Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +173 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 2.76945424079895,
|
| 14 |
+
"learning_rate": 9.940874595551404e-05,
|
| 15 |
+
"loss": 1.2118,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0,
|
| 20 |
+
"grad_norm": 1.4828996658325195,
|
| 21 |
+
"learning_rate": 9.760113134728384e-05,
|
| 22 |
+
"loss": 0.8364,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.0,
|
| 27 |
+
"grad_norm": 1.7079859972000122,
|
| 28 |
+
"learning_rate": 9.46214189061859e-05,
|
| 29 |
+
"loss": 0.6766,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 4.0,
|
| 34 |
+
"grad_norm": 2.6615920066833496,
|
| 35 |
+
"learning_rate": 9.054297904161868e-05,
|
| 36 |
+
"loss": 0.545,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.0,
|
| 41 |
+
"grad_norm": 4.234976768493652,
|
| 42 |
+
"learning_rate": 8.54662364786137e-05,
|
| 43 |
+
"loss": 0.4208,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.0,
|
| 48 |
+
"grad_norm": 14.309597969055176,
|
| 49 |
+
"learning_rate": 7.951619746781474e-05,
|
| 50 |
+
"loss": 0.3242,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 7.0,
|
| 55 |
+
"grad_norm": 6.556349277496338,
|
| 56 |
+
"learning_rate": 7.283937171671498e-05,
|
| 57 |
+
"loss": 0.2409,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 8.0,
|
| 62 |
+
"grad_norm": 5.399975776672363,
|
| 63 |
+
"learning_rate": 6.560016483442075e-05,
|
| 64 |
+
"loss": 0.1779,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.0,
|
| 69 |
+
"grad_norm": 4.709582328796387,
|
| 70 |
+
"learning_rate": 5.797683011992432e-05,
|
| 71 |
+
"loss": 0.1373,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 10.0,
|
| 76 |
+
"grad_norm": 1.5215970277786255,
|
| 77 |
+
"learning_rate": 5.0157079374293983e-05,
|
| 78 |
+
"loss": 0.1079,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 11.0,
|
| 83 |
+
"grad_norm": 8.067852973937988,
|
| 84 |
+
"learning_rate": 4.233346081315196e-05,
|
| 85 |
+
"loss": 0.0849,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 12.0,
|
| 90 |
+
"grad_norm": 1.95754873752594,
|
| 91 |
+
"learning_rate": 3.469861789057497e-05,
|
| 92 |
+
"loss": 0.0693,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 13.0,
|
| 97 |
+
"grad_norm": 0.9738472104072571,
|
| 98 |
+
"learning_rate": 2.7440545777907746e-05,
|
| 99 |
+
"loss": 0.0583,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 14.0,
|
| 104 |
+
"grad_norm": 0.98776775598526,
|
| 105 |
+
"learning_rate": 2.0737962298724512e-05,
|
| 106 |
+
"loss": 0.0505,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 15.0,
|
| 111 |
+
"grad_norm": 1.5931845903396606,
|
| 112 |
+
"learning_rate": 1.4755907302881927e-05,
|
| 113 |
+
"loss": 0.0448,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 16.0,
|
| 118 |
+
"grad_norm": 2.104052782058716,
|
| 119 |
+
"learning_rate": 9.641678837679985e-06,
|
| 120 |
+
"loss": 0.0412,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 17.0,
|
| 125 |
+
"grad_norm": 0.45166563987731934,
|
| 126 |
+
"learning_rate": 5.521206181083111e-06,
|
| 127 |
+
"loss": 0.0386,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 18.0,
|
| 132 |
+
"grad_norm": 0.7560405135154724,
|
| 133 |
+
"learning_rate": 2.4959490449614096e-06,
|
| 134 |
+
"loss": 0.0368,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 19.0,
|
| 139 |
+
"grad_norm": 0.8283025026321411,
|
| 140 |
+
"learning_rate": 6.403993002590425e-07,
|
| 141 |
+
"loss": 0.0358,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 20.0,
|
| 146 |
+
"grad_norm": 0.7078251242637634,
|
| 147 |
+
"learning_rate": 2.4673990708934393e-10,
|
| 148 |
+
"loss": 0.0353,
|
| 149 |
+
"step": 2000
|
| 150 |
+
}
|
| 151 |
+
],
|
| 152 |
+
"logging_steps": 500,
|
| 153 |
+
"max_steps": 2000,
|
| 154 |
+
"num_input_tokens_seen": 0,
|
| 155 |
+
"num_train_epochs": 20,
|
| 156 |
+
"save_steps": 500,
|
| 157 |
+
"stateful_callbacks": {
|
| 158 |
+
"TrainerControl": {
|
| 159 |
+
"args": {
|
| 160 |
+
"should_epoch_stop": false,
|
| 161 |
+
"should_evaluate": false,
|
| 162 |
+
"should_log": false,
|
| 163 |
+
"should_save": true,
|
| 164 |
+
"should_training_stop": true
|
| 165 |
+
},
|
| 166 |
+
"attributes": {}
|
| 167 |
+
}
|
| 168 |
+
},
|
| 169 |
+
"total_flos": 1.56828324077568e+16,
|
| 170 |
+
"train_batch_size": 1,
|
| 171 |
+
"trial_name": null,
|
| 172 |
+
"trial_params": null
|
| 173 |
+
}
|