File size: 3,225 Bytes
e0071be ad2340a e0071be ad2340a e0071be f90ee9d e0071be f90ee9d e0071be f90ee9d e0071be f90ee9d e0071be f90ee9d e0071be ab4d8c9 f90ee9d ab4d8c9 f90ee9d ab4d8c9 f90ee9d ab4d8c9 f90ee9d ab4d8c9 04761e9 f90ee9d 04761e9 f90ee9d 04761e9 f90ee9d 04761e9 f90ee9d 04761e9 f90ee9d 04761e9 f90ee9d 04761e9 ad2340a e0071be ad2340a e0071be ad2340a e0071be |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.000708842814105972,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 7.08842814105972e-05,
"grad_norm": 0.05009423941373825,
"learning_rate": 2e-05,
"loss": 10.3888,
"step": 1
},
{
"epoch": 7.08842814105972e-05,
"eval_loss": 10.386297225952148,
"eval_runtime": 27.7495,
"eval_samples_per_second": 107.029,
"eval_steps_per_second": 107.029,
"step": 1
},
{
"epoch": 0.0001417685628211944,
"grad_norm": 0.07014117389917374,
"learning_rate": 4e-05,
"loss": 10.3973,
"step": 2
},
{
"epoch": 0.0002126528442317916,
"grad_norm": 0.08233338594436646,
"learning_rate": 6e-05,
"loss": 10.3902,
"step": 3
},
{
"epoch": 0.0002126528442317916,
"eval_loss": 10.386211395263672,
"eval_runtime": 36.0589,
"eval_samples_per_second": 82.365,
"eval_steps_per_second": 82.365,
"step": 3
},
{
"epoch": 0.0002835371256423888,
"grad_norm": 0.06442844867706299,
"learning_rate": 8e-05,
"loss": 10.3829,
"step": 4
},
{
"epoch": 0.000354421407052986,
"grad_norm": 0.0734759271144867,
"learning_rate": 0.0001,
"loss": 10.3837,
"step": 5
},
{
"epoch": 0.0004253056884635832,
"grad_norm": 0.08815142512321472,
"learning_rate": 0.00012,
"loss": 10.3935,
"step": 6
},
{
"epoch": 0.0004253056884635832,
"eval_loss": 10.385868072509766,
"eval_runtime": 27.2276,
"eval_samples_per_second": 109.081,
"eval_steps_per_second": 109.081,
"step": 6
},
{
"epoch": 0.0004961899698741804,
"grad_norm": 0.06906867027282715,
"learning_rate": 0.00014,
"loss": 10.392,
"step": 7
},
{
"epoch": 0.0005670742512847776,
"grad_norm": 0.09693009406328201,
"learning_rate": 0.00016,
"loss": 10.3971,
"step": 8
},
{
"epoch": 0.0006379585326953748,
"grad_norm": 0.07968022674322128,
"learning_rate": 0.00018,
"loss": 10.3808,
"step": 9
},
{
"epoch": 0.0006379585326953748,
"eval_loss": 10.38524055480957,
"eval_runtime": 23.5688,
"eval_samples_per_second": 126.014,
"eval_steps_per_second": 126.014,
"step": 9
},
{
"epoch": 0.000708842814105972,
"grad_norm": 0.07413484156131744,
"learning_rate": 0.0002,
"loss": 10.3821,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"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": true
},
"attributes": {}
}
},
"total_flos": 139007262720.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|