Instructions to use furproxy/9b-59 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use furproxy/9b-59 with Transformers:

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

pipe = pipeline("image-text-to-text", model="furproxy/9b-59")
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-59")
model = AutoModelForImageTextToText.from_pretrained("furproxy/9b-59")
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-59 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "furproxy/9b-59"
# 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-59",
		"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-59

SGLang

How to use furproxy/9b-59 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-59" \
    --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-59",
		"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-59" \
        --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-59",
		"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-59 with Docker Model Runner:
```
docker model run hf.co/furproxy/9b-59
```

9b-59 / trainer_state.json

furproxy

Upload folder using huggingface_hub

11d8a0d 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": 1.573991060256958,
	"learning_rate": 4.545454545454545e-07,
	"loss": 2.660639762878418,
	"step": 2
	},
	{
	"epoch": 0.01092896174863388,
	"grad_norm": 0.6165518760681152,
	"learning_rate": 1.3636363636363636e-06,
	"loss": 1.9370158910751343,
	"step": 4
	},
	{
	"epoch": 0.01639344262295082,
	"grad_norm": 0.5032806992530823,
	"learning_rate": 2.2727272727272728e-06,
	"loss": 1.883617877960205,
	"step": 6
	},
	{
	"epoch": 0.02185792349726776,
	"grad_norm": 0.5399006605148315,
	"learning_rate": 3.1818181818181817e-06,
	"loss": 1.7472549676895142,
	"step": 8
	},
	{
	"epoch": 0.0273224043715847,
	"grad_norm": 0.4401944577693939,
	"learning_rate": 4.0909090909090915e-06,
	"loss": 1.7204209566116333,
	"step": 10
	},
	{
	"epoch": 0.03278688524590164,
	"grad_norm": 0.4825930595397949,
	"learning_rate": 5e-06,
	"loss": 1.56802499294281,
	"step": 12
	},
	{
	"epoch": 0.03825136612021858,
	"grad_norm": 0.3861444294452667,
	"learning_rate": 5.909090909090909e-06,
	"loss": 1.478776216506958,
	"step": 14
	},
	{
	"epoch": 0.04371584699453552,
	"grad_norm": 0.29860642552375793,
	"learning_rate": 6.818181818181818e-06,
	"loss": 1.215264916419983,
	"step": 16
	},
	{
	"epoch": 0.04918032786885246,
	"grad_norm": 0.3623839318752289,
	"learning_rate": 7.727272727272727e-06,
	"loss": 1.1711786985397339,
	"step": 18
	},
	{
	"epoch": 0.0546448087431694,
	"grad_norm": 0.3934680223464966,
	"learning_rate": 8.636363636363637e-06,
	"loss": 1.4052964448928833,
	"step": 20
	},
	{
	"epoch": 0.060109289617486336,
	"grad_norm": 0.3248288929462433,
	"learning_rate": 9.545454545454547e-06,
	"loss": 1.337301254272461,
	"step": 22
	},
	{
	"epoch": 0.06557377049180328,
	"grad_norm": 0.41455528140068054,
	"learning_rate": 1.0454545454545455e-05,
	"loss": 1.4091546535491943,
	"step": 24
	},
	{
	"epoch": 0.07103825136612021,
	"grad_norm": 0.7718392610549927,
	"learning_rate": 1.1363636363636365e-05,
	"loss": 1.608378529548645,
	"step": 26
	},
	{
	"epoch": 0.07650273224043716,
	"grad_norm": 0.3031645715236664,
	"learning_rate": 1.2272727272727273e-05,
	"loss": 1.3645198345184326,
	"step": 28
	},
	{
	"epoch": 0.08196721311475409,
	"grad_norm": 0.3317704200744629,
	"learning_rate": 1.318181818181818e-05,
	"loss": 1.2910865545272827,
	"step": 30
	},
	{
	"epoch": 0.08743169398907104,
	"grad_norm": 0.3077561855316162,
	"learning_rate": 1.409090909090909e-05,
	"loss": 1.2850395441055298,
	"step": 32
	},
	{
	"epoch": 0.09289617486338798,
	"grad_norm": 0.6236030459403992,
	"learning_rate": 1.5e-05,
	"loss": 1.011098861694336,
	"step": 34
	},
	{
	"epoch": 0.09836065573770492,
	"grad_norm": 0.3117682635784149,
	"learning_rate": 1.590909090909091e-05,
	"loss": 1.1125837564468384,
	"step": 36
	},
	{
	"epoch": 0.10382513661202186,
	"grad_norm": 0.3884047269821167,
	"learning_rate": 1.6818181818181818e-05,
	"loss": 1.3625156879425049,
	"step": 38
	},
	{
	"epoch": 0.1092896174863388,
	"grad_norm": 0.21100102365016937,
	"learning_rate": 1.772727272727273e-05,
	"loss": 1.3091150522232056,
	"step": 40
	},
	{
	"epoch": 0.11475409836065574,
	"grad_norm": 0.7283101677894592,
	"learning_rate": 1.8636363636363638e-05,
	"loss": 0.9641504883766174,
	"step": 42
	},
	{
	"epoch": 0.12021857923497267,
	"grad_norm": 0.27201205492019653,
	"learning_rate": 1.9545454545454546e-05,
	"loss": 0.8841361403465271,
	"step": 44
	},
	{
	"epoch": 0.12568306010928962,
	"grad_norm": 0.2947981059551239,
	"learning_rate": 2.0454545454545457e-05,
	"loss": 1.3351988792419434,
	"step": 46
	},
	{
	"epoch": 0.13114754098360656,
	"grad_norm": 0.25678518414497375,
	"learning_rate": 2.1363636363636362e-05,
	"loss": 1.305159568786621,
	"step": 48
	},
	{
	"epoch": 0.1366120218579235,
	"grad_norm": 0.3346308767795563,
	"learning_rate": 2.2272727272727274e-05,
	"loss": 1.2757641077041626,
	"step": 50
	},
	{
	"epoch": 0.14207650273224043,
	"grad_norm": 0.39588257670402527,
	"learning_rate": 2.318181818181818e-05,
	"loss": 1.2430144548416138,
	"step": 52
	},
	{
	"epoch": 0.14754098360655737,
	"grad_norm": 1.0091103315353394,
	"learning_rate": 2.4090909090909093e-05,
	"loss": 0.886474609375,
	"step": 54
	},
	{
	"epoch": 0.15300546448087432,
	"grad_norm": 0.38303902745246887,
	"learning_rate": 2.5e-05,
	"loss": 1.45668363571167,
	"step": 56
	},
	{
	"epoch": 0.15846994535519127,
	"grad_norm": 0.5787215828895569,
	"learning_rate": 2.4999795867415925e-05,
	"loss": 1.4211903810501099,
	"step": 58
	},
	{
	"epoch": 0.16393442622950818,
	"grad_norm": 0.33087924122810364,
	"learning_rate": 2.499918347707172e-05,
	"loss": 1.3224607706069946,
	"step": 60
	},
	{
	"epoch": 0.16939890710382513,
	"grad_norm": 0.3203301727771759,
	"learning_rate": 2.499816285119117e-05,
	"loss": 1.5149167776107788,
	"step": 62
	},
	{
	"epoch": 0.17486338797814208,
	"grad_norm": 0.8560717701911926,
	"learning_rate": 2.499673402681304e-05,
	"loss": 1.1875461339950562,
	"step": 64
	},
	{
	"epoch": 0.18032786885245902,
	"grad_norm": 0.779531717300415,
	"learning_rate": 2.49948970557897e-05,
	"loss": 1.3079862594604492,
	"step": 66
	},
	{
	"epoch": 0.18579234972677597,
	"grad_norm": 0.3134159743785858,
	"learning_rate": 2.499265200478526e-05,
	"loss": 1.2827211618423462,
	"step": 68
	},
	{
	"epoch": 0.1912568306010929,
	"grad_norm": 0.5278278589248657,
	"learning_rate": 2.498999895527316e-05,
	"loss": 1.3154817819595337,
	"step": 70
	},
	{
	"epoch": 0.19672131147540983,
	"grad_norm": 0.34715163707733154,
	"learning_rate": 2.4986938003533195e-05,
	"loss": 1.1282734870910645,
	"step": 72
	},
	{
	"epoch": 0.20218579234972678,
	"grad_norm": 0.2873562276363373,
	"learning_rate": 2.498346926064803e-05,
	"loss": 1.2482017278671265,
	"step": 74
	},
	{
	"epoch": 0.20765027322404372,
	"grad_norm": 0.40799790620803833,
	"learning_rate": 2.497959285249916e-05,
	"loss": 1.3365082740783691,
	"step": 76
	},
	{
	"epoch": 0.21311475409836064,
	"grad_norm": 2.886547565460205,
	"learning_rate": 2.497530891976237e-05,
	"loss": 0.8918291926383972,
	"step": 78
	},
	{
	"epoch": 0.2185792349726776,
	"grad_norm": 0.35245203971862793,
	"learning_rate": 2.497061761790258e-05,
	"loss": 0.6639876961708069,
	"step": 80
	},
	{
	"epoch": 0.22404371584699453,
	"grad_norm": 0.48221555352211,
	"learning_rate": 2.4965519117168257e-05,
	"loss": 1.4380748271942139,
	"step": 82
	},
	{
	"epoch": 0.22950819672131148,
	"grad_norm": 0.51203852891922,
	"learning_rate": 2.49600136025852e-05,
	"loss": 0.7898932695388794,
	"step": 84
	},
	{
	"epoch": 0.23497267759562843,
	"grad_norm": 0.27620550990104675,
	"learning_rate": 2.495410127394983e-05,
	"loss": 1.3038958311080933,
	"step": 86
	},
	{
	"epoch": 0.24043715846994534,
	"grad_norm": 0.3855900764465332,
	"learning_rate": 2.494778234582197e-05,
	"loss": 1.272139072418213,
	"step": 88
	},
	{
	"epoch": 0.2459016393442623,
	"grad_norm": 2.9909884929656982,
	"learning_rate": 2.494105704751701e-05,
	"loss": 0.8982883095741272,
	"step": 90
	},
	{
	"epoch": 0.25136612021857924,
	"grad_norm": 0.8854891061782837,
	"learning_rate": 2.4933925623097626e-05,
	"loss": 1.3485952615737915,
	"step": 92
	},
	{
	"epoch": 0.2568306010928962,
	"grad_norm": 0.3434160053730011,
	"learning_rate": 2.49263883313649e-05,
	"loss": 1.1437045335769653,
	"step": 94
	},
	{
	"epoch": 0.26229508196721313,
	"grad_norm": 0.5682878494262695,
	"learning_rate": 2.4918445445848933e-05,
	"loss": 1.5587941408157349,
	"step": 96
	},
	{
	"epoch": 0.2677595628415301,
	"grad_norm": 0.2681918740272522,
	"learning_rate": 2.491009725479893e-05,
	"loss": 0.9907023906707764,
	"step": 98
	},
	{
	"epoch": 0.273224043715847,
	"grad_norm": 0.32420745491981506,
	"learning_rate": 2.4901344061172718e-05,
	"loss": 1.0972590446472168,
	"step": 100
	},
	{
	"epoch": 0.2786885245901639,
	"grad_norm": 0.3802216053009033,
	"learning_rate": 2.489218618262578e-05,
	"loss": 1.2862308025360107,
	"step": 102
	},
	{
	"epoch": 0.28415300546448086,
	"grad_norm": 0.9653081297874451,
	"learning_rate": 2.4882623951499687e-05,
	"loss": 1.0500785112380981,
	"step": 104
	},
	{
	"epoch": 0.2896174863387978,
	"grad_norm": 0.2368626743555069,
	"learning_rate": 2.4872657714810083e-05,
	"loss": 1.2645362615585327,
	"step": 106
	},
	{
	"epoch": 0.29508196721311475,
	"grad_norm": 0.29273951053619385,
	"learning_rate": 2.4862287834234058e-05,
	"loss": 1.4147664308547974,
	"step": 108
	},
	{
	"epoch": 0.3005464480874317,
	"grad_norm": 0.3903352618217468,
	"learning_rate": 2.4851514686097042e-05,
	"loss": 1.2646139860153198,
	"step": 110
	},
	{
	"epoch": 0.30601092896174864,
	"grad_norm": 0.25432300567626953,
	"learning_rate": 2.4840338661359128e-05,
	"loss": 1.2783875465393066,
	"step": 112
	},
	{
	"epoch": 0.3114754098360656,
	"grad_norm": 0.6913565397262573,
	"learning_rate": 2.4828760165600914e-05,
	"loss": 1.4046285152435303,
	"step": 114
	},
	{
	"epoch": 0.31693989071038253,
	"grad_norm": 0.7609861493110657,
	"learning_rate": 2.481677961900875e-05,
	"loss": 1.2646381855010986,
	"step": 116
	},
	{
	"epoch": 0.3224043715846995,
	"grad_norm": 0.3743007481098175,
	"learning_rate": 2.4804397456359513e-05,
	"loss": 1.031684160232544,
	"step": 118
	},
	{
	"epoch": 0.32786885245901637,
	"grad_norm": 0.79277104139328,
	"learning_rate": 2.4791614127004825e-05,
	"loss": 1.2975627183914185,
	"step": 120
	},
	{
	"epoch": 0.3333333333333333,
	"grad_norm": 0.8501270413398743,
	"learning_rate": 2.477843009485474e-05,
	"loss": 1.358191728591919,
	"step": 122
	},
	{
	"epoch": 0.33879781420765026,
	"grad_norm": 0.3265473246574402,
	"learning_rate": 2.4764845838360912e-05,
	"loss": 1.051877498626709,
	"step": 124
	},
	{
	"epoch": 0.3442622950819672,
	"grad_norm": 0.35509005188941956,
	"learning_rate": 2.475086185049923e-05,
	"loss": 1.0525556802749634,
