Instructions to use somukandula/context-aware-abstention-qwen-0.5b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use somukandula/context-aware-abstention-qwen-0.5b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="somukandula/context-aware-abstention-qwen-0.5b-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("somukandula/context-aware-abstention-qwen-0.5b-v2")
model = AutoModelForCausalLM.from_pretrained("somukandula/context-aware-abstention-qwen-0.5b-v2", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use somukandula/context-aware-abstention-qwen-0.5b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "somukandula/context-aware-abstention-qwen-0.5b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "somukandula/context-aware-abstention-qwen-0.5b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/somukandula/context-aware-abstention-qwen-0.5b-v2

SGLang

How to use somukandula/context-aware-abstention-qwen-0.5b-v2 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 "somukandula/context-aware-abstention-qwen-0.5b-v2" \
    --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": "somukandula/context-aware-abstention-qwen-0.5b-v2",
		"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 "somukandula/context-aware-abstention-qwen-0.5b-v2" \
        --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": "somukandula/context-aware-abstention-qwen-0.5b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use somukandula/context-aware-abstention-qwen-0.5b-v2 with Docker Model Runner:
```
docker model run hf.co/somukandula/context-aware-abstention-qwen-0.5b-v2
```

somukandula commited on May 2

Commit

2c60494

verified ·

1 Parent(s): fb25f35

Training in progress, step 1000, checkpoint

Browse files

Files changed (5) hide show

last-checkpoint/model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/rng_state.pth +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/trainer_state.json +559 -4

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83da3cc8d0218d62a3164a7f716bade572679ed97e6acdc62c1a60da3e0b312d
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:d6e36b41feb21954e8f396a2d8342f35a3b4f0170ff153e8a1d351d55d23aee3
 size 1976163472

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb10ff4270335cfa294cb8498658921326a00498f3ac6ab8a415df9ba2cadef1
 size 3952497611

 version https://git-lfs.github.com/spec/v1
+oid sha256:92e3465bef651dabb018fb28f710ca4e9921e22cb7ce494aa47f070b09f77e85
 size 3952497611

last-checkpoint/rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a763ef6ed853db2b72ad6002c008f5c95fc932fde0276699fb1687f7a8bc945
 size 14455

 version https://git-lfs.github.com/spec/v1
+oid sha256:a5c072297b22cc2262340128dcd1a46763a029e534c43cd59943bae67d4d6c32
 size 14455

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809d84065af7746ce8e1dde90d00972c61a19282d6465b5b2c63be219520d047
 size 1465

 version https://git-lfs.github.com/spec/v1
+oid sha256:7860e2aded14c970768e5cc51a1f317cd1d854d3438aee28e508e1c5ae782642
 size 1465

