transcript-correction-loras / meta-llama__meta-llama-3.1-8b

2.07 GB

Ctrl+K

Delete meta-llama__meta-llama-3.1-8b/sft/checkpoints

3d7271d verified 11 days ago

epoch_0001
Upload epoch checkpoint epoch_0001 (profile=llama3_1_8b_base, step=574) 18 days ago
epoch_0002
Upload epoch checkpoint epoch_0002 (profile=llama3_1_8b_base, step=1150) 20 days ago
epoch_0003
Upload epoch checkpoint epoch_0003 (profile=llama3_1_8b_base, step=1725) 20 days ago
grpo
Upload full trainer checkpoint step=660 (profile=llama3_1_8b_base_lessdata_grpo, run_type=grpo) 12 days ago
sft
Delete meta-llama__meta-llama-3.1-8b/sft/checkpoints 11 days ago
README.md

5.23 kB
Refresh base adapter to best eval_loss (profile=llama3_1_8b_base, step=288, eval_loss=0.048465) 20 days ago
adapter_config.json

1.19 kB
Refresh base adapter to best eval_loss (profile=llama3_1_8b_base, step=432, eval_loss=0.040582) 18 days ago
adapter_model.safetensors

83.9 MB
xet

Refresh base adapter to best eval_loss (profile=llama3_1_8b_base, step=432, eval_loss=0.040582) 18 days ago
best_eval_metrics.json

95 Bytes
Refresh base adapter to best eval_loss (profile=llama3_1_8b_base, step=432, eval_loss=0.040582) 18 days ago
chat_template.jinja

587 Bytes
Refresh base adapter to best eval_loss (profile=llama3_1_8b_base, step=288, eval_loss=0.048465) 20 days ago
tokenizer.json

17.2 MB
xet

Refresh base adapter to best eval_loss (profile=llama3_1_8b_base, step=288, eval_loss=0.048465) 20 days ago
tokenizer_config.json

433 Bytes
Refresh base adapter to best eval_loss (profile=llama3_1_8b_base, step=288, eval_loss=0.048465) 20 days ago