	"step": 126
	},
	{
	"epoch": 0.34972677595628415,
	"grad_norm": 0.3058815896511078,
	"learning_rate": 2.473647863875193e-05,
	"loss": 1.325781226158142,
	"step": 128
	},
	{
	"epoch": 0.3551912568306011,
	"grad_norm": 0.3684760332107544,
	"learning_rate": 2.472169672508918e-05,
	"loss": 1.2639888525009155,
	"step": 130
	},
	{
	"epoch": 0.36065573770491804,
	"grad_norm": 0.31321296095848083,
	"learning_rate": 2.4706516645950126e-05,
	"loss": 1.2196840047836304,
	"step": 132
	},
	{
	"epoch": 0.366120218579235,
	"grad_norm": 0.6234083771705627,
	"learning_rate": 2.4690938952223446e-05,
	"loss": 1.122013807296753,
	"step": 134
	},
	{
	"epoch": 0.37158469945355194,
	"grad_norm": 0.5376752614974976,
	"learning_rate": 2.4674964209227338e-05,
	"loss": 1.0269572734832764,
	"step": 136
	},
	{
	"epoch": 0.3770491803278688,
	"grad_norm": 0.3545861542224884,
	"learning_rate": 2.4658592996689018e-05,
	"loss": 0.9930480718612671,
	"step": 138
	},
	{
	"epoch": 0.3825136612021858,
	"grad_norm": 0.2623893618583679,
	"learning_rate": 2.464182590872366e-05,
	"loss": 0.6596786379814148,
	"step": 140
	},
	{
	"epoch": 0.3879781420765027,
	"grad_norm": 0.2950592339038849,
	"learning_rate": 2.4624663553812876e-05,
	"loss": 1.2530113458633423,
	"step": 142
	},
	{
	"epoch": 0.39344262295081966,
	"grad_norm": 0.36303240060806274,
	"learning_rate": 2.4607106554782592e-05,
	"loss": 1.278784155845642,
	"step": 144
	},
	{
	"epoch": 0.3989071038251366,
	"grad_norm": 0.28947484493255615,
	"learning_rate": 2.4589155548780468e-05,
	"loss": 1.2354241609573364,
	"step": 146
	},
	{
	"epoch": 0.40437158469945356,
	"grad_norm": 0.32500797510147095,
	"learning_rate": 2.4570811187252763e-05,
	"loss": 1.230383038520813,
	"step": 148
	},
	{
	"epoch": 0.4098360655737705,
	"grad_norm": 0.27029216289520264,
	"learning_rate": 2.4552074135920718e-05,
	"loss": 1.1657707691192627,
	"step": 150
	},
	{
	"epoch": 0.41530054644808745,
	"grad_norm": 0.7339510321617126,
	"learning_rate": 2.4532945074756356e-05,
	"loss": 1.271276831626892,
	"step": 152
	},
	{
	"epoch": 0.4207650273224044,
	"grad_norm": 0.29380178451538086,
	"learning_rate": 2.4513424697957853e-05,
	"loss": 1.2509087324142456,
	"step": 154
	},
	{
	"epoch": 0.4262295081967213,
	"grad_norm": 0.3937924802303314,
	"learning_rate": 2.4493513713924312e-05,
	"loss": 1.2946242094039917,
	"step": 156
	},
	{
	"epoch": 0.43169398907103823,
	"grad_norm": 0.4068252146244049,
	"learning_rate": 2.4473212845230066e-05,
	"loss": 1.028969168663025,
	"step": 158
	},
	{
	"epoch": 0.4371584699453552,
	"grad_norm": 0.2621578276157379,
	"learning_rate": 2.4452522828598448e-05,
	"loss": 1.2205129861831665,
	"step": 160
	},
	{
	"epoch": 0.4426229508196721,
	"grad_norm": 0.4484550654888153,
	"learning_rate": 2.4431444414875076e-05,
	"loss": 0.7462490797042847,
	"step": 162
	},
	{
	"epoch": 0.44808743169398907,
	"grad_norm": 0.3683895170688629,
	"learning_rate": 2.440997836900058e-05,
	"loss": 1.6338239908218384,
	"step": 164
	},
	{
	"epoch": 0.453551912568306,
	"grad_norm": 3.4501283168792725,
	"learning_rate": 2.438812546998286e-05,
	"loss": 0.7732384204864502,
	"step": 166
	},
	{
	"epoch": 0.45901639344262296,
	"grad_norm": 0.5550245046615601,
	"learning_rate": 2.4365886510868798e-05,
	"loss": 1.1818565130233765,
	"step": 168
	},
	{
	"epoch": 0.4644808743169399,
	"grad_norm": 0.39989838004112244,
	"learning_rate": 2.4343262298715504e-05,
	"loss": 1.2723463773727417,
	"step": 170
	},
	{
	"epoch": 0.46994535519125685,
	"grad_norm": 0.49861252307891846,
	"learning_rate": 2.4320253654560986e-05,
	"loss": 1.3423465490341187,
	"step": 172
	},
	{
	"epoch": 0.47540983606557374,
	"grad_norm": 0.4895351231098175,
	"learning_rate": 2.429686141339441e-05,
	"loss": 1.4451054334640503,
	"step": 174
	},
	{
	"epoch": 0.4808743169398907,
	"grad_norm": 0.27367469668388367,
	"learning_rate": 2.427308642412576e-05,
	"loss": 1.2423328161239624,
	"step": 176
	},
	{
	"epoch": 0.48633879781420764,
	"grad_norm": 0.6150447726249695,
	"learning_rate": 2.4248929549555024e-05,
	"loss": 1.208847165107727,
	"step": 178
	},
	{
	"epoch": 0.4918032786885246,
	"grad_norm": 0.21229158341884613,
	"learning_rate": 2.422439166634091e-05,
	"loss": 1.2032520771026611,
	"step": 180
	},
	{
	"epoch": 0.4972677595628415,
	"grad_norm": 0.38285210728645325,
	"learning_rate": 2.4199473664969033e-05,
	"loss": 1.1992058753967285,
	"step": 182
	},
	{
	"epoch": 0.5027322404371585,
	"grad_norm": 1.3906806707382202,
	"learning_rate": 2.4174176449719557e-05,
	"loss": 1.3618383407592773,
	"step": 184
	},
	{
	"epoch": 0.5081967213114754,
	"grad_norm": 1.3885375261306763,
	"learning_rate": 2.4148500938634432e-05,
	"loss": 1.2250099182128906,
	"step": 186
	},
	{
	"epoch": 0.5136612021857924,
	"grad_norm": 0.5974783897399902,
	"learning_rate": 2.412244806348404e-05,
	"loss": 1.208520770072937,
	"step": 188
	},
	{
	"epoch": 0.5191256830601093,
	"grad_norm": 0.2837812900543213,
	"learning_rate": 2.4096018769733402e-05,
	"loss": 1.256629467010498,
	"step": 190
	},
	{
	"epoch": 0.5245901639344263,
	"grad_norm": 0.5171183943748474,
	"learning_rate": 2.4069214016507857e-05,
	"loss": 1.2277578115463257,
	"step": 192
	},
	{
	"epoch": 0.5300546448087432,
	"grad_norm": 0.5090808868408203,
	"learning_rate": 2.4042034776558252e-05,
	"loss": 1.2597812414169312,
	"step": 194
	},
	{
	"epoch": 0.5355191256830601,
	"grad_norm": 0.277024507522583,
	"learning_rate": 2.4014482036225657e-05,
	"loss": 1.3096250295639038,
	"step": 196
	},
	{
	"epoch": 0.5409836065573771,
	"grad_norm": 0.28094005584716797,
	"learning_rate": 2.398655679540555e-05,
	"loss": 1.1250698566436768,
	"step": 198
	},
	{
	"epoch": 0.546448087431694,
	"grad_norm": 0.49337470531463623,
	"learning_rate": 2.3958260067511546e-05,
	"loss": 1.2817038297653198,
	"step": 200
	},
	{
	"epoch": 0.5519125683060109,
	"grad_norm": 0.2434162199497223,
	"learning_rate": 2.392959287943861e-05,
	"loss": 1.095908761024475,
	"step": 202
	},
	{
	"epoch": 0.5573770491803278,
	"grad_norm": 0.8104755282402039,
	"learning_rate": 2.390055627152579e-05,
	"loss": 0.9623884558677673,
	"step": 204
	},
	{
	"epoch": 0.5628415300546448,
	"grad_norm": 0.2845552861690521,
	"learning_rate": 2.3871151297518478e-05,
	"loss": 1.2727272510528564,
	"step": 206
	},
	{
	"epoch": 0.5683060109289617,
	"grad_norm": 0.30428346991539,
	"learning_rate": 2.384137902453016e-05,
	"loss": 1.2006559371948242,
	"step": 208
	},
	{
	"epoch": 0.5737704918032787,
	"grad_norm": 0.5667380690574646,
	"learning_rate": 2.381124053300368e-05,
	"loss": 1.2453666925430298,
	"step": 210
	},
	{
	"epoch": 0.5792349726775956,
	"grad_norm": 0.2638285458087921,
	"learning_rate": 2.378073691667204e-05,
	"loss": 1.5382798910140991,
	"step": 212
	},
	{
	"epoch": 0.5846994535519126,
	"grad_norm": 0.2258531153202057,
	"learning_rate": 2.3749869282518718e-05,
	"loss": 1.2467749118804932,
	"step": 214
	},
	{
	"epoch": 0.5901639344262295,
	"grad_norm": 0.4023035168647766,
	"learning_rate": 2.3718638750737472e-05,
	"loss": 1.6013109683990479,
	"step": 216
	},
	{
	"epoch": 0.5956284153005464,
	"grad_norm": 0.2880134582519531,
	"learning_rate": 2.3687046454691712e-05,
	"loss": 1.2340466976165771,
	"step": 218
	},
	{
	"epoch": 0.6010928961748634,
	"grad_norm": 0.21783682703971863,
	"learning_rate": 2.3655093540873353e-05,
	"loss": 1.3127397298812866,
	"step": 220
	},
	{
	"epoch": 0.6065573770491803,
	"grad_norm": 0.23105667531490326,
	"learning_rate": 2.3622781168861214e-05,
	"loss": 1.1359162330627441,
	"step": 222
	},
	{
	"epoch": 0.6120218579234973,
	"grad_norm": 1.055073857307434,
	"learning_rate": 2.3590110511278933e-05,
	"loss": 1.0895743370056152,
	"step": 224
	},
	{
	"epoch": 0.6174863387978142,
	"grad_norm": 0.22074124217033386,
	"learning_rate": 2.3557082753752437e-05,
	"loss": 1.2820183038711548,
	"step": 226
	},
	{
	"epoch": 0.6229508196721312,
	"grad_norm": 2.2928848266601562,
	"learning_rate": 2.352369909486687e-05,
	"loss": 1.2790377140045166,
	"step": 228
	},
	{
	"epoch": 0.6284153005464481,
	"grad_norm": 0.1916349232196808,
	"learning_rate": 2.3489960746123128e-05,
	"loss": 0.7690463662147522,
	"step": 230
	},
	{
	"epoch": 0.6338797814207651,
	"grad_norm": 0.24763409793376923,
	"learning_rate": 2.3455868931893894e-05,
	"loss": 1.2869762182235718,
	"step": 232
	},
	{
	"epoch": 0.639344262295082,
	"grad_norm": 1.6581783294677734,
	"learning_rate": 2.342142488937919e-05,
	"loss": 0.9537703990936279,
	"step": 234
	},
	{
	"epoch": 0.644808743169399,
	"grad_norm": 0.7167282104492188,
	"learning_rate": 2.3386629868561492e-05,
	"loss": 0.891618549823761,
	"step": 236
	},
	{
	"epoch": 0.6502732240437158,
	"grad_norm": 0.4610043168067932,
	"learning_rate": 2.3351485132160346e-05,
	"loss": 1.3490716218948364,
	"step": 238
	},
	{
	"epoch": 0.6557377049180327,
	"grad_norm": 0.44225654006004333,
	"learning_rate": 2.331599195558659e-05,
	"loss": 1.2553770542144775,
	"step": 240
	},
	{
	"epoch": 0.6612021857923497,
	"grad_norm": 0.5151908993721008,
	"learning_rate": 2.3280151626896003e-05,
	"loss": 1.2040798664093018,
	"step": 242
	},
	{
	"epoch": 0.6666666666666666,
	"grad_norm": 0.2373773753643036,
	"learning_rate": 2.324396544674262e-05,
	"loss": 1.0659421682357788,
	"step": 244
	},
	{
	"epoch": 0.6721311475409836,
	"grad_norm": 0.2626818120479584,
	"learning_rate": 2.3207434728331502e-05,
	"loss": 1.2204513549804688,
	"step": 246
	},
	{
	"epoch": 0.6775956284153005,
	"grad_norm": 0.29700711369514465,
	"learning_rate": 2.317056079737108e-05,
	"loss": 1.2991636991500854,
	"step": 248
	},
	{
	"epoch": 0.6830601092896175,
	"grad_norm": 0.3610213100910187,
	"learning_rate": 2.3133344992025057e-05,
	"loss": 1.2486889362335205,
	"step": 250
	},
	{
	"epoch": 0.6885245901639344,
	"grad_norm": 0.2309371531009674,
	"learning_rate": 2.3095788662863838e-05,
	"loss": 1.1427106857299805,
	"step": 252
	},
	{
	"epoch": 0.6939890710382514,
	"grad_norm": 0.1426355540752411,
	"learning_rate": 2.305789317281551e-05,
	"loss": 1.2058444023132324,
	"step": 254
	},
	{
	"epoch": 0.6994535519125683,
	"grad_norm": 0.19725173711776733,
	"learning_rate": 2.30196598971164e-05,
	"loss": 1.1971604824066162,
	"step": 256
	},
	{
	"epoch": 0.7049180327868853,
	"grad_norm": 0.26061874628067017,
	"learning_rate": 2.2981090223261146e-05,
	"loss": 1.1320452690124512,
	"step": 258
	},
	{
	"epoch": 0.7103825136612022,
	"grad_norm": 0.1859847754240036,
	"learning_rate": 2.294218555095236e-05,
	"loss": 1.1934643983840942,
	"step": 260
	},
	{
	"epoch": 0.7158469945355191,
	"grad_norm": 0.21825049817562103,
	"learning_rate": 2.2902947292049827e-05,
	"loss": 1.2934924364089966,
	"step": 262
	},
	{
	"epoch": 0.7213114754098361,
	"grad_norm": 0.14852340519428253,
	"learning_rate": 2.2863376870519273e-05,
	"loss": 1.2320027351379395,
	"step": 264
	},
	{
	"epoch": 0.726775956284153,
	"grad_norm": 0.22215086221694946,
