Instructions to use xiangmin/Qwen2.5-1.5B-Open-R1-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xiangmin/Qwen2.5-1.5B-Open-R1-Distill with Transformers:

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

pipe = pipeline("text-generation", model="xiangmin/Qwen2.5-1.5B-Open-R1-Distill")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xiangmin/Qwen2.5-1.5B-Open-R1-Distill")
model = AutoModelForCausalLM.from_pretrained("xiangmin/Qwen2.5-1.5B-Open-R1-Distill")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xiangmin/Qwen2.5-1.5B-Open-R1-Distill with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xiangmin/Qwen2.5-1.5B-Open-R1-Distill"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xiangmin/Qwen2.5-1.5B-Open-R1-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xiangmin/Qwen2.5-1.5B-Open-R1-Distill

SGLang

How to use xiangmin/Qwen2.5-1.5B-Open-R1-Distill 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 "xiangmin/Qwen2.5-1.5B-Open-R1-Distill" \
    --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": "xiangmin/Qwen2.5-1.5B-Open-R1-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "xiangmin/Qwen2.5-1.5B-Open-R1-Distill" \
        --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": "xiangmin/Qwen2.5-1.5B-Open-R1-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xiangmin/Qwen2.5-1.5B-Open-R1-Distill with Docker Model Runner:
```
docker model run hf.co/xiangmin/Qwen2.5-1.5B-Open-R1-Distill
```

xiangmin commited on May 26, 2025

Commit

6e036f5

verified ·

1 Parent(s): 0a9d082

Model save

Browse files

Files changed (4) hide show

README.md +2 -4
all_results.json +4 -4
train_results.json +4 -4
trainer_state.json +215 -215

README.md CHANGED Viewed

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: open-r1/OpenR1-Math-220k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 # Model Card for Qwen2.5-1.5B-Open-R1-Distill
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
@@ -29,7 +27,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/cai-aml/huggingface/runs/si17d4wx)
 This model was trained with SFT.

 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill
 tags:
 - generated_from_trainer
 - trl
 - sft
 licence: license
 # Model Card for Qwen2.5-1.5B-Open-R1-Distill
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/cai-aml/huggingface/runs/dxxsdlyn)
 This model was trained with SFT.

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 1147472759488512.0,
-    "train_loss": 0.534455504293819,
-    "train_runtime": 5840.8745,
     "train_samples": 93733,
-    "train_samples_per_second": 16.048,
-    "train_steps_per_second": 0.125
 }

 {
     "total_flos": 1147472759488512.0,
+    "train_loss": 0.30104584323107625,
+    "train_runtime": 3582.5752,
     "train_samples": 93733,
+    "train_samples_per_second": 26.164,
+    "train_steps_per_second": 0.205
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 1147472759488512.0,
-    "train_loss": 0.534455504293819,
-    "train_runtime": 5840.8745,
     "train_samples": 93733,
-    "train_samples_per_second": 16.048,
-    "train_steps_per_second": 0.125
 }

 {
     "total_flos": 1147472759488512.0,
+    "train_loss": 0.30104584323107625,
+    "train_runtime": 3582.5752,
     "train_samples": 93733,
+    "train_samples_per_second": 26.164,
+    "train_steps_per_second": 0.205
 }

