Instructions to use furproxy/9b-49 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use furproxy/9b-49 with Transformers:

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

pipe = pipeline("image-text-to-text", model="furproxy/9b-49")
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-49")
model = AutoModelForImageTextToText.from_pretrained("furproxy/9b-49")
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-49 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "furproxy/9b-49"
# 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-49",
		"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-49

SGLang

How to use furproxy/9b-49 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-49" \
    --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-49",
		"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-49" \
        --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-49",
		"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-49 with Docker Model Runner:
```
docker model run hf.co/furproxy/9b-49
```

9b-49 / trainer_state.json

furproxy

Upload folder using huggingface_hub

06b00a7 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": 0.697250247001648,
	"learning_rate": 5.454545454545455e-07,
	"loss": 1.9263319969177246,
	"step": 2
	},
	{
	"epoch": 0.01092896174863388,
	"grad_norm": 0.721147894859314,
	"learning_rate": 1.6363636363636363e-06,
	"loss": 1.9639064073562622,
	"step": 4
	},
	{
	"epoch": 0.01639344262295082,
	"grad_norm": 0.7265484929084778,
	"learning_rate": 2.7272727272727272e-06,
	"loss": 1.8129602670669556,
	"step": 6
	},
	{
	"epoch": 0.02185792349726776,
	"grad_norm": 0.5450526475906372,
	"learning_rate": 3.818181818181818e-06,
	"loss": 1.9235541820526123,
	"step": 8
	},
	{
	"epoch": 0.0273224043715847,
	"grad_norm": 0.8771107196807861,
	"learning_rate": 4.90909090909091e-06,
	"loss": 2.251471519470215,
	"step": 10
	},
	{
	"epoch": 0.03278688524590164,
	"grad_norm": 10.971705436706543,
	"learning_rate": 6e-06,
	"loss": 3.0256073474884033,
	"step": 12
	},
	{
	"epoch": 0.03825136612021858,
	"grad_norm": 0.5691296458244324,
	"learning_rate": 7.090909090909091e-06,
	"loss": 1.903341293334961,
	"step": 14
	},
	{
	"epoch": 0.04371584699453552,
	"grad_norm": 0.632869303226471,
	"learning_rate": 8.181818181818181e-06,
	"loss": 1.824144721031189,
	"step": 16
	},
	{
	"epoch": 0.04918032786885246,
	"grad_norm": 2.687931776046753,
	"learning_rate": 9.272727272727273e-06,
	"loss": 2.273005962371826,
	"step": 18
	},
	{
	"epoch": 0.0546448087431694,
	"grad_norm": 1.9365599155426025,
	"learning_rate": 1.0363636363636364e-05,
	"loss": 1.9546592235565186,
	"step": 20
	},
	{
	"epoch": 0.060109289617486336,
	"grad_norm": 5.1370134353637695,
	"learning_rate": 1.1454545454545455e-05,
	"loss": 2.148141860961914,
	"step": 22
	},
	{
	"epoch": 0.06557377049180328,
	"grad_norm": 0.595227837562561,
	"learning_rate": 1.2545454545454545e-05,
	"loss": 1.7927855253219604,
	"step": 24
	},
	{
	"epoch": 0.07103825136612021,
	"grad_norm": 0.4974764585494995,
	"learning_rate": 1.3636363636363637e-05,
	"loss": 1.8154855966567993,
	"step": 26
	},
	{
	"epoch": 0.07650273224043716,
	"grad_norm": 0.4138644337654114,
	"learning_rate": 1.4727272727272728e-05,
	"loss": 1.7593921422958374,
	"step": 28
	},
	{
	"epoch": 0.08196721311475409,
	"grad_norm": 1.1251859664916992,
	"learning_rate": 1.5818181818181818e-05,
	"loss": 1.6035438776016235,
	"step": 30
	},
	{
	"epoch": 0.08743169398907104,
	"grad_norm": 3.0598487854003906,
	"learning_rate": 1.6909090909090907e-05,
	"loss": 1.9531118869781494,
	"step": 32
	},
	{
	"epoch": 0.09289617486338798,
	"grad_norm": 0.38799506425857544,
	"learning_rate": 1.8e-05,
	"loss": 1.632307529449463,
	"step": 34
	},
	{
	"epoch": 0.09836065573770492,
	"grad_norm": 1.2041815519332886,
	"learning_rate": 1.909090909090909e-05,
	"loss": 2.1407182216644287,
	"step": 36
	},
	{
	"epoch": 0.10382513661202186,
	"grad_norm": 1.2261812686920166,
	"learning_rate": 2.0181818181818183e-05,
	"loss": 1.7205183506011963,
	"step": 38
	},
	{
	"epoch": 0.1092896174863388,
	"grad_norm": 0.778466522693634,
	"learning_rate": 2.1272727272727273e-05,
	"loss": 1.4309196472167969,
	"step": 40
	},
	{
	"epoch": 0.11475409836065574,
	"grad_norm": 0.4726494550704956,
	"learning_rate": 2.2363636363636366e-05,
	"loss": 1.3979218006134033,
	"step": 42
	},
	{
	"epoch": 0.12021857923497267,
	"grad_norm": 0.46920815110206604,
	"learning_rate": 2.3454545454545456e-05,
	"loss": 1.5350127220153809,
	"step": 44
	},
	{
	"epoch": 0.12568306010928962,
	"grad_norm": 0.3451603353023529,
	"learning_rate": 2.454545454545455e-05,
	"loss": 1.2750825881958008,
	"step": 46
	},
	{
	"epoch": 0.13114754098360656,
	"grad_norm": 0.4018639326095581,
	"learning_rate": 2.5636363636363635e-05,
	"loss": 1.4977831840515137,
	"step": 48
	},
	{
	"epoch": 0.1366120218579235,
	"grad_norm": 0.32938382029533386,
	"learning_rate": 2.6727272727272728e-05,
	"loss": 1.455066204071045,
	"step": 50
	},
	{
	"epoch": 0.14207650273224043,
	"grad_norm": 0.3992089331150055,
	"learning_rate": 2.7818181818181818e-05,
	"loss": 1.50904381275177,
	"step": 52
	},
	{
	"epoch": 0.14754098360655737,
	"grad_norm": 0.48714780807495117,
	"learning_rate": 2.890909090909091e-05,
	"loss": 1.6593310832977295,
	"step": 54
	},
	{
	"epoch": 0.15300546448087432,
	"grad_norm": 0.5381816029548645,
	"learning_rate": 3e-05,
	"loss": 1.4189538955688477,
	"step": 56
	},
	{
	"epoch": 0.15846994535519127,
	"grad_norm": 2.2116336822509766,
	"learning_rate": 2.9997491688899256e-05,
	"loss": 1.0185623168945312,
	"step": 58
	},
	{
	"epoch": 0.16393442622950818,
	"grad_norm": 0.775851309299469,
	"learning_rate": 2.998996768768956e-05,
	"loss": 0.9615996479988098,
	"step": 60
	},
	{
	"epoch": 0.16939890710382513,
	"grad_norm": 0.5596693158149719,
	"learning_rate": 2.9977430792302124e-05,
	"loss": 1.397382378578186,
	"step": 62
	},
	{
	"epoch": 0.17486338797814208,
	"grad_norm": 0.37642741203308105,
	"learning_rate": 2.9959885661467903e-05,
	"loss": 1.1756441593170166,
	"step": 64
	},
	{
	"epoch": 0.18032786885245902,
	"grad_norm": 0.5881237983703613,
	"learning_rate": 2.993733881498636e-05,
	"loss": 0.8743929862976074,
	"step": 66
	},
	{
	"epoch": 0.18579234972677597,
	"grad_norm": 0.5072574615478516,
	"learning_rate": 2.9909798631302736e-05,
	"loss": 1.398439645767212,
	"step": 68
	},
	{
	"epoch": 0.1912568306010929,
	"grad_norm": 0.3287373185157776,
	"learning_rate": 2.987727534439457e-05,
	"loss": 1.2875562906265259,
	"step": 70
	},
	{
	"epoch": 0.19672131147540983,
	"grad_norm": 5.050961017608643,
	"learning_rate": 2.983978103996877e-05,
	"loss": 0.9359242916107178,
	"step": 72
	},
	{
	"epoch": 0.20218579234972678,
	"grad_norm": 0.4209338128566742,
	"learning_rate": 2.9797329650970525e-05,
	"loss": 1.1358091831207275,
	"step": 74
	},
	{
	"epoch": 0.20765027322404372,
	"grad_norm": 0.4743102490901947,
	"learning_rate": 2.974993695240579e-05,
	"loss": 1.252506971359253,
	"step": 76
	},
	{
	"epoch": 0.21311475409836064,
	"grad_norm": 0.7218373417854309,
	"learning_rate": 2.9697620555479297e-05,
	"loss": 1.3395963907241821,
	"step": 78
	},
	{
	"epoch": 0.2185792349726776,
	"grad_norm": 0.35181427001953125,
	"learning_rate": 2.9640399901050182e-05,
	"loss": 1.3289461135864258,
	"step": 80
	},
	{
	"epoch": 0.22404371584699453,
	"grad_norm": 0.6300466656684875,
	"learning_rate": 2.9578296252407734e-05,
	"loss": 1.3236968517303467,
	"step": 82
	},
	{
	"epoch": 0.22950819672131148,
	"grad_norm": 0.3324219286441803,
	"learning_rate": 2.9511332687369917e-05,
	"loss": 1.2778677940368652,
	"step": 84
	},
	{
	"epoch": 0.23497267759562843,
	"grad_norm": 0.3525979816913605,
	"learning_rate": 2.9439534089707624e-05,
	"loss": 1.2054697275161743,
	"step": 86
	},
	{
	"epoch": 0.24043715846994534,
	"grad_norm": 0.568080484867096,
	"learning_rate": 2.9362927139897832e-05,
	"loss": 0.8521115779876709,
	"step": 88
	},
	{
	"epoch": 0.2459016393442623,
	"grad_norm": 0.9504212141036987,
	"learning_rate": 2.9281540305209068e-05,
	"loss": 0.9611366987228394,
	"step": 90
	},
	{
	"epoch": 0.25136612021857924,
	"grad_norm": 0.5896546840667725,
	"learning_rate": 2.919540382912294e-05,
	"loss": 1.2202290296554565,
	"step": 92
	},
	{
	"epoch": 0.2568306010928962,
	"grad_norm": 0.4182462990283966,
	"learning_rate": 2.9104549720095634e-05,
	"loss": 0.7185679078102112,
	"step": 94
	},
	{
	"epoch": 0.26229508196721313,
	"grad_norm": 0.6521818041801453,
	"learning_rate": 2.9009011739663467e-05,
	"loss": 1.2726106643676758,
	"step": 96
	},
	{
	"epoch": 0.2677595628415301,
	"grad_norm": 0.5340232253074646,
	"learning_rate": 2.8908825389897094e-05,
	"loss": 1.2408103942871094,
	"step": 98
	},
	{
	"epoch": 0.273224043715847,
	"grad_norm": 0.3869662284851074,
	"learning_rate": 2.8804027900208843e-05,
	"loss": 1.1218898296356201,
	"step": 100
	},
	{
	"epoch": 0.2786885245901639,
	"grad_norm": 0.3763534724712372,
	"learning_rate": 2.8694658213518226e-05,
	"loss": 0.8273072242736816,
	"step": 102
	},
	{
	"epoch": 0.28415300546448086,
	"grad_norm": 0.36140915751457214,
	"learning_rate": 2.8580756971780686e-05,
	"loss": 1.3101215362548828,
	"step": 104
	},
	{
	"epoch": 0.2896174863387978,
	"grad_norm": 0.45537811517715454,
	"learning_rate": 2.846236650088497e-05,
	"loss": 1.2583913803100586,
	"step": 106
	},
	{
	"epoch": 0.29508196721311475,
	"grad_norm": 0.512202799320221,
	"learning_rate": 2.833953079492476e-05,
	"loss": 1.346620798110962,
	"step": 108
	},
	{
	"epoch": 0.3005464480874317,
	"grad_norm": 0.2695588767528534,
	"learning_rate": 2.82122954998504e-05,
	"loss": 1.265444278717041,
	"step": 110
	},
	{
	"epoch": 0.30601092896174864,
	"grad_norm": 0.3954983949661255,
	"learning_rate": 2.808070789650679e-05,
	"loss": 1.2438230514526367,
	"step": 112
	},
	{
	"epoch": 0.3114754098360656,
	"grad_norm": 0.6031639575958252,
	"learning_rate": 2.7944816883063727e-05,
	"loss": 1.0083987712860107,
	"step": 114
	},
	{
	"epoch": 0.31693989071038253,
	"grad_norm": 0.3518785834312439,
	"learning_rate": 2.7804672956845295e-05,
	"loss": 1.22913658618927,
	"step": 116
	},
	{
	"epoch": 0.3224043715846995,
	"grad_norm": 0.6181989908218384,
	"learning_rate": 2.766032819556495e-05,
	"loss": 1.2250205278396606,
	"step": 118
	},
	{
	"epoch": 0.32786885245901637,
	"grad_norm": 4.4156494140625,
	"learning_rate": 2.7511836237973366e-05,
	"loss": 0.9285832047462463,
	"step": 120
	},
	{
	"epoch": 0.3333333333333333,
	"grad_norm": 0.6863148212432861,
	"learning_rate": 2.735925226392618e-05,
	"loss": 1.5127151012420654,
	"step": 122
	},
	{
	"epoch": 0.33879781420765026,
	"grad_norm": 0.2905527651309967,
	"learning_rate": 2.7202632973879086e-05,
	"loss": 1.2349207401275635,
	"step": 124
	},
	{
	"epoch": 0.3442622950819672,
	"grad_norm": 0.2775297462940216,
	"learning_rate": 2.7042036567817838e-05,