	"learning_rate": 2.282347572238068e-05,
	"loss": 1.0896164178848267,
	"step": 266
	},
	{
	"epoch": 0.73224043715847,
	"grad_norm": 0.2927921414375305,
	"learning_rate": 2.278324529565617e-05,
	"loss": 1.2266433238983154,
	"step": 268
	},
	{
	"epoch": 0.7377049180327869,
	"grad_norm": 0.19128933548927307,
	"learning_rate": 2.274268705031748e-05,
	"loss": 1.2257647514343262,
	"step": 270
	},
	{
	"epoch": 0.7431693989071039,
	"grad_norm": 0.18742051720619202,
	"learning_rate": 2.2701802458232945e-05,
	"loss": 1.1814370155334473,
	"step": 272
	},
	{
	"epoch": 0.7486338797814208,
	"grad_norm": 0.3515142500400543,
	"learning_rate": 2.266059300311411e-05,
	"loss": 1.204115867614746,
	"step": 274
	},
	{
	"epoch": 0.7540983606557377,
	"grad_norm": 0.19052213430404663,
	"learning_rate": 2.2619060180461873e-05,
	"loss": 1.253179907798767,
	"step": 276
	},
	{
	"epoch": 0.7595628415300546,
	"grad_norm": 0.21446406841278076,
	"learning_rate": 2.2577205497512227e-05,
	"loss": 1.221806526184082,
	"step": 278
	},
	{
	"epoch": 0.7650273224043715,
	"grad_norm": 0.4379148483276367,
	"learning_rate": 2.253503047318153e-05,
	"loss": 0.8980993628501892,
	"step": 280
	},
	{
	"epoch": 0.7704918032786885,
	"grad_norm": 0.6354475021362305,
	"learning_rate": 2.249253663801143e-05,
	"loss": 1.2315393686294556,
	"step": 282
	},
	{
	"epoch": 0.7759562841530054,
	"grad_norm": 0.16127297282218933,
	"learning_rate": 2.244972553411328e-05,
	"loss": 1.2106963396072388,
	"step": 284
	},
	{
	"epoch": 0.7814207650273224,
	"grad_norm": 0.16545647382736206,
	"learning_rate": 2.2406598715112188e-05,
	"loss": 1.2198878526687622,
	"step": 286
	},
	{
	"epoch": 0.7868852459016393,
	"grad_norm": 0.17703773081302643,
	"learning_rate": 2.2363157746090647e-05,
	"loss": 1.1894257068634033,
	"step": 288
	},
	{
	"epoch": 0.7923497267759563,
	"grad_norm": 0.18015217781066895,
	"learning_rate": 2.231940420353173e-05,
	"loss": 1.162126064300537,
	"step": 290
	},
	{
	"epoch": 0.7978142076502732,
	"grad_norm": 0.971755862236023,
	"learning_rate": 2.2275339675261865e-05,
	"loss": 1.1871088743209839,
	"step": 292
	},
	{
	"epoch": 0.8032786885245902,
	"grad_norm": 0.2369270771741867,
	"learning_rate": 2.2230965760393242e-05,
	"loss": 1.187207818031311,
	"step": 294
	},
	{
	"epoch": 0.8087431693989071,
	"grad_norm": 0.521456778049469,
	"learning_rate": 2.218628406926575e-05,
	"loss": 1.5364131927490234,
	"step": 296
	},
	{
	"epoch": 0.8142076502732241,
	"grad_norm": 0.5664535164833069,
	"learning_rate": 2.214129622338856e-05,
	"loss": 0.925621509552002,
	"step": 298
	},
	{
	"epoch": 0.819672131147541,
	"grad_norm": 0.24125301837921143,
	"learning_rate": 2.2096003855381268e-05,
	"loss": 1.6008453369140625,
	"step": 300
	},
	{
	"epoch": 0.825136612021858,
	"grad_norm": 0.25689688324928284,
	"learning_rate": 2.2050408608914652e-05,
	"loss": 1.223463773727417,
	"step": 302
	},
	{
	"epoch": 0.8306010928961749,
	"grad_norm": 0.4135361909866333,
	"learning_rate": 2.200451213865102e-05,
	"loss": 0.9032531380653381,
	"step": 304
	},
	{
	"epoch": 0.8360655737704918,
	"grad_norm": 0.4481862783432007,
	"learning_rate": 2.195831611018416e-05,
	"loss": 1.557176113128662,
	"step": 306
	},
	{
	"epoch": 0.8415300546448088,
	"grad_norm": 0.598118245601654,
	"learning_rate": 2.1911822199978905e-05,
	"loss": 1.0001596212387085,
	"step": 308
	},
	{
	"epoch": 0.8469945355191257,
	"grad_norm": 0.1991797536611557,
	"learning_rate": 2.186503209531028e-05,
	"loss": 1.2186784744262695,
	"step": 310
	},
	{
	"epoch": 0.8524590163934426,
	"grad_norm": 0.23143993318080902,
	"learning_rate": 2.1817947494202283e-05,
	"loss": 1.2285571098327637,
	"step": 312
	},
	{
	"epoch": 0.8579234972677595,
	"grad_norm": 0.2992916405200958,
	"learning_rate": 2.1770570105366253e-05,
	"loss": 1.2401832342147827,
	"step": 314
	},
	{
	"epoch": 0.8633879781420765,
	"grad_norm": 0.3111695945262909,
	"learning_rate": 2.1722901648138872e-05,
	"loss": 1.2467424869537354,
	"step": 316
	},
	{
	"epoch": 0.8688524590163934,
	"grad_norm": 0.29361769556999207,
	"learning_rate": 2.1674943852419754e-05,
	"loss": 1.1437691450119019,
	"step": 318
	},
	{
	"epoch": 0.8743169398907104,
	"grad_norm": 0.2712153196334839,
	"learning_rate": 2.1626698458608678e-05,
	"loss": 1.3648308515548706,
	"step": 320
	},
	{
	"epoch": 0.8797814207650273,
	"grad_norm": 0.36124688386917114,
	"learning_rate": 2.1578167217542434e-05,
	"loss": 1.098549485206604,
	"step": 322
	},
	{
	"epoch": 0.8852459016393442,
	"grad_norm": 0.38840731978416443,
	"learning_rate": 2.1529351890431267e-05,
	"loss": 0.7575273513793945,
	"step": 324
	},
	{
	"epoch": 0.8907103825136612,
	"grad_norm": 0.26621684432029724,
	"learning_rate": 2.1480254248794972e-05,
	"loss": 1.25328528881073,
	"step": 326
	},
	{
	"epoch": 0.8961748633879781,
	"grad_norm": 0.3533453643321991,
	"learning_rate": 2.1430876074398613e-05,
	"loss": 1.0998711585998535,
	"step": 328
	},
	{
	"epoch": 0.9016393442622951,
	"grad_norm": 0.2502342164516449,
	"learning_rate": 2.138121915918785e-05,
	"loss": 1.2683922052383423,
	"step": 330
	},
	{
	"epoch": 0.907103825136612,
	"grad_norm": 1.4214491844177246,
	"learning_rate": 2.133128530522391e-05,
	"loss": 1.303632140159607,
	"step": 332
	},
	{
	"epoch": 0.912568306010929,
	"grad_norm": 0.4628271162509918,
	"learning_rate": 2.1281076324618197e-05,
	"loss": 1.1815130710601807,
	"step": 334
	},
	{
	"epoch": 0.9180327868852459,
	"grad_norm": 0.29728227853775024,
	"learning_rate": 2.123059403946653e-05,
	"loss": 1.2302957773208618,
	"step": 336
	},
	{
	"epoch": 0.9234972677595629,
	"grad_norm": 0.26023662090301514,
	"learning_rate": 2.1179840281783002e-05,
	"loss": 1.2583401203155518,
	"step": 338
	},
	{
	"epoch": 0.9289617486338798,
	"grad_norm": 0.20131556689739227,
	"learning_rate": 2.1128816893433524e-05,
	"loss": 1.2529937028884888,
	"step": 340
	},
	{
	"epoch": 0.9344262295081968,
	"grad_norm": 0.2651193141937256,
	"learning_rate": 2.107752572606895e-05,
	"loss": 1.2728800773620605,
	"step": 342
	},
	{
	"epoch": 0.9398907103825137,
	"grad_norm": 1.3046387434005737,
	"learning_rate": 2.1025968641057917e-05,
	"loss": 1.2606099843978882,
	"step": 344
	},
	{
	"epoch": 0.9453551912568307,
	"grad_norm": 0.23248107731342316,
	"learning_rate": 2.097414750941927e-05,
	"loss": 1.6241867542266846,
	"step": 346
	},
	{
	"epoch": 0.9508196721311475,
	"grad_norm": 0.457072913646698,
	"learning_rate": 2.092206421175416e-05,
	"loss": 1.0590146780014038,
	"step": 348
	},
	{
	"epoch": 0.9562841530054644,
	"grad_norm": 0.19466765224933624,
	"learning_rate": 2.0869720638177817e-05,
	"loss": 0.9096658825874329,
	"step": 350
	},
	{
	"epoch": 0.9617486338797814,
	"grad_norm": 0.2271135449409485,
	"learning_rate": 2.0817118688250933e-05,
	"loss": 1.2334853410720825,
	"step": 352
	},
	{
	"epoch": 0.9672131147540983,
	"grad_norm": 0.2870445251464844,
	"learning_rate": 2.0764260270910753e-05,
	"loss": 0.9327258467674255,
	"step": 354
	},
	{
	"epoch": 0.9726775956284153,
	"grad_norm": 0.3647417724132538,
	"learning_rate": 2.0711147304401775e-05,
	"loss": 1.1043840646743774,
	"step": 356
	},
	{
	"epoch": 0.9781420765027322,
	"grad_norm": 0.2910922169685364,
	"learning_rate": 2.0657781716206156e-05,
	"loss": 0.7837404608726501,
	"step": 358
	},
	{
	"epoch": 0.9836065573770492,
	"grad_norm": 0.26856181025505066,
	"learning_rate": 2.0604165442973738e-05,
	"loss": 1.2202802896499634,
	"step": 360
	},
	{
	"epoch": 0.9890710382513661,
	"grad_norm": 0.7940663695335388,
	"learning_rate": 2.0550300430451805e-05,
	"loss": 0.9926665425300598,
	"step": 362
	},
	{
	"epoch": 0.994535519125683,
	"grad_norm": 0.3847670257091522,
	"learning_rate": 2.049618863341443e-05,
	"loss": 1.2039496898651123,
	"step": 364
	},
	{
	"epoch": 1.0,
	"grad_norm": 0.4092676043510437,
	"learning_rate": 2.0441832015591565e-05,
	"loss": 1.1870145797729492,
	"step": 366
	},
	{
	"epoch": 1.005464480874317,
	"grad_norm": 0.2678527235984802,
	"learning_rate": 2.038723254959775e-05,
	"loss": 1.052931785583496,
	"step": 368
	},
	{
	"epoch": 1.010928961748634,
	"grad_norm": 0.3561493158340454,
	"learning_rate": 2.033239221686057e-05,
	"loss": 0.9613900780677795,
	"step": 370
	},
	{
	"epoch": 1.0163934426229508,
	"grad_norm": 0.3432145416736603,
	"learning_rate": 2.0277313007548702e-05,
	"loss": 0.9641975164413452,
	"step": 372
	},
	{
	"epoch": 1.0218579234972678,
	"grad_norm": 0.5496553778648376,
	"learning_rate": 2.022199692049971e-05,
	"loss": 0.9910390377044678,
	"step": 374
	},
	{
	"epoch": 1.0273224043715847,
	"grad_norm": 1.1139615774154663,
	"learning_rate": 2.0166445963147514e-05,
	"loss": 0.8240501284599304,
	"step": 376
	},
	{
	"epoch": 1.0327868852459017,
	"grad_norm": 0.38149014115333557,
	"learning_rate": 2.0110662151449538e-05,
	"loss": 0.9968246817588806,
	"step": 378
	},
	{
	"epoch": 1.0382513661202186,
	"grad_norm": 0.41972488164901733,
	"learning_rate": 2.0054647509813533e-05,
	"loss": 0.705604612827301,
	"step": 380
	},
	{
	"epoch": 1.0437158469945356,
	"grad_norm": 0.7368504405021667,
	"learning_rate": 1.9998404071024132e-05,
	"loss": 0.833368718624115,
	"step": 382
	},
	{
	"epoch": 1.0491803278688525,
	"grad_norm": 0.2574571967124939,
	"learning_rate": 1.9941933876169064e-05,
	"loss": 0.9591267704963684,
	"step": 384
	},
	{
	"epoch": 1.0546448087431695,
	"grad_norm": 0.6520720720291138,
	"learning_rate": 1.9885238974565092e-05,
	"loss": 0.7256029844284058,
	"step": 386
	},
	{
	"epoch": 1.0601092896174864,
	"grad_norm": 0.43294209241867065,
	"learning_rate": 1.982832142368365e-05,
	"loss": 0.6323433518409729,
	"step": 388
	},
	{
	"epoch": 1.0655737704918034,
	"grad_norm": 0.29659733176231384,
	"learning_rate": 1.9771183289076148e-05,
	"loss": 1.1004457473754883,
	"step": 390
	},
	{
	"epoch": 1.0710382513661203,
	"grad_norm": 0.19339755177497864,
	"learning_rate": 1.9713826644299056e-05,
	"loss": 0.9760780334472656,
	"step": 392
	},
	{
	"epoch": 1.0765027322404372,
	"grad_norm": 0.2182750552892685,
	"learning_rate": 1.96562535708386e-05,
	"loss": 0.6805109977722168,
	"step": 394
	},
	{
	"epoch": 1.0819672131147542,
	"grad_norm": 0.26215946674346924,
	"learning_rate": 1.959846615803528e-05,
	"loss": 1.012329339981079,
	"step": 396
	},
	{
	"epoch": 1.0874316939890711,
	"grad_norm": 0.220313161611557,
	"learning_rate": 1.954046650300801e-05,
	"loss": 0.9814585447311401,
	"step": 398
	},
	{
	"epoch": 1.092896174863388,
	"grad_norm": 0.339661568403244,
	"learning_rate": 1.9482256710578028e-05,
	"loss": 1.0675204992294312,
	"step": 400
	},
	{
	"epoch": 1.098360655737705,
	"grad_norm": 0.5715194344520569,
	"learning_rate": 1.94238388931925e-05,
	"loss": 1.002265214920044,
	"step": 402
	},
	{
	"epoch": 1.1038251366120218,
	"grad_norm": 0.326412171125412,
	"learning_rate": 1.9365215170847887e-05,
	"loss": 1.1493186950683594,
	"step": 404
	},
	{
	"epoch": 1.1092896174863387,
	"grad_norm": 0.781463086605072,
