239046,
	"grad_norm": 0.2783852219581604,
	"learning_rate": 6.228769847765468e-06,
	"loss": 0.626663327217102,
	"step": 698
	},
	{
	"epoch": 2.7888446215139444,
	"grad_norm": 0.2537877857685089,
	"learning_rate": 6.178560893812774e-06,
	"loss": 0.8403069376945496,
	"step": 700
	},
	{
	"epoch": 2.7968127490039842,
	"grad_norm": 0.1850716918706894,
	"learning_rate": 6.1285615194799695e-06,
	"loss": 0.48170754313468933,
	"step": 702
	},
	{
	"epoch": 2.804780876494024,
	"grad_norm": 0.4740298390388489,
	"learning_rate": 6.0787738981533825e-06,
	"loss": 0.8492451906204224,
	"step": 704
	},
	{
	"epoch": 2.812749003984064,
	"grad_norm": 0.20938153564929962,
	"learning_rate": 6.0292001940148174e-06,
	"loss": 0.7743903398513794,
	"step": 706
	},
	{
	"epoch": 2.8207171314741037,
	"grad_norm": 0.3462710380554199,
	"learning_rate": 5.979842561947455e-06,
	"loss": 0.8912703990936279,
	"step": 708
	},
	{
	"epoch": 2.8286852589641436,
	"grad_norm": 0.2809637188911438,
	"learning_rate": 5.9307031474422074e-06,
	"loss": 0.43541547656059265,
	"step": 710
	},
	{
	"epoch": 2.8366533864541834,
	"grad_norm": 0.20937590301036835,
	"learning_rate": 5.88178408650445e-06,
	"loss": 0.9104054570198059,
	"step": 712
	},
	{
	"epoch": 2.8446215139442232,
	"grad_norm": 0.2386903315782547,
	"learning_rate": 5.833087505561148e-06,
	"loss": 0.5239242315292358,
	"step": 714
	},
	{
	"epoch": 2.852589641434263,
	"grad_norm": 0.3977036476135254,
	"learning_rate": 5.784615521368468e-06,
	"loss": 0.7960683107376099,
	"step": 716
	},
	{
	"epoch": 2.860557768924303,
	"grad_norm": 0.9357836842536926,
	"learning_rate": 5.736370240919735e-06,
	"loss": 0.5691960453987122,
	"step": 718
	},
	{
	"epoch": 2.8685258964143427,
	"grad_norm": 0.204420268535614,
	"learning_rate": 5.688353761353862e-06,
	"loss": 0.49336379766464233,
	"step": 720
	},
	{
	"epoch": 2.8764940239043826,
	"grad_norm": 0.2908172607421875,
	"learning_rate": 5.640568169864173e-06,
	"loss": 0.4811123311519623,
	"step": 722
	},
	{
	"epoch": 2.8844621513944224,
	"grad_norm": 0.5298336148262024,
	"learning_rate": 5.5930155436076875e-06,
	"loss": 0.565929114818573,
	"step": 724
	},
	{
	"epoch": 2.8924302788844622,
	"grad_norm": 0.1939915418624878,
	"learning_rate": 5.5456979496148385e-06,
	"loss": 0.7743662595748901,
	"step": 726
	},
	{
	"epoch": 2.900398406374502,
	"grad_norm": 0.2288486510515213,
	"learning_rate": 5.498617444699603e-06,
	"loss": 0.46328917145729065,
	"step": 728
	},
	{
	"epoch": 2.908366533864542,
	"grad_norm": 0.35470640659332275,
	"learning_rate": 5.451776075370114e-06,
	"loss": 0.7746002674102783,
	"step": 730
	},
	{
	"epoch": 2.9163346613545817,
	"grad_norm": 0.39310505986213684,
	"learning_rate": 5.405175877739684e-06,
	"loss": 0.22616282105445862,
	"step": 732
	},
	{
	"epoch": 2.9243027888446216,
	"grad_norm": 0.27109962701797485,
	"learning_rate": 5.3588188774383235e-06,
	"loss": 0.8417502641677856,
	"step": 734
	},
	{
	"epoch": 2.9322709163346614,
	"grad_norm": 1.1222072839736938,
	"learning_rate": 5.3127070895246604e-06,
	"loss": 0.3744705617427826,
