File size: 1,919 Bytes
024263d |
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_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.24160147261849976,
"eval_steps": 500,
"global_step": 1050,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05752416014726185,
"grad_norm": 0.5827537775039673,
"learning_rate": 0.00016513000460193283,
"loss": 5.0544,
"step": 250
},
{
"epoch": 0.1150483202945237,
"grad_norm": 0.5847251415252686,
"learning_rate": 0.00016024045098941557,
"loss": 4.2362,
"step": 500
},
{
"epoch": 0.1150483202945237,
"eval_loss": 3.4322922229766846,
"eval_runtime": 35.9031,
"eval_samples_per_second": 109.74,
"eval_steps_per_second": 3.231,
"step": 500
},
{
"epoch": 0.17257248044178555,
"grad_norm": 0.6557937264442444,
"learning_rate": 0.0001553508973768983,
"loss": 4.0566,
"step": 750
},
{
"epoch": 0.2300966405890474,
"grad_norm": 0.6734243631362915,
"learning_rate": 0.00015046134376438104,
"loss": 3.9349,
"step": 1000
},
{
"epoch": 0.2300966405890474,
"eval_loss": 3.1976470947265625,
"eval_runtime": 35.3562,
"eval_samples_per_second": 111.437,
"eval_steps_per_second": 3.281,
"step": 1000
}
],
"logging_steps": 250,
"max_steps": 8692,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 350,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 805601909145600.0,
"train_batch_size": 34,
"trial_name": null,
"trial_params": null
}
|