File size: 1,580 Bytes
6a61139 |
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": 4.0,
"eval_steps": 500,
"global_step": 736,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.54,
"grad_norm": 1.9390450716018677,
"learning_rate": 0.00017282608695652174,
"loss": 1.766,
"step": 100
},
{
"epoch": 1.09,
"grad_norm": 1.6820060014724731,
"learning_rate": 0.0001456521739130435,
"loss": 1.4593,
"step": 200
},
{
"epoch": 1.63,
"grad_norm": 1.9340823888778687,
"learning_rate": 0.00011847826086956522,
"loss": 1.3828,
"step": 300
},
{
"epoch": 2.17,
"grad_norm": 2.359797477722168,
"learning_rate": 9.130434782608696e-05,
"loss": 1.348,
"step": 400
},
{
"epoch": 2.72,
"grad_norm": 2.2974631786346436,
"learning_rate": 6.413043478260869e-05,
"loss": 1.288,
"step": 500
},
{
"epoch": 3.26,
"grad_norm": 2.135037422180176,
"learning_rate": 3.695652173913043e-05,
"loss": 1.2496,
"step": 600
},
{
"epoch": 3.8,
"grad_norm": 2.4940547943115234,
"learning_rate": 9.782608695652175e-06,
"loss": 1.2264,
"step": 700
}
],
"logging_steps": 100,
"max_steps": 736,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 1.846229215266048e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|