Instructions to use roonbug/b5e92jps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use roonbug/b5e92jps with Transformers:

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

pipe = pipeline("image-text-to-text", model="roonbug/b5e92jps")
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/b5e92jps")
model = AutoModelForImageTextToText.from_pretrained("roonbug/b5e92jps")
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/b5e92jps with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roonbug/b5e92jps"
# 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/b5e92jps",
		"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/b5e92jps

SGLang

How to use roonbug/b5e92jps 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/b5e92jps" \
    --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/b5e92jps",
		"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/b5e92jps" \
        --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/b5e92jps",
		"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/b5e92jps with Docker Model Runner:
```
docker model run hf.co/roonbug/b5e92jps
```

b5e92jps / checkpoint-2000 /trainer_state.json

roonbug

Upload folder using huggingface_hub

6c8f4b6 verified about 1 month ago

raw

history blame contribute delete

88 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.890224225226729,
	"eval_steps": 100,
	"global_step": 2000,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"entropy": 0.7622424783185124,
	"epoch": 0.004451121126133645,
	"grad_norm": 1888.0,
	"learning_rate": 1.8e-07,
	"loss": 36.8185,
	"mean_token_accuracy": 0.6663544788956642,
	"num_tokens": 63133.0,
	"step": 10
	},
	{
	"entropy": 0.8160548411309719,
	"epoch": 0.00890224225226729,
	"grad_norm": 1728.0,
	"learning_rate": 3.8e-07,
	"loss": 36.6381,
	"mean_token_accuracy": 0.649208546616137,
	"num_tokens": 128968.0,
	"step": 20
	},
	{
	"entropy": 0.8332255953922868,
	"epoch": 0.013353363378400934,
	"grad_norm": 948.0,
	"learning_rate": 5.800000000000001e-07,
	"loss": 34.7797,
	"mean_token_accuracy": 0.6578839531168341,
	"num_tokens": 193314.0,
	"step": 30
	},
	{
	"entropy": 0.9456521481275558,
	"epoch": 0.01780448450453458,
	"grad_norm": 716.0,
	"learning_rate": 7.8e-07,
	"loss": 34.1076,
	"mean_token_accuracy": 0.6613732609897852,
	"num_tokens": 257189.0,
	"step": 40
	},
	{
	"entropy": 0.9749895730987191,
	"epoch": 0.022255605630668224,
	"grad_norm": 660.0,
	"learning_rate": 9.800000000000001e-07,
	"loss": 29.937,
	"mean_token_accuracy": 0.6729008939117194,
	"num_tokens": 324224.0,
	"step": 50
	},
	{
	"entropy": 1.0305172327905894,
	"epoch": 0.026706726756801868,
	"grad_norm": 492.0,
	"learning_rate": 1.1800000000000001e-06,
	"loss": 28.3561,
	"mean_token_accuracy": 0.680633837915957,
	"num_tokens": 394654.0,
	"step": 60
	},
	{
	"entropy": 1.0123192116618156,
	"epoch": 0.031157847882935515,
	"grad_norm": 404.0,
	"learning_rate": 1.3800000000000001e-06,
	"loss": 26.0449,
	"mean_token_accuracy": 0.6903208963572979,
	"num_tokens": 461658.0,
	"step": 70
	},
	{
	"entropy": 1.024911842495203,
	"epoch": 0.03560896900906916,
	"grad_norm": 250.0,
	"learning_rate": 1.5800000000000001e-06,
	"loss": 23.6986,
	"mean_token_accuracy": 0.6996766375377774,
	"num_tokens": 528285.0,
	"step": 80
	},
	{
	"entropy": 1.0939506959170102,
	"epoch": 0.04006009013520281,
	"grad_norm": 227.0,
	"learning_rate": 1.7800000000000001e-06,
	"loss": 23.2949,
	"mean_token_accuracy": 0.6969541085883975,
	"num_tokens": 595336.0,
	"step": 90
	},
	{
	"entropy": 1.0676697574555873,
	"epoch": 0.04451121126133645,
	"grad_norm": 278.0,
	"learning_rate": 1.98e-06,
	"loss": 21.5533,
	"mean_token_accuracy": 0.7063678905367852,
	"num_tokens": 663126.0,
	"step": 100
	},
	{
	"epoch": 0.04451121126133645,
	"eval_biology_entropy": 1.5063953498601914,
	"eval_biology_loss": 1.9373619556427002,
	"eval_biology_mean_token_accuracy": 0.6030384682416916,
	"eval_biology_num_tokens": 663126.0,
	"eval_biology_runtime": 37.2317,
	"eval_biology_samples_per_second": 13.429,
	"eval_biology_steps_per_second": 13.429,
	"step": 100
	},
	{
	"epoch": 0.04451121126133645,
	"eval_chemistry_entropy": 1.0538504299521447,
	"eval_chemistry_loss": 1.2949438095092773,
	"eval_chemistry_mean_token_accuracy": 0.7114702309370041,
	"eval_chemistry_num_tokens": 663126.0,
	"eval_chemistry_runtime": 41.1049,
	"eval_chemistry_samples_per_second": 12.164,
	"eval_chemistry_steps_per_second": 12.164,
	"step": 100
	},
	{
	"epoch": 0.04451121126133645,
	"eval_math_entropy": 0.8524410739541054,
	"eval_math_loss": 1.2029013633728027,
	"eval_math_mean_token_accuracy": 0.7322385207414627,
	"eval_math_num_tokens": 663126.0,
	"eval_math_runtime": 41.5152,
	"eval_math_samples_per_second": 12.044,
	"eval_math_steps_per_second": 12.044,
	"step": 100
	},
	{
	"epoch": 0.04451121126133645,
	"eval_physics_entropy": 0.9442882173061371,
	"eval_physics_loss": 1.1572656631469727,
	"eval_physics_mean_token_accuracy": 0.7343679416179657,
	"eval_physics_num_tokens": 663126.0,
	"eval_physics_runtime": 45.8024,
	"eval_physics_samples_per_second": 10.916,
	"eval_physics_steps_per_second": 10.916,
	"step": 100
	},
	{
	"entropy": 1.0567705381661654,
	"epoch": 0.048962332387470095,
	"grad_norm": 202.0,
	"learning_rate": 2.1800000000000003e-06,
	"loss": 20.0858,
	"mean_token_accuracy": 0.7180810730904341,
	"num_tokens": 731060.0,
	"step": 110
	},
	{
	"entropy": 1.0101547280326486,
	"epoch": 0.053413453513603736,
	"grad_norm": 202.0,
	"learning_rate": 2.38e-06,
	"loss": 18.8763,
	"mean_token_accuracy": 0.7310481067746878,
	"num_tokens": 801635.0,
	"step": 120
	},
	{
	"entropy": 1.0049639470875262,
	"epoch": 0.05786457463973738,
	"grad_norm": 154.0,
	"learning_rate": 2.5800000000000003e-06,
	"loss": 19.1729,
	"mean_token_accuracy": 0.7293503576889634,
	"num_tokens": 867260.0,
	"step": 130
	},
	{
	"entropy": 1.0176106113940477,
	"epoch": 0.06231569576587103,
	"grad_norm": 144.0,
	"learning_rate": 2.7800000000000005e-06,
	"loss": 18.97,
	"mean_token_accuracy": 0.7298020845279097,
	"num_tokens": 931344.0,
	"step": 140
	},
	{
	"entropy": 1.0698495015501976,
	"epoch": 0.06676681689200467,
	"grad_norm": 169.0,
	"learning_rate": 2.9800000000000003e-06,
	"loss": 17.4943,
	"mean_token_accuracy": 0.7370716020464897,
	"num_tokens": 993586.0,
	"step": 150
	},
	{
	"entropy": 1.0634983357042074,
	"epoch": 0.07121793801813832,
	"grad_norm": 123.0,
	"learning_rate": 3.1800000000000005e-06,
	"loss": 16.9373,
	"mean_token_accuracy": 0.7367568526417017,
	"num_tokens": 1060812.0,
	"step": 160
	},
	{
	"entropy": 1.0108168195933103,
	"epoch": 0.07566905914427197,
	"grad_norm": 125.0,
	"learning_rate": 3.3800000000000007e-06,
	"loss": 15.569,
	"mean_token_accuracy": 0.7519758876413107,
	"num_tokens": 1131832.0,
	"step": 170
	},
	{
	"entropy": 0.9829567475244403,
	"epoch": 0.08012018027040561,
	"grad_norm": 99.0,
	"learning_rate": 3.58e-06,
	"loss": 15.2082,
	"mean_token_accuracy": 0.7475447814911604,
	"num_tokens": 1200650.0,
	"step": 180
	},
	{
	"entropy": 0.9538513226434588,
	"epoch": 0.08457130139653925,
	"grad_norm": 119.0,
	"learning_rate": 3.7800000000000002e-06,
	"loss": 15.0014,
	"mean_token_accuracy": 0.7515964422374963,
	"num_tokens": 1265107.0,
	"step": 190
	},
	{
	"entropy": 0.9125228714197874,
	"epoch": 0.0890224225226729,
	"grad_norm": 117.0,
	"learning_rate": 3.980000000000001e-06,
	"loss": 14.4833,
	"mean_token_accuracy": 0.7538308618590236,
	"num_tokens": 1327380.0,
	"step": 200
	},
	{
	"epoch": 0.0890224225226729,
	"eval_biology_entropy": 1.280277446448803,
	"eval_biology_loss": 1.453066349029541,
	"eval_biology_mean_token_accuracy": 0.6518876985907555,
	"eval_biology_num_tokens": 1327380.0,
	"eval_biology_runtime": 36.821,
	"eval_biology_samples_per_second": 13.579,
	"eval_biology_steps_per_second": 13.579,
	"step": 200
	},
	{
	"epoch": 0.0890224225226729,
	"eval_chemistry_entropy": 0.8954760466217995,
	"eval_chemistry_loss": 0.9106767177581787,
	"eval_chemistry_mean_token_accuracy": 0.7551076735854149,
	"eval_chemistry_num_tokens": 1327380.0,
	"eval_chemistry_runtime": 40.4689,
	"eval_chemistry_samples_per_second": 12.355,
	"eval_chemistry_steps_per_second": 12.355,
	"step": 200
	},
	{
	"epoch": 0.0890224225226729,
	"eval_math_entropy": 0.7658050524294376,
	"eval_math_loss": 0.9040815234184265,
	"eval_math_mean_token_accuracy": 0.7642563463449478,
	"eval_math_num_tokens": 1327380.0,
	"eval_math_runtime": 41.4556,
	"eval_math_samples_per_second": 12.061,
	"eval_math_steps_per_second": 12.061,
	"step": 200
	},
	{
	"epoch": 0.0890224225226729,
	"eval_physics_entropy": 0.8174435417056084,
	"eval_physics_loss": 0.8484614491462708,
	"eval_physics_mean_token_accuracy": 0.7708570960760116,
	"eval_physics_num_tokens": 1327380.0,
	"eval_physics_runtime": 45.875,
	"eval_physics_samples_per_second": 10.899,
	"eval_physics_steps_per_second": 10.899,
	"step": 200
	},
	{
	"entropy": 0.9408239619806409,
	"epoch": 0.09347354364880654,
	"grad_norm": 126.5,
	"learning_rate": 4.18e-06,
	"loss": 15.2387,
	"mean_token_accuracy": 0.7457781180739402,
	"num_tokens": 1393379.0,
	"step": 210
	},
	{
	"entropy": 0.8950148992240429,
	"epoch": 0.09792466477494019,
	"grad_norm": 95.0,
	"learning_rate": 4.38e-06,
	"loss": 14.2337,
	"mean_token_accuracy": 0.7587446294724941,
	"num_tokens": 1460130.0,
	"step": 220
	},
	{
	"entropy": 0.859116705879569,
	"epoch": 0.10237578590107384,
	"grad_norm": 94.0,
	"learning_rate": 4.58e-06,
	"loss": 13.7082,
	"mean_token_accuracy": 0.76347241923213,
	"num_tokens": 1529183.0,
