File size: 4,002 Bytes
ecb4cb6 |
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": 7064,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0002832058906825262,
"grad_norm": 5.138741493225098,
"learning_rate": 0.0,
"loss": 2.7345,
"step": 1
},
{
"epoch": 0.2832058906825262,
"grad_norm": 3.8642654418945312,
"learning_rate": 1.0608849557522124e-05,
"loss": 2.3628,
"step": 1000
},
{
"epoch": 0.2832058906825262,
"eval_cosine_accuracy": 0.9549968242645264,
"eval_loss": 1.1044740676879883,
"eval_runtime": 24.643,
"eval_samples_per_second": 384.125,
"eval_steps_per_second": 1.501,
"step": 1000
},
{
"epoch": 0.5664117813650524,
"grad_norm": 3.815659999847412,
"learning_rate": 2.1228318584070797e-05,
"loss": 1.8255,
"step": 2000
},
{
"epoch": 0.5664117813650524,
"eval_cosine_accuracy": 0.965983510017395,
"eval_loss": 1.0202418565750122,
"eval_runtime": 23.6988,
"eval_samples_per_second": 399.43,
"eval_steps_per_second": 1.561,
"step": 2000
},
{
"epoch": 0.8496176720475785,
"grad_norm": 3.5664591789245605,
"learning_rate": 2.953801221347022e-05,
"loss": 1.6176,
"step": 3000
},
{
"epoch": 0.8496176720475785,
"eval_cosine_accuracy": 0.9692584276199341,
"eval_loss": 0.9256343841552734,
"eval_runtime": 27.6579,
"eval_samples_per_second": 342.253,
"eval_steps_per_second": 1.338,
"step": 3000
},
{
"epoch": 1.1327483724879706,
"grad_norm": 3.3883819580078125,
"learning_rate": 2.6882909992034692e-05,
"loss": 1.9619,
"step": 4000
},
{
"epoch": 1.1327483724879706,
"eval_cosine_accuracy": 0.9713712334632874,
"eval_loss": 0.8905332088470459,
"eval_runtime": 24.0669,
"eval_samples_per_second": 393.32,
"eval_steps_per_second": 1.537,
"step": 4000
},
{
"epoch": 1.4157939428247948,
"grad_norm": 3.606387138366699,
"learning_rate": 2.4230462872820605e-05,
"loss": 1.4568,
"step": 5000
},
{
"epoch": 1.4157939428247948,
"eval_cosine_accuracy": 0.9725332856178284,
"eval_loss": 0.8822396397590637,
"eval_runtime": 23.9729,
"eval_samples_per_second": 394.862,
"eval_steps_per_second": 1.543,
"step": 5000
},
{
"epoch": 1.698839513161619,
"grad_norm": 3.6768007278442383,
"learning_rate": 2.1575360651385078e-05,
"loss": 1.3739,
"step": 6000
},
{
"epoch": 1.698839513161619,
"eval_cosine_accuracy": 0.9725332856178284,
"eval_loss": 0.8737966418266296,
"eval_runtime": 24.139,
"eval_samples_per_second": 392.145,
"eval_steps_per_second": 1.533,
"step": 6000
},
{
"epoch": 1.9818850834984434,
"grad_norm": 3.6265289783477783,
"learning_rate": 1.8922913532170987e-05,
"loss": 1.3245,
"step": 7000
},
{
"epoch": 1.9818850834984434,
"eval_cosine_accuracy": 0.9744347929954529,
"eval_loss": 0.8641142249107361,
"eval_runtime": 24.3115,
"eval_samples_per_second": 389.364,
"eval_steps_per_second": 1.522,
"step": 7000
}
],
"logging_steps": 1000,
"max_steps": 14124,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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
}
|