File size: 2,661 Bytes
2efc4ed 4cea407 2efc4ed 4cea407 2efc4ed eefc788 4cea407 eefc788 2efc4ed eefc788 4cea407 eefc788 2efc4ed eefc788 4cea407 eefc788 2efc4ed eefc788 4cea407 eefc788 2efc4ed eefc788 4cea407 eefc788 2efc4ed eefc788 2efc4ed eefc788 2efc4ed eefc788 2efc4ed eefc788 2efc4ed eefc788 2efc4ed 4cea407 eefc788 2efc4ed 4cea407 2efc4ed 4cea407 2efc4ed 4cea407 2efc4ed |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.6666666666666665,
"eval_steps": 500,
"global_step": 21,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.26666666666666666,
"grad_norm": 7.614686012268066,
"learning_rate": 9.047619047619048e-05,
"loss": 9.6721,
"step": 2
},
{
"epoch": 0.5333333333333333,
"grad_norm": 10.107391357421875,
"learning_rate": 8.095238095238096e-05,
"loss": 9.4969,
"step": 4
},
{
"epoch": 0.8,
"grad_norm": 11.758378028869629,
"learning_rate": 7.142857142857143e-05,
"loss": 9.3036,
"step": 6
},
{
"epoch": 1.0,
"grad_norm": 8.324995994567871,
"learning_rate": 6.19047619047619e-05,
"loss": 6.8191,
"step": 8
},
{
"epoch": 1.2666666666666666,
"grad_norm": 15.543440818786621,
"learning_rate": 5.2380952380952384e-05,
"loss": 8.8411,
"step": 10
},
{
"epoch": 1.5333333333333332,
"grad_norm": 16.783220291137695,
"learning_rate": 4.2857142857142856e-05,
"loss": 8.5329,
"step": 12
},
{
"epoch": 1.8,
"grad_norm": 19.108684539794922,
"learning_rate": 3.3333333333333335e-05,
"loss": 8.2567,
"step": 14
},
{
"epoch": 2.0,
"grad_norm": 8.789897918701172,
"learning_rate": 2.380952380952381e-05,
"loss": 6.1492,
"step": 16
},
{
"epoch": 2.2666666666666666,
"grad_norm": 17.98725128173828,
"learning_rate": 1.4285714285714285e-05,
"loss": 8.0423,
"step": 18
},
{
"epoch": 2.533333333333333,
"grad_norm": 14.338889122009277,
"learning_rate": 4.7619047619047615e-06,
"loss": 7.9496,
"step": 20
},
{
"epoch": 2.6666666666666665,
"step": 21,
"total_flos": 82187025809664.0,
"train_loss": 8.28742908296131,
"train_runtime": 577.7205,
"train_samples_per_second": 0.623,
"train_steps_per_second": 0.036
}
],
"logging_steps": 2,
"max_steps": 21,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 82187025809664.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|