	"step": 230
	},
	{
	"entropy": 0.8980951353907585,
	"epoch": 0.10682690702720747,
	"grad_norm": 118.5,
	"learning_rate": 4.78e-06,
	"loss": 14.5897,
	"mean_token_accuracy": 0.7553087200969457,
	"num_tokens": 1597405.0,
	"step": 240
	},
	{
	"entropy": 0.9019628280773759,
	"epoch": 0.11127802815334112,
	"grad_norm": 98.5,
	"learning_rate": 4.980000000000001e-06,
	"loss": 14.5049,
	"mean_token_accuracy": 0.7539074700325727,
	"num_tokens": 1661767.0,
	"step": 250
	},
	{
	"entropy": 0.9095736019313335,
	"epoch": 0.11572914927947477,
	"grad_norm": 80.0,
	"learning_rate": 5.18e-06,
	"loss": 14.553,
	"mean_token_accuracy": 0.7567780796438456,
	"num_tokens": 1728207.0,
	"step": 260
	},
	{
	"entropy": 0.855735239200294,
	"epoch": 0.12018027040560841,
	"grad_norm": 99.0,
	"learning_rate": 5.380000000000001e-06,
	"loss": 13.731,
	"mean_token_accuracy": 0.7652106903493404,
	"num_tokens": 1796055.0,
	"step": 270
	},
	{
	"entropy": 0.830021676234901,
	"epoch": 0.12463139153174206,
	"grad_norm": 97.5,
	"learning_rate": 5.580000000000001e-06,
	"loss": 13.2554,
	"mean_token_accuracy": 0.7721017152070999,
	"num_tokens": 1859684.0,
	"step": 280
	},
	{
	"entropy": 0.8921441739425063,
	"epoch": 0.1290825126578757,
	"grad_norm": 106.5,
	"learning_rate": 5.78e-06,
	"loss": 14.4012,
	"mean_token_accuracy": 0.7561684042215348,
	"num_tokens": 1921704.0,
	"step": 290
	},
	{
	"entropy": 0.8731818461790681,
	"epoch": 0.13353363378400934,
	"grad_norm": 87.5,
	"learning_rate": 5.98e-06,
	"loss": 13.9502,
	"mean_token_accuracy": 0.7628704030066729,
	"num_tokens": 1985766.0,
	"step": 300
	},
	{
	"epoch": 0.13353363378400934,
	"eval_biology_entropy": 1.2637426958680154,
	"eval_biology_loss": 1.3796980381011963,
	"eval_biology_mean_token_accuracy": 0.6648430502414704,
	"eval_biology_num_tokens": 1985766.0,
	"eval_biology_runtime": 37.0397,
	"eval_biology_samples_per_second": 13.499,
	"eval_biology_steps_per_second": 13.499,
	"step": 300
	},
	{
	"epoch": 0.13353363378400934,
	"eval_chemistry_entropy": 0.8489444836974144,
	"eval_chemistry_loss": 0.8385273814201355,
	"eval_chemistry_mean_token_accuracy": 0.7699487572312355,
	"eval_chemistry_num_tokens": 1985766.0,
	"eval_chemistry_runtime": 40.8665,
	"eval_chemistry_samples_per_second": 12.235,
	"eval_chemistry_steps_per_second": 12.235,
	"step": 300
	},
	{
	"epoch": 0.13353363378400934,
	"eval_math_entropy": 0.7357360773980618,
	"eval_math_loss": 0.8767910599708557,
	"eval_math_mean_token_accuracy": 0.7708948514461518,
	"eval_math_num_tokens": 1985766.0,
	"eval_math_runtime": 41.8192,
	"eval_math_samples_per_second": 11.956,
	"eval_math_steps_per_second": 11.956,
	"step": 300
	},
	{
	"epoch": 0.13353363378400934,
	"eval_physics_entropy": 0.7905060887336731,
	"eval_physics_loss": 0.7890318632125854,
	"eval_physics_mean_token_accuracy": 0.7825853993296623,
	"eval_physics_num_tokens": 1985766.0,
	"eval_physics_runtime": 46.1418,
	"eval_physics_samples_per_second": 10.836,
	"eval_physics_steps_per_second": 10.836,
	"step": 300
	},
	{
	"entropy": 0.8452363438904286,
	"epoch": 0.137984754910143,
	"grad_norm": 96.0,
	"learning_rate": 6.18e-06,
	"loss": 13.634,
	"mean_token_accuracy": 0.7645608998835087,
	"num_tokens": 2049041.0,
	"step": 310
	},
	{
	"entropy": 0.8076417898759246,
	"epoch": 0.14243587603627664,
	"grad_norm": 80.5,
	"learning_rate": 6.380000000000001e-06,
	"loss": 12.8943,
	"mean_token_accuracy": 0.7760006580501795,
	"num_tokens": 2118068.0,
	"step": 320
	},
	{
	"entropy": 0.8085115062072873,
	"epoch": 0.14688699716241027,
	"grad_norm": 106.5,
	"learning_rate": 6.5800000000000005e-06,
	"loss": 12.7928,
	"mean_token_accuracy": 0.7790838234126568,
	"num_tokens": 2186387.0,
	"step": 330
	},
	{
	"entropy": 0.824213713593781,
	"epoch": 0.15133811828854393,
	"grad_norm": 82.5,
	"learning_rate": 6.780000000000001e-06,
	"loss": 13.389,
	"mean_token_accuracy": 0.7689453203231096,
	"num_tokens": 2252650.0,
	"step": 340
	},
	{
	"entropy": 0.797634300775826,
	"epoch": 0.15578923941467757,
	"grad_norm": 85.5,
	"learning_rate": 6.98e-06,
	"loss": 12.8088,
	"mean_token_accuracy": 0.7797435287386179,
	"num_tokens": 2320358.0,
	"step": 350
	},
	{
	"entropy": 0.7920836627483367,
	"epoch": 0.16024036054081123,
	"grad_norm": 88.0,
	"learning_rate": 7.180000000000001e-06,
	"loss": 12.6336,
	"mean_token_accuracy": 0.7806293956935406,
	"num_tokens": 2388824.0,
	"step": 360
	},
	{
	"entropy": 0.7749077206477523,
	"epoch": 0.16469148166694486,
	"grad_norm": 80.5,
	"learning_rate": 7.3800000000000005e-06,
	"loss": 12.3995,
	"mean_token_accuracy": 0.7864189695566892,
	"num_tokens": 2456144.0,
	"step": 370
	},
	{
	"entropy": 0.8578483302146196,
	"epoch": 0.1691426027930785,
	"grad_norm": 81.0,
	"learning_rate": 7.58e-06,
	"loss": 13.8496,
	"mean_token_accuracy": 0.7662820883095265,
	"num_tokens": 2515325.0,
	"step": 380
	},
	{
	"entropy": 0.7971056224778295,
	"epoch": 0.17359372391921216,
	"grad_norm": 68.0,
	"learning_rate": 7.78e-06,
	"loss": 12.6922,
	"mean_token_accuracy": 0.7778837148100137,
	"num_tokens": 2580490.0,
	"step": 390
	},
	{
	"entropy": 0.7984419580549001,
	"epoch": 0.1780448450453458,
	"grad_norm": 70.5,
	"learning_rate": 7.980000000000002e-06,
	"loss": 12.8255,
	"mean_token_accuracy": 0.7773921977728605,
	"num_tokens": 2644330.0,
	"step": 400
	},
	{
	"epoch": 0.1780448450453458,
	"eval_biology_entropy": 1.2305693982243537,
	"eval_biology_loss": 1.3490314483642578,
	"eval_biology_mean_token_accuracy": 0.6716532117724419,
	"eval_biology_num_tokens": 2644330.0,
	"eval_biology_runtime": 36.6001,
	"eval_biology_samples_per_second": 13.661,
	"eval_biology_steps_per_second": 13.661,
	"step": 400
	},
	{
	"epoch": 0.1780448450453458,
	"eval_chemistry_entropy": 0.7882854393720626,
	"eval_chemistry_loss": 0.7991188764572144,
	"eval_chemistry_mean_token_accuracy": 0.778610565006733,
	"eval_chemistry_num_tokens": 2644330.0,
	"eval_chemistry_runtime": 40.3843,
	"eval_chemistry_samples_per_second": 12.381,
	"eval_chemistry_steps_per_second": 12.381,
	"step": 400
	},
	{
	"epoch": 0.1780448450453458,
	"eval_math_entropy": 0.6974474709928036,
	"eval_math_loss": 0.8647986054420471,
	"eval_math_mean_token_accuracy": 0.7742947788238526,
	"eval_math_num_tokens": 2644330.0,
	"eval_math_runtime": 41.8502,
	"eval_math_samples_per_second": 11.947,
	"eval_math_steps_per_second": 11.947,
	"step": 400
	},
	{
	"epoch": 0.1780448450453458,
	"eval_physics_entropy": 0.740912606716156,
	"eval_physics_loss": 0.7630434632301331,
	"eval_physics_mean_token_accuracy": 0.7882855938673019,
	"eval_physics_num_tokens": 2644330.0,
	"eval_physics_runtime": 46.1492,
	"eval_physics_samples_per_second": 10.834,
	"eval_physics_steps_per_second": 10.834,
	"step": 400
	},
	{
	"entropy": 0.7443430663086474,
	"epoch": 0.18249596617147945,
	"grad_norm": 72.5,
	"learning_rate": 8.18e-06,
	"loss": 11.7994,
	"mean_token_accuracy": 0.7938185524195432,
	"num_tokens": 2713234.0,
	"step": 410
	},
	{
	"entropy": 0.7856309018097818,
	"epoch": 0.18694708729761308,
	"grad_norm": 78.0,
	"learning_rate": 8.380000000000001e-06,
	"loss": 12.9567,
	"mean_token_accuracy": 0.7781453486531973,
	"num_tokens": 2783261.0,
	"step": 420
	},
	{
	"entropy": 0.799421458132565,
	"epoch": 0.19139820842374672,
	"grad_norm": 61.25,
	"learning_rate": 8.580000000000001e-06,
	"loss": 12.6392,
	"mean_token_accuracy": 0.7806750666350126,
	"num_tokens": 2850170.0,
	"step": 430
	},
	{
	"entropy": 0.7786322007887065,
	"epoch": 0.19584932954988038,
	"grad_norm": 80.5,
	"learning_rate": 8.78e-06,
	"loss": 12.4988,
	"mean_token_accuracy": 0.7827117882668972,
	"num_tokens": 2913700.0,
	"step": 440
	},
	{
	"entropy": 0.763565490860492,
	"epoch": 0.200300450676014,
	"grad_norm": 81.0,
	"learning_rate": 8.98e-06,
	"loss": 12.4779,
	"mean_token_accuracy": 0.7831043265759945,
	"num_tokens": 2981212.0,
	"step": 450
	},
	{
	"entropy": 0.7708647299557925,
	"epoch": 0.20475157180214767,
	"grad_norm": 85.0,
	"learning_rate": 9.180000000000002e-06,
	"loss": 12.1503,
	"mean_token_accuracy": 0.7912418570369482,
	"num_tokens": 3048973.0,
	"step": 460
	},
	{
	"entropy": 0.769937212113291,
	"epoch": 0.2092026929282813,
	"grad_norm": 62.0,
	"learning_rate": 9.38e-06,
	"loss": 12.6137,
	"mean_token_accuracy": 0.7829986553639173,
	"num_tokens": 3117033.0,
	"step": 470
	},
	{
	"entropy": 0.7863288868218661,
	"epoch": 0.21365381405441494,
	"grad_norm": 74.5,
	"learning_rate": 9.58e-06,
	"loss": 12.3857,
	"mean_token_accuracy": 0.7842021461576223,
	"num_tokens": 3185255.0,
	"step": 480
	},
	{
	"entropy": 0.7699232887476682,
	"epoch": 0.2181049351805486,
	"grad_norm": 74.5,
	"learning_rate": 9.780000000000001e-06,
	"loss": 12.4166,
	"mean_token_accuracy": 0.7846909243613481,
	"num_tokens": 3253121.0,
	"step": 490
	},
	{
	"entropy": 0.7251296367496252,
	"epoch": 0.22255605630668224,
	"grad_norm": 75.0,
	"learning_rate": 9.980000000000001e-06,
	"loss": 11.4498,
	"mean_token_accuracy": 0.7972834445536137,
	"num_tokens": 3322823.0,
	"step": 500
	},
	{
	"epoch": 0.22255605630668224,
	"eval_biology_entropy": 1.1898637573719024,
	"eval_biology_loss": 1.338150978088379,
	"eval_biology_mean_token_accuracy": 0.6746688461303711,
	"eval_biology_num_tokens": 3322823.0,
	"eval_biology_runtime": 37.4484,
	"eval_biology_samples_per_second": 13.352,
	"eval_biology_steps_per_second": 13.352,
	"step": 500
	},
	{
	"epoch": 0.22255605630668224,
	"eval_chemistry_entropy": 0.7506220785379409,
	"eval_chemistry_loss": 0.7758934497833252,
	"eval_chemistry_mean_token_accuracy": 0.7828538768291473,