	"step": 736
	},
	{
	"epoch": 2.9402390438247012,
	"grad_norm": 0.9205291867256165,
	"learning_rate": 5.266842518398369e-06,
	"loss": 0.5713416934013367,
	"step": 738
	},
	{
	"epoch": 2.948207171314741,
	"grad_norm": 0.26441994309425354,
	"learning_rate": 5.2212271577130495e-06,
	"loss": 0.848888635635376,
	"step": 740
	},
	{
	"epoch": 2.956175298804781,
	"grad_norm": 0.9064684510231018,
	"learning_rate": 5.1758629902895375e-06,
	"loss": 0.25246933102607727,
	"step": 742
	},
	{
	"epoch": 2.9641434262948207,
	"grad_norm": 0.6127145886421204,
	"learning_rate": 5.1307519880297385e-06,
	"loss": 0.6468943953514099,
	"step": 744
	},
	{
	"epoch": 2.9721115537848606,
	"grad_norm": 0.4546615779399872,
	"learning_rate": 5.085896111830908e-06,
	"loss": 0.6896576881408691,
	"step": 746
	},
	{
	"epoch": 2.9800796812749004,
	"grad_norm": 0.5989493727684021,
	"learning_rate": 5.041297311500417e-06,
	"loss": 0.3880175054073334,
	"step": 748
	},
	{
	"epoch": 2.9880478087649402,
	"grad_norm": 0.24675695598125458,
	"learning_rate": 4.996957525670984e-06,
	"loss": 0.12411849945783615,
	"step": 750
	},
	{
	"epoch": 2.99601593625498,
	"grad_norm": 0.26221850514411926,
	"learning_rate": 4.952878681716416e-06,
	"loss": 0.7962881922721863,
	"step": 752
	},
	{
	"epoch": 3.00398406374502,
	"grad_norm": 0.34225115180015564,
	"learning_rate": 4.9090626956678355e-06,
	"loss": 0.3844722807407379,
	"step": 754
	},
	{
	"epoch": 3.0119521912350598,
	"grad_norm": 0.3443976640701294,
	"learning_rate": 4.865511472130379e-06,
	"loss": 0.35608866810798645,
	"step": 756
	},
	{
	"epoch": 3.0199203187250996,
	"grad_norm": 0.2815234661102295,
	"learning_rate": 4.822226904200422e-06,
	"loss": 0.17388103902339935,
	"step": 758
	},
	{
	"epoch": 3.0278884462151394,
	"grad_norm": 0.29143962264060974,
	"learning_rate": 4.779210873383273e-06,
	"loss": 0.3388209342956543,
	"step": 760
	},
	{
	"epoch": 3.0358565737051793,
	"grad_norm": 1.1175932884216309,
	"learning_rate": 4.7364652495114e-06,
	"loss": 0.3835744559764862,
	"step": 762
	},
	{
	"epoch": 3.043824701195219,
	"grad_norm": 0.3416759967803955,
	"learning_rate": 4.693991890663152e-06,
	"loss": 0.5161765813827515,
	"step": 764
	},
	{
	"epoch": 3.051792828685259,
	"grad_norm": 0.2444799840450287,
	"learning_rate": 4.651792643081986e-06,
	"loss": 0.17736996710300446,
	"step": 766
	},
	{
	"epoch": 3.0597609561752988,
	"grad_norm": 0.28991037607192993,
	"learning_rate": 4.609869341096217e-06,
	"loss": 0.37515631318092346,
	"step": 768
	},
	{
	"epoch": 3.0677290836653386,
	"grad_norm": 0.32158225774765015,
	"learning_rate": 4.568223807039282e-06,
	"loss": 0.3763376772403717,
	"step": 770
	},
	{
	"epoch": 3.0756972111553784,
	"grad_norm": 0.34686094522476196,
	"learning_rate": 4.52685785117052e-06,
	"loss": 0.5709128975868225,
	"step": 772
	},
	{
	"epoch": 3.0836653386454183,
	"grad_norm": 0.7250041961669922,
	"learning_rate": 4.485773271596503e-06,
	"loss": 0.5019816160202026,
	"step": 774
	},
	{
	"epoch": 3.091633466135458,
	"grad_norm": 0.054395563900470734,