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
   "eval_steps": 100,
-  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -573,6 +573,561 @@
       "eval_samples_per_second": 1.475,
       "eval_steps_per_second": 1.475,
       "step": 500
     }
   ],
   "logging_steps": 10,
@@ -587,12 +1142,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 63485398699008.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 1.0,
   "eval_steps": 100,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 1.475,
       "eval_steps_per_second": 1.475,
       "step": 500
+    },
+    {
+      "entropy": 0.6581952810287476,
+      "epoch": 0.51,
+      "grad_norm": 0.2650947868824005,
+      "learning_rate": 1.473e-05,
+      "loss": 0.8746847152709961,
+      "mean_token_accuracy": 0.8366666734218597,
+      "num_tokens": 30180.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.2867848143563606,
+      "epoch": 0.52,
+      "grad_norm": 0.0694449320435524,
+      "learning_rate": 1.4429999999999999e-05,
+      "loss": 0.8548201560974121,
+      "mean_token_accuracy": 0.9023809552192688,
+      "num_tokens": 30787.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.6530944091908168,
+      "epoch": 0.53,
+      "grad_norm": 0.02836558222770691,
+      "learning_rate": 1.413e-05,
+      "loss": 1.4652270317077636,
+      "mean_token_accuracy": 0.794761911034584,
+      "num_tokens": 31402.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.35715593958157116,
+      "epoch": 0.54,
+      "grad_norm": 0.015686016529798508,
+      "learning_rate": 1.3830000000000001e-05,
+      "loss": 1.026433563232422,
+      "mean_token_accuracy": 0.8828571438789368,
+      "num_tokens": 31952.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.6746627187123522,
+      "epoch": 0.55,
+      "grad_norm": 0.47357332706451416,
+      "learning_rate": 1.3530000000000001e-05,
+      "loss": 2.541259765625,
+      "mean_token_accuracy": 0.7191666692495347,
+      "num_tokens": 32489.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.8612912893295288,
+      "epoch": 0.56,
+      "grad_norm": 0.26455482840538025,
+      "learning_rate": 1.323e-05,
+      "loss": 1.4012706756591797,
+      "mean_token_accuracy": 0.8428571462631226,
+      "num_tokens": 33085.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.5583918301854283,
+      "epoch": 0.57,
+      "grad_norm": 64.6652603149414,
+      "learning_rate": 1.293e-05,
+      "loss": 2.232314682006836,
+      "mean_token_accuracy": 0.6770238131284714,
+      "num_tokens": 33766.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.22949749184772372,
+      "epoch": 0.58,
+      "grad_norm": 32.17295455932617,
+      "learning_rate": 1.263e-05,
+      "loss": 0.6436846256256104,
+      "mean_token_accuracy": 0.8900000005960464,
+      "num_tokens": 34339.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.4105657983804122,
+      "epoch": 0.59,
+      "grad_norm": 0.35221877694129944,
+      "learning_rate": 1.2329999999999999e-05,
+      "loss": 1.1233172416687012,
+      "mean_token_accuracy": 0.8490476220846176,
+      "num_tokens": 34887.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.46966382283717395,
+      "epoch": 0.6,
+      "grad_norm": 57.49447250366211,
+      "learning_rate": 1.2030000000000002e-05,
+      "loss": 1.294736671447754,
+      "mean_token_accuracy": 0.8233333379030228,
+      "num_tokens": 35518.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.6,
+      "eval_entropy": 0.736768285461585,
+      "eval_loss": 1.3659862279891968,
+      "eval_mean_token_accuracy": 0.7910032506287098,
+      "eval_num_tokens": 35518.0,
+      "eval_runtime": 58.971,
+      "eval_samples_per_second": 1.696,
+      "eval_steps_per_second": 1.696,
+      "step": 600
+    },
+    {
+      "entropy": 0.3451525355922058,
+      "epoch": 0.61,
+      "grad_norm": 37.80137252807617,
+      "learning_rate": 1.1730000000000001e-05,
+      "loss": 0.9265684127807617,
+      "mean_token_accuracy": 0.8773809552192688,
+      "num_tokens": 36134.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.9583770901896059,
+      "epoch": 0.62,
+      "grad_norm": 107.27765655517578,