	"eval_chemistry_num_tokens": 3322823.0,
	"eval_chemistry_runtime": 40.7375,
	"eval_chemistry_samples_per_second": 12.274,
	"eval_chemistry_steps_per_second": 12.274,
	"step": 500
	},
	{
	"epoch": 0.22255605630668224,
	"eval_math_entropy": 0.6889803909361363,
	"eval_math_loss": 0.8622512817382812,
	"eval_math_mean_token_accuracy": 0.7754237843751908,
	"eval_math_num_tokens": 3322823.0,
	"eval_math_runtime": 41.9238,
	"eval_math_samples_per_second": 11.926,
	"eval_math_steps_per_second": 11.926,
	"step": 500
	},
	{
	"epoch": 0.22255605630668224,
	"eval_physics_entropy": 0.7242196025848389,
	"eval_physics_loss": 0.7506964802742004,
	"eval_physics_mean_token_accuracy": 0.7921671935915947,
	"eval_physics_num_tokens": 3322823.0,
	"eval_physics_runtime": 45.9692,
	"eval_physics_samples_per_second": 10.877,
	"eval_physics_steps_per_second": 10.877,
	"step": 500
	},
	{
	"entropy": 0.7351194931194186,
	"epoch": 0.2270071774328159,
	"grad_norm": 75.0,
	"learning_rate": 1.018e-05,
	"loss": 11.9225,
	"mean_token_accuracy": 0.7910898551344872,
	"num_tokens": 3393393.0,
	"step": 510
	},
	{
	"entropy": 0.8338562373071909,
	"epoch": 0.23145829855894953,
	"grad_norm": 79.0,
	"learning_rate": 1.038e-05,
	"loss": 13.1291,
	"mean_token_accuracy": 0.774738060683012,
	"num_tokens": 3454750.0,
	"step": 520
	},
	{
	"entropy": 0.7108834735117853,
	"epoch": 0.2359094196850832,
	"grad_norm": 70.5,
	"learning_rate": 1.0580000000000002e-05,
	"loss": 11.7207,
	"mean_token_accuracy": 0.7975892208516597,
	"num_tokens": 3526914.0,
	"step": 530
	},
	{
	"entropy": 0.8373067150823772,
	"epoch": 0.24036054081121683,
	"grad_norm": 72.0,
	"learning_rate": 1.0780000000000002e-05,
	"loss": 13.0512,
	"mean_token_accuracy": 0.7754946660250426,
	"num_tokens": 3589449.0,
	"step": 540
	},
	{
	"entropy": 0.7569006633013486,
	"epoch": 0.24481166193735046,
	"grad_norm": 79.0,
	"learning_rate": 1.0980000000000002e-05,
	"loss": 12.267,
	"mean_token_accuracy": 0.786787087097764,
	"num_tokens": 3655092.0,
	"step": 550
	},
	{
	"entropy": 0.7805684333667159,
	"epoch": 0.24926278306348412,
	"grad_norm": 93.5,
	"learning_rate": 1.1180000000000001e-05,
	"loss": 12.5142,
	"mean_token_accuracy": 0.7839910417795182,
	"num_tokens": 3719113.0,
	"step": 560
	},
	{
	"entropy": 0.7685065409168601,
	"epoch": 0.25371390418961776,
	"grad_norm": 65.5,
	"learning_rate": 1.138e-05,
	"loss": 12.4558,
	"mean_token_accuracy": 0.7818987771868706,
	"num_tokens": 3785282.0,
	"step": 570
	},
	{
	"entropy": 0.774918237887323,
	"epoch": 0.2581650253157514,
	"grad_norm": 61.25,
	"learning_rate": 1.1580000000000001e-05,
	"loss": 12.415,
	"mean_token_accuracy": 0.7842379476875067,
	"num_tokens": 3852276.0,
	"step": 580
	},
	{
	"entropy": 0.7105797030963004,
	"epoch": 0.262616146441885,
	"grad_norm": 67.5,
	"learning_rate": 1.178e-05,
	"loss": 11.3721,
	"mean_token_accuracy": 0.7995343253016471,
	"num_tokens": 3925649.0,
	"step": 590
	},
	{
	"entropy": 0.7462131816893816,
	"epoch": 0.2670672675680187,
	"grad_norm": 74.5,
	"learning_rate": 1.198e-05,
	"loss": 11.8831,
	"mean_token_accuracy": 0.7898255579173565,
	"num_tokens": 3990505.0,
	"step": 600
	},
	{
	"epoch": 0.2670672675680187,
	"eval_biology_entropy": 1.2392896317243576,
	"eval_biology_loss": 1.3273310661315918,
	"eval_biology_mean_token_accuracy": 0.6752943544387817,
	"eval_biology_num_tokens": 3990505.0,
	"eval_biology_runtime": 36.4668,
	"eval_biology_samples_per_second": 13.711,
	"eval_biology_steps_per_second": 13.711,
	"step": 600
	},
	{
	"epoch": 0.2670672675680187,
	"eval_chemistry_entropy": 0.7596916342377663,
	"eval_chemistry_loss": 0.7626407742500305,
	"eval_chemistry_mean_token_accuracy": 0.7862690081000328,
	"eval_chemistry_num_tokens": 3990505.0,
	"eval_chemistry_runtime": 40.266,
	"eval_chemistry_samples_per_second": 12.417,
	"eval_chemistry_steps_per_second": 12.417,
	"step": 600
	},
	{
	"epoch": 0.2670672675680187,
	"eval_math_entropy": 0.6872916958034039,
	"eval_math_loss": 0.8660696148872375,
	"eval_math_mean_token_accuracy": 0.7750280216932297,
	"eval_math_num_tokens": 3990505.0,
	"eval_math_runtime": 41.4933,
	"eval_math_samples_per_second": 12.05,
	"eval_math_steps_per_second": 12.05,
	"step": 600
	},
	{
	"epoch": 0.2670672675680187,
	"eval_physics_entropy": 0.7289359270334244,
	"eval_physics_loss": 0.744917631149292,
	"eval_physics_mean_token_accuracy": 0.7920673425793647,
	"eval_physics_num_tokens": 3990505.0,
	"eval_physics_runtime": 46.0067,
	"eval_physics_samples_per_second": 10.868,
	"eval_physics_steps_per_second": 10.868,
	"step": 600
	},
	{
	"entropy": 0.7445939108729362,
	"epoch": 0.27151838869415235,
	"grad_norm": 65.5,
	"learning_rate": 1.218e-05,
	"loss": 11.9377,
	"mean_token_accuracy": 0.790003751963377,
	"num_tokens": 4060657.0,
	"step": 610
	},
	{
	"entropy": 0.7278808873146773,
	"epoch": 0.275969509820286,
	"grad_norm": 65.0,
	"learning_rate": 1.2380000000000002e-05,
	"loss": 11.5778,
	"mean_token_accuracy": 0.7942668478935957,
	"num_tokens": 4133119.0,
	"step": 620
	},
	{
	"entropy": 0.7475641055032611,
	"epoch": 0.2804206309464196,
	"grad_norm": 70.5,
	"learning_rate": 1.2580000000000002e-05,
	"loss": 11.9803,
	"mean_token_accuracy": 0.7913637235760689,
	"num_tokens": 4200051.0,
	"step": 630
	},
	{
	"entropy": 0.7986388958990573,
	"epoch": 0.2848717520725533,
	"grad_norm": 71.0,
	"learning_rate": 1.2780000000000001e-05,
	"loss": 12.767,
	"mean_token_accuracy": 0.782176585495472,
	"num_tokens": 4267403.0,
	"step": 640
	},
	{
	"entropy": 0.7370933200232684,
	"epoch": 0.28932287319868694,
	"grad_norm": 72.0,
	"learning_rate": 1.2980000000000001e-05,
	"loss": 11.8884,
	"mean_token_accuracy": 0.7921638786792755,
	"num_tokens": 4333268.0,
	"step": 650
	},
	{
	"entropy": 0.737369327340275,
	"epoch": 0.29377399432482054,
	"grad_norm": 79.0,
	"learning_rate": 1.3180000000000001e-05,
	"loss": 11.7388,
	"mean_token_accuracy": 0.7942005816847086,
	"num_tokens": 4400242.0,
	"step": 660
	},
	{
	"entropy": 0.7550807458348572,
	"epoch": 0.2982251154509542,
	"grad_norm": 74.5,
	"learning_rate": 1.3380000000000002e-05,
	"loss": 12.0296,
	"mean_token_accuracy": 0.7894790366291999,
	"num_tokens": 4464714.0,
	"step": 670
	},
	{
	"entropy": 0.7167205691337586,
	"epoch": 0.30267623657708786,
	"grad_norm": 63.75,
	"learning_rate": 1.3580000000000002e-05,
	"loss": 11.5706,
	"mean_token_accuracy": 0.796867698058486,
	"num_tokens": 4535458.0,
	"step": 680
	},
	{
	"entropy": 0.7481121812015772,
	"epoch": 0.3071273577032215,
	"grad_norm": 67.0,
	"learning_rate": 1.378e-05,
	"loss": 11.985,
	"mean_token_accuracy": 0.7914165269583464,
	"num_tokens": 4599099.0,
	"step": 690
	},
	{
	"entropy": 0.7162985533475876,
	"epoch": 0.31157847882935513,
	"grad_norm": 56.25,
	"learning_rate": 1.398e-05,
	"loss": 11.4683,
	"mean_token_accuracy": 0.7971325770020485,
	"num_tokens": 4662903.0,
	"step": 700
	},
	{
	"epoch": 0.31157847882935513,
	"eval_biology_entropy": 1.2363531575202942,
	"eval_biology_loss": 1.32443106174469,
	"eval_biology_mean_token_accuracy": 0.6762348954081535,
	"eval_biology_num_tokens": 4662903.0,
	"eval_biology_runtime": 36.3542,
	"eval_biology_samples_per_second": 13.754,
	"eval_biology_steps_per_second": 13.754,
	"step": 700
	},
	{
	"epoch": 0.31157847882935513,
	"eval_chemistry_entropy": 0.7484616157412529,
	"eval_chemistry_loss": 0.7520119547843933,
	"eval_chemistry_mean_token_accuracy": 0.7884139549732209,
	"eval_chemistry_num_tokens": 4662903.0,
	"eval_chemistry_runtime": 41.3205,
	"eval_chemistry_samples_per_second": 12.101,
	"eval_chemistry_steps_per_second": 12.101,
	"step": 700
	},
	{
	"epoch": 0.31157847882935513,
	"eval_math_entropy": 0.6818331519067288,
	"eval_math_loss": 0.862537145614624,
	"eval_math_mean_token_accuracy": 0.7769467064142227,
	"eval_math_num_tokens": 4662903.0,
	"eval_math_runtime": 42.2089,
	"eval_math_samples_per_second": 11.846,
	"eval_math_steps_per_second": 11.846,
	"step": 700
	},
	{
	"epoch": 0.31157847882935513,
	"eval_physics_entropy": 0.7252178380489349,
	"eval_physics_loss": 0.7445859313011169,
	"eval_physics_mean_token_accuracy": 0.7919469431638718,
	"eval_physics_num_tokens": 4662903.0,
	"eval_physics_runtime": 45.6964,
	"eval_physics_samples_per_second": 10.942,
	"eval_physics_steps_per_second": 10.942,
	"step": 700
	},
	{
	"entropy": 0.7590530560351908,
	"epoch": 0.3160295999554888,
	"grad_norm": 83.5,
	"learning_rate": 1.418e-05,
	"loss": 12.3935,
	"mean_token_accuracy": 0.7850905049592256,
	"num_tokens": 4729166.0,
	"step": 710
	},
	{
	"entropy": 0.800558901950717,
	"epoch": 0.32048072108162245,
	"grad_norm": 79.0,
	"learning_rate": 1.4380000000000001e-05,
	"loss": 12.7943,
	"mean_token_accuracy": 0.7798430301249027,
	"num_tokens": 4796815.0,
	"step": 720
	},
	{
	"entropy": 0.6950356176123023,
	"epoch": 0.32493184220775606,
	"grad_norm": 69.0,
	"learning_rate": 1.4580000000000001e-05,
	"loss": 11.0797,
	"mean_token_accuracy": 0.803941647708416,
	"num_tokens": 4865172.0,
	"step": 730
	},
	{
	"entropy": 0.7522321011871099,
	"epoch": 0.3293829633338897,
	"grad_norm": 64.0,
	"learning_rate": 1.478e-05,
	"loss": 12.1663,
	"mean_token_accuracy": 0.7838000770658254,
	"num_tokens": 4932671.0,
	"step": 740
	},
	{
	"entropy": 0.7758943744935095,
	"epoch": 0.3338340844600234,
	"grad_norm": 65.0,
	"learning_rate": 1.498e-05,
	"loss": 12.4442,
	"mean_token_accuracy": 0.7852539490908385,
	"num_tokens": 4998710.0,
	"step": 750
	},
	{
	"entropy": 0.7163919297046959,
	"epoch": 0.338285205586157,
	"grad_norm": 67.5,
	"learning_rate": 1.5180000000000002e-05,