	"learning_rate": 4.444971854192848e-06,
	"loss": 0.3104590177536011,
	"step": 776
	},
	{
	"epoch": 3.099601593625498,
	"grad_norm": 0.2409711331129074,
	"learning_rate": 4.404455372526615e-06,
	"loss": 0.33854958415031433,
	"step": 778
	},
	{
	"epoch": 3.1075697211155378,
	"grad_norm": 0.2990105450153351,
	"learning_rate": 4.3642255877791876e-06,
	"loss": 0.5261071920394897,
	"step": 780
	},
	{
	"epoch": 3.1155378486055776,
	"grad_norm": 0.09115161001682281,
	"learning_rate": 4.324284248669742e-06,
	"loss": 0.11824757605791092,
	"step": 782
	},
	{
	"epoch": 3.1235059760956174,
	"grad_norm": 0.2456287443637848,
	"learning_rate": 4.2846330913792136e-06,
	"loss": 0.6229012608528137,
	"step": 784
	},
	{
	"epoch": 3.1314741035856573,
	"grad_norm": 0.4126826524734497,
	"learning_rate": 4.245273839474835e-06,
	"loss": 0.41413745284080505,
	"step": 786
	},
	{
	"epoch": 3.139442231075697,
	"grad_norm": 0.7544516324996948,
	"learning_rate": 4.20620820383523e-06,
	"loss": 0.3049668073654175,
	"step": 788
	},
	{
	"epoch": 3.147410358565737,
	"grad_norm": 0.1292313188314438,
	"learning_rate": 4.167437882576009e-06,
	"loss": 0.2927045524120331,
	"step": 790
	},
	{
	"epoch": 3.1553784860557768,
	"grad_norm": 0.5389977693557739,
	"learning_rate": 4.128964560975993e-06,
	"loss": 0.38354364037513733,
	"step": 792
	},
	{
	"epoch": 3.1633466135458166,
	"grad_norm": 0.05460236594080925,
	"learning_rate": 4.090789911403938e-06,
	"loss": 0.1887034922838211,
	"step": 794
	},
	{
	"epoch": 3.1713147410358564,
	"grad_norm": 0.4996011257171631,
	"learning_rate": 4.0529155932458444e-06,
	"loss": 0.33719515800476074,
	"step": 796
	},
	{
	"epoch": 3.1792828685258963,
	"grad_norm": 0.3487769365310669,
	"learning_rate": 4.015343252832824e-06,
	"loss": 0.3880740702152252,
	"step": 798
	},
	{
	"epoch": 3.187250996015936,
	"grad_norm": 0.3392852544784546,
	"learning_rate": 3.978074523369533e-06,
	"loss": 0.4826694428920746,
	"step": 800
	},
	{
	"epoch": 3.195219123505976,
	"grad_norm": 0.20547737181186676,
	"learning_rate": 3.941111024863193e-06,
	"loss": 0.38525742292404175,
	"step": 802
	},
	{
	"epoch": 3.2031872509960158,
	"grad_norm": 0.3879428207874298,
	"learning_rate": 3.90445436405316e-06,
	"loss": 0.25935789942741394,
	"step": 804
	},
	{
	"epoch": 3.2111553784860556,
	"grad_norm": 0.6928282976150513,
	"learning_rate": 3.86810613434109e-06,
	"loss": 0.4072348177433014,
	"step": 806
	},
	{
	"epoch": 3.2191235059760954,
	"grad_norm": 0.4690568745136261,
	"learning_rate": 3.832067915721661e-06,
	"loss": 0.0453445203602314,
	"step": 808
	},
	{
	"epoch": 3.2270916334661353,
	"grad_norm": 0.24398498237133026,
	"learning_rate": 3.7963412747139204e-06,
	"loss": 0.3684697151184082,
	"step": 810
	},
	{
	"epoch": 3.235059760956175,
	"grad_norm": 0.45747777819633484,
	"learning_rate": 3.7609277642931642e-06,
	"loss": 0.27333521842956543,
	"step": 812
	},
	{
	"epoch": 3.243027888446215,
	"grad_norm": 0.2253321260213852,
	"learning_rate": 3.725828923823447e-06,
	"loss": 0.45263350009918213,
	"step": 814
	},
	{
	"epoch": 3.2509960159362548,
