Instructions to use furproxy/9b-54 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use furproxy/9b-54 with Transformers:

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

pipe = pipeline("image-text-to-text", model="furproxy/9b-54")
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-54")
model = AutoModelForImageTextToText.from_pretrained("furproxy/9b-54")
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-54 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "furproxy/9b-54"
# 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-54",
		"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-54

SGLang

How to use furproxy/9b-54 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-54" \
    --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-54",
		"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-54" \
        --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-54",
		"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-54 with Docker Model Runner:
```
docker model run hf.co/furproxy/9b-54
```

9b-54 / trainer_state.json

furproxy

Upload folder using huggingface_hub

ee2cdea verified about 2 months ago

raw

history blame contribute delete

103 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 3.0,
	"eval_steps": 500,
	"global_step": 1098,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.00546448087431694,
	"grad_norm": 0.23241105675697327,
	"learning_rate": 3.6363636363636366e-07,
	"loss": 2.7663679122924805,
	"step": 2
	},
	{
	"epoch": 0.01092896174863388,
	"grad_norm": 0.20422983169555664,
	"learning_rate": 1.090909090909091e-06,
	"loss": 1.9384474754333496,
	"step": 4
	},
	{
	"epoch": 0.01639344262295082,
	"grad_norm": 0.199067622423172,
	"learning_rate": 1.8181818181818183e-06,
	"loss": 1.9044784307479858,
	"step": 6
	},
	{
	"epoch": 0.02185792349726776,
	"grad_norm": 0.23435044288635254,
	"learning_rate": 2.5454545454545456e-06,
	"loss": 1.7989522218704224,
	"step": 8
	},
	{
	"epoch": 0.0273224043715847,
	"grad_norm": 0.22486603260040283,
	"learning_rate": 3.272727272727273e-06,
	"loss": 1.8125925064086914,
	"step": 10
	},
	{
	"epoch": 0.03278688524590164,
	"grad_norm": 0.16707547008991241,
	"learning_rate": 4.000000000000001e-06,
	"loss": 1.6252872943878174,
	"step": 12
	},
	{
	"epoch": 0.03825136612021858,
	"grad_norm": 0.11193601042032242,
	"learning_rate": 4.727272727272728e-06,
	"loss": 1.5324492454528809,
	"step": 14
	},
	{
	"epoch": 0.04371584699453552,
	"grad_norm": 0.10569358617067337,
	"learning_rate": 5.4545454545454545e-06,
	"loss": 1.2910876274108887,
	"step": 16
	},
	{
	"epoch": 0.04918032786885246,
	"grad_norm": 0.2930830419063568,
	"learning_rate": 6.181818181818182e-06,
	"loss": 1.1632479429244995,
	"step": 18
	},
	{
	"epoch": 0.0546448087431694,
	"grad_norm": 0.16945035755634308,
	"learning_rate": 6.90909090909091e-06,
	"loss": 1.4446367025375366,
	"step": 20
	},
	{
	"epoch": 0.060109289617486336,
	"grad_norm": 0.16067177057266235,
	"learning_rate": 7.636363636363638e-06,
	"loss": 1.2816951274871826,
	"step": 22
	},
	{
	"epoch": 0.06557377049180328,
	"grad_norm": 0.11728192120790482,
	"learning_rate": 8.363636363636365e-06,
	"loss": 1.4356242418289185,
	"step": 24
	},
	{
	"epoch": 0.07103825136612021,
	"grad_norm": 0.33978065848350525,
	"learning_rate": 9.090909090909091e-06,
	"loss": 1.6120140552520752,
	"step": 26
	},
	{
	"epoch": 0.07650273224043716,
	"grad_norm": 0.13070262968540192,
	"learning_rate": 9.81818181818182e-06,
	"loss": 1.393876314163208,
	"step": 28
	},
	{
	"epoch": 0.08196721311475409,
	"grad_norm": 0.10509130358695984,
	"learning_rate": 1.0545454545454546e-05,
	"loss": 1.2700122594833374,
	"step": 30
	},
	{
	"epoch": 0.08743169398907104,
	"grad_norm": 0.1495838314294815,
	"learning_rate": 1.1272727272727272e-05,
	"loss": 1.3333828449249268,
	"step": 32
	},
	{
	"epoch": 0.09289617486338798,
	"grad_norm": 0.5792630314826965,
	"learning_rate": 1.2e-05,
	"loss": 1.0171189308166504,
	"step": 34
	},
	{
	"epoch": 0.09836065573770492,
	"grad_norm": 0.09606198966503143,
	"learning_rate": 1.2727272727272728e-05,
	"loss": 1.119741439819336,
	"step": 36
	},
	{
	"epoch": 0.10382513661202186,
	"grad_norm": 0.12487119436264038,
	"learning_rate": 1.3454545454545455e-05,
	"loss": 1.3798904418945312,
	"step": 38
	},
	{
	"epoch": 0.1092896174863388,
	"grad_norm": 0.07102937251329422,
	"learning_rate": 1.4181818181818183e-05,
	"loss": 1.3242915868759155,
	"step": 40
	},
	{
	"epoch": 0.11475409836065574,
	"grad_norm": 0.19717426598072052,
	"learning_rate": 1.4909090909090911e-05,
	"loss": 0.9329365491867065,
	"step": 42
	},
	{
	"epoch": 0.12021857923497267,
	"grad_norm": 0.08408994972705841,
	"learning_rate": 1.563636363636364e-05,
	"loss": 0.8571876883506775,
	"step": 44
	},
	{
	"epoch": 0.12568306010928962,
	"grad_norm": 0.09981869906187057,
	"learning_rate": 1.6363636363636366e-05,
	"loss": 1.3420907258987427,
	"step": 46
	},
	{
	"epoch": 0.13114754098360656,
	"grad_norm": 0.11734086275100708,
	"learning_rate": 1.7090909090909092e-05,
	"loss": 1.304795503616333,
	"step": 48
	},
	{
	"epoch": 0.1366120218579235,
	"grad_norm": 0.14026959240436554,
	"learning_rate": 1.781818181818182e-05,
	"loss": 1.269639492034912,
	"step": 50
	},
	{
	"epoch": 0.14207650273224043,
	"grad_norm": 0.12195869535207748,
	"learning_rate": 1.8545454545454545e-05,
	"loss": 1.2368900775909424,
	"step": 52
	},
	{
	"epoch": 0.14754098360655737,
	"grad_norm": 0.32812365889549255,
	"learning_rate": 1.9272727272727275e-05,
	"loss": 0.7080382108688354,
	"step": 54
	},
	{
	"epoch": 0.15300546448087432,
	"grad_norm": 0.19641871750354767,
	"learning_rate": 2e-05,
	"loss": 1.4196542501449585,
	"step": 56
	},
	{
	"epoch": 0.15846994535519127,
	"grad_norm": 0.13444043695926666,
	"learning_rate": 1.9998327792599505e-05,
	"loss": 1.4084272384643555,
	"step": 58
	},
	{
	"epoch": 0.16393442622950818,
	"grad_norm": 0.16206051409244537,
	"learning_rate": 1.999331179179304e-05,
	"loss": 1.2947711944580078,
	"step": 60
	},
	{
	"epoch": 0.16939890710382513,
	"grad_norm": 0.13851064443588257,
	"learning_rate": 1.9984953861534752e-05,
	"loss": 1.5364221334457397,
	"step": 62
	},
	{
	"epoch": 0.17486338797814208,
	"grad_norm": 0.24502862989902496,
	"learning_rate": 1.997325710764527e-05,
	"loss": 1.1034942865371704,
	"step": 64
	},
	{
	"epoch": 0.18032786885245902,
	"grad_norm": 0.21653936803340912,
	"learning_rate": 1.9958225876657575e-05,
	"loss": 1.3003474473953247,
	"step": 66
	},
	{
	"epoch": 0.18579234972677597,
	"grad_norm": 0.12236165255308151,
	"learning_rate": 1.9939865754201825e-05,
	"loss": 1.2659997940063477,
	"step": 68
	},
	{
	"epoch": 0.1912568306010929,
	"grad_norm": 0.2843843996524811,
	"learning_rate": 1.9918183562929717e-05,
	"loss": 1.320336103439331,
	"step": 70
	},
	{
	"epoch": 0.19672131147540983,
	"grad_norm": 0.1539740264415741,
	"learning_rate": 1.9893187359979183e-05,
	"loss": 1.1016457080841064,
	"step": 72
	},
	{
	"epoch": 0.20218579234972678,
	"grad_norm": 0.1354515552520752,
	"learning_rate": 1.986488643398035e-05,
	"loss": 1.4368224143981934,
	"step": 74
	},
	{
	"epoch": 0.20765027322404372,
	"grad_norm": 0.14250975847244263,
	"learning_rate": 1.9833291301603863e-05,
	"loss": 1.3135349750518799,
	"step": 76
	},
	{
	"epoch": 0.21311475409836064,
	"grad_norm": 2.250478744506836,
	"learning_rate": 1.9798413703652867e-05,
	"loss": 1.1084109544754028,
	"step": 78
	},
	{
	"epoch": 0.2185792349726776,
	"grad_norm": 0.07655666023492813,
	"learning_rate": 1.976026660070012e-05,
	"loss": 0.7299535870552063,
	"step": 80
	},
	{
	"epoch": 0.22404371584699453,
	"grad_norm": 0.11502671241760254,
	"learning_rate": 1.9718864168271823e-05,
	"loss": 1.3118858337402344,
	"step": 82
	},
	{
	"epoch": 0.22950819672131148,
	"grad_norm": 0.11101143807172775,
	"learning_rate": 1.9674221791579946e-05,
	"loss": 0.7135340571403503,
	"step": 84
	},
	{
	"epoch": 0.23497267759562843,
	"grad_norm": 0.06640731543302536,
	"learning_rate": 1.9626356059805085e-05,
	"loss": 1.2577087879180908,
	"step": 86
	},
	{
	"epoch": 0.24043715846994534,
	"grad_norm": 0.10447928309440613,
	"learning_rate": 1.957528475993189e-05,
	"loss": 1.236086130142212,
	"step": 88
	},
	{
	"epoch": 0.2459016393442623,
	"grad_norm": 0.7586353421211243,
	"learning_rate": 1.952102687013938e-05,
	"loss": 0.9215405583381653,
	"step": 90
	},
	{
	"epoch": 0.25136612021857924,
	"grad_norm": 0.17681649327278137,
	"learning_rate": 1.946360255274863e-05,
	"loss": 1.3206024169921875,
	"step": 92
	},
	{
	"epoch": 0.2568306010928962,
	"grad_norm": 0.09881044924259186,
	"learning_rate": 1.9403033146730424e-05,
	"loss": 1.1016768217086792,
	"step": 94
	},
	{
	"epoch": 0.26229508196721313,
	"grad_norm": 0.18392790853977203,
	"learning_rate": 1.9339341159775647e-05,
	"loss": 1.5615978240966797,
	"step": 96
	},
	{
	"epoch": 0.2677595628415301,
	"grad_norm": 0.10873087495565414,
	"learning_rate": 1.9272550259931398e-05,
	"loss": 0.9698639512062073,
	"step": 98
	},
	{
	"epoch": 0.273224043715847,
	"grad_norm": 0.09143725037574768,
	"learning_rate": 1.9202685266805896e-05,
	"loss": 1.022253155708313,
	"step": 100
	},
	{
	"epoch": 0.2786885245901639,
	"grad_norm": 0.21886828541755676,
	"learning_rate": 1.9129772142345484e-05,
	"loss": 1.229724645614624,
	"step": 102
	},
	{
	"epoch": 0.28415300546448086,
	"grad_norm": 0.21221189200878143,
	"learning_rate": 1.9053837981187125e-05,
	"loss": 0.9091554284095764,
	"step": 104
	},
	{
	"epoch": 0.2896174863387978,
	"grad_norm": 0.16236251592636108,
	"learning_rate": 1.897491100058998e-05,
	"loss": 1.2335375547409058,
	"step": 106
	},
	{
	"epoch": 0.29508196721311475,
	"grad_norm": 0.1724518984556198,
	"learning_rate": 1.8893020529949838e-05,
	"loss": 1.3930922746658325,
	"step": 108
	},
	{
	"epoch": 0.3005464480874317,
	"grad_norm": 0.33721551299095154,
	"learning_rate": 1.880819699990027e-05,
	"loss": 1.2754117250442505,
	"step": 110
	},
	{
	"epoch": 0.30601092896174864,
	"grad_norm": 0.07887385040521622,
	"learning_rate": 1.8720471931004526e-05,
	"loss": 1.2538396120071411,
	"step": 112
	},
	{
	"epoch": 0.3114754098360656,
	"grad_norm": 0.2448997050523758,
	"learning_rate": 1.8629877922042485e-05,
	"loss": 1.3684722185134888,
	"step": 114
	},
	{
	"epoch": 0.31693989071038253,
	"grad_norm": 0.10887415707111359,
	"learning_rate": 1.8536448637896866e-05,
	"loss": 1.2443941831588745,
	"step": 116
	},
	{
	"epoch": 0.3224043715846995,
	"grad_norm": 0.09768451005220413,
	"learning_rate": 1.84402187970433e-05,
	"loss": 1.0020421743392944,
	"step": 118
	},
	{
	"epoch": 0.32786885245901637,
	"grad_norm": 0.20493730902671814,
	"learning_rate": 1.834122415864891e-05,
	"loss": 1.2622389793395996,
	"step": 120
	},
	{
	"epoch": 0.3333333333333333,
	"grad_norm": 0.22100353240966797,
	"learning_rate": 1.8239501509284123e-05,
	"loss": 1.334355354309082,
	"step": 122
	},
	{
	"epoch": 0.33879781420765026,
	"grad_norm": 0.10817477852106094,