	"loss": 11.5154,
	"mean_token_accuracy": 0.7952407207340002,
	"num_tokens": 5066948.0,
	"step": 760
	},
	{
	"entropy": 0.753566917218268,
	"epoch": 0.34273632671229065,
	"grad_norm": 67.0,
	"learning_rate": 1.5380000000000002e-05,
	"loss": 12.0632,
	"mean_token_accuracy": 0.7887947488576174,
	"num_tokens": 5129950.0,
	"step": 770
	},
	{
	"entropy": 0.7747300613671542,
	"epoch": 0.3471874478384243,
	"grad_norm": 64.5,
	"learning_rate": 1.5580000000000003e-05,
	"loss": 12.4883,
	"mean_token_accuracy": 0.7800568122416734,
	"num_tokens": 5193519.0,
	"step": 780
	},
	{
	"entropy": 0.7476665185764432,
	"epoch": 0.351638568964558,
	"grad_norm": 91.0,
	"learning_rate": 1.578e-05,
	"loss": 11.9465,
	"mean_token_accuracy": 0.7881375091150403,
	"num_tokens": 5256503.0,
	"step": 790
	},
	{
	"entropy": 0.8204591780900955,
	"epoch": 0.3560896900906916,
	"grad_norm": 68.0,
	"learning_rate": 1.5980000000000003e-05,
	"loss": 13.1278,
	"mean_token_accuracy": 0.7780214017257094,
	"num_tokens": 5324751.0,
	"step": 800
	},
	{
	"epoch": 0.3560896900906916,
	"eval_biology_entropy": 1.3236136644482612,
	"eval_biology_loss": 1.3220669031143188,
	"eval_biology_mean_token_accuracy": 0.6748943754434585,
	"eval_biology_num_tokens": 5324751.0,
	"eval_biology_runtime": 36.5537,
	"eval_biology_samples_per_second": 13.679,
	"eval_biology_steps_per_second": 13.679,
	"step": 800
	},
	{
	"epoch": 0.3560896900906916,
	"eval_chemistry_entropy": 0.7881391143500804,
	"eval_chemistry_loss": 0.7549666166305542,
	"eval_chemistry_mean_token_accuracy": 0.7878072342276573,
	"eval_chemistry_num_tokens": 5324751.0,
	"eval_chemistry_runtime": 40.4688,
	"eval_chemistry_samples_per_second": 12.355,
	"eval_chemistry_steps_per_second": 12.355,
	"step": 800
	},
	{
	"epoch": 0.3560896900906916,
	"eval_math_entropy": 0.7137112567722798,
	"eval_math_loss": 0.8679834008216858,
	"eval_math_mean_token_accuracy": 0.774067041516304,
	"eval_math_num_tokens": 5324751.0,
	"eval_math_runtime": 41.3922,
	"eval_math_samples_per_second": 12.08,
	"eval_math_steps_per_second": 12.08,
	"step": 800
	},
	{
	"epoch": 0.3560896900906916,
	"eval_physics_entropy": 0.764995231449604,
	"eval_physics_loss": 0.750312864780426,
	"eval_physics_mean_token_accuracy": 0.7906691903471946,
	"eval_physics_num_tokens": 5324751.0,
	"eval_physics_runtime": 45.8484,
	"eval_physics_samples_per_second": 10.906,
	"eval_physics_steps_per_second": 10.906,
	"step": 800
	},
	{
	"entropy": 0.6771990330889821,
	"epoch": 0.36054081121682524,
	"grad_norm": 65.0,
	"learning_rate": 1.618e-05,
	"loss": 11.1158,
	"mean_token_accuracy": 0.8028291787952184,
	"num_tokens": 5391664.0,
	"step": 810
	},
	{
	"entropy": 0.7129247286356986,
	"epoch": 0.3649919323429589,
	"grad_norm": 70.5,
	"learning_rate": 1.638e-05,
	"loss": 11.1981,
	"mean_token_accuracy": 0.8007186874747276,
	"num_tokens": 5458519.0,
	"step": 820
	},
	{
	"entropy": 0.7549328833818436,
	"epoch": 0.3694430534690925,
	"grad_norm": 65.0,
	"learning_rate": 1.658e-05,
	"loss": 12.1723,
	"mean_token_accuracy": 0.7901175323873758,
	"num_tokens": 5523391.0,
	"step": 830
	},
	{
	"entropy": 0.7134035120718181,
	"epoch": 0.37389417459522617,
	"grad_norm": 59.0,
	"learning_rate": 1.6780000000000002e-05,
	"loss": 11.7326,
	"mean_token_accuracy": 0.795387938991189,
	"num_tokens": 5585508.0,
	"step": 840
	},
	{
	"entropy": 0.7443888144567609,
	"epoch": 0.37834529572135983,
	"grad_norm": 71.0,
	"learning_rate": 1.698e-05,
	"loss": 11.8848,
	"mean_token_accuracy": 0.7947730336338281,
	"num_tokens": 5650755.0,
	"step": 850
	},
	{
	"entropy": 0.7494110313244164,
	"epoch": 0.38279641684749344,
	"grad_norm": 61.5,
	"learning_rate": 1.718e-05,
	"loss": 11.969,
	"mean_token_accuracy": 0.788362193852663,
	"num_tokens": 5716321.0,
	"step": 860
	},
	{
	"entropy": 0.7754998824559152,
	"epoch": 0.3872475379736271,
	"grad_norm": 67.0,
	"learning_rate": 1.7380000000000003e-05,
	"loss": 12.4655,
	"mean_token_accuracy": 0.7815641265362501,
	"num_tokens": 5782698.0,
	"step": 870
	},
	{
	"entropy": 0.7258908217772841,
	"epoch": 0.39169865909976076,
	"grad_norm": 54.5,
	"learning_rate": 1.758e-05,
	"loss": 11.662,
	"mean_token_accuracy": 0.7951392225921154,
	"num_tokens": 5848889.0,
	"step": 880
	},
	{
	"entropy": 0.7699500862509012,
	"epoch": 0.3961497802258944,
	"grad_norm": 65.5,
	"learning_rate": 1.7780000000000003e-05,
	"loss": 12.5712,
	"mean_token_accuracy": 0.7857454361394047,
	"num_tokens": 5912919.0,
	"step": 890
	},
	{
	"entropy": 0.7454446164891124,
	"epoch": 0.400600901352028,
	"grad_norm": 60.75,
	"learning_rate": 1.798e-05,
	"loss": 11.8793,
	"mean_token_accuracy": 0.793294046446681,
	"num_tokens": 5980229.0,
	"step": 900
	},
	{
	"epoch": 0.400600901352028,
	"eval_biology_entropy": 1.2526325694918632,
	"eval_biology_loss": 1.3328229188919067,
	"eval_biology_mean_token_accuracy": 0.6739730868339538,
	"eval_biology_num_tokens": 5980229.0,
	"eval_biology_runtime": 37.1628,
	"eval_biology_samples_per_second": 13.454,
	"eval_biology_steps_per_second": 13.454,
	"step": 900
	},
	{
	"epoch": 0.400600901352028,
	"eval_chemistry_entropy": 0.7478999142050743,
	"eval_chemistry_loss": 0.7579869627952576,
	"eval_chemistry_mean_token_accuracy": 0.7872751998305321,
	"eval_chemistry_num_tokens": 5980229.0,
	"eval_chemistry_runtime": 41.0567,
	"eval_chemistry_samples_per_second": 12.178,
	"eval_chemistry_steps_per_second": 12.178,
	"step": 900
	},
	{
	"epoch": 0.400600901352028,
	"eval_math_entropy": 0.691623161137104,
	"eval_math_loss": 0.8888975977897644,
	"eval_math_mean_token_accuracy": 0.7720628465414048,
	"eval_math_num_tokens": 5980229.0,
	"eval_math_runtime": 41.3967,
	"eval_math_samples_per_second": 12.078,
	"eval_math_steps_per_second": 12.078,
	"step": 900
	},
	{
	"epoch": 0.400600901352028,
	"eval_physics_entropy": 0.7361411595344544,
	"eval_physics_loss": 0.7520632743835449,
	"eval_physics_mean_token_accuracy": 0.7907493528723717,
	"eval_physics_num_tokens": 5980229.0,
	"eval_physics_runtime": 46.0024,
	"eval_physics_samples_per_second": 10.869,
	"eval_physics_steps_per_second": 10.869,
	"step": 900
	},
	{
	"entropy": 0.7022204802371561,
	"epoch": 0.4050520224781617,
	"grad_norm": 61.0,
	"learning_rate": 1.8180000000000002e-05,
	"loss": 11.4405,
	"mean_token_accuracy": 0.798212106898427,
	"num_tokens": 6048508.0,
	"step": 910
	},
	{
	"entropy": 0.7361409039236605,
	"epoch": 0.40950314360429535,
	"grad_norm": 60.25,
	"learning_rate": 1.8380000000000004e-05,
	"loss": 11.7212,
	"mean_token_accuracy": 0.7943942189216614,
	"num_tokens": 6114855.0,
	"step": 920
	},
	{
	"entropy": 0.7555323796346783,
	"epoch": 0.41395426473042896,
	"grad_norm": 54.0,
	"learning_rate": 1.858e-05,
	"loss": 12.1222,
	"mean_token_accuracy": 0.7887333419173956,
	"num_tokens": 6179050.0,
	"step": 930
	},
	{
	"entropy": 0.7449197143316268,
	"epoch": 0.4184053858565626,
	"grad_norm": 59.0,
	"learning_rate": 1.878e-05,
	"loss": 12.1501,
	"mean_token_accuracy": 0.7886579774320126,
	"num_tokens": 6244987.0,
	"step": 940
	},
	{
	"entropy": 0.7183629649691283,
	"epoch": 0.4228565069826963,
	"grad_norm": 66.0,
	"learning_rate": 1.898e-05,
	"loss": 11.6027,
	"mean_token_accuracy": 0.794747618958354,
	"num_tokens": 6310799.0,
	"step": 950
	},
	{
	"entropy": 0.7170003782957792,
	"epoch": 0.4273076281088299,
	"grad_norm": 63.5,
	"learning_rate": 1.918e-05,
	"loss": 11.5812,
	"mean_token_accuracy": 0.7965250793844462,
	"num_tokens": 6378152.0,
	"step": 960
	},
	{
	"entropy": 0.7422669138759375,
	"epoch": 0.43175874923496355,
	"grad_norm": 54.0,
	"learning_rate": 1.938e-05,
	"loss": 11.7787,
	"mean_token_accuracy": 0.7933820992708206,
	"num_tokens": 6442491.0,
	"step": 970
	},
	{
	"entropy": 0.7739317396655678,
	"epoch": 0.4362098703610972,
	"grad_norm": 57.75,
	"learning_rate": 1.9580000000000002e-05,
	"loss": 12.5927,
	"mean_token_accuracy": 0.7841954406350851,
	"num_tokens": 6510231.0,
	"step": 980
	},
	{
	"entropy": 0.745883577503264,
	"epoch": 0.44066099148723087,
	"grad_norm": 57.25,
	"learning_rate": 1.978e-05,
	"loss": 12.0418,
	"mean_token_accuracy": 0.790126183629036,
	"num_tokens": 6572858.0,
	"step": 990
	},
	{
	"entropy": 0.7626472780480981,
	"epoch": 0.4451121126133645,
	"grad_norm": 48.0,
	"learning_rate": 1.9980000000000002e-05,
	"loss": 12.3648,
	"mean_token_accuracy": 0.7834480810910464,
	"num_tokens": 6637273.0,
	"step": 1000
	},
	{
	"epoch": 0.4451121126133645,
	"eval_biology_entropy": 1.2697618773579598,
	"eval_biology_loss": 1.3405715227127075,
	"eval_biology_mean_token_accuracy": 0.6724427245259285,
	"eval_biology_num_tokens": 6637273.0,
	"eval_biology_runtime": 34.6717,
	"eval_biology_samples_per_second": 14.421,
	"eval_biology_steps_per_second": 14.421,
	"step": 1000
	},
	{
	"epoch": 0.4451121126133645,
	"eval_chemistry_entropy": 0.7615428499877452,
	"eval_chemistry_loss": 0.7553035616874695,
	"eval_chemistry_mean_token_accuracy": 0.7880414368510247,
	"eval_chemistry_num_tokens": 6637273.0,
	"eval_chemistry_runtime": 38.9404,
	"eval_chemistry_samples_per_second": 12.84,
	"eval_chemistry_steps_per_second": 12.84,
	"step": 1000
	},
	{
	"epoch": 0.4451121126133645,
	"eval_math_entropy": 0.7116467788815498,
	"eval_math_loss": 0.8722440004348755,
	"eval_math_mean_token_accuracy": 0.7725971038341523,
	"eval_math_num_tokens": 6637273.0,
	"eval_math_runtime": 39.9329,
	"eval_math_samples_per_second": 12.521,
	"eval_math_steps_per_second": 12.521,
	"step": 1000
	},
	{
	"epoch": 0.4451121126133645,
	"eval_physics_entropy": 0.7675083922743797,