	"learning_rate": 1.9306387671012965e-05,
	"loss": 0.9932349920272827,
	"step": 406
	},
	{
	"epoch": 1.1147540983606556,
	"grad_norm": 0.7584837675094604,
	"learning_rate": 1.9247358528551662e-05,
	"loss": 0.6940405368804932,
	"step": 408
	},
	{
	"epoch": 1.1202185792349726,
	"grad_norm": 0.2473216950893402,
	"learning_rate": 1.918812988564555e-05,
	"loss": 1.1692583560943604,
	"step": 410
	},
	{
	"epoch": 1.1256830601092895,
	"grad_norm": 0.4508194923400879,
	"learning_rate": 1.9128703891716138e-05,
	"loss": 0.7730159759521484,
	"step": 412
	},
	{
	"epoch": 1.1311475409836065,
	"grad_norm": 0.20886428654193878,
	"learning_rate": 1.906908270334683e-05,
	"loss": 0.8129177689552307,
	"step": 414
	},
	{
	"epoch": 1.1366120218579234,
	"grad_norm": 1.0284196138381958,
	"learning_rate": 1.90092684842047e-05,
	"loss": 0.7486385703086853,
	"step": 416
	},
	{
	"epoch": 1.1420765027322404,
	"grad_norm": 0.29529622197151184,
	"learning_rate": 1.8949263404961936e-05,
	"loss": 0.9710283279418945,
	"step": 418
	},
	{
	"epoch": 1.1475409836065573,
	"grad_norm": 0.19345751404762268,
	"learning_rate": 1.888906964321711e-05,
	"loss": 0.9194430112838745,
	"step": 420
	},
	{
	"epoch": 1.1530054644808743,
	"grad_norm": 0.1850510686635971,
	"learning_rate": 1.88286893834161e-05,
	"loss": 1.015109896659851,
	"step": 422
	},
	{
	"epoch": 1.1584699453551912,
	"grad_norm": 1.9381911754608154,
	"learning_rate": 1.8768124816772854e-05,
	"loss": 0.7446098327636719,
	"step": 424
	},
	{
	"epoch": 1.1639344262295082,
	"grad_norm": 0.8182835578918457,
	"learning_rate": 1.870737814118987e-05,
	"loss": 0.7042106986045837,
	"step": 426
	},
	{
	"epoch": 1.169398907103825,
	"grad_norm": 0.3277008831501007,
	"learning_rate": 1.86464515611784e-05,
	"loss": 1.1486928462982178,
	"step": 428
	},
	{
	"epoch": 1.174863387978142,
	"grad_norm": 0.23618929088115692,
	"learning_rate": 1.8585347287778493e-05,
	"loss": 0.9731719493865967,
	"step": 430
	},
	{
	"epoch": 1.180327868852459,
	"grad_norm": 0.2742961645126343,
	"learning_rate": 1.8524067538478713e-05,
	"loss": 1.040266752243042,
	"step": 432
	},
	{
	"epoch": 1.185792349726776,
	"grad_norm": 0.27158892154693604,
	"learning_rate": 1.8462614537135708e-05,
	"loss": 0.8597835898399353,
	"step": 434
	},
	{
	"epoch": 1.1912568306010929,
	"grad_norm": 0.2809169292449951,
	"learning_rate": 1.840099051389346e-05,
	"loss": 1.0985636711120605,
	"step": 436
	},
	{
	"epoch": 1.1967213114754098,
	"grad_norm": 0.27836382389068604,
	"learning_rate": 1.8339197705102396e-05,
	"loss": 0.9655686616897583,
	"step": 438
	},
	{
	"epoch": 1.2021857923497268,
	"grad_norm": 0.2705060839653015,
	"learning_rate": 1.8277238353238193e-05,
	"loss": 0.8749003410339355,
	"step": 440
	},
	{
	"epoch": 1.2076502732240437,
	"grad_norm": 0.40282824635505676,
	"learning_rate": 1.8215114706820435e-05,
	"loss": 0.9861440062522888,
	"step": 442
	},
	{
	"epoch": 1.2131147540983607,
	"grad_norm": 0.28667566180229187,
	"learning_rate": 1.8152829020330975e-05,
	"loss": 0.9603111743927002,
	"step": 444
	},
	{
	"epoch": 1.2185792349726776,
	"grad_norm": 0.20321297645568848,
	"learning_rate": 1.8090383554132158e-05,
	"loss": 0.6063272953033447,
	"step": 446
	},
	{
	"epoch": 1.2240437158469946,
	"grad_norm": 0.2519320845603943,
	"learning_rate": 1.8027780574384753e-05,
	"loss": 1.0045597553253174,
	"step": 448
	},
	{
	"epoch": 1.2295081967213115,
	"grad_norm": 0.2760215401649475,
	"learning_rate": 1.796502235296575e-05,
	"loss": 0.9750694036483765,
	"step": 450
	},
	{
	"epoch": 1.2349726775956285,
	"grad_norm": 1.3805330991744995,
	"learning_rate": 1.7902111167385883e-05,
	"loss": 0.9757618308067322,
	"step": 452
	},
	{
	"epoch": 1.2404371584699454,
	"grad_norm": 0.41420966386795044,
	"learning_rate": 1.7839049300707003e-05,
	"loss": 1.1883511543273926,
	"step": 454
	},
	{
	"epoch": 1.2459016393442623,
	"grad_norm": 3.457296371459961,
	"learning_rate": 1.7775839041459203e-05,
	"loss": 0.8075215816497803,
	"step": 456
	},
	{
	"epoch": 1.2513661202185793,
	"grad_norm": 0.41424238681793213,
	"learning_rate": 1.7712482683557778e-05,
	"loss": 0.7205969095230103,
	"step": 458
	},
	{
	"epoch": 1.2568306010928962,
	"grad_norm": 0.23676064610481262,
	"learning_rate": 1.7648982526219995e-05,
	"loss": 0.9795306324958801,
	"step": 460
	},
	{
	"epoch": 1.2622950819672132,
	"grad_norm": 0.5828472375869751,
	"learning_rate": 1.7585340873881617e-05,
	"loss": 0.7240006923675537,
	"step": 462
	},
	{
	"epoch": 1.2677595628415301,
	"grad_norm": 0.41735684871673584,
	"learning_rate": 1.7521560036113303e-05,
	"loss": 0.9175815582275391,
	"step": 464
	},
	{
	"epoch": 1.273224043715847,
	"grad_norm": 1.274187684059143,
	"learning_rate": 1.7457642327536777e-05,
	"loss": 1.003617763519287,
	"step": 466
	},
	{
	"epoch": 1.278688524590164,
	"grad_norm": 0.19330422580242157,
	"learning_rate": 1.7393590067740852e-05,
	"loss": 0.9662733674049377,
	"step": 468
	},
	{
	"epoch": 1.2841530054644807,
	"grad_norm": 0.4729224443435669,
	"learning_rate": 1.732940558119722e-05,
	"loss": 1.0254093408584595,
	"step": 470
	},
	{
	"epoch": 1.289617486338798,
	"grad_norm": 0.2658669352531433,
	"learning_rate": 1.726509119717612e-05,
	"loss": 1.1315693855285645,
	"step": 472
	},
	{
	"epoch": 1.2950819672131146,
	"grad_norm": 0.17870910465717316,
	"learning_rate": 1.7200649249661806e-05,
	"loss": 1.0432623624801636,
	"step": 474
	},
	{
	"epoch": 1.3005464480874318,
	"grad_norm": 0.6331385970115662,
	"learning_rate": 1.7136082077267837e-05,
	"loss": 0.4694063067436218,
	"step": 476
	},
	{
	"epoch": 1.3060109289617485,
	"grad_norm": 0.24067234992980957,
	"learning_rate": 1.7071392023152208e-05,
	"loss": 0.9866682291030884,
	"step": 478
	},
	{
	"epoch": 1.3114754098360657,
	"grad_norm": 0.2517263889312744,
	"learning_rate": 1.700658143493233e-05,
	"loss": 1.1108297109603882,
	"step": 480
	},
	{
	"epoch": 1.3169398907103824,
	"grad_norm": 0.15475492179393768,
	"learning_rate": 1.6941652664599814e-05,
	"loss": 0.8292356133460999,
	"step": 482
	},
	{
	"epoch": 1.3224043715846996,
	"grad_norm": 0.412447988986969,
	"learning_rate": 1.687660806843514e-05,
	"loss": 0.6224348545074463,
	"step": 484
	},
	{
	"epoch": 1.3278688524590163,
	"grad_norm": 0.20403409004211426,
	"learning_rate": 1.681145000692213e-05,
	"loss": 0.9716439843177795,
	"step": 486
	},
	{
	"epoch": 1.3333333333333333,
	"grad_norm": 0.32221364974975586,
	"learning_rate": 1.6746180844662286e-05,
	"loss": 0.9632929563522339,
	"step": 488
	},
	{
	"epoch": 1.3387978142076502,
	"grad_norm": 0.4680832028388977,
	"learning_rate": 1.6680802950288988e-05,
	"loss": 0.678726851940155,
	"step": 490
	},
	{
	"epoch": 1.3442622950819672,
	"grad_norm": 0.24255001544952393,
	"learning_rate": 1.661531869638153e-05,
	"loss": 1.0519957542419434,
	"step": 492
	},
	{
	"epoch": 1.349726775956284,
	"grad_norm": 0.14533624053001404,
	"learning_rate": 1.6549730459379012e-05,
	"loss": 0.7603930234909058,
	"step": 494
	},
	{
	"epoch": 1.355191256830601,
	"grad_norm": 0.29373615980148315,
	"learning_rate": 1.648404061949412e-05,
	"loss": 1.014536738395691,
	"step": 496
	},
	{
	"epoch": 1.360655737704918,
	"grad_norm": 0.8250491619110107,
	"learning_rate": 1.641825156062671e-05,
	"loss": 0.9662138223648071,
	"step": 498
	},
	{
	"epoch": 1.366120218579235,
	"grad_norm": 0.2744878828525543,
	"learning_rate": 1.635236567027734e-05,
	"loss": 1.1449735164642334,
	"step": 500
	},
	{
	"epoch": 1.3715846994535519,
	"grad_norm": 0.3034563362598419,
	"learning_rate": 1.6286385339460596e-05,
	"loss": 0.9222993850708008,
	"step": 502
	},
	{
	"epoch": 1.3770491803278688,
	"grad_norm": 0.2692282795906067,
	"learning_rate": 1.6220312962618332e-05,
	"loss": 0.6134414076805115,
	"step": 504
	},
	{
	"epoch": 1.3825136612021858,
	"grad_norm": 0.5227485299110413,
	"learning_rate": 1.6154150937532775e-05,
	"loss": 0.9774447679519653,
	"step": 506
	},
	{
	"epoch": 1.3879781420765027,
	"grad_norm": 0.2803296148777008,
	"learning_rate": 1.6087901665239502e-05,
	"loss": 0.9835152626037598,
	"step": 508
	},
	{
	"epoch": 1.3934426229508197,
	"grad_norm": 0.3903689980506897,
	"learning_rate": 1.602156754994032e-05,
	"loss": 1.0372285842895508,
	"step": 510
	},
	{
	"epoch": 1.3989071038251366,
	"grad_norm": 0.18825502693653107,
	"learning_rate": 1.5955150998916003e-05,
	"loss": 0.9928014874458313,
	"step": 512
	},
	{
	"epoch": 1.4043715846994536,
	"grad_norm": 0.1467607021331787,
	"learning_rate": 1.5888654422438946e-05,
	"loss": 0.793111264705658,
	"step": 514
	},
	{
	"epoch": 1.4098360655737705,
	"grad_norm": 0.1626003533601761,
	"learning_rate": 1.5822080233685678e-05,
	"loss": 0.6302416324615479,
	"step": 516
	},
	{
	"epoch": 1.4153005464480874,
	"grad_norm": 0.21208561956882477,
	"learning_rate": 1.575543084864929e-05,
	"loss": 1.056746006011963,
	"step": 518
	},
	{
	"epoch": 1.4207650273224044,
	"grad_norm": 0.5272570252418518,
	"learning_rate": 1.5688708686051784e-05,
	"loss": 0.6418699026107788,
	"step": 520
	},
	{
	"epoch": 1.4262295081967213,
	"grad_norm": 0.2039785534143448,
	"learning_rate": 1.5621916167256255e-05,
	"loss": 0.9852989315986633,
	"step": 522
	},
	{
	"epoch": 1.4316939890710383,
	"grad_norm": 2.6706042289733887,
	"learning_rate": 1.555505571617906e-05,
	"loss": 0.786631166934967,
	"step": 524
	},
	{
	"epoch": 1.4371584699453552,
	"grad_norm": 0.8656861186027527,
	"learning_rate": 1.5488129759201822e-05,
	"loss": 0.9886066913604736,
	"step": 526
	},
	{
	"epoch": 1.4426229508196722,
	"grad_norm": 0.3004356920719147,
	"learning_rate": 1.5421140725083388e-05,
	"loss": 0.6762040257453918,
	"step": 528
	},
	{
	"epoch": 1.4480874316939891,
	"grad_norm": 0.6082632541656494,
	"learning_rate": 1.53540910448717e-05,
	"loss": 0.7938519716262817,
	"step": 530
	},
	{
	"epoch": 1.453551912568306,
	"grad_norm": 0.4222017824649811,
	"learning_rate": 1.5286983151815553e-05,
	"loss": 0.5967254042625427,
	"step": 532
	},
	{
	"epoch": 1.459016393442623,
	"grad_norm": 0.20243442058563232,
	"learning_rate": 1.52198194812763e-05,
	"loss": 0.9870072603225708,
	"step": 534
	},
	{
	"epoch": 1.46448087431694,
	"grad_norm": 0.21171127259731293,
	"learning_rate": 1.515260247063948e-05,
	"loss": 0.9821056127548218,
	"step": 536
	},
	{
	"epoch": 1.469945355191257,
	"grad_norm": 0.19740687310695648,
	"learning_rate": 1.5085334559226342e-05,
	"loss": 0.9811551570892334,
	"step": 538
	},
	{
	"epoch": 1.4754098360655736,
	"grad_norm": 0.1451021134853363,
	"learning_rate": 1.5018018188205354e-05,
	"loss": 1.0408740043640137,
	"step": 540
	},
	{
	"epoch": 1.4808743169398908,
	"grad_norm": 0.2504618763923645,
	"learning_rate": 1.4950655800503577e-05,
	"loss": 0.967536985874176,
	"step": 542
	},
	{
	"epoch": 1.4863387978142075,
	"grad_norm": 0.2872159481048584,
	"learning_rate": 1.4883249840718045e-05,
	"loss": 0.8747035264968872,
	"step": 544
	},
	{
	"epoch": 1.4918032786885247,