+      "learning_rate": 1.143e-05,
+      "loss": 2.295991897583008,
+      "mean_token_accuracy": 0.7400000020861626,
+      "num_tokens": 36699.0,
+      "step": 620
+    },
+    {
+      "entropy": 1.026821926701814,
+      "epoch": 0.63,
+      "grad_norm": 93.11579132080078,
+      "learning_rate": 1.113e-05,
+      "loss": 1.9422128677368165,
+      "mean_token_accuracy": 0.7183333396911621,
+      "num_tokens": 37283.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.7774730216711759,
+      "epoch": 0.64,
+      "grad_norm": 204.85580444335938,
+      "learning_rate": 1.083e-05,
+      "loss": 1.3309831619262695,
+      "mean_token_accuracy": 0.7738888919353485,
+      "num_tokens": 37968.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.7349455378018319,
+      "epoch": 0.65,
+      "grad_norm": 1.482122778892517,
+      "learning_rate": 1.0529999999999999e-05,
+      "loss": 1.176546859741211,
+      "mean_token_accuracy": 0.7619047671556473,
+      "num_tokens": 38540.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.27391568799503146,
+      "epoch": 0.66,
+      "grad_norm": 12.381733894348145,
+      "learning_rate": 1.023e-05,
+      "loss": 0.6918275833129883,
+      "mean_token_accuracy": 0.8930952399969101,
+      "num_tokens": 39094.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.1004896673723124,
+      "epoch": 0.67,
+      "grad_norm": 0.03492867574095726,
+      "learning_rate": 9.930000000000001e-06,
+      "loss": 0.2918921232223511,
+      "mean_token_accuracy": 0.9523809552192688,
+      "num_tokens": 39661.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.9908906043478055,
+      "epoch": 0.68,
+      "grad_norm": 0.06755176931619644,
+      "learning_rate": 9.630000000000001e-06,
+      "loss": 1.8555622100830078,
+      "mean_token_accuracy": 0.7571428656578064,
+      "num_tokens": 40324.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.46606744623859414,
+      "epoch": 0.69,
+      "grad_norm": 0.020008454099297523,
+      "learning_rate": 9.33e-06,
+      "loss": 1.5950393676757812,
+      "mean_token_accuracy": 0.8166666716337204,
+      "num_tokens": 40979.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.651082917675376,
+      "epoch": 0.7,
+      "grad_norm": 171.28536987304688,
+      "learning_rate": 9.03e-06,
+      "loss": 1.6578060150146485,
+      "mean_token_accuracy": 0.7446428596973419,
+      "num_tokens": 41569.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.7,
+      "eval_entropy": 0.4609421466873027,
+      "eval_loss": 1.6514569520950317,
+      "eval_mean_token_accuracy": 0.783146109431982,
+      "eval_num_tokens": 41569.0,
+      "eval_runtime": 57.3197,
+      "eval_samples_per_second": 1.745,
+      "eval_steps_per_second": 1.745,
+      "step": 700
+    },
+    {
+      "entropy": 0.5237987950094976,
+      "epoch": 0.71,
+      "grad_norm": 57.0805549621582,
+      "learning_rate": 8.73e-06,
+      "loss": 1.5300618171691895,
+      "mean_token_accuracy": 0.8150000005960465,
+      "num_tokens": 42214.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.9100498335435987,
+      "epoch": 0.72,
+      "grad_norm": 177.79803466796875,
+      "learning_rate": 8.43e-06,
+      "loss": 1.8969627380371095,
+      "mean_token_accuracy": 0.707857146859169,
+      "num_tokens": 42835.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.6799977218732238,
+      "epoch": 0.73,
+      "grad_norm": 0.859414279460907,
+      "learning_rate": 8.13e-06,
+      "loss": 1.8602033615112306,
+      "mean_token_accuracy": 0.7766666740179062,
+      "num_tokens": 43464.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.7358979027718305,
+      "epoch": 0.74,
+      "grad_norm": 59.640167236328125,
+      "learning_rate": 7.830000000000001e-06,
+      "loss": 1.2427146911621094,
+      "mean_token_accuracy": 0.8309523850679398,
+      "num_tokens": 44060.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.31579577242955564,
+      "epoch": 0.75,
+      "grad_norm": 0.6564598679542542,
+      "learning_rate": 7.53e-06,
+      "loss": 1.7427587509155273,
+      "mean_token_accuracy": 0.7794047683477402,