	"eval_physics_loss": 0.7605612874031067,
	"eval_physics_mean_token_accuracy": 0.7887651996016503,
	"eval_physics_num_tokens": 6637273.0,
	"eval_physics_runtime": 44.6453,
	"eval_physics_samples_per_second": 11.199,
	"eval_physics_steps_per_second": 11.199,
	"step": 1000
	},
	{
	"entropy": 0.7314162964001298,
	"epoch": 0.44956323373949814,
	"grad_norm": 57.5,
	"learning_rate": 1.9980000000000002e-05,
	"loss": 11.7366,
	"mean_token_accuracy": 0.7923816435039044,
	"num_tokens": 6700799.0,
	"step": 1010
	},
	{
	"entropy": 0.7421712795272469,
	"epoch": 0.4540143548656318,
	"grad_norm": 57.5,
	"learning_rate": 1.995777777777778e-05,
	"loss": 12.1497,
	"mean_token_accuracy": 0.7892091479152441,
	"num_tokens": 6765798.0,
	"step": 1020
	},
	{
	"entropy": 0.6979273453354835,
	"epoch": 0.4584654759917654,
	"grad_norm": 58.5,
	"learning_rate": 1.9935555555555557e-05,
	"loss": 11.3013,
	"mean_token_accuracy": 0.7992341227829456,
	"num_tokens": 6832774.0,
	"step": 1030
	},
	{
	"entropy": 0.7764921618625522,
	"epoch": 0.46291659711789906,
	"grad_norm": 56.5,
	"learning_rate": 1.9913333333333335e-05,
	"loss": 12.4581,
	"mean_token_accuracy": 0.783613259345293,
	"num_tokens": 6896684.0,
	"step": 1040
	},
	{
	"entropy": 0.7277746710926294,
	"epoch": 0.4673677182440327,
	"grad_norm": 57.75,
	"learning_rate": 1.9891111111111112e-05,
	"loss": 11.7064,
	"mean_token_accuracy": 0.798894327133894,
	"num_tokens": 6964423.0,
	"step": 1050
	},
	{
	"entropy": 0.7224507334642112,
	"epoch": 0.4718188393701664,
	"grad_norm": 52.75,
	"learning_rate": 1.986888888888889e-05,
	"loss": 11.8859,
	"mean_token_accuracy": 0.7931920390576124,
	"num_tokens": 7033417.0,
	"step": 1060
	},
	{
	"entropy": 0.7771790644153953,
	"epoch": 0.4762699604963,
	"grad_norm": 55.0,
	"learning_rate": 1.9846666666666668e-05,
	"loss": 12.3152,
	"mean_token_accuracy": 0.7860798113048076,
	"num_tokens": 7101274.0,
	"step": 1070
	},
	{
	"entropy": 0.7393451489508152,
	"epoch": 0.48072108162243365,
	"grad_norm": 52.5,
	"learning_rate": 1.9824444444444445e-05,
	"loss": 12.1816,
	"mean_token_accuracy": 0.7896892268210649,
	"num_tokens": 7166608.0,
	"step": 1080
	},
	{
	"entropy": 0.7223112307488918,
	"epoch": 0.4851722027485673,
	"grad_norm": 72.0,
	"learning_rate": 1.9802222222222226e-05,
	"loss": 11.573,
	"mean_token_accuracy": 0.7999571479856968,
	"num_tokens": 7240958.0,
	"step": 1090
	},
	{
	"entropy": 0.7434121018275619,
	"epoch": 0.4896233238747009,
	"grad_norm": 55.0,
	"learning_rate": 1.978e-05,
	"loss": 11.995,
	"mean_token_accuracy": 0.7897290639579296,
	"num_tokens": 7311968.0,
	"step": 1100
	},
	{
	"epoch": 0.4896233238747009,
	"eval_biology_entropy": 1.2825020100474358,
	"eval_biology_loss": 1.3549916744232178,
	"eval_biology_mean_token_accuracy": 0.6708763095140458,
	"eval_biology_num_tokens": 7311968.0,
	"eval_biology_runtime": 34.7487,
	"eval_biology_samples_per_second": 14.389,
	"eval_biology_steps_per_second": 14.389,
	"step": 1100
	},
	{
	"epoch": 0.4896233238747009,
	"eval_chemistry_entropy": 0.7363105757832528,
	"eval_chemistry_loss": 0.7509695887565613,
	"eval_chemistry_mean_token_accuracy": 0.7897556048631668,
	"eval_chemistry_num_tokens": 7311968.0,
	"eval_chemistry_runtime": 39.5761,
	"eval_chemistry_samples_per_second": 12.634,
	"eval_chemistry_steps_per_second": 12.634,
	"step": 1100
	},
	{
	"epoch": 0.4896233238747009,
	"eval_math_entropy": 0.6904492176771164,
	"eval_math_loss": 0.8790993690490723,
	"eval_math_mean_token_accuracy": 0.7729596102237701,
	"eval_math_num_tokens": 7311968.0,
	"eval_math_runtime": 40.1018,
	"eval_math_samples_per_second": 12.468,
	"eval_math_steps_per_second": 12.468,
	"step": 1100
	},
	{
	"epoch": 0.4896233238747009,
	"eval_physics_entropy": 0.7335765887498855,
	"eval_physics_loss": 0.7572531700134277,
	"eval_physics_mean_token_accuracy": 0.7901599068641663,
	"eval_physics_num_tokens": 7311968.0,
	"eval_physics_runtime": 44.6604,
	"eval_physics_samples_per_second": 11.196,
	"eval_physics_steps_per_second": 11.196,
	"step": 1100
	},
	{
	"entropy": 0.7318524705246091,
	"epoch": 0.4940744450008346,
	"grad_norm": 60.75,
	"learning_rate": 1.975777777777778e-05,
	"loss": 11.7678,
	"mean_token_accuracy": 0.7911851242184639,
	"num_tokens": 7378961.0,
	"step": 1110
	},
	{
	"entropy": 0.7082980162464082,
	"epoch": 0.49852556612696824,
	"grad_norm": 61.75,
	"learning_rate": 1.9735555555555556e-05,
	"loss": 11.4456,
	"mean_token_accuracy": 0.7980625631287694,
	"num_tokens": 7444923.0,
	"step": 1120
	},
	{
	"entropy": 0.7435412630438805,
	"epoch": 0.5029766872531019,
	"grad_norm": 55.5,
	"learning_rate": 1.9713333333333337e-05,
	"loss": 11.7624,
	"mean_token_accuracy": 0.7926325134932994,
	"num_tokens": 7509885.0,
	"step": 1130
	},
	{
	"entropy": 0.7542540356516838,
	"epoch": 0.5074278083792355,
	"grad_norm": 54.0,
	"learning_rate": 1.969111111111111e-05,
	"loss": 12.4162,
	"mean_token_accuracy": 0.7846910808235407,
	"num_tokens": 7576456.0,
	"step": 1140
	},
	{
	"entropy": 0.7760613728314638,
	"epoch": 0.5118789295053692,
	"grad_norm": 57.0,
	"learning_rate": 1.9668888888888892e-05,
	"loss": 12.3585,
	"mean_token_accuracy": 0.7867991000413894,
	"num_tokens": 7641821.0,
	"step": 1150
	},
	{
	"entropy": 0.7095673834905029,
	"epoch": 0.5163300506315028,
	"grad_norm": 54.5,
	"learning_rate": 1.9646666666666666e-05,
	"loss": 11.5013,
	"mean_token_accuracy": 0.7958923596888781,
	"num_tokens": 7706502.0,
	"step": 1160
	},
	{
	"entropy": 0.8006078721955419,
	"epoch": 0.5207811717576365,
	"grad_norm": 64.5,
	"learning_rate": 1.9624444444444447e-05,
	"loss": 12.8183,
	"mean_token_accuracy": 0.7838775899261237,
	"num_tokens": 7772353.0,
	"step": 1170
	},
	{
	"entropy": 0.7142350310459733,
	"epoch": 0.52523229288377,
	"grad_norm": 50.25,
	"learning_rate": 1.9602222222222225e-05,
	"loss": 11.7207,
	"mean_token_accuracy": 0.795654509216547,
	"num_tokens": 7838516.0,
	"step": 1180
	},
	{
	"entropy": 0.7257593980059027,
	"epoch": 0.5296834140099037,
	"grad_norm": 61.25,
	"learning_rate": 1.9580000000000002e-05,
	"loss": 11.5084,
	"mean_token_accuracy": 0.7954147141426802,
	"num_tokens": 7902568.0,
	"step": 1190
	},
	{
	"entropy": 0.7607359967194498,
	"epoch": 0.5341345351360374,
	"grad_norm": 54.25,
	"learning_rate": 1.955777777777778e-05,
	"loss": 12.0382,
	"mean_token_accuracy": 0.788224334642291,
	"num_tokens": 7969704.0,
	"step": 1200
	},
	{
	"epoch": 0.5341345351360374,
	"eval_biology_entropy": 1.2328835948705674,
	"eval_biology_loss": 1.3470529317855835,
	"eval_biology_mean_token_accuracy": 0.6719091883301735,
	"eval_biology_num_tokens": 7969704.0,
	"eval_biology_runtime": 34.5402,
	"eval_biology_samples_per_second": 14.476,
	"eval_biology_steps_per_second": 14.476,
	"step": 1200
	},
	{
	"epoch": 0.5341345351360374,
	"eval_chemistry_entropy": 0.727981344461441,
	"eval_chemistry_loss": 0.7450346946716309,
	"eval_chemistry_mean_token_accuracy": 0.7906108702421188,
	"eval_chemistry_num_tokens": 7969704.0,
	"eval_chemistry_runtime": 39.3686,
	"eval_chemistry_samples_per_second": 12.7,
	"eval_chemistry_steps_per_second": 12.7,
	"step": 1200
	},
	{
	"epoch": 0.5341345351360374,
	"eval_math_entropy": 0.6775654193758964,
	"eval_math_loss": 0.8872368931770325,
	"eval_math_mean_token_accuracy": 0.7717010715007782,
	"eval_math_num_tokens": 7969704.0,
	"eval_math_runtime": 40.8591,
	"eval_math_samples_per_second": 12.237,
	"eval_math_steps_per_second": 12.237,
	"step": 1200
	},
	{
	"epoch": 0.5341345351360374,
	"eval_physics_entropy": 0.728905067563057,
	"eval_physics_loss": 0.7556765079498291,
	"eval_physics_mean_token_accuracy": 0.7903099409341812,
	"eval_physics_num_tokens": 7969704.0,
	"eval_physics_runtime": 44.9155,
	"eval_physics_samples_per_second": 11.132,
	"eval_physics_steps_per_second": 11.132,
	"step": 1200
	},
	{
	"entropy": 0.6951992505230009,
	"epoch": 0.538585656262171,
	"grad_norm": 48.0,
	"learning_rate": 1.9535555555555557e-05,
	"loss": 11.4334,
	"mean_token_accuracy": 0.7958714343607426,
	"num_tokens": 8034765.0,
	"step": 1210
	},
	{
	"entropy": 0.7527200236916542,
	"epoch": 0.5430367773883047,
	"grad_norm": 45.75,
	"learning_rate": 1.9513333333333335e-05,
	"loss": 11.9919,
	"mean_token_accuracy": 0.7917780404910445,
	"num_tokens": 8103869.0,
	"step": 1220
	},
	{
	"entropy": 0.686318707279861,
	"epoch": 0.5474878985144384,
	"grad_norm": 44.25,
	"learning_rate": 1.9491111111111113e-05,
	"loss": 11.1097,
	"mean_token_accuracy": 0.8036415990442037,
	"num_tokens": 8173386.0,
	"step": 1230
	},
	{
	"entropy": 0.7415073176845908,
	"epoch": 0.551939019640572,
	"grad_norm": 53.75,
	"learning_rate": 1.946888888888889e-05,
	"loss": 11.8806,
	"mean_token_accuracy": 0.7891732029616833,
	"num_tokens": 8242162.0,
	"step": 1240
	},
	{
	"entropy": 0.7266354532912374,
	"epoch": 0.5563901407667056,
	"grad_norm": 61.0,
	"learning_rate": 1.9446666666666668e-05,
	"loss": 11.6483,
	"mean_token_accuracy": 0.7947042044252157,
	"num_tokens": 8308919.0,
	"step": 1250
	},
	{
	"entropy": 0.7407059632241726,
	"epoch": 0.5608412618928392,
	"grad_norm": 67.0,
	"learning_rate": 1.9424444444444446e-05,
	"loss": 12.0106,
	"mean_token_accuracy": 0.7900955501943827,
	"num_tokens": 8365617.0,
	"step": 1260
	},
	{
	"entropy": 0.7527385540306568,
	"epoch": 0.5652923830189729,
	"grad_norm": 48.0,
	"learning_rate": 1.9402222222222223e-05,
	"loss": 11.9171,
	"mean_token_accuracy": 0.7914537958800792,
	"num_tokens": 8430728.0,
	"step": 1270
	},
	{
	"entropy": 0.7172600775957108,
	"epoch": 0.5697435041451065,
	"grad_norm": 49.25,
	"learning_rate": 1.938e-05,