	"learning_rate": 1.8135088649252725e-05,
	"loss": 0.9958959221839905,
	"step": 124
	},
	{
	"epoch": 0.3442622950819672,
	"grad_norm": 0.1272984892129898,
	"learning_rate": 1.8028024378545224e-05,
	"loss": 0.9933403134346008,
	"step": 126
	},
	{
	"epoch": 0.34972677595628415,
	"grad_norm": 0.15175071358680725,
	"learning_rate": 1.7918348482420692e-05,
	"loss": 1.309685230255127,
	"step": 128
	},
	{
	"epoch": 0.3551912568306011,
	"grad_norm": 0.08403439074754715,
	"learning_rate": 1.7806101716622486e-05,
	"loss": 1.237076759338379,
	"step": 130
	},
	{
	"epoch": 0.36065573770491804,
	"grad_norm": 0.0816800594329834,
	"learning_rate": 1.7691325792233378e-05,
	"loss": 1.1985251903533936,
	"step": 132
	},
	{
	"epoch": 0.366120218579235,
	"grad_norm": 0.1994868814945221,
	"learning_rate": 1.7574063360175625e-05,
	"loss": 1.0995125770568848,
	"step": 134
	},
	{
	"epoch": 0.37158469945355194,
	"grad_norm": 0.21855318546295166,
	"learning_rate": 1.745435799536183e-05,
	"loss": 0.9361122250556946,
	"step": 136
	},
	{
	"epoch": 0.3770491803278688,
	"grad_norm": 0.09870662540197372,
	"learning_rate": 1.7332254180502407e-05,
	"loss": 0.9252831935882568,
	"step": 138
	},
	{
	"epoch": 0.3825136612021858,
	"grad_norm": 0.16326409578323364,
	"learning_rate": 1.7207797289575777e-05,
	"loss": 0.5687403678894043,
	"step": 140
	},
	{
	"epoch": 0.3879781420765027,
	"grad_norm": 0.10890620201826096,
	"learning_rate": 1.708103357096728e-05,
	"loss": 1.2131319046020508,
	"step": 142
	},
	{
	"epoch": 0.39344262295081966,
	"grad_norm": 0.09764160215854645,
	"learning_rate": 1.695201013028322e-05,
	"loss": 1.2462400197982788,
	"step": 144
	},
	{
	"epoch": 0.3989071038251366,
	"grad_norm": 0.16440223157405853,
	"learning_rate": 1.6820774912846335e-05,
	"loss": 1.2056647539138794,
	"step": 146
	},
	{
	"epoch": 0.40437158469945356,
	"grad_norm": 0.3588426113128662,
	"learning_rate": 1.668737668587926e-05,
	"loss": 1.2008482217788696,
	"step": 148
	},
	{
	"epoch": 0.4098360655737705,
	"grad_norm": 0.11627013236284256,
	"learning_rate": 1.655186502038251e-05,
	"loss": 1.1384965181350708,
	"step": 150
	},
	{
	"epoch": 0.41530054644808745,
	"grad_norm": 0.08151569962501526,
	"learning_rate": 1.641429027271384e-05,
	"loss": 1.2373915910720825,
	"step": 152
	},
	{
	"epoch": 0.4207650273224044,
	"grad_norm": 0.11254062503576279,
	"learning_rate": 1.6274703565875736e-05,
	"loss": 1.2118054628372192,
	"step": 154
	},
	{
	"epoch": 0.4262295081967213,
	"grad_norm": 0.18413741886615753,
	"learning_rate": 1.613315677051801e-05,
	"loss": 1.2632805109024048,
	"step": 156
	},
	{
	"epoch": 0.43169398907103823,
	"grad_norm": 0.13130782544612885,
	"learning_rate": 1.598970248566261e-05,
	"loss": 0.971778154373169,
	"step": 158
	},
	{
	"epoch": 0.4371584699453552,
	"grad_norm": 0.11005275696516037,
	"learning_rate": 1.5844394019157697e-05,
	"loss": 1.1907391548156738,
	"step": 160
	},
	{
	"epoch": 0.4426229508196721,
	"grad_norm": 0.27727824449539185,
	"learning_rate": 1.5697285367868393e-05,
	"loss": 0.6190683841705322,
	"step": 162
	},
	{
	"epoch": 0.44808743169398907,
	"grad_norm": 0.14197178184986115,
	"learning_rate": 1.5548431197611448e-05,
	"loss": 1.5833417177200317,
	"step": 164
	},
	{
	"epoch": 0.453551912568306,
	"grad_norm": 0.4161648452281952,
	"learning_rate": 1.539788682284133e-05,
	"loss": 0.7078179717063904,
	"step": 166
	},
	{
	"epoch": 0.45901639344262296,
	"grad_norm": 0.10775762796401978,
	"learning_rate": 1.5245708186095275e-05,
	"loss": 1.1315946578979492,
	"step": 168
	},
	{
	"epoch": 0.4644808743169399,
	"grad_norm": 0.12663501501083374,
	"learning_rate": 1.5091951837204973e-05,
	"loss": 1.218740463256836,
	"step": 170
	},
	{
	"epoch": 0.46994535519125685,
	"grad_norm": 0.23885132372379303,
	"learning_rate": 1.4936674912282525e-05,
	"loss": 1.2896463871002197,
	"step": 172
	},
	{
	"epoch": 0.47540983606557374,
	"grad_norm": 0.8457244634628296,
	"learning_rate": 1.4779935112488597e-05,
	"loss": 1.4194824695587158,
	"step": 174
	},
	{
	"epoch": 0.4808743169398907,
	"grad_norm": 0.08335787802934647,
	"learning_rate": 1.4621790682590556e-05,
	"loss": 1.2021723985671997,
	"step": 176
	},
	{
	"epoch": 0.48633879781420764,
	"grad_norm": 0.10485303401947021,
	"learning_rate": 1.4462300389318635e-05,
	"loss": 1.1588122844696045,
	"step": 178
	},
	{
	"epoch": 0.4918032786885246,
	"grad_norm": 0.11188313364982605,
	"learning_rate": 1.4301523499528099e-05,
	"loss": 1.1702033281326294,
	"step": 180
	},
	{
	"epoch": 0.4972677595628415,
	"grad_norm": 0.12386136502027512,
	"learning_rate": 1.4139519758175602e-05,
	"loss": 1.1308914422988892,
	"step": 182
	},
	{
	"epoch": 0.5027322404371585,
	"grad_norm": 0.2648775577545166,
	"learning_rate": 1.3976349366117861e-05,
	"loss": 1.3322463035583496,
	"step": 184
	},
	{
	"epoch": 0.5081967213114754,
	"grad_norm": 0.1508917361497879,
	"learning_rate": 1.3812072957740898e-05,
	"loss": 1.1352683305740356,
	"step": 186
	},
	{
	"epoch": 0.5136612021857924,
	"grad_norm": 0.26597723364830017,
	"learning_rate": 1.3646751578428231e-05,
	"loss": 1.1803580522537231,
	"step": 188
	},
	{
	"epoch": 0.5191256830601093,
	"grad_norm": 0.09911347925662994,
	"learning_rate": 1.3480446661876295e-05,
	"loss": 1.22324538230896,
	"step": 190
	},
	{
	"epoch": 0.5245901639344263,
	"grad_norm": 0.2967340648174286,
	"learning_rate": 1.3313220007265572e-05,
	"loss": 1.1710972785949707,
	"step": 192
	},
	{
	"epoch": 0.5300546448087432,
	"grad_norm": 0.09805179387331009,
	"learning_rate": 1.3145133756295936e-05,
	"loss": 1.194231390953064,
	"step": 194
	},
	{
	"epoch": 0.5355191256830601,
	"grad_norm": 0.1383579820394516,
	"learning_rate": 1.2976250370094668e-05,
	"loss": 1.253728985786438,
	"step": 196
	},
	{
	"epoch": 0.5409836065573771,
	"grad_norm": 0.0955134779214859,
	"learning_rate": 1.2806632606005822e-05,
	"loss": 1.0406149625778198,
	"step": 198
	},
	{
	"epoch": 0.546448087431694,
	"grad_norm": 0.1062760204076767,
	"learning_rate": 1.2636343494269479e-05,
	"loss": 1.2303603887557983,
	"step": 200
	},
	{
	"epoch": 0.5519125683060109,
	"grad_norm": 0.0993717610836029,
	"learning_rate": 1.2465446314599609e-05,
	"loss": 1.0265294313430786,
	"step": 202
	},
	{
	"epoch": 0.5573770491803278,
	"grad_norm": 0.26846495270729065,
	"learning_rate": 1.2294004572669228e-05,
	"loss": 0.8886614441871643,
	"step": 204
	},
	{
	"epoch": 0.5628415300546448,
	"grad_norm": 0.1153939738869667,
	"learning_rate": 1.2122081976511581e-05,
	"loss": 1.2078245878219604,
	"step": 206
	},
	{
	"epoch": 0.5683060109289617,
	"grad_norm": 0.16638191044330597,
	"learning_rate": 1.1949742412846142e-05,
	"loss": 1.1955982446670532,
	"step": 208
	},
	{
	"epoch": 0.5737704918032787,
	"grad_norm": 0.12783703207969666,
	"learning_rate": 1.177704992333818e-05,
	"loss": 1.194825291633606,
	"step": 210
	},
	{
	"epoch": 0.5792349726775956,
	"grad_norm": 0.10933943092823029,
	"learning_rate": 1.1604068680800809e-05,
	"loss": 1.4728552103042603,
	"step": 212
	},
	{
	"epoch": 0.5846994535519126,
	"grad_norm": 0.09695154428482056,
	"learning_rate": 1.1430862965348224e-05,
	"loss": 1.187117099761963,
	"step": 214
	},
	{
	"epoch": 0.5901639344262295,
	"grad_norm": 0.1849643737077713,
	"learning_rate": 1.1257497140509141e-05,
	"loss": 1.547567367553711,
	"step": 216
	},
	{
	"epoch": 0.5956284153005464,
	"grad_norm": 0.11740607768297195,
	"learning_rate": 1.1084035629309176e-05,
	"loss": 1.1611906290054321,
	"step": 218
	},
	{
	"epoch": 0.6010928961748634,
	"grad_norm": 0.20028969645500183,
	"learning_rate": 1.0910542890331162e-05,
	"loss": 1.2552645206451416,
	"step": 220
	},
	{
	"epoch": 0.6065573770491803,
	"grad_norm": 0.21303501725196838,
	"learning_rate": 1.0737083393762213e-05,
	"loss": 1.0489044189453125,
	"step": 222
	},
	{
	"epoch": 0.6120218579234973,
	"grad_norm": 0.47717615962028503,
	"learning_rate": 1.0563721597436525e-05,
	"loss": 1.0029484033584595,
	"step": 224
	},
	{
	"epoch": 0.6174863387978142,
	"grad_norm": 0.09277418255805969,
	"learning_rate": 1.039052192288271e-05,
	"loss": 1.2073832750320435,
	"step": 226
	},
	{
	"epoch": 0.6229508196721312,
	"grad_norm": 1.184064269065857,
	"learning_rate": 1.0217548731384677e-05,
	"loss": 1.2144676446914673,
	"step": 228
	},
	{
	"epoch": 0.6284153005464481,
	"grad_norm": 0.08467663079500198,
	"learning_rate": 1.0044866300064842e-05,
	"loss": 0.6675528287887573,
	"step": 230
	},
	{
	"epoch": 0.6338797814207651,
	"grad_norm": 0.12579751014709473,
	"learning_rate": 9.872538797998672e-06,
	"loss": 1.21137273311615,
	"step": 232
	},
	{
	"epoch": 0.639344262295082,
	"grad_norm": 0.20576755702495575,
	"learning_rate": 9.700630262369337e-06,
	"loss": 0.9463342428207397,
	"step": 234
	},
	{
	"epoch": 0.644808743169399,
	"grad_norm": 0.11935203522443771,
	"learning_rate": 9.529204574671391e-06,
	"loss": 0.8104769587516785,
	"step": 236
	},
	{
	"epoch": 0.6502732240437158,
	"grad_norm": 0.1750505119562149,
	"learning_rate": 9.3583254369723e-06,
	"loss": 1.2798433303833008,
	"step": 238
	},
	{
	"epoch": 0.6557377049180327,
	"grad_norm": 0.2776470184326172,
	"learning_rate": 9.188056348240655e-06,
	"loss": 1.2103146314620972,
	"step": 240
	},
	{
	"epoch": 0.6612021857923497,
	"grad_norm": 0.3298132121562958,
	"learning_rate": 9.018460580749842e-06,
	"loss": 1.1388304233551025,
	"step": 242
	},
	{
	"epoch": 0.6666666666666666,
	"grad_norm": 0.11938371509313583,
	"learning_rate": 8.849601156565972e-06,
	"loss": 0.9363460540771484,
	"step": 244
	},
	{
	"epoch": 0.6721311475409836,
	"grad_norm": 0.09460209310054779,
	"learning_rate": 8.68154082412877e-06,
	"loss": 1.1563094854354858,
	"step": 246
	},
	{
	"epoch": 0.6775956284153005,
	"grad_norm": 0.15788520872592926,
	"learning_rate": 8.514342034934159e-06,
	"loss": 1.2280900478363037,
	"step": 248
	},
	{
	"epoch": 0.6830601092896175,
	"grad_norm": 0.948505163192749,
	"learning_rate": 8.348066920327163e-06,
	"loss": 1.1906379461288452,
	"step": 250
	},
	{
	"epoch": 0.6885245901639344,
	"grad_norm": 0.12994378805160522,
	"learning_rate": 8.182777268413822e-06,
	"loss": 1.0413599014282227,
	"step": 252
	},
	{
	"epoch": 0.6939890710382514,
	"grad_norm": 0.1265498697757721,
	"learning_rate": 8.018534501100611e-06,
	"loss": 1.1458451747894287,
	"step": 254
	},
	{
	"epoch": 0.6994535519125683,
	"grad_norm": 0.11216244846582413,
	"learning_rate": 7.855399651269982e-06,
	"loss": 1.1375198364257812,
	"step": 256
	},
	{
	"epoch": 0.7049180327868853,
	"grad_norm": 0.10773710161447525,
	"learning_rate": 7.6934333401004e-06,
	"loss": 1.0727012157440186,
	"step": 258
	},
	{
	"epoch": 0.7103825136612022,
	"grad_norm": 0.12872548401355743,
	"learning_rate": 7.53269575453947e-06,
	"loss": 1.1428802013397217,
	"step": 260
	},
	{
	"epoch": 0.7158469945355191,
	"grad_norm": 0.20889542996883392,
	"learning_rate": 7.373246624938324e-06,
	"loss": 1.2273454666137695,
	"step": 262
	},
	{
	"epoch": 0.7213114754098361,
	"grad_norm": 0.21219481527805328,