	"grad_norm": 0.40673020482063293,
	"learning_rate": 3.6910462789906697e-06,
	"loss": 0.0962015688419342,
	"step": 816
	},
	{
	"epoch": 3.2589641434262946,
	"grad_norm": 0.4036368429660797,
	"learning_rate": 3.6565813417362476e-06,
	"loss": 0.5429524779319763,
	"step": 818
	},
	{
	"epoch": 3.2669322709163344,
	"grad_norm": 0.5956811904907227,
	"learning_rate": 3.622435610191398e-06,
	"loss": 0.20509321987628937,
	"step": 820
	},
	{
	"epoch": 3.2749003984063743,
	"grad_norm": 1.8914116621017456,
	"learning_rate": 3.5886105686120267e-06,
	"loss": 0.20021887123584747,
	"step": 822
	},
	{
	"epoch": 3.2828685258964145,
	"grad_norm": 0.8176438212394714,
	"learning_rate": 3.5551076873141875e-06,
	"loss": 0.3322441577911377,
	"step": 824
	},
	{
	"epoch": 3.2908366533864544,
	"grad_norm": 0.24719004333019257,
	"learning_rate": 3.5219284226101992e-06,
	"loss": 0.521284818649292,
	"step": 826
	},
	{
	"epoch": 3.298804780876494,
	"grad_norm": 0.4595783054828644,
	"learning_rate": 3.4890742167453134e-06,
	"loss": 0.660916268825531,
	"step": 828
	},
	{
	"epoch": 3.306772908366534,
	"grad_norm": 0.32658329606056213,
	"learning_rate": 3.4565464978350447e-06,
	"loss": 0.4208177924156189,
	"step": 830
	},
	{
	"epoch": 3.314741035856574,
	"grad_norm": 0.2831469178199768,
	"learning_rate": 3.4243466798030813e-06,
	"loss": 0.23003339767456055,
	"step": 832
	},
	{
	"epoch": 3.3227091633466137,
	"grad_norm": 1.099875569343567,
	"learning_rate": 3.3924761623198276e-06,
	"loss": 0.17236332595348358,
	"step": 834
	},
	{
	"epoch": 3.3306772908366535,
	"grad_norm": 0.6602292060852051,
	"learning_rate": 3.360936330741563e-06,
	"loss": 0.33426642417907715,
	"step": 836
	},
	{
	"epoch": 3.3386454183266934,
	"grad_norm": 0.5026458501815796,
	"learning_rate": 3.329728556050219e-06,
	"loss": 0.41616302728652954,
	"step": 838
	},
	{
	"epoch": 3.346613545816733,
	"grad_norm": 3.4541831016540527,
	"learning_rate": 3.2988541947937948e-06,
	"loss": 0.07192525267601013,
	"step": 840
	},
	{
	"epoch": 3.354581673306773,
	"grad_norm": 0.48100268840789795,
	"learning_rate": 3.2683145890273803e-06,
	"loss": 0.2855004668235779,
	"step": 842
	},
	{
	"epoch": 3.362549800796813,
	"grad_norm": 0.5678504705429077,
	"learning_rate": 3.2381110662548244e-06,
	"loss": 0.43228018283843994,
	"step": 844
	},
	{
	"epoch": 3.3705179282868527,
	"grad_norm": 0.24944768846035004,
	"learning_rate": 3.208244939371029e-06,
	"loss": 0.5930905342102051,
	"step": 846
	},
	{
	"epoch": 3.3784860557768925,
	"grad_norm": 0.2541601359844208,
	"learning_rate": 3.178717506604878e-06,
	"loss": 0.5573995113372803,
	"step": 848
	},
	{
	"epoch": 3.3864541832669324,
	"grad_norm": 0.4352867901325226,
	"learning_rate": 3.1495300514628137e-06,
	"loss": 0.4143456220626831,
	"step": 850
	},
	{
	"epoch": 3.394422310756972,
	"grad_norm": 0.27721530199050903,
	"learning_rate": 3.120683842673029e-06,
	"loss": 0.5134739875793457,
	"step": 852
	},
	{
	"epoch": 3.402390438247012,
	"grad_norm": 0.2205602526664734,
	"learning_rate": 3.092180134130341e-06,
	"loss": 0.3087632358074188,