+      "num_tokens": 44635.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.3871447135694325,
+      "epoch": 0.76,
+      "grad_norm": 0.08916488289833069,
+      "learning_rate": 7.23e-06,
+      "loss": 0.5494258880615235,
+      "mean_token_accuracy": 0.8638888895511627,
+      "num_tokens": 45205.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.31627349692862483,
+      "epoch": 0.77,
+      "grad_norm": 0.17271661758422852,
+      "learning_rate": 6.9300000000000006e-06,
+      "loss": 0.9221712112426758,
+      "mean_token_accuracy": 0.8933333337306977,
+      "num_tokens": 45745.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.21427990994416177,
+      "epoch": 0.78,
+      "grad_norm": 93.88026428222656,
+      "learning_rate": 6.63e-06,
+      "loss": 1.2273402214050293,
+      "mean_token_accuracy": 0.8244444489479065,
+      "num_tokens": 46375.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.6328038854058832,
+      "epoch": 0.79,
+      "grad_norm": 0.08321687579154968,
+      "learning_rate": 6.3299999999999995e-06,
+      "loss": 1.449633502960205,
+      "mean_token_accuracy": 0.8183982685208321,
+      "num_tokens": 46920.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.8517522903392092,
+      "epoch": 0.8,
+      "grad_norm": 0.360664963722229,
+      "learning_rate": 6.030000000000001e-06,
+      "loss": 1.5935587882995605,
+      "mean_token_accuracy": 0.746666669845581,
+      "num_tokens": 47483.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "eval_entropy": 0.5362537594168679,
+      "eval_loss": 1.291225790977478,
+      "eval_mean_token_accuracy": 0.809991346001625,
+      "eval_num_tokens": 47483.0,
+      "eval_runtime": 54.557,
+      "eval_samples_per_second": 1.833,
+      "eval_steps_per_second": 1.833,
+      "step": 800
+    },
+    {
+      "entropy": 0.5658039237372577,
+      "epoch": 0.81,
+      "grad_norm": 24.69063377380371,
+      "learning_rate": 5.73e-06,
+      "loss": 1.6795099258422852,
+      "mean_token_accuracy": 0.7500000089406967,
+      "num_tokens": 48112.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.23472772459499538,
+      "epoch": 0.82,
+      "grad_norm": 0.13677963614463806,
+      "learning_rate": 5.43e-06,
+      "loss": 0.620347547531128,
+      "mean_token_accuracy": 0.9066666692495347,
+      "num_tokens": 48686.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.17872974590864033,
+      "epoch": 0.83,
+      "grad_norm": 0.062276676297187805,
+      "learning_rate": 5.130000000000001e-06,
+      "loss": 0.3392207384109497,
+      "mean_token_accuracy": 0.9583333313465119,
+      "num_tokens": 49263.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.7390760766458697,
+      "epoch": 0.84,
+      "grad_norm": 55.52785110473633,
+      "learning_rate": 4.83e-06,
+      "loss": 1.9530868530273438,
+      "mean_token_accuracy": 0.6723809599876404,
+      "num_tokens": 49957.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.2889916429063305,
+      "epoch": 0.85,
+      "grad_norm": 0.03663825988769531,
+      "learning_rate": 4.53e-06,
+      "loss": 0.8394488334655762,
+      "mean_token_accuracy": 0.9300000011920929,
+      "num_tokens": 50557.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.3451875123893842,
+      "epoch": 0.86,
+      "grad_norm": 256.18017578125,
+      "learning_rate": 4.229999999999999e-06,
+      "loss": 1.5904621124267577,
+      "mean_token_accuracy": 0.7757142901420593,
+      "num_tokens": 51137.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.739490092662163,
+      "epoch": 0.87,
+      "grad_norm": 127.49256896972656,
+      "learning_rate": 3.9300000000000005e-06,
+      "loss": 2.1090816497802733,
+      "mean_token_accuracy": 0.7933333396911622,
+      "num_tokens": 51710.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.36512562771094964,
+      "epoch": 0.88,
+      "grad_norm": 189.27102661132812,
+      "learning_rate": 3.63e-06,
+      "loss": 1.6141580581665038,
+      "mean_token_accuracy": 0.8483333349227905,
+      "num_tokens": 52235.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.3579067521728575,
+      "epoch": 0.89,
