File size: 2,477 Bytes
71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 5e85ff0 71ede04 |
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 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.721170395869191,
"eval_steps": 5000,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1721170395869191,
"grad_norm": 134.16664123535156,
"learning_rate": 2.224770642201835e-06,
"loss": 10.8697,
"step": 100
},
{
"epoch": 0.3442340791738382,
"grad_norm": 69.6041259765625,
"learning_rate": 4.5183486238532115e-06,
"loss": 9.1125,
"step": 200
},
{
"epoch": 0.5163511187607573,
"grad_norm": 103.4394760131836,
"learning_rate": 6.8119266055045875e-06,
"loss": 6.8873,
"step": 300
},
{
"epoch": 0.6884681583476764,
"grad_norm": 32.237342834472656,
"learning_rate": 9.08256880733945e-06,
"loss": 3.1124,
"step": 400
},
{
"epoch": 0.8605851979345955,
"grad_norm": 13.523033142089844,
"learning_rate": 1.1376146788990828e-05,
"loss": 1.0882,
"step": 500
},
{
"epoch": 1.0327022375215147,
"grad_norm": 56.13002395629883,
"learning_rate": 1.3669724770642203e-05,
"loss": 0.869,
"step": 600
},
{
"epoch": 1.2048192771084336,
"grad_norm": 4.41276741027832,
"learning_rate": 1.5963302752293578e-05,
"loss": 0.6952,
"step": 700
},
{
"epoch": 1.3769363166953528,
"grad_norm": 1.8771318197250366,
"learning_rate": 1.8256880733944955e-05,
"loss": 0.5522,
"step": 800
},
{
"epoch": 1.549053356282272,
"grad_norm": 5.131401062011719,
"learning_rate": 1.9938798928981258e-05,
"loss": 0.5184,
"step": 900
},
{
"epoch": 1.721170395869191,
"grad_norm": 3.2520999908447266,
"learning_rate": 1.9683794466403164e-05,
"loss": 0.3996,
"step": 1000
}
],
"logging_steps": 100,
"max_steps": 8715,
"num_input_tokens_seen": 0,
"num_train_epochs": 15,
"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": 128,
"trial_name": null,
"trial_params": null
}
|