File size: 1,447 Bytes
7a8e5c5 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 5,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2,
"grad_norm": 24.891183513642243,
"learning_rate": 1e-05,
"loss": 0.9347,
"step": 1
},
{
"epoch": 1.0,
"grad_norm": 16.280986656758667,
"learning_rate": 0.0,
"loss": 1.0354,
"step": 5
},
{
"epoch": 1.0,
"eval_loss": 0.8034714460372925,
"eval_runtime": 13.3934,
"eval_samples_per_second": 19.637,
"eval_steps_per_second": 0.373,
"step": 5
},
{
"epoch": 1.0,
"step": 5,
"total_flos": 2093796556800.0,
"train_loss": 1.0152987003326417,
"train_runtime": 126.4024,
"train_samples_per_second": 2.081,
"train_steps_per_second": 0.04
}
],
"logging_steps": 5,
"max_steps": 5,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2093796556800.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|