	"step": 854
	},
	{
	"epoch": 3.410358565737052,
	"grad_norm": 0.3095087707042694,
	"learning_rate": 3.064020164841661e-06,
	"loss": 0.46302488446235657,
	"step": 856
	},
	{
	"epoch": 3.4183266932270917,
	"grad_norm": 0.3580918312072754,
	"learning_rate": 3.03620515887216e-06,
	"loss": 0.4601234793663025,
	"step": 858
	},
	{
	"epoch": 3.4262948207171315,
	"grad_norm": 0.4854097366333008,
	"learning_rate": 3.0087363252920392e-06,
	"loss": 0.5634459257125854,
	"step": 860
	},
	{
	"epoch": 3.4342629482071714,
	"grad_norm": 0.24722632765769958,
	"learning_rate": 2.9816148581239945e-06,
	"loss": 0.3312654495239258,
	"step": 862
	},
	{
	"epoch": 3.442231075697211,
	"grad_norm": 0.8358548283576965,
	"learning_rate": 2.954841936291304e-06,
	"loss": 0.23872403800487518,
	"step": 864
	},
	{
	"epoch": 3.450199203187251,
	"grad_norm": 0.3561617136001587,
	"learning_rate": 2.9284187235665706e-06,
	"loss": 0.4579213261604309,
	"step": 866
	},
	{
	"epoch": 3.458167330677291,
	"grad_norm": 0.2745280861854553,
	"learning_rate": 2.902346368521161e-06,
	"loss": 0.38387465476989746,
	"step": 868
	},
	{
	"epoch": 3.4661354581673307,
	"grad_norm": 0.33510804176330566,
	"learning_rate": 2.8766260044752596e-06,
	"loss": 0.3727482557296753,
	"step": 870
	},
	{
	"epoch": 3.4741035856573705,
	"grad_norm": 0.05946040898561478,
	"learning_rate": 2.851258749448613e-06,
	"loss": 0.336728572845459,
	"step": 872
	},
	{
	"epoch": 3.4820717131474104,
	"grad_norm": 0.08459708839654922,
	"learning_rate": 2.8262457061119275e-06,
	"loss": 0.31364670395851135,
	"step": 874
	},
	{
	"epoch": 3.49003984063745,
	"grad_norm": 0.24611854553222656,
	"learning_rate": 2.801587961738936e-06,
	"loss": 0.26714128255844116,
	"step": 876
	},
	{
	"epoch": 3.49800796812749,
	"grad_norm": 0.3433525860309601,
	"learning_rate": 2.7772865881591487e-06,
	"loss": 0.3233880400657654,
	"step": 878
	},
	{
	"epoch": 3.50597609561753,
	"grad_norm": 0.077357217669487,
	"learning_rate": 2.7533426417112463e-06,
	"loss": 0.1428777575492859,
	"step": 880
	},
	{
	"epoch": 3.5139442231075697,
	"grad_norm": 0.23806530237197876,
	"learning_rate": 2.729757163197175e-06,
	"loss": 0.1798655092716217,
	"step": 882
	},
	{
	"epoch": 3.5219123505976095,
	"grad_norm": 0.41716670989990234,
	"learning_rate": 2.706531177836896e-06,
	"loss": 0.04974370449781418,
	"step": 884
	},
	{
	"epoch": 3.5298804780876494,
	"grad_norm": 0.7920284271240234,
	"learning_rate": 2.683665695223827e-06,
	"loss": 0.46149638295173645,
	"step": 886
	},
	{
	"epoch": 3.537848605577689,
	"grad_norm": 0.3813696801662445,
	"learning_rate": 2.661161709280954e-06,
	"loss": 0.47457778453826904,
	"step": 888
	},
	{
	"epoch": 3.545816733067729,
	"grad_norm": 0.4823150932788849,
	"learning_rate": 2.6390201982176284e-06,
	"loss": 0.2846560478210449,
	"step": 890
	},
	{
	"epoch": 3.553784860557769,
	"grad_norm": 1.2098549604415894,
	"learning_rate": 2.617242124487048e-06,
	"loss": 0.3184957206249237,
	"step": 892
	},
	{
	"epoch": 3.5617529880478087,
	"grad_norm": 0.2593185305595398,
	"learning_rate": 2.595828434744411e-06,