trainer_state.json CHANGED Viewed

@@ -491,701 +491,701 @@
     },
     {
       "epoch": 0.41609822646657574,
-      "grad_norm": 0.3099209598552495,
       "learning_rate": 3.55443126760184e-05,
       "loss": 0.5344,
-      "num_tokens": 233617525.0,
       "step": 305
     },
     {
       "epoch": 0.4229195088676671,
-      "grad_norm": 0.3529220471477521,
       "learning_rate": 3.506806758087894e-05,
-      "loss": 0.5321,
-      "num_tokens": 237394471.0,
       "step": 310
     },
     {
       "epoch": 0.4297407912687585,
-      "grad_norm": 0.3162865974560433,
       "learning_rate": 3.458796781007437e-05,
       "loss": 0.5267,
-      "num_tokens": 241114261.0,
       "step": 315
     },
     {
       "epoch": 0.43656207366984995,
-      "grad_norm": 0.28886537698280157,
       "learning_rate": 3.410425789483854e-05,
       "loss": 0.527,
-      "num_tokens": 244967987.0,
       "step": 320
     },
     {
       "epoch": 0.4433833560709413,
-      "grad_norm": 0.28164089279301285,
       "learning_rate": 3.3617184205175304e-05,
       "loss": 0.5335,
-      "num_tokens": 248751095.0,
       "step": 325
     },
     {
       "epoch": 0.45020463847203274,
-      "grad_norm": 0.3413109548071712,
       "learning_rate": 3.312699482437392e-05,
       "loss": 0.5207,
-      "num_tokens": 252607265.0,
       "step": 330
     },
     {
       "epoch": 0.45702592087312416,
-      "grad_norm": 0.3092721268667011,
       "learning_rate": 3.263393942265168e-05,
       "loss": 0.5274,
-      "num_tokens": 256417909.0,
       "step": 335
     },
     {
       "epoch": 0.4638472032742155,
-      "grad_norm": 0.2590061007411309,
       "learning_rate": 3.213826912998838e-05,
       "loss": 0.5199,
-      "num_tokens": 260456429.0,
       "step": 340
     },
     {
       "epoch": 0.47066848567530695,
-      "grad_norm": 0.2711268499630015,
       "learning_rate": 3.164023640821719e-05,
-      "loss": 0.5132,
-      "num_tokens": 264287905.0,
       "step": 345
     },
     {
       "epoch": 0.47748976807639837,
-      "grad_norm": 0.27680149244124186,
       "learning_rate": 3.114009492243721e-05,
       "loss": 0.5216,
-      "num_tokens": 268098790.0,
       "step": 350
     },
     {
       "epoch": 0.4843110504774898,
-      "grad_norm": 0.2823801438277264,
       "learning_rate": 3.063809941181321e-05,
       "loss": 0.5312,
-      "num_tokens": 271974065.0,
       "step": 355
     },
     {
       "epoch": 0.49113233287858116,
-      "grad_norm": 0.28194159167640576,
       "learning_rate": 3.0134505559828203e-05,
       "loss": 0.535,
-      "num_tokens": 275852045.0,
       "step": 360
     },
     {
       "epoch": 0.4979536152796726,
-      "grad_norm": 0.28231899006661904,
       "learning_rate": 2.9629569864055125e-05,
-      "loss": 0.513,
-      "num_tokens": 279504484.0,
       "step": 365
     },
     {
       "epoch": 0.504774897680764,
-      "grad_norm": 0.2670208895882678,
       "learning_rate": 2.9123549505513868e-05,
-      "loss": 0.515,
-      "num_tokens": 283461546.0,
       "step": 370
     },
     {
       "epoch": 0.5115961800818554,
-      "grad_norm": 0.2612428242224826,
       "learning_rate": 2.8616702217680134e-05,
       "loss": 0.5229,
-      "num_tokens": 287371918.0,
       "step": 375
     },
     {
       "epoch": 0.5184174624829468,
-      "grad_norm": 0.2729592102578874,
       "learning_rate": 2.810928615521303e-05,
       "loss": 0.5096,
-      "num_tokens": 291057738.0,
       "step": 380
     },
     {
       "epoch": 0.5252387448840382,
-      "grad_norm": 0.2778899693883255,
       "learning_rate": 2.7601559762468022e-05,
       "loss": 0.5188,
-      "num_tokens": 294881963.0,
       "step": 385
     },
     {
       "epoch": 0.5320600272851296,
-      "grad_norm": 0.274603578763847,
       "learning_rate": 2.7093781641862387e-05,
-      "loss": 0.5213,
-      "num_tokens": 298677895.0,
       "step": 390
     },
     {
       "epoch": 0.538881309686221,
-      "grad_norm": 0.26619780357847966,
       "learning_rate": 2.658621042216021e-05,
       "loss": 0.5056,
-      "num_tokens": 302387985.0,
       "step": 395
     },
     {
       "epoch": 0.5457025920873124,
-      "grad_norm": 0.39558826097700545,
       "learning_rate": 2.6079104626743845e-05,
-      "loss": 0.5276,
-      "num_tokens": 306130593.0,
       "step": 400
     },
     {
       "epoch": 0.5525238744884038,
-      "grad_norm": 0.29167229643413684,
       "learning_rate": 2.5572722541939113e-05,
-      "loss": 0.5251,
-      "num_tokens": 309952008.0,
       "step": 405
     },
     {
       "epoch": 0.5593451568894953,
-      "grad_norm": 0.3040463384774853,
       "learning_rate": 2.5067322085461315e-05,
