File size: 1,652 Bytes
d4acba9 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0008925914906277894,
"eval_steps": 3,
"global_step": 3,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0002975304968759298,
"grad_norm": 4.187718868255615,
"learning_rate": 2e-05,
"loss": 6.1983,
"step": 1
},
{
"epoch": 0.0002975304968759298,
"eval_loss": 3.89170503616333,
"eval_runtime": 280.5373,
"eval_samples_per_second": 5.047,
"eval_steps_per_second": 2.524,
"step": 1
},
{
"epoch": 0.0005950609937518596,
"grad_norm": 2.15948748588562,
"learning_rate": 4e-05,
"loss": 3.5477,
"step": 2
},
{
"epoch": 0.0008925914906277894,
"grad_norm": 3.185936689376831,
"learning_rate": 6e-05,
"loss": 4.6576,
"step": 3
},
{
"epoch": 0.0008925914906277894,
"eval_loss": 3.8822848796844482,
"eval_runtime": 280.3445,
"eval_samples_per_second": 5.051,
"eval_steps_per_second": 2.525,
"step": 3
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1080837210636288.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|