	"loss": 0.7096160650253296,
	"step": 894
	},
	{
	"epoch": 3.5697211155378485,
	"grad_norm": 0.10369162261486053,
	"learning_rate": 2.574780059805779e-06,
	"loss": 0.10589734464883804,
	"step": 896
	},
	{
	"epoch": 3.5776892430278884,
	"grad_norm": 0.26918283104896545,
	"learning_rate": 2.5540979146076145e-06,
	"loss": 0.2939029335975647,
	"step": 898
	},
	{
	"epoch": 3.585657370517928,
	"grad_norm": 0.2926011383533478,
	"learning_rate": 2.5337828981669966e-06,
	"loss": 0.09356319904327393,
	"step": 900
	},
	{
	"epoch": 3.593625498007968,
	"grad_norm": 1.341439962387085,
	"learning_rate": 2.513835893542561e-06,
	"loss": 0.09488323330879211,
	"step": 902
	},
	{
	"epoch": 3.601593625498008,
	"grad_norm": 0.47240838408470154,
	"learning_rate": 2.494257767796101e-06,
	"loss": 0.3548218905925751,
	"step": 904
	},
	{
	"epoch": 3.6095617529880477,
	"grad_norm": 0.49076366424560547,
	"learning_rate": 2.475049371954888e-06,
	"loss": 0.2988426685333252,
	"step": 906
	},
	{
	"epoch": 3.6175298804780875,
	"grad_norm": 0.2681836783885956,
	"learning_rate": 2.4562115409746662e-06,
	"loss": 0.5401598215103149,
	"step": 908
	},
	{
	"epoch": 3.6254980079681274,
	"grad_norm": 0.406819611787796,
	"learning_rate": 2.4377450937033753e-06,
	"loss": 0.4441235661506653,
	"step": 910
	},
	{
	"epoch": 3.633466135458167,
	"grad_norm": 0.05496419966220856,
	"learning_rate": 2.419650832845541e-06,
	"loss": 0.019690319895744324,
	"step": 912
	},
	{
	"epoch": 3.641434262948207,
	"grad_norm": 0.29483741521835327,
	"learning_rate": 2.40192954492739e-06,
	"loss": 0.4060436189174652,
	"step": 914
	},
	{
	"epoch": 3.649402390438247,
	"grad_norm": 0.4651680290699005,
	"learning_rate": 2.3845820002626623e-06,
	"loss": 0.4076462984085083,
	"step": 916
	},
	{
	"epoch": 3.6573705179282867,
	"grad_norm": 2.9567272663116455,
	"learning_rate": 2.3676089529191234e-06,
	"loss": 0.047276318073272705,
	"step": 918
	},
	{
	"epoch": 3.6653386454183265,
	"grad_norm": 0.32289329171180725,
	"learning_rate": 2.3510111406857915e-06,
	"loss": 0.5000100135803223,
	"step": 920
	},
	{
	"epoch": 3.6733067729083664,
	"grad_norm": 0.23058217763900757,
	"learning_rate": 2.3347892850408575e-06,
	"loss": 0.06835205107927322,
	"step": 922
	},
	{
	"epoch": 3.681274900398406,
	"grad_norm": 1.3678746223449707,
	"learning_rate": 2.3189440911203328e-06,
	"loss": 0.35598766803741455,
	"step": 924
	},
	{
	"epoch": 3.6892430278884465,
	"grad_norm": 0.30284255743026733,
	"learning_rate": 2.3034762476873973e-06,
	"loss": 0.13118457794189453,
	"step": 926
	},
	{
	"epoch": 3.6972111553784863,
	"grad_norm": 0.8098158836364746,
	"learning_rate": 2.2883864271024524e-06,
	"loss": 0.29144927859306335,
	"step": 928
	},
	{
	"epoch": 3.705179282868526,
	"grad_norm": 0.131113201379776,
	"learning_rate": 2.273675285293905e-06,
	"loss": 0.4039907455444336,
	"step": 930
	},
	{
	"epoch": 3.713147410358566,
	"grad_norm": 0.34469276666641235,
	"learning_rate": 2.2593434617296474e-06,
	"loss": 0.5197895765304565,
	"step": 932
	},
	{
	"epoch": 3.721115537848606,