	"grad_norm": 0.7941830158233643,
	"learning_rate": 1.4815802755027019e-05,
	"loss": 1.1690365076065063,
	"step": 546
	},
	{
	"epoch": 1.4972677595628414,
	"grad_norm": 0.818136990070343,
	"learning_rate": 1.474831699110124e-05,
	"loss": 0.5261512994766235,
	"step": 548
	},
	{
	"epoch": 1.5027322404371586,
	"grad_norm": 0.25710561871528625,
	"learning_rate": 1.4680794998015081e-05,
	"loss": 0.9896012544631958,
	"step": 550
	},
	{
	"epoch": 1.5081967213114753,
	"grad_norm": 0.2098042219877243,
	"learning_rate": 1.4613239226157693e-05,
	"loss": 0.9484928250312805,
	"step": 552
	},
	{
	"epoch": 1.5136612021857925,
	"grad_norm": 0.21850721538066864,
	"learning_rate": 1.4545652127144052e-05,
	"loss": 0.9997845888137817,
	"step": 554
	},
	{
	"epoch": 1.5191256830601092,
	"grad_norm": 0.2467595338821411,
	"learning_rate": 1.4478036153726013e-05,
	"loss": 0.9743095636367798,
	"step": 556
	},
	{
	"epoch": 1.5245901639344264,
	"grad_norm": 0.23051407933235168,
	"learning_rate": 1.4410393759703286e-05,
	"loss": 0.7760718464851379,
	"step": 558
	},
	{
	"epoch": 1.530054644808743,
	"grad_norm": 0.29818111658096313,
	"learning_rate": 1.4342727399834396e-05,
	"loss": 0.6354138851165771,
	"step": 560
	},
	{
	"epoch": 1.5355191256830603,
	"grad_norm": 0.5161439180374146,
	"learning_rate": 1.4275039529747592e-05,
	"loss": 0.893290638923645,
	"step": 562
	},
	{
	"epoch": 1.540983606557377,
	"grad_norm": 0.8079479336738586,
	"learning_rate": 1.4207332605851725e-05,
	"loss": 0.7297835946083069,
	"step": 564
	},
	{
	"epoch": 1.5464480874316942,
	"grad_norm": 0.19712623953819275,
	"learning_rate": 1.413960908524713e-05,
	"loss": 0.9552266597747803,
	"step": 566
	},
	{
	"epoch": 1.5519125683060109,
	"grad_norm": 0.35008788108825684,
	"learning_rate": 1.407187142563643e-05,
	"loss": 0.7161392569541931,
	"step": 568
	},
	{
	"epoch": 1.5573770491803278,
	"grad_norm": 0.30580294132232666,
	"learning_rate": 1.4004122085235349e-05,
	"loss": 1.1108880043029785,
	"step": 570
	},
	{
	"epoch": 1.5628415300546448,
	"grad_norm": 0.28407377004623413,
	"learning_rate": 1.3936363522683532e-05,
	"loss": 0.9953396916389465,
	"step": 572
	},
	{
	"epoch": 1.5683060109289617,
	"grad_norm": 0.3069007396697998,
	"learning_rate": 1.3868598196955273e-05,
	"loss": 0.9776367545127869,
	"step": 574
	},
	{
	"epoch": 1.5737704918032787,
	"grad_norm": 0.22995546460151672,
	"learning_rate": 1.3800828567270318e-05,
	"loss": 0.7785615921020508,
	"step": 576
	},
	{
	"epoch": 1.5792349726775956,
	"grad_norm": 0.33251991868019104,
	"learning_rate": 1.3733057093004605e-05,
	"loss": 1.0668448209762573,
	"step": 578
	},
	{
	"epoch": 1.5846994535519126,
	"grad_norm": 0.46238404512405396,
	"learning_rate": 1.3665286233601002e-05,
	"loss": 0.577606201171875,
	"step": 580
	},
	{
	"epoch": 1.5901639344262295,
	"grad_norm": 0.29064756631851196,
	"learning_rate": 1.3597518448480075e-05,
	"loss": 0.6106272339820862,
	"step": 582
	},
	{
	"epoch": 1.5956284153005464,
	"grad_norm": 0.39371079206466675,
	"learning_rate": 1.3529756196950815e-05,
	"loss": 0.741959810256958,
	"step": 584
	},
	{
	"epoch": 1.6010928961748634,
	"grad_norm": 0.19503989815711975,
	"learning_rate": 1.3462001938121405e-05,
	"loss": 1.024315595626831,
	"step": 586
	},
	{
	"epoch": 1.6065573770491803,
	"grad_norm": 0.222434401512146,
	"learning_rate": 1.3394258130809961e-05,
	"loss": 1.0157414674758911,
	"step": 588
	},
	{
	"epoch": 1.6120218579234973,
	"grad_norm": 0.2086457908153534,
	"learning_rate": 1.332652723345533e-05,
	"loss": 0.7172755002975464,
	"step": 590
	},
	{
	"epoch": 1.6174863387978142,
	"grad_norm": 0.25153470039367676,
	"learning_rate": 1.3258811704027823e-05,
	"loss": 0.9605967998504639,
	"step": 592
	},
	{
	"epoch": 1.6229508196721312,
	"grad_norm": 1.1914056539535522,
	"learning_rate": 1.3191113999940072e-05,
	"loss": 0.7792953252792358,
	"step": 594
	},
	{
	"epoch": 1.6284153005464481,
	"grad_norm": 0.3395598828792572,
	"learning_rate": 1.3123436577957814e-05,
	"loss": 0.39568331837654114,
	"step": 596
	},
	{
	"epoch": 1.633879781420765,
	"grad_norm": 0.21833889186382294,
	"learning_rate": 1.305578189411075e-05,
	"loss": 0.997237503528595,
	"step": 598
	},
	{
	"epoch": 1.639344262295082,
	"grad_norm": 0.4959961771965027,
	"learning_rate": 1.2988152403603387e-05,
	"loss": 1.0844365358352661,
	"step": 600
	},
	{
	"epoch": 1.644808743169399,
	"grad_norm": 0.17567996680736542,
	"learning_rate": 1.2920550560725985e-05,
	"loss": 1.0519412755966187,
	"step": 602
	},
	{
	"epoch": 1.650273224043716,
	"grad_norm": 0.2537671625614166,
	"learning_rate": 1.2852978818765457e-05,
	"loss": 1.0641611814498901,
	"step": 604
	},
	{
	"epoch": 1.6557377049180326,
	"grad_norm": 0.272575318813324,
	"learning_rate": 1.2785439629916346e-05,
	"loss": 1.0360894203186035,
	"step": 606
	},
	{
	"epoch": 1.6612021857923498,
	"grad_norm": 0.22028231620788574,
	"learning_rate": 1.2717935445191823e-05,
	"loss": 0.8390608429908752,
	"step": 608
	},
	{
	"epoch": 1.6666666666666665,
	"grad_norm": 0.2603016793727875,
	"learning_rate": 1.2650468714334764e-05,
	"loss": 1.0364290475845337,
	"step": 610
	},
	{
	"epoch": 1.6721311475409837,
	"grad_norm": 0.9713470339775085,
	"learning_rate": 1.2583041885728841e-05,
	"loss": 0.6826381087303162,
	"step": 612
	},
	{
	"epoch": 1.6775956284153004,
	"grad_norm": 0.23464682698249817,
	"learning_rate": 1.2515657406309653e-05,
	"loss": 0.9781528115272522,
	"step": 614
	},
	{
	"epoch": 1.6830601092896176,
	"grad_norm": 0.2752858102321625,
	"learning_rate": 1.2448317721475938e-05,
	"loss": 1.009163737297058,
	"step": 616
	},
	{
	"epoch": 1.6885245901639343,
	"grad_norm": 0.19153419137001038,
	"learning_rate": 1.2381025275000826e-05,
	"loss": 0.5738469362258911,
	"step": 618
	},
	{
	"epoch": 1.6939890710382515,
	"grad_norm": 0.2596787214279175,
	"learning_rate": 1.2313782508943165e-05,
	"loss": 0.9725096225738525,
	"step": 620
	},
	{
	"epoch": 1.6994535519125682,
	"grad_norm": 0.36354807019233704,
	"learning_rate": 1.224659186355888e-05,
	"loss": 1.1703816652297974,
	"step": 622
	},
	{
	"epoch": 1.7049180327868854,
	"grad_norm": 0.2569591701030731,
	"learning_rate": 1.2179455777212426e-05,
	"loss": 0.6586411595344543,
	"step": 624
	},
	{
	"epoch": 1.710382513661202,
	"grad_norm": 0.14563089609146118,
	"learning_rate": 1.2112376686288302e-05,
	"loss": 0.5979112386703491,
	"step": 626
	},
	{
	"epoch": 1.7158469945355193,
	"grad_norm": 0.17862805724143982,
	"learning_rate": 1.204535702510263e-05,
	"loss": 1.0485451221466064,
	"step": 628
	},
	{
	"epoch": 1.721311475409836,
	"grad_norm": 0.46438074111938477,
	"learning_rate": 1.1978399225814802e-05,
	"loss": 0.7404160499572754,
	"step": 630
	},
	{
	"epoch": 1.7267759562841531,
	"grad_norm": 0.16041846573352814,
	"learning_rate": 1.1911505718339238e-05,
	"loss": 0.9989252686500549,
	"step": 632
	},
	{
	"epoch": 1.7322404371584699,
	"grad_norm": 0.16997864842414856,
	"learning_rate": 1.1844678930257189e-05,
	"loss": 1.0865825414657593,
	"step": 634
	},
	{
	"epoch": 1.737704918032787,
	"grad_norm": 0.19891749322414398,
	"learning_rate": 1.1777921286728649e-05,
	"loss": 0.8886318206787109,
	"step": 636
	},
	{
	"epoch": 1.7431693989071038,
	"grad_norm": 0.1822405755519867,
	"learning_rate": 1.1711235210404322e-05,
	"loss": 0.9987983107566833,
	"step": 638
	},
	{
	"epoch": 1.748633879781421,
	"grad_norm": 0.5658647418022156,
	"learning_rate": 1.1644623121337744e-05,
	"loss": 0.8494293689727783,
	"step": 640
	},
	{
	"epoch": 1.7540983606557377,
	"grad_norm": 0.2527749836444855,
	"learning_rate": 1.1578087436897425e-05,
	"loss": 1.0923233032226562,
	"step": 642
	},
	{
	"epoch": 1.7595628415300546,
	"grad_norm": 0.17464260756969452,
	"learning_rate": 1.1511630571679133e-05,
	"loss": 0.9967983961105347,
	"step": 644
	},
	{
	"epoch": 1.7650273224043715,
	"grad_norm": 0.18370413780212402,
	"learning_rate": 1.1445254937418262e-05,
	"loss": 0.6361693739891052,
	"step": 646
	},
	{
	"epoch": 1.7704918032786885,
	"grad_norm": 0.277452290058136,
	"learning_rate": 1.1378962942902325e-05,
	"loss": 0.9944519996643066,
	"step": 648
	},
	{
	"epoch": 1.7759562841530054,
	"grad_norm": 0.17650683224201202,
	"learning_rate": 1.1312756993883528e-05,
	"loss": 0.9504789113998413,
	"step": 650
	},
	{
	"epoch": 1.7814207650273224,
	"grad_norm": 0.1316922903060913,
	"learning_rate": 1.1246639492991464e-05,
	"loss": 0.9381383657455444,
	"step": 652
	},
	{
	"epoch": 1.7868852459016393,
	"grad_norm": 0.44887641072273254,
	"learning_rate": 1.1180612839645918e-05,
	"loss": 0.9580968022346497,
	"step": 654
	},
	{
	"epoch": 1.7923497267759563,
	"grad_norm": 0.5374517440795898,
	"learning_rate": 1.1114679429969799e-05,
	"loss": 0.8842057585716248,
	"step": 656
	},
	{
	"epoch": 1.7978142076502732,
	"grad_norm": 0.2197987288236618,
	"learning_rate": 1.1048841656702183e-05,
	"loss": 0.6668030023574829,
	"step": 658
	},
	{
	"epoch": 1.8032786885245902,
	"grad_norm": 0.2299073338508606,
	"learning_rate": 1.0983101909111476e-05,
	"loss": 0.9139745831489563,
	"step": 660
	},
	{
	"epoch": 1.8087431693989071,
	"grad_norm": 0.17643967270851135,
	"learning_rate": 1.0917462572908709e-05,
	"loss": 0.9805459976196289,
	"step": 662
	},
	{
	"epoch": 1.814207650273224,
	"grad_norm": 0.23675832152366638,
	"learning_rate": 1.0851926030160964e-05,
	"loss": 1.0229063034057617,
	"step": 664
	},
	{
	"epoch": 1.819672131147541,
	"grad_norm": 0.3587989807128906,
	"learning_rate": 1.0786494659204919e-05,
	"loss": 0.9302806854248047,
	"step": 666
	},
	{
	"epoch": 1.825136612021858,
	"grad_norm": 0.18514367938041687,
	"learning_rate": 1.0721170834560539e-05,
	"loss": 0.9443346261978149,
	"step": 668
	},
	{
	"epoch": 1.830601092896175,
	"grad_norm": 0.1954764574766159,
	"learning_rate": 1.0655956926844917e-05,
	"loss": 0.6162158250808716,
	"step": 670
	},
	{
	"epoch": 1.8360655737704918,
	"grad_norm": 0.6150888800621033,
	"learning_rate": 1.0590855302686232e-05,
	"loss": 0.864729642868042,
	"step": 672
	},
	{
	"epoch": 1.8415300546448088,
	"grad_norm": 0.15662595629692078,
	"learning_rate": 1.0525868324637867e-05,
	"loss": 0.9829941391944885,
	"step": 674
	},
	{
	"epoch": 1.8469945355191257,
	"grad_norm": 0.1537102609872818,
	"learning_rate": 1.046099835109266e-05,
	"loss": 0.9522998332977295,
	"step": 676
	},
	{
	"epoch": 1.8524590163934427,
	"grad_norm": 0.13544432818889618,
	"learning_rate": 1.0396247736197342e-05,
	"loss": 0.22472639381885529,
	"step": 678
	},
	{
	"epoch": 1.8579234972677594,
	"grad_norm": 0.214643195271492,
	"learning_rate": 1.0331618829767084e-05,
	"loss": 0.9816657900810242,
	"step": 680
	},
	{
	"epoch": 1.8633879781420766,
	"grad_norm": 0.14030401408672333,
	"learning_rate": 1.026711397720023e-05,
	"loss": 0.9638572931289673,
	"step": 682
	},
	{
	"epoch": 1.8688524590163933,
	"grad_norm": 0.23839998245239258,
	"learning_rate": 1.0202735519393172e-05,