	"loss": 11.5836,
	"mean_token_accuracy": 0.7958250787109137,
	"num_tokens": 8497852.0,
	"step": 1280
	},
	{
	"entropy": 0.7470160932280123,
	"epoch": 0.5741946252712402,
	"grad_norm": 50.0,
	"learning_rate": 1.935777777777778e-05,
	"loss": 12.1357,
	"mean_token_accuracy": 0.7876220095902682,
	"num_tokens": 8558952.0,
	"step": 1290
	},
	{
	"entropy": 0.7452291272580623,
	"epoch": 0.5786457463973739,
	"grad_norm": 57.75,
	"learning_rate": 1.9335555555555556e-05,
	"loss": 11.8494,
	"mean_token_accuracy": 0.7954678740352392,
	"num_tokens": 8622868.0,
	"step": 1300
	},
	{
	"epoch": 0.5786457463973739,
	"eval_biology_entropy": 1.270399274289608,
	"eval_biology_loss": 1.3523783683776855,
	"eval_biology_mean_token_accuracy": 0.6706679166555405,
	"eval_biology_num_tokens": 8622868.0,
	"eval_biology_runtime": 35.3016,
	"eval_biology_samples_per_second": 14.164,
	"eval_biology_steps_per_second": 14.164,
	"step": 1300
	},
	{
	"epoch": 0.5786457463973739,
	"eval_chemistry_entropy": 0.7226660187542439,
	"eval_chemistry_loss": 0.7358337640762329,
	"eval_chemistry_mean_token_accuracy": 0.7928519014120102,
	"eval_chemistry_num_tokens": 8622868.0,
	"eval_chemistry_runtime": 39.6574,
	"eval_chemistry_samples_per_second": 12.608,
	"eval_chemistry_steps_per_second": 12.608,
	"step": 1300
	},
	{
	"epoch": 0.5786457463973739,
	"eval_math_entropy": 0.6689038871824742,
	"eval_math_loss": 0.8895673155784607,
	"eval_math_mean_token_accuracy": 0.7727138675451278,
	"eval_math_num_tokens": 8622868.0,
	"eval_math_runtime": 40.5077,
	"eval_math_samples_per_second": 12.343,
	"eval_math_steps_per_second": 12.343,
	"step": 1300
	},
	{
	"epoch": 0.5786457463973739,
	"eval_physics_entropy": 0.7133040081262588,
	"eval_physics_loss": 0.7542717456817627,
	"eval_physics_mean_token_accuracy": 0.7914812366366386,
	"eval_physics_num_tokens": 8622868.0,
	"eval_physics_runtime": 44.946,
	"eval_physics_samples_per_second": 11.124,
	"eval_physics_steps_per_second": 11.124,
	"step": 1300
	},
	{
	"entropy": 0.6984654633328319,
	"epoch": 0.5830968675235075,
	"grad_norm": 55.75,
	"learning_rate": 1.9313333333333334e-05,
	"loss": 11.4106,
	"mean_token_accuracy": 0.7972324814647436,
	"num_tokens": 8694510.0,
	"step": 1310
	},
	{
	"entropy": 0.7897671807557345,
	"epoch": 0.5875479886496411,
	"grad_norm": 65.0,
	"learning_rate": 1.9291111111111115e-05,
	"loss": 12.6834,
	"mean_token_accuracy": 0.7794294957071543,
	"num_tokens": 8757753.0,
	"step": 1320
	},
	{
	"entropy": 0.7390378901734949,
	"epoch": 0.5919991097757747,
	"grad_norm": 51.0,
	"learning_rate": 1.926888888888889e-05,
	"loss": 11.8734,
	"mean_token_accuracy": 0.7966042939573527,
	"num_tokens": 8823153.0,
	"step": 1330
	},
	{
	"entropy": 0.7496651741676033,
	"epoch": 0.5964502309019084,
	"grad_norm": 53.25,
	"learning_rate": 1.924666666666667e-05,
	"loss": 12.1236,
	"mean_token_accuracy": 0.788444896414876,
	"num_tokens": 8886401.0,
	"step": 1340
	},
	{
	"entropy": 0.7156450959853828,
	"epoch": 0.6009013520280421,
	"grad_norm": 45.75,
	"learning_rate": 1.9224444444444444e-05,
	"loss": 11.4242,
	"mean_token_accuracy": 0.7963771104812623,
	"num_tokens": 8958530.0,
	"step": 1350
	},
	{
	"entropy": 0.7286824054084718,
	"epoch": 0.6053524731541757,
	"grad_norm": 55.0,
	"learning_rate": 1.9202222222222225e-05,
	"loss": 11.7964,
	"mean_token_accuracy": 0.7932926584035158,
	"num_tokens": 9024677.0,
	"step": 1360
	},
	{
	"entropy": 0.7564192423596978,
	"epoch": 0.6098035942803094,
	"grad_norm": 52.25,
	"learning_rate": 1.918e-05,
	"loss": 11.9791,
	"mean_token_accuracy": 0.790202745422721,
	"num_tokens": 9090280.0,
	"step": 1370
	},
	{
	"entropy": 0.7076619225554168,
	"epoch": 0.614254715406443,
	"grad_norm": 52.75,
	"learning_rate": 1.915777777777778e-05,
	"loss": 11.5864,
	"mean_token_accuracy": 0.7959123384207487,
	"num_tokens": 9153771.0,
	"step": 1380
	},
	{
	"entropy": 0.6782314692623913,
	"epoch": 0.6187058365325766,
	"grad_norm": 47.5,
	"learning_rate": 1.9135555555555555e-05,
	"loss": 10.7507,
	"mean_token_accuracy": 0.8093214847147465,
	"num_tokens": 9227117.0,
	"step": 1390
	},
	{
	"entropy": 0.7308899962343276,
	"epoch": 0.6231569576587103,
	"grad_norm": 50.25,
	"learning_rate": 1.9113333333333336e-05,
	"loss": 11.9294,
	"mean_token_accuracy": 0.790796834975481,
	"num_tokens": 9291760.0,
	"step": 1400
	},
	{
	"epoch": 0.6231569576587103,
	"eval_biology_entropy": 1.2965683770179748,
	"eval_biology_loss": 1.3410367965698242,
	"eval_biology_mean_token_accuracy": 0.6702442263960838,
	"eval_biology_num_tokens": 9291760.0,
	"eval_biology_runtime": 35.3518,
	"eval_biology_samples_per_second": 14.144,
	"eval_biology_steps_per_second": 14.144,
	"step": 1400
	},
	{
	"epoch": 0.6231569576587103,
	"eval_chemistry_entropy": 0.7365462110638619,
	"eval_chemistry_loss": 0.7281596660614014,
	"eval_chemistry_mean_token_accuracy": 0.7939923223257065,
	"eval_chemistry_num_tokens": 9291760.0,
	"eval_chemistry_runtime": 39.6432,
	"eval_chemistry_samples_per_second": 12.613,
	"eval_chemistry_steps_per_second": 12.613,
	"step": 1400
	},
	{
	"epoch": 0.6231569576587103,
	"eval_math_entropy": 0.7127760598063468,
	"eval_math_loss": 0.8852732181549072,
	"eval_math_mean_token_accuracy": 0.772164557814598,
	"eval_math_num_tokens": 9291760.0,
	"eval_math_runtime": 40.409,
	"eval_math_samples_per_second": 12.373,
	"eval_math_steps_per_second": 12.373,
	"step": 1400
	},
	{
	"epoch": 0.6231569576587103,
	"eval_physics_entropy": 0.7410066242218017,
	"eval_physics_loss": 0.7547739148139954,
	"eval_physics_mean_token_accuracy": 0.7911624670028686,
	"eval_physics_num_tokens": 9291760.0,
	"eval_physics_runtime": 45.0651,
	"eval_physics_samples_per_second": 11.095,
	"eval_physics_steps_per_second": 11.095,
	"step": 1400
	},
	{
	"entropy": 0.764516063220799,
	"epoch": 0.6276080787848439,
	"grad_norm": 51.25,
	"learning_rate": 1.9091111111111113e-05,
	"loss": 12.1236,
	"mean_token_accuracy": 0.7861191317439079,
	"num_tokens": 9357561.0,
	"step": 1410
	},
	{
	"entropy": 0.7065011899918318,
	"epoch": 0.6320591999109776,
	"grad_norm": 56.0,
	"learning_rate": 1.906888888888889e-05,
	"loss": 11.5089,
	"mean_token_accuracy": 0.798106643371284,
	"num_tokens": 9425022.0,
	"step": 1420
	},
	{
	"entropy": 0.7121715405024588,
	"epoch": 0.6365103210371112,
	"grad_norm": 56.25,
	"learning_rate": 1.904666666666667e-05,
	"loss": 11.3189,
	"mean_token_accuracy": 0.8004428222775459,
	"num_tokens": 9492028.0,
	"step": 1430
	},
	{
	"entropy": 0.6874197697266936,
	"epoch": 0.6409614421632449,
	"grad_norm": 53.25,
	"learning_rate": 1.9024444444444446e-05,
	"loss": 11.048,
	"mean_token_accuracy": 0.8003636717796325,
	"num_tokens": 9561091.0,
	"step": 1440
	},
	{
	"entropy": 0.7115700559690594,
	"epoch": 0.6454125632893785,
	"grad_norm": 51.25,
	"learning_rate": 1.9002222222222224e-05,
	"loss": 11.3964,
	"mean_token_accuracy": 0.7977115370333194,
	"num_tokens": 9628383.0,
	"step": 1450
	},
	{
	"entropy": 0.6615842315368354,
	"epoch": 0.6498636844155121,
	"grad_norm": 46.25,
	"learning_rate": 1.898e-05,
	"loss": 10.652,
	"mean_token_accuracy": 0.8100770756602287,
	"num_tokens": 9695723.0,
	"step": 1460
	},
	{
	"entropy": 0.6988324311561882,
	"epoch": 0.6543148055416458,
	"grad_norm": 48.5,
	"learning_rate": 1.895777777777778e-05,
	"loss": 11.2433,
	"mean_token_accuracy": 0.8033667050302029,
	"num_tokens": 9763393.0,
	"step": 1470
	},
	{
	"entropy": 0.740055176243186,
	"epoch": 0.6587659266677794,
	"grad_norm": 45.75,
	"learning_rate": 1.8935555555555556e-05,
	"loss": 11.6971,
	"mean_token_accuracy": 0.7966903638094663,
	"num_tokens": 9827272.0,
	"step": 1480
	},
	{
	"entropy": 0.6889881357550621,
	"epoch": 0.6632170477939131,
	"grad_norm": 47.75,
	"learning_rate": 1.8913333333333334e-05,
	"loss": 11.1825,
	"mean_token_accuracy": 0.8002750147134066,
	"num_tokens": 9892418.0,
	"step": 1490
	},
	{
	"entropy": 0.6946229469962418,
	"epoch": 0.6676681689200468,
	"grad_norm": 48.75,
	"learning_rate": 1.8891111111111115e-05,
	"loss": 11.1311,
	"mean_token_accuracy": 0.802448557689786,
	"num_tokens": 9955369.0,
	"step": 1500
	},
	{
	"epoch": 0.6676681689200468,
	"eval_biology_entropy": 1.225859948515892,
	"eval_biology_loss": 1.344753384590149,
	"eval_biology_mean_token_accuracy": 0.6716743484735489,
	"eval_biology_num_tokens": 9955369.0,
	"eval_biology_runtime": 35.0712,
	"eval_biology_samples_per_second": 14.257,
	"eval_biology_steps_per_second": 14.257,
	"step": 1500
	},
	{
	"epoch": 0.6676681689200468,
	"eval_chemistry_entropy": 0.6977527342438697,
	"eval_chemistry_loss": 0.7168055176734924,
	"eval_chemistry_mean_token_accuracy": 0.7972170073986053,
	"eval_chemistry_num_tokens": 9955369.0,
	"eval_chemistry_runtime": 39.4894,
	"eval_chemistry_samples_per_second": 12.662,
	"eval_chemistry_steps_per_second": 12.662,
	"step": 1500
	},
	{
	"epoch": 0.6676681689200468,
	"eval_math_entropy": 0.670133613884449,
	"eval_math_loss": 0.8919703960418701,
	"eval_math_mean_token_accuracy": 0.7722328932285308,
	"eval_math_num_tokens": 9955369.0,
	"eval_math_runtime": 40.4938,
	"eval_math_samples_per_second": 12.348,
	"eval_math_steps_per_second": 12.348,
	"step": 1500
	},
	{
	"epoch": 0.6676681689200468,
	"eval_physics_entropy": 0.7054080674946308,
	"eval_physics_loss": 0.7483915090560913,
	"eval_physics_mean_token_accuracy": 0.7919600957632065,
	"eval_physics_num_tokens": 9955369.0,
	"eval_physics_runtime": 44.9964,
	"eval_physics_samples_per_second": 11.112,
	"eval_physics_steps_per_second": 11.112,
	"step": 1500
	},
	{
	"entropy": 0.7044103164225817,