	"learning_rate": 7.215145202855746e-06,
	"loss": 1.1816091537475586,
	"step": 264
	},
	{
	"epoch": 0.726775956284153,
	"grad_norm": 0.10101748257875443,
	"learning_rate": 7.0584502390401865e-06,
	"loss": 0.9967770576477051,
	"step": 266
	},
	{
	"epoch": 0.73224043715847,
	"grad_norm": 0.22779417037963867,
	"learning_rate": 6.903219961597891e-06,
	"loss": 1.1276934146881104,
	"step": 268
	},
	{
	"epoch": 0.7377049180327869,
	"grad_norm": 0.0829336941242218,
	"learning_rate": 6.7495120543552475e-06,
	"loss": 1.172729730606079,
	"step": 270
	},
	{
	"epoch": 0.7431693989071039,
	"grad_norm": 0.1042322888970375,
	"learning_rate": 6.59738363542336e-06,
	"loss": 1.133504867553711,
	"step": 272
	},
	{
	"epoch": 0.7486338797814208,
	"grad_norm": 0.12385440617799759,
	"learning_rate": 6.446891235972894e-06,
	"loss": 1.1612567901611328,
	"step": 274
	},
	{
	"epoch": 0.7540983606557377,
	"grad_norm": 0.2772475779056549,
	"learning_rate": 6.298090779226977e-06,
	"loss": 1.207811951637268,
	"step": 276
	},
	{
	"epoch": 0.7595628415300546,
	"grad_norm": 0.11887267976999283,
	"learning_rate": 6.151037559680047e-06,
	"loss": 1.1781216859817505,
	"step": 278
	},
	{
	"epoch": 0.7650273224043715,
	"grad_norm": 0.24976657330989838,
	"learning_rate": 6.005786222550319e-06,
	"loss": 0.8156208992004395,
	"step": 280
	},
	{
	"epoch": 0.7704918032786885,
	"grad_norm": 0.09995827078819275,
	"learning_rate": 5.8623907434735515e-06,
	"loss": 1.2025524377822876,
	"step": 282
	},
	{
	"epoch": 0.7759562841530054,
	"grad_norm": 0.17814989387989044,
	"learning_rate": 5.720904408445589e-06,
	"loss": 1.1644903421401978,
	"step": 284
	},
	{
	"epoch": 0.7814207650273224,
	"grad_norm": 0.08649664372205734,
	"learning_rate": 5.581379794021202e-06,
	"loss": 1.1790955066680908,
	"step": 286
	},
	{
	"epoch": 0.7868852459016393,
	"grad_norm": 0.13469792902469635,
	"learning_rate": 5.443868747776579e-06,
	"loss": 1.1462353467941284,
	"step": 288
	},
	{
	"epoch": 0.7923497267759563,
	"grad_norm": 0.08754783868789673,
	"learning_rate": 5.308422369042644e-06,
	"loss": 1.0591084957122803,
	"step": 290
	},
	{
	"epoch": 0.7978142076502732,
	"grad_norm": 0.5429996252059937,
	"learning_rate": 5.175090989916483e-06,
	"loss": 1.1352485418319702,
	"step": 292
	},
	{
	"epoch": 0.8032786885245902,
	"grad_norm": 0.0844668596982956,
	"learning_rate": 5.043924156557844e-06,
	"loss": 1.1482046842575073,
	"step": 294
	},
	{
	"epoch": 0.8087431693989071,
	"grad_norm": 0.7184237837791443,
	"learning_rate": 4.914970610777725e-06,
	"loss": 1.4919184446334839,
	"step": 296
	},
	{
	"epoch": 0.8142076502732241,
	"grad_norm": 0.13735006749629974,
	"learning_rate": 4.788278271925802e-06,
	"loss": 0.8253867626190186,
	"step": 298
	},
	{
	"epoch": 0.819672131147541,
	"grad_norm": 0.1467600017786026,
	"learning_rate": 4.663894219083548e-06,
	"loss": 1.5542583465576172,
	"step": 300
	},
	{
	"epoch": 0.825136612021858,
	"grad_norm": 0.19855302572250366,
	"learning_rate": 4.541864673569551e-06,
	"loss": 1.1880155801773071,
	"step": 302
	},
	{
	"epoch": 0.8306010928961749,
	"grad_norm": 0.06581619381904602,
	"learning_rate": 4.422234981763613e-06,
	"loss": 0.719045877456665,
	"step": 304
	},
	{
	"epoch": 0.8360655737704918,
	"grad_norm": 0.24002951383590698,
	"learning_rate": 4.305049598255946e-06,
	"loss": 1.526334285736084,
	"step": 306
	},
	{
	"epoch": 0.8415300546448088,
	"grad_norm": 0.12296368926763535,
	"learning_rate": 4.190352069327777e-06,
	"loss": 0.8090255856513977,
	"step": 308
	},
	{
	"epoch": 0.8469945355191257,
	"grad_norm": 0.11732060462236404,
	"learning_rate": 4.078185016769484e-06,
	"loss": 1.188048005104065,
	"step": 310
	},
	{
	"epoch": 0.8524590163934426,
	"grad_norm": 0.11243297159671783,
	"learning_rate": 3.968590122042265e-06,
	"loss": 1.1868927478790283,
	"step": 312
	},
	{
	"epoch": 0.8579234972677595,
	"grad_norm": 0.19882725179195404,
	"learning_rate": 3.861608110789228e-06,
	"loss": 1.194838285446167,
	"step": 314
	},
	{
	"epoch": 0.8633879781420765,
	"grad_norm": 0.1381818950176239,
	"learning_rate": 3.757278737701697e-06,
	"loss": 1.203479528427124,
	"step": 316
	},
	{
	"epoch": 0.8688524590163934,
	"grad_norm": 0.12520438432693481,
	"learning_rate": 3.6556407717462856e-06,
	"loss": 1.0257017612457275,
	"step": 318
	},
	{
	"epoch": 0.8743169398907104,
	"grad_norm": 0.09709858149290085,
	"learning_rate": 3.5567319817582944e-06,
	"loss": 1.3691281080245972,
	"step": 320
	},
	{
	"epoch": 0.8797814207650273,
	"grad_norm": 0.08708924800157547,
	"learning_rate": 3.4605891224067423e-06,
	"loss": 1.0822453498840332,
	"step": 322
	},
	{
	"epoch": 0.8852459016393442,
	"grad_norm": 0.10322949290275574,
	"learning_rate": 3.3672479205362764e-06,
	"loss": 0.46839311718940735,
	"step": 324
	},
	{
	"epoch": 0.8907103825136612,
	"grad_norm": 0.15026327967643738,
	"learning_rate": 3.276743061891014e-06,
	"loss": 1.159508228302002,
	"step": 326
	},
	{
	"epoch": 0.8961748633879781,
	"grad_norm": 0.295035183429718,
	"learning_rate": 3.1891081782252726e-06,
	"loss": 1.0394455194473267,
	"step": 328
	},
	{
	"epoch": 0.9016393442622951,
	"grad_norm": 0.11241143941879272,
	"learning_rate": 3.1043758348059384e-06,
	"loss": 1.2095626592636108,
	"step": 330
	},
	{
	"epoch": 0.907103825136612,
	"grad_norm": 0.20652705430984497,
	"learning_rate": 3.0225775183111784e-06,
	"loss": 1.2480474710464478,
	"step": 332
	},
	{
	"epoch": 0.912568306010929,
	"grad_norm": 0.12176910787820816,
	"learning_rate": 2.943743625129917e-06,
	"loss": 0.9860284924507141,
	"step": 334
	},
	{
	"epoch": 0.9180327868852459,
	"grad_norm": 0.7734562754631042,
	"learning_rate": 2.867903450066513e-06,
	"loss": 1.1385536193847656,
	"step": 336
	},
	{
	"epoch": 0.9234972677595629,
	"grad_norm": 0.1453840732574463,
	"learning_rate": 2.795085175454741e-06,
	"loss": 1.1383990049362183,
	"step": 338
	},
	{
	"epoch": 0.9289617486338798,
	"grad_norm": 0.11631204187870026,
	"learning_rate": 2.7253158606851983e-06,
	"loss": 1.151549220085144,
	"step": 340
	},
	{
	"epoch": 0.9344262295081968,
	"grad_norm": 0.4026157855987549,
	"learning_rate": 2.6586214321499952e-06,
	"loss": 1.23691987991333,
	"step": 342
	},
	{
	"epoch": 0.9398907103825137,
	"grad_norm": 0.3281600773334503,
	"learning_rate": 2.5950266736084558e-06,
	"loss": 1.1340752840042114,
	"step": 344
	},
	{
	"epoch": 0.9453551912568307,
	"grad_norm": 0.1483088731765747,
	"learning_rate": 2.5345552169774413e-06,
	"loss": 1.5082932710647583,
	"step": 346
	},
	{
	"epoch": 0.9508196721311475,
	"grad_norm": 0.1787729412317276,
	"learning_rate": 2.477229533549685e-06,
	"loss": 0.7625555396080017,
	"step": 348
	},
	{
	"epoch": 0.9562841530054644,
	"grad_norm": 0.09882060438394547,
	"learning_rate": 2.423070925643422e-06,
	"loss": 0.7790077924728394,
	"step": 350
	},
	{
	"epoch": 0.9617486338797814,
	"grad_norm": 0.09993410110473633,
	"learning_rate": 2.372099518686416e-06,
	"loss": 1.1514798402786255,
	"step": 352
	},
	{
	"epoch": 0.9672131147540983,
	"grad_norm": 0.0816822201013565,
	"learning_rate": 2.324334253737321e-06,
	"loss": 0.8181242942810059,
	"step": 354
	},
	{
	"epoch": 0.9726775956284153,
	"grad_norm": 0.13193772733211517,
	"learning_rate": 2.2797928804471413e-06,
	"loss": 1.0354417562484741,
	"step": 356
	},
	{
	"epoch": 0.9781420765027322,
	"grad_norm": 0.09249108284711838,
	"learning_rate": 2.2384919504634465e-06,
	"loss": 0.6940630674362183,
	"step": 358
	},
	{
	"epoch": 0.9836065573770492,
	"grad_norm": 0.10684558004140854,
	"learning_rate": 2.2004468112797345e-06,
	"loss": 1.154773473739624,
	"step": 360
	},
	{
	"epoch": 0.9890710382513661,
	"grad_norm": 0.19959105551242828,
	"learning_rate": 2.165671600532298e-06,
	"loss": 0.9004580974578857,
	"step": 362
	},
	{
	"epoch": 0.994535519125683,
	"grad_norm": 0.08442464470863342,
	"learning_rate": 2.134179240746638e-06,
	"loss": 1.1354343891143799,
	"step": 364
	},
	{
	"epoch": 1.0,
	"grad_norm": 0.13439127802848816,
	"learning_rate": 2.1059814345354434e-06,
	"loss": 1.111499309539795,
	"step": 366
	},
	{
	"epoch": 1.005464480874317,
	"grad_norm": 0.3562772274017334,
	"learning_rate": 2.0810886602498733e-06,
	"loss": 1.0153237581253052,
	"step": 368
	},
	{
	"epoch": 1.010928961748634,
	"grad_norm": 0.1327170431613922,
	"learning_rate": 2.059510168085791e-06,
	"loss": 1.090681791305542,
	"step": 370
	},
	{
	"epoch": 1.0163934426229508,
	"grad_norm": 0.08891897648572922,
	"learning_rate": 2.0412539766463697e-06,
	"loss": 1.055408000946045,
	"step": 372
	},
	{
	"epoch": 1.0218579234972678,
	"grad_norm": 0.11671415716409683,
	"learning_rate": 2.0263268699623746e-06,
	"loss": 1.0153884887695312,
	"step": 374
	},
	{
	"epoch": 1.0273224043715847,
	"grad_norm": 0.1955808699131012,
	"learning_rate": 2.0147343949711965e-06,
	"loss": 0.8129119277000427,
	"step": 376
	},
	{
	"epoch": 1.0327868852459017,
	"grad_norm": 0.11424767225980759,
	"learning_rate": 2.0064808594556066e-06,
	"loss": 1.0032305717468262,
	"step": 378
	},
	{
	"epoch": 1.0382513661202186,
	"grad_norm": 0.09951414912939072,
	"learning_rate": 2.0015693304429757e-06,
	"loss": 0.6713349223136902,
	"step": 380
	},
	{
	"epoch": 1.0437158469945356,
	"grad_norm": 0.157700777053833,
	"learning_rate": 2.000001633065562e-06,
	"loss": 0.9018054008483887,
	"step": 382
	},
	{
	"epoch": 1.0491803278688525,
	"grad_norm": 0.11729155480861664,
	"learning_rate": 2.0017783498822896e-06,
	"loss": 1.0324310064315796,
	"step": 384
	},
	{
	"epoch": 1.0546448087431695,
	"grad_norm": 0.12463416904211044,
	"learning_rate": 2.006898820662268e-06,
	"loss": 0.6445884704589844,
	"step": 386
	},
	{
	"epoch": 1.0601092896174864,
	"grad_norm": 0.47830504179000854,
	"learning_rate": 2.0153611426301325e-06,
	"loss": 0.5118352174758911,
	"step": 388
	},
	{
	"epoch": 1.0655737704918034,
	"grad_norm": 0.20129992067813873,
	"learning_rate": 2.027162171173126e-06,
	"loss": 1.1220747232437134,
	"step": 390
	},
	{
	"epoch": 1.0710382513661203,
	"grad_norm": 0.10175406187772751,
	"learning_rate": 2.0422975210096317e-06,
	"loss": 0.9721101522445679,
	"step": 392
	},
	{
	"epoch": 1.0765027322404372,
	"grad_norm": 0.15038686990737915,
	"learning_rate": 2.0607615678187605e-06,
	"loss": 0.5728106498718262,
	"step": 394
	},
	{
	"epoch": 1.0819672131147542,
	"grad_norm": 0.12541523575782776,
	"learning_rate": 2.082547450330353e-06,
	"loss": 1.0776091814041138,
	"step": 396
	},
	{
	"epoch": 1.0874316939890711,
	"grad_norm": 0.1422613561153412,
	"learning_rate": 2.1076470728746407e-06,
	"loss": 0.9820076823234558,
	"step": 398
	},
	{
	"epoch": 1.092896174863388,
	"grad_norm": 0.4176431894302368,
	"learning_rate": 2.136051108390608e-06,
	"loss": 1.1005867719650269,
	"step": 400
	},
	{
	"epoch": 1.098360655737705,
	"grad_norm": 0.17192092537879944,
	"learning_rate": 2.167749001891944e-06,
	"loss": 0.9484550356864929,
	"step": 402
	},
	{
	"epoch": 1.1038251366120218,
	"grad_norm": 0.19980178773403168,
	"learning_rate": 2.202728974389296e-06,
