Model: Neelectric/Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.13 Source: Original Platform
9 lines
260 B
JSON
9 lines
260 B
JSON
{
|
|
"ewc_loss": 1.055002212524414e-05,
|
|
"total_flos": 3.1829322264618205e+19,
|
|
"train_loss": 1.0248253059881185,
|
|
"train_runtime": 37191.1487,
|
|
"train_samples": 145693,
|
|
"train_samples_per_second": 11.752,
|
|
"train_steps_per_second": 0.735
|
|
} |