transcript-correction-loras / meta-llama__llama-3.2-3b

2.19 GB

Ctrl+K

Upload full trainer checkpoint step=29325 (profile=llama3_2_3b_base, run_type=sft)

87249d8 verified 12 days ago

epoch_0001
Upload epoch checkpoint epoch_0001 (profile=llama3_2_3b_base, step=1428) 17 days ago
epoch_0002
Upload epoch checkpoint epoch_0002 (profile=llama3_2_3b_base, step=2856) 17 days ago
epoch_0003
Upload epoch checkpoint epoch_0003 (profile=llama3_2_3b_base, step=4284) 17 days ago
epoch_0004
Upload epoch checkpoint epoch_0004 (profile=llama3_2_3b_base, step=2300) 19 days ago
sft
Upload full trainer checkpoint step=29325 (profile=llama3_2_3b_base, run_type=sft) 12 days ago
README.md

5.22 kB
Refresh base adapter to best eval_loss (profile=llama3_2_3b_base, step=288, eval_loss=0.060103) 19 days ago
adapter_config.json

1.19 kB
Refresh base adapter to best eval_loss (profile=llama3_2_3b_base, step=1428, eval_loss=0.038845) 17 days ago
adapter_model.safetensors

97.3 MB
xet

Refresh base adapter to best eval_loss (profile=llama3_2_3b_base, step=2856, eval_loss=0.037086) 17 days ago
best_eval_metrics.json

81 Bytes
Refresh base adapter to best eval_loss (profile=llama3_2_3b_base, step=2856, eval_loss=0.037086) 17 days ago
chat_template.jinja

587 Bytes
Refresh base adapter to best eval_loss (profile=llama3_2_3b_base, step=288, eval_loss=0.060103) 19 days ago
tokenizer.json

17.2 MB
xet

Refresh base adapter to best eval_loss (profile=llama3_2_3b_base, step=288, eval_loss=0.060103) 19 days ago
tokenizer_config.json

433 Bytes
Refresh base adapter to best eval_loss (profile=llama3_2_3b_base, step=288, eval_loss=0.060103) 19 days ago