	"loss": 1.039968729019165,
	"step": 404
	},
	{
	"epoch": 1.1092896174863387,
	"grad_norm": 0.3821330666542053,
	"learning_rate": 2.240978027267357e-06,
	"loss": 1.1210821866989136,
	"step": 406
	},
	{
	"epoch": 1.1147540983606556,
	"grad_norm": 0.17232535779476166,
	"learning_rate": 2.2824819471151736e-06,
	"loss": 0.6310506463050842,
	"step": 408
	},
	{
	"epoch": 1.1202185792349726,
	"grad_norm": 0.1672593653202057,
	"learning_rate": 2.327225311007878e-06,
	"loss": 1.1975295543670654,
	"step": 410
	},
	{
	"epoch": 1.1256830601092895,
	"grad_norm": 0.1546320766210556,
	"learning_rate": 2.3751914922378623e-06,
	"loss": 0.6439824104309082,
	"step": 412
	},
	{
	"epoch": 1.1311475409836065,
	"grad_norm": 0.12194650620222092,
	"learning_rate": 2.4263626664932998e-06,
	"loss": 0.7317380309104919,
	"step": 414
	},
	{
	"epoch": 1.1366120218579234,
	"grad_norm": 0.4037162959575653,
	"learning_rate": 2.4807198184816817e-06,
	"loss": 0.6151731610298157,
	"step": 416
	},
	{
	"epoch": 1.1420765027322404,
	"grad_norm": 0.14404965937137604,
	"learning_rate": 2.5382427489959373e-06,
	"loss": 1.0358096361160278,
	"step": 418
	},
	{
	"epoch": 1.1475409836065573,
	"grad_norm": 0.14871248602867126,
	"learning_rate": 2.5989100824204876e-06,
	"loss": 0.9391909837722778,
	"step": 420
	},
	{
	"epoch": 1.1530054644808743,
	"grad_norm": 0.10675734281539917,
	"learning_rate": 2.662699274674462e-06,
	"loss": 1.0057426691055298,
	"step": 422
	},
	{
	"epoch": 1.1584699453551912,
	"grad_norm": 0.14187511801719666,
	"learning_rate": 2.7295866215891107e-06,
	"loss": 0.7259042859077454,
	"step": 424
	},
	{
	"epoch": 1.1639344262295082,
	"grad_norm": 0.23252590000629425,
	"learning_rate": 2.799547267716326e-06,
	"loss": 0.6342077851295471,
	"step": 426
	},
	{
	"epoch": 1.169398907103825,
	"grad_norm": 0.11477074027061462,
	"learning_rate": 2.872555215564946e-06,
	"loss": 1.1057250499725342,
	"step": 428
	},
	{
	"epoch": 1.174863387978142,
	"grad_norm": 0.12571924924850464,
	"learning_rate": 2.9485833352614895e-06,
	"loss": 1.0438354015350342,
	"step": 430
	},
	{
	"epoch": 1.180327868852459,
	"grad_norm": 0.11532790958881378,
	"learning_rate": 3.027603374631647e-06,
	"loss": 1.0102614164352417,
	"step": 432
	},
	{
	"epoch": 1.185792349726776,
	"grad_norm": 0.12962767481803894,
	"learning_rate": 3.1095859696988273e-06,
	"loss": 0.7555112242698669,
	"step": 434
	},
	{
	"epoch": 1.1912568306010929,
	"grad_norm": 0.16368405520915985,
	"learning_rate": 3.1945006555958885e-06,
	"loss": 1.0447275638580322,
	"step": 436
	},
	{
	"epoch": 1.1967213114754098,
	"grad_norm": 0.10939529538154602,
	"learning_rate": 3.2823158778858976e-06,
	"loss": 1.0501242876052856,
	"step": 438
	},
	{
	"epoch": 1.2021857923497268,
	"grad_norm": 0.28014352917671204,
	"learning_rate": 3.372999004287839e-06,
	"loss": 0.8902407288551331,
	"step": 440
	},
	{
	"epoch": 1.2076502732240437,
	"grad_norm": 0.22510351240634918,
	"learning_rate": 3.4665163368028044e-06,
	"loss": 1.0529145002365112,
	"step": 442
	},
	{
	"epoch": 1.2131147540983607,
	"grad_norm": 0.11745640635490417,
	"learning_rate": 3.562833124236238e-06,
	"loss": 1.0241260528564453,
	"step": 444
	},
	{
	"epoch": 1.2185792349726776,
	"grad_norm": 0.10882380604743958,
	"learning_rate": 3.6619135751115325e-06,
	"loss": 0.5796948075294495,
	"step": 446
	},
	{
	"epoch": 1.2240437158469946,
	"grad_norm": 0.11475440114736557,
	"learning_rate": 3.763720870970201e-06,
	"loss": 0.9688222408294678,
	"step": 448
	},
	{
	"epoch": 1.2295081967213115,
	"grad_norm": 0.11639797687530518,
	"learning_rate": 3.86821718005367e-06,
	"loss": 1.0046788454055786,
	"step": 450
	},
	{
	"epoch": 1.2349726775956285,
	"grad_norm": 0.16791078448295593,
	"learning_rate": 3.975363671361641e-06,
	"loss": 0.9738149642944336,
	"step": 452
	},
	{
	"epoch": 1.2404371584699454,
	"grad_norm": 0.27022409439086914,
	"learning_rate": 4.0851205290817254e-06,
	"loss": 0.25824788212776184,
	"step": 454
	},
	{
	"epoch": 1.2459016393442623,
	"grad_norm": 0.3601982295513153,
	"learning_rate": 4.197446967385105e-06,
	"loss": 0.7551949620246887,
	"step": 456
	},
	{
	"epoch": 1.2513661202185793,
	"grad_norm": 0.3413498103618622,
	"learning_rate": 4.312301245582571e-06,
	"loss": 0.6455928683280945,
	"step": 458
	},
	{
	"epoch": 1.2568306010928962,
	"grad_norm": 0.15276941657066345,
	"learning_rate": 4.429640683635466e-06,
	"loss": 1.0521637201309204,
	"step": 460
	},
	{
	"epoch": 1.2622950819672132,
	"grad_norm": 0.28445929288864136,
	"learning_rate": 4.549421678015633e-06,
	"loss": 0.6878266334533691,
	"step": 462
	},
	{
	"epoch": 1.2677595628415301,
	"grad_norm": 0.34402215480804443,
	"learning_rate": 4.671599717908582e-06,
	"loss": 0.9702850580215454,
	"step": 464
	},
	{
	"epoch": 1.273224043715847,
	"grad_norm": 0.12396188825368881,
	"learning_rate": 4.796129401753752e-06,
	"loss": 1.006730556488037,
	"step": 466
	},
	{
	"epoch": 1.278688524590164,
	"grad_norm": 0.1135745644569397,
	"learning_rate": 4.922964454115837e-06,
	"loss": 0.9473859667778015,
	"step": 468
	},
	{
	"epoch": 1.2841530054644807,
	"grad_norm": 0.1671561449766159,
	"learning_rate": 5.0520577428807835e-06,
	"loss": 0.9789319634437561,
	"step": 470
	},
	{
	"epoch": 1.289617486338798,
	"grad_norm": 0.09278880804777145,
	"learning_rate": 5.183361296770197e-06,
	"loss": 1.2953110933303833,
	"step": 472
	},
	{
	"epoch": 1.2950819672131146,
	"grad_norm": 0.14171801507472992,
	"learning_rate": 5.316826323167505e-06,
	"loss": 0.9902119636535645,
	"step": 474
	},
	{
	"epoch": 1.3005464480874318,
	"grad_norm": 0.233398899435997,
	"learning_rate": 5.4524032262494175e-06,
	"loss": 0.49475741386413574,
	"step": 476
	},
	{
	"epoch": 1.3060109289617485,
	"grad_norm": 0.15780876576900482,
	"learning_rate": 5.590041625415783e-06,
	"loss": 1.0600972175598145,
	"step": 478
	},
	{
	"epoch": 1.3114754098360657,
	"grad_norm": 0.10637230426073074,
	"learning_rate": 5.7296903740111076e-06,
	"loss": 1.0665287971496582,
	"step": 480
	},
	{
	"epoch": 1.3169398907103824,
	"grad_norm": 0.09512165188789368,
	"learning_rate": 5.87129757833077e-06,
	"loss": 0.8561606407165527,
	"step": 482
	},
	{
	"epoch": 1.3224043715846996,
	"grad_norm": 0.19713814556598663,
	"learning_rate": 6.014810616904747e-06,
	"loss": 0.6718865633010864,
	"step": 484
	},
	{
	"epoch": 1.3278688524590163,
	"grad_norm": 0.11173432320356369,
	"learning_rate": 6.160176160051906e-06,
	"loss": 0.9568278789520264,
	"step": 486
	},
	{
	"epoch": 1.3333333333333333,
	"grad_norm": 0.1460486352443695,
	"learning_rate": 6.307340189697344e-06,
	"loss": 1.088982105255127,
	"step": 488
	},
	{
	"epoch": 1.3387978142076502,
	"grad_norm": 0.17626726627349854,
	"learning_rate": 6.456248019445626e-06,
	"loss": 0.632489800453186,
	"step": 490
	},
	{
	"epoch": 1.3442622950819672,
	"grad_norm": 0.0857512503862381,
	"learning_rate": 6.606844314902321e-06,
	"loss": 1.0565383434295654,
	"step": 492
	},
	{
	"epoch": 1.349726775956284,
	"grad_norm": 0.04572976753115654,
	"learning_rate": 6.7590731142363915e-06,
	"loss": 0.8708642721176147,
	"step": 494
	},
	{
	"epoch": 1.355191256830601,
	"grad_norm": 0.25216469168663025,
	"learning_rate": 6.912877848975638e-06,
	"loss": 1.0493139028549194,
	"step": 496
	},
	{
	"epoch": 1.360655737704918,
	"grad_norm": 0.2923753559589386,
	"learning_rate": 7.068201365027712e-06,
	"loss": 0.8828723430633545,
	"step": 498
	},
	{
	"epoch": 1.366120218579235,
	"grad_norm": 0.21058304607868195,
	"learning_rate": 7.2249859439185875e-06,
	"loss": 1.1987463235855103,
	"step": 500
	},
	{
	"epoch": 1.3715846994535519,
	"grad_norm": 0.12390316277742386,
	"learning_rate": 7.3831733242409285e-06,
	"loss": 0.9241117835044861,
	"step": 502
	},
	{
	"epoch": 1.3770491803278688,
	"grad_norm": 0.09202788770198822,
	"learning_rate": 7.5427047233040485e-06,
	"loss": 0.5438337922096252,
	"step": 504
	},
	{
	"epoch": 1.3825136612021858,
	"grad_norm": 0.09361044317483902,
	"learning_rate": 7.703520858977702e-06,
	"loss": 0.8399773240089417,
	"step": 506
	},
	{
	"epoch": 1.3879781420765027,
	"grad_norm": 0.11776993423700333,
	"learning_rate": 7.865561971721389e-06,
	"loss": 1.012689471244812,
	"step": 508
	},
	{
	"epoch": 1.3934426229508197,
	"grad_norm": 0.11572909355163574,
	"learning_rate": 8.02876784679115e-06,
	"loss": 1.0279278755187988,
	"step": 510
	},
	{
	"epoch": 1.3989071038251366,
	"grad_norm": 0.15213985741138458,
	"learning_rate": 8.193077836615386e-06,
	"loss": 1.1416020393371582,
	"step": 512
	},
	{
	"epoch": 1.4043715846994536,
	"grad_norm": 0.04757779836654663,
	"learning_rate": 8.35843088333168e-06,
	"loss": 0.7897922396659851,
	"step": 514
	},
	{
	"epoch": 1.4098360655737705,
	"grad_norm": 0.1259109377861023,
	"learning_rate": 8.524765541475935e-06,
	"loss": 0.7295854687690735,
	"step": 516
	},
	{
	"epoch": 1.4153005464480874,
	"grad_norm": 0.7025004625320435,
	"learning_rate": 8.692020000815627e-06,
	"loss": 1.0215600728988647,
	"step": 518
	},
	{
	"epoch": 1.4207650273224044,
	"grad_norm": 0.3152309060096741,
	"learning_rate": 8.860132109318622e-06,
	"loss": 0.5573855638504028,
	"step": 520
	},
	{
	"epoch": 1.4262295081967213,
	"grad_norm": 0.14202211797237396,
	"learning_rate": 9.029039396248916e-06,
	"loss": 1.0810049772262573,
	"step": 522
	},
	{
	"epoch": 1.4316939890710383,
	"grad_norm": 0.15890736877918243,
	"learning_rate": 9.198679095380924e-06,
	"loss": 0.958807647228241,
	"step": 524
	},
	{
	"epoch": 1.4371584699453552,
	"grad_norm": 0.440880686044693,
	"learning_rate": 9.368988168323451e-06,
	"loss": 0.9619909524917603,
	"step": 526
	},
	{
	"epoch": 1.4426229508196722,
	"grad_norm": 0.09399222582578659,
	"learning_rate": 9.539903327944926e-06,
	"loss": 0.6587854623794556,
	"step": 528
	},
	{
	"epoch": 1.4480874316939891,
	"grad_norm": 0.43031588196754456,
	"learning_rate": 9.711361061890942e-06,
	"loss": 0.7227563261985779,
	"step": 530
	},
	{
	"epoch": 1.453551912568306,
	"grad_norm": 0.2343519926071167,
	"learning_rate": 9.8832976561856e-06,
	"loss": 0.6935963034629822,
	"step": 532
	},
	{
	"epoch": 1.459016393442623,
	"grad_norm": 0.8154575824737549,
	"learning_rate": 1.0055649218907688e-05,
	"loss": 1.0704255104064941,
	"step": 534
	},
	{
	"epoch": 1.46448087431694,
	"grad_norm": 0.1126905083656311,
	"learning_rate": 1.0228351703933075e-05,
	"loss": 1.0404987335205078,
	"step": 536
	},
	{
	"epoch": 1.469945355191257,
	"grad_norm": 0.11301713436841965,
	"learning_rate": 1.0401340934734287e-05,
	"loss": 1.0789377689361572,
	"step": 538
	},
	{
	"epoch": 1.4754098360655736,
	"grad_norm": 0.07608981430530548,
	"learning_rate": 1.0574552628228691e-05,
	"loss": 1.0320706367492676,
	"step": 540
	},
	{
	"epoch": 1.4808743169398908,
	"grad_norm": 0.3283179700374603,
	"learning_rate": 1.0747922418666115e-05,
	"loss": 1.0364580154418945,
	"step": 542
	},
	{
	"epoch": 1.4863387978142075,
	"grad_norm": 0.16681601107120514,
	"learning_rate": 1.0921385881547311e-05,