-      "loss": 0.5105,
-      "num_tokens": 313725489.0,
       "step": 410
     },
     {
       "epoch": 0.5661664392905866,
-      "grad_norm": 0.3170563745378486,
       "learning_rate": 2.4563160675048846e-05,
-      "loss": 0.5156,
-      "num_tokens": 317525148.0,
       "step": 415
     },
     {
       "epoch": 0.572987721691678,
-      "grad_norm": 0.26263360764520943,
       "learning_rate": 2.406049509735156e-05,
       "loss": 0.5154,
-      "num_tokens": 321410101.0,
       "step": 420
     },
     {
       "epoch": 0.5798090040927695,
-      "grad_norm": 0.28279429332439865,
       "learning_rate": 2.355958137714056e-05,
       "loss": 0.5108,
-      "num_tokens": 325102278.0,
       "step": 425
     },
     {
       "epoch": 0.5866302864938608,
-      "grad_norm": 0.2710949104594765,
       "learning_rate": 2.3060674646906004e-05,
-      "loss": 0.5155,
-      "num_tokens": 328831071.0,
       "step": 430
     },
     {
       "epoch": 0.5934515688949522,
-      "grad_norm": 0.3080171220709838,
       "learning_rate": 2.2564029016909416e-05,
       "loss": 0.5049,
-      "num_tokens": 332767044.0,
       "step": 435
     },
     {
       "epoch": 0.6002728512960437,
-      "grad_norm": 0.26331637507299344,
       "learning_rate": 2.2069897445756627e-05,
       "loss": 0.5028,
-      "num_tokens": 336595638.0,
       "step": 440
     },
     {
       "epoch": 0.607094133697135,
-      "grad_norm": 0.2684843667821617,
       "learning_rate": 2.1578531611557322e-05,
       "loss": 0.5158,
-      "num_tokens": 340358925.0,
       "step": 445
     },
     {
       "epoch": 0.6139154160982264,
-      "grad_norm": 0.2385819727205317,
       "learning_rate": 2.109018178373675e-05,
-      "loss": 0.5146,
-      "num_tokens": 344239058.0,
       "step": 450
     },
     {
       "epoch": 0.6207366984993179,
-      "grad_norm": 0.2598960975843206,
       "learning_rate": 2.0605096695564973e-05,
-      "loss": 0.5181,
-      "num_tokens": 348080585.0,
       "step": 455
     },
     {
       "epoch": 0.6275579809004093,
-      "grad_norm": 0.24602112714779262,
       "learning_rate": 2.0123523417468466e-05,
       "loss": 0.5115,
-      "num_tokens": 351817695.0,
       "step": 460
     },
     {
       "epoch": 0.6343792633015006,
-      "grad_norm": 0.2501964592548225,
       "learning_rate": 1.9645707231188742e-05,
-      "loss": 0.5058,
-      "num_tokens": 355639183.0,
       "step": 465
     },
     {
       "epoch": 0.6412005457025921,
-      "grad_norm": 0.24391824225090533,
       "learning_rate": 1.9171891504851925e-05,
-      "loss": 0.5244,
-      "num_tokens": 359437581.0,
       "step": 470
     },
     {
       "epoch": 0.6480218281036835,
-      "grad_norm": 0.25070191219804666,
       "learning_rate": 1.8702317569013094e-05,
       "loss": 0.5005,
-      "num_tokens": 363189983.0,
       "step": 475
     },
     {
       "epoch": 0.654843110504775,
-      "grad_norm": 0.22730280722360974,
       "learning_rate": 1.8237224593738327e-05,
       "loss": 0.5027,
-      "num_tokens": 366863209.0,
       "step": 480
     },
     {
       "epoch": 0.6616643929058663,
-      "grad_norm": 0.2276661675885326,
       "learning_rate": 1.7776849466787223e-05,
-      "loss": 0.517,
-      "num_tokens": 370725860.0,
       "step": 485
     },
     {
       "epoch": 0.6684856753069577,
-      "grad_norm": 0.23399685197875958,
       "learning_rate": 1.7321426672957896e-05,
       "loss": 0.5025,
-      "num_tokens": 374566515.0,
       "step": 490
     },
     {
       "epoch": 0.6753069577080492,
-      "grad_norm": 0.2545696283757528,
       "learning_rate": 1.6871188174655787e-05,
       "loss": 0.4957,
-      "num_tokens": 378330489.0,
       "step": 495
     },
     {
       "epoch": 0.6821282401091405,
-      "grad_norm": 0.23612681642030256,
       "learning_rate": 1.6426363293747334e-05,
       "loss": 0.5001,
-      "num_tokens": 382103468.0,
       "step": 500
     },
     {
       "epoch": 0.6889495225102319,
-      "grad_norm": 0.23953988886028593,
       "learning_rate": 1.598717859475846e-05,
-      "loss": 0.5086,
-      "num_tokens": 385837297.0,
       "step": 505
     },
     {
       "epoch": 0.6957708049113234,
-      "grad_norm": 0.23473822783088263,
       "learning_rate": 1.5553857769477553e-05,
-      "loss": 0.5055,
-      "num_tokens": 389586680.0,
       "step": 510
     },
     {
       "epoch": 0.7025920873124147,
-      "grad_norm": 0.23023236031367206,
       "learning_rate": 1.5126621523021518e-05,
       "loss": 0.51,
-      "num_tokens": 393428760.0,
       "step": 515
     },
     {
       "epoch": 0.7094133697135061,
-      "grad_norm": 0.2589772804506706,
       "learning_rate": 1.4705687461423209e-05,
