Instructions to use roonbug/afsck72p with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use roonbug/afsck72p with Transformers:

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

pipe = pipeline("image-text-to-text", model="roonbug/afsck72p")
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("roonbug/afsck72p")
model = AutoModelForImageTextToText.from_pretrained("roonbug/afsck72p")
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 roonbug/afsck72p with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roonbug/afsck72p"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "roonbug/afsck72p",
		"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/roonbug/afsck72p

SGLang

How to use roonbug/afsck72p 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 "roonbug/afsck72p" \
    --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": "roonbug/afsck72p",
		"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 "roonbug/afsck72p" \
        --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": "roonbug/afsck72p",
		"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 roonbug/afsck72p with Docker Model Runner:
```
docker model run hf.co/roonbug/afsck72p
```

afsck72p / checkpoint-3000 /trainer_state.json

roonbug

Upload folder using huggingface_hub

75048d6 verified about 1 month ago

raw

history blame contribute delete

103 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 1.2,
	"eval_steps": 100,
	"global_step": 3000,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"entropy": 0.3589675037190318,
	"epoch": 0.004,
	"grad_norm": 221.0,
	"learning_rate": 1.8e-07,
	"loss": 14.235,
	"mean_token_accuracy": 0.8023731399327516,
	"num_tokens": 89176.0,
	"step": 10
	},
	{
	"entropy": 0.381451623653993,
	"epoch": 0.008,
	"grad_norm": 251.0,
	"learning_rate": 3.8e-07,
	"loss": 16.438,
	"mean_token_accuracy": 0.7818928115069866,
	"num_tokens": 173886.0,
	"step": 20
	},
	{
	"entropy": 0.36998924349900336,
	"epoch": 0.012,
	"grad_norm": 284.0,
	"learning_rate": 5.800000000000001e-07,
	"loss": 15.3069,
	"mean_token_accuracy": 0.7961655277758837,
	"num_tokens": 258970.0,
	"step": 30
	},
	{
	"entropy": 0.3889644297771156,
	"epoch": 0.016,
	"grad_norm": 296.0,
	"learning_rate": 7.8e-07,
	"loss": 15.6587,
	"mean_token_accuracy": 0.7874974697828293,
	"num_tokens": 338352.0,
	"step": 40
	},
	{
	"entropy": 0.3830348197836429,
	"epoch": 0.02,
	"grad_norm": 330.0,
	"learning_rate": 9.800000000000001e-07,
	"loss": 15.0754,
	"mean_token_accuracy": 0.7973605334758759,
	"num_tokens": 424243.0,
	"step": 50
	},
	{
	"entropy": 0.40132593517191706,
	"epoch": 0.024,
	"grad_norm": 284.0,
	"learning_rate": 1.1800000000000001e-06,
	"loss": 15.9374,
	"mean_token_accuracy": 0.7853362146764994,
	"num_tokens": 505613.0,
	"step": 60
	},
	{
	"entropy": 0.41173397554084656,
	"epoch": 0.028,
	"grad_norm": 201.0,
	"learning_rate": 1.3800000000000001e-06,
	"loss": 15.1473,
	"mean_token_accuracy": 0.7896888509392739,
	"num_tokens": 584157.0,
	"step": 70
	},
	{
	"entropy": 0.4223371436353773,
	"epoch": 0.032,
	"grad_norm": 164.0,
	"learning_rate": 1.5800000000000001e-06,
	"loss": 13.7069,
	"mean_token_accuracy": 0.8018626874312759,
	"num_tokens": 671193.0,
	"step": 80
	},
	{
	"entropy": 0.4982604907825589,
	"epoch": 0.036,
	"grad_norm": 240.0,
	"learning_rate": 1.7800000000000001e-06,
	"loss": 14.6572,
	"mean_token_accuracy": 0.7824514407664538,
	"num_tokens": 753947.0,
	"step": 90
	},
	{
	"entropy": 0.4913600580766797,
	"epoch": 0.04,
	"grad_norm": 155.0,
	"learning_rate": 1.98e-06,
	"loss": 13.0149,
	"mean_token_accuracy": 0.8003234412521124,
	"num_tokens": 835868.0,
	"step": 100
	},
	{
	"epoch": 0.04,
	"eval_chemistry_entropy": 0.41473443768918516,
	"eval_chemistry_loss": 0.7713431119918823,
	"eval_chemistry_mean_token_accuracy": 0.8103395719528198,
	"eval_chemistry_num_tokens": 835868.0,
	"eval_chemistry_runtime": 53.7203,
	"eval_chemistry_samples_per_second": 9.307,
	"eval_chemistry_steps_per_second": 9.307,
	"step": 100
	},
	{
	"epoch": 0.04,
	"eval_physics_entropy": 0.5291771245449781,
	"eval_physics_loss": 0.8209348917007446,
	"eval_physics_mean_token_accuracy": 0.7944456633925437,
	"eval_physics_num_tokens": 835868.0,
	"eval_physics_runtime": 62.4292,
	"eval_physics_samples_per_second": 8.009,
	"eval_physics_steps_per_second": 8.009,
	"step": 100
	},
	{
	"entropy": 0.5052730706520379,
	"epoch": 0.044,
	"grad_norm": 132.0,
	"learning_rate": 2.1800000000000003e-06,
	"loss": 11.9999,
	"mean_token_accuracy": 0.807476469874382,
	"num_tokens": 917534.0,
	"step": 110
	},
	{
	"entropy": 0.5510593980550766,
	"epoch": 0.048,
	"grad_norm": 100.5,
	"learning_rate": 2.38e-06,
	"loss": 11.8438,
	"mean_token_accuracy": 0.8063667319715023,
	"num_tokens": 1001008.0,
	"step": 120
	},
	{
	"entropy": 0.59730707956478,
	"epoch": 0.052,
	"grad_norm": 87.5,
	"learning_rate": 2.5800000000000003e-06,
	"loss": 11.8941,
	"mean_token_accuracy": 0.8023553561419249,
	"num_tokens": 1085098.0,
	"step": 130
	},
	{
	"entropy": 0.6581894762814045,
	"epoch": 0.056,
	"grad_norm": 102.0,
	"learning_rate": 2.7800000000000005e-06,
	"loss": 12.6245,
	"mean_token_accuracy": 0.7945734079927206,
	"num_tokens": 1166615.0,
	"step": 140
	},
	{
	"entropy": 0.6519844191148877,
	"epoch": 0.06,
	"grad_norm": 70.5,
	"learning_rate": 2.9800000000000003e-06,
	"loss": 11.5194,
	"mean_token_accuracy": 0.8026637583971024,
	"num_tokens": 1248387.0,
	"step": 150
	},
	{
	"entropy": 0.7085968372412026,
	"epoch": 0.064,
	"grad_norm": 72.0,
	"learning_rate": 3.1800000000000005e-06,
	"loss": 12.4073,
	"mean_token_accuracy": 0.7906260795891284,
	"num_tokens": 1331208.0,
	"step": 160
	},
	{
	"entropy": 0.6624301395379006,
	"epoch": 0.068,
	"grad_norm": 66.5,
	"learning_rate": 3.3800000000000007e-06,
	"loss": 11.3744,
	"mean_token_accuracy": 0.8067036394029856,
	"num_tokens": 1416841.0,
	"step": 170
	},
	{
	"entropy": 0.664617495983839,
	"epoch": 0.072,
	"grad_norm": 70.5,
	"learning_rate": 3.58e-06,
	"loss": 11.3264,
	"mean_token_accuracy": 0.8068108163774014,
	"num_tokens": 1499449.0,
	"step": 180
	},
	{
	"entropy": 0.6721668383106589,
	"epoch": 0.076,
	"grad_norm": 70.5,
	"learning_rate": 3.7800000000000002e-06,
	"loss": 11.2874,
	"mean_token_accuracy": 0.8029039859771728,
	"num_tokens": 1585982.0,
	"step": 190
	},
	{
	"entropy": 0.6800463449209928,
	"epoch": 0.08,
	"grad_norm": 58.5,
	"learning_rate": 3.980000000000001e-06,
	"loss": 11.4959,
	"mean_token_accuracy": 0.8001787267625332,
	"num_tokens": 1667532.0,
	"step": 200
	},
	{
	"epoch": 0.08,
	"eval_chemistry_entropy": 0.579608644425869,
	"eval_chemistry_loss": 0.6572756171226501,
	"eval_chemistry_mean_token_accuracy": 0.8160659775733948,
	"eval_chemistry_num_tokens": 1667532.0,
	"eval_chemistry_runtime": 53.9736,
	"eval_chemistry_samples_per_second": 9.264,
	"eval_chemistry_steps_per_second": 9.264,
	"step": 200
	},
	{
	"epoch": 0.08,
	"eval_physics_entropy": 0.6811966061294079,
	"eval_physics_loss": 0.714818000793457,
	"eval_physics_mean_token_accuracy": 0.8037424722313881,
	"eval_physics_num_tokens": 1667532.0,
	"eval_physics_runtime": 62.6745,
	"eval_physics_samples_per_second": 7.978,
	"eval_physics_steps_per_second": 7.978,
	"step": 200
	},
	{
	"entropy": 0.6441303874365986,
	"epoch": 0.084,
	"grad_norm": 65.5,
	"learning_rate": 4.18e-06,
	"loss": 10.9679,
	"mean_token_accuracy": 0.8105842903256416,
	"num_tokens": 1750813.0,
	"step": 210
	},
	{
	"entropy": 0.7001293174922466,
	"epoch": 0.088,
	"grad_norm": 63.5,
	"learning_rate": 4.38e-06,
	"loss": 11.3739,
	"mean_token_accuracy": 0.8039855100214481,
	"num_tokens": 1835489.0,
	"step": 220
	},
	{
	"entropy": 0.7212686208076775,
	"epoch": 0.092,
	"grad_norm": 68.5,
	"learning_rate": 4.58e-06,
	"loss": 11.9056,
	"mean_token_accuracy": 0.7951413784176111,
	"num_tokens": 1915115.0,
	"step": 230
	},
	{
	"entropy": 0.6619318895973265,
	"epoch": 0.096,
	"grad_norm": 66.5,
	"learning_rate": 4.78e-06,
	"loss": 10.9428,
	"mean_token_accuracy": 0.8108693141490221,
	"num_tokens": 2007176.0,
	"step": 240
	},
	{
	"entropy": 0.6880421325564384,
	"epoch": 0.1,
	"grad_norm": 55.5,
	"learning_rate": 4.980000000000001e-06,
	"loss": 11.3231,
	"mean_token_accuracy": 0.8026650555431842,
	"num_tokens": 2088696.0,
	"step": 250
	},
	{
	"entropy": 0.7066576741635799,
	"epoch": 0.104,
	"grad_norm": 58.25,
	"learning_rate": 5.18e-06,
	"loss": 11.6232,
	"mean_token_accuracy": 0.799198641628027,
	"num_tokens": 2171335.0,
	"step": 260
	},
	{
	"entropy": 0.6949395652860403,
	"epoch": 0.108,
	"grad_norm": 69.5,
	"learning_rate": 5.380000000000001e-06,
	"loss": 11.2549,
	"mean_token_accuracy": 0.8055713165551424,
	"num_tokens": 2254168.0,
	"step": 270
	},
	{
	"entropy": 0.666729858610779,
	"epoch": 0.112,
	"grad_norm": 67.0,
	"learning_rate": 5.580000000000001e-06,
	"loss": 10.8193,
	"mean_token_accuracy": 0.8086711473762989,
	"num_tokens": 2342259.0,
	"step": 280
	},
	{
	"entropy": 0.6924487132579088,
	"epoch": 0.116,
	"grad_norm": 60.5,
	"learning_rate": 5.78e-06,
	"loss": 11.1656,
	"mean_token_accuracy": 0.8066085658967495,
	"num_tokens": 2426289.0,
	"step": 290
	},
	{
	"entropy": 0.7209857527166605,
	"epoch": 0.12,
	"grad_norm": 53.75,
	"learning_rate": 5.98e-06,
	"loss": 11.7716,
	"mean_token_accuracy": 0.7946148321032525,
	"num_tokens": 2504279.0,
	"step": 300
	},
	{
	"epoch": 0.12,
	"eval_chemistry_entropy": 0.6136138401329517,
	"eval_chemistry_loss": 0.6401469707489014,
	"eval_chemistry_mean_token_accuracy": 0.8167599263191223,
	"eval_chemistry_num_tokens": 2504279.0,
	"eval_chemistry_runtime": 53.6939,
	"eval_chemistry_samples_per_second": 9.312,
	"eval_chemistry_steps_per_second": 9.312,
	"step": 300
	},
	{
	"epoch": 0.12,
	"eval_physics_entropy": 0.678692765057087,
	"eval_physics_loss": 0.6855186820030212,
	"eval_physics_mean_token_accuracy": 0.8083885474801064,
	"eval_physics_num_tokens": 2504279.0,
	"eval_physics_runtime": 62.4413,
	"eval_physics_samples_per_second": 8.008,
	"eval_physics_steps_per_second": 8.008,
	"step": 300
	},
	{
	"entropy": 0.7016886103898287,
	"epoch": 0.124,
	"grad_norm": 51.0,
	"learning_rate": 6.18e-06,
	"loss": 11.5109,
	"mean_token_accuracy": 0.79740143828094,
	"num_tokens": 2583599.0,
	"step": 310
	},
	{
	"entropy": 0.6659886735491455,
	"epoch": 0.128,
	"grad_norm": 50.5,
	"learning_rate": 6.380000000000001e-06,
	"loss": 10.6687,
	"mean_token_accuracy": 0.8114107441157102,
	"num_tokens": 2663987.0,
	"step": 320
	},
	{
	"entropy": 0.6984131418168544,
	"epoch": 0.132,
	"grad_norm": 55.5,
	"learning_rate": 6.5800000000000005e-06,
	"loss": 11.5084,
	"mean_token_accuracy": 0.8018826052546502,
	"num_tokens": 2743933.0,
	"step": 330
	},
	{
	"entropy": 0.685006461199373,
	"epoch": 0.136,
	"grad_norm": 43.25,
	"learning_rate": 6.780000000000001e-06,
	"loss": 11.0885,
	"mean_token_accuracy": 0.8083073671907186,
	"num_tokens": 2829720.0,
	"step": 340
	},
	{
	"entropy": 0.6919135926291347,
	"epoch": 0.14,
	"grad_norm": 44.25,
	"learning_rate": 6.98e-06,
	"loss": 11.1629,
	"mean_token_accuracy": 0.8035723548382521,
