File size: 1,431 Bytes
e9c143a |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 345,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.43,
"learning_rate": 1.710144927536232e-05,
"loss": 0.6709,
"step": 50
},
{
"epoch": 0.87,
"learning_rate": 1.420289855072464e-05,
"loss": 0.6336,
"step": 100
},
{
"epoch": 1.3,
"learning_rate": 1.1304347826086957e-05,
"loss": 0.6521,
"step": 150
},
{
"epoch": 1.74,
"learning_rate": 8.405797101449275e-06,
"loss": 0.6488,
"step": 200
},
{
"epoch": 2.17,
"learning_rate": 5.507246376811595e-06,
"loss": 0.6343,
"step": 250
},
{
"epoch": 2.61,
"learning_rate": 2.6086956521739132e-06,
"loss": 0.639,
"step": 300
},
{
"epoch": 3.0,
"step": 345,
"total_flos": 2129448603776928.0,
"train_loss": 0.6446961886640908,
"train_runtime": 166.583,
"train_samples_per_second": 66.057,
"train_steps_per_second": 2.071
}
],
"logging_steps": 50,
"max_steps": 345,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 2129448603776928.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|