File size: 3,124 Bytes
5ead133 |
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 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 1000,
"global_step": 5578,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003586800573888092,
"grad_norm": 5.781733512878418,
"learning_rate": 0.0,
"loss": 4.1091,
"step": 1
},
{
"epoch": 0.3586800573888092,
"grad_norm": 5.474567413330078,
"learning_rate": 1.4332855093256816e-05,
"loss": 3.2109,
"step": 1000
},
{
"epoch": 0.3586800573888092,
"eval_cosine_accuracy": 0.9464717507362366,
"eval_loss": 0.5677164196968079,
"eval_runtime": 34.9651,
"eval_samples_per_second": 271.957,
"eval_steps_per_second": 1.087,
"step": 1000
},
{
"epoch": 0.7173601147776184,
"grad_norm": 6.178121566772461,
"learning_rate": 1.9035549179021205e-05,
"loss": 1.8968,
"step": 2000
},
{
"epoch": 0.7173601147776184,
"eval_cosine_accuracy": 0.9513092637062073,
"eval_loss": 0.5238887667655945,
"eval_runtime": 33.5859,
"eval_samples_per_second": 283.125,
"eval_steps_per_second": 1.131,
"step": 2000
},
{
"epoch": 1.0759856630824374,
"grad_norm": 4.709190368652344,
"learning_rate": 1.7441415590626496e-05,
"loss": 1.4326,
"step": 3000
},
{
"epoch": 1.0759856630824374,
"eval_cosine_accuracy": 0.9547796845436096,
"eval_loss": 0.49907511472702026,
"eval_runtime": 33.4837,
"eval_samples_per_second": 283.989,
"eval_steps_per_second": 1.135,
"step": 3000
},
{
"epoch": 1.4344086021505376,
"grad_norm": 6.273707866668701,
"learning_rate": 1.5847282002231787e-05,
"loss": 1.5752,
"step": 4000
},
{
"epoch": 1.4344086021505376,
"eval_cosine_accuracy": 0.9569880962371826,
"eval_loss": 0.48718422651290894,
"eval_runtime": 33.7017,
"eval_samples_per_second": 282.152,
"eval_steps_per_second": 1.128,
"step": 4000
},
{
"epoch": 1.792831541218638,
"grad_norm": 5.117976188659668,
"learning_rate": 1.4254742547425475e-05,
"loss": 1.4586,
"step": 5000
},
{
"epoch": 1.792831541218638,
"eval_cosine_accuracy": 0.9577242732048035,
"eval_loss": 0.48695915937423706,
"eval_runtime": 33.7015,
"eval_samples_per_second": 282.154,
"eval_steps_per_second": 1.128,
"step": 5000
}
],
"logging_steps": 1000,
"max_steps": 13940,
"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
}
|