	"num_tokens": 2915814.0,
	"step": 350
	},
	{
	"entropy": 0.6693393810652196,
	"epoch": 0.144,
	"grad_norm": 68.5,
	"learning_rate": 7.180000000000001e-06,
	"loss": 10.8935,
	"mean_token_accuracy": 0.8098476737737655,
	"num_tokens": 2997824.0,
	"step": 360
	},
	{
	"entropy": 0.6817218182608485,
	"epoch": 0.148,
	"grad_norm": 55.0,
	"learning_rate": 7.3800000000000005e-06,
	"loss": 10.9932,
	"mean_token_accuracy": 0.8062656305730342,
	"num_tokens": 3076422.0,
	"step": 370
	},
	{
	"entropy": 0.6472045814618468,
	"epoch": 0.152,
	"grad_norm": 48.5,
	"learning_rate": 7.58e-06,
	"loss": 10.5274,
	"mean_token_accuracy": 0.8134200550615788,
	"num_tokens": 3159946.0,
	"step": 380
	},
	{
	"entropy": 0.639185450039804,
	"epoch": 0.156,
	"grad_norm": 54.25,
	"learning_rate": 7.78e-06,
	"loss": 10.3706,
	"mean_token_accuracy": 0.8159802399575711,
	"num_tokens": 3247218.0,
	"step": 390
	},
	{
	"entropy": 0.6741150500252843,
	"epoch": 0.16,
	"grad_norm": 53.25,
	"learning_rate": 7.980000000000002e-06,
	"loss": 10.9071,
	"mean_token_accuracy": 0.8088992539793253,
	"num_tokens": 3330597.0,
	"step": 400
	},
	{
	"epoch": 0.16,
	"eval_chemistry_entropy": 0.6244144983887673,
	"eval_chemistry_loss": 0.6363974809646606,
	"eval_chemistry_mean_token_accuracy": 0.8181359567642212,
	"eval_chemistry_num_tokens": 3330597.0,
	"eval_chemistry_runtime": 53.6338,
	"eval_chemistry_samples_per_second": 9.322,
	"eval_chemistry_steps_per_second": 9.322,
	"step": 400
	},
	{
	"epoch": 0.16,
	"eval_physics_entropy": 0.6705876287817955,
	"eval_physics_loss": 0.6704522371292114,
	"eval_physics_mean_token_accuracy": 0.8111195236444473,
	"eval_physics_num_tokens": 3330597.0,
	"eval_physics_runtime": 62.3611,
	"eval_physics_samples_per_second": 8.018,
	"eval_physics_steps_per_second": 8.018,
	"step": 400
	},
	{
	"entropy": 0.6919050188735127,
	"epoch": 0.164,
	"grad_norm": 57.25,
	"learning_rate": 8.18e-06,
	"loss": 11.1447,
	"mean_token_accuracy": 0.8047709062695503,
	"num_tokens": 3414445.0,
	"step": 410
	},
	{
	"entropy": 0.6699288227595389,
	"epoch": 0.168,
	"grad_norm": 59.75,
	"learning_rate": 8.380000000000001e-06,
	"loss": 10.7791,
	"mean_token_accuracy": 0.8070078935474158,
	"num_tokens": 3496104.0,
	"step": 420
	},
	{
	"entropy": 0.6792626342736184,
	"epoch": 0.172,
	"grad_norm": 48.75,
	"learning_rate": 8.580000000000001e-06,
	"loss": 11.0757,
	"mean_token_accuracy": 0.8060608543455601,
	"num_tokens": 3576979.0,
	"step": 430
	},
	{
	"entropy": 0.6533824939280748,
	"epoch": 0.176,
	"grad_norm": 61.0,
	"learning_rate": 8.78e-06,
	"loss": 10.5681,
	"mean_token_accuracy": 0.8110670737922192,
	"num_tokens": 3658264.0,
	"step": 440
	},
	{
	"entropy": 0.6711471493355929,
	"epoch": 0.18,
	"grad_norm": 57.25,
	"learning_rate": 8.98e-06,
	"loss": 10.9005,
	"mean_token_accuracy": 0.8076804723590613,
	"num_tokens": 3739142.0,
	"step": 450
	},
	{
	"entropy": 0.6721100191585719,
	"epoch": 0.184,
	"grad_norm": 55.0,
	"learning_rate": 9.180000000000002e-06,
	"loss": 10.792,
	"mean_token_accuracy": 0.8070170730352402,
	"num_tokens": 3821352.0,
	"step": 460
	},
	{
	"entropy": 0.6371375021524728,
	"epoch": 0.188,
	"grad_norm": 45.75,
	"learning_rate": 9.38e-06,
	"loss": 10.3376,
	"mean_token_accuracy": 0.8134377617388964,
	"num_tokens": 3905291.0,
	"step": 470
	},
	{
	"entropy": 0.6436822958290577,
	"epoch": 0.192,
	"grad_norm": 45.75,
	"learning_rate": 9.58e-06,
	"loss": 10.4275,
	"mean_token_accuracy": 0.8145703230053186,
	"num_tokens": 3995568.0,
	"step": 480
	},
	{
	"entropy": 0.6615747599862516,
	"epoch": 0.196,
	"grad_norm": 55.25,
	"learning_rate": 9.780000000000001e-06,
	"loss": 10.75,
	"mean_token_accuracy": 0.8106145299971104,
	"num_tokens": 4075670.0,
	"step": 490
	},
	{
	"entropy": 0.6414908402599394,
	"epoch": 0.2,
	"grad_norm": 55.0,
	"learning_rate": 9.980000000000001e-06,
	"loss": 10.318,
	"mean_token_accuracy": 0.8157790113240481,
	"num_tokens": 4160918.0,
	"step": 500
	},
	{
	"epoch": 0.2,
	"eval_chemistry_entropy": 0.6180844354629517,
	"eval_chemistry_loss": 0.6358755230903625,
	"eval_chemistry_mean_token_accuracy": 0.8190241982936859,
	"eval_chemistry_num_tokens": 4160918.0,
	"eval_chemistry_runtime": 53.6,
	"eval_chemistry_samples_per_second": 9.328,
	"eval_chemistry_steps_per_second": 9.328,
	"step": 500
	},
	{
	"epoch": 0.2,
	"eval_physics_entropy": 0.6517913154959679,
	"eval_physics_loss": 0.6597976088523865,
	"eval_physics_mean_token_accuracy": 0.8130922448635102,
	"eval_physics_num_tokens": 4160918.0,
	"eval_physics_runtime": 62.5405,
	"eval_physics_samples_per_second": 7.995,
	"eval_physics_steps_per_second": 7.995,
	"step": 500
	},
	{
	"entropy": 0.6417077989317477,
	"epoch": 0.204,
	"grad_norm": 48.75,
	"learning_rate": 1.018e-05,
	"loss": 10.4263,
	"mean_token_accuracy": 0.8166976355016231,
	"num_tokens": 4238810.0,
	"step": 510
	},
	{
	"entropy": 0.635231535602361,
	"epoch": 0.208,
	"grad_norm": 48.75,
	"learning_rate": 1.038e-05,
	"loss": 10.327,
	"mean_token_accuracy": 0.8165579732507467,
	"num_tokens": 4321436.0,
	"step": 520
	},
	{
	"entropy": 0.6600574821233749,
	"epoch": 0.212,
	"grad_norm": 49.5,
	"learning_rate": 1.0580000000000002e-05,
	"loss": 10.4772,
	"mean_token_accuracy": 0.811732816696167,
	"num_tokens": 4401710.0,
	"step": 530
	},
	{
	"entropy": 0.6544907880946994,
	"epoch": 0.216,
	"grad_norm": 46.75,
	"learning_rate": 1.0780000000000002e-05,
	"loss": 10.7566,
	"mean_token_accuracy": 0.808320876955986,
	"num_tokens": 4482225.0,
	"step": 540
	},
	{
	"entropy": 0.6429057026281952,
	"epoch": 0.22,
	"grad_norm": 51.25,
	"learning_rate": 1.0980000000000002e-05,
	"loss": 10.4272,
	"mean_token_accuracy": 0.8134562011808157,
	"num_tokens": 4564662.0,
	"step": 550
	},
	{
	"entropy": 0.6186996471136809,
	"epoch": 0.224,
	"grad_norm": 42.0,
	"learning_rate": 1.1180000000000001e-05,
	"loss": 9.9666,
	"mean_token_accuracy": 0.8213985275477171,
	"num_tokens": 4648491.0,
	"step": 560
	},
	{
	"entropy": 0.6025784744881093,
	"epoch": 0.228,
	"grad_norm": 40.75,
	"learning_rate": 1.138e-05,
	"loss": 9.8638,
	"mean_token_accuracy": 0.8230083137750626,
	"num_tokens": 4731596.0,
	"step": 570
	},
	{
	"entropy": 0.6584511337801814,
	"epoch": 0.232,
	"grad_norm": 45.0,
	"learning_rate": 1.1580000000000001e-05,
	"loss": 10.6688,
	"mean_token_accuracy": 0.8104485847055912,
	"num_tokens": 4813449.0,
	"step": 580
	},
	{
	"entropy": 0.6477856112644076,
	"epoch": 0.236,
	"grad_norm": 40.25,
	"learning_rate": 1.178e-05,
	"loss": 10.3036,
	"mean_token_accuracy": 0.8149273872375489,
	"num_tokens": 4899144.0,
	"step": 590
	},
	{
	"entropy": 0.632176025211811,
	"epoch": 0.24,
	"grad_norm": 44.5,
	"learning_rate": 1.198e-05,
	"loss": 10.4072,
	"mean_token_accuracy": 0.8141517870128154,
	"num_tokens": 4986175.0,
	"step": 600
	},
	{
	"epoch": 0.24,
	"eval_chemistry_entropy": 0.6246057401299476,
	"eval_chemistry_loss": 0.6355127096176147,
	"eval_chemistry_mean_token_accuracy": 0.8170186321735382,
	"eval_chemistry_num_tokens": 4986175.0,
	"eval_chemistry_runtime": 53.7353,
	"eval_chemistry_samples_per_second": 9.305,
	"eval_chemistry_steps_per_second": 9.305,
	"step": 600
	},
	{
	"epoch": 0.24,
	"eval_physics_entropy": 0.6429958860874176,
	"eval_physics_loss": 0.6528828740119934,
	"eval_physics_mean_token_accuracy": 0.8143444744944572,
	"eval_physics_num_tokens": 4986175.0,
	"eval_physics_runtime": 62.4695,
	"eval_physics_samples_per_second": 8.004,
	"eval_physics_steps_per_second": 8.004,
	"step": 600
	},
	{
	"entropy": 0.6520758749917149,
	"epoch": 0.244,
	"grad_norm": 50.0,
	"learning_rate": 1.218e-05,
	"loss": 10.5332,
	"mean_token_accuracy": 0.8124375600367785,
	"num_tokens": 5071994.0,
	"step": 610
	},
	{
	"entropy": 0.6255051350221038,
	"epoch": 0.248,
	"grad_norm": 43.5,
	"learning_rate": 1.2380000000000002e-05,
	"loss": 10.0529,
	"mean_token_accuracy": 0.8187242690473795,
	"num_tokens": 5164741.0,
	"step": 620
	},
	{
	"entropy": 0.6554224069230259,
	"epoch": 0.252,
	"grad_norm": 47.5,
	"learning_rate": 1.2580000000000002e-05,
	"loss": 10.7383,
	"mean_token_accuracy": 0.8093429666012526,
	"num_tokens": 5245878.0,
	"step": 630
	},
	{
	"entropy": 0.635463903658092,
	"epoch": 0.256,
	"grad_norm": 51.0,
	"learning_rate": 1.2780000000000001e-05,
	"loss": 10.3241,
	"mean_token_accuracy": 0.8143212880939246,
	"num_tokens": 5329320.0,
	"step": 640
	},
	{
	"entropy": 0.6407582541927695,
	"epoch": 0.26,
	"grad_norm": 44.75,
	"learning_rate": 1.2980000000000001e-05,
	"loss": 10.3061,
	"mean_token_accuracy": 0.8153956741094589,
	"num_tokens": 5412557.0,
	"step": 650
	},
	{
	"entropy": 0.6218360926955938,
	"epoch": 0.264,
	"grad_norm": 55.25,
	"learning_rate": 1.3180000000000001e-05,
	"loss": 10.1715,
	"mean_token_accuracy": 0.8187983844429254,
	"num_tokens": 5497259.0,
	"step": 660
	},
	{
	"entropy": 0.6525244776159524,
	"epoch": 0.268,
	"grad_norm": 48.5,
	"learning_rate": 1.3380000000000002e-05,
	"loss": 10.5148,
	"mean_token_accuracy": 0.8133967652916908,
	"num_tokens": 5576721.0,
	"step": 670
	},
	{
	"entropy": 0.6617097955197095,
	"epoch": 0.272,
	"grad_norm": 50.0,
	"learning_rate": 1.3580000000000002e-05,
	"loss": 10.7486,
	"mean_token_accuracy": 0.8067130610346794,
	"num_tokens": 5658796.0,
	"step": 680
	},
	{
	"entropy": 0.6757121763192118,
	"epoch": 0.276,
	"grad_norm": 47.25,
	"learning_rate": 1.378e-05,
	"loss": 10.8755,
	"mean_token_accuracy": 0.8065906465053558,
	"num_tokens": 5737499.0,
	"step": 690
	},
	{
	"entropy": 0.6453007774427533,
	"epoch": 0.28,
	"grad_norm": 62.5,
	"learning_rate": 1.398e-05,
	"loss": 10.4792,
	"mean_token_accuracy": 0.8154859133064747,
	"num_tokens": 5819027.0,
	"step": 700
	},
	{
	"epoch": 0.28,
	"eval_chemistry_entropy": 0.6300962825417519,
	"eval_chemistry_loss": 0.6389291882514954,
	"eval_chemistry_mean_token_accuracy": 0.8176450840234757,
	"eval_chemistry_num_tokens": 5819027.0,
	"eval_chemistry_runtime": 53.7695,
	"eval_chemistry_samples_per_second": 9.299,
	"eval_chemistry_steps_per_second": 9.299,
	"step": 700
	},
	{
	"epoch": 0.28,
	"eval_physics_entropy": 0.6429837597608566,
	"eval_physics_loss": 0.6483125686645508,
	"eval_physics_mean_token_accuracy": 0.8155634801387787,
	"eval_physics_num_tokens": 5819027.0,
	"eval_physics_runtime": 62.5294,
	"eval_physics_samples_per_second": 7.996,
	"eval_physics_steps_per_second": 7.996,
	"step": 700
	},
	{
	"entropy": 0.6762596594169736,
	"epoch": 0.284,
	"grad_norm": 59.0,
	"learning_rate": 1.418e-05,
	"loss": 10.8583,
	"mean_token_accuracy": 0.8072559602558613,
	"num_tokens": 5898693.0,
	"step": 710
	},
	{
	"entropy": 0.6340524691157043,
	"epoch": 0.288,
	"grad_norm": 47.75,
	"learning_rate": 1.4380000000000001e-05,
	"loss": 10.3892,
	"mean_token_accuracy": 0.8159883081912994,
	"num_tokens": 5980201.0,
	"step": 720
	},
	{
	"entropy": 0.6257706139236688,
	"epoch": 0.292,
	"grad_norm": 46.25,
	"learning_rate": 1.4580000000000001e-05,
	"loss": 10.052,
	"mean_token_accuracy": 0.8204058665782213,
	"num_tokens": 6059507.0,
	"step": 730
	},
	{
	"entropy": 0.6355020292103291,
	"epoch": 0.296,