	"epoch": 0.6721192900461804,
	"grad_norm": 59.0,
	"learning_rate": 1.886888888888889e-05,
	"loss": 11.356,
	"mean_token_accuracy": 0.7981578037142754,
	"num_tokens": 10026298.0,
	"step": 1510
	},
	{
	"entropy": 0.6750010882504285,
	"epoch": 0.676570411172314,
	"grad_norm": 48.5,
	"learning_rate": 1.884666666666667e-05,
	"loss": 10.656,
	"mean_token_accuracy": 0.8101748798042536,
	"num_tokens": 10096065.0,
	"step": 1520
	},
	{
	"entropy": 0.6924384200014174,
	"epoch": 0.6810215322984476,
	"grad_norm": 51.25,
	"learning_rate": 1.8824444444444445e-05,
	"loss": 11.3517,
	"mean_token_accuracy": 0.8001077000051737,
	"num_tokens": 10160745.0,
	"step": 1530
	},
	{
	"entropy": 0.673445784766227,
	"epoch": 0.6854726534245813,
	"grad_norm": 46.75,
	"learning_rate": 1.8802222222222226e-05,
	"loss": 10.659,
	"mean_token_accuracy": 0.8083447456359864,
	"num_tokens": 10233806.0,
	"step": 1540
	},
	{
	"entropy": 0.6894099942408503,
	"epoch": 0.689923774550715,
	"grad_norm": 56.75,
	"learning_rate": 1.878e-05,
	"loss": 11.2095,
	"mean_token_accuracy": 0.8019303198903799,
	"num_tokens": 10298845.0,
	"step": 1550
	},
	{
	"entropy": 0.6929447575472295,
	"epoch": 0.6943748956768486,
	"grad_norm": 49.25,
	"learning_rate": 1.875777777777778e-05,
	"loss": 11.0324,
	"mean_token_accuracy": 0.8037194091826677,
	"num_tokens": 10364601.0,
	"step": 1560
	},
	{
	"entropy": 0.6951657691970468,
	"epoch": 0.6988260168029823,
	"grad_norm": 52.0,
	"learning_rate": 1.873555555555556e-05,
	"loss": 11.2917,
	"mean_token_accuracy": 0.7976405322551727,
	"num_tokens": 10434433.0,
	"step": 1570
	},
	{
	"entropy": 0.7162799044512212,
	"epoch": 0.703277137929116,
	"grad_norm": 55.75,
	"learning_rate": 1.8713333333333336e-05,
	"loss": 11.4194,
	"mean_token_accuracy": 0.79690898694098,
	"num_tokens": 10500891.0,
	"step": 1580
	},
	{
	"entropy": 0.7040263103321195,
	"epoch": 0.7077282590552495,
	"grad_norm": 49.0,
	"learning_rate": 1.8691111111111114e-05,
	"loss": 11.4425,
	"mean_token_accuracy": 0.8009267061948776,
	"num_tokens": 10567784.0,
	"step": 1590
	},
	{
	"entropy": 0.7154285722412169,
	"epoch": 0.7121793801813832,
	"grad_norm": 45.5,
	"learning_rate": 1.866888888888889e-05,
	"loss": 11.2045,
	"mean_token_accuracy": 0.8016629904508591,
	"num_tokens": 10633325.0,
	"step": 1600
	},
	{
	"epoch": 0.7121793801813832,
	"eval_biology_entropy": 1.2686697797775268,
	"eval_biology_loss": 1.3475232124328613,
	"eval_biology_mean_token_accuracy": 0.6715757512450218,
	"eval_biology_num_tokens": 10633325.0,
	"eval_biology_runtime": 37.2608,
	"eval_biology_samples_per_second": 13.419,
	"eval_biology_steps_per_second": 13.419,
	"step": 1600
	},
	{
	"epoch": 0.7121793801813832,
	"eval_chemistry_entropy": 0.7082813937962055,
	"eval_chemistry_loss": 0.709429144859314,
	"eval_chemistry_mean_token_accuracy": 0.7980507612228394,
	"eval_chemistry_num_tokens": 10633325.0,
	"eval_chemistry_runtime": 41.5255,
	"eval_chemistry_samples_per_second": 12.041,
	"eval_chemistry_steps_per_second": 12.041,
	"step": 1600
	},
	{
	"epoch": 0.7121793801813832,
	"eval_math_entropy": 0.700207156687975,
	"eval_math_loss": 0.8887552618980408,
	"eval_math_mean_token_accuracy": 0.7707038291096687,
	"eval_math_num_tokens": 10633325.0,
	"eval_math_runtime": 41.5728,
	"eval_math_samples_per_second": 12.027,
	"eval_math_steps_per_second": 12.027,
	"step": 1600
	},
	{
	"epoch": 0.7121793801813832,
	"eval_physics_entropy": 0.7126084741950035,
	"eval_physics_loss": 0.7438511848449707,
	"eval_physics_mean_token_accuracy": 0.7933549825549125,
	"eval_physics_num_tokens": 10633325.0,
	"eval_physics_runtime": 45.9285,
	"eval_physics_samples_per_second": 10.886,
	"eval_physics_steps_per_second": 10.886,
	"step": 1600
	},
	{
	"entropy": 0.6555963907390833,
	"epoch": 0.7166305013075168,
	"grad_norm": 46.75,
	"learning_rate": 1.864666666666667e-05,
	"loss": 10.7285,
	"mean_token_accuracy": 0.8088797086849808,
	"num_tokens": 10699737.0,
	"step": 1610
	},
	{
	"entropy": 0.622994406428188,
	"epoch": 0.7210816224336505,
	"grad_norm": 54.0,
	"learning_rate": 1.8624444444444446e-05,
	"loss": 9.9832,
	"mean_token_accuracy": 0.818326310813427,
	"num_tokens": 10764319.0,
	"step": 1620
	},
	{
	"entropy": 0.7015501054003834,
	"epoch": 0.7255327435597841,
	"grad_norm": 49.0,
	"learning_rate": 1.8602222222222224e-05,
	"loss": 11.2865,
	"mean_token_accuracy": 0.79976800493896,
	"num_tokens": 10831617.0,
	"step": 1630
	},
	{
	"entropy": 0.717830996774137,
	"epoch": 0.7299838646859178,
	"grad_norm": 58.25,
	"learning_rate": 1.858e-05,
	"loss": 11.4257,
	"mean_token_accuracy": 0.8004014391452074,
	"num_tokens": 10897916.0,
	"step": 1640
	},
	{
	"entropy": 0.6889832572080195,
	"epoch": 0.7344349858120514,
	"grad_norm": 48.0,
	"learning_rate": 1.855777777777778e-05,
	"loss": 11.124,
	"mean_token_accuracy": 0.8024733573198318,
	"num_tokens": 10965483.0,
	"step": 1650
	},
	{
	"entropy": 0.7227079953998328,
	"epoch": 0.738886106938185,
	"grad_norm": 47.5,
	"learning_rate": 1.8535555555555557e-05,
	"loss": 11.6312,
	"mean_token_accuracy": 0.7963551234453916,
	"num_tokens": 11030485.0,
	"step": 1660
	},
	{
	"entropy": 0.6877313646487891,
	"epoch": 0.7433372280643187,
	"grad_norm": 51.25,
	"learning_rate": 1.8513333333333335e-05,
	"loss": 11.0117,
	"mean_token_accuracy": 0.8049852427095174,
	"num_tokens": 11097108.0,
	"step": 1670
	},
	{
	"entropy": 0.6374788259156048,
	"epoch": 0.7477883491904523,
	"grad_norm": 48.5,
	"learning_rate": 1.8491111111111112e-05,
	"loss": 10.4188,
	"mean_token_accuracy": 0.8140723098069429,
	"num_tokens": 11165356.0,
	"step": 1680
	},
	{
	"entropy": 0.7090142169035971,
	"epoch": 0.752239470316586,
	"grad_norm": 46.25,
	"learning_rate": 1.846888888888889e-05,
	"loss": 11.254,
	"mean_token_accuracy": 0.8003898195922374,
	"num_tokens": 11234429.0,
	"step": 1690
	},
	{
	"entropy": 0.6993439633399248,
	"epoch": 0.7566905914427197,
	"grad_norm": 49.0,
	"learning_rate": 1.8446666666666667e-05,
	"loss": 11.1632,
	"mean_token_accuracy": 0.8017345808446408,
	"num_tokens": 11299223.0,
	"step": 1700
	},
	{
	"epoch": 0.7566905914427197,
	"eval_biology_entropy": 1.2939974426627159,
	"eval_biology_loss": 1.3418560028076172,
	"eval_biology_mean_token_accuracy": 0.6719679839015007,
	"eval_biology_num_tokens": 11299223.0,
	"eval_biology_runtime": 37.3694,
	"eval_biology_samples_per_second": 13.38,
	"eval_biology_steps_per_second": 13.38,
	"step": 1700
	},
	{
	"epoch": 0.7566905914427197,
	"eval_chemistry_entropy": 0.6994238477945328,
	"eval_chemistry_loss": 0.7064142227172852,
	"eval_chemistry_mean_token_accuracy": 0.799383031964302,
	"eval_chemistry_num_tokens": 11299223.0,
	"eval_chemistry_runtime": 41.2811,
	"eval_chemistry_samples_per_second": 12.112,
	"eval_chemistry_steps_per_second": 12.112,
	"step": 1700
	},
	{
	"epoch": 0.7566905914427197,
	"eval_math_entropy": 0.7065025750994682,
	"eval_math_loss": 0.8846055865287781,
	"eval_math_mean_token_accuracy": 0.7727578555345536,
	"eval_math_num_tokens": 11299223.0,
	"eval_math_runtime": 42.3209,
	"eval_math_samples_per_second": 11.814,
	"eval_math_steps_per_second": 11.814,
	"step": 1700
	},
	{
	"epoch": 0.7566905914427197,
	"eval_physics_entropy": 0.7156323294043541,
	"eval_physics_loss": 0.7419880628585815,
	"eval_physics_mean_token_accuracy": 0.794500320136547,
	"eval_physics_num_tokens": 11299223.0,
	"eval_physics_runtime": 46.3513,
	"eval_physics_samples_per_second": 10.787,
	"eval_physics_steps_per_second": 10.787,
	"step": 1700
	},
	{
	"entropy": 0.6807379337958992,
	"epoch": 0.7611417125688533,
	"grad_norm": 44.5,
	"learning_rate": 1.842444444444445e-05,
	"loss": 10.903,
	"mean_token_accuracy": 0.806118119508028,
	"num_tokens": 11371200.0,
	"step": 1710
	},
	{
	"entropy": 0.6858457752503455,
	"epoch": 0.7655928336949869,
	"grad_norm": 48.5,
	"learning_rate": 1.8402222222222223e-05,
	"loss": 11.2529,
	"mean_token_accuracy": 0.8003716830164194,
	"num_tokens": 11436799.0,
	"step": 1720
	},
	{
	"entropy": 0.6833723585121334,
	"epoch": 0.7700439548211205,
	"grad_norm": 56.25,
	"learning_rate": 1.8380000000000004e-05,
	"loss": 10.8605,
	"mean_token_accuracy": 0.8072644464671612,
	"num_tokens": 11502965.0,
	"step": 1730
	},
	{
	"entropy": 0.7146074397489428,
	"epoch": 0.7744950759472542,
	"grad_norm": 46.5,
	"learning_rate": 1.8357777777777778e-05,
	"loss": 11.5601,
	"mean_token_accuracy": 0.7982227748259902,
	"num_tokens": 11567422.0,
	"step": 1740
	},
	{
	"entropy": 0.6696322374045849,
	"epoch": 0.7789461970733879,
	"grad_norm": 38.5,
	"learning_rate": 1.833555555555556e-05,
	"loss": 10.8469,
	"mean_token_accuracy": 0.8079163532704114,
	"num_tokens": 11637076.0,
	"step": 1750
	},
	{
	"entropy": 0.7314721707254648,
	"epoch": 0.7833973181995215,
	"grad_norm": 50.0,
	"learning_rate": 1.8313333333333333e-05,
	"loss": 11.7653,
	"mean_token_accuracy": 0.7910329852253198,
	"num_tokens": 11703496.0,
	"step": 1760
	},
	{
	"entropy": 0.645071561448276,
	"epoch": 0.7878484393256552,
	"grad_norm": 36.75,
	"learning_rate": 1.8291111111111114e-05,
	"loss": 10.1798,
	"mean_token_accuracy": 0.8178190600126982,
	"num_tokens": 11772773.0,
	"step": 1770
	},
	{
	"entropy": 0.656541757658124,
	"epoch": 0.7922995604517888,
	"grad_norm": 46.75,
	"learning_rate": 1.8268888888888888e-05,
	"loss": 10.7678,
	"mean_token_accuracy": 0.8082757320255041,
	"num_tokens": 11840317.0,
	"step": 1780
	},
	{
	"entropy": 0.7429797733202577,
	"epoch": 0.7967506815779224,
	"grad_norm": 59.75,
	"learning_rate": 1.824666666666667e-05,
	"loss": 11.9596,
