TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
smollm-350M-instruct-test2-noOH / train_results.json
loubnabnl's picture
loubnabnl HF staff
Model save
2b29917 verified
raw
history blame contribute delete
247 Bytes
{
"epoch": 1.9993181043300376,
"total_flos": 143858545459200.0,
"train_loss": 0.8359313647060732,
"train_runtime": 3324.125,
"train_samples": 286314,
"train_samples_per_second": 56.452,
"train_steps_per_second": 0.441
}