	"loss": 0.8939827680587769,
	"step": 544
	},
	{
	"epoch": 1.4918032786885247,
	"grad_norm": 0.21713408827781677,
	"learning_rate": 1.1094878557564217e-05,
	"loss": 1.1266794204711914,
	"step": 546
	},
	{
	"epoch": 1.4972677595628414,
	"grad_norm": 0.14162234961986542,
	"learning_rate": 1.1268335976553098e-05,
	"loss": 0.37908974289894104,
	"step": 548
	},
	{
	"epoch": 1.5027322404371586,
	"grad_norm": 0.08663295209407806,
	"learning_rate": 1.144169368145179e-05,
	"loss": 1.0336085557937622,
	"step": 550
	},
	{
	"epoch": 1.5081967213114753,
	"grad_norm": 0.1834978312253952,
	"learning_rate": 1.1614887252252076e-05,
	"loss": 1.0525389909744263,
	"step": 552
	},
	{
	"epoch": 1.5136612021857925,
	"grad_norm": 0.13017012178897858,
	"learning_rate": 1.1787852329938198e-05,
	"loss": 1.0565928220748901,
	"step": 554
	},
	{
	"epoch": 1.5191256830601092,
	"grad_norm": 0.10501047968864441,
	"learning_rate": 1.1960524640402862e-05,
	"loss": 1.1221007108688354,
	"step": 556
	},
	{
	"epoch": 1.5245901639344264,
	"grad_norm": 0.0911460742354393,
	"learning_rate": 1.2132840018331514e-05,
	"loss": 0.7799986004829407,
	"step": 558
	},
	{
	"epoch": 1.530054644808743,
	"grad_norm": 0.12136353552341461,
	"learning_rate": 1.2304734431046335e-05,
	"loss": 0.6321024298667908,
	"step": 560
	},
	{
	"epoch": 1.5355191256830603,
	"grad_norm": 0.6391102075576782,
	"learning_rate": 1.2476144002300864e-05,
	"loss": 0.8896136283874512,
	"step": 562
	},
	{
	"epoch": 1.540983606557377,
	"grad_norm": 0.21880479156970978,
	"learning_rate": 1.264700503601655e-05,
	"loss": 0.7882946133613586,
	"step": 564
	},
	{
	"epoch": 1.5464480874316942,
	"grad_norm": 0.10457222163677216,
	"learning_rate": 1.2817254039952253e-05,
	"loss": 1.0469473600387573,
	"step": 566
	},
	{
	"epoch": 1.5519125683060109,
	"grad_norm": 0.21689452230930328,
	"learning_rate": 1.2986827749298138e-05,
	"loss": 0.7880579233169556,
	"step": 568
	},
	{
	"epoch": 1.5573770491803278,
	"grad_norm": 0.10684338957071304,
	"learning_rate": 1.3155663150184942e-05,
	"loss": 1.1512001752853394,
	"step": 570
	},
	{
	"epoch": 1.5628415300546448,
	"grad_norm": 0.08281126618385315,
	"learning_rate": 1.3323697503100035e-05,
	"loss": 1.0108344554901123,
	"step": 572
	},
	{
	"epoch": 1.5683060109289617,
	"grad_norm": 0.08205148577690125,
	"learning_rate": 1.3490868366201527e-05,
	"loss": 1.0739396810531616,
	"step": 574
	},
	{
	"epoch": 1.5737704918032787,
	"grad_norm": 0.14288611710071564,
	"learning_rate": 1.3657113618521763e-05,
	"loss": 0.7893604040145874,
	"step": 576
	},
	{
	"epoch": 1.5792349726775956,
	"grad_norm": 0.1151369959115982,
	"learning_rate": 1.3822371483051593e-05,
	"loss": 1.0953106880187988,
	"step": 578
	},
	{
	"epoch": 1.5846994535519126,
	"grad_norm": 0.12557563185691833,
	"learning_rate": 1.3986580549696777e-05,
	"loss": 0.5041826367378235,
	"step": 580
	},
	{
	"epoch": 1.5901639344262295,
	"grad_norm": 0.09901826828718185,
	"learning_rate": 1.4149679798098097e-05,
	"loss": 0.6635845899581909,
	"step": 582
	},
	{
	"epoch": 1.5956284153005464,
	"grad_norm": 0.1395505666732788,
	"learning_rate": 1.4311608620306626e-05,
	"loss": 0.6669992804527283,
	"step": 584
	},
	{
	"epoch": 1.6010928961748634,
	"grad_norm": 0.1357533186674118,
	"learning_rate": 1.447230684330573e-05,
	"loss": 1.0561128854751587,
	"step": 586
	},
	{
	"epoch": 1.6065573770491803,
	"grad_norm": 0.07983239740133286,
	"learning_rate": 1.4631714751371456e-05,
	"loss": 1.016318440437317,
	"step": 588
	},
	{
	"epoch": 1.6120218579234973,
	"grad_norm": 0.11813154071569443,
	"learning_rate": 1.4789773108263016e-05,
	"loss": 0.7854833006858826,
	"step": 590
	},
	{
	"epoch": 1.6174863387978142,
	"grad_norm": 0.14835046231746674,
	"learning_rate": 1.4946423179235068e-05,
	"loss": 1.0739095211029053,
	"step": 592
	},
	{
	"epoch": 1.6229508196721312,
	"grad_norm": 0.17924216389656067,
	"learning_rate": 1.5101606752863606e-05,
	"loss": 0.840874433517456,
	"step": 594
	},
	{
	"epoch": 1.6284153005464481,
	"grad_norm": 0.10418872535228729,
	"learning_rate": 1.5255266162677466e-05,
	"loss": 0.336093544960022,
	"step": 596
	},
	{
	"epoch": 1.633879781420765,
	"grad_norm": 0.13057978451251984,
	"learning_rate": 1.540734430858725e-05,
	"loss": 1.1894792318344116,
	"step": 598
	},
	{
	"epoch": 1.639344262295082,
	"grad_norm": 0.12744714319705963,
	"learning_rate": 1.5557784678103852e-05,
	"loss": 1.1345218420028687,
	"step": 600
	},
	{
	"epoch": 1.644808743169399,
	"grad_norm": 0.11343944817781448,
	"learning_rate": 1.5706531367338546e-05,
	"loss": 1.0770057439804077,
	"step": 602
	},
	{
	"epoch": 1.650273224043716,
	"grad_norm": 0.10060634464025497,
	"learning_rate": 1.5853529101776985e-05,
	"loss": 1.0950847864151,
	"step": 604
	},
	{
	"epoch": 1.6557377049180326,
	"grad_norm": 0.3996407985687256,
	"learning_rate": 1.5998723256819298e-05,
	"loss": 1.1565852165222168,
	"step": 606
	},
	{
	"epoch": 1.6612021857923498,
	"grad_norm": 0.1252470165491104,
	"learning_rate": 1.614205987807872e-05,
	"loss": 0.9427963495254517,
	"step": 608
	},
	{
	"epoch": 1.6666666666666665,
	"grad_norm": 0.08708234131336212,
	"learning_rate": 1.628348570143105e-05,
	"loss": 1.1373974084854126,
	"step": 610
	},
	{
	"epoch": 1.6721311475409837,
	"grad_norm": 0.6713199019432068,
	"learning_rate": 1.6422948172807745e-05,
	"loss": 0.7651968002319336,
	"step": 612
	},
	{
	"epoch": 1.6775956284153004,
	"grad_norm": 0.18165543675422668,
	"learning_rate": 1.6560395467725086e-05,
	"loss": 1.0242265462875366,
	"step": 614
	},
	{
	"epoch": 1.6830601092896176,
	"grad_norm": 0.21526610851287842,
	"learning_rate": 1.6695776510542253e-05,
	"loss": 1.1028822660446167,
	"step": 616
	},
	{
	"epoch": 1.6885245901639343,
	"grad_norm": 0.09745687246322632,
	"learning_rate": 1.6829040993441085e-05,
	"loss": 0.6104081869125366,
	"step": 618
	},
	{
	"epoch": 1.6939890710382515,
	"grad_norm": 0.1572287529706955,
	"learning_rate": 1.696013939512057e-05,
	"loss": 1.0959326028823853,
	"step": 620
	},
	{
	"epoch": 1.6994535519125682,
	"grad_norm": 0.17827695608139038,
	"learning_rate": 1.7089022999199064e-05,
	"loss": 1.233556866645813,
	"step": 622
	},
	{
	"epoch": 1.7049180327868854,
	"grad_norm": 0.1473863422870636,
	"learning_rate": 1.7215643912317323e-05,
	"loss": 0.732525110244751,
	"step": 624
	},
	{
	"epoch": 1.710382513661202,
	"grad_norm": 0.12968477606773376,
	"learning_rate": 1.73399550819358e-05,
	"loss": 0.6740303635597229,
	"step": 626
	},
	{
	"epoch": 1.7158469945355193,
	"grad_norm": 0.06875219196081161,
	"learning_rate": 1.746191031381943e-05,
	"loss": 1.095910906791687,
	"step": 628
	},
	{
	"epoch": 1.721311475409836,
	"grad_norm": 0.13739925622940063,
	"learning_rate": 1.7581464289203475e-05,
	"loss": 0.8012250661849976,
	"step": 630
	},
	{
	"epoch": 1.7267759562841531,
	"grad_norm": 0.16408398747444153,
	"learning_rate": 1.7698572581634083e-05,
	"loss": 1.0673834085464478,
	"step": 632
	},
	{
	"epoch": 1.7322404371584699,
	"grad_norm": 0.09738543629646301,
	"learning_rate": 1.781319167347718e-05,
	"loss": 1.1305607557296753,
	"step": 634
	},
	{
	"epoch": 1.737704918032787,
	"grad_norm": 0.09281567484140396,
	"learning_rate": 1.7925278972089748e-05,
	"loss": 0.9764953851699829,
	"step": 636
	},
	{
	"epoch": 1.7431693989071038,
	"grad_norm": 0.09890922904014587,
	"learning_rate": 1.8034792825647287e-05,
	"loss": 1.0016361474990845,
	"step": 638
	},
	{
	"epoch": 1.748633879781421,
	"grad_norm": 0.34490931034088135,
	"learning_rate": 1.8141692538621716e-05,
	"loss": 0.8936794996261597,
	"step": 640
	},
	{
	"epoch": 1.7540983606557377,
	"grad_norm": 0.10054787993431091,
	"learning_rate": 1.8245938386903896e-05,
	"loss": 1.1207398176193237,
	"step": 642
	},
	{
	"epoch": 1.7595628415300546,
	"grad_norm": 0.2044786661863327,
	"learning_rate": 1.8347491632565156e-05,
	"loss": 1.0461924076080322,
	"step": 644
	},
	{
	"epoch": 1.7650273224043715,
	"grad_norm": 0.06816514581441879,
	"learning_rate": 1.8446314538252407e-05,
	"loss": 0.6392666101455688,
	"step": 646
	},
	{
	"epoch": 1.7704918032786885,
	"grad_norm": 0.0854775607585907,
	"learning_rate": 1.8542370381211374e-05,
	"loss": 1.0239224433898926,
	"step": 648
	},
	{
	"epoch": 1.7759562841530054,
	"grad_norm": 0.09861481189727783,
	"learning_rate": 1.8635623466932843e-05,
	"loss": 1.0791953802108765,
	"step": 650
	},
	{
	"epoch": 1.7814207650273224,
	"grad_norm": 0.09283293783664703,
	"learning_rate": 1.8726039142416796e-05,
	"loss": 1.1317287683486938,
	"step": 652
	},
	{
	"epoch": 1.7868852459016393,
	"grad_norm": 0.1488487869501114,
	"learning_rate": 1.881358380904954e-05,
	"loss": 0.9950046539306641,
	"step": 654
	},
	{
	"epoch": 1.7923497267759563,
	"grad_norm": 0.4881657361984253,
	"learning_rate": 1.889822493508897e-05,
	"loss": 1.0590057373046875,
	"step": 656
	},
	{
	"epoch": 1.7978142076502732,
	"grad_norm": 0.1867472380399704,
	"learning_rate": 1.897993106775346e-05,
	"loss": 0.9436238408088684,
	"step": 658
	},
	{
	"epoch": 1.8032786885245902,
	"grad_norm": 0.19811779260635376,
	"learning_rate": 1.9058671844909742e-05,
	"loss": 1.0728529691696167,
	"step": 660
	},
	{
	"epoch": 1.8087431693989071,
	"grad_norm": 0.0855625569820404,
	"learning_rate": 1.9134418006355532e-05,
	"loss": 1.1045749187469482,
	"step": 662
	},
	{
	"epoch": 1.814207650273224,
	"grad_norm": 0.1337461769580841,
	"learning_rate": 1.9207141404692667e-05,
	"loss": 1.0828365087509155,
	"step": 664
	},
	{
	"epoch": 1.819672131147541,
	"grad_norm": 0.08743517845869064,
	"learning_rate": 1.927681501578672e-05,
	"loss": 1.3723547458648682,
	"step": 666
	},
	{
	"epoch": 1.825136612021858,
	"grad_norm": 0.0916970744729042,
	"learning_rate": 1.934341294880924e-05,
	"loss": 1.1413710117340088,
	"step": 668
	},
	{
	"epoch": 1.830601092896175,
	"grad_norm": 0.13558737933635712,
	"learning_rate": 1.9406910455858783e-05,
	"loss": 0.7378701567649841,
	"step": 670
	},
	{
	"epoch": 1.8360655737704918,
	"grad_norm": 0.23225541412830353,
	"learning_rate": 1.9467283941157304e-05,
	"loss": 1.2266825437545776,
	"step": 672
	},
	{
	"epoch": 1.8415300546448088,
	"grad_norm": 0.12275075912475586,
	"learning_rate": 1.952451096981838e-05,
	"loss": 1.105077862739563,
	"step": 674
	},
	{
	"epoch": 1.8469945355191257,
	"grad_norm": 0.08732561767101288,
	"learning_rate": 1.957857027618405e-05,
	"loss": 1.1363401412963867,
	"step": 676
	},
	{
	"epoch": 1.8524590163934427,
	"grad_norm": 0.05239817127585411,
	"learning_rate": 1.9629441771727166e-05,
	"loss": 0.27085718512535095,
	"step": 678
	},
	{
	"epoch": 1.8579234972677594,
	"grad_norm": 0.0899297297000885,
	"learning_rate": 1.9677106552516317e-05,
	"loss": 1.068323016166687,
	"step": 680
	},
	{
	"epoch": 1.8633879781420766,
	"grad_norm": 0.07155214250087738,
	"learning_rate": 1.9721546906240577e-05,
	"loss": 1.0824123620986938,
	"step": 682
	},
	{
	"epoch": 1.8688524590163933,
	"grad_norm": 0.09562800824642181,
	"learning_rate": 1.976274631879142e-05,