	"grad_norm": 47.0,
	"learning_rate": 1.478e-05,
	"loss": 10.3665,
	"mean_token_accuracy": 0.8142751138657331,
	"num_tokens": 6139830.0,
	"step": 740
	},
	{
	"entropy": 0.6532576438970864,
	"epoch": 0.3,
	"grad_norm": 47.25,
	"learning_rate": 1.498e-05,
	"loss": 10.3728,
	"mean_token_accuracy": 0.8153154000639915,
	"num_tokens": 6218134.0,
	"step": 750
	},
	{
	"entropy": 0.6463365102186799,
	"epoch": 0.304,
	"grad_norm": 47.0,
	"learning_rate": 1.5180000000000002e-05,
	"loss": 10.4965,
	"mean_token_accuracy": 0.8147804290056229,
	"num_tokens": 6298858.0,
	"step": 760
	},
	{
	"entropy": 0.6870367551222444,
	"epoch": 0.308,
	"grad_norm": 55.0,
	"learning_rate": 1.5380000000000002e-05,
	"loss": 11.2005,
	"mean_token_accuracy": 0.8020890522748232,
	"num_tokens": 6375761.0,
	"step": 770
	},
	{
	"entropy": 0.6256772884167731,
	"epoch": 0.312,
	"grad_norm": 41.75,
	"learning_rate": 1.5580000000000003e-05,
	"loss": 10.0914,
	"mean_token_accuracy": 0.8196329109370708,
	"num_tokens": 6456502.0,
	"step": 780
	},
	{
	"entropy": 0.6423514087684452,
	"epoch": 0.316,
	"grad_norm": 49.75,
	"learning_rate": 1.578e-05,
	"loss": 10.492,
	"mean_token_accuracy": 0.8146003533154726,
	"num_tokens": 6537521.0,
	"step": 790
	},
	{
	"entropy": 0.6631265950389207,
	"epoch": 0.32,
	"grad_norm": 43.0,
	"learning_rate": 1.5980000000000003e-05,
	"loss": 10.7489,
	"mean_token_accuracy": 0.8101503010839224,
	"num_tokens": 6622798.0,
	"step": 800
	},
	{
	"epoch": 0.32,
	"eval_chemistry_entropy": 0.6421979127824307,
	"eval_chemistry_loss": 0.6415462493896484,
	"eval_chemistry_mean_token_accuracy": 0.817062867641449,
	"eval_chemistry_num_tokens": 6622798.0,
	"eval_chemistry_runtime": 53.6883,
	"eval_chemistry_samples_per_second": 9.313,
	"eval_chemistry_steps_per_second": 9.313,
	"step": 800
	},
	{
	"epoch": 0.32,
	"eval_physics_entropy": 0.6440860625505448,
	"eval_physics_loss": 0.6467884182929993,
	"eval_physics_mean_token_accuracy": 0.8157004522681236,
	"eval_physics_num_tokens": 6622798.0,
	"eval_physics_runtime": 62.4499,
	"eval_physics_samples_per_second": 8.006,
	"eval_physics_steps_per_second": 8.006,
	"step": 800
	},
	{
	"entropy": 0.6417643938213586,
	"epoch": 0.324,
	"grad_norm": 54.0,
	"learning_rate": 1.618e-05,
	"loss": 10.54,
	"mean_token_accuracy": 0.8144381437450647,
	"num_tokens": 6699373.0,
	"step": 810
	},
	{
	"entropy": 0.6635292621329427,
	"epoch": 0.328,
	"grad_norm": 43.25,
	"learning_rate": 1.638e-05,
	"loss": 10.6337,
	"mean_token_accuracy": 0.8078649930655957,
	"num_tokens": 6782985.0,
	"step": 820
	},
	{
	"entropy": 0.6515420666895807,
	"epoch": 0.332,
	"grad_norm": 51.5,
	"learning_rate": 1.658e-05,
	"loss": 10.4447,
	"mean_token_accuracy": 0.8119669426232576,
	"num_tokens": 6868578.0,
	"step": 830
	},
	{
	"entropy": 0.6081873361952603,
	"epoch": 0.336,
	"grad_norm": 40.0,
	"learning_rate": 1.6780000000000002e-05,
	"loss": 9.8522,
	"mean_token_accuracy": 0.8244299061596394,
	"num_tokens": 6953611.0,
	"step": 840
	},
	{
	"entropy": 0.6503613390959799,
	"epoch": 0.34,
	"grad_norm": 52.0,
	"learning_rate": 1.698e-05,
	"loss": 10.6425,
	"mean_token_accuracy": 0.8126828409731388,
	"num_tokens": 7037831.0,
	"step": 850
	},
	{
	"entropy": 0.611198160611093,
	"epoch": 0.344,
	"grad_norm": 56.75,
	"learning_rate": 1.718e-05,
	"loss": 9.9189,
	"mean_token_accuracy": 0.8207242820411921,
	"num_tokens": 7121949.0,
	"step": 860
	},
	{
	"entropy": 0.6327245706692338,
	"epoch": 0.348,
	"grad_norm": 44.0,
	"learning_rate": 1.7380000000000003e-05,
	"loss": 10.2368,
	"mean_token_accuracy": 0.8166516173630953,
	"num_tokens": 7206056.0,
	"step": 870
	},
	{
	"entropy": 0.6341161539778113,
	"epoch": 0.352,
	"grad_norm": 51.5,
	"learning_rate": 1.758e-05,
	"loss": 10.2941,
	"mean_token_accuracy": 0.816456102579832,
	"num_tokens": 7290378.0,
	"step": 880
	},
	{
	"entropy": 0.6554373924620449,
	"epoch": 0.356,
	"grad_norm": 42.5,
	"learning_rate": 1.7780000000000003e-05,
	"loss": 10.5667,
	"mean_token_accuracy": 0.8104542337357998,
	"num_tokens": 7367952.0,
	"step": 890
	},
	{
	"entropy": 0.6374449659138918,
	"epoch": 0.36,
	"grad_norm": 59.75,
	"learning_rate": 1.798e-05,
	"loss": 10.3565,
	"mean_token_accuracy": 0.816227027028799,
	"num_tokens": 7452920.0,
	"step": 900
	},
	{
	"epoch": 0.36,
	"eval_chemistry_entropy": 0.6640482069849968,
	"eval_chemistry_loss": 0.6512866020202637,
	"eval_chemistry_mean_token_accuracy": 0.8145369750261306,
	"eval_chemistry_num_tokens": 7452920.0,
	"eval_chemistry_runtime": 53.5846,
	"eval_chemistry_samples_per_second": 9.331,
	"eval_chemistry_steps_per_second": 9.331,
	"step": 900
	},
	{
	"epoch": 0.36,
	"eval_physics_entropy": 0.65689039093256,
	"eval_physics_loss": 0.64650559425354,
	"eval_physics_mean_token_accuracy": 0.8153353578448296,
	"eval_physics_num_tokens": 7452920.0,
	"eval_physics_runtime": 62.3633,
	"eval_physics_samples_per_second": 8.018,
	"eval_physics_steps_per_second": 8.018,
	"step": 900
	},
	{
	"entropy": 0.6258705526590347,
	"epoch": 0.364,
	"grad_norm": 43.75,
	"learning_rate": 1.8180000000000002e-05,
	"loss": 10.013,
	"mean_token_accuracy": 0.8192542195320129,
	"num_tokens": 7535961.0,
	"step": 910
	},
	{
	"entropy": 0.6131137845106422,
	"epoch": 0.368,
	"grad_norm": 43.5,
	"learning_rate": 1.8380000000000004e-05,
	"loss": 9.9858,
	"mean_token_accuracy": 0.8190763648599386,
	"num_tokens": 7621082.0,
	"step": 920
	},
	{
	"entropy": 0.6138401796109975,
	"epoch": 0.372,
	"grad_norm": 46.75,
	"learning_rate": 1.858e-05,
	"loss": 10.0396,
	"mean_token_accuracy": 0.8174721483141184,
	"num_tokens": 7705651.0,
	"step": 930
	},
	{
	"entropy": 0.7146476589143276,
	"epoch": 0.376,
	"grad_norm": 46.25,
	"learning_rate": 1.878e-05,
	"loss": 11.4452,
	"mean_token_accuracy": 0.7953129142522812,
	"num_tokens": 7787036.0,
	"step": 940
	},
	{
	"entropy": 0.6485187427140773,
	"epoch": 0.38,
	"grad_norm": 56.5,
	"learning_rate": 1.898e-05,
	"loss": 10.5487,
	"mean_token_accuracy": 0.8087487578392029,
	"num_tokens": 7869437.0,
	"step": 950
	},
	{
	"entropy": 0.633660759497434,
	"epoch": 0.384,
	"grad_norm": 42.0,
	"learning_rate": 1.918e-05,
	"loss": 10.1676,
	"mean_token_accuracy": 0.8168184392154216,
	"num_tokens": 7955570.0,
	"step": 960
	},
	{
	"entropy": 0.5985365292057395,
	"epoch": 0.388,
	"grad_norm": 38.25,
	"learning_rate": 1.938e-05,
	"loss": 9.8157,
	"mean_token_accuracy": 0.8218576721847057,
	"num_tokens": 8038818.0,
	"step": 970
	},
	{
	"entropy": 0.6344430455937982,
	"epoch": 0.392,
	"grad_norm": 39.75,
	"learning_rate": 1.9580000000000002e-05,
	"loss": 10.1821,
	"mean_token_accuracy": 0.8146390464156866,
	"num_tokens": 8123527.0,
	"step": 980
	},
	{
	"entropy": 0.6378526957705617,
	"epoch": 0.396,
	"grad_norm": 43.75,
	"learning_rate": 1.978e-05,
	"loss": 10.2889,
	"mean_token_accuracy": 0.8144868839532137,
	"num_tokens": 8206501.0,
	"step": 990
	},
	{
	"entropy": 0.6167035531252623,
	"epoch": 0.4,
	"grad_norm": 36.25,
	"learning_rate": 1.9980000000000002e-05,
	"loss": 10.0591,
	"mean_token_accuracy": 0.819990050420165,
	"num_tokens": 8291049.0,
	"step": 1000
	},
	{
	"epoch": 0.4,
	"eval_chemistry_entropy": 0.6586475971937179,
	"eval_chemistry_loss": 0.6543877124786377,
	"eval_chemistry_mean_token_accuracy": 0.8140276271104813,
	"eval_chemistry_num_tokens": 8291049.0,
	"eval_chemistry_runtime": 53.801,
	"eval_chemistry_samples_per_second": 9.294,
	"eval_chemistry_steps_per_second": 9.294,
	"step": 1000
	},
	{
	"epoch": 0.4,
	"eval_physics_entropy": 0.645909442961216,
	"eval_physics_loss": 0.6488538980484009,
	"eval_physics_mean_token_accuracy": 0.8152267854809762,
	"eval_physics_num_tokens": 8291049.0,
	"eval_physics_runtime": 63.4318,
	"eval_physics_samples_per_second": 7.882,
	"eval_physics_steps_per_second": 7.882,
	"step": 1000
	},
	{
	"entropy": 0.6288712982088327,
	"epoch": 0.404,
	"grad_norm": 44.75,
	"learning_rate": 1.9980000000000002e-05,
	"loss": 10.1535,
	"mean_token_accuracy": 0.8175500966608524,
	"num_tokens": 8373687.0,
	"step": 1010
	},
	{
	"entropy": 0.6477080984972418,
	"epoch": 0.408,
	"grad_norm": 41.25,
	"learning_rate": 1.995777777777778e-05,
	"loss": 10.4444,
	"mean_token_accuracy": 0.8120142377912998,
	"num_tokens": 8459795.0,
	"step": 1020
	},
	{
	"entropy": 0.6198763550259173,
	"epoch": 0.412,
	"grad_norm": 48.25,
	"learning_rate": 1.9935555555555557e-05,
	"loss": 10.145,
	"mean_token_accuracy": 0.8183699958026409,
	"num_tokens": 8544948.0,
	"step": 1030
	},
	{
	"entropy": 0.6268251063302159,
	"epoch": 0.416,
	"grad_norm": 43.5,
	"learning_rate": 1.9913333333333335e-05,
	"loss": 10.1171,
	"mean_token_accuracy": 0.8166644174605608,
	"num_tokens": 8627310.0,
	"step": 1040
	},
	{
	"entropy": 0.7168899232521653,
	"epoch": 0.42,
	"grad_norm": 45.0,
	"learning_rate": 1.9891111111111112e-05,
	"loss": 11.6477,
	"mean_token_accuracy": 0.7963819321244955,
	"num_tokens": 8707798.0,
	"step": 1050
	},
	{
	"entropy": 0.6254937417805195,
	"epoch": 0.424,
	"grad_norm": 39.5,
	"learning_rate": 1.986888888888889e-05,
	"loss": 10.0341,
	"mean_token_accuracy": 0.8202919337898493,
	"num_tokens": 8792574.0,
	"step": 1060
	},
	{
	"entropy": 0.6258060172200203,
	"epoch": 0.428,
	"grad_norm": 49.75,
	"learning_rate": 1.9846666666666668e-05,
	"loss": 10.2091,
	"mean_token_accuracy": 0.8151731941848993,
	"num_tokens": 8878637.0,
	"step": 1070
	},
	{
	"entropy": 0.6487020991742611,
	"epoch": 0.432,
	"grad_norm": 49.75,
	"learning_rate": 1.9824444444444445e-05,
	"loss": 10.4063,
	"mean_token_accuracy": 0.8136575162410736,
	"num_tokens": 8958371.0,
	"step": 1080
	},
	{
	"entropy": 0.6037185428664088,
	"epoch": 0.436,
	"grad_norm": 49.25,
	"learning_rate": 1.9802222222222226e-05,
	"loss": 9.8187,
	"mean_token_accuracy": 0.8217611808329821,
	"num_tokens": 9040649.0,
	"step": 1090
	},
	{
	"entropy": 0.5906071299687028,
	"epoch": 0.44,
	"grad_norm": 42.0,
	"learning_rate": 1.978e-05,
	"loss": 9.5257,
	"mean_token_accuracy": 0.8266360804438591,
	"num_tokens": 9125564.0,
	"step": 1100
	},
	{
	"epoch": 0.44,
	"eval_chemistry_entropy": 0.6296808683276176,
	"eval_chemistry_loss": 0.6599302291870117,
	"eval_chemistry_mean_token_accuracy": 0.8118611789941788,
	"eval_chemistry_num_tokens": 9125564.0,
	"eval_chemistry_runtime": 54.5116,
	"eval_chemistry_samples_per_second": 9.172,
	"eval_chemistry_steps_per_second": 9.172,
	"step": 1100
	},
	{
	"epoch": 0.44,
	"eval_physics_entropy": 0.6190407463014126,
	"eval_physics_loss": 0.6459570527076721,
	"eval_physics_mean_token_accuracy": 0.815562941968441,
	"eval_physics_num_tokens": 9125564.0,
	"eval_physics_runtime": 63.2267,
	"eval_physics_samples_per_second": 7.908,
	"eval_physics_steps_per_second": 7.908,
	"step": 1100
	},
	{
	"entropy": 0.6702354967594146,
	"epoch": 0.444,
	"grad_norm": 41.25,
	"learning_rate": 1.975777777777778e-05,
	"loss": 10.8062,
	"mean_token_accuracy": 0.810298365727067,
	"num_tokens": 9210443.0,
	"step": 1110
	},
	{
	"entropy": 0.6155520310625434,
	"epoch": 0.448,
	"grad_norm": 39.75,
	"learning_rate": 1.9735555555555556e-05,
	"loss": 10.1142,
