File size: 1,659 Bytes
2fa2e36 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.3276897870016384,
"eval_steps": 500,
"global_step": 1500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.10922992900054615,
"grad_norm": 0.9561710357666016,
"learning_rate": 1.4564520827264783e-05,
"loss": 0.7634,
"step": 500
},
{
"epoch": 0.10922992900054615,
"eval_loss": 0.3866455852985382,
"eval_runtime": 53.8542,
"eval_samples_per_second": 1.727,
"eval_steps_per_second": 1.727,
"step": 500
},
{
"epoch": 0.2184598580010923,
"grad_norm": 0.6381384134292603,
"learning_rate": 2.9129041654529566e-05,
"loss": 0.2265,
"step": 1000
},
{
"epoch": 0.2184598580010923,
"eval_loss": 0.28045815229415894,
"eval_runtime": 53.8781,
"eval_samples_per_second": 1.726,
"eval_steps_per_second": 1.726,
"step": 1000
},
{
"epoch": 0.3276897870016384,
"grad_norm": 0.80877685546875,
"learning_rate": 4.3693562481794354e-05,
"loss": 0.13,
"step": 1500
},
{
"epoch": 0.3276897870016384,
"eval_loss": 0.24824748933315277,
"eval_runtime": 53.7906,
"eval_samples_per_second": 1.729,
"eval_steps_per_second": 1.729,
"step": 1500
}
],
"logging_steps": 500,
"max_steps": 228850,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 3.125496486039245e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|