	"loss": 1.1945700645446777,
	"step": 126
	},
	{
	"epoch": 0.34972677595628415,
	"grad_norm": 0.3885118067264557,
	"learning_rate": 2.6877522723631036e-05,
	"loss": 0.8623289465904236,
	"step": 128
	},
	{
	"epoch": 0.3551912568306011,
	"grad_norm": 0.48008739948272705,
	"learning_rate": 2.6709152574933727e-05,
	"loss": 1.019203543663025,
	"step": 130
	},
	{
	"epoch": 0.36065573770491804,
	"grad_norm": 1.9439845085144043,
	"learning_rate": 2.6536988688350067e-05,
	"loss": 0.9837391376495361,
	"step": 132
	},
	{
	"epoch": 0.366120218579235,
	"grad_norm": 0.30251508951187134,
	"learning_rate": 2.6361095040263437e-05,
	"loss": 1.2110865116119385,
	"step": 134
	},
	{
	"epoch": 0.37158469945355194,
	"grad_norm": 0.3148176074028015,
	"learning_rate": 2.618153699304274e-05,
	"loss": 1.2147680521011353,
	"step": 136
	},
	{
	"epoch": 0.3770491803278688,
	"grad_norm": 0.42469698190689087,
	"learning_rate": 2.599838127075361e-05,
	"loss": 1.2221580743789673,
	"step": 138
	},
	{
	"epoch": 0.3825136612021858,
	"grad_norm": 0.33319714665412903,
	"learning_rate": 2.5811695934363666e-05,
	"loss": 0.7449063062667847,
	"step": 140
	},
	{
	"epoch": 0.3879781420765027,
	"grad_norm": 0.4343816339969635,
	"learning_rate": 2.5621550356450914e-05,
	"loss": 0.8672135472297668,
	"step": 142
	},
	{
	"epoch": 0.39344262295081966,
	"grad_norm": 0.44463595747947693,
	"learning_rate": 2.5428015195424825e-05,
	"loss": 0.8414742946624756,
	"step": 144
	},
	{
	"epoch": 0.3989071038251366,
	"grad_norm": 0.7496324181556702,
	"learning_rate": 2.5231162369269498e-05,
	"loss": 0.7604200839996338,
	"step": 146
	},
	{
	"epoch": 0.40437158469945356,
	"grad_norm": 0.36488234996795654,
	"learning_rate": 2.503106502881889e-05,
	"loss": 1.2763407230377197,
	"step": 148
	},
	{
	"epoch": 0.4098360655737705,
	"grad_norm": 0.34441977739334106,
	"learning_rate": 2.4827797530573762e-05,
	"loss": 1.190218210220337,
	"step": 150
	},
	{
	"epoch": 0.41530054644808745,
	"grad_norm": 0.4284515082836151,
	"learning_rate": 2.4621435409070757e-05,
	"loss": 1.2155894041061401,
	"step": 152
	},
	{
	"epoch": 0.4207650273224044,
	"grad_norm": 0.6492432355880737,
	"learning_rate": 2.4412055348813602e-05,
	"loss": 1.1843308210372925,
	"step": 154
	},
	{
	"epoch": 0.4262295081967213,
	"grad_norm": 0.34537646174430847,
	"learning_rate": 2.4199735155777017e-05,
	"loss": 1.2178831100463867,
	"step": 156
	},
	{
	"epoch": 0.43169398907103823,
	"grad_norm": 1.2686742544174194,
	"learning_rate": 2.3984553728493914e-05,
	"loss": 1.0317703485488892,
	"step": 158
	},
	{
	"epoch": 0.4371584699453552,
	"grad_norm": 0.5937894582748413,
	"learning_rate": 2.3766591028736547e-05,
	"loss": 1.2135744094848633,
	"step": 160
	},
	{
	"epoch": 0.4426229508196721,
	"grad_norm": 2.5808207988739014,
	"learning_rate": 2.3545928051802588e-05,
	"loss": 0.8519853353500366,
	"step": 162
	},
	{
	"epoch": 0.44808743169398907,
	"grad_norm": 0.3145885765552521,
	"learning_rate": 2.332264679641717e-05,
	"loss": 1.2207863330841064,
	"step": 164
	},
	{
	"epoch": 0.453551912568306,
	"grad_norm": 1.2698609828948975,
	"learning_rate": 2.3096830234261996e-05,
	"loss": 0.843329131603241,
	"step": 166
	},
	{
	"epoch": 0.45901639344262296,
	"grad_norm": 0.2692093849182129,
	"learning_rate": 2.2868562279142912e-05,
	"loss": 1.206931233406067,
	"step": 168
	},
	{
	"epoch": 0.4644808743169399,
	"grad_norm": 0.31359997391700745,
	"learning_rate": 2.2637927755807458e-05,
	"loss": 1.532818078994751,
	"step": 170
	},
	{
	"epoch": 0.46994535519125685,
	"grad_norm": 0.8711612820625305,
	"learning_rate": 2.2405012368423786e-05,
	"loss": 0.9171653389930725,
	"step": 172
	},
	{
	"epoch": 0.47540983606557374,
	"grad_norm": 0.41555553674697876,
	"learning_rate": 2.2169902668732893e-05,
	"loss": 1.2091866731643677,
	"step": 174
	},
	{
	"epoch": 0.4808743169398907,
	"grad_norm": 0.3255589008331299,
	"learning_rate": 2.193268602388583e-05,
	"loss": 1.1792771816253662,
	"step": 176
	},
	{
	"epoch": 0.48633879781420764,
	"grad_norm": 2.388908624649048,
	"learning_rate": 2.1693450583977953e-05,
	"loss": 1.2991008758544922,
	"step": 178
	},
	{
	"epoch": 0.4918032786885246,
	"grad_norm": 0.8777170777320862,
	"learning_rate": 2.1452285249292147e-05,
	"loss": 0.9539348483085632,
	"step": 180
	},
	{
	"epoch": 0.4972677595628415,
	"grad_norm": 0.5306017398834229,
	"learning_rate": 2.12092796372634e-05,
	"loss": 1.217163324356079,
	"step": 182
	},
	{
	"epoch": 0.5027322404371585,
	"grad_norm": 0.3937690556049347,
	"learning_rate": 2.096452404917679e-05,
	"loss": 1.1728050708770752,
	"step": 184
	},
	{
	"epoch": 0.5081967213114754,
	"grad_norm": 0.4189966022968292,
	"learning_rate": 2.0718109436611348e-05,
	"loss": 1.1901968717575073,
	"step": 186
	},
	{
	"epoch": 0.5136612021857924,
	"grad_norm": 0.8861513733863831,
	"learning_rate": 2.0470127367642345e-05,
	"loss": 0.4577289819717407,
	"step": 188
	},
	{
	"epoch": 0.5191256830601093,
	"grad_norm": 0.8669730424880981,
	"learning_rate": 2.022066999281444e-05,
	"loss": 1.170414924621582,
	"step": 190
	},
	{
	"epoch": 0.5245901639344263,
	"grad_norm": 0.43784815073013306,
	"learning_rate": 1.9969830010898358e-05,
	"loss": 1.2003910541534424,
	"step": 192
	},
	{
	"epoch": 0.5300546448087432,
	"grad_norm": 0.2408360242843628,
	"learning_rate": 1.9717700634443903e-05,
	"loss": 1.196523904800415,
	"step": 194
	},
	{
	"epoch": 0.5355191256830601,
	"grad_norm": 0.275288462638855,
	"learning_rate": 1.9464375555142e-05,
	"loss": 0.9004436135292053,
	"step": 196
	},
	{
	"epoch": 0.5409836065573771,
	"grad_norm": 0.30962035059928894,
	"learning_rate": 1.9209948909008734e-05,
	"loss": 1.002712368965149,
	"step": 198
	},
	{
	"epoch": 0.546448087431694,
	"grad_norm": 0.37051403522491455,
	"learning_rate": 1.8954515241404218e-05,
	"loss": 1.0420843362808228,
	"step": 200
	},
	{
	"epoch": 0.5519125683060109,
	"grad_norm": 0.37618082761764526,
	"learning_rate": 1.8698169471899414e-05,
	"loss": 1.0357520580291748,
	"step": 202
	},
	{
	"epoch": 0.5573770491803278,
	"grad_norm": 0.3667483627796173,
	"learning_rate": 1.8441006859003842e-05,
	"loss": 1.15482759475708,
	"step": 204
	},
	{
	"epoch": 0.5628415300546448,
	"grad_norm": 0.35124123096466064,
	"learning_rate": 1.818312296476737e-05,
	"loss": 1.1959636211395264,
	"step": 206
	},
	{
	"epoch": 0.5683060109289617,
	"grad_norm": 0.35074105858802795,
	"learning_rate": 1.792461361926921e-05,
	"loss": 1.087142825126648,
	"step": 208
	},
	{
	"epoch": 0.5737704918032787,
	"grad_norm": 0.40441736578941345,
	"learning_rate": 1.766557488500727e-05,
	"loss": 1.23688805103302,
	"step": 210
	},
	{
	"epoch": 0.5792349726775956,
	"grad_norm": 0.40216121077537537,
	"learning_rate": 1.7406103021201212e-05,
	"loss": 1.175810694694519,
	"step": 212
	},
	{
	"epoch": 0.5846994535519126,
	"grad_norm": 0.356263130903244,
	"learning_rate": 1.7146294448022335e-05,
	"loss": 1.2632404565811157,
	"step": 214
	},
	{
	"epoch": 0.5901639344262295,
	"grad_norm": 0.379120409488678,
	"learning_rate": 1.688624571076371e-05,
	"loss": 1.1749930381774902,
	"step": 216
	},
	{
	"epoch": 0.5956284153005464,
	"grad_norm": 0.4688524901866913,
	"learning_rate": 1.6626053443963762e-05,
	"loss": 1.2324018478393555,
	"step": 218
	},
	{
	"epoch": 0.6010928961748634,
	"grad_norm": 0.3071102797985077,
	"learning_rate": 1.636581433549674e-05,
	"loss": 1.0937501192092896,
	"step": 220
	},
	{
	"epoch": 0.6065573770491803,
	"grad_norm": 0.4043320417404175,
	"learning_rate": 1.610562509064332e-05,
	"loss": 0.7812168598175049,
	"step": 222
	},
	{
	"epoch": 0.6120218579234973,
	"grad_norm": 0.37222233414649963,
	"learning_rate": 1.5845582396154786e-05,
	"loss": 1.1552724838256836,
	"step": 224
	},
	{
	"epoch": 0.6174863387978142,
	"grad_norm": 0.32638704776763916,
	"learning_rate": 1.5585782884324064e-05,
	"loss": 1.1811174154281616,
	"step": 226
	},
	{
	"epoch": 0.6229508196721312,
	"grad_norm": 1.021145224571228,
	"learning_rate": 1.5326323097077015e-05,
	"loss": 0.7545455694198608,
	"step": 228
	},
	{
	"epoch": 0.6284153005464481,
	"grad_norm": 1.044705867767334,
	"learning_rate": 1.5067299450097261e-05,
	"loss": 1.1588557958602905,
	"step": 230
	},
	{
	"epoch": 0.6338797814207651,
	"grad_norm": 0.417707622051239,
	"learning_rate": 1.4808808196998006e-05,
	"loss": 1.1800490617752075,
	"step": 232
	},
	{
	"epoch": 0.639344262295082,
	"grad_norm": 0.4615285396575928,
	"learning_rate": 1.4550945393554004e-05,
	"loss": 0.9214609861373901,
	"step": 234
	},
	{
	"epoch": 0.644808743169399,
	"grad_norm": 0.9104841947555542,
	"learning_rate": 1.4293806862007085e-05,
	"loss": 1.4733829498291016,
	"step": 236
	},
	{
	"epoch": 0.6502732240437158,
	"grad_norm": 0.5479267239570618,
	"learning_rate": 1.4037488155458448e-05,
	"loss": 1.122392177581787,
	"step": 238
	},
	{
	"epoch": 0.6557377049180327,
	"grad_norm": 1.7201780080795288,
	"learning_rate": 1.3782084522360981e-05,
	"loss": 1.0747902393341064,
	"step": 240
	},
	{
	"epoch": 0.6612021857923497,
	"grad_norm": 0.2870098948478699,
	"learning_rate": 1.3527690871124762e-05,
	"loss": 0.7035287022590637,
	"step": 242
	},
	{
	"epoch": 0.6666666666666666,
	"grad_norm": 0.618334174156189,
	"learning_rate": 1.3274401734848958e-05,
	"loss": 1.2590125799179077,
	"step": 244
	},
	{
	"epoch": 0.6721311475409836,
	"grad_norm": 0.9182770848274231,
	"learning_rate": 1.3022311236193156e-05,
	"loss": 1.1282920837402344,
	"step": 246
	},
	{
	"epoch": 0.6775956284153005,
	"grad_norm": 0.3048880398273468,
	"learning_rate": 1.2771513052401236e-05,
	"loss": 1.1468207836151123,
	"step": 248
	},
	{
	"epoch": 0.6830601092896175,
	"grad_norm": 0.46364668011665344,
	"learning_rate": 1.2522100380490744e-05,
	"loss": 0.41445863246917725,
	"step": 250
	},
	{
	"epoch": 0.6885245901639344,
	"grad_norm": 0.3374931216239929,
	"learning_rate": 1.2274165902620732e-05,
	"loss": 1.205442190170288,
	"step": 252
	},
	{
	"epoch": 0.6939890710382514,
	"grad_norm": 0.30988192558288574,
	"learning_rate": 1.2027801751650918e-05,
	"loss": 1.1606954336166382,
	"step": 254
	},
	{
	"epoch": 0.6994535519125683,
	"grad_norm": 0.6835072040557861,
	"learning_rate": 1.1783099476904972e-05,
	"loss": 0.9375866651535034,
	"step": 256
	},
	{
	"epoch": 0.7049180327868853,
	"grad_norm": 0.5492672324180603,
	"learning_rate": 1.1540150010150599e-05,
	"loss": 1.1717281341552734,
	"step": 258
	},
	{
	"epoch": 0.7103825136612022,
	"grad_norm": 1.321418285369873,
	"learning_rate": 1.1299043631809205e-05,
	"loss": 1.0042099952697754,
	"step": 260
	},
	{
	"epoch": 0.7158469945355191,
	"grad_norm": 0.5885441303253174,
	"learning_rate": 1.1059869937407486e-05,
	"loss": 1.1690725088119507,
	"step": 262
	},
	{
	"epoch": 0.7213114754098361,
	"grad_norm": 0.4145934581756592,
	"learning_rate": 1.082271780428362e-05,
	"loss": 1.1503442525863647,
	"step": 264
	},
	{
	"epoch": 0.726775956284153,
