File size: 2,074 Bytes
939d6ba |
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_metric": null,
"best_model_checkpoint": null,
"epoch": 4.938271604938271,
"eval_steps": 500,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.6172839506172839,
"grad_norm": 62.88630294799805,
"learning_rate": 9.916000000000001e-06,
"loss": 6.6856,
"step": 50
},
{
"epoch": 1.2345679012345678,
"grad_norm": 387.6339111328125,
"learning_rate": 9.818000000000002e-06,
"loss": 5.5869,
"step": 100
},
{
"epoch": 1.8518518518518519,
"grad_norm": 245.18975830078125,
"learning_rate": 9.718e-06,
"loss": 5.159,
"step": 150
},
{
"epoch": 2.4691358024691357,
"grad_norm": 330.3158264160156,
"learning_rate": 9.618e-06,
"loss": 4.0494,
"step": 200
},
{
"epoch": 3.0864197530864197,
"grad_norm": 138.14215087890625,
"learning_rate": 9.518000000000001e-06,
"loss": 3.6313,
"step": 250
},
{
"epoch": 3.7037037037037037,
"grad_norm": 166.69479370117188,
"learning_rate": 9.418e-06,
"loss": 3.3391,
"step": 300
},
{
"epoch": 4.320987654320987,
"grad_norm": 107.54407501220703,
"learning_rate": 9.318e-06,
"loss": 3.3295,
"step": 350
},
{
"epoch": 4.938271604938271,
"grad_norm": 293.8923034667969,
"learning_rate": 9.218e-06,
"loss": 3.0956,
"step": 400
}
],
"logging_steps": 50,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 62,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.528972664832e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|