File size: 2,236 Bytes
2d60ecc |
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 89 90 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 1000,
"global_step": 3933,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000508646998982706,
"grad_norm": 4.802672863006592,
"learning_rate": 0.0,
"loss": 3.5148,
"step": 1
},
{
"epoch": 0.508646998982706,
"grad_norm": 4.325772285461426,
"learning_rate": 2.994574432010851e-05,
"loss": 2.3332,
"step": 1000
},
{
"epoch": 0.508646998982706,
"eval_cosine_accuracy": 0.9514144659042358,
"eval_loss": 0.4182649254798889,
"eval_runtime": 40.3586,
"eval_samples_per_second": 235.613,
"eval_steps_per_second": 0.942,
"step": 1000
},
{
"epoch": 1.0172852058973056,
"grad_norm": 4.248680114746094,
"learning_rate": 2.6554764326890472e-05,
"loss": 1.1848,
"step": 2000
},
{
"epoch": 1.0172852058973056,
"eval_cosine_accuracy": 0.9598275423049927,
"eval_loss": 0.36312881112098694,
"eval_runtime": 39.402,
"eval_samples_per_second": 241.333,
"eval_steps_per_second": 0.964,
"step": 2000
},
{
"epoch": 1.5256736146415861,
"grad_norm": 3.5537898540496826,
"learning_rate": 2.316378433367243e-05,
"loss": 1.2233,
"step": 3000
},
{
"epoch": 1.5256736146415861,
"eval_cosine_accuracy": 0.964454710483551,
"eval_loss": 0.35020381212234497,
"eval_runtime": 39.2709,
"eval_samples_per_second": 242.139,
"eval_steps_per_second": 0.968,
"step": 3000
}
],
"logging_steps": 1000,
"max_steps": 9830,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 0.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|