File size: 1,589 Bytes
e00cb48 |
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 68 69 70 71 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.938271604938271,
"eval_steps": 500,
"global_step": 700,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.7054673721340388,
"grad_norm": 0.2144777774810791,
"learning_rate": 0.0002,
"loss": 1.3606,
"step": 100
},
{
"epoch": 1.4109347442680775,
"grad_norm": 0.18283842504024506,
"learning_rate": 0.0002,
"loss": 1.2686,
"step": 200
},
{
"epoch": 2.1164021164021163,
"grad_norm": 0.22576524317264557,
"learning_rate": 0.0002,
"loss": 1.2149,
"step": 300
},
{
"epoch": 2.821869488536155,
"grad_norm": 0.2537195384502411,
"learning_rate": 0.0002,
"loss": 1.1427,
"step": 400
},
{
"epoch": 3.527336860670194,
"grad_norm": 0.36884188652038574,
"learning_rate": 0.0002,
"loss": 1.0694,
"step": 500
},
{
"epoch": 4.232804232804233,
"grad_norm": 0.6655462384223938,
"learning_rate": 0.0002,
"loss": 0.9957,
"step": 600
},
{
"epoch": 4.938271604938271,
"grad_norm": 0.47897958755493164,
"learning_rate": 0.0002,
"loss": 0.972,
"step": 700
}
],
"logging_steps": 100,
"max_steps": 705,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 100,
"total_flos": 8.23802837336064e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|