	"mean_token_accuracy": 0.8205059375613928,
	"num_tokens": 9294388.0,
	"step": 1120
	},
	{
	"entropy": 0.5996189665980637,
	"epoch": 0.452,
	"grad_norm": 43.75,
	"learning_rate": 1.9713333333333337e-05,
	"loss": 9.4709,
	"mean_token_accuracy": 0.8281105298548936,
	"num_tokens": 9371203.0,
	"step": 1130
	},
	{
	"entropy": 0.6231001582928002,
	"epoch": 0.456,
	"grad_norm": 42.0,
	"learning_rate": 1.969111111111111e-05,
	"loss": 10.1464,
	"mean_token_accuracy": 0.8164454229176045,
	"num_tokens": 9455428.0,
	"step": 1140
	},
	{
	"entropy": 0.6021164663136005,
	"epoch": 0.46,
	"grad_norm": 39.0,
	"learning_rate": 1.9668888888888892e-05,
	"loss": 9.6895,
	"mean_token_accuracy": 0.8233658988028765,
	"num_tokens": 9539605.0,
	"step": 1150
	},
	{
	"entropy": 0.6290203684009612,
	"epoch": 0.464,
	"grad_norm": 42.0,
	"learning_rate": 1.9646666666666666e-05,
	"loss": 10.1725,
	"mean_token_accuracy": 0.8175587739795447,
	"num_tokens": 9620366.0,
	"step": 1160
	},
	{
	"entropy": 0.6108594150282443,
	"epoch": 0.468,
	"grad_norm": 51.75,
	"learning_rate": 1.9624444444444447e-05,
	"loss": 9.947,
	"mean_token_accuracy": 0.819192311167717,
	"num_tokens": 9706621.0,
	"step": 1170
	},
	{
	"entropy": 0.6204524893313647,
	"epoch": 0.472,
	"grad_norm": 39.5,
	"learning_rate": 1.9602222222222225e-05,
	"loss": 9.9455,
	"mean_token_accuracy": 0.8174036685377359,
	"num_tokens": 9788925.0,
	"step": 1180
	},
	{
	"entropy": 0.5935720985755324,
	"epoch": 0.476,
	"grad_norm": 36.5,
	"learning_rate": 1.9580000000000002e-05,
	"loss": 9.6394,
	"mean_token_accuracy": 0.8253184624016285,
	"num_tokens": 9869908.0,
	"step": 1190
	},
	{
	"entropy": 0.6630870910361409,
	"epoch": 0.48,
	"grad_norm": 47.0,
	"learning_rate": 1.955777777777778e-05,
	"loss": 10.7476,
	"mean_token_accuracy": 0.808968411386013,
	"num_tokens": 9955431.0,
	"step": 1200
	},
	{
	"epoch": 0.48,
	"eval_chemistry_entropy": 0.6792522894442081,
	"eval_chemistry_loss": 0.6633003354072571,
	"eval_chemistry_mean_token_accuracy": 0.8119940814971924,
	"eval_chemistry_num_tokens": 9955431.0,
	"eval_chemistry_runtime": 53.9215,
	"eval_chemistry_samples_per_second": 9.273,
	"eval_chemistry_steps_per_second": 9.273,
	"step": 1200
	},
	{
	"epoch": 0.48,
	"eval_physics_entropy": 0.650343769878149,
	"eval_physics_loss": 0.6420111656188965,
	"eval_physics_mean_token_accuracy": 0.8167362776398659,
	"eval_physics_num_tokens": 9955431.0,
	"eval_physics_runtime": 62.6062,
	"eval_physics_samples_per_second": 7.986,
	"eval_physics_steps_per_second": 7.986,
	"step": 1200
	},
	{
	"entropy": 0.612500429712236,
	"epoch": 0.484,
	"grad_norm": 47.0,
	"learning_rate": 1.9535555555555557e-05,
	"loss": 9.9347,
	"mean_token_accuracy": 0.8223837319761514,
	"num_tokens": 10038293.0,
	"step": 1210
	},
	{
	"entropy": 0.6377324659377337,
	"epoch": 0.488,
	"grad_norm": 40.5,
	"learning_rate": 1.9513333333333335e-05,
	"loss": 10.2831,
	"mean_token_accuracy": 0.817806663736701,
	"num_tokens": 10119599.0,
	"step": 1220
	},
	{
	"entropy": 0.6632728383876383,
	"epoch": 0.492,
	"grad_norm": 44.75,
	"learning_rate": 1.9491111111111113e-05,
	"loss": 10.6639,
	"mean_token_accuracy": 0.80819180496037,
	"num_tokens": 10204514.0,
	"step": 1230
	},
	{
	"entropy": 0.6558596555143594,
	"epoch": 0.496,
	"grad_norm": 36.0,
	"learning_rate": 1.946888888888889e-05,
	"loss": 10.5429,
	"mean_token_accuracy": 0.8120821505784989,
	"num_tokens": 10289883.0,
	"step": 1240
	},
	{
	"entropy": 0.6169624142348766,
	"epoch": 0.5,
	"grad_norm": 46.75,
	"learning_rate": 1.9446666666666668e-05,
	"loss": 10.0534,
	"mean_token_accuracy": 0.8196999322623014,
	"num_tokens": 10368762.0,
	"step": 1250
	},
	{
	"entropy": 0.6267159227281809,
	"epoch": 0.504,
	"grad_norm": 41.0,
	"learning_rate": 1.9424444444444446e-05,
	"loss": 10.096,
	"mean_token_accuracy": 0.8189252704381943,
	"num_tokens": 10454683.0,
	"step": 1260
	},
	{
	"entropy": 0.6419813117012382,
	"epoch": 0.508,
	"grad_norm": 42.0,
	"learning_rate": 1.9402222222222223e-05,
	"loss": 10.4847,
	"mean_token_accuracy": 0.8120944950729608,
	"num_tokens": 10539515.0,
	"step": 1270
	},
	{
	"entropy": 0.684658529702574,
	"epoch": 0.512,
	"grad_norm": 46.25,
	"learning_rate": 1.938e-05,
	"loss": 10.9876,
	"mean_token_accuracy": 0.8051567550748586,
	"num_tokens": 10619468.0,
	"step": 1280
	},
	{
	"entropy": 0.6482914222404361,
	"epoch": 0.516,
	"grad_norm": 42.75,
	"learning_rate": 1.935777777777778e-05,
	"loss": 10.3902,
	"mean_token_accuracy": 0.8132968720048666,
	"num_tokens": 10698439.0,
	"step": 1290
	},
	{
	"entropy": 0.6492844991385937,
	"epoch": 0.52,
	"grad_norm": 40.25,
	"learning_rate": 1.9335555555555556e-05,
	"loss": 10.5517,
	"mean_token_accuracy": 0.809664323553443,
	"num_tokens": 10781285.0,
	"step": 1300
	},
	{
	"epoch": 0.52,
	"eval_chemistry_entropy": 0.6645045831203461,
	"eval_chemistry_loss": 0.6653202176094055,
	"eval_chemistry_mean_token_accuracy": 0.811331033706665,
	"eval_chemistry_num_tokens": 10781285.0,
	"eval_chemistry_runtime": 55.4768,
	"eval_chemistry_samples_per_second": 9.013,
	"eval_chemistry_steps_per_second": 9.013,
	"step": 1300
	},
	{
	"epoch": 0.52,
	"eval_physics_entropy": 0.6388631807863713,
	"eval_physics_loss": 0.6363136172294617,
	"eval_physics_mean_token_accuracy": 0.8173955215811729,
	"eval_physics_num_tokens": 10781285.0,
	"eval_physics_runtime": 62.7946,
	"eval_physics_samples_per_second": 7.962,
	"eval_physics_steps_per_second": 7.962,
	"step": 1300
	},
	{
	"entropy": 0.6285697594285011,
	"epoch": 0.524,
	"grad_norm": 43.5,
	"learning_rate": 1.9313333333333334e-05,
	"loss": 10.221,
	"mean_token_accuracy": 0.8181417305022478,
	"num_tokens": 10864773.0,
	"step": 1310
	},
	{
	"entropy": 0.6136522050015628,
	"epoch": 0.528,
	"grad_norm": 38.0,
	"learning_rate": 1.9291111111111115e-05,
	"loss": 9.8866,
	"mean_token_accuracy": 0.8212735544890165,
	"num_tokens": 10944904.0,
	"step": 1320
	},
	{
	"entropy": 0.6457662120461464,
	"epoch": 0.532,
	"grad_norm": 45.75,
	"learning_rate": 1.926888888888889e-05,
	"loss": 10.3524,
	"mean_token_accuracy": 0.8151355512440205,
	"num_tokens": 11023958.0,
	"step": 1330
	},
	{
	"entropy": 0.5919691896066069,
	"epoch": 0.536,
	"grad_norm": 43.75,
	"learning_rate": 1.924666666666667e-05,
	"loss": 9.6708,
	"mean_token_accuracy": 0.8262011889368296,
	"num_tokens": 11106538.0,
	"step": 1340
	},
	{
	"entropy": 0.6490627369843424,
	"epoch": 0.54,
	"grad_norm": 51.75,
	"learning_rate": 1.9224444444444444e-05,
	"loss": 10.464,
	"mean_token_accuracy": 0.8134491160511971,
	"num_tokens": 11187142.0,
	"step": 1350
	},
	{
	"entropy": 0.6667550153099,
	"epoch": 0.544,
	"grad_norm": 54.5,
	"learning_rate": 1.9202222222222225e-05,
	"loss": 10.8278,
	"mean_token_accuracy": 0.8061591122299433,
	"num_tokens": 11266409.0,
	"step": 1360
	},
	{
	"entropy": 0.6294793977402151,
	"epoch": 0.548,
	"grad_norm": 48.5,
	"learning_rate": 1.918e-05,
	"loss": 10.153,
	"mean_token_accuracy": 0.8186534035950899,
	"num_tokens": 11350094.0,
	"step": 1370
	},
	{
	"entropy": 0.6307276577688754,
	"epoch": 0.552,
	"grad_norm": 46.5,
	"learning_rate": 1.915777777777778e-05,
	"loss": 10.2431,
	"mean_token_accuracy": 0.8161013640463353,
	"num_tokens": 11438391.0,
	"step": 1380
	},
	{
	"entropy": 0.6490003860555589,
	"epoch": 0.556,
	"grad_norm": 47.25,
	"learning_rate": 1.9135555555555555e-05,
	"loss": 10.292,
	"mean_token_accuracy": 0.8154143560677767,
	"num_tokens": 11521583.0,
	"step": 1390
	},
	{
	"entropy": 0.5914541745558382,
	"epoch": 0.56,
	"grad_norm": 41.0,
	"learning_rate": 1.9113333333333336e-05,
	"loss": 9.6568,
	"mean_token_accuracy": 0.8256826549768448,
	"num_tokens": 11605544.0,
	"step": 1400
	},
	{
	"epoch": 0.56,
	"eval_chemistry_entropy": 0.6548177749216556,
	"eval_chemistry_loss": 0.6667582988739014,
	"eval_chemistry_mean_token_accuracy": 0.8108637844324111,
	"eval_chemistry_num_tokens": 11605544.0,
	"eval_chemistry_runtime": 53.9633,
	"eval_chemistry_samples_per_second": 9.266,
	"eval_chemistry_steps_per_second": 9.266,
	"step": 1400
	},
	{
	"epoch": 0.56,
	"eval_physics_entropy": 0.6302824917435647,
	"eval_physics_loss": 0.6326262354850769,
	"eval_physics_mean_token_accuracy": 0.8184790652990341,
	"eval_physics_num_tokens": 11605544.0,
	"eval_physics_runtime": 62.6194,
	"eval_physics_samples_per_second": 7.985,
	"eval_physics_steps_per_second": 7.985,
	"step": 1400
	},
	{
	"entropy": 0.6050882572308183,
	"epoch": 0.564,
	"grad_norm": 39.25,
	"learning_rate": 1.9091111111111113e-05,
	"loss": 9.7547,
	"mean_token_accuracy": 0.8240263950079679,
	"num_tokens": 11686173.0,
	"step": 1410
	},
	{
	"entropy": 0.637587258964777,
	"epoch": 0.568,
	"grad_norm": 36.75,
	"learning_rate": 1.906888888888889e-05,
	"loss": 10.1842,
	"mean_token_accuracy": 0.818510303273797,
	"num_tokens": 11765430.0,
	"step": 1420
	},
	{
	"entropy": 0.6074552223086357,
	"epoch": 0.572,
	"grad_norm": 38.5,
	"learning_rate": 1.904666666666667e-05,
	"loss": 9.9644,
	"mean_token_accuracy": 0.8220620211213827,
	"num_tokens": 11850973.0,
	"step": 1430
	},
	{
	"entropy": 0.617229042109102,
	"epoch": 0.576,
	"grad_norm": 53.0,
	"learning_rate": 1.9024444444444446e-05,
	"loss": 9.9445,
	"mean_token_accuracy": 0.820784068480134,
	"num_tokens": 11931715.0,
	"step": 1440
	},
	{
	"entropy": 0.59880430418998,
	"epoch": 0.58,
	"grad_norm": 43.25,
	"learning_rate": 1.9002222222222224e-05,
	"loss": 9.5273,
	"mean_token_accuracy": 0.8268065106123685,
	"num_tokens": 12012155.0,
	"step": 1450
	},
	{
	"entropy": 0.6227379216812551,
	"epoch": 0.584,
	"grad_norm": 43.25,
	"learning_rate": 1.898e-05,
	"loss": 10.1233,
	"mean_token_accuracy": 0.8189155597239732,
	"num_tokens": 12093686.0,
	"step": 1460
	},
	{
	"entropy": 0.6201856574974954,
	"epoch": 0.588,
	"grad_norm": 41.75,
	"learning_rate": 1.895777777777778e-05,
	"loss": 9.9752,
	"mean_token_accuracy": 0.8193617489188909,
	"num_tokens": 12177581.0,
	"step": 1470
	},
	{
	"entropy": 0.6364695785567165,
	"epoch": 0.592,
	"grad_norm": 46.5,
	"learning_rate": 1.8935555555555556e-05,
	"loss": 10.3954,
	"mean_token_accuracy": 0.8134158592671156,
	"num_tokens": 12257243.0,
	"step": 1480
	},
	{
	"entropy": 0.6294575407169759,
	"epoch": 0.596,
	"grad_norm": 59.0,
	"learning_rate": 1.8913333333333334e-05,
	"loss": 10.1581,
	"mean_token_accuracy": 0.8173588078469038,
	"num_tokens": 12338544.0,
	"step": 1490
	},
	{
	"entropy": 0.6043597641400993,
	"epoch": 0.6,
	"grad_norm": 41.25,
	"learning_rate": 1.8891111111111115e-05,
	"loss": 9.7064,
	"mean_token_accuracy": 0.8232355277985335,
	"num_tokens": 12422008.0,
	"step": 1500
	},
	{
	"epoch": 0.6,
	"eval_chemistry_entropy": 0.6489740502238274,
	"eval_chemistry_loss": 0.6658231019973755,
	"eval_chemistry_mean_token_accuracy": 0.8121171447038651,
	"eval_chemistry_num_tokens": 12422008.0,
	"eval_chemistry_runtime": 53.9084,
	"eval_chemistry_samples_per_second": 9.275,
	"eval_chemistry_steps_per_second": 9.275,
	"step": 1500
	},
	{
	"epoch": 0.6,
	"eval_physics_entropy": 0.6161783193051815,
	"eval_physics_loss": 0.628398597240448,
	"eval_physics_mean_token_accuracy": 0.8198308848142624,