	"loss": 1.0398223400115967,
	"step": 684
	},
	{
	"epoch": 1.8743169398907105,
	"grad_norm": 0.09326054900884628,
	"learning_rate": 1.9800689480399383e-05,
	"loss": 0.726788341999054,
	"step": 686
	},
	{
	"epoch": 1.8797814207650272,
	"grad_norm": 0.16305072605609894,
	"learning_rate": 1.9835362291323222e-05,
	"loss": 1.152515172958374,
	"step": 688
	},
	{
	"epoch": 1.8852459016393444,
	"grad_norm": 0.08776555955410004,
	"learning_rate": 1.9866751867089363e-05,
	"loss": 1.1057515144348145,
	"step": 690
	},
	{
	"epoch": 1.890710382513661,
	"grad_norm": 0.34914299845695496,
	"learning_rate": 1.9894846543279838e-05,
	"loss": 0.7560766339302063,
	"step": 692
	},
	{
	"epoch": 1.8961748633879782,
	"grad_norm": 0.13801546394824982,
	"learning_rate": 1.991963587986677e-05,
	"loss": 1.1189141273498535,
	"step": 694
	},
	{
	"epoch": 1.901639344262295,
	"grad_norm": 0.33698874711990356,
	"learning_rate": 1.9941110665091922e-05,
	"loss": 1.122489333152771,
	"step": 696
	},
	{
	"epoch": 1.9071038251366121,
	"grad_norm": 0.15018677711486816,
	"learning_rate": 1.9959262918889774e-05,
	"loss": 0.9824838638305664,
	"step": 698
	},
	{
	"epoch": 1.9125683060109289,
	"grad_norm": 0.07216078788042068,
	"learning_rate": 1.9974085895852973e-05,
	"loss": 1.1157559156417847,
	"step": 700
	},
	{
	"epoch": 1.918032786885246,
	"grad_norm": 0.07695994526147842,
	"learning_rate": 1.99855740877389e-05,
	"loss": 1.0270991325378418,
	"step": 702
	},
	{
	"epoch": 1.9234972677595628,
	"grad_norm": 0.10790321230888367,
	"learning_rate": 1.9993723225516553e-05,
	"loss": 1.146857738494873,
	"step": 704
	},
	{
	"epoch": 1.92896174863388,
	"grad_norm": 0.09250786900520325,
	"learning_rate": 1.9998530280952938e-05,
	"loss": 1.1385565996170044,
	"step": 706
	},
	{
	"epoch": 1.9344262295081966,
	"grad_norm": 0.07818273454904556,
	"learning_rate": 1.9999993467738345e-05,
	"loss": 1.1723568439483643,
	"step": 708
	},
	{
	"epoch": 1.9398907103825138,
	"grad_norm": 0.09822240471839905,
	"learning_rate": 1.9998112242150162e-05,
	"loss": 0.9018577337265015,
	"step": 710
	},
	{
	"epoch": 1.9453551912568305,
	"grad_norm": 0.07508859038352966,
	"learning_rate": 1.999288730325491e-05,
	"loss": 0.6304239630699158,
	"step": 712
	},
	{
	"epoch": 1.9508196721311475,
	"grad_norm": 0.18517723679542542,
	"learning_rate": 1.9984320592648474e-05,
	"loss": 1.108601689338684,
	"step": 714
	},
	{
	"epoch": 1.9562841530054644,
	"grad_norm": 0.2125580906867981,
	"learning_rate": 1.9972415293734607e-05,
	"loss": 0.8507819175720215,
	"step": 716
	},
	{
	"epoch": 1.9617486338797814,
	"grad_norm": 0.09725981950759888,
	"learning_rate": 1.995717583054196e-05,
	"loss": 1.1092121601104736,
	"step": 718
	},
	{
	"epoch": 1.9672131147540983,
	"grad_norm": 0.16010290384292603,
	"learning_rate": 1.9938607866080114e-05,
	"loss": 1.0979053974151611,
	"step": 720
	},
	{
	"epoch": 1.9726775956284153,
	"grad_norm": 0.10000172257423401,
	"learning_rate": 1.991671830023521e-05,
	"loss": 1.1372826099395752,
	"step": 722
	},
	{
	"epoch": 1.9781420765027322,
	"grad_norm": 0.12482127547264099,
	"learning_rate": 1.989151526720591e-05,
	"loss": 1.0039864778518677,
	"step": 724
	},
	{
	"epoch": 1.9836065573770492,
	"grad_norm": 0.19064390659332275,
	"learning_rate": 1.986300813248073e-05,
	"loss": 1.076819896697998,
	"step": 726
	},
	{
	"epoch": 1.989071038251366,
	"grad_norm": 0.0709768533706665,
	"learning_rate": 1.9831207489357825e-05,
	"loss": 1.0897186994552612,
	"step": 728
	},
	{
	"epoch": 1.994535519125683,
	"grad_norm": 0.1523556411266327,
	"learning_rate": 1.979612515500847e-05,
	"loss": 1.0046844482421875,
	"step": 730
	},
	{
	"epoch": 2.0,
	"grad_norm": 0.07687041908502579,
	"learning_rate": 1.97577741660858e-05,
	"loss": 1.1337778568267822,
	"step": 732
	},
	{
	"epoch": 2.0054644808743167,
	"grad_norm": 0.06963507831096649,
	"learning_rate": 1.9716168773880382e-05,
	"loss": 0.6142993569374084,
	"step": 734
	},
	{
	"epoch": 2.010928961748634,
	"grad_norm": 0.08646684885025024,
	"learning_rate": 1.9671324439024374e-05,
	"loss": 0.8584022521972656,
	"step": 736
	},
	{
	"epoch": 2.0163934426229506,
	"grad_norm": 0.09564807265996933,
	"learning_rate": 1.9623257825746357e-05,
	"loss": 0.8110524415969849,
	"step": 738
	},
	{
	"epoch": 2.021857923497268,
	"grad_norm": 0.11263297498226166,
	"learning_rate": 1.9571986795678878e-05,
	"loss": 0.8699367642402649,
	"step": 740
	},
	{
	"epoch": 2.0273224043715845,
	"grad_norm": 0.33164191246032715,
	"learning_rate": 1.951753040122102e-05,
	"loss": 0.8090985417366028,
	"step": 742
	},
	{
	"epoch": 2.0327868852459017,
	"grad_norm": 0.13913966715335846,
	"learning_rate": 1.9459908878458532e-05,
	"loss": 0.9339433908462524,
	"step": 744
	},
	{
	"epoch": 2.0382513661202184,
	"grad_norm": 0.1326131969690323,
	"learning_rate": 1.939914363964402e-05,
	"loss": 1.050421953201294,
	"step": 746
	},
	{
	"epoch": 2.0437158469945356,
	"grad_norm": 0.11959031224250793,
	"learning_rate": 1.9335257265240168e-05,
	"loss": 1.0097161531448364,
	"step": 748
	},
	{
	"epoch": 2.0491803278688523,
	"grad_norm": 0.20392794907093048,
	"learning_rate": 1.9268273495528768e-05,
	"loss": 0.7200921773910522,
	"step": 750
	},
	{
	"epoch": 2.0546448087431695,
	"grad_norm": 0.3636847138404846,
	"learning_rate": 1.9198217221788806e-05,
	"loss": 0.605461597442627,
	"step": 752
	},
	{
	"epoch": 2.060109289617486,
	"grad_norm": 1.16413414478302,
	"learning_rate": 1.9125114477046807e-05,
	"loss": 0.6320473551750183,
	"step": 754
	},
	{
	"epoch": 2.0655737704918034,
	"grad_norm": 0.21701183915138245,
	"learning_rate": 1.9048992426402947e-05,
	"loss": 1.0904141664505005,
	"step": 756
	},
	{
	"epoch": 2.07103825136612,
	"grad_norm": 0.14577004313468933,
	"learning_rate": 1.896987935693643e-05,
	"loss": 1.002879023551941,
	"step": 758
	},
	{
	"epoch": 2.0765027322404372,
	"grad_norm": 0.2534794509410858,
	"learning_rate": 1.888780466719397e-05,
	"loss": 0.9008995890617371,
	"step": 760
	},
	{
	"epoch": 2.081967213114754,
	"grad_norm": 0.13845816254615784,
	"learning_rate": 1.8802798856265254e-05,
	"loss": 1.0071299076080322,
	"step": 762
	},
	{
	"epoch": 2.087431693989071,
	"grad_norm": 0.1185113936662674,
	"learning_rate": 1.8714893512449424e-05,
	"loss": 0.9370182752609253,
	"step": 764
	},
	{
	"epoch": 2.092896174863388,
	"grad_norm": 0.1452389359474182,
	"learning_rate": 1.8624121301516808e-05,
	"loss": 1.0715157985687256,
	"step": 766
	},
	{
	"epoch": 2.098360655737705,
	"grad_norm": 0.10411622375249863,
	"learning_rate": 1.853051595457026e-05,
	"loss": 0.8296530246734619,
	"step": 768
	},
	{
	"epoch": 2.1038251366120218,
	"grad_norm": 0.26561427116394043,
	"learning_rate": 1.843411225551065e-05,
	"loss": 0.9580831527709961,
	"step": 770
	},
	{
	"epoch": 2.109289617486339,
	"grad_norm": 0.29404425621032715,
	"learning_rate": 1.8334946028111088e-05,
	"loss": 0.8596486449241638,
	"step": 772
	},
	{
	"epoch": 2.1147540983606556,
	"grad_norm": 0.08718276768922806,
	"learning_rate": 1.8233054122704765e-05,
	"loss": 0.8322362899780273,
	"step": 774
	},
	{
	"epoch": 2.120218579234973,
	"grad_norm": 0.08565963804721832,
	"learning_rate": 1.8128474402491286e-05,
	"loss": 0.9187090396881104,
	"step": 776
	},
	{
	"epoch": 2.1256830601092895,
	"grad_norm": 0.413748174905777,
	"learning_rate": 1.802124572946668e-05,
	"loss": 0.8059758543968201,
	"step": 778
	},
	{
	"epoch": 2.1311475409836067,
	"grad_norm": 0.08740316331386566,
	"learning_rate": 1.791140794998219e-05,
	"loss": 0.8861984610557556,
	"step": 780
	},
	{
	"epoch": 2.1366120218579234,
	"grad_norm": 0.06927383691072464,
	"learning_rate": 1.7799001879937294e-05,
	"loss": 0.9507087469100952,
	"step": 782
	},
	{
	"epoch": 2.1420765027322406,
	"grad_norm": 0.08840641379356384,
	"learning_rate": 1.768406928961248e-05,
	"loss": 1.0136234760284424,
	"step": 784
	},
	{
	"epoch": 2.1475409836065573,
	"grad_norm": 0.1088033989071846,
	"learning_rate": 1.7566652888147328e-05,
	"loss": 0.7027506828308105,
	"step": 786
	},
	{
	"epoch": 2.1530054644808745,
	"grad_norm": 0.2902282178401947,
	"learning_rate": 1.7446796307669725e-05,
	"loss": 0.8324766755104065,
	"step": 788
	},
	{
	"epoch": 2.158469945355191,
	"grad_norm": 0.12461357563734055,
	"learning_rate": 1.732454408708209e-05,
	"loss": 1.0693421363830566,
	"step": 790
	},
	{
	"epoch": 2.1639344262295084,
	"grad_norm": 0.11356167495250702,
	"learning_rate": 1.719994165551063e-05,
	"loss": 0.6516219973564148,
	"step": 792
	},
	{
	"epoch": 2.169398907103825,
	"grad_norm": 0.3933297097682953,
	"learning_rate": 1.7073035315423838e-05,
	"loss": 0.7549520134925842,
	"step": 794
	},
	{
	"epoch": 2.1748633879781423,
	"grad_norm": 0.0880681499838829,
	"learning_rate": 1.6943872225426396e-05,
	"loss": 0.890471875667572,
	"step": 796
	},
	{
	"epoch": 2.180327868852459,
	"grad_norm": 0.13298313319683075,
	"learning_rate": 1.6812500382734977e-05,
	"loss": 0.9139057397842407,
	"step": 798
	},
	{
	"epoch": 2.185792349726776,
	"grad_norm": 0.22635987401008606,
	"learning_rate": 1.6678968605342348e-05,
	"loss": 0.8639968037605286,
	"step": 800
	},
	{
	"epoch": 2.191256830601093,
	"grad_norm": 0.15127940475940704,
	"learning_rate": 1.6543326513876602e-05,
	"loss": 0.949240505695343,
	"step": 802
	},
	{
	"epoch": 2.19672131147541,
	"grad_norm": 0.1014222800731659,
	"learning_rate": 1.6405624513162002e-05,
	"loss": 0.8963988423347473,
	"step": 804
	},
	{
	"epoch": 2.202185792349727,
	"grad_norm": 0.08098163455724716,
	"learning_rate": 1.6265913773488456e-05,
	"loss": 0.9640499353408813,
	"step": 806
	},
	{
	"epoch": 2.2076502732240435,
	"grad_norm": 0.5575600266456604,
	"learning_rate": 1.6124246211596606e-05,
	"loss": 0.8397250771522522,
	"step": 808
	},
	{
	"epoch": 2.2131147540983607,
	"grad_norm": 0.09522633999586105,
	"learning_rate": 1.598067447138542e-05,
	"loss": 0.6495193839073181,
	"step": 810
	},
	{
	"epoch": 2.2185792349726774,
	"grad_norm": 0.0872296467423439,
	"learning_rate": 1.5835251904349688e-05,
	"loss": 0.9478666186332703,
	"step": 812
	},
	{
	"epoch": 2.2240437158469946,
	"grad_norm": 0.14140820503234863,
	"learning_rate": 1.5688032549754453e-05,
	"loss": 0.8577138185501099,
	"step": 814
	},
	{
	"epoch": 2.2295081967213113,
	"grad_norm": 0.11184604465961456,
	"learning_rate": 1.553907111455401e-05,
	"loss": 0.8024045825004578,
	"step": 816
	},
	{
	"epoch": 2.2349726775956285,
	"grad_norm": 0.1329488754272461,
	"learning_rate": 1.538842295306264e-05,
	"loss": 0.9610792994499207,
	"step": 818
	},
	{
	"epoch": 2.240437158469945,
	"grad_norm": 0.1702757477760315,
	"learning_rate": 1.5236144046384917e-05,
	"loss": 0.9774719476699829,
	"step": 820
	},
	{
	"epoch": 2.2459016393442623,
	"grad_norm": 0.26356950402259827,
	"learning_rate": 1.5082290981612987e-05,
	"loss": 1.0529048442840576,
	"step": 822
	},
	{
	"epoch": 2.251366120218579,
	"grad_norm": 0.08985842764377594,
	"learning_rate": 1.4926920930798736e-05,
	"loss": 0.7446960806846619,
