Commit
·
c098c70
1
Parent(s):
808d890
End of training
Browse files- README.md +1 -0
- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +613 -0
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model: microsoft/wavlm-base
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
|
|
|
| 1 |
---
|
| 2 |
base_model: microsoft/wavlm-base
|
| 3 |
tags:
|
| 4 |
+
- audio-classification
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"eval_accuracy": 0.8974400257607471,
|
| 4 |
+
"eval_loss": 0.4151269197463989,
|
| 5 |
+
"eval_runtime": 499.658,
|
| 6 |
+
"eval_samples_per_second": 49.722,
|
| 7 |
+
"eval_steps_per_second": 24.861,
|
| 8 |
+
"train_loss": 0.5747933341999246,
|
| 9 |
+
"train_runtime": 22880.3496,
|
| 10 |
+
"train_samples_per_second": 11.092,
|
| 11 |
+
"train_steps_per_second": 0.173
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"eval_accuracy": 0.8974400257607471,
|
| 4 |
+
"eval_loss": 0.4151269197463989,
|
| 5 |
+
"eval_runtime": 499.658,
|
| 6 |
+
"eval_samples_per_second": 49.722,
|
| 7 |
+
"eval_steps_per_second": 24.861
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"train_loss": 0.5747933341999246,
|
| 4 |
+
"train_runtime": 22880.3496,
|
| 5 |
+
"train_samples_per_second": 11.092,
|
| 6 |
+
"train_steps_per_second": 0.173
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,613 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.027737604454159737,
|
| 3 |
+
"best_model_checkpoint": "/home/cloudwalker/ASVmodel/wavlm-base_5/checkpoint-100",
|
| 4 |
+
"epoch": 9.98109640831758,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 3960,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.25,
|
| 13 |
+
"learning_rate": 7.575757575757576e-05,
|
| 14 |
+
"loss": 0.3764,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.25,
|
| 19 |
+
"eval_accuracy": 0.9947673482530993,
|
| 20 |
+
"eval_loss": 0.027737604454159737,
|
| 21 |
+
"eval_runtime": 497.2467,
|
| 22 |
+
"eval_samples_per_second": 49.963,
|
| 23 |
+
"eval_steps_per_second": 24.982,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.5,
|
| 28 |
+
"learning_rate": 0.00015151515151515152,
|
| 29 |
+
"loss": 0.1211,
|
| 30 |
+
"step": 200
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5,
|
| 34 |
+
"eval_accuracy": 0.998108195137659,
|
| 35 |
+
"eval_loss": 0.02966056950390339,
|
| 36 |
+
"eval_runtime": 498.935,
|
| 37 |
+
"eval_samples_per_second": 49.794,
|
| 38 |
+
"eval_steps_per_second": 24.897,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.76,
|
| 43 |
+
"learning_rate": 0.00022727272727272725,
|
| 44 |
+
"loss": 0.2525,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.76,
|
| 49 |
+
"eval_accuracy": 0.9168008372242795,
|
| 50 |
+
"eval_loss": 1.283957839012146,
|
| 51 |
+
"eval_runtime": 499.0992,
|
| 52 |
+
"eval_samples_per_second": 49.778,
|
| 53 |
+
"eval_steps_per_second": 24.889,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.01,
|
| 58 |
+
"learning_rate": 0.00029966329966329963,
|
| 59 |
+
"loss": 0.784,
|
| 60 |
+
"step": 400
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.01,
|
| 64 |
+
"eval_accuracy": 0.8974400257607471,
|
| 65 |
+
"eval_loss": 0.34426796436309814,
|
| 66 |
+
"eval_runtime": 499.2746,
|
| 67 |
+
"eval_samples_per_second": 49.76,
|
| 68 |
+
"eval_steps_per_second": 24.88,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.26,
|
| 73 |
+
"learning_rate": 0.00029124579124579125,
|
| 74 |
+
"loss": 0.6053,
|
| 75 |
+
"step": 500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.26,
|
| 79 |
+
"eval_accuracy": 0.8974400257607471,
|
| 80 |
+
"eval_loss": 0.3957619071006775,
|
| 81 |
+
"eval_runtime": 499.3187,
|
| 82 |
+
"eval_samples_per_second": 49.756,
|
| 83 |
+
"eval_steps_per_second": 24.878,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.51,
|
| 88 |
+
"learning_rate": 0.0002828282828282828,
|
| 89 |
+
"loss": 0.6038,
|
| 90 |
+
"step": 600
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.51,
|
| 94 |
+
"eval_accuracy": 0.8974400257607471,
|
| 95 |
+
"eval_loss": 0.4848286509513855,
|
| 96 |
+
"eval_runtime": 499.175,
|
| 97 |
+
"eval_samples_per_second": 49.77,
|
| 98 |
+
"eval_steps_per_second": 24.885,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.76,
|
| 103 |
+
"learning_rate": 0.0002744107744107744,
|
| 104 |
+
"loss": 0.5996,
|
| 105 |
+
"step": 700
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.76,
|
| 109 |
+
"eval_accuracy": 0.8974400257607471,
|
| 110 |
+
"eval_loss": 0.39541468024253845,
|
| 111 |
+
"eval_runtime": 499.7897,
|
| 112 |
+
"eval_samples_per_second": 49.709,
|
| 113 |
+
"eval_steps_per_second": 24.854,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.02,
|
| 118 |
+
"learning_rate": 0.00026599326599326595,
|
| 119 |
+
"loss": 0.5914,
|
| 120 |
+
"step": 800
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.02,
|
| 124 |
+
"eval_accuracy": 0.8974400257607471,
|
| 125 |