	"eval_physics_num_tokens": 12422008.0,
	"eval_physics_runtime": 62.5175,
	"eval_physics_samples_per_second": 7.998,
	"eval_physics_steps_per_second": 7.998,
	"step": 1500
	},
	{
	"entropy": 0.6060653101652861,
	"epoch": 0.604,
	"grad_norm": 42.75,
	"learning_rate": 1.886888888888889e-05,
	"loss": 9.894,
	"mean_token_accuracy": 0.8234386540949344,
	"num_tokens": 12505134.0,
	"step": 1510
	},
	{
	"entropy": 0.5880289922468365,
	"epoch": 0.608,
	"grad_norm": 50.75,
	"learning_rate": 1.884666666666667e-05,
	"loss": 9.4441,
	"mean_token_accuracy": 0.8280234813690186,
	"num_tokens": 12583154.0,
	"step": 1520
	},
	{
	"entropy": 0.625719802454114,
	"epoch": 0.612,
	"grad_norm": 41.0,
	"learning_rate": 1.8824444444444445e-05,
	"loss": 10.0379,
	"mean_token_accuracy": 0.8188928976655007,
	"num_tokens": 12666601.0,
	"step": 1530
	},
	{
	"entropy": 0.6189737745560706,
	"epoch": 0.616,
	"grad_norm": 39.0,
	"learning_rate": 1.8802222222222226e-05,
	"loss": 9.953,
	"mean_token_accuracy": 0.8189409743994475,
	"num_tokens": 12746458.0,
	"step": 1540
	},
	{
	"entropy": 0.6307426829822361,
	"epoch": 0.62,
	"grad_norm": 37.0,
	"learning_rate": 1.878e-05,
	"loss": 10.3275,
	"mean_token_accuracy": 0.8165652919560671,
	"num_tokens": 12831572.0,
	"step": 1550
	},
	{
	"entropy": 0.633724972512573,
	"epoch": 0.624,
	"grad_norm": 41.25,
	"learning_rate": 1.875777777777778e-05,
	"loss": 10.0729,
	"mean_token_accuracy": 0.8192374683916569,
	"num_tokens": 12905392.0,
	"step": 1560
	},
	{
	"entropy": 0.6234388993121683,
	"epoch": 0.628,
	"grad_norm": 44.25,
	"learning_rate": 1.873555555555556e-05,
	"loss": 10.1334,
	"mean_token_accuracy": 0.8167661242187023,
	"num_tokens": 12986513.0,
	"step": 1570
	},
	{
	"entropy": 0.6102577080950141,
	"epoch": 0.632,
	"grad_norm": 36.75,
	"learning_rate": 1.8713333333333336e-05,
	"loss": 9.8003,
	"mean_token_accuracy": 0.8206873726099729,
	"num_tokens": 13071058.0,
	"step": 1580
	},
	{
	"entropy": 0.6236647194251418,
	"epoch": 0.636,
	"grad_norm": 43.25,
	"learning_rate": 1.8691111111111114e-05,
	"loss": 10.1304,
	"mean_token_accuracy": 0.816493471711874,
	"num_tokens": 13151842.0,
	"step": 1590
	},
	{
	"entropy": 0.6845891922712326,
	"epoch": 0.64,
	"grad_norm": 45.75,
	"learning_rate": 1.866888888888889e-05,
	"loss": 11.213,
	"mean_token_accuracy": 0.8044512301683426,
	"num_tokens": 13232198.0,
	"step": 1600
	},
	{
	"epoch": 0.64,
	"eval_chemistry_entropy": 0.6778704892992974,
	"eval_chemistry_loss": 0.6664143204689026,
	"eval_chemistry_mean_token_accuracy": 0.8122610586881638,
	"eval_chemistry_num_tokens": 13232198.0,
	"eval_chemistry_runtime": 53.6359,
	"eval_chemistry_samples_per_second": 9.322,
	"eval_chemistry_steps_per_second": 9.322,
	"step": 1600
	},
	{
	"epoch": 0.64,
	"eval_physics_entropy": 0.6401235084533692,
	"eval_physics_loss": 0.6214710474014282,
	"eval_physics_mean_token_accuracy": 0.8208677229285241,
	"eval_physics_num_tokens": 13232198.0,
	"eval_physics_runtime": 62.3791,
	"eval_physics_samples_per_second": 8.016,
	"eval_physics_steps_per_second": 8.016,
	"step": 1600
	},
	{
	"entropy": 0.6061294285580516,
	"epoch": 0.644,
	"grad_norm": 41.5,
	"learning_rate": 1.864666666666667e-05,
	"loss": 9.6671,
	"mean_token_accuracy": 0.8222626011818648,
	"num_tokens": 13318037.0,
	"step": 1610
	},
	{
	"entropy": 0.6353385791182518,
	"epoch": 0.648,
	"grad_norm": 47.5,
	"learning_rate": 1.8624444444444446e-05,
	"loss": 10.2781,
	"mean_token_accuracy": 0.8162215132266283,
	"num_tokens": 13401064.0,
	"step": 1620
	},
	{
	"entropy": 0.6056097308173776,
	"epoch": 0.652,
	"grad_norm": 51.25,
	"learning_rate": 1.8602222222222224e-05,
	"loss": 9.9383,
	"mean_token_accuracy": 0.8226072300225497,
	"num_tokens": 13488222.0,
	"step": 1630
	},
	{
	"entropy": 0.6103159219957888,
	"epoch": 0.656,
	"grad_norm": 39.25,
	"learning_rate": 1.858e-05,
	"loss": 9.7041,
	"mean_token_accuracy": 0.8251269839704036,
	"num_tokens": 13575902.0,
	"step": 1640
	},
	{
	"entropy": 0.6257463837042451,
	"epoch": 0.66,
	"grad_norm": 38.75,
	"learning_rate": 1.855777777777778e-05,
	"loss": 10.1428,
	"mean_token_accuracy": 0.8161589603871107,
	"num_tokens": 13655826.0,
	"step": 1650
	},
	{
	"entropy": 0.6265889365226031,
	"epoch": 0.664,
	"grad_norm": 52.0,
	"learning_rate": 1.8535555555555557e-05,
	"loss": 10.1095,
	"mean_token_accuracy": 0.8177770785987377,
	"num_tokens": 13733192.0,
	"step": 1660
	},
	{
	"entropy": 0.5957706947810948,
	"epoch": 0.668,
	"grad_norm": 35.75,
	"learning_rate": 1.8513333333333335e-05,
	"loss": 9.5903,
	"mean_token_accuracy": 0.8270833406597375,
	"num_tokens": 13816716.0,
	"step": 1670
	},
	{
	"entropy": 0.6371551887132227,
	"epoch": 0.672,
	"grad_norm": 41.75,
	"learning_rate": 1.8491111111111112e-05,
	"loss": 10.4787,
	"mean_token_accuracy": 0.8113816611468792,
	"num_tokens": 13895997.0,
	"step": 1680
	},
	{
	"entropy": 0.5986419206485152,
	"epoch": 0.676,
	"grad_norm": 40.5,
	"learning_rate": 1.846888888888889e-05,
	"loss": 9.5155,
	"mean_token_accuracy": 0.8267723452299833,
	"num_tokens": 13988168.0,
	"step": 1690
	},
	{
	"entropy": 0.5948348139412701,
	"epoch": 0.68,
	"grad_norm": 43.5,
	"learning_rate": 1.8446666666666667e-05,
	"loss": 9.6889,
	"mean_token_accuracy": 0.8268945027142763,
	"num_tokens": 14074579.0,
	"step": 1700
	},
	{
	"epoch": 0.68,
	"eval_chemistry_entropy": 0.6539524466097355,
	"eval_chemistry_loss": 0.6660082340240479,
	"eval_chemistry_mean_token_accuracy": 0.8111258904933929,
	"eval_chemistry_num_tokens": 14074579.0,
	"eval_chemistry_runtime": 53.558,
	"eval_chemistry_samples_per_second": 9.336,
	"eval_chemistry_steps_per_second": 9.336,
	"step": 1700
	},
	{
	"epoch": 0.68,
	"eval_physics_entropy": 0.6102372957170009,
	"eval_physics_loss": 0.6197578310966492,
	"eval_physics_mean_token_accuracy": 0.8214541796445847,
	"eval_physics_num_tokens": 14074579.0,
	"eval_physics_runtime": 62.3426,
	"eval_physics_samples_per_second": 8.02,
	"eval_physics_steps_per_second": 8.02,
	"step": 1700
	},
	{
	"entropy": 0.6658952804282308,
	"epoch": 0.684,
	"grad_norm": 36.75,
	"learning_rate": 1.842444444444445e-05,
	"loss": 10.7562,
	"mean_token_accuracy": 0.8074348546564579,
	"num_tokens": 14153649.0,
	"step": 1710
	},
	{
	"entropy": 0.6083603931590915,
	"epoch": 0.688,
	"grad_norm": 41.5,
	"learning_rate": 1.8402222222222223e-05,
	"loss": 9.7355,
	"mean_token_accuracy": 0.822414780780673,
	"num_tokens": 14234888.0,
	"step": 1720
	},
	{
	"entropy": 0.6043023524805904,
	"epoch": 0.692,
	"grad_norm": 48.25,
	"learning_rate": 1.8380000000000004e-05,
	"loss": 9.8462,
	"mean_token_accuracy": 0.8208967238664627,
	"num_tokens": 14323183.0,
	"step": 1730
	},
	{
	"entropy": 0.613863595854491,
	"epoch": 0.696,
	"grad_norm": 42.25,
	"learning_rate": 1.8357777777777778e-05,
	"loss": 9.8414,
	"mean_token_accuracy": 0.821249233186245,
	"num_tokens": 14411150.0,
	"step": 1740
	},
	{
	"entropy": 0.6170497369021177,
	"epoch": 0.7,
	"grad_norm": 38.0,
	"learning_rate": 1.833555555555556e-05,
	"loss": 10.0544,
	"mean_token_accuracy": 0.8183467876166105,
	"num_tokens": 14490628.0,
	"step": 1750
	},
	{
	"entropy": 0.6329357607290149,
	"epoch": 0.704,
	"grad_norm": 43.75,
	"learning_rate": 1.8313333333333333e-05,
	"loss": 10.3231,
	"mean_token_accuracy": 0.814619118347764,
	"num_tokens": 14567908.0,
	"step": 1760
	},
	{
	"entropy": 0.6202297451905906,
	"epoch": 0.708,
	"grad_norm": 38.25,
	"learning_rate": 1.8291111111111114e-05,
	"loss": 9.8856,
	"mean_token_accuracy": 0.8198208883404732,
	"num_tokens": 14647291.0,
	"step": 1770
	},
	{
	"entropy": 0.5805901409126818,
	"epoch": 0.712,
	"grad_norm": 42.25,
	"learning_rate": 1.8268888888888888e-05,
	"loss": 9.4144,
	"mean_token_accuracy": 0.8300752732902765,
	"num_tokens": 14728975.0,
	"step": 1780
	},
	{
	"entropy": 0.6089818102307618,
	"epoch": 0.716,
	"grad_norm": 41.0,
	"learning_rate": 1.824666666666667e-05,
	"loss": 9.7038,
	"mean_token_accuracy": 0.825373613089323,
	"num_tokens": 14804586.0,
	"step": 1790
	},
	{
	"entropy": 0.6049615413881838,
	"epoch": 0.72,
	"grad_norm": 43.75,
	"learning_rate": 1.8224444444444447e-05,
	"loss": 9.9003,
	"mean_token_accuracy": 0.8198985580354929,
	"num_tokens": 14882927.0,
	"step": 1800
	},
	{
	"epoch": 0.72,
	"eval_chemistry_entropy": 0.6426224761903286,
	"eval_chemistry_loss": 0.6654659509658813,
	"eval_chemistry_mean_token_accuracy": 0.8117904326915741,
	"eval_chemistry_num_tokens": 14882927.0,
	"eval_chemistry_runtime": 53.7762,
	"eval_chemistry_samples_per_second": 9.298,
	"eval_chemistry_steps_per_second": 9.298,
	"step": 1800
	},
	{
	"epoch": 0.72,
	"eval_physics_entropy": 0.6037323722243308,
	"eval_physics_loss": 0.616446316242218,
	"eval_physics_mean_token_accuracy": 0.8222740324139595,
	"eval_physics_num_tokens": 14882927.0,
	"eval_physics_runtime": 62.498,
	"eval_physics_samples_per_second": 8.0,
	"eval_physics_steps_per_second": 8.0,
	"step": 1800
	},
	{
	"entropy": 0.6227391706779599,
	"epoch": 0.724,
	"grad_norm": 43.25,
	"learning_rate": 1.8202222222222225e-05,
	"loss": 9.9987,
	"mean_token_accuracy": 0.818676395714283,
	"num_tokens": 14966717.0,
	"step": 1810
	},
	{
	"entropy": 0.5725922109559178,
	"epoch": 0.728,
	"grad_norm": 42.5,
	"learning_rate": 1.8180000000000002e-05,
	"loss": 9.3114,
	"mean_token_accuracy": 0.8298240959644317,
	"num_tokens": 15052770.0,
	"step": 1820
	},
	{
	"entropy": 0.6312758250162005,
	"epoch": 0.732,
	"grad_norm": 35.0,
	"learning_rate": 1.815777777777778e-05,
	"loss": 10.2655,
	"mean_token_accuracy": 0.8184621930122375,
	"num_tokens": 15135882.0,
	"step": 1830
	},
	{
	"entropy": 0.6022148390300572,
	"epoch": 0.736,
	"grad_norm": 48.0,
	"learning_rate": 1.8135555555555557e-05,
	"loss": 9.6266,
	"mean_token_accuracy": 0.8265880558639764,
	"num_tokens": 15217342.0,
	"step": 1840
	},
	{
	"entropy": 0.6001213543117047,
	"epoch": 0.74,
	"grad_norm": 44.25,
	"learning_rate": 1.8113333333333335e-05,
	"loss": 9.7379,
	"mean_token_accuracy": 0.8232456650584936,
	"num_tokens": 15303623.0,
	"step": 1850
	},
	{
	"entropy": 0.5776225552894175,
	"epoch": 0.744,
	"grad_norm": 46.25,
	"learning_rate": 1.8091111111111113e-05,
	"loss": 9.2318,
	"mean_token_accuracy": 0.8330205090343952,
	"num_tokens": 15385161.0,
	"step": 1860
	},
	{
	"entropy": 0.6180003954097628,
	"epoch": 0.748,
	"grad_norm": 44.25,
	"learning_rate": 1.806888888888889e-05,
	"loss": 10.2082,
	"mean_token_accuracy": 0.8174183562397956,
	"num_tokens": 15466126.0,
	"step": 1870
	},
	{
	"entropy": 0.5681312756612897,
	"epoch": 0.752,
	"grad_norm": 44.75,
	"learning_rate": 1.8046666666666668e-05,
	"loss": 9.0644,
	"mean_token_accuracy": 0.8345625158399343,
	"num_tokens": 15547710.0,
	"step": 1880
	},
	{
	"entropy": 0.6220970245078206,
	"epoch": 0.756,
	"grad_norm": 46.25,
	"learning_rate": 1.8024444444444445e-05,
	"loss": 9.9613,
	"mean_token_accuracy": 0.8187067184597254,
	"num_tokens": 15625904.0,
	"step": 1890
	},
	{
	"entropy": 0.6236506992951035,
	"epoch": 0.76,
	"grad_norm": 43.75,
	"learning_rate": 1.8002222222222223e-05,
	"loss": 10.1366,