	"grad_norm": 0.2677764296531677,
	"learning_rate": 2.2453915793892665e-06,
	"loss": 0.23381216824054718,
	"step": 934
	},
	{
	"epoch": 3.7290836653386457,
	"grad_norm": 0.4345526099205017,
	"learning_rate": 2.231820244736958e-06,
	"loss": 0.4805620014667511,
	"step": 936
	},
	{
	"epoch": 3.7370517928286855,
	"grad_norm": 0.4274682402610779,
	"learning_rate": 2.2186300476951693e-06,
	"loss": 0.1564408391714096,
	"step": 938
	},
	{
	"epoch": 3.7450199203187253,
	"grad_norm": 1.1103200912475586,
	"learning_rate": 2.2058215616189578e-06,
	"loss": 0.47250640392303467,
	"step": 940
	},
	{
	"epoch": 3.752988047808765,
	"grad_norm": 0.2901248037815094,
	"learning_rate": 2.1933953432710588e-06,
	"loss": 0.25581350922584534,
	"step": 942
	},
	{
	"epoch": 3.760956175298805,
	"grad_norm": 0.2037886381149292,
	"learning_rate": 2.181351932797695e-06,
	"loss": 0.3167116641998291,
	"step": 944
	},
	{
	"epoch": 3.768924302788845,
	"grad_norm": 0.36940625309944153,
	"learning_rate": 2.169691853705094e-06,
	"loss": 0.6154989004135132,
	"step": 946
	},
	{
	"epoch": 3.7768924302788847,
	"grad_norm": 0.3643878102302551,
	"learning_rate": 2.1584156128367303e-06,
	"loss": 0.3078484535217285,
	"step": 948
	},
	{
	"epoch": 3.7848605577689245,
	"grad_norm": 0.4483620822429657,
	"learning_rate": 2.147523700351291e-06,
	"loss": 0.5290223956108093,
	"step": 950
	},
	{
	"epoch": 3.7928286852589643,
	"grad_norm": 0.5038286447525024,
	"learning_rate": 2.137016589701375e-06,
	"loss": 0.5246944427490234,
	"step": 952
	},
	{
	"epoch": 3.800796812749004,
	"grad_norm": 0.3047266900539398,
	"learning_rate": 2.126894737612914e-06,
	"loss": 0.29258349537849426,
	"step": 954
	},
	{
	"epoch": 3.808764940239044,
	"grad_norm": 0.3544226884841919,
	"learning_rate": 2.117158584065313e-06,
	"loss": 0.3819803297519684,
	"step": 956
	},
	{
	"epoch": 3.816733067729084,
	"grad_norm": 0.9558009505271912,
	"learning_rate": 2.107808552272329e-06,
	"loss": 0.25099891424179077,
	"step": 958
	},
	{
	"epoch": 3.8247011952191237,
	"grad_norm": 0.3349020779132843,
	"learning_rate": 2.0988450486636745e-06,
	"loss": 0.17486253380775452,
	"step": 960
	},
	{
	"epoch": 3.8326693227091635,
	"grad_norm": 0.13526098430156708,
	"learning_rate": 2.090268462867351e-06,
	"loss": 0.31952333450317383,
	"step": 962
	},
	{
	"epoch": 3.8406374501992033,
	"grad_norm": 0.412202388048172,
	"learning_rate": 2.0820791676927093e-06,
	"loss": 0.6047512292861938,
	"step": 964
	},
	{
	"epoch": 3.848605577689243,
	"grad_norm": 0.3296831250190735,
	"learning_rate": 2.0742775191142496e-06,
	"loss": 0.16787327826023102,
	"step": 966
	},
	{
	"epoch": 3.856573705179283,
	"grad_norm": 0.28071603178977966,
	"learning_rate": 2.066863856256143e-06,
	"loss": 0.3841116726398468,
	"step": 968
	},
	{
	"epoch": 3.864541832669323,
	"grad_norm": 0.29851338267326355,
	"learning_rate": 2.0598385013774933e-06,
	"loss": 0.346584677696228,
	"step": 970
	},
	{
	"epoch": 3.8725099601593627,
	"grad_norm": 0.03955311328172684,
	"learning_rate": 2.053201759858327e-06,
	"loss": 0.2920938730239868,