-      "loss": 0.5221,
-      "num_tokens": 397158700.0,
       "step": 520
     },
     {
       "epoch": 0.7162346521145976,
-      "grad_norm": 0.2415958133778606,
       "learning_rate": 1.4291269980797139e-05,
-      "loss": 0.5064,
-      "num_tokens": 400923938.0,
       "step": 525
     },
     {
       "epoch": 0.723055934515689,
-      "grad_norm": 0.22668113790836616,
       "learning_rate": 1.3883580158140291e-05,
-      "loss": 0.5004,
-      "num_tokens": 404685655.0,
       "step": 530
     },
     {
       "epoch": 0.7298772169167803,
-      "grad_norm": 0.22127981327259097,
       "learning_rate": 1.3482825643823293e-05,
       "loss": 0.5061,
-      "num_tokens": 408582799.0,
       "step": 535
     },
     {
       "epoch": 0.7366984993178718,
-      "grad_norm": 0.2259924969508103,
       "learning_rate": 1.3089210555827086e-05,
       "loss": 0.5118,
-      "num_tokens": 412386009.0,
       "step": 540
     },
     {
       "epoch": 0.7435197817189632,
-      "grad_norm": 0.2180260894680547,
       "learning_rate": 1.270293537577855e-05,
       "loss": 0.5148,
-      "num_tokens": 416372039.0,
       "step": 545
     },
     {
       "epoch": 0.7503410641200545,
-      "grad_norm": 0.22274596139404082,
       "learning_rate": 1.232419684683844e-05,
-      "loss": 0.4994,
-      "num_tokens": 420051975.0,
       "step": 550
     },
     {
       "epoch": 0.757162346521146,
-      "grad_norm": 0.22524105300086206,
       "learning_rate": 1.1953187873493303e-05,
-      "loss": 0.5,
-      "num_tokens": 423685709.0,
       "step": 555
     },
     {
       "epoch": 0.7639836289222374,
-      "grad_norm": 0.23121126044864895,
       "learning_rate": 1.1590097423302684e-05,
       "loss": 0.496,
-      "num_tokens": 427405904.0,
       "step": 560
     },
     {
       "epoch": 0.7708049113233287,
-      "grad_norm": 0.2253367969358726,
       "learning_rate": 1.1235110430651421e-05,
       "loss": 0.496,
-      "num_tokens": 431288378.0,
       "step": 565
     },
     {
       "epoch": 0.7776261937244202,
-      "grad_norm": 0.23618031425846644,
       "learning_rate": 1.0888407702556284e-05,
       "loss": 0.4998,
-      "num_tokens": 435077995.0,
       "step": 570
     },
     {
       "epoch": 0.7844474761255116,
-      "grad_norm": 0.24326628120813396,
       "learning_rate": 1.0550165826574766e-05,
-      "loss": 0.4996,
-      "num_tokens": 439006864.0,
       "step": 575
     },
     {
       "epoch": 0.791268758526603,
-      "grad_norm": 0.23402109238815982,
       "learning_rate": 1.0220557080862985e-05,
       "loss": 0.5149,
-      "num_tokens": 443045688.0,
       "step": 580
     },
     {
       "epoch": 0.7980900409276944,
-      "grad_norm": 0.2168709652784759,
       "learning_rate": 9.899749346428556e-06,
       "loss": 0.5021,
-      "num_tokens": 446852018.0,
       "step": 585
     },
     {
       "epoch": 0.8049113233287858,
-      "grad_norm": 0.20973047446941873,
       "learning_rate": 9.587906021623016e-06,
       "loss": 0.5161,
-      "num_tokens": 450687287.0,
       "step": 590
     },
     {
       "epoch": 0.8117326057298773,
-      "grad_norm": 0.2387886991698634,
       "learning_rate": 9.28518593891749e-06,
       "loss": 0.5013,
-      "num_tokens": 454483896.0,
       "step": 595
     },
     {
       "epoch": 0.8185538881309686,
-      "grad_norm": 0.2251531608022542,
       "learning_rate": 8.99174328400385e-06,
-      "loss": 0.4996,
-      "num_tokens": 458325861.0,
       "step": 600
     },
     {
       "epoch": 0.82537517053206,
-      "grad_norm": 0.23014309977486713,
       "learning_rate": 8.707727517262697e-06,
       "loss": 0.5049,
-      "num_tokens": 462055868.0,
       "step": 605
     },
     {
       "epoch": 0.8321964529331515,
-      "grad_norm": 0.2096077092845327,
       "learning_rate": 8.433283297638053e-06,
-      "loss": 0.4992,
-      "num_tokens": 465973876.0,
       "step": 610
     },
     {
       "epoch": 0.8390177353342428,
-      "grad_norm": 0.22206287075780984,
       "learning_rate": 8.168550408957632e-06,
       "loss": 0.497,
-      "num_tokens": 469791498.0,
       "step": 615
     },
     {
       "epoch": 0.8458390177353342,
-      "grad_norm": 0.2319999609225239,
       "learning_rate": 7.91366368873613e-06,
       "loss": 0.4944,
-      "num_tokens": 473570581.0,
       "step": 620
     },
     {
       "epoch": 0.8526603001364257,
-      "grad_norm": 0.2274136998295581,
       "learning_rate": 7.66875295949791e-06,
-      "loss": 0.5104,
-      "num_tokens": 477401353.0,
       "step": 625
     },
     {
       "epoch": 0.859481582537517,
-      "grad_norm": 0.2046769390363853,
       "learning_rate": 7.4339429626539e-06,