	"step": 824
	},
	{
	"epoch": 2.2568306010928962,
	"grad_norm": 0.278573602437973,
	"learning_rate": 1.4770091629708562e-05,
	"loss": 0.5461352467536926,
	"step": 826
	},
	{
	"epoch": 2.262295081967213,
	"grad_norm": 0.6094837784767151,
	"learning_rate": 1.461186135636868e-05,
	"loss": 0.7116088271141052,
	"step": 828
	},
	{
	"epoch": 2.26775956284153,
	"grad_norm": 0.09571769088506699,
	"learning_rate": 1.4452288909408864e-05,
	"loss": 0.8776818513870239,
	"step": 830
	},
	{
	"epoch": 2.273224043715847,
	"grad_norm": 0.15052512288093567,
	"learning_rate": 1.4291433586212831e-05,
	"loss": 0.5412632822990417,
	"step": 832
	},
	{
	"epoch": 2.278688524590164,
	"grad_norm": 0.2911688983440399,
	"learning_rate": 1.4129355160883216e-05,
	"loss": 0.6831727623939514,
	"step": 834
	},
	{
	"epoch": 2.2841530054644807,
	"grad_norm": 0.2999238073825836,
	"learning_rate": 1.3966113862029429e-05,
	"loss": 1.0725103616714478,
	"step": 836
	},
	{
	"epoch": 2.289617486338798,
	"grad_norm": 0.33608266711235046,
	"learning_rate": 1.3801770350386568e-05,
	"loss": 0.9445420503616333,
	"step": 838
	},
	{
	"epoch": 2.2950819672131146,
	"grad_norm": 0.11400384455919266,
	"learning_rate": 1.363638569627384e-05,
	"loss": 0.7809190154075623,
	"step": 840
	},
	{
	"epoch": 2.300546448087432,
	"grad_norm": 0.07464587688446045,
	"learning_rate": 1.3470021356900696e-05,
	"loss": 0.9480050802230835,
	"step": 842
	},
	{
	"epoch": 2.3060109289617485,
	"grad_norm": 0.0809248611330986,
	"learning_rate": 1.3302739153529252e-05,
	"loss": 1.0223753452301025,
	"step": 844
	},
	{
	"epoch": 2.3114754098360657,
	"grad_norm": 0.0836072638630867,
	"learning_rate": 1.3134601248501366e-05,
	"loss": 0.5357997417449951,
	"step": 846
	},
	{
	"epoch": 2.3169398907103824,
	"grad_norm": 0.10634348541498184,
	"learning_rate": 1.2965670122139071e-05,
	"loss": 0.9999401569366455,
	"step": 848
	},
	{
	"epoch": 2.3224043715846996,
	"grad_norm": 0.09218322485685349,
	"learning_rate": 1.2796008549526752e-05,
	"loss": 0.9290571808815002,
	"step": 850
	},
	{
	"epoch": 2.3278688524590163,
	"grad_norm": 0.13691577315330505,
	"learning_rate": 1.262567957718378e-05,
	"loss": 0.80766761302948,
	"step": 852
	},
	{
	"epoch": 2.3333333333333335,
	"grad_norm": 0.5151943564414978,
	"learning_rate": 1.2454746499636408e-05,
	"loss": 0.9886870384216309,
	"step": 854
	},
	{
	"epoch": 2.33879781420765,
	"grad_norm": 0.08581722527742386,
	"learning_rate": 1.2283272835897359e-05,
	"loss": 0.9574921727180481,
	"step": 856
	},
	{
	"epoch": 2.3442622950819674,
	"grad_norm": 0.13452446460723877,
	"learning_rate": 1.2111322305862088e-05,
	"loss": 0.6717698574066162,
	"step": 858
	},
	{
	"epoch": 2.349726775956284,
	"grad_norm": 0.10753488540649414,
	"learning_rate": 1.1938958806630322e-05,
	"loss": 0.8548917770385742,
	"step": 860
	},
	{
	"epoch": 2.3551912568306013,
	"grad_norm": 0.0970119908452034,
	"learning_rate": 1.1766246388761841e-05,
	"loss": 0.9632062911987305,
	"step": 862
	},
	{
	"epoch": 2.360655737704918,
	"grad_norm": 0.13308054208755493,
	"learning_rate": 1.1593249232475162e-05,
	"loss": 0.6643819808959961,
	"step": 864
	},
	{
	"epoch": 2.366120218579235,
	"grad_norm": 0.24448184669017792,
	"learning_rate": 1.142003162379808e-05,
	"loss": 1.241449236869812,
	"step": 866
	},
	{
	"epoch": 2.371584699453552,
	"grad_norm": 0.14363636076450348,
	"learning_rate": 1.1246657930678817e-05,
	"loss": 0.9594497680664062,
	"step": 868
	},
	{
	"epoch": 2.3770491803278686,
	"grad_norm": 0.08895833790302277,
	"learning_rate": 1.1073192579066867e-05,
	"loss": 0.8083928227424622,
	"step": 870
	},
	{
	"epoch": 2.3825136612021858,
	"grad_norm": 0.1053352952003479,
	"learning_rate": 1.0899700028972169e-05,
	"loss": 0.859566330909729,
	"step": 872
	},
	{
	"epoch": 2.387978142076503,
	"grad_norm": 0.16995586454868317,
	"learning_rate": 1.072624475051166e-05,
	"loss": 0.9505580067634583,
	"step": 874
	},
	{
	"epoch": 2.3934426229508197,
	"grad_norm": 0.42757925391197205,
	"learning_rate": 1.055289119995206e-05,
	"loss": 0.6944902539253235,
	"step": 876
	},
	{
	"epoch": 2.3989071038251364,
	"grad_norm": 0.122571662068367,
	"learning_rate": 1.0379703795757853e-05,
	"loss": 0.8935880064964294,
	"step": 878
	},
	{
	"epoch": 2.4043715846994536,
	"grad_norm": 0.09966963529586792,
	"learning_rate": 1.0206746894653252e-05,
	"loss": 0.9855829477310181,
	"step": 880
	},
	{
	"epoch": 2.4098360655737707,
	"grad_norm": 0.09130659699440002,
	"learning_rate": 1.0034084767707164e-05,
	"loss": 0.5046952962875366,
	"step": 882
	},
	{
	"epoch": 2.4153005464480874,
	"grad_norm": 0.08370860666036606,
	"learning_rate": 9.861781576449879e-06,
	"loss": 0.8278293609619141,
	"step": 884
	},
	{
	"epoch": 2.420765027322404,
	"grad_norm": 0.09103255718946457,
	"learning_rate": 9.689901349030646e-06,
	"loss": 0.9132435917854309,
	"step": 886
	},
	{
	"epoch": 2.4262295081967213,
	"grad_norm": 0.17922845482826233,
	"learning_rate": 9.518507956424643e-06,
	"loss": 0.6458944082260132,
	"step": 888
	},
	{
	"epoch": 2.431693989071038,
	"grad_norm": 0.07886765152215958,
	"learning_rate": 9.347665088698444e-06,
	"loss": 0.5420209765434265,
	"step": 890
	},
	{
	"epoch": 2.4371584699453552,
	"grad_norm": 0.12056568264961243,
	"learning_rate": 9.177436231342623e-06,
	"loss": 0.8368343710899353,
	"step": 892
	},
	{
	"epoch": 2.442622950819672,
	"grad_norm": 0.1841779351234436,
	"learning_rate": 9.00788464168054e-06,
	"loss": 0.5313267111778259,
	"step": 894
	},
	{
	"epoch": 2.448087431693989,
	"grad_norm": 0.09516401588916779,
	"learning_rate": 8.839073325361751e-06,
	"loss": 0.7824960947036743,
	"step": 896
	},
	{
	"epoch": 2.453551912568306,
	"grad_norm": 0.11680221557617188,
	"learning_rate": 8.67106501294902e-06,
	"loss": 0.8697406053543091,
	"step": 898
	},
	{
	"epoch": 2.459016393442623,
	"grad_norm": 0.29455330967903137,
	"learning_rate": 8.503922136607536e-06,
	"loss": 0.9425011277198792,
	"step": 900
	},
	{
	"epoch": 2.4644808743169397,
	"grad_norm": 0.0904950276017189,
	"learning_rate": 8.337706806905029e-06,
	"loss": 0.8952743411064148,
	"step": 902
	},
	{
	"epoch": 2.469945355191257,
	"grad_norm": 0.09989660233259201,
	"learning_rate": 8.172480789731374e-06,
	"loss": 0.7953454256057739,
	"step": 904
	},
	{
	"epoch": 2.4754098360655736,
	"grad_norm": 0.20192794501781464,
	"learning_rate": 8.00830548334625e-06,
	"loss": 0.8293022513389587,
	"step": 906
	},
	{
	"epoch": 2.480874316939891,
	"grad_norm": 0.04934593662619591,
	"learning_rate": 7.84524189556352e-06,
	"loss": 0.40420135855674744,
	"step": 908
	},
	{
	"epoch": 2.4863387978142075,
	"grad_norm": 0.0565824918448925,
	"learning_rate": 7.68335062108057e-06,
	"loss": 0.8528041243553162,
	"step": 910
	},
	{
	"epoch": 2.4918032786885247,
	"grad_norm": 0.13608448207378387,
	"learning_rate": 7.522691818961252e-06,
	"loss": 0.7207663059234619,
	"step": 912
	},
	{
	"epoch": 2.4972677595628414,
	"grad_norm": 0.13163967430591583,
	"learning_rate": 7.3633251902806165e-06,
	"loss": 0.942747950553894,
	"step": 914
	},
	{
	"epoch": 2.5027322404371586,
	"grad_norm": 0.09808902442455292,
	"learning_rate": 7.205309955939983e-06,
	"loss": 0.7634099125862122,
	"step": 916
	},
	{
	"epoch": 2.5081967213114753,
	"grad_norm": 0.09887581318616867,
	"learning_rate": 7.048704834660296e-06,
	"loss": 0.9049314260482788,
	"step": 918
	},
	{
	"epoch": 2.5136612021857925,
	"grad_norm": 0.0817629024386406,
	"learning_rate": 6.8935680211621715e-06,
	"loss": 0.8354104161262512,
	"step": 920
	},
	{
	"epoch": 2.519125683060109,
	"grad_norm": 0.09578151255846024,
	"learning_rate": 6.739957164540634e-06,
	"loss": 0.8901323080062866,
	"step": 922
	},
	{
	"epoch": 2.5245901639344264,
	"grad_norm": 0.2716790735721588,
	"learning_rate": 6.587929346842625e-06,
	"loss": 0.542881429195404,
	"step": 924
	},
	{
	"epoch": 2.530054644808743,
	"grad_norm": 0.07322418689727783,
	"learning_rate": 6.437541061855222e-06,
	"loss": 0.48108160495758057,
	"step": 926
	},
	{
	"epoch": 2.5355191256830603,
	"grad_norm": 0.18133673071861267,
	"learning_rate": 6.288848194112459e-06,
	"loss": 0.605663537979126,
	"step": 928
	},
	{
	"epoch": 2.540983606557377,
	"grad_norm": 0.23896083235740662,
	"learning_rate": 6.141905998128495e-06,
	"loss": 0.9464154243469238,
	"step": 930
	},
	{
	"epoch": 2.546448087431694,
	"grad_norm": 0.16439692676067352,
	"learning_rate": 5.996769077865029e-06,
	"loss": 0.616335391998291,
	"step": 932
	},
	{
	"epoch": 2.551912568306011,
	"grad_norm": 0.1357869654893875,
	"learning_rate": 5.853491366440313e-06,
	"loss": 0.899514377117157,
	"step": 934
	},
	{
	"epoch": 2.557377049180328,
	"grad_norm": 0.6998143196105957,
	"learning_rate": 5.712126106087557e-06,
	"loss": 0.7158923149108887,
	"step": 936
	},
	{
	"epoch": 2.5628415300546448,
	"grad_norm": 0.22336842119693756,
	"learning_rate": 5.572725828369961e-06,
	"loss": 0.5384737849235535,
	"step": 938
	},
	{
	"epoch": 2.5683060109289615,
	"grad_norm": 0.13469916582107544,
	"learning_rate": 5.4353423346599944e-06,
	"loss": 0.9431443214416504,
	"step": 940
	},
	{
	"epoch": 2.5737704918032787,
	"grad_norm": 0.13996966183185577,
	"learning_rate": 5.30002667688986e-06,
	"loss": 0.5406258702278137,
	"step": 942
	},
	{
	"epoch": 2.579234972677596,
	"grad_norm": 0.17135582864284515,
	"learning_rate": 5.1668291385804995e-06,
	"loss": 0.9542285203933716,
	"step": 944
	},
	{
	"epoch": 2.5846994535519126,
	"grad_norm": 0.07237273454666138,
	"learning_rate": 5.03579921615621e-06,
	"loss": 0.2618236243724823,
	"step": 946
	},
	{
	"epoch": 2.5901639344262293,
	"grad_norm": 0.09927342087030411,
	"learning_rate": 4.906985600551651e-06,
	"loss": 0.8278122544288635,
	"step": 948
	},
	{
	"epoch": 2.5956284153005464,
	"grad_norm": 0.12567152082920074,
	"learning_rate": 4.780436159118221e-06,
	"loss": 0.6845787167549133,
	"step": 950
	},
	{
	"epoch": 2.6010928961748636,
	"grad_norm": 0.1773616075515747,
	"learning_rate": 4.656197917836474e-06,
	"loss": 0.856772243976593,
	"step": 952
	},
	{
	"epoch": 2.6065573770491803,
	"grad_norm": 0.1038050726056099,
	"learning_rate": 4.5343170438411885e-06,
	"loss": 0.5110206604003906,
	"step": 954
	},
	{
	"epoch": 2.612021857923497,
	"grad_norm": 0.10283994674682617,
	"learning_rate": 4.414838828265581e-06,
	"loss": 0.33818623423576355,
	"step": 956
	},
	{
	"epoch": 2.6174863387978142,
	"grad_norm": 0.09708721190690994,
	"learning_rate": 4.297807669411057e-06,
	"loss": 0.5298760533332825,
	"step": 958
	},
	{
	"epoch": 2.6229508196721314,
	"grad_norm": 0.08416345715522766,
	"learning_rate": 4.183267056248689e-06,
	"loss": 0.7988206744194031,
	"step": 960
	},
	{
	"epoch": 2.628415300546448,
	"grad_norm": 0.4326683580875397,
	"learning_rate": 4.071259552258709e-06,
	"loss": 0.6375377178192139,
	"step": 962
	},
	{
	"epoch": 2.633879781420765,
	"grad_norm": 0.0943351686000824,
	"learning_rate": 3.961826779613801e-06,
	"loss": 0.9425459504127502,
	"step": 964
	},
	{
