File size: 1,816 Bytes
cdb8442 |
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 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 346,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1447178002894356,
"grad_norm": 0.5892243385314941,
"learning_rate": 0.00019977600780563863,
"loss": 1.3906,
"step": 50
},
{
"epoch": 0.2894356005788712,
"grad_norm": 0.36873894929885864,
"learning_rate": 0.00019535370438781766,
"loss": 0.1788,
"step": 100
},
{
"epoch": 0.4341534008683068,
"grad_norm": 0.19239167869091034,
"learning_rate": 0.00018550668718999872,
"loss": 0.1467,
"step": 150
},
{
"epoch": 0.5788712011577424,
"grad_norm": 0.2375071942806244,
"learning_rate": 0.00017079515731006085,
"loss": 0.153,
"step": 200
},
{
"epoch": 0.723589001447178,
"grad_norm": 0.3418053090572357,
"learning_rate": 0.0001520560600914168,
"loss": 0.203,
"step": 250
},
{
"epoch": 0.8683068017366136,
"grad_norm": 0.39986488223075867,
"learning_rate": 0.00013035547093784186,
"loss": 0.1199,
"step": 300
}
],
"logging_steps": 50,
"max_steps": 692,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 1.5509080308252672e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|