File size: 1,886 Bytes
ce9fa40 |
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 |
{
"best_metric": 0.15345074236392975,
"best_model_checkpoint": "checkpoints/checkpoint-36",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 36,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"embedding_loss": 0.4647,
"epoch": 0.1111111111111111,
"grad_norm": 3.230494976043701,
"learning_rate": 5e-06,
"step": 1
},
{
"epoch": 1.0,
"eval_embedding_loss": 0.17025126516819,
"eval_embedding_runtime": 0.1505,
"eval_embedding_samples_per_second": 398.721,
"eval_embedding_steps_per_second": 26.581,
"step": 9
},
{
"epoch": 2.0,
"eval_embedding_loss": 0.16353432834148407,
"eval_embedding_runtime": 0.1844,
"eval_embedding_samples_per_second": 325.435,
"eval_embedding_steps_per_second": 21.696,
"step": 18
},
{
"epoch": 3.0,
"eval_embedding_loss": 0.15655823051929474,
"eval_embedding_runtime": 0.1458,
"eval_embedding_samples_per_second": 411.565,
"eval_embedding_steps_per_second": 27.438,
"step": 27
},
{
"epoch": 4.0,
"eval_embedding_loss": 0.15345074236392975,
"eval_embedding_runtime": 0.1356,
"eval_embedding_samples_per_second": 442.32,
"eval_embedding_steps_per_second": 29.488,
"step": 36
}
],
"logging_steps": 50,
"max_steps": 36,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|