File size: 1,401 Bytes
03c2b9c 04bf5bd 03c2b9c 04bf5bd 03c2b9c 04bf5bd 03c2b9c 04bf5bd 03c2b9c 04bf5bd 03c2b9c 04bf5bd 03c2b9c 04bf5bd 03c2b9c 04bf5bd 03c2b9c |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 3750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.4,
"learning_rate": 4.3333333333333334e-05,
"loss": 0.4395,
"step": 500
},
{
"epoch": 0.8,
"learning_rate": 3.6666666666666666e-05,
"loss": 0.4735,
"step": 1000
},
{
"epoch": 1.2,
"learning_rate": 3e-05,
"loss": 0.3482,
"step": 1500
},
{
"epoch": 1.6,
"learning_rate": 2.3333333333333336e-05,
"loss": 0.2636,
"step": 2000
},
{
"epoch": 2.0,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.2316,
"step": 2500
},
{
"epoch": 2.4,
"learning_rate": 1e-05,
"loss": 0.1222,
"step": 3000
},
{
"epoch": 2.8,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.1307,
"step": 3500
},
{
"epoch": 3.0,
"step": 3750,
"total_flos": 2.40331104e+16,
"train_loss": 0.27894207763671874,
"train_runtime": 4884.0553,
"train_samples_per_second": 36.855,
"train_steps_per_second": 0.768
}
],
"max_steps": 3750,
"num_train_epochs": 3,
"total_flos": 2.40331104e+16,
"trial_name": null,
"trial_params": null
}
|