	"mean_token_accuracy": 0.8179228503257037,
	"num_tokens": 15704494.0,
	"step": 1900
	},
	{
	"epoch": 0.76,
	"eval_chemistry_entropy": 0.653880989164114,
	"eval_chemistry_loss": 0.6663482189178467,
	"eval_chemistry_mean_token_accuracy": 0.8113617711067199,
	"eval_chemistry_num_tokens": 15704494.0,
	"eval_chemistry_runtime": 53.799,
	"eval_chemistry_samples_per_second": 9.294,
	"eval_chemistry_steps_per_second": 9.294,
	"step": 1900
	},
	{
	"epoch": 0.76,
	"eval_physics_entropy": 0.6113817873895169,
	"eval_physics_loss": 0.6128407716751099,
	"eval_physics_mean_token_accuracy": 0.8226233792304992,
	"eval_physics_num_tokens": 15704494.0,
	"eval_physics_runtime": 62.4981,
	"eval_physics_samples_per_second": 8.0,
	"eval_physics_steps_per_second": 8.0,
	"step": 1900
	},
	{
	"entropy": 0.5962172176688909,
	"epoch": 0.764,
	"grad_norm": 37.0,
	"learning_rate": 1.798e-05,
	"loss": 9.5664,
	"mean_token_accuracy": 0.8239004660397768,
	"num_tokens": 15792219.0,
	"step": 1910
	},
	{
	"entropy": 0.5950108816847205,
	"epoch": 0.768,
	"grad_norm": 38.5,
	"learning_rate": 1.7957777777777778e-05,
	"loss": 9.6608,
	"mean_token_accuracy": 0.8227977603673935,
	"num_tokens": 15877177.0,
	"step": 1920
	},
	{
	"entropy": 0.5919695955701172,
	"epoch": 0.772,
	"grad_norm": 35.0,
	"learning_rate": 1.7935555555555556e-05,
	"loss": 9.5476,
	"mean_token_accuracy": 0.8272939085960388,
	"num_tokens": 15965749.0,
	"step": 1930
	},
	{
	"entropy": 0.6036200723610818,
	"epoch": 0.776,
	"grad_norm": 37.75,
	"learning_rate": 1.7913333333333337e-05,
	"loss": 9.7425,
	"mean_token_accuracy": 0.8256110638380051,
	"num_tokens": 16050530.0,
	"step": 1940
	},
	{
	"entropy": 0.6186987873166799,
	"epoch": 0.78,
	"grad_norm": 39.0,
	"learning_rate": 1.789111111111111e-05,
	"loss": 10.0185,
	"mean_token_accuracy": 0.8216598622500897,
	"num_tokens": 16136804.0,
	"step": 1950
	},
	{
	"entropy": 0.6003677137196064,
	"epoch": 0.784,
	"grad_norm": 42.5,
	"learning_rate": 1.7868888888888892e-05,
	"loss": 9.6501,
	"mean_token_accuracy": 0.8250759091228247,
	"num_tokens": 16219640.0,
	"step": 1960
	},
	{
	"entropy": 0.5993524115532637,
	"epoch": 0.788,
	"grad_norm": 42.5,
	"learning_rate": 1.7846666666666666e-05,
	"loss": 9.5775,
	"mean_token_accuracy": 0.8249216306954622,
	"num_tokens": 16299595.0,
	"step": 1970
	},
	{
	"entropy": 0.616146298404783,
	"epoch": 0.792,
	"grad_norm": 47.5,
	"learning_rate": 1.7824444444444447e-05,
	"loss": 10.0021,
	"mean_token_accuracy": 0.8181390602141618,
	"num_tokens": 16378820.0,
	"step": 1980
	},
	{
	"entropy": 0.6191745470277965,
	"epoch": 0.796,
	"grad_norm": 44.25,
	"learning_rate": 1.780222222222222e-05,
	"loss": 10.0675,
	"mean_token_accuracy": 0.8181126184761525,
	"num_tokens": 16464611.0,
	"step": 1990
	},
	{
	"entropy": 0.6169021054171026,
	"epoch": 0.8,
	"grad_norm": 34.5,
	"learning_rate": 1.7780000000000003e-05,
	"loss": 9.9317,
	"mean_token_accuracy": 0.8213718693703413,
	"num_tokens": 16548261.0,
	"step": 2000
	},
	{
	"epoch": 0.8,
	"eval_chemistry_entropy": 0.6557240565121174,
	"eval_chemistry_loss": 0.6643321514129639,
	"eval_chemistry_mean_token_accuracy": 0.810910725414753,
	"eval_chemistry_num_tokens": 16548261.0,
	"eval_chemistry_runtime": 53.5999,
	"eval_chemistry_samples_per_second": 9.328,
	"eval_chemistry_steps_per_second": 9.328,
	"step": 2000
	},
	{
	"epoch": 0.8,
	"eval_physics_entropy": 0.6022120754122734,
	"eval_physics_loss": 0.6109762787818909,
	"eval_physics_mean_token_accuracy": 0.8232671258449554,
	"eval_physics_num_tokens": 16548261.0,
	"eval_physics_runtime": 62.4211,
	"eval_physics_samples_per_second": 8.01,
	"eval_physics_steps_per_second": 8.01,
	"step": 2000
	},
	{
	"entropy": 0.5769328207708895,
	"epoch": 0.804,
	"grad_norm": 38.25,
	"learning_rate": 1.7757777777777777e-05,
	"loss": 9.3469,
	"mean_token_accuracy": 0.8289602052420377,
	"num_tokens": 16633428.0,
	"step": 2010
	},
	{
	"entropy": 0.639338431507349,
	"epoch": 0.808,
	"grad_norm": 38.75,
	"learning_rate": 1.7735555555555558e-05,
	"loss": 10.3607,
	"mean_token_accuracy": 0.8114439073950053,
	"num_tokens": 16711667.0,
	"step": 2020
	},
	{
	"entropy": 0.6080935266800225,
	"epoch": 0.812,
	"grad_norm": 37.5,
	"learning_rate": 1.7713333333333335e-05,
	"loss": 9.5741,
	"mean_token_accuracy": 0.8260014273226262,
	"num_tokens": 16789903.0,
	"step": 2030
	},
	{
	"entropy": 0.6141686610877514,
	"epoch": 0.816,
	"grad_norm": 34.0,
	"learning_rate": 1.7691111111111113e-05,
	"loss": 10.2542,
	"mean_token_accuracy": 0.8148800980299711,
	"num_tokens": 16870533.0,
	"step": 2040
	},
	{
	"entropy": 0.6198380364105105,
	"epoch": 0.82,
	"grad_norm": 42.0,
	"learning_rate": 1.766888888888889e-05,
	"loss": 9.8252,
	"mean_token_accuracy": 0.8211232393980026,
	"num_tokens": 16955146.0,
	"step": 2050
	},
	{
	"entropy": 0.6109458804130554,
	"epoch": 0.824,
	"grad_norm": 50.25,
	"learning_rate": 1.7646666666666668e-05,
	"loss": 9.9951,
	"mean_token_accuracy": 0.8190602369606494,
	"num_tokens": 17035600.0,
	"step": 2060
	},
	{
	"entropy": 0.616765193361789,
	"epoch": 0.828,
	"grad_norm": 42.0,
	"learning_rate": 1.7624444444444446e-05,
	"loss": 9.8759,
	"mean_token_accuracy": 0.8201179711148143,
	"num_tokens": 17114437.0,
	"step": 2070
	},
	{
	"entropy": 0.585936988517642,
	"epoch": 0.832,
	"grad_norm": 37.25,
	"learning_rate": 1.7602222222222223e-05,
	"loss": 9.4614,
	"mean_token_accuracy": 0.8275429684668779,
	"num_tokens": 17196371.0,
	"step": 2080
	},
	{
	"entropy": 0.6425325162708759,
	"epoch": 0.836,
	"grad_norm": 48.0,
	"learning_rate": 1.758e-05,
	"loss": 10.4242,
	"mean_token_accuracy": 0.8143802944570779,
	"num_tokens": 17277519.0,
	"step": 2090
	},
	{
	"entropy": 0.594513074401766,
	"epoch": 0.84,
	"grad_norm": 39.75,
	"learning_rate": 1.755777777777778e-05,
	"loss": 9.5434,
	"mean_token_accuracy": 0.8270172599703074,
	"num_tokens": 17356919.0,
	"step": 2100
	},
	{
	"epoch": 0.84,
	"eval_chemistry_entropy": 0.6422495054602623,
	"eval_chemistry_loss": 0.6657618284225464,
	"eval_chemistry_mean_token_accuracy": 0.8119068529605865,
	"eval_chemistry_num_tokens": 17356919.0,
	"eval_chemistry_runtime": 53.6953,
	"eval_chemistry_samples_per_second": 9.312,
	"eval_chemistry_steps_per_second": 9.312,
	"step": 2100
	},
	{
	"epoch": 0.84,
	"eval_physics_entropy": 0.5935313543379307,
	"eval_physics_loss": 0.6082729697227478,
	"eval_physics_mean_token_accuracy": 0.8237810920476913,
	"eval_physics_num_tokens": 17356919.0,
	"eval_physics_runtime": 62.7719,
	"eval_physics_samples_per_second": 7.965,
	"eval_physics_steps_per_second": 7.965,
	"step": 2100
	},
	{
	"entropy": 0.5766649033874274,
	"epoch": 0.844,
	"grad_norm": 36.75,
	"learning_rate": 1.7535555555555556e-05,
	"loss": 9.3985,
	"mean_token_accuracy": 0.8289091024547816,
	"num_tokens": 17438912.0,
	"step": 2110
	},
	{
	"entropy": 0.6027551379054785,
	"epoch": 0.848,
	"grad_norm": 41.5,
	"learning_rate": 1.7513333333333334e-05,
	"loss": 9.5153,
	"mean_token_accuracy": 0.8274124126881361,
	"num_tokens": 17527066.0,
	"step": 2120
	},
	{
	"entropy": 0.6090564800426364,
	"epoch": 0.852,
	"grad_norm": 36.25,
	"learning_rate": 1.749111111111111e-05,
	"loss": 9.9486,
	"mean_token_accuracy": 0.8203190270811319,
	"num_tokens": 17610559.0,
	"step": 2130
	},
	{
	"entropy": 0.6409425543621182,
	"epoch": 0.856,
	"grad_norm": 40.5,
	"learning_rate": 1.746888888888889e-05,
	"loss": 10.2511,
	"mean_token_accuracy": 0.8137188758701086,
	"num_tokens": 17689902.0,
	"step": 2140
	},
	{
	"entropy": 0.604229504428804,
	"epoch": 0.86,
	"grad_norm": 45.25,
	"learning_rate": 1.7446666666666667e-05,
	"loss": 9.8022,
	"mean_token_accuracy": 0.8243927512317896,
	"num_tokens": 17774080.0,
	"step": 2150
	},
	{
	"entropy": 0.608985879831016,
	"epoch": 0.864,
	"grad_norm": 39.75,
	"learning_rate": 1.7424444444444444e-05,
	"loss": 9.8919,
	"mean_token_accuracy": 0.8220306746661663,
	"num_tokens": 17859605.0,
	"step": 2160
	},
	{
	"entropy": 0.58911108141765,
	"epoch": 0.868,
	"grad_norm": 36.5,
	"learning_rate": 1.7402222222222222e-05,
	"loss": 9.4426,
	"mean_token_accuracy": 0.8251889403909445,
	"num_tokens": 17942040.0,
	"step": 2170
	},
	{
	"entropy": 0.6174473416060209,
	"epoch": 0.872,
	"grad_norm": 39.0,
	"learning_rate": 1.7380000000000003e-05,
	"loss": 9.9753,
	"mean_token_accuracy": 0.8203635964542627,
	"num_tokens": 18019924.0,
	"step": 2180
	},
	{
	"entropy": 0.6417605724185705,
	"epoch": 0.876,
	"grad_norm": 38.5,
	"learning_rate": 1.735777777777778e-05,
	"loss": 10.2624,
	"mean_token_accuracy": 0.8150792047381401,
	"num_tokens": 18102852.0,
	"step": 2190
	},
	{
	"entropy": 0.6028793597593903,
	"epoch": 0.88,
	"grad_norm": 46.25,
	"learning_rate": 1.7335555555555558e-05,
	"loss": 9.7194,
	"mean_token_accuracy": 0.8240158323198556,
	"num_tokens": 18187315.0,
	"step": 2200
	},
	{
	"epoch": 0.88,
	"eval_chemistry_entropy": 0.6486237399280071,
	"eval_chemistry_loss": 0.6654757261276245,
	"eval_chemistry_mean_token_accuracy": 0.812120854973793,
	"eval_chemistry_num_tokens": 18187315.0,
	"eval_chemistry_runtime": 54.4927,
	"eval_chemistry_samples_per_second": 9.176,
	"eval_chemistry_steps_per_second": 9.176,
	"step": 2200
	},
	{
	"epoch": 0.88,
	"eval_physics_entropy": 0.5944115283489227,
	"eval_physics_loss": 0.6044148206710815,
	"eval_physics_mean_token_accuracy": 0.8247024840712547,
	"eval_physics_num_tokens": 18187315.0,
	"eval_physics_runtime": 63.2321,
	"eval_physics_samples_per_second": 7.907,
	"eval_physics_steps_per_second": 7.907,
	"step": 2200
	},
	{
	"entropy": 0.5587692123837769,
	"epoch": 0.884,
	"grad_norm": 44.75,
	"learning_rate": 1.7313333333333336e-05,
	"loss": 9.1233,
	"mean_token_accuracy": 0.8343214184045792,
	"num_tokens": 18275135.0,
	"step": 2210
	},
	{
	"entropy": 0.5347248839214445,
	"epoch": 0.888,
	"grad_norm": 45.25,
	"learning_rate": 1.7291111111111113e-05,
	"loss": 8.4862,
	"mean_token_accuracy": 0.8402233418077231,
	"num_tokens": 18366329.0,
	"step": 2220
	},
	{
	"entropy": 0.6030035736039281,
	"epoch": 0.892,
	"grad_norm": 43.25,
	"learning_rate": 1.726888888888889e-05,
	"loss": 9.7969,
	"mean_token_accuracy": 0.8230024907737971,
	"num_tokens": 18449966.0,
	"step": 2230
	},
	{
	"entropy": 0.5451280565932393,
	"epoch": 0.896,
	"grad_norm": 35.75,
	"learning_rate": 1.724666666666667e-05,
	"loss": 8.8341,
	"mean_token_accuracy": 0.836723905801773,
	"num_tokens": 18536790.0,
	"step": 2240
	},
	{
	"entropy": 0.5979954308830202,
	"epoch": 0.9,
	"grad_norm": 35.75,
	"learning_rate": 1.7224444444444446e-05,
	"loss": 9.6096,
	"mean_token_accuracy": 0.8243920177221298,
	"num_tokens": 18619194.0,
	"step": 2250
	},
	{
	"entropy": 0.594355533272028,
	"epoch": 0.904,
	"grad_norm": 39.5,
	"learning_rate": 1.7202222222222224e-05,
	"loss": 9.5494,
	"mean_token_accuracy": 0.8267385013401508,
	"num_tokens": 18701809.0,
	"step": 2260
	},
	{
	"entropy": 0.6269824390299619,
	"epoch": 0.908,
	"grad_norm": 38.5,
	"learning_rate": 1.718e-05,
	"loss": 10.0915,
	"mean_token_accuracy": 0.8181608844548464,
	"num_tokens": 18785677.0,
	"step": 2270
	},
