File size: 1,356 Bytes
8509db4 66e1cfc 8509db4 66e1cfc 8509db4 66e1cfc 8509db4 66e1cfc 8509db4 66e1cfc 8509db4 66e1cfc 8509db4 66e1cfc 8509db4 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 18,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 1.3159,
"step": 1
},
{
"epoch": 0.28,
"learning_rate": 0.00018314696123025454,
"loss": 1.2515,
"step": 5
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 1.1683,
"step": 10
},
{
"epoch": 0.83,
"learning_rate": 1.6853038769745467e-05,
"loss": 1.11,
"step": 15
},
{
"epoch": 1.0,
"eval_loss": 1.0904877185821533,
"eval_runtime": 15.6992,
"eval_samples_per_second": 7.899,
"eval_steps_per_second": 0.51,
"step": 18
},
{
"epoch": 1.0,
"step": 18,
"total_flos": 1.0560439065981747e+17,
"train_loss": 1.168492575486501,
"train_runtime": 457.8696,
"train_samples_per_second": 2.496,
"train_steps_per_second": 0.039
}
],
"logging_steps": 5,
"max_steps": 18,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 1.0560439065981747e+17,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|