File size: 1,677 Bytes
af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c af2c5aa 780a12c 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 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 3300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.45,
"grad_norm": 3.782728910446167,
"learning_rate": 4.242424242424243e-05,
"loss": 0.532,
"step": 500
},
{
"epoch": 0.91,
"grad_norm": 3.925285816192627,
"learning_rate": 3.484848484848485e-05,
"loss": 0.4013,
"step": 1000
},
{
"epoch": 1.36,
"grad_norm": 7.782624244689941,
"learning_rate": 2.7272727272727273e-05,
"loss": 0.281,
"step": 1500
},
{
"epoch": 1.82,
"grad_norm": 3.6547534465789795,
"learning_rate": 1.9696969696969697e-05,
"loss": 0.2454,
"step": 2000
},
{
"epoch": 2.27,
"grad_norm": 0.9583206176757812,
"learning_rate": 1.2121212121212122e-05,
"loss": 0.1696,
"step": 2500
},
{
"epoch": 2.73,
"grad_norm": 11.225361824035645,
"learning_rate": 4.5454545454545455e-06,
"loss": 0.1393,
"step": 3000
},
{
"epoch": 3.0,
"step": 3300,
"total_flos": 2871828253461180.0,
"train_loss": 0.27864328904585406,
"train_runtime": 413.6435,
"train_samples_per_second": 127.632,
"train_steps_per_second": 7.978
}
],
"logging_steps": 500,
"max_steps": 3300,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 2871828253461180.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|