	"grad_norm": 0.3795332610607147,
	"learning_rate": 1.0587675358560278e-05,
	"loss": 0.7821759581565857,
	"step": 266
	},
	{
	"epoch": 0.73224043715847,
	"grad_norm": 0.34867045283317566,
	"learning_rate": 1.0354829942396837e-05,
	"loss": 1.1533390283584595,
	"step": 268
	},
	{
	"epoch": 0.7377049180327869,
	"grad_norm": 0.3432830572128296,
	"learning_rate": 1.012426808153287e-05,
	"loss": 1.1842344999313354,
	"step": 270
	},
	{
	"epoch": 0.7431693989071039,
	"grad_norm": 0.37027257680892944,
	"learning_rate": 9.896075453135039e-06,
	"loss": 1.2416757345199585,
	"step": 272
	},
	{
	"epoch": 0.7486338797814208,
	"grad_norm": 0.8126760721206665,
	"learning_rate": 9.67033685395934e-06,
	"loss": 1.2841261625289917,
	"step": 274
	},
	{
	"epoch": 0.7540983606557377,
	"grad_norm": 0.7494352459907532,
	"learning_rate": 9.447136168840466e-06,
	"loss": 1.2585190534591675,
	"step": 276
	},
	{
	"epoch": 0.7595628415300546,
	"grad_norm": 0.6677407026290894,
	"learning_rate": 9.226556339520069e-06,
	"loss": 0.826260507106781,
	"step": 278
	},
	{
	"epoch": 0.7650273224043715,
	"grad_norm": 0.294973224401474,
	"learning_rate": 9.008679333825478e-06,
	"loss": 1.1650235652923584,
	"step": 280
	},
	{
	"epoch": 0.7704918032786885,
	"grad_norm": 0.4066277742385864,
	"learning_rate": 8.793586115210326e-06,
	"loss": 1.0734792947769165,
	"step": 282
	},
	{
	"epoch": 0.7759562841530054,
	"grad_norm": 0.24723787605762482,
	"learning_rate": 8.581356612668382e-06,
	"loss": 1.1951000690460205,
	"step": 284
	},
	{
	"epoch": 0.7814207650273224,
	"grad_norm": 0.7921513319015503,
	"learning_rate": 8.372069691031804e-06,
	"loss": 1.210968017578125,
	"step": 286
	},
	{
	"epoch": 0.7868852459016393,
	"grad_norm": 0.9979972243309021,
	"learning_rate": 8.165803121664869e-06,
	"loss": 0.7500867247581482,
	"step": 288
	},
	{
	"epoch": 0.7923497267759563,
	"grad_norm": 0.3506968915462494,
	"learning_rate": 7.962633553563965e-06,
	"loss": 0.8001227974891663,
	"step": 290
	},
	{
	"epoch": 0.7978142076502732,
	"grad_norm": 0.33423033356666565,
	"learning_rate": 7.762636484874723e-06,
	"loss": 0.9556211233139038,
	"step": 292
	},
	{
	"epoch": 0.8032786885245902,
	"grad_norm": 0.3771698474884033,
	"learning_rate": 7.565886234836767e-06,
	"loss": 1.159753441810608,
	"step": 294
	},
	{
	"epoch": 0.8087431693989071,
	"grad_norm": 0.36711210012435913,
	"learning_rate": 7.3724559161665876e-06,
	"loss": 1.1728172302246094,
	"step": 296
	},
	{
	"epoch": 0.8142076502732241,
	"grad_norm": 0.3197503685951233,
	"learning_rate": 7.182417407888703e-06,
	"loss": 1.1757210493087769,
	"step": 298
	},
	{
	"epoch": 0.819672131147541,
	"grad_norm": 0.3136984705924988,
	"learning_rate": 6.995841328625321e-06,
	"loss": 0.8655977845191956,
	"step": 300
	},
	{
	"epoch": 0.825136612021858,
	"grad_norm": 0.393072247505188,
	"learning_rate": 6.812797010354325e-06,
	"loss": 1.1789922714233398,
	"step": 302
	},
	{
	"epoch": 0.8306010928961749,
	"grad_norm": 3.821265935897827,
	"learning_rate": 6.63335247264542e-06,
	"loss": 1.08378005027771,
	"step": 304
	},
	{
	"epoch": 0.8360655737704918,
	"grad_norm": 0.33668431639671326,
	"learning_rate": 6.457574397383919e-06,
	"loss": 1.1709719896316528,
	"step": 306
	},
	{
	"epoch": 0.8415300546448088,
	"grad_norm": 0.3578186631202698,
	"learning_rate": 6.285528103991665e-06,
	"loss": 1.193668246269226,
	"step": 308
	},
	{
	"epoch": 0.8469945355191257,
	"grad_norm": 0.3615029752254486,
	"learning_rate": 6.117277525154225e-06,
	"loss": 1.15645432472229,
	"step": 310
	},
	{
	"epoch": 0.8524590163934426,
	"grad_norm": 0.38210004568099976,
	"learning_rate": 5.952885183063397e-06,
	"loss": 1.1638695001602173,
	"step": 312
	},
	{
	"epoch": 0.8579234972677595,
	"grad_norm": 0.35445594787597656,
	"learning_rate": 5.792412166183841e-06,
	"loss": 1.1909141540527344,
	"step": 314
	},
	{
	"epoch": 0.8633879781420765,
	"grad_norm": 0.5096743702888489,
	"learning_rate": 5.635918106552546e-06,
	"loss": 1.201849102973938,
	"step": 316
	},
	{
	"epoch": 0.8688524590163934,
	"grad_norm": 1.2665657997131348,
	"learning_rate": 5.483461157619428e-06,
	"loss": 0.7697218656539917,
	"step": 318
	},
	{
	"epoch": 0.8743169398907104,
	"grad_norm": 0.31564080715179443,
	"learning_rate": 5.335097972637441e-06,
	"loss": 1.154910683631897,
	"step": 320
	},
	{
	"epoch": 0.8797814207650273,
	"grad_norm": 0.41027265787124634,
	"learning_rate": 5.1908836836101135e-06,
	"loss": 0.810014545917511,
	"step": 322
	},
	{
	"epoch": 0.8852459016393442,
	"grad_norm": 0.5105057954788208,
	"learning_rate": 5.050871880804414e-06,
	"loss": 1.4533857107162476,
	"step": 324
	},
	{
	"epoch": 0.8907103825136612,
	"grad_norm": 0.35378292202949524,
	"learning_rate": 4.915114592836521e-06,
	"loss": 1.1535991430282593,
	"step": 326
	},
	{
	"epoch": 0.8961748633879781,
	"grad_norm": 1.3628326654434204,
	"learning_rate": 4.783662267337909e-06,
	"loss": 1.1089421510696411,
	"step": 328
	},
	{
	"epoch": 0.9016393442622951,
	"grad_norm": 0.2328273057937622,
	"learning_rate": 4.656563752208907e-06,
	"loss": 1.2124766111373901,
	"step": 330
	},
	{
	"epoch": 0.907103825136612,
	"grad_norm": 0.31986290216445923,
	"learning_rate": 4.533866277466767e-06,
	"loss": 1.1944669485092163,
	"step": 332
	},
	{
	"epoch": 0.912568306010929,
	"grad_norm": 1.5621281862258911,
	"learning_rate": 4.415615437694876e-06,
	"loss": 1.3944669961929321,
	"step": 334
	},
	{
	"epoch": 0.9180327868852459,
	"grad_norm": 2.3418469429016113,
	"learning_rate": 4.3018551750997694e-06,
	"loss": 1.1178382635116577,
	"step": 336
	},
	{
	"epoch": 0.9234972677595629,
	"grad_norm": 0.40905457735061646,
	"learning_rate": 4.192627763182111e-06,
	"loss": 1.1970925331115723,
	"step": 338
	},
	{
	"epoch": 0.9289617486338798,
	"grad_norm": 1.2464805841445923,
	"learning_rate": 4.087973791027797e-06,
	"loss": 0.7709401249885559,
	"step": 340
	},
	{
	"epoch": 0.9344262295081968,
	"grad_norm": 0.713545560836792,
	"learning_rate": 3.987932148224993e-06,
	"loss": 1.1292576789855957,
	"step": 342
	},
	{
	"epoch": 0.9398907103825137,
	"grad_norm": 1.2035443782806396,
	"learning_rate": 3.8925400104126834e-06,
	"loss": 0.7497198581695557,
	"step": 344
	},
	{
	"epoch": 0.9453551912568307,
	"grad_norm": 0.3672787845134735,
	"learning_rate": 3.8018328254661618e-06,
	"loss": 1.1717313528060913,
	"step": 346
	},
	{
	"epoch": 0.9508196721311475,
	"grad_norm": 0.602628767490387,
	"learning_rate": 3.715844300324527e-06,
	"loss": 0.9975014328956604,
	"step": 348
	},
	{
	"epoch": 0.9562841530054644,
	"grad_norm": 0.4423633813858032,
	"learning_rate": 3.6346063884651327e-06,
	"loss": 1.1410292387008667,
	"step": 350
	},
	{
	"epoch": 0.9617486338797814,
	"grad_norm": 0.7007730007171631,
	"learning_rate": 3.558149278029624e-06,
	"loss": 1.3128447532653809,
	"step": 352
	},
	{
	"epoch": 0.9672131147540983,
	"grad_norm": 0.439485639333725,
	"learning_rate": 3.4865013806059817e-06,
	"loss": 0.7662681341171265,
	"step": 354
	},
	{
	"epoch": 0.9726775956284153,
	"grad_norm": 0.4370954930782318,
	"learning_rate": 3.419689320670712e-06,
	"loss": 0.7777884602546692,
	"step": 356
	},
	{
	"epoch": 0.9781420765027322,
	"grad_norm": 1.6398391723632812,
	"learning_rate": 3.35773792569517e-06,
	"loss": 1.1536012887954712,
	"step": 358
	},
	{
	"epoch": 0.9836065573770492,
	"grad_norm": 0.42289936542510986,
	"learning_rate": 3.300670216919602e-06,
	"loss": 0.8657046556472778,
	"step": 360
	},
	{
	"epoch": 0.9890710382513661,
	"grad_norm": 0.49119001626968384,
	"learning_rate": 3.2485074007984468e-06,
	"loss": 1.1398602724075317,
	"step": 362
	},
	{
	"epoch": 0.994535519125683,
	"grad_norm": 0.897072434425354,
	"learning_rate": 3.2012688611199566e-06,
	"loss": 1.2387840747833252,
	"step": 364
	},
	{
	"epoch": 1.0,
	"grad_norm": 0.38847413659095764,
	"learning_rate": 3.158972151803165e-06,
	"loss": 1.236254334449768,
	"step": 366
	},
	{
	"epoch": 1.005464480874317,
	"grad_norm": 0.31760314106941223,
	"learning_rate": 3.1216329903748095e-06,
	"loss": 0.761336088180542,
	"step": 368
	},
	{
	"epoch": 1.010928961748634,
	"grad_norm": 0.3967256247997284,
	"learning_rate": 3.089265252128686e-06,
	"loss": 1.2508467435836792,
	"step": 370
	},
	{
	"epoch": 1.0163934426229508,
	"grad_norm": 0.4457378387451172,
	"learning_rate": 3.061880964969555e-06,
	"loss": 1.246903419494629,
	"step": 372
	},
	{
	"epoch": 1.0218579234972678,
	"grad_norm": 0.3824722170829773,
	"learning_rate": 3.039490304943562e-06,
	"loss": 1.1185325384140015,
	"step": 374
	},
	{
	"epoch": 1.0273224043715847,
	"grad_norm": 0.3070431053638458,
	"learning_rate": 3.022101592456795e-06,
	"loss": 1.0686273574829102,
	"step": 376
	},
	{
	"epoch": 1.0327868852459017,
	"grad_norm": 0.28226983547210693,
	"learning_rate": 3.0097212891834095e-06,
	"loss": 1.0337367057800293,
	"step": 378
	},
	{
	"epoch": 1.0382513661202186,
	"grad_norm": 0.4869016110897064,
	"learning_rate": 3.0023539956644634e-06,
	"loss": 1.0311717987060547,
	"step": 380
	},
	{
	"epoch": 1.0437158469945356,
	"grad_norm": 0.8694993257522583,
	"learning_rate": 3.0000024495983428e-06,
	"loss": 0.7782408595085144,
	"step": 382
	},
	{
	"epoch": 1.0491803278688525,
	"grad_norm": 0.5946288108825684,
	"learning_rate": 3.002667524823434e-06,
	"loss": 1.0987261533737183,
	"step": 384
	},
	{
	"epoch": 1.0546448087431695,
	"grad_norm": 1.0870792865753174,
	"learning_rate": 3.010348230993402e-06,
	"loss": 1.0993095636367798,
	"step": 386
	},
	{
	"epoch": 1.0601092896174864,
	"grad_norm": 0.5876205563545227,
	"learning_rate": 3.0230417139451987e-06,
	"loss": 1.4858818054199219,
	"step": 388
	},
	{
	"epoch": 1.0655737704918034,
	"grad_norm": 0.8428175449371338,
	"learning_rate": 3.0407432567596883e-06,
	"loss": 0.9062157273292542,
	"step": 390
	},
	{
	"epoch": 1.0710382513661203,
	"grad_norm": 1.2778754234313965,
	"learning_rate": 3.0634462815144474e-06,
	"loss": 0.592805802822113,
	"step": 392
	},
	{
	"epoch": 1.0765027322404372,
	"grad_norm": 0.4570184648036957,
	"learning_rate": 3.0911423517281404e-06,
	"loss": 1.1192593574523926,
	"step": 394
	},
	{
	"epoch": 1.0819672131147542,
	"grad_norm": 0.42796361446380615,
	"learning_rate": 3.1238211754955294e-06,
	"loss": 1.0443531274795532,
	"step": 396
	},
	{
	"epoch": 1.0874316939890711,
	"grad_norm": 0.43680837750434875,
	"learning_rate": 3.161470609311961e-06,
	"loss": 1.0404291152954102,
	"step": 398
	},
	{
	"epoch": 1.092896174863388,
	"grad_norm": 0.40812206268310547,
	"learning_rate": 3.2040766625859115e-06,
	"loss": 1.1858930587768555,
	"step": 400
	},
	{
	"epoch": 1.098360655737705,
	"grad_norm": 0.5379334688186646,
	"learning_rate": 3.2516235028379157e-06,
	"loss": 1.0395185947418213,
	"step": 402
	},
	{
	"epoch": 1.1038251366120218,
	"grad_norm": 0.40824946761131287,
	"learning_rate": 3.304093461583944e-06,
	"loss": 1.026267170906067,
	"step": 404
	},
	{
	"epoch": 1.1092896174863387,
