File size: 2,241 Bytes
78f1a9b |
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": 1.0,
"eval_steps": 1000,
"global_step": 3090,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00032362459546925567,
"grad_norm": 6.455742835998535,
"learning_rate": 0.0,
"loss": 3.5189,
"step": 1
},
{
"epoch": 0.32362459546925565,
"grad_norm": 4.869843482971191,
"learning_rate": 2.020631067961165e-05,
"loss": 2.5841,
"step": 1000
},
{
"epoch": 0.32362459546925565,
"eval_cosine_accuracy": 0.9525712728500366,
"eval_loss": 0.5323272943496704,
"eval_runtime": 35.0009,
"eval_samples_per_second": 271.679,
"eval_steps_per_second": 1.086,
"step": 1000
},
{
"epoch": 0.6472491909385113,
"grad_norm": 6.113117694854736,
"learning_rate": 4.04126213592233e-05,
"loss": 1.5199,
"step": 2000
},
{
"epoch": 0.6472491909385113,
"eval_cosine_accuracy": 0.9623514413833618,
"eval_loss": 0.47361451387405396,
"eval_runtime": 34.0145,
"eval_samples_per_second": 279.557,
"eval_steps_per_second": 1.117,
"step": 2000
},
{
"epoch": 0.970873786407767,
"grad_norm": 6.593084812164307,
"learning_rate": 4.7340210355987055e-05,
"loss": 1.0615,
"step": 3000
},
{
"epoch": 0.970873786407767,
"eval_cosine_accuracy": 0.9607740044593811,
"eval_loss": 0.45996761322021484,
"eval_runtime": 33.7873,
"eval_samples_per_second": 281.437,
"eval_steps_per_second": 1.125,
"step": 3000
}
],
"logging_steps": 1000,
"max_steps": 12360,
"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": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|