	"epoch": 2.639344262295082,
	"grad_norm": 0.08805088698863983,
	"learning_rate": 3.85500940371226e-06,
	"loss": 0.8150487542152405,
	"step": 966
	},
	{
	"epoch": 2.644808743169399,
	"grad_norm": 0.07647102326154709,
	"learning_rate": 3.750847118066614e-06,
	"loss": 0.7014102935791016,
	"step": 968
	},
	{
	"epoch": 2.650273224043716,
	"grad_norm": 0.17416299879550934,
	"learning_rate": 3.6493786295535234e-06,
	"loss": 0.7047572135925293,
	"step": 970
	},
	{
	"epoch": 2.6557377049180326,
	"grad_norm": 0.1062597781419754,
	"learning_rate": 3.5506416440301885e-06,
	"loss": 1.0425673723220825,
	"step": 972
	},
	{
	"epoch": 2.66120218579235,
	"grad_norm": 0.1533363163471222,
	"learning_rate": 3.4546728523228067e-06,
	"loss": 0.5896174311637878,
	"step": 974
	},
	{
	"epoch": 2.6666666666666665,
	"grad_norm": 0.14529746770858765,
	"learning_rate": 3.361507916592206e-06,
	"loss": 0.8626460433006287,
	"step": 976
	},
	{
	"epoch": 2.6721311475409837,
	"grad_norm": 0.07237977534532547,
	"learning_rate": 3.271181457081715e-06,
	"loss": 0.9003605246543884,
	"step": 978
	},
	{
	"epoch": 2.6775956284153004,
	"grad_norm": 0.08640500158071518,
	"learning_rate": 3.1837270392522456e-06,
	"loss": 0.8033831715583801,
	"step": 980
	},
	{
	"epoch": 2.6830601092896176,
	"grad_norm": 0.1235438659787178,
	"learning_rate": 3.0991771613092686e-06,
	"loss": 1.0247108936309814,
	"step": 982
	},
	{
	"epoch": 2.6885245901639343,
	"grad_norm": 0.09095709025859833,
	"learning_rate": 3.017563242126483e-06,
	"loss": 0.5988020896911621,
	"step": 984
	},
	{
	"epoch": 2.6939890710382515,
	"grad_norm": 0.1297115683555603,
	"learning_rate": 2.9389156095704764e-06,
	"loss": 1.0478209257125854,
	"step": 986
	},
	{
	"epoch": 2.699453551912568,
	"grad_norm": 0.12489040940999985,
	"learning_rate": 2.8632634892308535e-06,
	"loss": 0.8566729426383972,
	"step": 988
	},
	{
	"epoch": 2.7049180327868854,
	"grad_norm": 0.08687499165534973,
	"learning_rate": 2.7906349935599326e-06,
	"loss": 0.7906680703163147,
	"step": 990
	},
	{
	"epoch": 2.710382513661202,
	"grad_norm": 0.26650258898735046,
	"learning_rate": 2.721057111426154e-06,
	"loss": 0.49348220229148865,
	"step": 992
	},
	{
	"epoch": 2.7158469945355193,
	"grad_norm": 0.1376582682132721,
	"learning_rate": 2.6545556980849417e-06,
	"loss": 0.9247549176216125,
	"step": 994
	},
	{
	"epoch": 2.721311475409836,
	"grad_norm": 0.08857110887765884,
	"learning_rate": 2.591155465570866e-06,
	"loss": 0.8927129507064819,
	"step": 996
	},
	{
	"epoch": 2.726775956284153,
	"grad_norm": 0.07012514770030975,
	"learning_rate": 2.5308799735145813e-06,
	"loss": 0.8281713724136353,
	"step": 998
	},
	{
	"epoch": 2.73224043715847,
	"grad_norm": 0.36359021067619324,
	"learning_rate": 2.473751620388069e-06,
	"loss": 1.0165328979492188,
	"step": 1000
	},
	{
	"epoch": 2.737704918032787,
	"grad_norm": 0.1266205608844757,
	"learning_rate": 2.419791635181301e-06,
	"loss": 0.8732631206512451,
	"step": 1002
	},
	{
	"epoch": 2.7431693989071038,
	"grad_norm": 0.0775340348482132,
	"learning_rate": 2.369020069513521e-06,
	"loss": 0.8283519744873047,
	"step": 1004
	},
	{
	"epoch": 2.748633879781421,
	"grad_norm": 0.26210060715675354,
	"learning_rate": 2.3214557901820258e-06,
	"loss": 0.3722708523273468,
	"step": 1006
	},
	{
	"epoch": 2.7540983606557377,
	"grad_norm": 0.1599731147289276,
	"learning_rate": 2.27711647215124e-06,
	"loss": 1.0166616439819336,
	"step": 1008
	},
	{
	"epoch": 2.7595628415300544,
	"grad_norm": 0.18406230211257935,
	"learning_rate": 2.2360185919846593e-06,
	"loss": 1.0183711051940918,
	"step": 1010
	},
	{
	"epoch": 2.7650273224043715,
	"grad_norm": 0.24661096930503845,
	"learning_rate": 2.1981774217221474e-06,
	"loss": 0.6995247602462769,
	"step": 1012
	},
	{
	"epoch": 2.7704918032786887,
	"grad_norm": 0.10282541066408157,
	"learning_rate": 2.1636070232047966e-06,
	"loss": 0.9614273309707642,
	"step": 1014
	},
	{
	"epoch": 2.7759562841530054,
	"grad_norm": 0.15983141958713531,
	"learning_rate": 2.1323202428495544e-06,
	"loss": 0.7532384991645813,
	"step": 1016
	},
	{
	"epoch": 2.781420765027322,
	"grad_norm": 0.09075122326612473,
	"learning_rate": 2.104328706875452e-06,
	"loss": 0.9738923907279968,
	"step": 1018
	},
	{
	"epoch": 2.7868852459016393,
	"grad_norm": 0.21000061929225922,
	"learning_rate": 2.079642816983293e-06,
	"loss": 0.6343734860420227,
	"step": 1020
	},
	{
	"epoch": 2.7923497267759565,
	"grad_norm": 0.12519368529319763,
	"learning_rate": 2.0582717464903546e-06,
	"loss": 0.9371435046195984,
	"step": 1022
	},
	{
	"epoch": 2.797814207650273,
	"grad_norm": 0.08356457203626633,
	"learning_rate": 2.040223436921581e-06,
	"loss": 0.455655038356781,
	"step": 1024
	},
	{
	"epoch": 2.80327868852459,
	"grad_norm": 0.1446380466222763,
	"learning_rate": 2.025504595058489e-06,
	"loss": 0.9525520205497742,
	"step": 1026
	},
	{
	"epoch": 2.808743169398907,
	"grad_norm": 0.30293965339660645,
	"learning_rate": 2.0141206904469206e-06,
	"loss": 0.6948819160461426,
	"step": 1028
	},
	{
	"epoch": 2.8142076502732243,
	"grad_norm": 0.07843527942895889,
	"learning_rate": 2.006075953364551e-06,
	"loss": 0.7919158935546875,
	"step": 1030
	},
	{
	"epoch": 2.819672131147541,
	"grad_norm": 0.10344526171684265,
	"learning_rate": 2.0013733732489103e-06,
	"loss": 0.789183497428894,
	"step": 1032
	},
	{
	"epoch": 2.8251366120218577,
	"grad_norm": 0.1789560317993164,
	"learning_rate": 2.000014697586502e-06,
	"loss": 0.7047494053840637,
	"step": 1034
	},
	{
	"epoch": 2.830601092896175,
	"grad_norm": 0.11639666557312012,
	"learning_rate": 2.0020004312634374e-06,
	"loss": 1.0080572366714478,
	"step": 1036
	},
	{
	"epoch": 2.836065573770492,
	"grad_norm": 0.08672972768545151,
	"learning_rate": 2.0073298363778166e-06,
	"loss": 0.8355114459991455,
	"step": 1038
	},
	{
	"epoch": 2.841530054644809,
	"grad_norm": 0.11700020730495453,
	"learning_rate": 2.016000932513934e-06,
	"loss": 0.9271637797355652,
	"step": 1040
	},
	{
	"epoch": 2.8469945355191255,
	"grad_norm": 0.07531187683343887,
	"learning_rate": 2.0280104974782058e-06,
	"loss": 0.9033800363540649,
	"step": 1042
	},
	{
	"epoch": 2.8524590163934427,
	"grad_norm": 0.1744087040424347,
	"learning_rate": 2.043354068496541e-06,
	"loss": 0.7458989024162292,
	"step": 1044
	},
	{
	"epoch": 2.8579234972677594,
	"grad_norm": 0.09162133932113647,
	"learning_rate": 2.0620259438727168e-06,
	"loss": 0.9592632055282593,
	"step": 1046
	},
	{
	"epoch": 2.8633879781420766,
	"grad_norm": 0.030708037316799164,
	"learning_rate": 2.084019185107135e-06,
	"loss": 0.46672046184539795,
	"step": 1048
	},
	{
	"epoch": 2.8688524590163933,
	"grad_norm": 0.12400135397911072,
	"learning_rate": 2.1093256194751822e-06,
	"loss": 0.8463804721832275,
	"step": 1050
	},
	{
	"epoch": 2.8743169398907105,
	"grad_norm": 0.18339043855667114,
	"learning_rate": 2.137935843064233e-06,
	"loss": 0.8194495439529419,
	"step": 1052
	},
	{
	"epoch": 2.879781420765027,
	"grad_norm": 0.11495642364025116,
	"learning_rate": 2.1698392242681502e-06,
	"loss": 0.9895132184028625,
	"step": 1054
	},
	{
	"epoch": 2.8852459016393444,
	"grad_norm": 0.8155518770217896,
	"learning_rate": 2.2050239077380097e-06,
	"loss": 0.7439733743667603,
	"step": 1056
	},
	{
	"epoch": 2.890710382513661,
	"grad_norm": 0.3202117383480072,
	"learning_rate": 2.2434768187875723e-06,
	"loss": 0.6009439826011658,
	"step": 1058
	},
	{
	"epoch": 2.8961748633879782,
	"grad_norm": 0.10869040340185165,
	"learning_rate": 2.285183668251853e-06,
	"loss": 0.8892866969108582,
	"step": 1060
	},
	{
	"epoch": 2.901639344262295,
	"grad_norm": 0.12712760269641876,
	"learning_rate": 2.3301289577970028e-06,
	"loss": 0.8923851847648621,
	"step": 1062
	},
	{
	"epoch": 2.907103825136612,
	"grad_norm": 0.08466093987226486,
	"learning_rate": 2.3782959856795113e-06,
	"loss": 0.9176651239395142,
	"step": 1064
	},
	{
	"epoch": 2.912568306010929,
	"grad_norm": 0.08564656227827072,
	"learning_rate": 2.4296668529525998e-06,
	"loss": 0.5260547995567322,
	"step": 1066
	},
	{
	"epoch": 2.918032786885246,
	"grad_norm": 0.5003576278686523,
	"learning_rate": 2.4842224701175147e-06,
	"loss": 0.6537207961082458,
	"step": 1068
	},
	{
	"epoch": 2.9234972677595628,
	"grad_norm": 0.1762370467185974,
	"learning_rate": 2.541942564217196e-06,
	"loss": 0.7581856846809387,
	"step": 1070
	},
	{
	"epoch": 2.92896174863388,
	"grad_norm": 0.09134093672037125,
	"learning_rate": 2.6028056863697506e-06,
	"loss": 0.9717255234718323,
	"step": 1072
	},
	{
	"epoch": 2.9344262295081966,
	"grad_norm": 0.10428964346647263,
	"learning_rate": 2.6667892197388884e-06,
	"loss": 0.5648120045661926,
	"step": 1074
	},
	{
	"epoch": 2.939890710382514,
	"grad_norm": 0.1324595808982849,
	"learning_rate": 2.7338693879383967e-06,
	"loss": 0.6206448674201965,
	"step": 1076
	},
	{
	"epoch": 2.9453551912568305,
	"grad_norm": 0.17810961604118347,
	"learning_rate": 2.8040212638674506e-06,
	"loss": 0.5412209033966064,
	"step": 1078
	},
	{
	"epoch": 2.9508196721311473,
	"grad_norm": 0.15168237686157227,
	"learning_rate": 2.877218778973578e-06,
	"loss": 0.979107677936554,
	"step": 1080
	},
	{
	"epoch": 2.9562841530054644,
	"grad_norm": 0.3206607401371002,
	"learning_rate": 2.9534347329398027e-06,
	"loss": 0.6219339370727539,
	"step": 1082
	},
	{
	"epoch": 2.9617486338797816,
	"grad_norm": 0.10671282559633255,
	"learning_rate": 3.0326408037922827e-06,
	"loss": 0.9135304093360901,
	"step": 1084
	},
	{
	"epoch": 2.9672131147540983,
	"grad_norm": 0.0563555508852005,
	"learning_rate": 3.1148075584248306e-06,
	"loss": 0.5136356353759766,
	"step": 1086
	},
	{
	"epoch": 2.972677595628415,
	"grad_norm": 0.10856077820062637,
	"learning_rate": 3.199904463536296e-06,
	"loss": 1.0512590408325195,
	"step": 1088
	},
	{
	"epoch": 2.978142076502732,
	"grad_norm": 0.08381670713424683,
	"learning_rate": 3.2878998969767954e-06,
	"loss": 0.7392516732215881,
	"step": 1090
	},
	{
	"epoch": 2.9836065573770494,
	"grad_norm": 0.08783172816038132,
	"learning_rate": 3.378761159498547e-06,
	"loss": 0.744635820388794,
	"step": 1092
	},
	{
	"epoch": 2.989071038251366,
	"grad_norm": 1.6826421022415161,
	"learning_rate": 3.472454486906972e-06,
	"loss": 0.8086671233177185,
	"step": 1094
	},
	{
	"epoch": 2.994535519125683,
	"grad_norm": 0.23645569384098053,
	"learning_rate": 3.5689450626075132e-06,
	"loss": 0.5458236336708069,
	"step": 1096
	},
	{
	"epoch": 3.0,
	"grad_norm": 0.11009235680103302,
	"learning_rate": 3.668197030543573e-06,
	"loss": 0.8465088605880737,
	"step": 1098
	},
	{
	"epoch": 3.0,
	"step": 1098,
	"total_flos": 4.842473815785079e+18,
	"train_loss": 0.9778182457162166,
	"train_runtime": 38444.4554,
	"train_samples_per_second": 1.714,
	"train_steps_per_second": 0.029
	}
	],
	"logging_steps": 2,
	"max_steps": 1098,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 3,
	"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": 4.842473815785079e+18,
	"train_batch_size": 1,
	"trial_name": null,
	"trial_params": null
	}