	"grad_norm": 0.603408694267273,
	"learning_rate": 3.3614670409010353e-06,
	"loss": 1.076138973236084,
	"step": 406
	},
	{
	"epoch": 1.1147540983606556,
	"grad_norm": 0.41980448365211487,
	"learning_rate": 3.4237229206727602e-06,
	"loss": 1.3695933818817139,
	"step": 408
	},
	{
	"epoch": 1.1202185792349726,
	"grad_norm": 0.869969367980957,
	"learning_rate": 3.490837966511817e-06,
	"loss": 1.047141671180725,
	"step": 410
	},
	{
	"epoch": 1.1256830601092895,
	"grad_norm": 0.38264161348342896,
	"learning_rate": 3.5627872383567937e-06,
	"loss": 1.0203361511230469,
	"step": 412
	},
	{
	"epoch": 1.1311475409836065,
	"grad_norm": 0.30198222398757935,
	"learning_rate": 3.6395439997399494e-06,
	"loss": 0.5207374095916748,
	"step": 414
	},
	{
	"epoch": 1.1366120218579234,
	"grad_norm": 1.9066449403762817,
	"learning_rate": 3.721079727722522e-06,
	"loss": 1.2205498218536377,
	"step": 416
	},
	{
	"epoch": 1.1420765027322404,
	"grad_norm": 0.28766530752182007,
	"learning_rate": 3.8073641234939055e-06,
	"loss": 1.1669960021972656,
	"step": 418
	},
	{
	"epoch": 1.1475409836065573,
	"grad_norm": 0.4494319558143616,
	"learning_rate": 3.898365123630732e-06,
	"loss": 1.0348408222198486,
	"step": 420
	},
	{
	"epoch": 1.1530054644808743,
	"grad_norm": 0.7580645680427551,
	"learning_rate": 3.994048912011692e-06,
	"loss": 1.0489870309829712,
	"step": 422
	},
	{
	"epoch": 1.1584699453551912,
	"grad_norm": 0.30486011505126953,
	"learning_rate": 4.094379932383666e-06,
	"loss": 1.0182819366455078,
	"step": 424
	},
	{
	"epoch": 1.1639344262295082,
	"grad_norm": 0.5283482074737549,
	"learning_rate": 4.199320901574489e-06,
	"loss": 0.7681307792663574,
	"step": 426
	},
	{
	"epoch": 1.169398907103825,
	"grad_norm": 0.6967251896858215,
	"learning_rate": 4.3088328233474185e-06,
	"loss": 1.1920503377914429,
	"step": 428
	},
	{
	"epoch": 1.174863387978142,
	"grad_norm": 0.30848848819732666,
	"learning_rate": 4.422875002892234e-06,
	"loss": 1.1227927207946777,
	"step": 430
	},
	{
	"epoch": 1.180327868852459,
	"grad_norm": 0.4338774085044861,
	"learning_rate": 4.54140506194747e-06,
	"loss": 1.0621066093444824,
	"step": 432
	},
	{
	"epoch": 1.185792349726776,
	"grad_norm": 0.5365703701972961,
	"learning_rate": 4.664378954548241e-06,
	"loss": 1.0539458990097046,
	"step": 434
	},
	{
	"epoch": 1.1912568306010929,
	"grad_norm": 0.9198355674743652,
	"learning_rate": 4.791750983393832e-06,
	"loss": 0.6073042750358582,
	"step": 436
	},
	{
	"epoch": 1.1967213114754098,
	"grad_norm": 0.2908204197883606,
	"learning_rate": 4.9234738168288466e-06,
	"loss": 0.4756653904914856,
	"step": 438
	},
	{
	"epoch": 1.2021857923497268,
	"grad_norm": 0.43431609869003296,
	"learning_rate": 5.059498506431758e-06,
	"loss": 0.9815635085105896,
	"step": 440
	},
	{
	"epoch": 1.2076502732240437,
	"grad_norm": 0.8783625364303589,
	"learning_rate": 5.199774505204206e-06,
	"loss": 1.324447512626648,
	"step": 442
	},
	{
	"epoch": 1.2131147540983607,
	"grad_norm": 0.8234128355979919,
	"learning_rate": 5.344249686354357e-06,
	"loss": 1.26932692527771,
	"step": 444
	},
	{
	"epoch": 1.2185792349726776,
	"grad_norm": 0.35708698630332947,
	"learning_rate": 5.492870362667299e-06,
	"loss": 0.5943037271499634,
	"step": 446
	},
	{
	"epoch": 1.2240437158469946,
	"grad_norm": 0.3496783375740051,
	"learning_rate": 5.645581306455302e-06,
	"loss": 0.8465991616249084,
	"step": 448
	},
	{
	"epoch": 1.2295081967213115,
	"grad_norm": 0.34306076169013977,
	"learning_rate": 5.802325770080506e-06,
	"loss": 1.0558314323425293,
	"step": 450
	},
	{
	"epoch": 1.2349726775956285,
	"grad_norm": 0.6199325919151306,
	"learning_rate": 5.96304550704246e-06,
	"loss": 0.7405421137809753,
	"step": 452
	},
	{
	"epoch": 1.2404371584699454,
	"grad_norm": 0.5972355604171753,
	"learning_rate": 6.127680793622588e-06,
	"loss": 1.023563027381897,
	"step": 454
	},
	{
	"epoch": 1.2459016393442623,
	"grad_norm": 0.36354729533195496,
	"learning_rate": 6.296170451077657e-06,
	"loss": 1.149239420890808,
	"step": 456
	},
	{
	"epoch": 1.2513661202185793,
	"grad_norm": 0.5815706849098206,
	"learning_rate": 6.468451868373856e-06,
	"loss": 0.5993931889533997,
	"step": 458
	},
	{
	"epoch": 1.2568306010928962,
	"grad_norm": 0.884687066078186,
	"learning_rate": 6.6444610254532e-06,
	"loss": 1.1250090599060059,
	"step": 460
	},
	{
	"epoch": 1.2622950819672132,
	"grad_norm": 0.5644488334655762,
	"learning_rate": 6.824132517023449e-06,
	"loss": 1.117283821105957,
	"step": 462
	},
	{
	"epoch": 1.2677595628415301,
	"grad_norm": 1.1574392318725586,
	"learning_rate": 7.007399576862872e-06,
	"loss": 0.8585411906242371,
	"step": 464
	},
	{
	"epoch": 1.273224043715847,
	"grad_norm": 0.31241562962532043,
	"learning_rate": 7.1941941026306275e-06,
	"loss": 1.159734845161438,
	"step": 466
	},
	{
	"epoch": 1.278688524590164,
	"grad_norm": 3.079608678817749,
	"learning_rate": 7.3844466811737555e-06,
	"loss": 0.43219655752182007,
	"step": 468
	},
	{
	"epoch": 1.2841530054644807,
	"grad_norm": 1.1515812873840332,
	"learning_rate": 7.578086614321175e-06,
	"loss": 0.32784971594810486,
	"step": 470
	},
	{
	"epoch": 1.289617486338798,
	"grad_norm": 0.8713538646697998,
	"learning_rate": 7.775041945155295e-06,
	"loss": 0.972320556640625,
	"step": 472
	},
	{
	"epoch": 1.2950819672131146,
	"grad_norm": 1.0352020263671875,
	"learning_rate": 7.975239484751258e-06,
	"loss": 0.8251127004623413,
	"step": 474
	},
	{
	"epoch": 1.3005464480874318,
	"grad_norm": 0.41140851378440857,
	"learning_rate": 8.178604839374125e-06,
	"loss": 1.0359759330749512,
	"step": 476
	},
	{
	"epoch": 1.3060109289617485,
	"grad_norm": 0.30868738889694214,
	"learning_rate": 8.385062438123673e-06,
	"loss": 1.13455331325531,
	"step": 478
	},
	{
	"epoch": 1.3114754098360657,
	"grad_norm": 0.603076159954071,
	"learning_rate": 8.594535561016661e-06,
	"loss": 1.1488956212997437,
	"step": 480
	},
	{
	"epoch": 1.3169398907103824,
	"grad_norm": 0.32255861163139343,
	"learning_rate": 8.806946367496155e-06,
	"loss": 1.1327383518218994,
	"step": 482
	},
	{
	"epoch": 1.3224043715846996,
	"grad_norm": 0.37436342239379883,
	"learning_rate": 9.02221592535712e-06,
	"loss": 1.0864595174789429,
	"step": 484
	},
	{
	"epoch": 1.3278688524590163,
	"grad_norm": 0.4781150221824646,
	"learning_rate": 9.240264240077859e-06,
	"loss": 0.2114480584859848,
	"step": 486
	},
	{
	"epoch": 1.3333333333333333,
	"grad_norm": 0.7249221205711365,
	"learning_rate": 9.461010284546016e-06,
	"loss": 1.14420747756958,
	"step": 488
	},
	{
	"epoch": 1.3387978142076502,
	"grad_norm": 0.31920719146728516,
	"learning_rate": 9.684372029168438e-06,
	"loss": 0.9852396249771118,
	"step": 490
	},
	{
	"epoch": 1.3442622950819672,
	"grad_norm": 0.31214451789855957,
	"learning_rate": 9.91026647235348e-06,
	"loss": 1.109579086303711,
	"step": 492
	},
	{
	"epoch": 1.349726775956284,
	"grad_norm": 1.5647644996643066,
	"learning_rate": 1.0138609671354586e-05,
	"loss": 0.6934401988983154,
	"step": 494
	},
	{
	"epoch": 1.355191256830601,
	"grad_norm": 0.3006077706813812,
	"learning_rate": 1.0369316773463458e-05,
	"loss": 1.0647120475769043,
	"step": 496
	},
	{
	"epoch": 1.360655737704918,
	"grad_norm": 0.3098089098930359,
	"learning_rate": 1.0602302047541566e-05,
	"loss": 0.8615930676460266,
	"step": 498
	},
	{
	"epoch": 1.366120218579235,
	"grad_norm": 0.30825164914131165,
	"learning_rate": 1.083747891587788e-05,
	"loss": 0.9996722340583801,
	"step": 500
	},
	{
	"epoch": 1.3715846994535519,
	"grad_norm": 0.31744763255119324,
	"learning_rate": 1.1074759986361392e-05,
	"loss": 1.1010159254074097,
	"step": 502
	},
	{
	"epoch": 1.3770491803278688,
	"grad_norm": 0.660419225692749,
	"learning_rate": 1.1314057084956073e-05,
	"loss": 0.9897991418838501,
	"step": 504
	},
	{
	"epoch": 1.3825136612021858,
	"grad_norm": 0.4726075530052185,
	"learning_rate": 1.1555281288466553e-05,
	"loss": 0.7116650342941284,
	"step": 506
	},
	{
	"epoch": 1.3879781420765027,
	"grad_norm": 0.4236489236354828,
	"learning_rate": 1.1798342957582084e-05,
	"loss": 0.7277122139930725,
	"step": 508
	},
	{
	"epoch": 1.3934426229508197,
	"grad_norm": 0.3505037724971771,
	"learning_rate": 1.2043151770186725e-05,
	"loss": 1.0869934558868408,
	"step": 510
	},
	{
	"epoch": 1.3989071038251366,
	"grad_norm": 0.4062495529651642,
	"learning_rate": 1.2289616754923078e-05,
	"loss": 1.0307718515396118,
	"step": 512
	},
	{
	"epoch": 1.4043715846994536,
	"grad_norm": 0.9875432252883911,
	"learning_rate": 1.253764632499752e-05,
	"loss": 0.6626445055007935,
	"step": 514
	},
	{
	"epoch": 1.4098360655737705,
	"grad_norm": 0.6780223846435547,
	"learning_rate": 1.2787148312213901e-05,
	"loss": 1.4220600128173828,
	"step": 516
	},
	{
	"epoch": 1.4153005464480874,
	"grad_norm": 0.32189661264419556,
	"learning_rate": 1.3038030001223439e-05,
	"loss": 0.7831554412841797,
	"step": 518
	},
	{
	"epoch": 1.4207650273224044,
	"grad_norm": 0.38265976309776306,
	"learning_rate": 1.3290198163977933e-05,
	"loss": 0.7503346800804138,
	"step": 520
	},
	{
	"epoch": 1.4262295081967213,
	"grad_norm": 0.7597147226333618,
	"learning_rate": 1.3543559094373372e-05,
	"loss": 0.7089603543281555,
	"step": 522
	},
	{
	"epoch": 1.4316939890710383,
	"grad_norm": 0.4683310091495514,
	"learning_rate": 1.3798018643071386e-05,
	"loss": 0.7786340117454529,
	"step": 524
	},
	{
	"epoch": 1.4371584699453552,
	"grad_norm": 0.4911711812019348,
	"learning_rate": 1.4053482252485178e-05,
	"loss": 0.9898138642311096,
	"step": 526
	},
	{
	"epoch": 1.4426229508196722,
	"grad_norm": 0.29452064633369446,
	"learning_rate": 1.4309854991917388e-05,
	"loss": 1.0076603889465332,
	"step": 528
	},
	{
	"epoch": 1.4480874316939891,
	"grad_norm": 0.31045207381248474,
	"learning_rate": 1.4567041592836413e-05,
	"loss": 0.6953315734863281,
	"step": 530
	},
	{
	"epoch": 1.453551912568306,
	"grad_norm": 0.39866623282432556,
	"learning_rate": 1.48249464842784e-05,
	"loss": 1.1244227886199951,
	"step": 532
	},
	{
	"epoch": 1.459016393442623,
	"grad_norm": 0.4015820026397705,
	"learning_rate": 1.508347382836153e-05,
	"loss": 1.071346402168274,
	"step": 534
	},
	{
	"epoch": 1.46448087431694,
	"grad_norm": 0.4267948269844055,
	"learning_rate": 1.534252755589961e-05,
	"loss": 1.0431689023971558,
	"step": 536
	},
	{
	"epoch": 1.469945355191257,
	"grad_norm": 0.24437487125396729,
	"learning_rate": 1.5602011402101432e-05,
	"loss": 0.6640901565551758,
	"step": 538
	},
	{
	"epoch": 1.4754098360655736,
	"grad_norm": 0.2949664890766144,
	"learning_rate": 1.5861828942343037e-05,
	"loss": 0.8600192070007324,
	"step": 540
	},
	{
	"epoch": 1.4808743169398908,
	"grad_norm": 3.951502561569214,
	"learning_rate": 1.612188362799917e-05,
	"loss": 1.1732059717178345,
	"step": 542
	},
	{
	"epoch": 1.4863387978142075,
	"grad_norm": 0.34538793563842773,
	"learning_rate": 1.6382078822320964e-05,
	"loss": 1.0121636390686035,
	"step": 544
	},
	{
