Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +160 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 18390,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.8156606851549756,
|
| 14 |
+
"grad_norm": 2.7835583686828613,
|
| 15 |
+
"learning_rate": 0.00019968889417401253,
|
| 16 |
+
"loss": 0.6438,
|
| 17 |
+
"step": 1000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.631321370309951,
|
| 21 |
+
"grad_norm": 0.3261709213256836,
|
| 22 |
+
"learning_rate": 0.00019676585418772425,
|
| 23 |
+
"loss": 0.2388,
|
| 24 |
+
"step": 2000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.4469820554649266,
|
| 28 |
+
"grad_norm": 2.9635205268859863,
|
| 29 |
+
"learning_rate": 0.00019084912501825553,
|
| 30 |
+
"loss": 0.2032,
|
| 31 |
+
"step": 3000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.262642740619902,
|
| 35 |
+
"grad_norm": 2.162414312362671,
|
| 36 |
+
"learning_rate": 0.00018212175520336934,
|
| 37 |
+
"loss": 0.163,
|
| 38 |
+
"step": 4000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 4.078303425774878,
|
| 42 |
+
"grad_norm": 3.4721012115478516,
|
| 43 |
+
"learning_rate": 0.00017085374734710157,
|
| 44 |
+
"loss": 0.1519,
|
| 45 |
+
"step": 5000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 4.893964110929853,
|
| 49 |
+
"grad_norm": 1.8501887321472168,
|
| 50 |
+
"learning_rate": 0.0001573937049265616,
|
| 51 |
+
"loss": 0.13,
|
| 52 |
+
"step": 6000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 5.709624796084829,
|
| 56 |
+
"grad_norm": 3.3048102855682373,
|
| 57 |
+
"learning_rate": 0.00014215804738782126,
|
| 58 |
+
"loss": 0.1186,
|
| 59 |
+
"step": 7000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 6.525285481239804,
|
| 63 |
+
"grad_norm": 2.223738193511963,
|
| 64 |
+
"learning_rate": 0.00012561812718836913,
|
| 65 |
+
"loss": 0.1046,
|
| 66 |
+
"step": 8000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 7.3409461663947795,
|
| 70 |
+
"grad_norm": 0.2893391251564026,
|
| 71 |
+
"learning_rate": 0.00010828564735203954,
|
| 72 |
+
"loss": 0.0957,
|
| 73 |
+
"step": 9000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 8.156606851549755,
|
| 77 |
+
"grad_norm": 0.24986231327056885,
|
| 78 |
+
"learning_rate": 9.069683068014265e-05,
|
| 79 |
+
"loss": 0.0912,
|
| 80 |
+
"step": 10000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 8.97226753670473,
|
| 84 |
+
"grad_norm": 0.6728571653366089,
|
| 85 |
+
"learning_rate": 7.339583038310173e-05,
|
| 86 |
+
"loss": 0.08,
|
| 87 |
+
"step": 11000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 9.787928221859707,
|
| 91 |
+
"grad_norm": 0.3318624794483185,
|
| 92 |
+
"learning_rate": 5.69178953654216e-05,
|
| 93 |
+
"loss": 0.0722,
|
| 94 |
+
"step": 12000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 10.603588907014682,
|
| 98 |
+
"grad_norm": 0.1652187556028366,
|
| 99 |
+
"learning_rate": 4.177281098721372e-05,
|
| 100 |
+
"loss": 0.07,
|
| 101 |
+
"step": 13000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 11.419249592169658,
|
| 105 |
+
"grad_norm": 0.13997943699359894,
|
| 106 |
+
"learning_rate": 2.8429127602959905e-05,
|
| 107 |
+
"loss": 0.0635,
|
| 108 |
+
"step": 14000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 12.234910277324634,
|
| 112 |
+
"grad_norm": 0.17078348994255066,
|
| 113 |
+
"learning_rate": 1.729966480637476e-05,
|
| 114 |
+
"loss": 0.0607,
|
| 115 |
+
"step": 15000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 13.05057096247961,
|
| 119 |
+
"grad_norm": 0.10830472409725189,
|
| 120 |
+
"learning_rate": 8.728739843127509e-06,
|
| 121 |
+
"loss": 0.0599,
|
| 122 |
+
"step": 16000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 13.866231647634583,
|
| 126 |
+
"grad_norm": 0.13888326287269592,
|
| 127 |
+
"learning_rate": 2.9815153118197825e-06,
|
| 128 |
+
"loss": 0.0566,
|
| 129 |
+
"step": 17000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 14.681892332789559,
|
| 133 |
+
"grad_norm": 0.138445645570755,
|
| 134 |
+
"learning_rate": 2.3579570823278885e-07,
|
| 135 |
+
"loss": 0.0556,
|
| 136 |
+
"step": 18000
|
| 137 |
+
}
|
| 138 |
+
],
|
| 139 |
+
"logging_steps": 1000,
|
| 140 |
+
"max_steps": 18390,
|
| 141 |
+
"num_input_tokens_seen": 0,
|
| 142 |
+
"num_train_epochs": 15,
|
| 143 |
+
"save_steps": 6000,
|
| 144 |
+
"stateful_callbacks": {
|
| 145 |
+
"TrainerControl": {
|
| 146 |
+
"args": {
|
| 147 |
+
"should_epoch_stop": false,
|
| 148 |
+
"should_evaluate": false,
|
| 149 |
+
"should_log": false,
|
| 150 |
+
"should_save": true,
|
| 151 |
+
"should_training_stop": true
|
| 152 |
+
},
|
| 153 |
+
"attributes": {}
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"total_flos": 7.5627004461372e+16,
|
| 157 |
+
"train_batch_size": 1,
|
| 158 |
+
"trial_name": null,
|
| 159 |
+
"trial_params": null
|
| 160 |
+
}
|