File size: 1,286 Bytes
af2c5aa |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.2727272727272725,
"eval_steps": 500,
"global_step": 2500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.45,
"grad_norm": 4.369685173034668,
"learning_rate": 4.242424242424243e-05,
"loss": 0.4661,
"step": 500
},
{
"epoch": 0.91,
"grad_norm": 3.9891207218170166,
"learning_rate": 3.484848484848485e-05,
"loss": 0.3327,
"step": 1000
},
{
"epoch": 1.36,
"grad_norm": 9.819967269897461,
"learning_rate": 2.7272727272727273e-05,
"loss": 0.2258,
"step": 1500
},
{
"epoch": 1.82,
"grad_norm": 1.7621924877166748,
"learning_rate": 1.9696969696969697e-05,
"loss": 0.1772,
"step": 2000
},
{
"epoch": 2.27,
"grad_norm": 21.205034255981445,
"learning_rate": 1.2121212121212122e-05,
"loss": 0.1106,
"step": 2500
}
],
"logging_steps": 500,
"max_steps": 3300,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 2019349980886680.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|