	"epoch": 1.4918032786885247,
	"grad_norm": 0.8434890508651733,
	"learning_rate": 1.6642317836346324e-05,
	"loss": 0.7092042565345764,
	"step": 546
	},
	{
	"epoch": 1.4972677595628414,
	"grad_norm": 0.849798321723938,
	"learning_rate": 1.6902503964829644e-05,
	"loss": 0.8493767380714417,
	"step": 548
	},
	{
	"epoch": 1.5027322404371586,
	"grad_norm": 0.2791331708431244,
	"learning_rate": 1.7162540522177685e-05,
	"loss": 1.0140348672866821,
	"step": 550
	},
	{
	"epoch": 1.5081967213114753,
	"grad_norm": 0.6075169444084167,
	"learning_rate": 1.7422330878378113e-05,
	"loss": 0.8161216974258423,
	"step": 552
	},
	{
	"epoch": 1.5136612021857925,
	"grad_norm": 0.361250638961792,
	"learning_rate": 1.7681778494907298e-05,
	"loss": 1.0384575128555298,
	"step": 554
	},
	{
	"epoch": 1.5191256830601092,
	"grad_norm": 0.3741307854652405,
	"learning_rate": 1.794078696060429e-05,
	"loss": 0.7678899168968201,
	"step": 556
	},
	{
	"epoch": 1.5245901639344264,
	"grad_norm": 0.3114408552646637,
	"learning_rate": 1.819926002749727e-05,
	"loss": 1.02855384349823,
	"step": 558
	},
	{
	"epoch": 1.530054644808743,
	"grad_norm": 0.18622533977031708,
	"learning_rate": 1.84571016465695e-05,
	"loss": 0.2526892423629761,
	"step": 560
	},
	{
	"epoch": 1.5355191256830603,
	"grad_norm": 0.23625467717647552,
	"learning_rate": 1.8714216003451295e-05,
	"loss": 1.0640628337860107,
	"step": 562
	},
	{
	"epoch": 1.540983606557377,
	"grad_norm": 0.724408745765686,
	"learning_rate": 1.8970507554024827e-05,
	"loss": 0.7283908724784851,
	"step": 564
	},
	{
	"epoch": 1.5464480874316942,
	"grad_norm": 0.3644772171974182,
	"learning_rate": 1.922588105992838e-05,
	"loss": 1.1399354934692383,
	"step": 566
	},
	{
	"epoch": 1.5519125683060109,
	"grad_norm": 0.9722273349761963,
	"learning_rate": 1.9480241623947206e-05,
	"loss": 1.1557573080062866,
	"step": 568
	},
	{
	"epoch": 1.5573770491803278,
	"grad_norm": 0.4744189381599426,
	"learning_rate": 1.9733494725277413e-05,
	"loss": 1.133260726928711,
	"step": 570
	},
	{
	"epoch": 1.5628415300546448,
	"grad_norm": 2.321540594100952,
	"learning_rate": 1.998554625465005e-05,
	"loss": 0.6360920071601868,
	"step": 572
	},
	{
	"epoch": 1.5683060109289617,
	"grad_norm": 0.6282745599746704,
	"learning_rate": 2.0236302549302293e-05,
	"loss": 0.9884318709373474,
	"step": 574
	},
	{
	"epoch": 1.5737704918032787,
	"grad_norm": 0.25726932287216187,
	"learning_rate": 2.0485670427782644e-05,
	"loss": 1.072218656539917,
	"step": 576
	},
	{
	"epoch": 1.5792349726775956,
	"grad_norm": 0.3337240517139435,
	"learning_rate": 2.073355722457739e-05,
	"loss": 1.0474885702133179,
	"step": 578
	},
	{
	"epoch": 1.5846994535519126,
	"grad_norm": 0.3079088628292084,
	"learning_rate": 2.0979870824545165e-05,
	"loss": 1.0121105909347534,
	"step": 580
	},
	{
	"epoch": 1.5901639344262295,
	"grad_norm": 0.33754849433898926,
	"learning_rate": 2.1224519697147145e-05,
	"loss": 1.059688925743103,
	"step": 582
	},
	{
	"epoch": 1.5956284153005464,
	"grad_norm": 0.8730252385139465,
	"learning_rate": 2.1467412930459936e-05,
	"loss": 0.5801796317100525,
	"step": 584
	},
	{
	"epoch": 1.6010928961748634,
	"grad_norm": 1.4568897485733032,
	"learning_rate": 2.1708460264958595e-05,
	"loss": 1.0416557788848877,
	"step": 586
	},
	{
	"epoch": 1.6065573770491803,
	"grad_norm": 0.33535847067832947,
	"learning_rate": 2.194757212705718e-05,
	"loss": 1.0528165102005005,
	"step": 588
	},
	{
	"epoch": 1.6120218579234973,
	"grad_norm": 0.39254218339920044,
	"learning_rate": 2.2184659662394522e-05,
	"loss": 1.2890545129776,
	"step": 590
	},
	{
	"epoch": 1.6174863387978142,
	"grad_norm": 0.39055129885673523,
	"learning_rate": 2.24196347688526e-05,
	"loss": 1.0770164728164673,
	"step": 592
	},
	{
	"epoch": 1.6229508196721312,
	"grad_norm": 0.3632502853870392,
	"learning_rate": 2.265241012929541e-05,
	"loss": 1.0873066186904907,
	"step": 594
	},
	{
	"epoch": 1.6284153005464481,
	"grad_norm": 0.43228334188461304,
	"learning_rate": 2.28828992440162e-05,
	"loss": 1.009541630744934,
	"step": 596
	},
	{
	"epoch": 1.633879781420765,
	"grad_norm": 0.34224361181259155,
	"learning_rate": 2.3111016462880873e-05,
	"loss": 1.3436585664749146,
	"step": 598
	},
	{
	"epoch": 1.639344262295082,
	"grad_norm": 1.0117156505584717,
	"learning_rate": 2.333667701715578e-05,
	"loss": 0.9953033328056335,
	"step": 600
	},
	{
	"epoch": 1.644808743169399,
	"grad_norm": 0.4946202337741852,
	"learning_rate": 2.3559797051007815e-05,
	"loss": 1.3335758447647095,
	"step": 602
	},
	{
	"epoch": 1.650273224043716,
	"grad_norm": 0.30347269773483276,
	"learning_rate": 2.3780293652665477e-05,
	"loss": 0.9623563289642334,
	"step": 604
	},
	{
	"epoch": 1.6557377049180326,
	"grad_norm": 0.32685670256614685,
	"learning_rate": 2.399808488522895e-05,
	"loss": 1.137532353401184,
	"step": 606
	},
	{
	"epoch": 1.6612021857923498,
	"grad_norm": 0.3293339014053345,
	"learning_rate": 2.4213089817118078e-05,
	"loss": 1.055052399635315,
	"step": 608
	},
	{
	"epoch": 1.6666666666666665,
	"grad_norm": 0.46230047941207886,
	"learning_rate": 2.4425228552146573e-05,
	"loss": 1.1524425745010376,
	"step": 610
	},
	{
	"epoch": 1.6721311475409837,
	"grad_norm": 0.6461423635482788,
	"learning_rate": 2.4634422259211614e-05,
	"loss": 0.6941080689430237,
	"step": 612
	},
	{
	"epoch": 1.6775956284153004,
	"grad_norm": 1.0476462841033936,
	"learning_rate": 2.4840593201587626e-05,
	"loss": 0.8486734628677368,
	"step": 614
	},
	{
	"epoch": 1.6830601092896176,
	"grad_norm": 2.0571165084838867,
	"learning_rate": 2.5043664765813377e-05,
	"loss": 0.7663911581039429,
	"step": 616
	},
	{
	"epoch": 1.6885245901639343,
	"grad_norm": 0.4737246334552765,
	"learning_rate": 2.524356149016163e-05,
	"loss": 1.0844976902008057,
	"step": 618
	},
	{
	"epoch": 1.6939890710382515,
	"grad_norm": 0.3629366457462311,
	"learning_rate": 2.544020909268085e-05,
	"loss": 1.0529444217681885,
	"step": 620
	},
	{
	"epoch": 1.6994535519125682,
	"grad_norm": 0.3002009689807892,
	"learning_rate": 2.5633534498798598e-05,
	"loss": 1.004475474357605,
	"step": 622
	},
	{
	"epoch": 1.7049180327868854,
	"grad_norm": 6.076183319091797,
	"learning_rate": 2.5823465868475985e-05,
	"loss": 0.6815961599349976,
	"step": 624
	},
	{
	"epoch": 1.710382513661202,
	"grad_norm": 0.3336254954338074,
	"learning_rate": 2.60099326229037e-05,
	"loss": 1.1199313402175903,
	"step": 626
	},
	{
	"epoch": 1.7158469945355193,
	"grad_norm": 0.39660659432411194,
	"learning_rate": 2.619286547072914e-05,
	"loss": 1.038909673690796,
	"step": 628
	},
	{
	"epoch": 1.721311475409836,
	"grad_norm": 3.282057523727417,
	"learning_rate": 2.6372196433805214e-05,
	"loss": 0.709031879901886,
	"step": 630
	},
	{
	"epoch": 1.7267759562841531,
	"grad_norm": 0.4394005835056305,
	"learning_rate": 2.654785887245112e-05,
	"loss": 0.7367001175880432,
	"step": 632
	},
	{
	"epoch": 1.7322404371584699,
	"grad_norm": 0.32146531343460083,
	"learning_rate": 2.671978751021577e-05,
	"loss": 1.2364336252212524,
	"step": 634
	},
	{
	"epoch": 1.737704918032787,
	"grad_norm": 0.4605696499347687,
	"learning_rate": 2.6887918458134622e-05,
	"loss": 0.9947465658187866,
	"step": 636
	},
	{
	"epoch": 1.7431693989071038,
	"grad_norm": 0.3082851469516754,
	"learning_rate": 2.705218923847093e-05,
	"loss": 1.0885943174362183,
	"step": 638
	},
	{
	"epoch": 1.748633879781421,
	"grad_norm": 0.31364598870277405,
	"learning_rate": 2.7212538807932576e-05,
	"loss": 1.113791823387146,
	"step": 640
	},
	{
	"epoch": 1.7540983606557377,
	"grad_norm": 0.375470906496048,
	"learning_rate": 2.7368907580355843e-05,
	"loss": 0.7379390001296997,
	"step": 642
	},
	{
	"epoch": 1.7595628415300546,
	"grad_norm": 0.7673870921134949,
	"learning_rate": 2.7521237448847734e-05,
	"loss": 0.3575439751148224,
	"step": 644
	},
	{
	"epoch": 1.7650273224043715,
	"grad_norm": 0.4010154604911804,
	"learning_rate": 2.766947180737861e-05,
	"loss": 1.1416033506393433,
	"step": 646
	},
	{
	"epoch": 1.7704918032786885,
	"grad_norm": 0.27221986651420593,
	"learning_rate": 2.781355557181706e-05,
	"loss": 0.8822421431541443,
	"step": 648
	},
	{
	"epoch": 1.7759562841530054,
	"grad_norm": 0.496616005897522,
	"learning_rate": 2.7953435200399262e-05,
	"loss": 0.7749378085136414,
	"step": 650
	},
	{
	"epoch": 1.7814207650273224,
	"grad_norm": 0.7093772888183594,
	"learning_rate": 2.8089058713625194e-05,
	"loss": 0.7831916809082031,
	"step": 652
	},
	{
	"epoch": 1.7868852459016393,
	"grad_norm": 0.351391464471817,
	"learning_rate": 2.8220375713574307e-05,
	"loss": 1.0371301174163818,
	"step": 654
	},
	{
	"epoch": 1.7923497267759563,
	"grad_norm": 0.2960720658302307,
	"learning_rate": 2.8347337402633456e-05,
	"loss": 1.0718927383422852,
	"step": 656
	},
	{
	"epoch": 1.7978142076502732,
	"grad_norm": 0.6162258386611938,
	"learning_rate": 2.846989660163019e-05,
	"loss": 0.9962674379348755,
	"step": 658
	},
	{
	"epoch": 1.8032786885245902,
	"grad_norm": 0.4377414286136627,
	"learning_rate": 2.858800776736461e-05,
	"loss": 1.1022226810455322,
	"step": 660
	},
	{
	"epoch": 1.8087431693989071,
	"grad_norm": 0.2909747064113617,
	"learning_rate": 2.87016270095333e-05,
	"loss": 0.8855769634246826,
	"step": 662
	},
	{
	"epoch": 1.814207650273224,
	"grad_norm": 1.3076122999191284,
	"learning_rate": 2.8810712107039e-05,
	"loss": 0.6500188708305359,
	"step": 664
	},
	{
	"epoch": 1.819672131147541,
	"grad_norm": 0.303838849067688,
	"learning_rate": 2.8915222523680082e-05,
	"loss": 1.117383360862732,
	"step": 666
	},
	{
	"epoch": 1.825136612021858,
	"grad_norm": 0.28003278374671936,
	"learning_rate": 2.9015119423213857e-05,
	"loss": 1.067117691040039,
	"step": 668
	},
	{
	"epoch": 1.830601092896175,
	"grad_norm": 0.5866938829421997,
	"learning_rate": 2.9110365683788173e-05,
	"loss": 1.0645062923431396,
	"step": 670
	},
	{
	"epoch": 1.8360655737704918,
	"grad_norm": 0.4505460262298584,
	"learning_rate": 2.9200925911735956e-05,
	"loss": 1.0651450157165527,
	"step": 672
	},
	{
	"epoch": 1.8415300546448088,
	"grad_norm": 1.2405760288238525,
	"learning_rate": 2.9286766454727563e-05,
	"loss": 0.7814494967460632,
	"step": 674
	},
	{
	"epoch": 1.8469945355191257,
	"grad_norm": 0.34474292397499084,
	"learning_rate": 2.9367855414276073e-05,
	"loss": 1.151155710220337,
	"step": 676
	},
	{
	"epoch": 1.8524590163934427,
	"grad_norm": 0.3130297064781189,
	"learning_rate": 2.9444162657590747e-05,
	"loss": 0.960390567779541,
	"step": 678
	},
	{
	"epoch": 1.8579234972677594,
	"grad_norm": 0.37524649500846863,
	"learning_rate": 2.951565982877447e-05,
	"loss": 1.011980414390564,
	"step": 680
	},
	{
	"epoch": 1.8633879781420766,
	"grad_norm": 0.2684651017189026,
	"learning_rate": 2.9582320359360864e-05,
	"loss": 1.1165417432785034,
	"step": 682
	},
	{
	"epoch": 1.8688524590163933,
	"grad_norm": 0.6099388003349304,
	"learning_rate": 2.9644119478187126e-05,
	"loss": 0.9011784195899963,
