File size: 3,995 Bytes
d575606 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 1000,
"global_step": 7866,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000254323499491353,
"grad_norm": 6.461288928985596,
"learning_rate": 0.0,
"loss": 3.7722,
"step": 1
},
{
"epoch": 0.254323499491353,
"grad_norm": 5.289657115936279,
"learning_rate": 1.5244150559511698e-05,
"loss": 2.8712,
"step": 1000
},
{
"epoch": 0.254323499491353,
"eval_cosine_accuracy": 0.9444736838340759,
"eval_loss": 0.5577611327171326,
"eval_runtime": 35.3135,
"eval_samples_per_second": 269.274,
"eval_steps_per_second": 1.076,
"step": 1000
},
{
"epoch": 0.508646998982706,
"grad_norm": 6.285799026489258,
"learning_rate": 2.9944048830111903e-05,
"loss": 1.8052,
"step": 2000
},
{
"epoch": 0.508646998982706,
"eval_cosine_accuracy": 0.9498369693756104,
"eval_loss": 0.5062179565429688,
"eval_runtime": 34.9468,
"eval_samples_per_second": 272.099,
"eval_steps_per_second": 1.087,
"step": 2000
},
{
"epoch": 0.762970498474059,
"grad_norm": 6.981422424316406,
"learning_rate": 2.8250254323499494e-05,
"loss": 1.2908,
"step": 3000
},
{
"epoch": 0.762970498474059,
"eval_cosine_accuracy": 0.9575139284133911,
"eval_loss": 0.4583439528942108,
"eval_runtime": 34.7917,
"eval_samples_per_second": 273.312,
"eval_steps_per_second": 1.092,
"step": 3000
},
{
"epoch": 1.0172852058973056,
"grad_norm": 6.195133209228516,
"learning_rate": 2.6554764326890472e-05,
"loss": 1.0201,
"step": 4000
},
{
"epoch": 1.0172852058973056,
"eval_cosine_accuracy": 0.9621411561965942,
"eval_loss": 0.4364590048789978,
"eval_runtime": 35.4237,
"eval_samples_per_second": 268.436,
"eval_steps_per_second": 1.073,
"step": 4000
},
{
"epoch": 1.2714794102694458,
"grad_norm": 6.555699825286865,
"learning_rate": 2.4859274330281453e-05,
"loss": 1.2224,
"step": 5000
},
{
"epoch": 1.2714794102694458,
"eval_cosine_accuracy": 0.962666928768158,
"eval_loss": 0.4258391261100769,
"eval_runtime": 36.1657,
"eval_samples_per_second": 262.928,
"eval_steps_per_second": 1.051,
"step": 5000
},
{
"epoch": 1.5256736146415861,
"grad_norm": 4.430365562438965,
"learning_rate": 2.316378433367243e-05,
"loss": 1.1341,
"step": 6000
},
{
"epoch": 1.5256736146415861,
"eval_cosine_accuracy": 0.964454710483551,
"eval_loss": 0.4155160188674927,
"eval_runtime": 35.2226,
"eval_samples_per_second": 269.969,
"eval_steps_per_second": 1.079,
"step": 6000
},
{
"epoch": 1.7798678190137265,
"grad_norm": 5.276082515716553,
"learning_rate": 2.146998982706002e-05,
"loss": 1.0798,
"step": 7000
},
{
"epoch": 1.7798678190137265,
"eval_cosine_accuracy": 0.9657166600227356,
"eval_loss": 0.42145127058029175,
"eval_runtime": 35.2976,
"eval_samples_per_second": 269.395,
"eval_steps_per_second": 1.077,
"step": 7000
}
],
"logging_steps": 1000,
"max_steps": 19660,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 256,
"trial_name": null,
"trial_params": null
}
|