File size: 1,669 Bytes
32a47bf |
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": 0.035555555555555556,
"eval_steps": 4,
"global_step": 4,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008888888888888889,
"grad_norm": 0.3842334449291229,
"learning_rate": 0.0001,
"loss": 1.6342,
"step": 1
},
{
"epoch": 0.017777777777777778,
"grad_norm": 0.3358556032180786,
"learning_rate": 8.535533905932738e-05,
"loss": 1.4708,
"step": 2
},
{
"epoch": 0.02666666666666667,
"grad_norm": 0.3367025852203369,
"learning_rate": 5e-05,
"loss": 1.4667,
"step": 3
},
{
"epoch": 0.035555555555555556,
"grad_norm": 0.3284144699573517,
"learning_rate": 1.4644660940672627e-05,
"loss": 1.5967,
"step": 4
},
{
"epoch": 0.035555555555555556,
"eval_accuracy": 0.5943584982531214,
"eval_loss": 1.5761107206344604,
"eval_runtime": 22.9023,
"eval_samples_per_second": 4.366,
"eval_steps_per_second": 4.366,
"step": 4
}
],
"logging_steps": 1.0,
"max_steps": 5,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 4,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 270007380246528.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|