	"loss": 0.8905544281005859,
	"step": 684
	},
	{
	"epoch": 1.8743169398907105,
	"grad_norm": 0.6069282293319702,
	"learning_rate": 1.013848579265542e-05,
	"loss": 0.7191258668899536,
	"step": 686
	},
	{
	"epoch": 1.8797814207650272,
	"grad_norm": 0.18707877397537231,
	"learning_rate": 1.0074367128624787e-05,
	"loss": 0.9472928047180176,
	"step": 688
	},
	{
	"epoch": 1.8852459016393444,
	"grad_norm": 0.1760343462228775,
	"learning_rate": 1.0010381854182808e-05,
	"loss": 1.0247843265533447,
	"step": 690
	},
	{
	"epoch": 1.890710382513661,
	"grad_norm": 0.2688332796096802,
	"learning_rate": 9.946532291370258e-06,
	"loss": 0.7216252684593201,
	"step": 692
	},
	{
	"epoch": 1.8961748633879782,
	"grad_norm": 0.2513716518878937,
	"learning_rate": 9.882820757302921e-06,
	"loss": 0.9491530060768127,
	"step": 694
	},
	{
	"epoch": 1.901639344262295,
	"grad_norm": 0.1897820681333542,
	"learning_rate": 9.819249564087476e-06,
	"loss": 0.9903871417045593,
	"step": 696
	},
	{
	"epoch": 1.9071038251366121,
	"grad_norm": 0.2507593631744385,
	"learning_rate": 9.755821018737602e-06,
	"loss": 0.739215075969696,
	"step": 698
	},
	{
	"epoch": 1.9125683060109289,
	"grad_norm": 0.2772381901741028,
	"learning_rate": 9.692537423090254e-06,
	"loss": 0.9631948471069336,
	"step": 700
	},
	{
	"epoch": 1.918032786885246,
	"grad_norm": 0.1794651299715042,
	"learning_rate": 9.629401073722121e-06,
	"loss": 0.9130382537841797,
	"step": 702
	},
	{
	"epoch": 1.9234972677595628,
	"grad_norm": 0.18744076788425446,
	"learning_rate": 9.566414261866308e-06,
	"loss": 0.9499990940093994,
	"step": 704
	},
	{
	"epoch": 1.92896174863388,
	"grad_norm": 0.21617577970027924,
	"learning_rate": 9.503579273329149e-06,
	"loss": 1.0123318433761597,
	"step": 706
	},
	{
	"epoch": 1.9344262295081966,
	"grad_norm": 0.17715895175933838,
	"learning_rate": 9.440898388407277e-06,
	"loss": 0.9562976360321045,
	"step": 708
	},
	{
	"epoch": 1.9398907103825138,
	"grad_norm": 0.1489608734846115,
	"learning_rate": 9.378373881804876e-06,
	"loss": 0.6913546323776245,
	"step": 710
	},
	{
	"epoch": 1.9453551912568305,
	"grad_norm": 0.24274346232414246,
	"learning_rate": 9.316008022551121e-06,
	"loss": 0.5943477749824524,
	"step": 712
	},
	{
	"epoch": 1.9508196721311475,
	"grad_norm": 0.25395557284355164,
	"learning_rate": 9.253803073917827e-06,
	"loss": 1.011484146118164,
	"step": 714
	},
	{
	"epoch": 1.9562841530054644,
	"grad_norm": 0.38927656412124634,
	"learning_rate": 9.19176129333734e-06,
	"loss": 0.6682248115539551,
	"step": 716
	},
	{
	"epoch": 1.9617486338797814,
	"grad_norm": 0.25566795468330383,
	"learning_rate": 9.129884932320593e-06,
	"loss": 0.9508749842643738,
	"step": 718
	},
	{
	"epoch": 1.9672131147540983,
	"grad_norm": 0.4887275993824005,
	"learning_rate": 9.0681762363754e-06,
	"loss": 1.0459179878234863,
	"step": 720
	},
	{
	"epoch": 1.9726775956284153,
	"grad_norm": 0.3566785454750061,
	"learning_rate": 9.006637444924973e-06,
	"loss": 0.9785248041152954,
	"step": 722
	},
	{
	"epoch": 1.9781420765027322,
	"grad_norm": 0.5626527667045593,
	"learning_rate": 8.945270791226646e-06,
	"loss": 0.945759117603302,
	"step": 724
	},
	{
	"epoch": 1.9836065573770492,
	"grad_norm": 5.221266269683838,
	"learning_rate": 8.884078502290838e-06,
	"loss": 0.9256299138069153,
	"step": 726
	},
	{
	"epoch": 1.989071038251366,
	"grad_norm": 0.2847398519515991,
	"learning_rate": 8.823062798800233e-06,
	"loss": 0.9720381498336792,
	"step": 728
	},
	{
	"epoch": 1.994535519125683,
	"grad_norm": 0.2270623743534088,
	"learning_rate": 8.762225895029169e-06,
	"loss": 0.8780955672264099,
	"step": 730
	},
	{
	"epoch": 2.0,
	"grad_norm": 0.18520908057689667,
	"learning_rate": 8.701569998763323e-06,
	"loss": 0.9250549674034119,
	"step": 732
	},
	{
	"epoch": 2.0054644808743167,
	"grad_norm": 0.17245544493198395,
	"learning_rate": 8.64109731121955e-06,
	"loss": 0.41599372029304504,
	"step": 734
	},
	{
	"epoch": 2.010928961748634,
	"grad_norm": 0.25467920303344727,
	"learning_rate": 8.580810026966034e-06,
	"loss": 0.7172941565513611,
	"step": 736
	},
	{
	"epoch": 2.0163934426229506,
	"grad_norm": 0.24227584898471832,
	"learning_rate": 8.520710333842605e-06,
	"loss": 0.747187614440918,
	"step": 738
	},
	{
	"epoch": 2.021857923497268,
	"grad_norm": 0.24147503077983856,
	"learning_rate": 8.460800412881386e-06,
	"loss": 0.6775767207145691,
	"step": 740
	},
	{
	"epoch": 2.0273224043715845,
	"grad_norm": 0.31402096152305603,
	"learning_rate": 8.401082438227617e-06,
	"loss": 0.402444452047348,
	"step": 742
	},
	{
	"epoch": 2.0327868852459017,
	"grad_norm": 0.42537474632263184,
	"learning_rate": 8.341558577060769e-06,
	"loss": 0.6484034657478333,
	"step": 744
	},
	{
	"epoch": 2.0382513661202184,
	"grad_norm": 0.3523010313510895,
	"learning_rate": 8.282230989515865e-06,
	"loss": 0.4699830114841461,
	"step": 746
	},
	{
	"epoch": 2.0437158469945356,
	"grad_norm": 0.5600184202194214,
	"learning_rate": 8.223101828605141e-06,
	"loss": 0.6734252572059631,
	"step": 748
	},
	{
	"epoch": 2.0491803278688523,
	"grad_norm": 0.15328167378902435,
	"learning_rate": 8.164173240139865e-06,
	"loss": 0.45088091492652893,
	"step": 750
	},
	{
	"epoch": 2.0546448087431695,
	"grad_norm": 0.6332978010177612,
	"learning_rate": 8.105447362652492e-06,
	"loss": 0.44899141788482666,
	"step": 752
	},
	{
	"epoch": 2.060109289617486,
	"grad_norm": 1.7822338342666626,
	"learning_rate": 8.046926327319037e-06,
	"loss": 0.5379037857055664,
	"step": 754
	},
	{
	"epoch": 2.0655737704918034,
	"grad_norm": 0.3468593657016754,
	"learning_rate": 7.988612257881757e-06,
	"loss": 0.6135660409927368,
	"step": 756
	},
	{
	"epoch": 2.07103825136612,
	"grad_norm": 0.4308558702468872,
	"learning_rate": 7.930507270572065e-06,
	"loss": 0.6905173659324646,
	"step": 758
	},
	{
	"epoch": 2.0765027322404372,
	"grad_norm": 0.214769646525383,
	"learning_rate": 7.872613474033722e-06,
	"loss": 0.6643854379653931,
	"step": 760
	},
	{
	"epoch": 2.081967213114754,
	"grad_norm": 0.2445564866065979,
	"learning_rate": 7.814932969246342e-06,
	"loss": 0.5414201021194458,
	"step": 762
	},
	{
	"epoch": 2.087431693989071,
	"grad_norm": 0.2596500515937805,
	"learning_rate": 7.75746784944912e-06,
	"loss": 0.6696488261222839,
	"step": 764
	},
	{
	"epoch": 2.092896174863388,
	"grad_norm": 0.30743348598480225,
	"learning_rate": 7.700220200064889e-06,
	"loss": 0.6852096319198608,
	"step": 766
	},
	{
	"epoch": 2.098360655737705,
	"grad_norm": 0.9081697463989258,
	"learning_rate": 7.643192098624413e-06,
	"loss": 0.665625810623169,
	"step": 768
	},
	{
	"epoch": 2.1038251366120218,
	"grad_norm": 0.2047584056854248,
	"learning_rate": 7.586385614691024e-06,
	"loss": 0.6999115943908691,
	"step": 770
	},
	{
	"epoch": 2.109289617486339,
	"grad_norm": 0.5113670229911804,
	"learning_rate": 7.529802809785497e-06,
	"loss": 0.6937403082847595,
	"step": 772
	},
	{
	"epoch": 2.1147540983606556,
	"grad_norm": 0.19943810999393463,
	"learning_rate": 7.473445737311244e-06,
	"loss": 0.7570751309394836,
	"step": 774
	},
	{
	"epoch": 2.120218579234973,
	"grad_norm": 0.24206914007663727,
	"learning_rate": 7.417316442479783e-06,
	"loss": 0.4566923677921295,
	"step": 776
	},
	{
	"epoch": 2.1256830601092895,
	"grad_norm": 0.5807485580444336,
	"learning_rate": 7.361416962236542e-06,
	"loss": 0.617829442024231,
	"step": 778
	},
	{
	"epoch": 2.1311475409836067,
	"grad_norm": 0.3329077959060669,
	"learning_rate": 7.305749325186914e-06,
	"loss": 0.6804491877555847,
	"step": 780
	},
	{
	"epoch": 2.1366120218579234,
	"grad_norm": 0.20504486560821533,
	"learning_rate": 7.2503155515226575e-06,
	"loss": 0.7602362632751465,
	"step": 782
	},
	{
	"epoch": 2.1420765027322406,
	"grad_norm": 0.1894470453262329,
	"learning_rate": 7.195117652948555e-06,
	"loss": 0.6853156089782715,
	"step": 784
	},
	{
	"epoch": 2.1475409836065573,
	"grad_norm": 0.11648036539554596,
	"learning_rate": 7.14015763260944e-06,
	"loss": 0.3979906439781189,
	"step": 786
	},
	{
	"epoch": 2.1530054644808745,
	"grad_norm": 1.0007914304733276,
	"learning_rate": 7.085437485017487e-06,
	"loss": 0.640531063079834,
	"step": 788
	},
	{
	"epoch": 2.158469945355191,
	"grad_norm": 0.1968093067407608,
	"learning_rate": 7.030959195979833e-06,
	"loss": 0.6763147115707397,
	"step": 790
	},
	{
	"epoch": 2.1639344262295084,
	"grad_norm": 0.2067585587501526,
	"learning_rate": 6.976724742526503e-06,
	"loss": 0.5175256729125977,
	"step": 792
	},
	{
	"epoch": 2.169398907103825,
	"grad_norm": 0.7652968764305115,
	"learning_rate": 6.92273609283868e-06,
	"loss": 0.4226246774196625,
	"step": 794
	},
	{
	"epoch": 2.1748633879781423,
	"grad_norm": 0.21701058745384216,
	"learning_rate": 6.868995206177264e-06,
	"loss": 0.6554322838783264,
	"step": 796
	},
	{
	"epoch": 2.180327868852459,
	"grad_norm": 1.6271648406982422,
	"learning_rate": 6.815504032811775e-06,
	"loss": 0.6646580100059509,
	"step": 798
	},
	{
	"epoch": 2.185792349726776,
	"grad_norm": 0.4442613422870636,
	"learning_rate": 6.7622645139495815e-06,
	"loss": 0.585219144821167,
	"step": 800
	},
	{
	"epoch": 2.191256830601093,
	"grad_norm": 0.23071300983428955,
	"learning_rate": 6.7092785816654515e-06,
	"loss": 0.6361981630325317,
	"step": 802
	},
	{
	"epoch": 2.19672131147541,
	"grad_norm": 0.15861168503761292,
	"learning_rate": 6.656548158831436e-06,
	"loss": 0.7302151322364807,
	"step": 804
	},
	{
	"epoch": 2.202185792349727,
	"grad_norm": 0.2113688737154007,
	"learning_rate": 6.6040751590470825e-06,
	"loss": 0.6704022884368896,
	"step": 806
	},
	{
	"epoch": 2.2076502732240435,
	"grad_norm": 0.13283978402614594,
	"learning_rate": 6.551861486569997e-06,
	"loss": 0.38798680901527405,
	"step": 808
	},
	{
	"epoch": 2.2131147540983607,
	"grad_norm": 0.23720614612102509,
	"learning_rate": 6.499909036246738e-06,
	"loss": 0.37715965509414673,
	"step": 810
	},
	{
	"epoch": 2.2185792349726774,
	"grad_norm": 0.23791414499282837,
	"learning_rate": 6.448219693444056e-06,
	"loss": 0.7323361039161682,
	"step": 812
	},
	{
	"epoch": 2.2240437158469946,
	"grad_norm": 0.24081940948963165,
	"learning_rate": 6.39679533398045e-06,
	"loss": 0.5640745759010315,
	"step": 814
	},
	{
	"epoch": 2.2295081967213113,
	"grad_norm": 0.3527999222278595,
	"learning_rate": 6.345637824058126e-06,
	"loss": 0.673088788986206,
	"step": 816
	},
	{
	"epoch": 2.2349726775956285,
	"grad_norm": 0.5025823712348938,
	"learning_rate": 6.294749020195253e-06,
	"loss": 0.6976668834686279,
	"step": 818
	},
	{
	"epoch": 2.240437158469945,
	"grad_norm": 0.2786237895488739,
	"learning_rate": 6.244130769158594e-06,
	"loss": 0.6512521505355835,
	"step": 820
	},
	{
	"epoch": 2.2459016393442623,
	"grad_norm": 1.141295313835144,
	"learning_rate": 6.193784907896478e-06,
	"loss": 0.6717444062232971,
	"step": 822
	},
	{
	"epoch": 2.251366120218579,
	"grad_norm": 0.32836222648620605,
	"learning_rate": 6.143713263472156e-06,
	"loss": 0.6926584839820862,
	"step": 824
