File size: 1,927 Bytes
2ea34c8 b85b358 2ea34c8 b85b358 2ea34c8 b85b358 2ea34c8 b85b358 2ea34c8 b85b358 2ea34c8 b85b358 2ea34c8 |
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": 0.5361930294906166,
"eval_steps": 200,
"global_step": 600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.17873100983020554,
"grad_norm": 0.8090553879737854,
"learning_rate": 9.999142157322298e-05,
"loss": 0.5369,
"step": 200
},
{
"epoch": 0.17873100983020554,
"eval_loss": 0.18719753623008728,
"eval_runtime": 42.7752,
"eval_samples_per_second": 4.231,
"eval_steps_per_second": 2.127,
"step": 200
},
{
"epoch": 0.3574620196604111,
"grad_norm": 0.3873799443244934,
"learning_rate": 9.95497608932715e-05,
"loss": 0.1345,
"step": 400
},
{
"epoch": 0.3574620196604111,
"eval_loss": 0.12613661587238312,
"eval_runtime": 44.9042,
"eval_samples_per_second": 4.031,
"eval_steps_per_second": 2.027,
"step": 400
},
{
"epoch": 0.5361930294906166,
"grad_norm": 0.22678756713867188,
"learning_rate": 9.844466810070319e-05,
"loss": 0.1057,
"step": 600
},
{
"epoch": 0.5361930294906166,
"eval_loss": 0.11514777690172195,
"eval_runtime": 44.9314,
"eval_samples_per_second": 4.028,
"eval_steps_per_second": 2.025,
"step": 600
}
],
"logging_steps": 200,
"max_steps": 5595,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.12499405330432e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|