       "loss": 0.5102,
-      "num_tokens": 481348892.0,
       "step": 630
     },
     {
       "epoch": 0.8663028649386084,
-      "grad_norm": 0.22846201748188963,
       "learning_rate": 7.2093532949665715e-06,
-      "loss": 0.508,
-      "num_tokens": 485171910.0,
       "step": 635
     },
     {
       "epoch": 0.8731241473396999,
-      "grad_norm": 0.20762434733770965,
       "learning_rate": 6.995098347635173e-06,
       "loss": 0.4933,
-      "num_tokens": 489059548.0,
       "step": 640
     },
     {
       "epoch": 0.8799454297407913,
-      "grad_norm": 0.20995778440608662,
       "learning_rate": 6.791287248032431e-06,
       "loss": 0.4966,
-      "num_tokens": 492893029.0,
       "step": 645
     },
     {
       "epoch": 0.8867667121418826,
-      "grad_norm": 0.2173052377166794,
       "learning_rate": 6.598023804122194e-06,
-      "loss": 0.5038,
-      "num_tokens": 496905674.0,
       "step": 650
     },
     {
       "epoch": 0.8935879945429741,
-      "grad_norm": 0.2035162341638187,
       "learning_rate": 6.415406451586528e-06,
-      "loss": 0.4993,
-      "num_tokens": 500864542.0,
       "step": 655
     },
     {
       "epoch": 0.9004092769440655,
-      "grad_norm": 0.20568936678232122,
       "learning_rate": 6.243528203689025e-06,
-      "loss": 0.5032,
-      "num_tokens": 504810366.0,
       "step": 660
     },
     {
       "epoch": 0.9072305593451568,
-      "grad_norm": 0.21574037095216414,
       "learning_rate": 6.0824766039e-06,
       "loss": 0.4994,
-      "num_tokens": 508607232.0,
       "step": 665
     },
     {
       "epoch": 0.9140518417462483,
-      "grad_norm": 0.20829091997292817,
       "learning_rate": 5.932333681307571e-06,
-      "loss": 0.5061,
-      "num_tokens": 512474084.0,
       "step": 670
     },
     {
       "epoch": 0.9208731241473397,
-      "grad_norm": 0.20452875029014483,
       "learning_rate": 5.793175908837471e-06,
       "loss": 0.4967,
-      "num_tokens": 516216104.0,
       "step": 675
     },
     {
       "epoch": 0.927694406548431,
-      "grad_norm": 0.2052072085504751,
       "learning_rate": 5.665074164302742e-06,
       "loss": 0.5064,
-      "num_tokens": 519966345.0,
       "step": 680
     },
     {
       "epoch": 0.9345156889495225,
-      "grad_norm": 0.1945613196672915,
       "learning_rate": 5.548093694303275e-06,
-      "loss": 0.4918,
-      "num_tokens": 523793837.0,
       "step": 685
     },
     {
       "epoch": 0.9413369713506139,
-      "grad_norm": 0.21553055514992556,
       "learning_rate": 5.442294080993446e-06,
       "loss": 0.5059,
-      "num_tokens": 527666864.0,
       "step": 690
     },
     {
       "epoch": 0.9481582537517054,
-      "grad_norm": 0.2024360201970052,
       "learning_rate": 5.347729211734919e-06,
-      "loss": 0.5033,
-      "num_tokens": 531466359.0,
       "step": 695
     },
     {
       "epoch": 0.9549795361527967,
-      "grad_norm": 0.19988923735791775,
       "learning_rate": 5.264447251649954e-06,
       "loss": 0.5057,
-      "num_tokens": 535253217.0,
       "step": 700
     },
     {
       "epoch": 0.9618008185538881,
-      "grad_norm": 0.20540497402805713,
       "learning_rate": 5.192490619089267e-06,
-      "loss": 0.4899,
-      "num_tokens": 539137436.0,
       "step": 705
     },
     {
       "epoch": 0.9686221009549796,
-      "grad_norm": 0.2061857821408682,
       "learning_rate": 5.1318959640269095e-06,
-      "loss": 0.5004,
-      "num_tokens": 542824098.0,
       "step": 710
     },
     {
       "epoch": 0.975443383356071,
-      "grad_norm": 0.2121827667911945,
       "learning_rate": 5.082694149393189e-06,
-      "loss": 0.5113,
-      "num_tokens": 546578047.0,
       "step": 715
     },
     {
       "epoch": 0.9822646657571623,
-      "grad_norm": 0.20411496705924861,
       "learning_rate": 5.044910235355121e-06,
       "loss": 0.4974,
-      "num_tokens": 550377811.0,
       "step": 720
     },
     {
       "epoch": 0.9890859481582538,
-      "grad_norm": 0.19437182334999942,
       "learning_rate": 5.0185634665524255e-06,
-      "loss": 0.4933,
-      "num_tokens": 554224024.0,
       "step": 725
     },
     {
       "epoch": 0.9959072305593452,
-      "grad_norm": 0.1908094183807672,
       "learning_rate": 5.003667262295572e-06,
-      "loss": 0.5014,
-      "num_tokens": 558001366.0,
       "step": 730
     },
     {
       "epoch": 1.0,
-      "num_tokens": 560311272.0,
       "step": 733,
       "total_flos": 1147472759488512.0,
-      "train_loss": 0.534455504293819,
-      "train_runtime": 5840.8745,
-      "train_samples_per_second": 16.048,
-      "train_steps_per_second": 0.125
     }
   ],
   "logging_steps": 5,

