Files
QWEN3-4B-Base-stage2/all_results.json

12 lines
346 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"eval_loss": 1.795795202255249,
"eval_runtime": 2.878,
"eval_samples_per_second": 25.018,
"eval_steps_per_second": 3.127,
"total_flos": 1.6013083311596544e+16,
"train_loss": 1.9567182964748806,
"train_runtime": 294.7814,
"train_samples_per_second": 12.087,
"train_steps_per_second": 0.305
}