quip-4k-qwen / all_results.json
Anis1123's picture
Initial model upload
ae07701 verified
raw
history blame contribute delete
257 Bytes
{
"epoch": 5.971724787935909,
"num_input_tokens_seen": 8259920,
"total_flos": 3.514168539537736e+17,
"train_loss": 2.724412232336372,
"train_runtime": 4977.287,
"train_samples_per_second": 5.116,
"train_steps_per_second": 0.159
}