	"step": 684
	},
	{
	"epoch": 1.8743169398907105,
	"grad_norm": 0.7181943655014038,
	"learning_rate": 2.9701034220599074e-05,
	"loss": 0.7465716004371643,
	"step": 686
	},
	{
	"epoch": 1.8797814207650272,
	"grad_norm": 0.31953608989715576,
	"learning_rate": 2.975304343698483e-05,
	"loss": 1.0670995712280273,
	"step": 688
	},
	{
	"epoch": 1.8852459016393444,
	"grad_norm": 0.3640364110469818,
	"learning_rate": 2.980012780063404e-05,
	"loss": 0.8072540760040283,
	"step": 690
	},
	{
	"epoch": 1.890710382513661,
	"grad_norm": 0.4549046754837036,
	"learning_rate": 2.9842269814919755e-05,
	"loss": 1.0721323490142822,
	"step": 692
	},
	{
	"epoch": 1.8961748633879782,
	"grad_norm": 0.9052984714508057,
	"learning_rate": 2.9879453819800156e-05,
	"loss": 0.8395594358444214,
	"step": 694
	},
	{
	"epoch": 1.901639344262295,
	"grad_norm": 0.32689180970191956,
	"learning_rate": 2.991166599763788e-05,
	"loss": 1.0846257209777832,
	"step": 696
	},
	{
	"epoch": 1.9071038251366121,
	"grad_norm": 0.43174540996551514,
	"learning_rate": 2.993889437833466e-05,
	"loss": 1.4478161334991455,
	"step": 698
	},
	{
	"epoch": 1.9125683060109289,
	"grad_norm": 0.30801597237586975,
	"learning_rate": 2.9961128843779457e-05,
	"loss": 1.0946073532104492,
	"step": 700
	},
	{
	"epoch": 1.918032786885246,
	"grad_norm": 0.29532310366630554,
	"learning_rate": 2.9978361131608348e-05,
	"loss": 1.0470151901245117,
	"step": 702
	},
	{
	"epoch": 1.9234972677595628,
	"grad_norm": 0.6861543655395508,
	"learning_rate": 2.999058483827483e-05,
	"loss": 1.1541780233383179,
	"step": 704
	},
	{
	"epoch": 1.92896174863388,
	"grad_norm": 0.373347669839859,
	"learning_rate": 2.9997795421429404e-05,
	"loss": 1.1399716138839722,
	"step": 706
	},
	{
	"epoch": 1.9344262295081966,
	"grad_norm": 0.31508007645606995,
	"learning_rate": 2.9999990201607516e-05,
	"loss": 1.1029908657073975,
	"step": 708
	},
	{
	"epoch": 1.9398907103825138,
	"grad_norm": 1.0937162637710571,
	"learning_rate": 2.999716836322524e-05,
	"loss": 1.2128394842147827,
	"step": 710
	},
	{
	"epoch": 1.9453551912568305,
	"grad_norm": 0.24902676045894623,
	"learning_rate": 2.9989330954882366e-05,
	"loss": 1.050254464149475,
	"step": 712
	},
	{
	"epoch": 1.9508196721311475,
	"grad_norm": 0.8138014078140259,
	"learning_rate": 2.9976480888972708e-05,
	"loss": 0.9359830021858215,
	"step": 714
	},
	{
	"epoch": 1.9562841530054644,
	"grad_norm": 0.4428923726081848,
	"learning_rate": 2.9958622940601907e-05,
	"loss": 1.1571717262268066,
	"step": 716
	},
	{
	"epoch": 1.9617486338797814,
	"grad_norm": 0.4176506996154785,
	"learning_rate": 2.9935763745812935e-05,
	"loss": 0.7543359398841858,
	"step": 718
	},
	{
	"epoch": 1.9672131147540983,
	"grad_norm": 0.32763925194740295,
	"learning_rate": 2.990791179912017e-05,
	"loss": 0.7445685863494873,
	"step": 720
	},
	{
	"epoch": 1.9726775956284153,
	"grad_norm": 0.3950430154800415,
	"learning_rate": 2.9875077450352817e-05,
	"loss": 1.0080370903015137,
	"step": 722
	},
	{
	"epoch": 1.9781420765027322,
	"grad_norm": 0.41049596667289734,
	"learning_rate": 2.9837272900808863e-05,
	"loss": 1.0963528156280518,
	"step": 724
	},
	{
	"epoch": 1.9836065573770492,
	"grad_norm": 0.9898220300674438,
	"learning_rate": 2.9794512198721092e-05,
	"loss": 0.7285370230674744,
	"step": 726
	},
	{
	"epoch": 1.989071038251366,
	"grad_norm": 0.3645866811275482,
	"learning_rate": 2.9746811234036736e-05,
	"loss": 0.8588154315948486,
	"step": 728
	},
	{
	"epoch": 1.994535519125683,
	"grad_norm": 0.23531635105609894,
	"learning_rate": 2.9694187732512702e-05,
	"loss": 1.1264981031417847,
	"step": 730
	},
	{
	"epoch": 2.0,
	"grad_norm": 0.6136480569839478,
	"learning_rate": 2.96366612491287e-05,
	"loss": 1.1605597734451294,
	"step": 732
	},
	{
	"epoch": 2.0054644808743167,
	"grad_norm": 0.3638727068901062,
	"learning_rate": 2.9574253160820573e-05,
	"loss": 0.5738942623138428,
	"step": 734
	},
	{
	"epoch": 2.010928961748634,
	"grad_norm": 0.38032037019729614,
	"learning_rate": 2.9506986658536562e-05,
	"loss": 0.8583514094352722,
	"step": 736
	},
	{
	"epoch": 2.0163934426229506,
	"grad_norm": 0.3164927363395691,
	"learning_rate": 2.9434886738619537e-05,
	"loss": 0.914330005645752,
	"step": 738
	},
	{
	"epoch": 2.021857923497268,
	"grad_norm": 0.2615019977092743,
	"learning_rate": 2.9357980193518312e-05,
	"loss": 0.9653261303901672,
	"step": 740
	},
	{
	"epoch": 2.0273224043715845,
	"grad_norm": 0.35523325204849243,
	"learning_rate": 2.927629560183153e-05,
	"loss": 0.9499996304512024,
	"step": 742
	},
	{
	"epoch": 2.0327868852459017,
	"grad_norm": 0.9985663294792175,
	"learning_rate": 2.91898633176878e-05,
	"loss": 1.293304681777954,
	"step": 744
	},
	{
	"epoch": 2.0382513661202184,
	"grad_norm": 0.4231744706630707,
	"learning_rate": 2.909871545946603e-05,
	"loss": 1.3876979351043701,
	"step": 746
	},
	{
	"epoch": 2.0437158469945356,
	"grad_norm": 0.36017516255378723,
	"learning_rate": 2.9002885897860252e-05,
	"loss": 1.1023402214050293,
	"step": 748
	},
	{
	"epoch": 2.0491803278688523,
	"grad_norm": 0.36883434653282166,
	"learning_rate": 2.8902410243293152e-05,
	"loss": 0.982643187046051,
	"step": 750
	},
	{
	"epoch": 2.0546448087431695,
	"grad_norm": 1.1026638746261597,
	"learning_rate": 2.8797325832683208e-05,
	"loss": 0.9915405511856079,
	"step": 752
	},
	{
	"epoch": 2.060109289617486,
	"grad_norm": 0.7558255195617676,
	"learning_rate": 2.868767171557021e-05,
	"loss": 0.5983301997184753,
	"step": 754
	},
	{
	"epoch": 2.0655737704918034,
	"grad_norm": 0.2940157353878021,
	"learning_rate": 2.8573488639604418e-05,
	"loss": 0.18914969265460968,
	"step": 756
	},
	{
	"epoch": 2.07103825136612,
	"grad_norm": 0.40500950813293457,
	"learning_rate": 2.845481903540464e-05,
	"loss": 1.0764596462249756,
	"step": 758
	},
	{
	"epoch": 2.0765027322404372,
	"grad_norm": 0.2900254428386688,
	"learning_rate": 2.8331707000790954e-05,
	"loss": 0.6835562586784363,
	"step": 760
	},
	{
	"epoch": 2.081967213114754,
	"grad_norm": 0.3581569492816925,
	"learning_rate": 2.820419828439788e-05,
	"loss": 1.024125576019287,
	"step": 762
	},
	{
	"epoch": 2.087431693989071,
	"grad_norm": 0.6350530982017517,
	"learning_rate": 2.8072340268674133e-05,
	"loss": 0.8588637709617615,
	"step": 764
	},
	{
	"epoch": 2.092896174863388,
	"grad_norm": 0.29905757308006287,
	"learning_rate": 2.793618195227521e-05,
	"loss": 1.1255227327346802,
	"step": 766
	},
	{
	"epoch": 2.098360655737705,
	"grad_norm": 0.6376034021377563,
	"learning_rate": 2.779577393185539e-05,
	"loss": 0.96219402551651,
	"step": 768
	},
	{
	"epoch": 2.1038251366120218,
	"grad_norm": 0.4236537516117096,
	"learning_rate": 2.765116838326597e-05,
	"loss": 1.024062991142273,
	"step": 770
	},
	{
	"epoch": 2.109289617486339,
	"grad_norm": 0.41378986835479736,
	"learning_rate": 2.750241904216663e-05,
	"loss": 0.9890310168266296,
	"step": 772
	},
	{
	"epoch": 2.1147540983606556,
	"grad_norm": 0.2886035442352295,
	"learning_rate": 2.7349581184057144e-05,
	"loss": 0.8476873636245728,
	"step": 774
	},
	{
	"epoch": 2.120218579234973,
	"grad_norm": 0.9165263772010803,
	"learning_rate": 2.719271160373693e-05,
	"loss": 0.6358259320259094,
	"step": 776
	},
	{
	"epoch": 2.1256830601092895,
	"grad_norm": 0.30565494298934937,
	"learning_rate": 2.703186859420002e-05,
	"loss": 0.9424027800559998,
	"step": 778
	},
	{
	"epoch": 2.1311475409836067,
	"grad_norm": 1.7092857360839844,
	"learning_rate": 2.6867111924973283e-05,
	"loss": 0.5238833427429199,
	"step": 780
	},
	{
	"epoch": 2.1366120218579234,
	"grad_norm": 0.6912135481834412,
	"learning_rate": 2.6698502819905935e-05,
	"loss": 0.6626419425010681,
	"step": 782
	},
	{
	"epoch": 2.1420765027322406,
	"grad_norm": 1.169651746749878,
	"learning_rate": 2.652610393441872e-05,
	"loss": 0.84641432762146,
	"step": 784
	},
	{
	"epoch": 2.1475409836065573,
	"grad_norm": 0.7925103902816772,
	"learning_rate": 2.6349979332220992e-05,
	"loss": 0.6377699971199036,
	"step": 786
	},
	{
	"epoch": 2.1530054644808745,
	"grad_norm": 14.70950984954834,
	"learning_rate": 2.6170194461504586e-05,
	"loss": 0.6009026169776917,
	"step": 788
	},
	{
	"epoch": 2.158469945355191,
	"grad_norm": 0.3301484286785126,
	"learning_rate": 2.5986816130623133e-05,
	"loss": 1.100122094154358,
	"step": 790
	},
	{
	"epoch": 2.1639344262295084,
	"grad_norm": 0.37357431650161743,
	"learning_rate": 2.579991248326594e-05,
	"loss": 0.920696496963501,
	"step": 792
	},
	{
	"epoch": 2.169398907103825,
	"grad_norm": 0.392766535282135,
	"learning_rate": 2.560955297313575e-05,
	"loss": 0.8580578565597534,
	"step": 794
	},
	{
	"epoch": 2.1748633879781423,
	"grad_norm": 0.4077216386795044,
	"learning_rate": 2.5415808338139595e-05,
	"loss": 0.6196969747543335,
	"step": 796
	},
	{
	"epoch": 2.180327868852459,
	"grad_norm": 0.40729326009750366,
	"learning_rate": 2.5218750574102465e-05,
	"loss": 0.6308495402336121,
	"step": 798
	},
	{
	"epoch": 2.185792349726776,
	"grad_norm": 0.2669661343097687,
	"learning_rate": 2.5018452908013522e-05,
	"loss": 0.9696865081787109,
	"step": 800
	},
	{
	"epoch": 2.191256830601093,
	"grad_norm": 0.49087321758270264,
	"learning_rate": 2.48149897708149e-05,
	"loss": 1.0563379526138306,
	"step": 802
	},
	{
	"epoch": 2.19672131147541,
	"grad_norm": 0.3579554855823517,
	"learning_rate": 2.4608436769743e-05,
	"loss": 1.1717143058776855,
	"step": 804
	},
	{
	"epoch": 2.202185792349727,
	"grad_norm": 0.2751805782318115,
	"learning_rate": 2.4398870660232684e-05,
	"loss": 0.939961850643158,
	"step": 806
	},
	{
	"epoch": 2.2076502732240435,
	"grad_norm": 1.9989415407180786,
	"learning_rate": 2.418636931739491e-05,
	"loss": 0.8161137700080872,
	"step": 808
	},
	{
	"epoch": 2.2131147540983607,
	"grad_norm": 0.5127248764038086,
	"learning_rate": 2.3971011707078125e-05,
	"loss": 1.0133951902389526,
	"step": 810
	},
	{
	"epoch": 2.2185792349726774,
	"grad_norm": 1.0294671058654785,
	"learning_rate": 2.3752877856524532e-05,
	"loss": 0.9799056649208069,
	"step": 812
	},
	{
	"epoch": 2.2240437158469946,
	"grad_norm": 0.8723068833351135,
	"learning_rate": 2.353204882463168e-05,
	"loss": 0.5277108550071716,
	"step": 814
	},
	{
	"epoch": 2.2295081967213113,
	"grad_norm": 0.42140084505081177,
	"learning_rate": 2.330860667183101e-05,
	"loss": 0.7577545642852783,
	"step": 816
	},
	{
	"epoch": 2.2349726775956285,
	"grad_norm": 1.2116085290908813,
	"learning_rate": 2.308263442959396e-05,
	"loss": 0.7222480773925781,
	"step": 818
	},
	{
	"epoch": 2.240437158469945,
	"grad_norm": 0.4509221911430359,
	"learning_rate": 2.2854216069577376e-05,
	"loss": 1.012153148651123,
	"step": 820
	},
	{
	"epoch": 2.2459016393442623,
	"grad_norm": 0.5047132968902588,
	"learning_rate": 2.2623436472419476e-05,
	"loss": 1.0092438459396362,
	"step": 822
	},
	{
	"epoch": 2.251366120218579,
	"grad_norm": 0.4681483507156372,
	"learning_rate": 2.2390381396198102e-05,