	},
	{
	"epoch": 2.2568306010928962,
	"grad_norm": 0.4723096489906311,
	"learning_rate": 6.0939176529974765e-06,
	"loss": 0.46854105591773987,
	"step": 826
	},
	{
	"epoch": 2.262295081967213,
	"grad_norm": 0.2536696791648865,
	"learning_rate": 6.044399883566959e-06,
	"loss": 0.4778412878513336,
	"step": 828
	},
	{
	"epoch": 2.26775956284153,
	"grad_norm": 0.19949211180210114,
	"learning_rate": 5.995161752192192e-06,
	"loss": 0.7425835132598877,
	"step": 830
	},
	{
	"epoch": 2.273224043715847,
	"grad_norm": 0.6780716180801392,
	"learning_rate": 5.9462050457366446e-06,
	"loss": 0.3689644932746887,
	"step": 832
	},
	{
	"epoch": 2.278688524590164,
	"grad_norm": 0.22472506761550903,
	"learning_rate": 5.897531540850807e-06,
	"loss": 0.3652177155017853,
	"step": 834
	},
	{
	"epoch": 2.2841530054644807,
	"grad_norm": 0.26355841755867004,
	"learning_rate": 5.849143003907717e-06,
	"loss": 0.632552444934845,
	"step": 836
	},
	{
	"epoch": 2.289617486338798,
	"grad_norm": 0.6640907526016235,
	"learning_rate": 5.801041190938849e-06,
	"loss": 0.7073798775672913,
	"step": 838
	},
	{
	"epoch": 2.2950819672131146,
	"grad_norm": 0.2682071626186371,
	"learning_rate": 5.75322784757041e-06,
	"loss": 0.4572494328022003,
	"step": 840
	},
	{
	"epoch": 2.300546448087432,
	"grad_norm": 0.23095370829105377,
	"learning_rate": 5.705704708959968e-06,
	"loss": 0.7449085712432861,
	"step": 842
	},
	{
	"epoch": 2.3060109289617485,
	"grad_norm": 0.19461746513843536,
	"learning_rate": 5.658473499733499e-06,
	"loss": 0.6545416712760925,
	"step": 844
	},
	{
	"epoch": 2.3114754098360657,
	"grad_norm": 0.1823868453502655,
	"learning_rate": 5.611535933922781e-06,
	"loss": 0.29822948575019836,
	"step": 846
	},
	{
	"epoch": 2.3169398907103824,
	"grad_norm": 0.19124025106430054,
	"learning_rate": 5.564893714903211e-06,
	"loss": 0.7034991383552551,
	"step": 848
	},
	{
	"epoch": 2.3224043715846996,
	"grad_norm": 0.19907920062541962,
	"learning_rate": 5.518548535331984e-06,
	"loss": 0.6916401386260986,
	"step": 850
	},
	{
	"epoch": 2.3278688524590163,
	"grad_norm": 0.3887382447719574,
	"learning_rate": 5.472502077086653e-06,
	"loss": 0.6322124004364014,
	"step": 852
	},
	{
	"epoch": 2.3333333333333335,
	"grad_norm": 0.23771852254867554,
	"learning_rate": 5.426756011204108e-06,
	"loss": 0.6052520871162415,
	"step": 854
	},
	{
	"epoch": 2.33879781420765,
	"grad_norm": 0.14829999208450317,
	"learning_rate": 5.381311997819933e-06,
	"loss": 0.7813782691955566,
	"step": 856
	},
	{
	"epoch": 2.3442622950819674,
	"grad_norm": 0.26474112272262573,
	"learning_rate": 5.336171686108153e-06,
	"loss": 0.5027655959129333,
	"step": 858
	},
	{
	"epoch": 2.349726775956284,
	"grad_norm": 0.2717822194099426,
	"learning_rate": 5.291336714221382e-06,
	"loss": 0.7000398635864258,
	"step": 860
	},
	{
	"epoch": 2.3551912568306013,
	"grad_norm": 0.24665828049182892,
	"learning_rate": 5.246808709231382e-06,
	"loss": 0.7338890433311462,
	"step": 862
	},
	{
	"epoch": 2.360655737704918,
	"grad_norm": 1.1350178718566895,
	"learning_rate": 5.202589287070019e-06,
	"loss": 0.5282155275344849,
	"step": 864
	},
	{
	"epoch": 2.366120218579235,
	"grad_norm": 1.0712934732437134,
	"learning_rate": 5.158680052470609e-06,
	"loss": 0.5917450785636902,
	"step": 866
	},
	{
	"epoch": 2.371584699453552,
	"grad_norm": 0.17483752965927124,
	"learning_rate": 5.115082598909689e-06,
	"loss": 0.7042443156242371,
	"step": 868
	},
	{
	"epoch": 2.3770491803278686,
	"grad_norm": 0.24676814675331116,
	"learning_rate": 5.071798508549189e-06,
	"loss": 0.715234100818634,
	"step": 870
	},
	{
	"epoch": 2.3825136612021858,
	"grad_norm": 0.22551953792572021,
	"learning_rate": 5.028829352179017e-06,
	"loss": 0.804095983505249,
	"step": 872
	},
	{
	"epoch": 2.387978142076503,
	"grad_norm": 0.18146005272865295,
	"learning_rate": 4.986176689160042e-06,
	"loss": 0.7026334404945374,
	"step": 874
	},
	{
	"epoch": 2.3934426229508197,
	"grad_norm": 0.5449501872062683,
	"learning_rate": 4.943842067367525e-06,
	"loss": 0.49338310956954956,
	"step": 876
	},
	{
	"epoch": 2.3989071038251364,
	"grad_norm": 0.1813872754573822,
	"learning_rate": 4.901827023134931e-06,
	"loss": 0.7016088366508484,
	"step": 878
	},
	{
	"epoch": 2.4043715846994536,
	"grad_norm": 0.15302123129367828,
	"learning_rate": 4.86013308119818e-06,
	"loss": 0.6298723816871643,
	"step": 880
	},
	{
	"epoch": 2.4098360655737707,
	"grad_norm": 0.18854597210884094,
	"learning_rate": 4.818761754640316e-06,
	"loss": 0.43687549233436584,
	"step": 882
	},
	{
	"epoch": 2.4153005464480874,
	"grad_norm": 0.22853216528892517,
	"learning_rate": 4.777714544836585e-06,
	"loss": 0.7133804559707642,
	"step": 884
	},
	{
	"epoch": 2.420765027322404,
	"grad_norm": 0.19461189210414886,
	"learning_rate": 4.736992941399972e-06,
	"loss": 0.7002368569374084,
	"step": 886
	},
	{
	"epoch": 2.4262295081967213,
	"grad_norm": 0.2936843931674957,
	"learning_rate": 4.696598422127119e-06,
	"loss": 0.3858260214328766,
	"step": 888
	},
	{
	"epoch": 2.431693989071038,
	"grad_norm": 0.25543907284736633,
	"learning_rate": 4.656532452944716e-06,
	"loss": 0.449078232049942,
	"step": 890
	},
	{
	"epoch": 2.4371584699453552,
	"grad_norm": 0.46111661195755005,
	"learning_rate": 4.616796487856282e-06,
	"loss": 0.641425371170044,
	"step": 892
	},
	{
	"epoch": 2.442622950819672,
	"grad_norm": 0.1983172744512558,
	"learning_rate": 4.577391968889416e-06,
	"loss": 0.3780648708343506,
	"step": 894
	},
	{
	"epoch": 2.448087431693989,
	"grad_norm": 0.28097936511039734,
	"learning_rate": 4.53832032604346e-06,
	"loss": 0.6762884259223938,
	"step": 896
	},
	{
	"epoch": 2.453551912568306,
	"grad_norm": 0.234109029173851,
	"learning_rate": 4.499582977237594e-06,
	"loss": 0.7201648950576782,
	"step": 898
	},
	{
	"epoch": 2.459016393442623,
	"grad_norm": 0.18416042625904083,
	"learning_rate": 4.461181328259397e-06,
	"loss": 0.6271026134490967,
	"step": 900
	},
	{
	"epoch": 2.4644808743169397,
	"grad_norm": 0.17045891284942627,
	"learning_rate": 4.423116772713817e-06,
	"loss": 0.7007759809494019,
	"step": 902
	},
	{
	"epoch": 2.469945355191257,
	"grad_norm": 0.1790081411600113,
	"learning_rate": 4.3853906919726045e-06,
	"loss": 0.710627019405365,
	"step": 904
	},
	{
	"epoch": 2.4754098360655736,
	"grad_norm": 0.8877317309379578,
	"learning_rate": 4.348004455124173e-06,
	"loss": 0.4587891399860382,
	"step": 906
	},
	{
	"epoch": 2.480874316939891,
	"grad_norm": 0.07845756411552429,
	"learning_rate": 4.310959418923926e-06,
	"loss": 0.13992244005203247,
	"step": 908
	},
	{
	"epoch": 2.4863387978142075,
	"grad_norm": 0.10895147174596786,
	"learning_rate": 4.274256927745015e-06,
	"loss": 0.49745655059814453,
	"step": 910
	},
	{
	"epoch": 2.4918032786885247,
	"grad_norm": 0.1617729514837265,
	"learning_rate": 4.23789831352955e-06,
	"loss": 0.4288228750228882,
	"step": 912
	},
	{
	"epoch": 2.4972677595628414,
	"grad_norm": 0.21319684386253357,
	"learning_rate": 4.2018848957402605e-06,
	"loss": 0.6953483819961548,
	"step": 914
	},
	{
	"epoch": 2.5027322404371586,
	"grad_norm": 0.2012702375650406,
	"learning_rate": 4.166217981312621e-06,
	"loss": 0.5614168047904968,
	"step": 916
	},
	{
	"epoch": 2.5081967213114753,
	"grad_norm": 0.20277954638004303,
	"learning_rate": 4.130898864607417e-06,
	"loss": 0.6851552724838257,
	"step": 918
	},
	{
	"epoch": 2.5136612021857925,
	"grad_norm": 0.2765226662158966,
	"learning_rate": 4.09592882736377e-06,
	"loss": 0.6657923460006714,
	"step": 920
	},
	{
	"epoch": 2.519125683060109,
	"grad_norm": 0.4667165279388428,
	"learning_rate": 4.061309138652622e-06,
	"loss": 0.7339661717414856,
	"step": 922
	},
	{
	"epoch": 2.5245901639344264,
	"grad_norm": 0.16822604835033417,
	"learning_rate": 4.027041054830689e-06,
	"loss": 0.6094578504562378,
	"step": 924
	},
	{
	"epoch": 2.530054644808743,
	"grad_norm": 0.14607980847358704,
	"learning_rate": 3.993125819494862e-06,
	"loss": 0.34630584716796875,
	"step": 926
	},
	{
	"epoch": 2.5355191256830603,
	"grad_norm": 0.15208321809768677,
	"learning_rate": 3.9595646634370745e-06,
	"loss": 0.4717685878276825,
	"step": 928
	},
	{
	"epoch": 2.540983606557377,
	"grad_norm": 0.2327331304550171,
	"learning_rate": 3.926358804599636e-06,
	"loss": 0.6192865371704102,
	"step": 930
	},
	{
	"epoch": 2.546448087431694,
	"grad_norm": 0.757671594619751,
	"learning_rate": 3.8935094480310425e-06,
	"loss": 0.5656976103782654,
	"step": 932
	},
	{
	"epoch": 2.551912568306011,
	"grad_norm": 0.22793398797512054,
	"learning_rate": 3.861017785842234e-06,
	"loss": 0.7342063188552856,
	"step": 934
	},
	{
	"epoch": 2.557377049180328,
	"grad_norm": 0.9295087456703186,
	"learning_rate": 3.828884997163339e-06,
	"loss": 0.5990333557128906,
	"step": 936
	},
	{
	"epoch": 2.5628415300546448,
	"grad_norm": 2.140310764312744,
	"learning_rate": 3.7971122481008757e-06,
	"loss": 0.5494145154953003,
	"step": 938
	},
	{
	"epoch": 2.5683060109289615,
	"grad_norm": 0.28645941615104675,
	"learning_rate": 3.7657006916954453e-06,
	"loss": 0.6415644288063049,
	"step": 940
	},
	{
	"epoch": 2.5737704918032787,
	"grad_norm": 0.38164955377578735,
	"learning_rate": 3.734651467879878e-06,
	"loss": 0.43504810333251953,
	"step": 942
	},
	{
	"epoch": 2.579234972677596,
	"grad_norm": 0.34789642691612244,
	"learning_rate": 3.7039657034378726e-06,
	"loss": 0.6228368282318115,
	"step": 944
	},
	{
	"epoch": 2.5846994535519126,
	"grad_norm": 0.07762913405895233,
	"learning_rate": 3.6736445119630964e-06,
	"loss": 0.16022926568984985,
	"step": 946
	},
	{
	"epoch": 2.5901639344262293,
	"grad_norm": 0.28069254755973816,
	"learning_rate": 3.6436889938187833e-06,
	"loss": 0.6584885716438293,
	"step": 948
	},
	{
	"epoch": 2.5956284153005464,
	"grad_norm": 0.24518746137619019,
	"learning_rate": 3.6141002360977864e-06,
	"loss": 0.43174296617507935,
	"step": 950
	},
	{
	"epoch": 2.6010928961748636,
	"grad_norm": 0.39224839210510254,
	"learning_rate": 3.584879312583141e-06,
	"loss": 0.5712751746177673,
	"step": 952
	},
	{
	"epoch": 2.6065573770491803,
	"grad_norm": 0.24317054450511932,
	"learning_rate": 3.5560272837090935e-06,
	"loss": 0.37820327281951904,
	"step": 954
	},
	{
	"epoch": 2.612021857923497,
	"grad_norm": 0.15435853600502014,
	"learning_rate": 3.527545196522615e-06,
	"loss": 0.17984823882579803,
	"step": 956
	},
	{
	"epoch": 2.6174863387978142,
	"grad_norm": 0.32159680128097534,
	"learning_rate": 3.499434084645407e-06,
	"loss": 0.4029221534729004,
	"step": 958
	},
	{
	"epoch": 2.6229508196721314,
	"grad_norm": 0.3094979226589203,
	"learning_rate": 3.4716949682363803e-06,
	"loss": 0.739897608757019,
	"step": 960
	},
	{
	"epoch": 2.628415300546448,
	"grad_norm": 0.425645112991333,
	"learning_rate": 3.4443288539546508e-06,
	"loss": 0.4608995020389557,
	"step": 962
	},
	{
	"epoch": 2.633879781420765,
	"grad_norm": 0.22378240525722504,
	"learning_rate": 3.417336734922998e-06,
	"loss": 0.6960005760192871,
