File size: 1,428 Bytes
35646dc |
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": 0.8888888888888888,
"eval_steps": 500,
"global_step": 7,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.13,
"learning_rate": 0.0,
"loss": 1.2027,
"step": 1
},
{
"epoch": 0.25,
"learning_rate": 2e-05,
"loss": 0.9798,
"step": 2
},
{
"epoch": 0.38,
"learning_rate": 2e-05,
"loss": 1.0002,
"step": 3
},
{
"epoch": 0.51,
"learning_rate": 2e-05,
"loss": 0.9289,
"step": 4
},
{
"epoch": 0.63,
"learning_rate": 2e-05,
"loss": 0.931,
"step": 5
},
{
"epoch": 0.76,
"learning_rate": 2e-05,
"loss": 0.8341,
"step": 6
},
{
"epoch": 0.89,
"learning_rate": 2e-05,
"loss": 0.8494,
"step": 7
},
{
"epoch": 0.89,
"step": 7,
"total_flos": 10589442539520.0,
"train_loss": 0.9608551774706159,
"train_runtime": 694.1399,
"train_samples_per_second": 1.448,
"train_steps_per_second": 0.01
}
],
"logging_steps": 1.0,
"max_steps": 7,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 10589442539520.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|