	"loss": 0.8176283836364746,
	"step": 824
	},
	{
	"epoch": 2.2568306010928962,
	"grad_norm": 0.9395934343338013,
	"learning_rate": 2.2155137444562842e-05,
	"loss": 0.8658889532089233,
	"step": 826
	},
	{
	"epoch": 2.262295081967213,
	"grad_norm": 0.8730800747871399,
	"learning_rate": 2.191779203455302e-05,
	"loss": 0.43443816900253296,
	"step": 828
	},
	{
	"epoch": 2.26775956284153,
	"grad_norm": 0.3437061607837677,
	"learning_rate": 2.1678433364113297e-05,
	"loss": 0.7622541189193726,
	"step": 830
	},
	{
	"epoch": 2.273224043715847,
	"grad_norm": 0.4882737696170807,
	"learning_rate": 2.1437150379319245e-05,
	"loss": 0.7550147771835327,
	"step": 832
	},
	{
	"epoch": 2.278688524590164,
	"grad_norm": 0.5824230313301086,
	"learning_rate": 2.1194032741324823e-05,
	"loss": 0.7233867645263672,
	"step": 834
	},
	{
	"epoch": 2.2841530054644807,
	"grad_norm": 0.455255925655365,
	"learning_rate": 2.0949170793044142e-05,
	"loss": 1.0538800954818726,
	"step": 836
	},
	{
	"epoch": 2.289617486338798,
	"grad_norm": 0.33487194776535034,
	"learning_rate": 2.070265552557985e-05,
	"loss": 0.9521304368972778,
	"step": 838
	},
	{
	"epoch": 2.2950819672131146,
	"grad_norm": 0.5424416661262512,
	"learning_rate": 2.0454578544410758e-05,
	"loss": 0.5176016092300415,
	"step": 840
	},
	{
	"epoch": 2.300546448087432,
	"grad_norm": 0.44442370533943176,
	"learning_rate": 2.0205032035351043e-05,
	"loss": 0.6318649649620056,
	"step": 842
	},
	{
	"epoch": 2.3060109289617485,
	"grad_norm": 0.17473050951957703,
	"learning_rate": 1.9954108730293875e-05,
	"loss": 0.5930679440498352,
	"step": 844
	},
	{
	"epoch": 2.3114754098360657,
	"grad_norm": 0.30008724331855774,
	"learning_rate": 1.9701901872752047e-05,
	"loss": 1.1380505561828613,
	"step": 846
	},
	{
	"epoch": 2.3169398907103824,
	"grad_norm": 0.3241089880466461,
	"learning_rate": 1.9448505183208607e-05,
	"loss": 1.0619306564331055,
	"step": 848
	},
	{
	"epoch": 2.3224043715846996,
	"grad_norm": 0.40371695160865784,
	"learning_rate": 1.919401282429013e-05,
	"loss": 0.9061838388442993,
	"step": 850
	},
	{
	"epoch": 2.3278688524590163,
	"grad_norm": 0.2833711504936218,
	"learning_rate": 1.893851936577567e-05,
	"loss": 0.9225311279296875,
	"step": 852
	},
	{
	"epoch": 2.3333333333333335,
	"grad_norm": 0.3210262060165405,
	"learning_rate": 1.868211974945461e-05,
	"loss": 0.7068516612052917,
	"step": 854
	},
	{
	"epoch": 2.33879781420765,
	"grad_norm": 0.2600228190422058,
	"learning_rate": 1.842490925384604e-05,
	"loss": 0.6802095174789429,
	"step": 856
	},
	{
	"epoch": 2.3442622950819674,
	"grad_norm": 0.3579116463661194,
	"learning_rate": 1.816698345879313e-05,
	"loss": 0.8223679065704346,
	"step": 858
	},
	{
	"epoch": 2.349726775956284,
	"grad_norm": 0.2626917064189911,
	"learning_rate": 1.790843820994548e-05,
	"loss": 0.6397656202316284,
	"step": 860
	},
	{
	"epoch": 2.3551912568306013,
	"grad_norm": 0.8502326011657715,
	"learning_rate": 1.7649369583142763e-05,
	"loss": 0.9318816065788269,
	"step": 862
	},
	{
	"epoch": 2.360655737704918,
	"grad_norm": 0.34465688467025757,
	"learning_rate": 1.738987384871274e-05,
	"loss": 0.8776544332504272,
	"step": 864
	},
	{
	"epoch": 2.366120218579235,
	"grad_norm": 0.35162287950515747,
	"learning_rate": 1.7130047435697118e-05,
	"loss": 0.6873989105224609,
	"step": 866
	},
	{
	"epoch": 2.371584699453552,
	"grad_norm": 2.411452054977417,
	"learning_rate": 1.6869986896018226e-05,
	"loss": 1.1587547063827515,
	"step": 868
	},
	{
	"epoch": 2.3770491803278686,
	"grad_norm": 0.40320128202438354,
	"learning_rate": 1.66097888686003e-05,
	"loss": 0.7416959404945374,
	"step": 870
	},
	{
	"epoch": 2.3825136612021858,
	"grad_norm": 0.7894490361213684,
	"learning_rate": 1.6349550043458252e-05,
	"loss": 0.5259535312652588,
	"step": 872
	},
	{
	"epoch": 2.387978142076503,
	"grad_norm": 0.5915789604187012,
	"learning_rate": 1.608936712576749e-05,
	"loss": 1.008756160736084,
	"step": 874
	},
	{
	"epoch": 2.3934426229508197,
	"grad_norm": 0.28783875703811646,
	"learning_rate": 1.582933679992809e-05,
	"loss": 0.7991337180137634,
	"step": 876
	},
	{
	"epoch": 2.3989071038251364,
	"grad_norm": 2.9894583225250244,
	"learning_rate": 1.556955569363678e-05,
	"loss": 0.49375149607658386,
	"step": 878
	},
	{
	"epoch": 2.4043715846994536,
	"grad_norm": 0.4313114285469055,
	"learning_rate": 1.531012034197988e-05,
	"loss": 1.1030757427215576,
	"step": 880
	},
	{
	"epoch": 2.4098360655737707,
	"grad_norm": 0.4268873631954193,
	"learning_rate": 1.5051127151560745e-05,
	"loss": 0.7422546148300171,
	"step": 882
	},
	{
	"epoch": 2.4153005464480874,
	"grad_norm": 0.4147166609764099,
	"learning_rate": 1.4792672364674816e-05,
	"loss": 0.7103762030601501,
	"step": 884
	},
	{
	"epoch": 2.420765027322404,
	"grad_norm": 0.7336945533752441,
	"learning_rate": 1.4534852023545968e-05,
	"loss": 0.8475983142852783,
	"step": 886
	},
	{
	"epoch": 2.4262295081967213,
	"grad_norm": 0.6543511748313904,
	"learning_rate": 1.4277761934636963e-05,
	"loss": 0.968014121055603,
	"step": 888
	},
	{
	"epoch": 2.431693989071038,
	"grad_norm": 0.49377578496932983,
	"learning_rate": 1.4021497633047664e-05,
	"loss": 0.6535788774490356,
	"step": 890
	},
	{
	"epoch": 2.4371584699453552,
	"grad_norm": 0.8991974592208862,
	"learning_rate": 1.3766154347013933e-05,
	"loss": 1.167250156402588,
	"step": 892
	},
	{
	"epoch": 2.442622950819672,
	"grad_norm": 0.5998942255973816,
	"learning_rate": 1.3511826962520809e-05,
	"loss": 0.7989946603775024,
	"step": 894
	},
	{
	"epoch": 2.448087431693989,
	"grad_norm": 0.25032103061676025,
	"learning_rate": 1.3258609988042627e-05,
	"loss": 0.4925026595592499,
	"step": 896
	},
	{
	"epoch": 2.453551912568306,
	"grad_norm": 0.3441256582736969,
	"learning_rate": 1.300659751942353e-05,
	"loss": 0.22913937270641327,
	"step": 898
	},
	{
	"epoch": 2.459016393442623,
	"grad_norm": 0.4925740659236908,
	"learning_rate": 1.2755883204911305e-05,
	"loss": 0.9754618406295776,
	"step": 900
	},
	{
	"epoch": 2.4644808743169397,
	"grad_norm": 0.3265496492385864,
	"learning_rate": 1.2506560210357541e-05,
	"loss": 0.47504350543022156,
	"step": 902
	},
	{
	"epoch": 2.469945355191257,
	"grad_norm": 0.30063438415527344,
	"learning_rate": 1.225872118459706e-05,
	"loss": 0.994674026966095,
	"step": 904
	},
	{
	"epoch": 2.4754098360655736,
	"grad_norm": 3.1096532344818115,
	"learning_rate": 1.2012458225019375e-05,
	"loss": 0.41736599802970886,
	"step": 906
	},
	{
	"epoch": 2.480874316939891,
	"grad_norm": 2.740457773208618,
	"learning_rate": 1.176786284334528e-05,
	"loss": 0.6344496011734009,
	"step": 908
	},
	{
	"epoch": 2.4863387978142075,
	"grad_norm": 0.3145305812358856,
	"learning_rate": 1.1525025931620855e-05,
	"loss": 0.9095264077186584,
	"step": 910
	},
	{
	"epoch": 2.4918032786885247,
	"grad_norm": 1.253567099571228,
	"learning_rate": 1.1284037728441877e-05,
	"loss": 0.5218656659126282,
	"step": 912
	},
	{
	"epoch": 2.4972677595628414,
	"grad_norm": 0.4414713382720947,
	"learning_rate": 1.1044987785420924e-05,
	"loss": 0.9621478319168091,
	"step": 914
	},
	{
	"epoch": 2.5027322404371586,
	"grad_norm": 0.2708357572555542,
	"learning_rate": 1.0807964933909975e-05,
	"loss": 1.0340259075164795,
	"step": 916
	},
	{
	"epoch": 2.5081967213114753,
	"grad_norm": 0.5265946388244629,
	"learning_rate": 1.0573057251990443e-05,
	"loss": 0.944985568523407,
	"step": 918
	},
	{
	"epoch": 2.5136612021857925,
	"grad_norm": 0.2796134948730469,
	"learning_rate": 1.0340352031743256e-05,
	"loss": 0.7973819375038147,
	"step": 920
	},
	{
	"epoch": 2.519125683060109,
	"grad_norm": 0.297129362821579,
	"learning_rate": 1.010993574681095e-05,
	"loss": 0.8349511027336121,
	"step": 922
	},
	{
	"epoch": 2.5245901639344264,
	"grad_norm": 0.8182933330535889,
	"learning_rate": 9.881894020263938e-06,
	"loss": 0.3968673050403595,
	"step": 924
	},
	{
	"epoch": 2.530054644808743,
	"grad_norm": 0.2900335192680359,
	"learning_rate": 9.656311592782831e-06,
	"loss": 0.9522480368614197,
	"step": 926
	},
	{
	"epoch": 2.5355191256830603,
	"grad_norm": 0.7127178311347961,
	"learning_rate": 9.433272291168689e-06,
	"loss": 0.9828237295150757,
	"step": 928
	},
	{
	"epoch": 2.540983606557377,
	"grad_norm": 0.6727446913719177,
	"learning_rate": 9.212858997192744e-06,
	"loss": 0.7021880149841309,
	"step": 930
	},
	{
	"epoch": 2.546448087431694,
	"grad_norm": 0.575061559677124,
	"learning_rate": 8.995153616797544e-06,
	"loss": 0.53633713722229,
	"step": 932
	},
	{
	"epoch": 2.551912568306011,
	"grad_norm": 0.6114161014556885,
	"learning_rate": 8.78023704966047e-06,
	"loss": 0.8347498178482056,
	"step": 934
	},
	{
	"epoch": 2.557377049180328,
	"grad_norm": 0.3482673168182373,
	"learning_rate": 8.568189159131336e-06,
	"loss": 0.8326533436775208,
	"step": 936
	},
	{
	"epoch": 2.5628415300546448,
	"grad_norm": 0.4061831533908844,
	"learning_rate": 8.359088742554941e-06,
	"loss": 0.9324700236320496,
	"step": 938
	},
	{
	"epoch": 2.5683060109289615,
	"grad_norm": 0.2786436676979065,
	"learning_rate": 8.15301350198999e-06,
	"loss": 0.8789687752723694,
	"step": 940
	},
	{
	"epoch": 2.5737704918032787,
	"grad_norm": 0.29912883043289185,
	"learning_rate": 7.950040015334789e-06,
	"loss": 0.8741180896759033,
	"step": 942
	},
	{
	"epoch": 2.579234972677596,
	"grad_norm": 0.23834018409252167,
	"learning_rate": 7.750243707870748e-06,
	"loss": 1.01088285446167,
	"step": 944
	},
	{
	"epoch": 2.5846994535519126,
	"grad_norm": 0.7520560026168823,
	"learning_rate": 7.553698824234314e-06,
	"loss": 0.9131101965904236,
	"step": 946
	},
	{
	"epoch": 2.5901639344262293,
	"grad_norm": 0.3973008096218109,
	"learning_rate": 7.360478400827475e-06,
	"loss": 0.6671414971351624,
	"step": 948
	},
	{
	"epoch": 2.5956284153005464,
	"grad_norm": 1.165856957435608,
	"learning_rate": 7.170654238677331e-06,
	"loss": 0.8358378410339355,
	"step": 950
	},
	{
	"epoch": 2.6010928961748636,
	"grad_norm": 0.6425595879554749,
	"learning_rate": 6.984296876754711e-06,
	"loss": 0.876006007194519,
	"step": 952
	},
	{
	"epoch": 2.6065573770491803,
	"grad_norm": 0.2834312319755554,
	"learning_rate": 6.801475565761783e-06,
	"loss": 0.8852624297142029,
	"step": 954
	},
	{
	"epoch": 2.612021857923497,
	"grad_norm": 0.26827678084373474,
	"learning_rate": 6.622258242398371e-06,
	"loss": 0.49164018034935,
	"step": 956
	},
	{
	"epoch": 2.6174863387978142,
	"grad_norm": 0.3386532962322235,
	"learning_rate": 6.4467115041165855e-06,
	"loss": 0.7272903919219971,
	"step": 958
	},
	{
	"epoch": 2.6229508196721314,
	"grad_norm": 0.2805633544921875,
	"learning_rate": 6.2749005843730336e-06,
	"loss": 0.7272099852561951,
	"step": 960
	},
	{
	"epoch": 2.628415300546448,
	"grad_norm": 0.27282318472862244,
	"learning_rate": 6.106889328388064e-06,
	"loss": 1.0292612314224243,
	"step": 962
	},
	{
	"epoch": 2.633879781420765,
	"grad_norm": 0.302123486995697,
	"learning_rate": 5.942740169420701e-06,