	{
	"entropy": 0.6125199305824935,
	"epoch": 0.912,
	"grad_norm": 37.25,
	"learning_rate": 1.715777777777778e-05,
	"loss": 9.9484,
	"mean_token_accuracy": 0.818399741128087,
	"num_tokens": 18869344.0,
	"step": 2280
	},
	{
	"entropy": 0.6096226529218256,
	"epoch": 0.916,
	"grad_norm": 35.25,
	"learning_rate": 1.7135555555555557e-05,
	"loss": 9.8473,
	"mean_token_accuracy": 0.8235837988555431,
	"num_tokens": 18954158.0,
	"step": 2290
	},
	{
	"entropy": 0.5883321419358254,
	"epoch": 0.92,
	"grad_norm": 51.75,
	"learning_rate": 1.7113333333333334e-05,
	"loss": 9.5237,
	"mean_token_accuracy": 0.8259769681841135,
	"num_tokens": 19033910.0,
	"step": 2300
	},
	{
	"epoch": 0.92,
	"eval_chemistry_entropy": 0.6482902157604694,
	"eval_chemistry_loss": 0.6630954742431641,
	"eval_chemistry_mean_token_accuracy": 0.8121933689117432,
	"eval_chemistry_num_tokens": 19033910.0,
	"eval_chemistry_runtime": 53.6836,
	"eval_chemistry_samples_per_second": 9.314,
	"eval_chemistry_steps_per_second": 9.314,
	"step": 2300
	},
	{
	"epoch": 0.92,
	"eval_physics_entropy": 0.5942936807274818,
	"eval_physics_loss": 0.5992915034294128,
	"eval_physics_mean_token_accuracy": 0.8255074183344842,
	"eval_physics_num_tokens": 19033910.0,
	"eval_physics_runtime": 62.5111,
	"eval_physics_samples_per_second": 7.999,
	"eval_physics_steps_per_second": 7.999,
	"step": 2300
	},
	{
	"entropy": 0.5868122247047722,
	"epoch": 0.924,
	"grad_norm": 39.0,
	"learning_rate": 1.7091111111111112e-05,
	"loss": 9.4248,
	"mean_token_accuracy": 0.8281576413661241,
	"num_tokens": 19116000.0,
	"step": 2310
	},
	{
	"entropy": 0.6330606296658516,
	"epoch": 0.928,
	"grad_norm": 42.25,
	"learning_rate": 1.706888888888889e-05,
	"loss": 10.0342,
	"mean_token_accuracy": 0.8173846624791622,
	"num_tokens": 19199834.0,
	"step": 2320
	},
	{
	"entropy": 0.5831953101791442,
	"epoch": 0.932,
	"grad_norm": 43.5,
	"learning_rate": 1.704666666666667e-05,
	"loss": 9.3531,
	"mean_token_accuracy": 0.8273360066115856,
	"num_tokens": 19277906.0,
	"step": 2330
	},
	{
	"entropy": 0.5802978583611548,
	"epoch": 0.936,
	"grad_norm": 39.75,
	"learning_rate": 1.7024444444444445e-05,
	"loss": 9.5706,
	"mean_token_accuracy": 0.8274037476629019,
	"num_tokens": 19361703.0,
	"step": 2340
	},
	{
	"entropy": 0.6136010095477105,
	"epoch": 0.94,
	"grad_norm": 34.75,
	"learning_rate": 1.7002222222222226e-05,
	"loss": 9.7159,
	"mean_token_accuracy": 0.8238754648715257,
	"num_tokens": 19444036.0,
	"step": 2350
	},
	{
	"entropy": 0.5773532028310001,
	"epoch": 0.944,
	"grad_norm": 41.75,
	"learning_rate": 1.698e-05,
	"loss": 9.3904,
	"mean_token_accuracy": 0.8301644638180733,
	"num_tokens": 19525385.0,
	"step": 2360
	},
	{
	"entropy": 0.5946352357976139,
	"epoch": 0.948,
	"grad_norm": 39.5,
	"learning_rate": 1.695777777777778e-05,
	"loss": 9.5084,
	"mean_token_accuracy": 0.8257039908319712,
	"num_tokens": 19606660.0,
	"step": 2370
	},
	{
	"entropy": 0.5877110615372658,
	"epoch": 0.952,
	"grad_norm": 42.25,
	"learning_rate": 1.6935555555555555e-05,
	"loss": 9.5004,
	"mean_token_accuracy": 0.8257838502526283,
	"num_tokens": 19690715.0,
	"step": 2380
	},
	{
	"entropy": 0.5759502210654318,
	"epoch": 0.956,
	"grad_norm": 41.0,
	"learning_rate": 1.6913333333333336e-05,
	"loss": 9.3654,
	"mean_token_accuracy": 0.8302419554442168,
	"num_tokens": 19773293.0,
	"step": 2390
	},
	{
	"entropy": 0.6265336956828833,
	"epoch": 0.96,
	"grad_norm": 36.25,
	"learning_rate": 1.689111111111111e-05,
	"loss": 10.1027,
	"mean_token_accuracy": 0.8185567751526832,
	"num_tokens": 19856973.0,
	"step": 2400
	},
	{
	"epoch": 0.96,
	"eval_chemistry_entropy": 0.6710790105164051,
	"eval_chemistry_loss": 0.66240394115448,
	"eval_chemistry_mean_token_accuracy": 0.8114456446170807,
	"eval_chemistry_num_tokens": 19856973.0,
	"eval_chemistry_runtime": 53.5716,
	"eval_chemistry_samples_per_second": 9.333,
	"eval_chemistry_steps_per_second": 9.333,
	"step": 2400
	},
	{
	"epoch": 0.96,
	"eval_physics_entropy": 0.6094872635900974,
	"eval_physics_loss": 0.5976263284683228,
	"eval_physics_mean_token_accuracy": 0.826532019495964,
	"eval_physics_num_tokens": 19856973.0,
	"eval_physics_runtime": 62.3185,
	"eval_physics_samples_per_second": 8.023,
	"eval_physics_steps_per_second": 8.023,
	"step": 2400
	},
	{
	"entropy": 0.5884977007284761,
	"epoch": 0.964,
	"grad_norm": 45.0,
	"learning_rate": 1.686888888888889e-05,
	"loss": 9.3858,
	"mean_token_accuracy": 0.8279317501932383,
	"num_tokens": 19939168.0,
	"step": 2410
	},
	{
	"entropy": 0.5823706248775125,
	"epoch": 0.968,
	"grad_norm": 42.75,
	"learning_rate": 1.684666666666667e-05,
	"loss": 9.5014,
	"mean_token_accuracy": 0.8305404994636774,
	"num_tokens": 20021093.0,
	"step": 2420
	},
	{
	"entropy": 0.574251430016011,
	"epoch": 0.972,
	"grad_norm": 39.75,
	"learning_rate": 1.6824444444444447e-05,
	"loss": 9.1394,
	"mean_token_accuracy": 0.8329744711518288,
	"num_tokens": 20109033.0,
	"step": 2430
	},
	{
	"entropy": 0.6081912533380092,
	"epoch": 0.976,
	"grad_norm": 44.25,
	"learning_rate": 1.6802222222222224e-05,
	"loss": 9.9884,
	"mean_token_accuracy": 0.8211883638054133,
	"num_tokens": 20190600.0,
	"step": 2440
	},
	{
	"entropy": 0.5859704153612256,
	"epoch": 0.98,
	"grad_norm": 39.5,
	"learning_rate": 1.6780000000000002e-05,
	"loss": 9.3289,
	"mean_token_accuracy": 0.8274181935936212,
	"num_tokens": 20269722.0,
	"step": 2450
	},
	{
	"entropy": 0.5964566855691373,
	"epoch": 0.984,
	"grad_norm": 43.0,
	"learning_rate": 1.675777777777778e-05,
	"loss": 9.6344,
	"mean_token_accuracy": 0.8237358272075653,
	"num_tokens": 20352255.0,
	"step": 2460
	},
	{
	"entropy": 0.5837171670980752,
	"epoch": 0.988,
	"grad_norm": 41.5,
	"learning_rate": 1.6735555555555557e-05,
	"loss": 9.4718,
	"mean_token_accuracy": 0.8284726958721876,
	"num_tokens": 20433069.0,
	"step": 2470
	},
	{
	"entropy": 0.5878238414414227,
	"epoch": 0.992,
	"grad_norm": 39.25,
	"learning_rate": 1.6713333333333335e-05,
	"loss": 9.5302,
	"mean_token_accuracy": 0.8285502199083566,
	"num_tokens": 20518014.0,
	"step": 2480
	},
	{
	"entropy": 0.5914754659868777,
	"epoch": 0.996,
	"grad_norm": 35.5,
	"learning_rate": 1.6691111111111112e-05,
	"loss": 9.4272,
	"mean_token_accuracy": 0.8259847860783338,
	"num_tokens": 20602688.0,
	"step": 2490
	},
	{
	"entropy": 0.565635210648179,
	"epoch": 1.0,
	"grad_norm": 44.75,
	"learning_rate": 1.666888888888889e-05,
	"loss": 9.1451,
	"mean_token_accuracy": 0.8311932869255543,
	"num_tokens": 20686804.0,
	"step": 2500
	},
	{
	"epoch": 1.0,
	"eval_chemistry_entropy": 0.6437437009811401,
	"eval_chemistry_loss": 0.6624347567558289,
	"eval_chemistry_mean_token_accuracy": 0.8123893816471099,
	"eval_chemistry_num_tokens": 20686804.0,
	"eval_chemistry_runtime": 53.5577,
	"eval_chemistry_samples_per_second": 9.336,
	"eval_chemistry_steps_per_second": 9.336,
	"step": 2500
	},
	{
	"epoch": 1.0,
	"eval_physics_entropy": 0.5847585182189942,
	"eval_physics_loss": 0.5949397087097168,
	"eval_physics_mean_token_accuracy": 0.8267857027053833,
	"eval_physics_num_tokens": 20686804.0,
	"eval_physics_runtime": 62.3711,
	"eval_physics_samples_per_second": 8.017,
	"eval_physics_steps_per_second": 8.017,
	"step": 2500
	},
	{
	"entropy": 0.43183089010417464,
	"epoch": 1.004,
	"grad_norm": 43.75,
	"learning_rate": 1.6646666666666668e-05,
	"loss": 6.4646,
	"mean_token_accuracy": 0.8771685600280762,
	"num_tokens": 20773982.0,
	"step": 2510
	},
	{
	"entropy": 0.3832437695004046,
	"epoch": 1.008,
	"grad_norm": 43.0,
	"learning_rate": 1.6624444444444445e-05,
	"loss": 6.4611,
	"mean_token_accuracy": 0.878194584697485,
	"num_tokens": 20859215.0,
	"step": 2520
	},
	{
	"entropy": 0.4238553931005299,
	"epoch": 1.012,
	"grad_norm": 71.5,
	"learning_rate": 1.6602222222222223e-05,
	"loss": 6.7028,
	"mean_token_accuracy": 0.8725548766553402,
	"num_tokens": 20939306.0,
	"step": 2530
	},
	{
	"entropy": 0.39157483652234076,
	"epoch": 1.016,
	"grad_norm": 42.0,
	"learning_rate": 1.658e-05,
	"loss": 6.2925,
	"mean_token_accuracy": 0.8792892958968878,
	"num_tokens": 21019542.0,
	"step": 2540
	},
	{
	"entropy": 0.3955075446516275,
	"epoch": 1.02,
	"grad_norm": 51.0,
	"learning_rate": 1.6557777777777778e-05,
	"loss": 6.4485,
	"mean_token_accuracy": 0.8764517173171044,
	"num_tokens": 21104882.0,
	"step": 2550
	},
	{
	"entropy": 0.41332366890273986,
	"epoch": 1.024,
	"grad_norm": 38.75,
	"learning_rate": 1.6535555555555556e-05,
	"loss": 6.582,
	"mean_token_accuracy": 0.8762725710868835,
	"num_tokens": 21186658.0,
	"step": 2560
	},
	{
	"entropy": 0.38238424006849525,
	"epoch": 1.028,
	"grad_norm": 44.25,
	"learning_rate": 1.6513333333333333e-05,
	"loss": 6.2961,
	"mean_token_accuracy": 0.8797769464552403,
	"num_tokens": 21268030.0,
	"step": 2570
	},
	{
	"entropy": 0.4287768125534058,
	"epoch": 1.032,
	"grad_norm": 44.5,
	"learning_rate": 1.6491111111111114e-05,
	"loss": 6.7601,
	"mean_token_accuracy": 0.8724630124866962,
	"num_tokens": 21351715.0,
	"step": 2580
	},
	{
	"entropy": 0.37041244744323193,
	"epoch": 1.036,
	"grad_norm": 46.75,
	"learning_rate": 1.646888888888889e-05,
	"loss": 6.1737,
	"mean_token_accuracy": 0.8821764189749957,
	"num_tokens": 21431494.0,
	"step": 2590
	},
	{
	"entropy": 0.41900953110307454,
	"epoch": 1.04,
	"grad_norm": 41.5,
	"learning_rate": 1.644666666666667e-05,
	"loss": 6.6902,
	"mean_token_accuracy": 0.8732660066336393,
	"num_tokens": 21517237.0,
	"step": 2600
	},
	{
	"epoch": 1.04,
	"eval_chemistry_entropy": 0.5526932182312012,
	"eval_chemistry_loss": 0.6754207015037537,
	"eval_chemistry_mean_token_accuracy": 0.8118693482875824,
	"eval_chemistry_num_tokens": 21517237.0,
	"eval_chemistry_runtime": 53.6728,
	"eval_chemistry_samples_per_second": 9.316,
	"eval_chemistry_steps_per_second": 9.316,
	"step": 2600
	},
	{
	"epoch": 1.04,
	"eval_physics_entropy": 0.5128993675708771,
	"eval_physics_loss": 0.6065174341201782,
	"eval_physics_mean_token_accuracy": 0.8264631150960923,
	"eval_physics_num_tokens": 21517237.0,
	"eval_physics_runtime": 62.4303,
	"eval_physics_samples_per_second": 8.009,
	"eval_physics_steps_per_second": 8.009,
	"step": 2600
	},
	{
	"entropy": 0.3923122527077794,
	"epoch": 1.044,
	"grad_norm": 52.5,
	"learning_rate": 1.6424444444444444e-05,
	"loss": 6.23,
	"mean_token_accuracy": 0.882063326984644,
	"num_tokens": 21597915.0,
	"step": 2610
	},
	{
	"entropy": 0.4064705569297075,
	"epoch": 1.048,
	"grad_norm": 36.25,
	"learning_rate": 1.6402222222222225e-05,
	"loss": 6.488,
	"mean_token_accuracy": 0.8772788297384977,
	"num_tokens": 21682780.0,
	"step": 2620
	},
	{
	"entropy": 0.38905340125784277,
	"epoch": 1.052,
	"grad_norm": 43.5,
	"learning_rate": 1.638e-05,
	"loss": 6.371,
	"mean_token_accuracy": 0.8803388915956021,
	"num_tokens": 21768676.0,
	"step": 2630
	},
	{
	"entropy": 0.3746905536390841,
	"epoch": 1.056,
	"grad_norm": 36.75,
	"learning_rate": 1.635777777777778e-05,
	"loss": 5.9046,
	"mean_token_accuracy": 0.8856078766286373,
	"num_tokens": 21852528.0,
	"step": 2640
	},
	{
	"entropy": 0.3955009472556412,
	"epoch": 1.06,
	"grad_norm": 46.25,
