File size: 1,930 Bytes
caa1f07 |
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": 6.0,
"eval_steps": 500,
"global_step": 8,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 2.581096649169922,
"learning_rate": 6.25e-06,
"loss": 1.2294,
"step": 1
},
{
"epoch": 2.0,
"grad_norm": 2.5810961723327637,
"learning_rate": 1.25e-05,
"loss": 1.2294,
"step": 2
},
{
"epoch": 2.612244897959184,
"grad_norm": 1.6523983478546143,
"learning_rate": 1.8750000000000002e-05,
"loss": 0.7504,
"step": 3
},
{
"epoch": 3.0,
"grad_norm": 0.9309479594230652,
"learning_rate": 2.5e-05,
"loss": 0.4609,
"step": 4
},
{
"epoch": 4.0,
"grad_norm": 2.275179147720337,
"learning_rate": 3.125e-05,
"loss": 1.16,
"step": 5
},
{
"epoch": 5.0,
"grad_norm": 2.085817575454712,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.1088,
"step": 6
},
{
"epoch": 5.224489795918367,
"grad_norm": 0.6138802766799927,
"learning_rate": 4.375e-05,
"loss": 0.2543,
"step": 7
},
{
"epoch": 6.0,
"grad_norm": 1.3060435056686401,
"learning_rate": 5e-05,
"loss": 0.7491,
"step": 8
}
],
"logging_steps": 1,
"max_steps": 60,
"num_input_tokens_seen": 0,
"num_train_epochs": 60,
"save_steps": 8,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1821593618546688.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|