	"loss": 0.9444547891616821,
	"step": 964
	},
	{
	"epoch": 2.639344262295082,
	"grad_norm": 0.37525907158851624,
	"learning_rate": 5.7825141055683895e-06,
	"loss": 0.7231637239456177,
	"step": 966
	},
	{
	"epoch": 2.644808743169399,
	"grad_norm": 0.26892736554145813,
	"learning_rate": 5.62627067709992e-06,
	"loss": 0.9579343795776367,
	"step": 968
	},
	{
	"epoch": 2.650273224043716,
	"grad_norm": 0.3834379017353058,
	"learning_rate": 5.474067944330285e-06,
	"loss": 1.0427404642105103,
	"step": 970
	},
	{
	"epoch": 2.6557377049180326,
	"grad_norm": 0.576501727104187,
	"learning_rate": 5.325962466045282e-06,
	"loss": 1.0664690732955933,
	"step": 972
	},
	{
	"epoch": 2.66120218579235,
	"grad_norm": 0.32818320393562317,
	"learning_rate": 5.18200927848421e-06,
	"loss": 0.9675801992416382,
	"step": 974
	},
	{
	"epoch": 2.6666666666666665,
	"grad_norm": 0.4426153004169464,
	"learning_rate": 5.042261874888308e-06,
	"loss": 0.8803547024726868,
	"step": 976
	},
	{
	"epoch": 2.6721311475409837,
	"grad_norm": 0.6687554717063904,
	"learning_rate": 4.906772185622572e-06,
	"loss": 0.4762001633644104,
	"step": 978
	},
	{
	"epoch": 2.6775956284153004,
	"grad_norm": 0.25917065143585205,
	"learning_rate": 4.775590558878368e-06,
	"loss": 0.8584491014480591,
	"step": 980
	},
	{
	"epoch": 2.6830601092896176,
	"grad_norm": 0.8609603643417358,
	"learning_rate": 4.648765741963903e-06,
	"loss": 1.0697994232177734,
	"step": 982
	},
	{
	"epoch": 2.6885245901639343,
	"grad_norm": 0.26177000999450684,
	"learning_rate": 4.526344863189724e-06,
	"loss": 1.0349247455596924,
	"step": 984
	},
	{
	"epoch": 2.6939890710382515,
	"grad_norm": 0.6148212552070618,
	"learning_rate": 4.408373414355714e-06,
	"loss": 1.1050891876220703,
	"step": 986
	},
	{
	"epoch": 2.699453551912568,
	"grad_norm": 0.3300875425338745,
	"learning_rate": 4.29489523384628e-06,
	"loss": 0.9843365550041199,
	"step": 988
	},
	{
	"epoch": 2.7049180327868854,
	"grad_norm": 0.3000809848308563,
	"learning_rate": 4.185952490339899e-06,
	"loss": 0.8345898985862732,
	"step": 990
	},
	{
	"epoch": 2.710382513661202,
	"grad_norm": 0.45524969696998596,
	"learning_rate": 4.081585667139231e-06,
	"loss": 0.8222418427467346,
	"step": 992
	},
	{
	"epoch": 2.7158469945355193,
	"grad_norm": 0.5290429592132568,
	"learning_rate": 3.981833547127413e-06,
	"loss": 0.8905819058418274,
	"step": 994
	},
	{
	"epoch": 2.721311475409836,
	"grad_norm": 0.9160144925117493,
	"learning_rate": 3.886733198356298e-06,
	"loss": 0.8706901669502258,
	"step": 996
	},
	{
	"epoch": 2.726775956284153,
	"grad_norm": 0.24170571565628052,
	"learning_rate": 3.7963199602718717e-06,
	"loss": 0.829027533531189,
	"step": 998
	},
	{
	"epoch": 2.73224043715847,
	"grad_norm": 0.28936469554901123,
	"learning_rate": 3.7106274305821034e-06,
	"loss": 0.9818518161773682,
	"step": 1000
	},
	{
	"epoch": 2.737704918032787,
	"grad_norm": 1.1057279109954834,
	"learning_rate": 3.6296874527719515e-06,
	"loss": 0.8876405954360962,
	"step": 1002
	},
	{
	"epoch": 2.7431693989071038,
	"grad_norm": 0.22955042123794556,
	"learning_rate": 3.553530104270281e-06,
	"loss": 0.5577114820480347,
	"step": 1004
	},
	{
	"epoch": 2.748633879781421,
	"grad_norm": 0.7059992551803589,
	"learning_rate": 3.4821836852730384e-06,
	"loss": 0.8629549741744995,
	"step": 1006
	},
	{
	"epoch": 2.7540983606557377,
	"grad_norm": 0.41986677050590515,
	"learning_rate": 3.41567470822686e-06,
	"loss": 1.2205630540847778,
	"step": 1008
	},
	{
	"epoch": 2.7595628415300544,
	"grad_norm": 0.3675086796283722,
	"learning_rate": 3.354027887976989e-06,
	"loss": 0.6176258325576782,
	"step": 1010
	},
	{
	"epoch": 2.7650273224043715,
	"grad_norm": 0.3218194842338562,
	"learning_rate": 3.297266132583221e-06,
	"loss": 0.9429301023483276,
	"step": 1012
	},
	{
	"epoch": 2.7704918032786887,
	"grad_norm": 6.591115951538086,
	"learning_rate": 3.245410534807195e-06,
	"loss": 0.8208173513412476,
	"step": 1014
	},
	{
	"epoch": 2.7759562841530054,
	"grad_norm": 0.31964442133903503,
	"learning_rate": 3.1984803642743314e-06,
	"loss": 0.6169829368591309,
	"step": 1016
	},
	{
	"epoch": 2.781420765027322,
	"grad_norm": 1.38068425655365,
	"learning_rate": 3.1564930603131777e-06,
	"loss": 0.4389287531375885,
	"step": 1018
	},
	{
	"epoch": 2.7868852459016393,
	"grad_norm": 0.2846753001213074,
	"learning_rate": 3.1194642254749395e-06,
	"loss": 0.9181113243103027,
	"step": 1020
	},
	{
	"epoch": 2.7923497267759565,
	"grad_norm": 0.31778064370155334,
	"learning_rate": 3.0874076197355317e-06,
	"loss": 0.9030160903930664,
	"step": 1022
	},
	{
	"epoch": 2.797814207650273,
	"grad_norm": 0.442088782787323,
	"learning_rate": 3.0603351553823717e-06,
	"loss": 0.807093620300293,
	"step": 1024
	},
	{
	"epoch": 2.80327868852459,
	"grad_norm": 0.3773954510688782,
	"learning_rate": 3.038256892587734e-06,
	"loss": 0.8687778115272522,
	"step": 1026
	},
	{
	"epoch": 2.808743169398907,
	"grad_norm": 0.3855181336402893,
	"learning_rate": 3.0211810356703803e-06,
	"loss": 1.0619217157363892,
	"step": 1028
	},
	{
	"epoch": 2.8142076502732243,
	"grad_norm": 0.2924480736255646,
	"learning_rate": 3.0091139300468266e-06,
	"loss": 0.7161194086074829,
	"step": 1030
	},
	{
	"epoch": 2.819672131147541,
	"grad_norm": 0.2923072278499603,
	"learning_rate": 3.0020600598733656e-06,
	"loss": 0.725647509098053,
	"step": 1032
	},
	{
	"epoch": 2.8251366120218577,
	"grad_norm": 0.36642518639564514,
	"learning_rate": 3.000022046379753e-06,
	"loss": 1.2020186185836792,
	"step": 1034
	},
	{
	"epoch": 2.830601092896175,
	"grad_norm": 0.7068674564361572,
	"learning_rate": 3.0030006468951557e-06,
	"loss": 1.0905146598815918,
	"step": 1036
	},
	{
	"epoch": 2.836065573770492,
	"grad_norm": 0.3369429409503937,
	"learning_rate": 3.0109947545667246e-06,
	"loss": 0.25182783603668213,
	"step": 1038
	},
	{
	"epoch": 2.841530054644809,
	"grad_norm": 0.3530783951282501,
	"learning_rate": 3.024001398770901e-06,
	"loss": 1.0270302295684814,
	"step": 1040
	},
	{
	"epoch": 2.8469945355191255,
	"grad_norm": 0.32281166315078735,
	"learning_rate": 3.042015746217308e-06,
	"loss": 0.9714375138282776,
	"step": 1042
	},
	{
	"epoch": 2.8524590163934427,
	"grad_norm": 0.5103802680969238,
	"learning_rate": 3.0650311027448116e-06,
	"loss": 0.9001659154891968,
	"step": 1044
	},
	{
	"epoch": 2.8579234972677594,
	"grad_norm": 0.39303264021873474,
	"learning_rate": 3.0930389158090754e-06,
	"loss": 1.1310542821884155,
	"step": 1046
	},
	{
	"epoch": 2.8633879781420766,
	"grad_norm": 0.30728888511657715,
	"learning_rate": 3.1260287776607025e-06,
	"loss": 0.9291237592697144,
	"step": 1048
	},
	{
	"epoch": 2.8688524590163933,
	"grad_norm": 0.9881218075752258,
	"learning_rate": 3.163988429212773e-06,
	"loss": 0.9141870141029358,
	"step": 1050
	},
	{
	"epoch": 2.8743169398907105,
	"grad_norm": 0.21143440902233124,
	"learning_rate": 3.206903764596349e-06,
	"loss": 0.49286749958992004,
	"step": 1052
	},
	{
	"epoch": 2.879781420765027,
	"grad_norm": 0.32137101888656616,
	"learning_rate": 3.254758836402225e-06,
	"loss": 1.0972161293029785,
	"step": 1054
	},
	{
	"epoch": 2.8852459016393444,
	"grad_norm": 0.33947762846946716,
	"learning_rate": 3.3075358616070144e-06,
	"loss": 0.9067559242248535,
	"step": 1056
	},
	{
	"epoch": 2.890710382513661,
	"grad_norm": 0.32341116666793823,
	"learning_rate": 3.365215228181358e-06,
	"loss": 0.7935602068901062,
	"step": 1058
	},
	{
	"epoch": 2.8961748633879782,
	"grad_norm": 0.3355255424976349,
	"learning_rate": 3.4277755023777795e-06,
	"loss": 0.9974086880683899,
	"step": 1060
	},
	{
	"epoch": 2.901639344262295,
	"grad_norm": 0.27966246008872986,
	"learning_rate": 3.495193436695504e-06,
	"loss": 0.6481755375862122,
	"step": 1062
	},
	{
	"epoch": 2.907103825136612,
	"grad_norm": 1.3332988023757935,
	"learning_rate": 3.567443978519267e-06,
	"loss": 0.4348956346511841,
	"step": 1064
	},
	{
	"epoch": 2.912568306010929,
	"grad_norm": 0.3482104539871216,
	"learning_rate": 3.6445002794288992e-06,
	"loss": 0.7822635173797607,
	"step": 1066
	},
	{
	"epoch": 2.918032786885246,
	"grad_norm": 0.3401924669742584,
	"learning_rate": 3.7263337051762718e-06,
	"loss": 0.6737417578697205,
	"step": 1068
	},
	{
	"epoch": 2.9234972677595628,
	"grad_norm": 0.2622358798980713,
	"learning_rate": 3.8129138463257943e-06,
	"loss": 0.818148136138916,
	"step": 1070
	},
	{
	"epoch": 2.92896174863388,
	"grad_norm": 0.5667299628257751,
	"learning_rate": 3.904208529554625e-06,
	"loss": 0.9563145637512207,
	"step": 1072
	},
	{
	"epoch": 2.9344262295081966,
	"grad_norm": 1.3791451454162598,
	"learning_rate": 4.000183829608332e-06,
	"loss": 1.3551911115646362,
	"step": 1074
	},
	{
	"epoch": 2.939890710382514,
	"grad_norm": 0.43662652373313904,
	"learning_rate": 4.100804081907595e-06,
	"loss": 0.38690492510795593,
	"step": 1076
	},
	{
	"epoch": 2.9453551912568305,
	"grad_norm": 0.31867608428001404,
	"learning_rate": 4.206031895801176e-06,
	"loss": 0.9536612033843994,
	"step": 1078
	},
	{
	"epoch": 2.9508196721311473,
	"grad_norm": 0.5429739356040955,
	"learning_rate": 4.315828168460367e-06,
	"loss": 0.5728800296783447,
	"step": 1080
	},
	{
	"epoch": 2.9562841530054644,
	"grad_norm": 0.21107900142669678,
	"learning_rate": 4.430152099409704e-06,
	"loss": 0.1516314148902893,
	"step": 1082
	},
	{
	"epoch": 2.9617486338797816,
	"grad_norm": 0.22951926290988922,
	"learning_rate": 4.548961205688424e-06,
	"loss": 1.0313093662261963,
	"step": 1084
	},
	{
	"epoch": 2.9672131147540983,
	"grad_norm": 0.28624290227890015,
	"learning_rate": 4.672211337637246e-06,
	"loss": 0.69117271900177,
	"step": 1086
	},
	{
	"epoch": 2.972677595628415,
	"grad_norm": 0.5194671154022217,
	"learning_rate": 4.7998566953044445e-06,
	"loss": 0.8698742389678955,
	"step": 1088
	},
	{
	"epoch": 2.978142076502732,
	"grad_norm": 0.413565993309021,
	"learning_rate": 4.931849845465193e-06,
	"loss": 1.0937373638153076,
	"step": 1090
	},
	{
	"epoch": 2.9836065573770494,
	"grad_norm": 0.9167707562446594,
	"learning_rate": 5.06814173924782e-06,
	"loss": 1.0198386907577515,
	"step": 1092
	},
	{
	"epoch": 2.989071038251366,
	"grad_norm": 0.9425981044769287,
	"learning_rate": 5.208681730360458e-06,
	"loss": 0.5489972233772278,
	"step": 1094
	},
	{
	"epoch": 2.994535519125683,
	"grad_norm": 0.38925519585609436,
	"learning_rate": 5.3534175939112694e-06,
	"loss": 0.9535996913909912,
	"step": 1096
	},
	{
	"epoch": 3.0,
	"grad_norm": 0.33070504665374756,
	"learning_rate": 5.50229554581536e-06,
	"loss": 0.64783775806427,
	"step": 1098
	},
	{
	"epoch": 3.0,
	"step": 1098,
	"total_flos": 4.929269661905715e+18,
	"train_loss": 1.00607624289008,
	"train_runtime": 12927.7338,
	"train_samples_per_second": 5.096,
	"train_steps_per_second": 0.085
	}
	],
	"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": 4.929269661905715e+18,
	"train_batch_size": 3,
	"trial_name": null,
	"trial_params": null
	}