File size: 2,928 Bytes
45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 08c18bd 45619b4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.005580530150364285,
"eval_steps": 3,
"global_step": 9,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006200589055960316,
"grad_norm": 0.16878783702850342,
"learning_rate": 4.000000000000001e-06,
"loss": 0.9729,
"step": 1
},
{
"epoch": 0.0012401178111920632,
"grad_norm": 0.0865061804652214,
"learning_rate": 8.000000000000001e-06,
"loss": 0.6661,
"step": 2
},
{
"epoch": 0.0018601767167880949,
"grad_norm": 0.0920981764793396,
"learning_rate": 1.2e-05,
"loss": 0.5954,
"step": 3
},
{
"epoch": 0.0018601767167880949,
"eval_loss": 0.762992262840271,
"eval_runtime": 33.3972,
"eval_samples_per_second": 2.994,
"eval_steps_per_second": 2.994,
"step": 3
},
{
"epoch": 0.0024802356223841263,
"grad_norm": 0.10451442003250122,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.7227,
"step": 4
},
{
"epoch": 0.0031002945279801583,
"grad_norm": 0.11351602524518967,
"learning_rate": 2e-05,
"loss": 0.5719,
"step": 5
},
{
"epoch": 0.0037203534335761897,
"grad_norm": 0.12484906613826752,
"learning_rate": 1.9200000000000003e-05,
"loss": 0.6972,
"step": 6
},
{
"epoch": 0.0037203534335761897,
"eval_loss": 0.7615777850151062,
"eval_runtime": 33.3804,
"eval_samples_per_second": 2.996,
"eval_steps_per_second": 2.996,
"step": 6
},
{
"epoch": 0.004340412339172222,
"grad_norm": 0.11116621643304825,
"learning_rate": 1.8400000000000003e-05,
"loss": 0.6789,
"step": 7
},
{
"epoch": 0.004960471244768253,
"grad_norm": 0.16013608872890472,
"learning_rate": 1.76e-05,
"loss": 0.6612,
"step": 8
},
{
"epoch": 0.005580530150364285,
"grad_norm": 0.1211152970790863,
"learning_rate": 1.6800000000000002e-05,
"loss": 0.5557,
"step": 9
},
{
"epoch": 0.005580530150364285,
"eval_loss": 0.7586225867271423,
"eval_runtime": 33.7015,
"eval_samples_per_second": 2.967,
"eval_steps_per_second": 2.967,
"step": 9
}
],
"logging_steps": 1,
"max_steps": 30,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.2923982083801088e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|