	"step": 972
	},
	{
	"epoch": 3.8804780876494025,
	"grad_norm": 0.051783155649900436,
	"learning_rate": 2.0469539201863224e-06,
	"loss": 0.2272939682006836,
	"step": 974
	},
	{
	"epoch": 3.8884462151394423,
	"grad_norm": 0.3298843204975128,
	"learning_rate": 2.0410952539442624e-06,
	"loss": 0.5179523229598999,
	"step": 976
	},
	{
	"epoch": 3.896414342629482,
	"grad_norm": 0.28545433282852173,
	"learning_rate": 2.0356260157982393e-06,
	"loss": 0.27209949493408203,
	"step": 978
	},
	{
	"epoch": 3.904382470119522,
	"grad_norm": 1.0891438722610474,
	"learning_rate": 2.030546443486575e-06,
	"loss": 0.24100713431835175,
	"step": 980
	},
	{
	"epoch": 3.912350597609562,
	"grad_norm": 0.6865116357803345,
	"learning_rate": 2.0258567578094947e-06,
	"loss": 0.18800026178359985,
	"step": 982
	},
	{
	"epoch": 3.9203187250996017,
	"grad_norm": 0.24787557125091553,
	"learning_rate": 2.0215571626195242e-06,
	"loss": 0.5200425982475281,
	"step": 984
	},
	{
	"epoch": 3.9282868525896415,
	"grad_norm": 0.6841551065444946,
	"learning_rate": 2.0176478448126306e-06,
	"loss": 0.1371404379606247,
	"step": 986
	},
	{
	"epoch": 3.9362549800796813,
	"grad_norm": 1.6476190090179443,
	"learning_rate": 2.014128974320099e-06,
	"loss": 0.41096165776252747,
	"step": 988
	},
	{
	"epoch": 3.944223107569721,
	"grad_norm": 0.20494024455547333,
	"learning_rate": 2.011000704101143e-06,
	"loss": 0.30098965764045715,
	"step": 990
	},
	{
	"epoch": 3.952191235059761,
	"grad_norm": 0.48796623945236206,
	"learning_rate": 2.00826317013626e-06,
	"loss": 0.5071312785148621,
	"step": 992
	},
	{
	"epoch": 3.960159362549801,
	"grad_norm": 0.33370301127433777,
	"learning_rate": 2.0059164914213175e-06,
	"loss": 0.13360963761806488,
	"step": 994
	},
	{
	"epoch": 3.9681274900398407,
	"grad_norm": 0.24733327329158783,
	"learning_rate": 2.00396076996238e-06,
	"loss": 0.41967302560806274,
	"step": 996
	},
	{
	"epoch": 3.9760956175298805,
	"grad_norm": 0.22083163261413574,
	"learning_rate": 2.0023960907712782e-06,
	"loss": 0.3552241027355194,
	"step": 998
	},
	{
	"epoch": 3.9840637450199203,
	"grad_norm": 0.4792640805244446,
	"learning_rate": 2.0012225218619097e-06,
	"loss": 0.2334318608045578,
	"step": 1000
	},
	{
	"epoch": 3.99203187250996,
	"grad_norm": 0.2573681175708771,
	"learning_rate": 2.0004401142472857e-06,
	"loss": 0.5154892802238464,
	"step": 1002
	},
	{
	"epoch": 4.0,
	"grad_norm": 0.1436181664466858,
	"learning_rate": 2.000048901937313e-06,
	"loss": 0.12288407981395721,
	"step": 1004
	},
	{
	"epoch": 4.0,
	"step": 1004,
	"total_flos": 4.038502240003031e+18,
	"train_loss": 0.7417308912200637,
	"train_runtime": 11316.072,
	"train_samples_per_second": 5.323,
	"train_steps_per_second": 0.089
	}
	],
	"logging_steps": 2,
	"max_steps": 1004,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 4,
	"save_steps": 99999,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": false,
	"should_training_stop": false
	},
	"attributes": {}
	}
	},
	"total_flos": 4.038502240003031e+18,
	"train_batch_size": 3,
	"trial_name": null,
	"trial_params": null
	}