File size: 1,590 Bytes
0a0c86c |
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": 0.15742535889148712,
"learning_rate": 0.0002,
"loss": 1.6387,
"step": 100
},
{
"epoch": 1.4109347442680775,
"grad_norm": 0.11075834929943085,
"learning_rate": 0.0002,
"loss": 1.3739,
"step": 200
},
{
"epoch": 2.1164021164021163,
"grad_norm": 0.14661015570163727,
"learning_rate": 0.0002,
"loss": 1.346,
"step": 300
},
{
"epoch": 2.821869488536155,
"grad_norm": 0.12617041170597076,
"learning_rate": 0.0002,
"loss": 1.3139,
"step": 400
},
{
"epoch": 3.527336860670194,
"grad_norm": 0.1267366111278534,
"learning_rate": 0.0002,
"loss": 1.2941,
"step": 500
},
{
"epoch": 4.232804232804233,
"grad_norm": 0.1768491268157959,
"learning_rate": 0.0002,
"loss": 1.2744,
"step": 600
},
{
"epoch": 4.938271604938271,
"grad_norm": 0.1833101063966751,
"learning_rate": 0.0002,
"loss": 1.3093,
"step": 700
}
],
"logging_steps": 100,
"max_steps": 705,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 100,
"total_flos": 7.333966423944576e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|