	"step": 964
	},
	{
	"epoch": 2.639344262295082,
	"grad_norm": 0.18555636703968048,
	"learning_rate": 3.3907195906918236e-06,
	"loss": 0.7077355980873108,
	"step": 966
	},
	{
	"epoch": 2.644808743169399,
	"grad_norm": 0.2145896553993225,
	"learning_rate": 3.364478387203602e-06,
	"loss": 0.5513492226600647,
	"step": 968
	},
	{
	"epoch": 2.650273224043716,
	"grad_norm": 0.7693909406661987,
	"learning_rate": 3.338614076757832e-06,
	"loss": 0.5141048431396484,
	"step": 970
	},
	{
	"epoch": 2.6557377049180326,
	"grad_norm": 0.3477981388568878,
	"learning_rate": 3.3131275979764746e-06,
	"loss": 0.6895625591278076,
	"step": 972
	},
	{
	"epoch": 2.66120218579235,
	"grad_norm": 0.19012540578842163,
	"learning_rate": 3.288019875769889e-06,
	"loss": 0.39245468378067017,
	"step": 974
	},
	{
	"epoch": 2.6666666666666665,
	"grad_norm": 0.24051906168460846,
	"learning_rate": 3.2632918213032687e-06,
	"loss": 0.6571274995803833,
	"step": 976
	},
	{
	"epoch": 2.6721311475409837,
	"grad_norm": 0.14302131533622742,
	"learning_rate": 3.2389443319635762e-06,
	"loss": 0.6791136860847473,
	"step": 978
	},
	{
	"epoch": 2.6775956284153004,
	"grad_norm": 0.21270255744457245,
	"learning_rate": 3.2149782913269715e-06,
	"loss": 0.7463234066963196,
	"step": 980
	},
	{
	"epoch": 2.6830601092896176,
	"grad_norm": 0.20450647175312042,
	"learning_rate": 3.1913945691267574e-06,
	"loss": 0.46346530318260193,
	"step": 982
	},
	{
	"epoch": 2.6885245901639343,
	"grad_norm": 0.18693040311336517,
	"learning_rate": 3.1681940212218013e-06,
	"loss": 0.3435611426830292,
	"step": 984
	},
	{
	"epoch": 2.6939890710382515,
	"grad_norm": 0.20872755348682404,
	"learning_rate": 3.145377489565492e-06,
	"loss": 0.6869267225265503,
	"step": 986
	},
	{
	"epoch": 2.699453551912568,
	"grad_norm": 0.19473455846309662,
	"learning_rate": 3.1229458021751754e-06,
	"loss": 0.7176718711853027,
	"step": 988
	},
	{
	"epoch": 2.7049180327868854,
	"grad_norm": 0.17841266095638275,
	"learning_rate": 3.100899773102103e-06,
	"loss": 0.618594229221344,
	"step": 990
	},
	{
	"epoch": 2.710382513661202,
	"grad_norm": 0.19311846792697906,
	"learning_rate": 3.0792402024019028e-06,
	"loss": 0.34453269839286804,
	"step": 992
	},
	{
	"epoch": 2.7158469945355193,
	"grad_norm": 0.22827599942684174,
	"learning_rate": 3.0579678761055294e-06,
	"loss": 0.6793984770774841,
	"step": 994
	},
	{
	"epoch": 2.721311475409836,
	"grad_norm": 0.1737447828054428,
	"learning_rate": 3.0370835661907522e-06,
	"loss": 0.7369482517242432,
	"step": 996
	},
	{
	"epoch": 2.726775956284153,
	"grad_norm": 0.17720820009708405,
	"learning_rate": 3.016588030554128e-06,
	"loss": 0.6935803294181824,
	"step": 998
	},
	{
	"epoch": 2.73224043715847,
	"grad_norm": 0.650160551071167,
	"learning_rate": 2.996482012983508e-06,
	"loss": 0.5621395707130432,
	"step": 1000
	},
	{
	"epoch": 2.737704918032787,
	"grad_norm": 0.23146776854991913,
	"learning_rate": 2.9767662431310373e-06,
	"loss": 0.6701301336288452,
	"step": 1002
	},
	{
	"epoch": 2.7431693989071038,
	"grad_norm": 0.45669713616371155,
	"learning_rate": 2.957441436486682e-06,
	"loss": 0.7368155121803284,
	"step": 1004
	},
	{
	"epoch": 2.748633879781421,
	"grad_norm": 0.2950546145439148,
	"learning_rate": 2.9385082943522553e-06,
	"loss": 0.2910221815109253,
	"step": 1006
	},
	{
	"epoch": 2.7540983606557377,
	"grad_norm": 0.19097362458705902,
	"learning_rate": 2.9199675038159764e-06,
	"loss": 0.7412728667259216,
	"step": 1008
	},
	{
	"epoch": 2.7595628415300544,
	"grad_norm": 0.24510665237903595,
	"learning_rate": 2.9018197377275334e-06,
	"loss": 0.6697684526443481,
	"step": 1010
	},
	{
	"epoch": 2.7650273224043715,
	"grad_norm": 0.14479011297225952,
	"learning_rate": 2.8840656546736607e-06,
	"loss": 0.5396718978881836,
	"step": 1012
	},
	{
	"epoch": 2.7704918032786887,
	"grad_norm": 0.23086193203926086,
	"learning_rate": 2.866705898954241e-06,
	"loss": 0.6256304383277893,
	"step": 1014
	},
	{
	"epoch": 2.7759562841530054,
	"grad_norm": 0.29304757714271545,
	"learning_rate": 2.8497411005589283e-06,
	"loss": 0.6394587755203247,
	"step": 1016
	},
	{
	"epoch": 2.781420765027322,
	"grad_norm": 0.3104848265647888,
	"learning_rate": 2.8331718751442793e-06,
	"loss": 0.6255086064338684,
	"step": 1018
	},
	{
	"epoch": 2.7868852459016393,
	"grad_norm": 0.14495858550071716,
	"learning_rate": 2.8169988240114145e-06,
	"loss": 0.40636876225471497,
	"step": 1020
	},
	{
	"epoch": 2.7923497267759565,
	"grad_norm": 0.29641368985176086,
	"learning_rate": 2.801222534084196e-06,
	"loss": 0.6926835179328918,
	"step": 1022
	},
	{
	"epoch": 2.797814207650273,
	"grad_norm": 0.2795805037021637,
	"learning_rate": 2.785843577887926e-06,
	"loss": 0.3881547749042511,
	"step": 1024
	},
	{
	"epoch": 2.80327868852459,
	"grad_norm": 0.45699605345726013,
	"learning_rate": 2.7708625135285717e-06,
	"loss": 0.7579897046089172,
	"step": 1026
	},
	{
	"epoch": 2.808743169398907,
	"grad_norm": 1.0389068126678467,
	"learning_rate": 2.7562798846725133e-06,
	"loss": 0.2406935691833496,
	"step": 1028
	},
	{
	"epoch": 2.8142076502732243,
	"grad_norm": 0.3375071585178375,
	"learning_rate": 2.742096220526808e-06,
	"loss": 0.686618447303772,
	"step": 1030
	},
	{
	"epoch": 2.819672131147541,
	"grad_norm": 0.18238572776317596,
	"learning_rate": 2.728312035819995e-06,
	"loss": 0.667717695236206,
	"step": 1032
	},
	{
	"epoch": 2.8251366120218577,
	"grad_norm": 0.49168893694877625,
	"learning_rate": 2.7149278307834047e-06,
	"loss": 0.5261977910995483,
	"step": 1034
	},
	{
	"epoch": 2.830601092896175,
	"grad_norm": 0.24831274151802063,
	"learning_rate": 2.701944091133011e-06,
	"loss": 0.7198750972747803,
	"step": 1036
	},
	{
	"epoch": 2.836065573770492,
	"grad_norm": 0.22962301969528198,
	"learning_rate": 2.6893612880518064e-06,
	"loss": 0.737044095993042,
	"step": 1038
	},
	{
	"epoch": 2.841530054644809,
	"grad_norm": 0.19474509358406067,
	"learning_rate": 2.677179878172699e-06,
	"loss": 0.7108073830604553,
	"step": 1040
	},
	{
	"epoch": 2.8469945355191255,
	"grad_norm": 0.20618607103824615,
	"learning_rate": 2.6654003035619427e-06,
	"loss": 0.6671370267868042,
	"step": 1042
	},
	{
	"epoch": 2.8524590163934427,
	"grad_norm": 0.1941603571176529,
	"learning_rate": 2.654022991703093e-06,
	"loss": 0.5263208746910095,
	"step": 1044
	},
	{
	"epoch": 2.8579234972677594,
	"grad_norm": 0.4619889259338379,
	"learning_rate": 2.6430483554814956e-06,
	"loss": 0.6518206596374512,
	"step": 1046
	},
	{
	"epoch": 2.8633879781420766,
	"grad_norm": 0.21917857229709625,
	"learning_rate": 2.632476793169303e-06,
	"loss": 0.3260215222835541,
	"step": 1048
	},
	{
	"epoch": 2.8688524590163933,
	"grad_norm": 0.17283010482788086,
	"learning_rate": 2.622308688411019e-06,
	"loss": 0.6257282495498657,
	"step": 1050
	},
	{
	"epoch": 2.8743169398907105,
	"grad_norm": 0.23165258765220642,
	"learning_rate": 2.612544410209574e-06,
	"loss": 0.6545224189758301,
	"step": 1052
	},
	{
	"epoch": 2.879781420765027,
	"grad_norm": 0.2500731945037842,
	"learning_rate": 2.6031843129129425e-06,
	"loss": 0.6312705278396606,
	"step": 1054
	},
	{
	"epoch": 2.8852459016393444,
	"grad_norm": 0.7894412875175476,
	"learning_rate": 2.594228736201274e-06,
	"loss": 0.6379542946815491,
	"step": 1056
	},
	{
	"epoch": 2.890710382513661,
	"grad_norm": 1.0066219568252563,
	"learning_rate": 2.5856780050745726e-06,
	"loss": 0.44013917446136475,
	"step": 1058
	},
	{
	"epoch": 2.8961748633879782,
	"grad_norm": 0.7618535757064819,
	"learning_rate": 2.577532429840896e-06,
	"loss": 0.6751360297203064,
	"step": 1060
	},
	{
	"epoch": 2.901639344262295,
	"grad_norm": 0.2618259787559509,
	"learning_rate": 2.5697923061051056e-06,
	"loss": 0.7184084057807922,
	"step": 1062
	},
	{
	"epoch": 2.907103825136612,
	"grad_norm": 0.17739877104759216,
	"learning_rate": 2.5624579147581233e-06,
	"loss": 0.8313037753105164,
	"step": 1064
	},
	{
	"epoch": 2.912568306010929,
	"grad_norm": 0.09571345150470734,
	"learning_rate": 2.555529521966754e-06,
	"loss": 0.3473111391067505,
	"step": 1066
	},
	{
	"epoch": 2.918032786885246,
	"grad_norm": 0.21488875150680542,
	"learning_rate": 2.5490073791640125e-06,
	"loss": 0.45797085762023926,
	"step": 1068
	},
	{
	"epoch": 2.9234972677595628,
	"grad_norm": 0.27381402254104614,
	"learning_rate": 2.542891723040009e-06,
	"loss": 0.5820063948631287,
	"step": 1070
	},
	{
	"epoch": 2.92896174863388,
	"grad_norm": 0.19229131937026978,
	"learning_rate": 2.5371827755333562e-06,
	"loss": 0.7217463254928589,
	"step": 1072
	},
	{
	"epoch": 2.9344262295081966,
	"grad_norm": 0.21169181168079376,
	"learning_rate": 2.5318807438231114e-06,
	"loss": 0.35460832715034485,
	"step": 1074
	},
	{
	"epoch": 2.939890710382514,
	"grad_norm": 0.20496554672718048,
	"learning_rate": 2.5269858203212634e-06,
	"loss": 0.3624781668186188,
	"step": 1076
	},
	{
	"epoch": 2.9453551912568305,
	"grad_norm": 0.267284095287323,
	"learning_rate": 2.522498182665746e-06,
	"loss": 0.4492642879486084,
	"step": 1078
	},
	{
	"epoch": 2.9508196721311473,
	"grad_norm": 0.286236971616745,
	"learning_rate": 2.5184179937139957e-06,
	"loss": 0.6190025210380554,
	"step": 1080
	},
	{
	"epoch": 2.9562841530054644,
	"grad_norm": 0.2303326278924942,
	"learning_rate": 2.5147454015370368e-06,
	"loss": 0.5356917977333069,
	"step": 1082
	},
	{
	"epoch": 2.9617486338797816,
	"grad_norm": 0.1802782416343689,
	"learning_rate": 2.511480539414109e-06,
	"loss": 0.6177518367767334,
	"step": 1084
	},
	{
	"epoch": 2.9672131147540983,
	"grad_norm": 0.15038588643074036,
	"learning_rate": 2.508623525827835e-06,
	"loss": 0.32314690947532654,
	"step": 1086
	},
	{
	"epoch": 2.972677595628415,
	"grad_norm": 0.20698142051696777,
	"learning_rate": 2.5061744644599134e-06,
	"loss": 0.6555347442626953,
	"step": 1088
	},
	{
	"epoch": 2.978142076502732,
	"grad_norm": 0.1626245528459549,
	"learning_rate": 2.504133444187364e-06,
	"loss": 0.5033056139945984,
	"step": 1090
	},
	{
	"epoch": 2.9836065573770494,
	"grad_norm": 0.20192566514015198,
	"learning_rate": 2.5025005390792964e-06,
	"loss": 0.6249701380729675,
	"step": 1092
	},
	{
	"epoch": 2.989071038251366,
	"grad_norm": 0.17979055643081665,
	"learning_rate": 2.5012758083942227e-06,
	"loss": 0.5733636021614075,
	"step": 1094
	},
	{
	"epoch": 2.994535519125683,
	"grad_norm": 0.41940733790397644,
	"learning_rate": 2.500459296577912e-06,
	"loss": 0.4294215440750122,
	"step": 1096
	},
	{
	"epoch": 3.0,
	"grad_norm": 0.2482825517654419,
	"learning_rate": 2.5000510332617706e-06,
	"loss": 0.6288962364196777,
	"step": 1098
	},
	{
	"epoch": 3.0,
	"step": 1098,
	"total_flos": 4.931331991116186e+18,
	"train_loss": 0.9040751279160407,
	"train_runtime": 12420.2984,
	"train_samples_per_second": 5.304,
	"train_steps_per_second": 0.088
	}
	],
	"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": 4.931331991116186e+18,
	"train_batch_size": 3,
	"trial_name": null,
	"trial_params": null
	}