     },
     {
       "epoch": 0.41609822646657574,
+      "grad_norm": 0.31150738136265943,
       "learning_rate": 3.55443126760184e-05,
       "loss": 0.5344,
+      "num_tokens": 3907038.0,
       "step": 305
     },
     {
       "epoch": 0.4229195088676671,
+      "grad_norm": 0.3468593061143695,
       "learning_rate": 3.506806758087894e-05,
+      "loss": 0.532,
+      "num_tokens": 7683984.0,
       "step": 310
     },
     {
       "epoch": 0.4297407912687585,
+      "grad_norm": 0.31656776462890823,
       "learning_rate": 3.458796781007437e-05,
       "loss": 0.5267,
+      "num_tokens": 11403774.0,
       "step": 315
     },
     {
       "epoch": 0.43656207366984995,
+      "grad_norm": 0.2905862187240268,
       "learning_rate": 3.410425789483854e-05,
       "loss": 0.527,
+      "num_tokens": 15257500.0,
       "step": 320
     },
     {
       "epoch": 0.4433833560709413,
+      "grad_norm": 0.2862429453666647,
       "learning_rate": 3.3617184205175304e-05,
       "loss": 0.5335,
+      "num_tokens": 19040608.0,
       "step": 325
     },
     {
       "epoch": 0.45020463847203274,
+      "grad_norm": 0.34169112866025547,
       "learning_rate": 3.312699482437392e-05,
       "loss": 0.5207,
+      "num_tokens": 22896778.0,
       "step": 330
     },
     {
       "epoch": 0.45702592087312416,
+      "grad_norm": 0.28811353179764293,
       "learning_rate": 3.263393942265168e-05,
       "loss": 0.5274,
+      "num_tokens": 26707422.0,
       "step": 335
     },
     {
       "epoch": 0.4638472032742155,
+      "grad_norm": 0.25952079134670186,
       "learning_rate": 3.213826912998838e-05,
       "loss": 0.5199,
+      "num_tokens": 30745942.0,
       "step": 340
     },
     {
       "epoch": 0.47066848567530695,
+      "grad_norm": 0.27171779465267426,
       "learning_rate": 3.164023640821719e-05,
+      "loss": 0.5131,
+      "num_tokens": 34577418.0,
       "step": 345
     },
     {
       "epoch": 0.47748976807639837,
+      "grad_norm": 0.2756410136692784,
       "learning_rate": 3.114009492243721e-05,
       "loss": 0.5216,
+      "num_tokens": 38388303.0,
       "step": 350
     },
     {
       "epoch": 0.4843110504774898,
+      "grad_norm": 0.2862166299702774,
       "learning_rate": 3.063809941181321e-05,
       "loss": 0.5312,
+      "num_tokens": 42263578.0,
       "step": 355
     },
     {
       "epoch": 0.49113233287858116,
+      "grad_norm": 0.2776215155538455,
       "learning_rate": 3.0134505559828203e-05,
       "loss": 0.535,
+      "num_tokens": 46141558.0,
       "step": 360
     },
     {
       "epoch": 0.4979536152796726,
+      "grad_norm": 0.27939238016420803,
       "learning_rate": 2.9629569864055125e-05,
+      "loss": 0.5129,
+      "num_tokens": 49793997.0,
       "step": 365
     },
     {
       "epoch": 0.504774897680764,
+      "grad_norm": 0.27656045657678896,
       "learning_rate": 2.9123549505513868e-05,
+      "loss": 0.5149,
+      "num_tokens": 53751059.0,
       "step": 370
     },
     {
       "epoch": 0.5115961800818554,
+      "grad_norm": 0.2612718920094276,
       "learning_rate": 2.8616702217680134e-05,
       "loss": 0.5229,
+      "num_tokens": 57661431.0,
       "step": 375
     },
     {
       "epoch": 0.5184174624829468,
+      "grad_norm": 0.2707456092353873,
       "learning_rate": 2.810928615521303e-05,
       "loss": 0.5096,
+      "num_tokens": 61347251.0,
       "step": 380
     },
     {
       "epoch": 0.5252387448840382,
+      "grad_norm": 0.2775857141913436,
       "learning_rate": 2.7601559762468022e-05,
       "loss": 0.5188,
+      "num_tokens": 65171476.0,
       "step": 385
     },
     {
       "epoch": 0.5320600272851296,
+      "grad_norm": 0.2749180870715325,
       "learning_rate": 2.7093781641862387e-05,
+      "loss": 0.5214,
+      "num_tokens": 68967408.0,
       "step": 390
     },
     {
       "epoch": 0.538881309686221,
+      "grad_norm": 0.2736617594464445,
       "learning_rate": 2.658621042216021e-05,
       "loss": 0.5056,
+      "num_tokens": 72677498.0,
       "step": 395
     },
     {
       "epoch": 0.5457025920873124,
+      "grad_norm": 0.3724340666807813,
       "learning_rate": 2.6079104626743845e-05,
+      "loss": 0.5275,
+      "num_tokens": 76420106.0,
       "step": 400
     },
     {
       "epoch": 0.5525238744884038,
+      "grad_norm": 0.30148187800324094,
       "learning_rate": 2.5572722541939113e-05,
+      "loss": 0.536,
+      "num_tokens": 80241521.0,
       "step": 405
     },
     {
       "epoch": 0.5593451568894953,
+      "grad_norm": 0.2878146937468534,
       "learning_rate": 2.5067322085461315e-05,
+      "loss": 0.5108,
+      "num_tokens": 84015002.0,
       "step": 410
     },
     {
       "epoch": 0.5661664392905866,
+      "grad_norm": 0.28481014661061205,
       "learning_rate": 2.4563160675048846e-05,
+      "loss": 0.5158,
+      "num_tokens": 87814661.0,
       "step": 415
     },
     {
       "epoch": 0.572987721691678,
+      "grad_norm": 0.24871308571539336,
       "learning_rate": 2.406049509735156e-05,
       "loss": 0.5154,
+      "num_tokens": 91699614.0,
       "step": 420
     },
     {
       "epoch": 0.5798090040927695,
+      "grad_norm": 0.26997468779109357,
       "learning_rate": 2.355958137714056e-05,
       "loss": 0.5108,
+      "num_tokens": 95391791.0,
       "step": 425
     },
     {
       "epoch": 0.5866302864938608,
+      "grad_norm": 0.26920569189193183,
       "learning_rate": 2.3060674646906004e-05,
+      "loss": 0.5156,
+      "num_tokens": 99120584.0,
       "step": 430
     },
     {
       "epoch": 0.5934515688949522,
+      "grad_norm": 0.3031035959753903,
       "learning_rate": 2.2564029016909416e-05,
       "loss": 0.5049,
+      "num_tokens": 103056557.0,
       "step": 435
     },
     {
       "epoch": 0.6002728512960437,
+      "grad_norm": 0.2579912157887462,
       "learning_rate": 2.2069897445756627e-05,
       "loss": 0.5028,
+      "num_tokens": 106885151.0,
       "step": 440
     },
     {
       "epoch": 0.607094133697135,
+      "grad_norm": 0.2784368496163028,
       "learning_rate": 2.1578531611557322e-05,
       "loss": 0.5158,
+      "num_tokens": 110648438.0,
       "step": 445
     },
     {
       "epoch": 0.6139154160982264,
