File size: 2,003 Bytes
0f32970 75e6317 1a4c389 75e6317 0f32970 1a4c389 0f32970 1a4c389 9990db2 2e8f4e6 0f32970 1a4c389 0f32970 1a4c389 0f32970 75e6317 0f32970 75e6317 0f32970 |
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 80 81 82 83 84 85 86 87 88 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.04,
"eval_steps": 3,
"global_step": 13,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"eval_loss": 5.956454753875732,
"eval_runtime": 0.3943,
"eval_samples_per_second": 15.218,
"eval_steps_per_second": 7.609,
"step": 1
},
{
"epoch": 0.24,
"eval_loss": 5.943696975708008,
"eval_runtime": 0.3931,
"eval_samples_per_second": 15.261,
"eval_steps_per_second": 7.631,
"step": 3
},
{
"epoch": 0.4,
"grad_norm": 10.887984275817871,
"learning_rate": 5e-05,
"loss": 6.0911,
"step": 5
},
{
"epoch": 0.48,
"eval_loss": 5.283447742462158,
"eval_runtime": 0.4178,
"eval_samples_per_second": 14.361,
"eval_steps_per_second": 7.18,
"step": 6
},
{
"epoch": 0.72,
"eval_loss": 3.5568253993988037,
"eval_runtime": 0.3981,
"eval_samples_per_second": 15.072,
"eval_steps_per_second": 7.536,
"step": 9
},
{
"epoch": 0.8,
"grad_norm": 5.7051615715026855,
"learning_rate": 0.0001,
"loss": 4.2865,
"step": 10
},
{
"epoch": 0.96,
"eval_loss": 2.183289051055908,
"eval_runtime": 0.4018,
"eval_samples_per_second": 14.934,
"eval_steps_per_second": 7.467,
"step": 12
}
],
"logging_steps": 5,
"max_steps": 13,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 4,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2404433522589696.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|