File size: 1,888 Bytes
f0d6920 |
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 74 75 76 77 78 79 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.0,
"eval_steps": 10,
"global_step": 34,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.3529411764705883,
"grad_norm": 0.36976027488708496,
"learning_rate": 9.722222222222223e-05,
"loss": 1.5945,
"step": 10
},
{
"epoch": 2.3529411764705883,
"eval_loss": 1.4627282619476318,
"eval_runtime": 8.4531,
"eval_samples_per_second": 1.893,
"eval_steps_per_second": 0.237,
"step": 10
},
{
"epoch": 4.705882352941177,
"grad_norm": 0.4368647336959839,
"learning_rate": 8.333333333333334e-05,
"loss": 1.3292,
"step": 20
},
{
"epoch": 4.705882352941177,
"eval_loss": 1.15525221824646,
"eval_runtime": 8.4549,
"eval_samples_per_second": 1.892,
"eval_steps_per_second": 0.237,
"step": 20
},
{
"epoch": 7.0588235294117645,
"grad_norm": 0.534726619720459,
"learning_rate": 6.944444444444444e-05,
"loss": 0.9997,
"step": 30
},
{
"epoch": 7.0588235294117645,
"eval_loss": 0.7809390425682068,
"eval_runtime": 8.4531,
"eval_samples_per_second": 1.893,
"eval_steps_per_second": 0.237,
"step": 30
}
],
"logging_steps": 10,
"max_steps": 80,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8611954795438080.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|