+      "grad_norm": 0.23783581714130014,
       "learning_rate": 2.109018178373675e-05,
+      "loss": 0.5147,
+      "num_tokens": 114528571.0,
       "step": 450
     },
     {
       "epoch": 0.6207366984993179,
+      "grad_norm": 0.2631301529092457,
       "learning_rate": 2.0605096695564973e-05,
+      "loss": 0.5182,
+      "num_tokens": 118370098.0,
       "step": 455
     },
     {
       "epoch": 0.6275579809004093,
+      "grad_norm": 0.23896035357377207,
       "learning_rate": 2.0123523417468466e-05,
       "loss": 0.5115,
+      "num_tokens": 122107208.0,
       "step": 460
     },
     {
       "epoch": 0.6343792633015006,
+      "grad_norm": 0.23911200744006897,
       "learning_rate": 1.9645707231188742e-05,
+      "loss": 0.5059,
+      "num_tokens": 125928696.0,
       "step": 465
     },
     {
       "epoch": 0.6412005457025921,
+      "grad_norm": 0.23484644246089895,
       "learning_rate": 1.9171891504851925e-05,
+      "loss": 0.5245,
+      "num_tokens": 129727094.0,
       "step": 470
     },
     {
       "epoch": 0.6480218281036835,
+      "grad_norm": 0.24843133644098161,
       "learning_rate": 1.8702317569013094e-05,
       "loss": 0.5005,
+      "num_tokens": 133479496.0,
       "step": 475
     },
     {
       "epoch": 0.654843110504775,
+      "grad_norm": 0.2298705134606327,
       "learning_rate": 1.8237224593738327e-05,
       "loss": 0.5027,
+      "num_tokens": 137152722.0,
       "step": 480
     },
     {
       "epoch": 0.6616643929058663,
+      "grad_norm": 0.22725265159045924,
       "learning_rate": 1.7776849466787223e-05,
+      "loss": 0.5171,
+      "num_tokens": 141015373.0,
       "step": 485
     },
     {
       "epoch": 0.6684856753069577,
+      "grad_norm": 0.23065567630923026,
       "learning_rate": 1.7321426672957896e-05,
       "loss": 0.5025,
+      "num_tokens": 144856028.0,
       "step": 490
     },
     {
       "epoch": 0.6753069577080492,
+      "grad_norm": 0.2535249608874267,
       "learning_rate": 1.6871188174655787e-05,
       "loss": 0.4957,
+      "num_tokens": 148620002.0,
       "step": 495
     },
     {
       "epoch": 0.6821282401091405,
+      "grad_norm": 0.2364234203218564,
       "learning_rate": 1.6426363293747334e-05,
       "loss": 0.5001,
+      "num_tokens": 152392981.0,
       "step": 500
     },
     {
       "epoch": 0.6889495225102319,
+      "grad_norm": 0.23889880611363135,
       "learning_rate": 1.598717859475846e-05,
+      "loss": 0.5087,
+      "num_tokens": 156126810.0,
       "step": 505
     },
     {
       "epoch": 0.6957708049113234,
+      "grad_norm": 0.2380901600704711,
       "learning_rate": 1.5553857769477553e-05,
+      "loss": 0.5056,
+      "num_tokens": 159876193.0,
       "step": 510
     },
     {
       "epoch": 0.7025920873124147,
+      "grad_norm": 0.23096714274240995,
       "learning_rate": 1.5126621523021518e-05,
       "loss": 0.51,
+      "num_tokens": 163718273.0,
       "step": 515
     },
     {
       "epoch": 0.7094133697135061,
+      "grad_norm": 0.2614099659251973,
       "learning_rate": 1.4705687461423209e-05,
+      "loss": 0.5222,
+      "num_tokens": 167448213.0,
       "step": 520
     },
     {
       "epoch": 0.7162346521145976,
+      "grad_norm": 0.24328778538778423,
       "learning_rate": 1.4291269980797139e-05,
+      "loss": 0.5065,
+      "num_tokens": 171213451.0,
       "step": 525
     },
     {
       "epoch": 0.723055934515689,
+      "grad_norm": 0.22585661056099277,
       "learning_rate": 1.3883580158140291e-05,
+      "loss": 0.5005,
+      "num_tokens": 174975168.0,
       "step": 530
     },
     {
       "epoch": 0.7298772169167803,
+      "grad_norm": 0.215782449764828,
       "learning_rate": 1.3482825643823293e-05,
       "loss": 0.5061,
+      "num_tokens": 178872312.0,
       "step": 535
     },
     {
       "epoch": 0.7366984993178718,
+      "grad_norm": 0.222477664399686,
       "learning_rate": 1.3089210555827086e-05,
       "loss": 0.5118,
+      "num_tokens": 182675522.0,
       "step": 540
     },
     {
       "epoch": 0.7435197817189632,
+      "grad_norm": 0.2161279545613622,
       "learning_rate": 1.270293537577855e-05,
       "loss": 0.5148,
+      "num_tokens": 186661552.0,
       "step": 545
     },
     {
       "epoch": 0.7503410641200545,
+      "grad_norm": 0.22038438633805268,
       "learning_rate": 1.232419684683844e-05,
+      "loss": 0.4995,
+      "num_tokens": 190341488.0,
       "step": 550
     },
     {
       "epoch": 0.757162346521146,
+      "grad_norm": 0.22277137142362485,
       "learning_rate": 1.1953187873493303e-05,
+      "loss": 0.5001,
+      "num_tokens": 193975222.0,
       "step": 555
     },
     {
       "epoch": 0.7639836289222374,
+      "grad_norm": 0.22629794051271598,
       "learning_rate": 1.1590097423302684e-05,
       "loss": 0.496,
+      "num_tokens": 197695417.0,
       "step": 560
     },
     {
       "epoch": 0.7708049113233287,
+      "grad_norm": 0.22169310674789464,
       "learning_rate": 1.1235110430651421e-05,
       "loss": 0.496,
+      "num_tokens": 201577891.0,
       "step": 565
     },
     {
       "epoch": 0.7776261937244202,
+      "grad_norm": 0.23737206300393107,
       "learning_rate": 1.0888407702556284e-05,
       "loss": 0.4998,
+      "num_tokens": 205367508.0,
       "step": 570
     },
     {
       "epoch": 0.7844474761255116,
+      "grad_norm": 0.2393464614182903,
       "learning_rate": 1.0550165826574766e-05,
+      "loss": 0.4997,
+      "num_tokens": 209296377.0,
       "step": 575
     },
     {
       "epoch": 0.791268758526603,
+      "grad_norm": 0.23434104494246727,
       "learning_rate": 1.0220557080862985e-05,
       "loss": 0.5149,
+      "num_tokens": 213335201.0,
       "step": 580
     },
     {
       "epoch": 0.7980900409276944,
+      "grad_norm": 0.2163862184189319,
       "learning_rate": 9.899749346428556e-06,
       "loss": 0.5021,
+      "num_tokens": 217141531.0,
       "step": 585
     },
     {
       "epoch": 0.8049113233287858,
+      "grad_norm": 0.20944439534899864,
       "learning_rate": 9.587906021623016e-06,
       "loss": 0.5161,
+      "num_tokens": 220976800.0,
       "step": 590
     },
     {
       "epoch": 0.8117326057298773,