	"mean_token_accuracy": 0.7920549724251031,
	"num_tokens": 11903376.0,
	"step": 1790
	},
	{
	"entropy": 0.6890028819441796,
	"epoch": 0.801201802704056,
	"grad_norm": 52.0,
	"learning_rate": 1.8224444444444447e-05,
	"loss": 10.9936,
	"mean_token_accuracy": 0.8042987301945687,
	"num_tokens": 11965530.0,
	"step": 1800
	},
	{
	"epoch": 0.801201802704056,
	"eval_biology_entropy": 1.277042101919651,
	"eval_biology_loss": 1.332998275756836,
	"eval_biology_mean_token_accuracy": 0.6726464540362358,
	"eval_biology_num_tokens": 11965530.0,
	"eval_biology_runtime": 37.3225,
	"eval_biology_samples_per_second": 13.397,
	"eval_biology_steps_per_second": 13.397,
	"step": 1800
	},
	{
	"epoch": 0.801201802704056,
	"eval_chemistry_entropy": 0.6964197388291359,
	"eval_chemistry_loss": 0.6977025270462036,
	"eval_chemistry_mean_token_accuracy": 0.800601690530777,
	"eval_chemistry_num_tokens": 11965530.0,
	"eval_chemistry_runtime": 41.1955,
	"eval_chemistry_samples_per_second": 12.137,
	"eval_chemistry_steps_per_second": 12.137,
	"step": 1800
	},
	{
	"epoch": 0.801201802704056,
	"eval_math_entropy": 0.691622546583414,
	"eval_math_loss": 0.884013831615448,
	"eval_math_mean_token_accuracy": 0.7728146443367004,
	"eval_math_num_tokens": 11965530.0,
	"eval_math_runtime": 41.3293,
	"eval_math_samples_per_second": 12.098,
	"eval_math_steps_per_second": 12.098,
	"step": 1800
	},
	{
	"epoch": 0.801201802704056,
	"eval_physics_entropy": 0.7113458831310272,
	"eval_physics_loss": 0.7380439639091492,
	"eval_physics_mean_token_accuracy": 0.7949880036711693,
	"eval_physics_num_tokens": 11965530.0,
	"eval_physics_runtime": 45.7175,
	"eval_physics_samples_per_second": 10.937,
	"eval_physics_steps_per_second": 10.937,
	"step": 1800
	},
	{
	"entropy": 0.6916238307952881,
	"epoch": 0.8056529238301897,
	"grad_norm": 54.0,
	"learning_rate": 1.8202222222222225e-05,
	"loss": 11.1738,
	"mean_token_accuracy": 0.802581525221467,
	"num_tokens": 12031493.0,
	"step": 1810
	},
	{
	"entropy": 0.6883499003015459,
	"epoch": 0.8101040449563234,
	"grad_norm": 47.0,
	"learning_rate": 1.8180000000000002e-05,
	"loss": 11.1564,
	"mean_token_accuracy": 0.8044124312698842,
	"num_tokens": 12097917.0,
	"step": 1820
	},
	{
	"entropy": 0.6930434329435229,
	"epoch": 0.814555166082457,
	"grad_norm": 46.25,
	"learning_rate": 1.815777777777778e-05,
	"loss": 11.0779,
	"mean_token_accuracy": 0.8034347232431174,
	"num_tokens": 12163029.0,
	"step": 1830
	},
	{
	"entropy": 0.6947093228809536,
	"epoch": 0.8190062872085907,
	"grad_norm": 58.5,
	"learning_rate": 1.8135555555555557e-05,
	"loss": 11.3123,
	"mean_token_accuracy": 0.7996832799166441,
	"num_tokens": 12224427.0,
	"step": 1840
	},
	{
	"entropy": 0.719798219576478,
	"epoch": 0.8234574083347244,
	"grad_norm": 43.25,
	"learning_rate": 1.8113333333333335e-05,
	"loss": 11.4131,
	"mean_token_accuracy": 0.8016381539404392,
	"num_tokens": 12291917.0,
	"step": 1850
	},
	{
	"entropy": 0.669582040514797,
	"epoch": 0.8279085294608579,
	"grad_norm": 48.25,
	"learning_rate": 1.8091111111111113e-05,
	"loss": 10.7576,
	"mean_token_accuracy": 0.8064643792808056,
	"num_tokens": 12365332.0,
	"step": 1860
	},
	{
	"entropy": 0.6633579313755036,
	"epoch": 0.8323596505869916,
	"grad_norm": 41.25,
	"learning_rate": 1.806888888888889e-05,
	"loss": 10.6729,
	"mean_token_accuracy": 0.806138664111495,
	"num_tokens": 12441423.0,
	"step": 1870
	},
	{
	"entropy": 0.6549396699294447,
	"epoch": 0.8368107717131252,
	"grad_norm": 50.5,
	"learning_rate": 1.8046666666666668e-05,
	"loss": 10.4457,
	"mean_token_accuracy": 0.8124689020216465,
	"num_tokens": 12509124.0,
	"step": 1880
	},
	{
	"entropy": 0.6255366197787225,
	"epoch": 0.8412618928392589,
	"grad_norm": 43.25,
	"learning_rate": 1.8024444444444445e-05,
	"loss": 10.236,
	"mean_token_accuracy": 0.8123138222843409,
	"num_tokens": 12575355.0,
	"step": 1890
	},
	{
	"entropy": 0.6981251872144639,
	"epoch": 0.8457130139653926,
	"grad_norm": 59.75,
	"learning_rate": 1.8002222222222223e-05,
	"loss": 11.3401,
	"mean_token_accuracy": 0.799917110055685,
	"num_tokens": 12642651.0,
	"step": 1900
	},
	{
	"epoch": 0.8457130139653926,
	"eval_biology_entropy": 1.2781688437461853,
	"eval_biology_loss": 1.337692379951477,
	"eval_biology_mean_token_accuracy": 0.6727457674741745,
	"eval_biology_num_tokens": 12642651.0,
	"eval_biology_runtime": 36.7254,
	"eval_biology_samples_per_second": 13.615,
	"eval_biology_steps_per_second": 13.615,
	"step": 1900
	},
	{
	"epoch": 0.8457130139653926,
	"eval_chemistry_entropy": 0.6981815086901187,
	"eval_chemistry_loss": 0.6955837607383728,
	"eval_chemistry_mean_token_accuracy": 0.8022230199575424,
	"eval_chemistry_num_tokens": 12642651.0,
	"eval_chemistry_runtime": 40.4028,
	"eval_chemistry_samples_per_second": 12.375,
	"eval_chemistry_steps_per_second": 12.375,
	"step": 1900
	},
	{
	"epoch": 0.8457130139653926,
	"eval_math_entropy": 0.6860641204416752,
	"eval_math_loss": 0.8941249251365662,
	"eval_math_mean_token_accuracy": 0.7716994079351425,
	"eval_math_num_tokens": 12642651.0,
	"eval_math_runtime": 41.4747,
	"eval_math_samples_per_second": 12.056,
	"eval_math_steps_per_second": 12.056,
	"step": 1900
	},
	{
	"epoch": 0.8457130139653926,
	"eval_physics_entropy": 0.7120301985144615,
	"eval_physics_loss": 0.7369678020477295,
	"eval_physics_mean_token_accuracy": 0.7946544420719147,
	"eval_physics_num_tokens": 12642651.0,
	"eval_physics_runtime": 45.5815,
	"eval_physics_samples_per_second": 10.969,
	"eval_physics_steps_per_second": 10.969,
	"step": 1900
	},
	{
	"entropy": 0.6538136603310705,
	"epoch": 0.8501641350915262,
	"grad_norm": 42.0,
	"learning_rate": 1.798e-05,
	"loss": 10.2863,
	"mean_token_accuracy": 0.8125439338386059,
	"num_tokens": 12710065.0,
	"step": 1910
	},
	{
	"entropy": 0.6856445983983577,
	"epoch": 0.8546152562176598,
	"grad_norm": 50.75,
	"learning_rate": 1.7957777777777778e-05,
	"loss": 10.9931,
	"mean_token_accuracy": 0.8032558988779783,
	"num_tokens": 12778408.0,
	"step": 1920
	},
	{
	"entropy": 0.6402218439616263,
	"epoch": 0.8590663773437934,
	"grad_norm": 53.75,
	"learning_rate": 1.7935555555555556e-05,
	"loss": 10.3931,
	"mean_token_accuracy": 0.8133255753666162,
	"num_tokens": 12845949.0,
	"step": 1930
	},
	{
	"entropy": 0.687981967907399,
	"epoch": 0.8635174984699271,
	"grad_norm": 53.5,
	"learning_rate": 1.7913333333333337e-05,
	"loss": 10.9298,
	"mean_token_accuracy": 0.8087461933493614,
	"num_tokens": 12910630.0,
	"step": 1940
	},
	{
	"entropy": 0.6755717716179788,
	"epoch": 0.8679686195960608,
	"grad_norm": 47.75,
	"learning_rate": 1.789111111111111e-05,
	"loss": 11.1314,
	"mean_token_accuracy": 0.8019361585378647,
	"num_tokens": 12975379.0,
	"step": 1950
	},
	{
	"entropy": 0.6678634139709174,
	"epoch": 0.8724197407221944,
	"grad_norm": 42.0,
	"learning_rate": 1.7868888888888892e-05,
	"loss": 10.5302,
	"mean_token_accuracy": 0.8089069448411464,
	"num_tokens": 13046473.0,
	"step": 1960
	},
	{
	"entropy": 0.7141758069396019,
	"epoch": 0.8768708618483281,
	"grad_norm": 44.75,
	"learning_rate": 1.7846666666666666e-05,
	"loss": 11.6782,
	"mean_token_accuracy": 0.7963042937219142,
	"num_tokens": 13105019.0,
	"step": 1970
	},
	{
	"entropy": 0.7312607789412141,
	"epoch": 0.8813219829744617,
	"grad_norm": 47.75,
	"learning_rate": 1.7824444444444447e-05,
	"loss": 11.4252,
	"mean_token_accuracy": 0.8010873660445214,
	"num_tokens": 13167768.0,
	"step": 1980
	},
	{
	"entropy": 0.6517805024050176,
	"epoch": 0.8857731041005953,
	"grad_norm": 46.25,
	"learning_rate": 1.780222222222222e-05,
	"loss": 10.6298,
	"mean_token_accuracy": 0.8119962867349386,
	"num_tokens": 13235899.0,
	"step": 1990
	},
	{
	"entropy": 0.6774258488789201,
	"epoch": 0.890224225226729,
	"grad_norm": 40.5,
	"learning_rate": 1.7780000000000003e-05,
	"loss": 10.7589,
	"mean_token_accuracy": 0.8065350767225027,
	"num_tokens": 13301659.0,
	"step": 2000
	},
	{
	"epoch": 0.890224225226729,
	"eval_biology_entropy": 1.2670730832815171,
	"eval_biology_loss": 1.333166241645813,
	"eval_biology_mean_token_accuracy": 0.6740682775974274,
	"eval_biology_num_tokens": 13301659.0,
	"eval_biology_runtime": 36.6935,
	"eval_biology_samples_per_second": 13.626,
	"eval_biology_steps_per_second": 13.626,
	"step": 2000
	},
	{
	"epoch": 0.890224225226729,
	"eval_chemistry_entropy": 0.6871010038554668,
	"eval_chemistry_loss": 0.6869096755981445,
	"eval_chemistry_mean_token_accuracy": 0.8039456156492233,
	"eval_chemistry_num_tokens": 13301659.0,
	"eval_chemistry_runtime": 40.6168,
	"eval_chemistry_samples_per_second": 12.31,
	"eval_chemistry_steps_per_second": 12.31,
	"step": 2000
	},
	{
	"epoch": 0.890224225226729,
	"eval_math_entropy": 0.6870918811559678,
	"eval_math_loss": 0.8818830847740173,
	"eval_math_mean_token_accuracy": 0.7737292177677154,
	"eval_math_num_tokens": 13301659.0,
	"eval_math_runtime": 41.1765,
	"eval_math_samples_per_second": 12.143,
	"eval_math_steps_per_second": 12.143,
	"step": 2000
	},
	{
	"epoch": 0.890224225226729,
	"eval_physics_entropy": 0.7050596924424172,
	"eval_physics_loss": 0.7348896861076355,
	"eval_physics_mean_token_accuracy": 0.7955606966018677,
	"eval_physics_num_tokens": 13301659.0,
	"eval_physics_runtime": 45.6515,
	"eval_physics_samples_per_second": 10.953,
	"eval_physics_steps_per_second": 10.953,
	"step": 2000
	}
	],
	"logging_steps": 10,
	"max_steps": 10000,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 5,
	"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": 8.919343158882048e+17,
	"train_batch_size": 1,
	"trial_name": null,
	"trial_params": null
	}