	"learning_rate": 1.6335555555555558e-05,
	"loss": 6.4522,
	"mean_token_accuracy": 0.8777095880359411,
	"num_tokens": 21939230.0,
	"step": 2650
	},
	{
	"entropy": 0.4184166899416596,
	"epoch": 1.064,
	"grad_norm": 41.5,
	"learning_rate": 1.6313333333333335e-05,
	"loss": 6.6604,
	"mean_token_accuracy": 0.8737866301089525,
	"num_tokens": 22021514.0,
	"step": 2660
	},
	{
	"entropy": 0.4157205421477556,
	"epoch": 1.068,
	"grad_norm": 44.0,
	"learning_rate": 1.6291111111111113e-05,
	"loss": 6.8267,
	"mean_token_accuracy": 0.8705848950892687,
	"num_tokens": 22106780.0,
	"step": 2670
	},
	{
	"entropy": 0.4116486982442439,
	"epoch": 1.072,
	"grad_norm": 35.75,
	"learning_rate": 1.626888888888889e-05,
	"loss": 6.48,
	"mean_token_accuracy": 0.8772596288472414,
	"num_tokens": 22192380.0,
	"step": 2680
	},
	{
	"entropy": 0.40143947368487715,
	"epoch": 1.076,
	"grad_norm": 46.75,
	"learning_rate": 1.6246666666666668e-05,
	"loss": 6.5291,
	"mean_token_accuracy": 0.87435936704278,
	"num_tokens": 22276772.0,
	"step": 2690
	},
	{
	"entropy": 0.4018312363885343,
	"epoch": 1.08,
	"grad_norm": 45.75,
	"learning_rate": 1.6224444444444446e-05,
	"loss": 6.2389,
	"mean_token_accuracy": 0.879636450484395,
	"num_tokens": 22356835.0,
	"step": 2700
	},
	{
	"epoch": 1.08,
	"eval_chemistry_entropy": 0.528339877396822,
	"eval_chemistry_loss": 0.6824756860733032,
	"eval_chemistry_mean_token_accuracy": 0.810719025850296,
	"eval_chemistry_num_tokens": 22356835.0,
	"eval_chemistry_runtime": 54.3738,
	"eval_chemistry_samples_per_second": 9.196,
	"eval_chemistry_steps_per_second": 9.196,
	"step": 2700
	},
	{
	"epoch": 1.08,
	"eval_physics_entropy": 0.48860630974173547,
	"eval_physics_loss": 0.6100344061851501,
	"eval_physics_mean_token_accuracy": 0.8260838712453842,
	"eval_physics_num_tokens": 22356835.0,
	"eval_physics_runtime": 62.4853,
	"eval_physics_samples_per_second": 8.002,
	"eval_physics_steps_per_second": 8.002,
	"step": 2700
	},
	{
	"entropy": 0.3871776068583131,
	"epoch": 1.084,
	"grad_norm": 38.5,
	"learning_rate": 1.6202222222222223e-05,
	"loss": 6.3317,
	"mean_token_accuracy": 0.8779322851449252,
	"num_tokens": 22438638.0,
	"step": 2710
	},
	{
	"entropy": 0.4119948163162917,
	"epoch": 1.088,
	"grad_norm": 59.75,
	"learning_rate": 1.618e-05,
	"loss": 6.6244,
	"mean_token_accuracy": 0.8736134715378284,
	"num_tokens": 22517971.0,
	"step": 2720
	},
	{
	"entropy": 0.39056964181363585,
	"epoch": 1.092,
	"grad_norm": 43.5,
	"learning_rate": 1.615777777777778e-05,
	"loss": 6.2406,
	"mean_token_accuracy": 0.8803118593990803,
	"num_tokens": 22599297.0,
	"step": 2730
	},
	{
	"entropy": 0.4071198822930455,
	"epoch": 1.096,
	"grad_norm": 45.0,
	"learning_rate": 1.6135555555555556e-05,
	"loss": 6.5373,
	"mean_token_accuracy": 0.8748777855187655,
	"num_tokens": 22681680.0,
	"step": 2740
	},
	{
	"entropy": 0.38830908089876176,
	"epoch": 1.1,
	"grad_norm": 42.5,
	"learning_rate": 1.6113333333333334e-05,
	"loss": 6.2908,
	"mean_token_accuracy": 0.8802915759384632,
	"num_tokens": 22768521.0,
	"step": 2750
	},
	{
	"entropy": 0.3899666819255799,
	"epoch": 1.104,
	"grad_norm": 35.0,
	"learning_rate": 1.609111111111111e-05,
	"loss": 6.1995,
	"mean_token_accuracy": 0.8794200260192155,
	"num_tokens": 22848694.0,
	"step": 2760
	},
	{
	"entropy": 0.3982271538116038,
	"epoch": 1.108,
	"grad_norm": 49.5,
	"learning_rate": 1.606888888888889e-05,
	"loss": 6.5132,
	"mean_token_accuracy": 0.8748826995491982,
	"num_tokens": 22934675.0,
	"step": 2770
	},
	{
	"entropy": 0.40925240265205504,
	"epoch": 1.112,
	"grad_norm": 41.0,
	"learning_rate": 1.6046666666666667e-05,
	"loss": 6.3908,
	"mean_token_accuracy": 0.8794612839818001,
	"num_tokens": 23016014.0,
	"step": 2780
	},
	{
	"entropy": 0.3979142210446298,
	"epoch": 1.116,
	"grad_norm": 42.5,
	"learning_rate": 1.6024444444444444e-05,
	"loss": 6.6062,
	"mean_token_accuracy": 0.8738579101860523,
	"num_tokens": 23099672.0,
	"step": 2790
	},
	{
	"entropy": 0.390972594358027,
	"epoch": 1.12,
	"grad_norm": 42.5,
	"learning_rate": 1.6002222222222222e-05,
	"loss": 6.0516,
	"mean_token_accuracy": 0.8840138420462609,
	"num_tokens": 23183889.0,
	"step": 2800
	},
	{
	"epoch": 1.12,
	"eval_chemistry_entropy": 0.5277839957475662,
	"eval_chemistry_loss": 0.6832934617996216,
	"eval_chemistry_mean_token_accuracy": 0.8105767689943314,
	"eval_chemistry_num_tokens": 23183889.0,
	"eval_chemistry_runtime": 53.7065,
	"eval_chemistry_samples_per_second": 9.31,
	"eval_chemistry_steps_per_second": 9.31,
	"step": 2800
	},
	{
	"epoch": 1.12,
	"eval_physics_entropy": 0.49138612353801725,
	"eval_physics_loss": 0.6074111461639404,
	"eval_physics_mean_token_accuracy": 0.8264175375699997,
	"eval_physics_num_tokens": 23183889.0,
	"eval_physics_runtime": 62.3744,
	"eval_physics_samples_per_second": 8.016,
	"eval_physics_steps_per_second": 8.016,
	"step": 2800
	},
	{
	"entropy": 0.35932957073673605,
	"epoch": 1.124,
	"grad_norm": 43.75,
	"learning_rate": 1.5980000000000003e-05,
	"loss": 6.0668,
	"mean_token_accuracy": 0.8830338750034571,
	"num_tokens": 23273263.0,
	"step": 2810
	},
	{
	"entropy": 0.3861358379013836,
	"epoch": 1.1280000000000001,
	"grad_norm": 49.75,
	"learning_rate": 1.5957777777777777e-05,
	"loss": 6.0376,
	"mean_token_accuracy": 0.8845888160169124,
	"num_tokens": 23354096.0,
	"step": 2820
	},
	{
	"entropy": 0.3910831346176565,
	"epoch": 1.1320000000000001,
	"grad_norm": 40.5,
	"learning_rate": 1.5935555555555558e-05,
	"loss": 6.3203,
	"mean_token_accuracy": 0.8786633264273405,
	"num_tokens": 23435009.0,
	"step": 2830
	},
	{
	"entropy": 0.39575566886924207,
	"epoch": 1.1360000000000001,
	"grad_norm": 39.25,
	"learning_rate": 1.5913333333333332e-05,
	"loss": 6.4965,
	"mean_token_accuracy": 0.8768609743565321,
	"num_tokens": 23523903.0,
	"step": 2840
	},
	{
	"entropy": 0.41750739673152565,
	"epoch": 1.1400000000000001,
	"grad_norm": 43.25,
	"learning_rate": 1.5891111111111113e-05,
	"loss": 6.597,
	"mean_token_accuracy": 0.8746554154902697,
	"num_tokens": 23609422.0,
	"step": 2850
	},
	{
	"entropy": 0.40066886888816955,
	"epoch": 1.144,
	"grad_norm": 41.25,
	"learning_rate": 1.5868888888888888e-05,
	"loss": 6.5186,
	"mean_token_accuracy": 0.8758725844323635,
	"num_tokens": 23684571.0,
	"step": 2860
	},
	{
	"entropy": 0.4339528376236558,
	"epoch": 1.148,
	"grad_norm": 40.0,
	"learning_rate": 1.584666666666667e-05,
	"loss": 6.9187,
	"mean_token_accuracy": 0.8712858468294143,
	"num_tokens": 23772422.0,
	"step": 2870
	},
	{
	"entropy": 0.407416142616421,
	"epoch": 1.152,
	"grad_norm": 39.25,
	"learning_rate": 1.5824444444444446e-05,
	"loss": 6.623,
	"mean_token_accuracy": 0.8760526139289141,
	"num_tokens": 23848848.0,
	"step": 2880
	},
	{
	"entropy": 0.41878221230581403,
	"epoch": 1.156,
	"grad_norm": 38.0,
	"learning_rate": 1.5802222222222224e-05,
	"loss": 6.6909,
	"mean_token_accuracy": 0.8737323805689812,
	"num_tokens": 23927139.0,
	"step": 2890
	},
	{
	"entropy": 0.3954612009227276,
	"epoch": 1.16,
	"grad_norm": 48.25,
	"learning_rate": 1.578e-05,
	"loss": 6.3773,
	"mean_token_accuracy": 0.8771356221288442,
	"num_tokens": 24011654.0,
	"step": 2900
	},
	{
	"epoch": 1.16,
	"eval_chemistry_entropy": 0.5298384475111961,
	"eval_chemistry_loss": 0.6839735507965088,
	"eval_chemistry_mean_token_accuracy": 0.8118355718851089,
	"eval_chemistry_num_tokens": 24011654.0,
	"eval_chemistry_runtime": 53.5702,
	"eval_chemistry_samples_per_second": 9.334,
	"eval_chemistry_steps_per_second": 9.334,
	"step": 2900
	},
	{
	"epoch": 1.16,
	"eval_physics_entropy": 0.4960176517665386,
	"eval_physics_loss": 0.6066020131111145,
	"eval_physics_mean_token_accuracy": 0.8260394994020462,
	"eval_physics_num_tokens": 24011654.0,
	"eval_physics_runtime": 62.3484,
	"eval_physics_samples_per_second": 8.019,
	"eval_physics_steps_per_second": 8.019,
	"step": 2900
	},
	{
	"entropy": 0.38181931935250757,
	"epoch": 1.164,
	"grad_norm": 43.25,
	"learning_rate": 1.575777777777778e-05,
	"loss": 6.1702,
	"mean_token_accuracy": 0.8803447645157576,
	"num_tokens": 24090340.0,
	"step": 2910
	},
	{
	"entropy": 0.41627788487821815,
	"epoch": 1.168,
	"grad_norm": 54.75,
	"learning_rate": 1.5735555555555557e-05,
	"loss": 6.6549,
	"mean_token_accuracy": 0.8718316704034805,
	"num_tokens": 24174589.0,
	"step": 2920
	},
	{
	"entropy": 0.3925532539375126,
	"epoch": 1.172,
	"grad_norm": 49.75,
	"learning_rate": 1.5713333333333334e-05,
	"loss": 6.2928,
	"mean_token_accuracy": 0.8777770098298788,
	"num_tokens": 24256063.0,
	"step": 2930
	},
	{
	"entropy": 0.43556569516658783,
	"epoch": 1.176,
	"grad_norm": 43.75,
	"learning_rate": 1.5691111111111112e-05,
	"loss": 7.023,
	"mean_token_accuracy": 0.8686692509800196,
	"num_tokens": 24336249.0,
	"step": 2940
	},
	{
	"entropy": 0.3898361031897366,
	"epoch": 1.18,
	"grad_norm": 36.5,
	"learning_rate": 1.5668888888888893e-05,
	"loss": 6.1418,
	"mean_token_accuracy": 0.8812136992812156,
	"num_tokens": 24415615.0,
	"step": 2950
	},
	{
	"entropy": 0.37849364345893266,
	"epoch": 1.184,
	"grad_norm": 42.5,
	"learning_rate": 1.5646666666666667e-05,
	"loss": 6.2013,
	"mean_token_accuracy": 0.8820504449307919,
	"num_tokens": 24495981.0,
	"step": 2960
	},
	{
	"entropy": 0.4079933548346162,
	"epoch": 1.188,
	"grad_norm": 49.0,
	"learning_rate": 1.5624444444444448e-05,
	"loss": 6.6523,
	"mean_token_accuracy": 0.8723030515015125,
	"num_tokens": 24575688.0,
	"step": 2970
	},
	{
	"entropy": 0.3756624376401305,
	"epoch": 1.192,
	"grad_norm": 42.0,
	"learning_rate": 1.5602222222222222e-05,
	"loss": 5.8133,
	"mean_token_accuracy": 0.8876727018505335,
	"num_tokens": 24658862.0,
	"step": 2980
	},
	{
	"entropy": 0.3933048089966178,
	"epoch": 1.196,
	"grad_norm": 43.25,
	"learning_rate": 1.5580000000000003e-05,
	"loss": 6.577,
	"mean_token_accuracy": 0.8762084610760212,
	"num_tokens": 24742908.0,
	"step": 2990
	},
	{
	"entropy": 0.41905345749109985,
	"epoch": 1.2,
	"grad_norm": 51.0,
	"learning_rate": 1.5557777777777778e-05,
	"loss": 6.5299,
	"mean_token_accuracy": 0.8759240590035915,
	"num_tokens": 24826245.0,
	"step": 3000
	},
	{
	"epoch": 1.2,
	"eval_chemistry_entropy": 0.5453705522418022,
	"eval_chemistry_loss": 0.6793319582939148,
	"eval_chemistry_mean_token_accuracy": 0.8109741320610047,
	"eval_chemistry_num_tokens": 24826245.0,
	"eval_chemistry_runtime": 53.5792,
	"eval_chemistry_samples_per_second": 9.332,
	"eval_chemistry_steps_per_second": 9.332,
	"step": 3000
	},
	{
	"epoch": 1.2,
	"eval_physics_entropy": 0.5037744672298431,
	"eval_physics_loss": 0.6024576425552368,
	"eval_physics_mean_token_accuracy": 0.8275209935307503,
	"eval_physics_num_tokens": 24826245.0,
	"eval_physics_runtime": 62.4678,
	"eval_physics_samples_per_second": 8.004,
	"eval_physics_steps_per_second": 8.004,
	"step": 3000
	}
	],
	"logging_steps": 10,
	"max_steps": 10000,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 4,
	"save_steps": 500,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": false
	},
	"attributes": {}
	}
	},
	"total_flos": 1.6647081277717281e+18,
	"train_batch_size": 1,
	"trial_name": null,
	"trial_params": null
	}