+      "grad_norm": 0.240618025701599,
       "learning_rate": 9.28518593891749e-06,
       "loss": 0.5013,
+      "num_tokens": 224773409.0,
       "step": 595
     },
     {
       "epoch": 0.8185538881309686,
+      "grad_norm": 0.22360256823330674,
       "learning_rate": 8.99174328400385e-06,
+      "loss": 0.4997,
+      "num_tokens": 228615374.0,
       "step": 600
     },
     {
       "epoch": 0.82537517053206,
+      "grad_norm": 0.22996095480097895,
       "learning_rate": 8.707727517262697e-06,
       "loss": 0.5049,
+      "num_tokens": 232345381.0,
       "step": 605
     },
     {
       "epoch": 0.8321964529331515,
+      "grad_norm": 0.20996010138499008,
       "learning_rate": 8.433283297638053e-06,
+      "loss": 0.4993,
+      "num_tokens": 236263389.0,
       "step": 610
     },
     {
       "epoch": 0.8390177353342428,
+      "grad_norm": 0.21860095878565663,
       "learning_rate": 8.168550408957632e-06,
       "loss": 0.497,
+      "num_tokens": 240081011.0,
       "step": 615
     },
     {
       "epoch": 0.8458390177353342,
+      "grad_norm": 0.2245915474005529,
       "learning_rate": 7.91366368873613e-06,
       "loss": 0.4944,
+      "num_tokens": 243860094.0,
       "step": 620
     },
     {
       "epoch": 0.8526603001364257,
+      "grad_norm": 0.2282695347327931,
       "learning_rate": 7.66875295949791e-06,
+      "loss": 0.5105,
+      "num_tokens": 247690866.0,
       "step": 625
     },
     {
       "epoch": 0.859481582537517,
+      "grad_norm": 0.20590616989328062,
       "learning_rate": 7.4339429626539e-06,
       "loss": 0.5102,
+      "num_tokens": 251638405.0,
       "step": 630
     },
     {
       "epoch": 0.8663028649386084,
+      "grad_norm": 0.22956608740204826,
       "learning_rate": 7.2093532949665715e-06,
+      "loss": 0.5081,
+      "num_tokens": 255461423.0,
       "step": 635
     },
     {
       "epoch": 0.8731241473396999,
+      "grad_norm": 0.20757611016240565,
       "learning_rate": 6.995098347635173e-06,
       "loss": 0.4933,
+      "num_tokens": 259349061.0,
       "step": 640
     },
     {
       "epoch": 0.8799454297407913,
+      "grad_norm": 0.20964621674214579,
       "learning_rate": 6.791287248032431e-06,
       "loss": 0.4966,
+      "num_tokens": 263182542.0,
       "step": 645
     },
     {
       "epoch": 0.8867667121418826,
+      "grad_norm": 0.21533152300615474,
       "learning_rate": 6.598023804122194e-06,
+      "loss": 0.5039,
+      "num_tokens": 267195187.0,
       "step": 650
     },
     {
       "epoch": 0.8935879945429741,
+      "grad_norm": 0.20262214665120437,
       "learning_rate": 6.415406451586528e-06,
+      "loss": 0.4994,
+      "num_tokens": 271154055.0,
       "step": 655
     },
     {
       "epoch": 0.9004092769440655,
+      "grad_norm": 0.20455436089558837,
       "learning_rate": 6.243528203689025e-06,
+      "loss": 0.5033,
+      "num_tokens": 275099879.0,
       "step": 660
     },
     {
       "epoch": 0.9072305593451568,
+      "grad_norm": 0.2160125533680774,
       "learning_rate": 6.0824766039e-06,
       "loss": 0.4994,
+      "num_tokens": 278896745.0,
       "step": 665
     },
     {
       "epoch": 0.9140518417462483,
+      "grad_norm": 0.20835263251242925,
       "learning_rate": 5.932333681307571e-06,
+      "loss": 0.5062,
+      "num_tokens": 282763597.0,
       "step": 670
     },
     {
       "epoch": 0.9208731241473397,
+      "grad_norm": 0.2056127608186567,
       "learning_rate": 5.793175908837471e-06,
       "loss": 0.4967,
+      "num_tokens": 286505617.0,
       "step": 675
     },
     {
       "epoch": 0.927694406548431,
+      "grad_norm": 0.20738306050857,
       "learning_rate": 5.665074164302742e-06,
       "loss": 0.5064,
+      "num_tokens": 290255858.0,
       "step": 680
     },
     {
       "epoch": 0.9345156889495225,
+      "grad_norm": 0.1943049409331778,
       "learning_rate": 5.548093694303275e-06,
+      "loss": 0.4919,
+      "num_tokens": 294083350.0,
       "step": 685
     },
     {
       "epoch": 0.9413369713506139,
+      "grad_norm": 0.21891210362180955,
       "learning_rate": 5.442294080993446e-06,
       "loss": 0.5059,
+      "num_tokens": 297956377.0,
       "step": 690
     },
     {
       "epoch": 0.9481582537517054,
+      "grad_norm": 0.2045825966835107,
       "learning_rate": 5.347729211734919e-06,
+      "loss": 0.5034,
+      "num_tokens": 301755872.0,
       "step": 695
     },
     {
       "epoch": 0.9549795361527967,
+      "grad_norm": 0.20096771321359547,
       "learning_rate": 5.264447251649954e-06,
       "loss": 0.5057,
+      "num_tokens": 305542730.0,
       "step": 700
     },
     {
       "epoch": 0.9618008185538881,
+      "grad_norm": 0.20627903017723062,
       "learning_rate": 5.192490619089267e-06,
+      "loss": 0.49,
+      "num_tokens": 309426949.0,
       "step": 705
     },
     {
       "epoch": 0.9686221009549796,
+      "grad_norm": 0.20761322654529332,
       "learning_rate": 5.1318959640269095e-06,
+      "loss": 0.5005,
+      "num_tokens": 313113611.0,
       "step": 710
     },
     {
       "epoch": 0.975443383356071,
+      "grad_norm": 0.2108636029151623,
       "learning_rate": 5.082694149393189e-06,
+      "loss": 0.5114,
+      "num_tokens": 316867560.0,
       "step": 715
     },
     {
       "epoch": 0.9822646657571623,
+      "grad_norm": 0.2031630473017727,
       "learning_rate": 5.044910235355121e-06,
       "loss": 0.4974,
+      "num_tokens": 320667324.0,
       "step": 720
     },
     {
       "epoch": 0.9890859481582538,
+      "grad_norm": 0.19315901995067375,
       "learning_rate": 5.0185634665524255e-06,
+      "loss": 0.4934,
+      "num_tokens": 324513537.0,
       "step": 725
     },
     {
       "epoch": 0.9959072305593452,
+      "grad_norm": 0.1922060062694041,
       "learning_rate": 5.003667262295572e-06,
+      "loss": 0.5015,
+      "num_tokens": 328290879.0,
       "step": 730
     },
     {
       "epoch": 1.0,
+      "num_tokens": 330600785.0,
       "step": 733,
       "total_flos": 1147472759488512.0,
+      "train_loss": 0.30104584323107625,
+      "train_runtime": 3582.5752,
+      "train_samples_per_second": 26.164,
+      "train_steps_per_second": 0.205
     }
   ],
   "logging_steps": 5,