Hugging Face's logo

sam2ai
/
DeepSeek-R1-Distill-Qwen-1.5B-Multilingual

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
DeepSeek-R1-Distill-Qwen-1.5B-Multilingual / trainer_log.jsonl
sam2ai's picture
sam2ai
Upload folder using huggingface_hub
c7e469e verified
raw
history blame contribute delete
5.33 kB
{"current_steps": 1, "total_steps": 19, "loss": 0.7163, "lr": 1e-05, "epoch": 0.05263157894736842, "percentage": 5.26, "elapsed_time": "0:00:06", "remaining_time": "0:01:53"}
{"current_steps": 2, "total_steps": 19, "loss": 0.6972, "lr": 9.924038765061042e-06, "epoch": 0.10526315789473684, "percentage": 10.53, "elapsed_time": "0:00:07", "remaining_time": "0:01:05"}
{"current_steps": 2, "total_steps": 19, "eval_loss": 0.5687638521194458, "epoch": 0.10526315789473684, "percentage": 10.53, "elapsed_time": "0:00:08", "remaining_time": "0:01:08"}
{"current_steps": 3, "total_steps": 19, "loss": 0.7795, "lr": 9.698463103929542e-06, "epoch": 0.15789473684210525, "percentage": 15.79, "elapsed_time": "0:00:09", "remaining_time": "0:00:50"}
{"current_steps": 4, "total_steps": 19, "loss": 0.6915, "lr": 9.330127018922195e-06, "epoch": 0.21052631578947367, "percentage": 21.05, "elapsed_time": "0:00:10", "remaining_time": "0:00:41"}
{"current_steps": 4, "total_steps": 19, "eval_loss": 0.5684303045272827, "epoch": 0.21052631578947367, "percentage": 21.05, "elapsed_time": "0:00:11", "remaining_time": "0:00:42"}
{"current_steps": 5, "total_steps": 19, "loss": 0.6744, "lr": 8.83022221559489e-06, "epoch": 0.2631578947368421, "percentage": 26.32, "elapsed_time": "0:00:12", "remaining_time": "0:00:35"}
{"current_steps": 6, "total_steps": 19, "loss": 0.7911, "lr": 8.213938048432697e-06, "epoch": 0.3157894736842105, "percentage": 31.58, "elapsed_time": "0:00:14", "remaining_time": "0:00:30"}
{"current_steps": 6, "total_steps": 19, "eval_loss": 0.5686608552932739, "epoch": 0.3157894736842105, "percentage": 31.58, "elapsed_time": "0:00:14", "remaining_time": "0:00:31"}
{"current_steps": 7, "total_steps": 19, "loss": 0.5594, "lr": 7.500000000000001e-06, "epoch": 0.3684210526315789, "percentage": 36.84, "elapsed_time": "0:00:15", "remaining_time": "0:00:27"}
{"current_steps": 8, "total_steps": 19, "loss": 0.7261, "lr": 6.710100716628345e-06, "epoch": 0.42105263157894735, "percentage": 42.11, "elapsed_time": "0:00:17", "remaining_time": "0:00:23"}
{"current_steps": 8, "total_steps": 19, "eval_loss": 0.5699889063835144, "epoch": 0.42105263157894735, "percentage": 42.11, "elapsed_time": "0:00:17", "remaining_time": "0:00:24"}
{"current_steps": 9, "total_steps": 19, "loss": 0.6122, "lr": 5.8682408883346535e-06, "epoch": 0.47368421052631576, "percentage": 47.37, "elapsed_time": "0:00:19", "remaining_time": "0:00:21"}
{"current_steps": 10, "total_steps": 19, "loss": 0.86, "lr": 5e-06, "epoch": 0.5263157894736842, "percentage": 52.63, "elapsed_time": "0:00:20", "remaining_time": "0:00:18"}
{"current_steps": 10, "total_steps": 19, "eval_loss": 0.568690836429596, "epoch": 0.5263157894736842, "percentage": 52.63, "elapsed_time": "0:00:20", "remaining_time": "0:00:18"}
{"current_steps": 11, "total_steps": 19, "loss": 0.7364, "lr": 4.131759111665349e-06, "epoch": 0.5789473684210527, "percentage": 57.89, "elapsed_time": "0:00:22", "remaining_time": "0:00:16"}
{"current_steps": 12, "total_steps": 19, "loss": 0.6903, "lr": 3.289899283371657e-06, "epoch": 0.631578947368421, "percentage": 63.16, "elapsed_time": "0:00:23", "remaining_time": "0:00:13"}
{"current_steps": 12, "total_steps": 19, "eval_loss": 0.5691469311714172, "epoch": 0.631578947368421, "percentage": 63.16, "elapsed_time": "0:00:24", "remaining_time": "0:00:14"}
{"current_steps": 13, "total_steps": 19, "loss": 0.663, "lr": 2.5000000000000015e-06, "epoch": 0.6842105263157895, "percentage": 68.42, "elapsed_time": "0:00:25", "remaining_time": "0:00:11"}
{"current_steps": 14, "total_steps": 19, "loss": 0.5994, "lr": 1.7860619515673034e-06, "epoch": 0.7368421052631579, "percentage": 73.68, "elapsed_time": "0:00:27", "remaining_time": "0:00:09"}
{"current_steps": 14, "total_steps": 19, "eval_loss": 0.5684089064598083, "epoch": 0.7368421052631579, "percentage": 73.68, "elapsed_time": "0:00:27", "remaining_time": "0:00:09"}
{"current_steps": 15, "total_steps": 19, "loss": 0.7457, "lr": 1.1697777844051105e-06, "epoch": 0.7894736842105263, "percentage": 78.95, "elapsed_time": "0:00:28", "remaining_time": "0:00:07"}
{"current_steps": 16, "total_steps": 19, "loss": 0.7792, "lr": 6.698729810778065e-07, "epoch": 0.8421052631578947, "percentage": 84.21, "elapsed_time": "0:00:30", "remaining_time": "0:00:05"}
{"current_steps": 16, "total_steps": 19, "eval_loss": 0.5695986747741699, "epoch": 0.8421052631578947, "percentage": 84.21, "elapsed_time": "0:00:30", "remaining_time": "0:00:05"}
{"current_steps": 17, "total_steps": 19, "loss": 0.6121, "lr": 3.015368960704584e-07, "epoch": 0.8947368421052632, "percentage": 89.47, "elapsed_time": "0:00:31", "remaining_time": "0:00:03"}
{"current_steps": 18, "total_steps": 19, "loss": 0.7023, "lr": 7.59612349389599e-08, "epoch": 0.9473684210526315, "percentage": 94.74, "elapsed_time": "0:00:33", "remaining_time": "0:00:01"}
{"current_steps": 18, "total_steps": 19, "eval_loss": 0.5688631534576416, "epoch": 0.9473684210526315, "percentage": 94.74, "elapsed_time": "0:00:33", "remaining_time": "0:00:01"}
{"current_steps": 19, "total_steps": 19, "loss": 0.7789, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:35", "remaining_time": "0:00:00"}
{"current_steps": 19, "total_steps": 19, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:51", "remaining_time": "0:00:00"}