+      "grad_norm": 40.83726119995117,
+      "learning_rate": 3.3300000000000003e-06,
+      "loss": 1.1513096809387207,
+      "mean_token_accuracy": 0.8666666716337204,
+      "num_tokens": 52865.0,
+      "step": 890
+    },
+    {
+      "entropy": 1.2824254330713303,
+      "epoch": 0.9,
+      "grad_norm": 58.594825744628906,
+      "learning_rate": 3.0300000000000002e-06,
+      "loss": 2.8049795150756838,
+      "mean_token_accuracy": 0.5883333355188369,
+      "num_tokens": 53435.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.9,
+      "eval_entropy": 0.5797992533538491,
+      "eval_loss": 1.262194037437439,
+      "eval_mean_token_accuracy": 0.8182532505691051,
+      "eval_num_tokens": 53435.0,
+      "eval_runtime": 58.521,
+      "eval_samples_per_second": 1.709,
+      "eval_steps_per_second": 1.709,
+      "step": 900
+    },
+    {
+      "entropy": 0.3366681849118322,
+      "epoch": 0.91,
+      "grad_norm": 32.87790298461914,
+      "learning_rate": 2.73e-06,
+      "loss": 0.47661585807800294,
+      "mean_token_accuracy": 0.9041666686534882,
+      "num_tokens": 54024.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.6118204056750983,
+      "epoch": 0.92,
+      "grad_norm": 0.7896237969398499,
+      "learning_rate": 2.43e-06,
+      "loss": 1.956801414489746,
+      "mean_token_accuracy": 0.7933333396911622,
+      "num_tokens": 54605.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.7288894818164409,
+      "epoch": 0.93,
+      "grad_norm": 0.16806739568710327,
+      "learning_rate": 2.13e-06,
+      "loss": 1.7675352096557617,
+      "mean_token_accuracy": 0.7876190513372421,
+      "num_tokens": 55295.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.4382998514920473,
+      "epoch": 0.94,
+      "grad_norm": 0.584433376789093,
+      "learning_rate": 1.83e-06,
+      "loss": 1.6188522338867188,
+      "mean_token_accuracy": 0.816666665673256,
+      "num_tokens": 55887.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.5724920945242047,
+      "epoch": 0.95,
+      "grad_norm": 10.927814483642578,
+      "learning_rate": 1.53e-06,
+      "loss": 1.0138172149658202,
+      "mean_token_accuracy": 0.8507142901420593,
+      "num_tokens": 56413.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.6996954609872773,
+      "epoch": 0.96,
+      "grad_norm": 0.10312433540821075,
+      "learning_rate": 1.23e-06,
+      "loss": 1.4810507774353028,
+      "mean_token_accuracy": 0.7691666692495346,
+      "num_tokens": 57003.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.49967088787816466,
+      "epoch": 0.97,
+      "grad_norm": 114.4696273803711,
+      "learning_rate": 9.3e-07,
+      "loss": 0.9684356689453125,
+      "mean_token_accuracy": 0.850833335518837,
+      "num_tokens": 57546.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.46252561938017606,
+      "epoch": 0.98,
+      "grad_norm": 55.80523681640625,
+      "learning_rate": 6.3e-07,
+      "loss": 0.6090232372283936,
+      "mean_token_accuracy": 0.8857142865657807,
+      "num_tokens": 58180.0,
+      "step": 980
+    },
+    {
+      "entropy": 1.3375183925963938,
+      "epoch": 0.99,
+      "grad_norm": 170.6082305908203,
+      "learning_rate": 3.2999999999999996e-07,
+      "loss": 2.3160438537597656,
+      "mean_token_accuracy": 0.6857142895460129,
+      "num_tokens": 58793.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.5723713244777173,
+      "epoch": 1.0,
+      "grad_norm": 0.11968730390071869,
+      "learning_rate": 3.0000000000000004e-08,
+      "loss": 0.8962030410766602,
+      "mean_token_accuracy": 0.8595238149166107,
+      "num_tokens": 59332.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.5731571038276888,
+      "eval_loss": 1.1951602697372437,
+      "eval_mean_token_accuracy": 0.8162532506883144,
+      "eval_num_tokens": 59332.0,
+      "eval_runtime": 56.0202,
+      "eval_samples_per_second": 1.785,
+      "eval_steps_per_second": 1.785,
+      "step": 1000
     }
   ],
   "logging_steps": 10,
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
+  "total_flos": 127408864687104.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null