File size: 3,369 Bytes
15521fa cf1e3a4 15521fa 76fd95e 15521fa cf1e3a4 15521fa cf1e3a4 15521fa cf1e3a4 15521fa cf1e3a4 15521fa cf1e3a4 76fd95e cf1e3a4 15521fa cf1e3a4 76fd95e cf1e3a4 15521fa 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e cf1e3a4 76fd95e 15521fa 76fd95e 15521fa cf1e3a4 15521fa |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.010260970687827069,
"eval_steps": 500,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006840647125218045,
"grad_norm": 0.6777583360671997,
"learning_rate": 0.0001931034482758621,
"loss": 2.5631,
"step": 10
},
{
"epoch": 0.001368129425043609,
"grad_norm": 0.529003918170929,
"learning_rate": 0.0001793103448275862,
"loss": 2.2202,
"step": 20
},
{
"epoch": 0.0020521941375654137,
"grad_norm": 0.6383516192436218,
"learning_rate": 0.00016551724137931035,
"loss": 2.2541,
"step": 30
},
{
"epoch": 0.002736258850087218,
"grad_norm": 0.547764778137207,
"learning_rate": 0.00015172413793103449,
"loss": 2.1831,
"step": 40
},
{
"epoch": 0.003420323562609023,
"grad_norm": NaN,
"learning_rate": 0.0001393103448275862,
"loss": 2.2025,
"step": 50
},
{
"epoch": 0.0041043882751308275,
"grad_norm": 0.6107162237167358,
"learning_rate": 0.00012551724137931035,
"loss": 2.1387,
"step": 60
},
{
"epoch": 0.004788452987652632,
"grad_norm": 0.5852159261703491,
"learning_rate": 0.00011172413793103449,
"loss": 2.1362,
"step": 70
},
{
"epoch": 0.005472517700174436,
"grad_norm": 0.587351381778717,
"learning_rate": 9.793103448275862e-05,
"loss": 2.1783,
"step": 80
},
{
"epoch": 0.006156582412696241,
"grad_norm": 0.4379996657371521,
"learning_rate": 8.413793103448277e-05,
"loss": 2.0619,
"step": 90
},
{
"epoch": 0.006840647125218046,
"grad_norm": 0.6348068714141846,
"learning_rate": 7.03448275862069e-05,
"loss": 2.1559,
"step": 100
},
{
"epoch": 0.0075247118377398505,
"grad_norm": 0.5908586382865906,
"learning_rate": 5.6551724137931037e-05,
"loss": 2.0957,
"step": 110
},
{
"epoch": 0.008208776550261655,
"grad_norm": 0.6663537621498108,
"learning_rate": 4.275862068965518e-05,
"loss": 2.2033,
"step": 120
},
{
"epoch": 0.008892841262783458,
"grad_norm": 0.5192745923995972,
"learning_rate": 2.8965517241379313e-05,
"loss": 2.0376,
"step": 130
},
{
"epoch": 0.009576905975305264,
"grad_norm": 0.6954190731048584,
"learning_rate": 1.5172413793103448e-05,
"loss": 2.108,
"step": 140
},
{
"epoch": 0.010260970687827069,
"grad_norm": 0.6196115016937256,
"learning_rate": 1.3793103448275862e-06,
"loss": 1.9693,
"step": 150
}
],
"logging_steps": 10,
"max_steps": 150,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.164445885681664e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|