+
"eval_loss": 0.3970233201980591,
|
| 126 |
+
"eval_runtime": 499.6888,
|
| 127 |
+
"eval_samples_per_second": 49.719,
|
| 128 |
+
"eval_steps_per_second": 24.859,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.27,
|
| 133 |
+
"learning_rate": 0.00025757575757575756,
|
| 134 |
+
"loss": 0.6077,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.27,
|
| 139 |
+
"eval_accuracy": 0.8974400257607471,
|
| 140 |
+
"eval_loss": 0.4722130298614502,
|
| 141 |
+
"eval_runtime": 499.722,
|
| 142 |
+
"eval_samples_per_second": 49.716,
|
| 143 |
+
"eval_steps_per_second": 24.858,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.52,
|
| 148 |
+
"learning_rate": 0.00024915824915824913,
|
| 149 |
+
"loss": 0.5991,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.52,
|
| 154 |
+
"eval_accuracy": 0.8974400257607471,
|
| 155 |
+
"eval_loss": 0.43623748421669006,
|
| 156 |
+
"eval_runtime": 499.9532,
|
| 157 |
+
"eval_samples_per_second": 49.693,
|
| 158 |
+
"eval_steps_per_second": 24.846,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.77,
|
| 163 |
+
"learning_rate": 0.00024074074074074072,
|
| 164 |
+
"loss": 0.5813,
|
| 165 |
+
"step": 1100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.77,
|
| 169 |
+
"eval_accuracy": 0.8974400257607471,
|
| 170 |
+
"eval_loss": 0.38707101345062256,
|
| 171 |
+
"eval_runtime": 499.9678,
|
| 172 |
+
"eval_samples_per_second": 49.691,
|
| 173 |
+
"eval_steps_per_second": 24.846,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.02,
|
| 178 |
+
"learning_rate": 0.0002323232323232323,
|
| 179 |
+
"loss": 0.5953,
|
| 180 |
+
"step": 1200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.02,
|
| 184 |
+
"eval_accuracy": 0.8974400257607471,
|
| 185 |
+
"eval_loss": 0.40134623646736145,
|
| 186 |
+
"eval_runtime": 499.6897,
|
| 187 |
+
"eval_samples_per_second": 49.719,
|
| 188 |
+
"eval_steps_per_second": 24.859,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.28,
|
| 193 |
+
"learning_rate": 0.0002239057239057239,
|
| 194 |
+
"loss": 0.5957,
|
| 195 |
+
"step": 1300
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.28,
|
| 199 |
+
"eval_accuracy": 0.8974400257607471,
|
| 200 |
+
"eval_loss": 0.46927762031555176,
|
| 201 |
+
"eval_runtime": 499.7933,
|
| 202 |
+
"eval_samples_per_second": 49.709,
|
| 203 |
+
"eval_steps_per_second": 24.854,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.53,
|
| 208 |
+
"learning_rate": 0.00021548821548821544,
|
| 209 |
+
"loss": 0.5852,
|
| 210 |
+
"step": 1400
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.53,
|
| 214 |
+
"eval_accuracy": 0.8974400257607471,
|
| 215 |
+
"eval_loss": 0.387899786233902,
|
| 216 |
+
"eval_runtime": 499.9294,
|
| 217 |
+
"eval_samples_per_second": 49.695,
|
| 218 |
+
"eval_steps_per_second": 24.848,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.78,
|
| 223 |
+
"learning_rate": 0.00020707070707070703,
|
| 224 |
+
"loss": 0.6066,
|
| 225 |
+
"step": 1500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.78,
|
| 229 |
+
"eval_accuracy": 0.8974400257607471,
|
| 230 |
+
"eval_loss": 0.42799168825149536,
|
| 231 |
+
"eval_runtime": 499.9481,
|
| 232 |
+
"eval_samples_per_second": 49.693,
|
| 233 |
+
"eval_steps_per_second": 24.847,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.03,
|
| 238 |
+
"learning_rate": 0.00019865319865319862,
|
| 239 |
+
"loss": 0.6085,
|
| 240 |
+
"step": 1600
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 4.03,
|
| 244 |
+
"eval_accuracy": 0.8974400257607471,
|
| 245 |
+
"eval_loss": 0.4358781576156616,
|
| 246 |
+
"eval_runtime": 499.7505,
|
| 247 |
+
"eval_samples_per_second": 49.713,
|
| 248 |
+
"eval_steps_per_second": 24.856,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.28,
|
| 253 |
+
"learning_rate": 0.00019023569023569022,
|
| 254 |
+
"loss": 0.5944,
|
| 255 |
+
"step": 1700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.28,
|
| 259 |
+
"eval_accuracy": 0.8974400257607471,
|
| 260 |
+
"eval_loss": 0.41665858030319214,
|
| 261 |
+
"eval_runtime": 499.6545,
|
| 262 |
+
"eval_samples_per_second": 49.722,
|
| 263 |
+
"eval_steps_per_second": 24.861,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.54,
|
| 268 |
+
"learning_rate": 0.0001818181818181818,
|
| 269 |
+
"loss": 0.5994,
|
| 270 |
+
"step": 1800
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.54,
|
| 274 |
+
"eval_accuracy": 0.8974400257607471,
|
| 275 |
+
"eval_loss": 0.4139242172241211,
|
| 276 |
+
"eval_runtime": 499.4729,
|
| 277 |
+
"eval_samples_per_second": 49.74,
|
| 278 |
+
"eval_steps_per_second": 24.87,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 4.79,
|
| 283 |
+
"learning_rate": 0.0001734006734006734,
|
| 284 |
+
"loss": 0.5953,
|
| 285 |
+
"step": 1900
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 4.79,
|
| 289 |
+
"eval_accuracy": 0.8974400257607471,
|
| 290 |
+
"eval_loss": 0.42556148767471313,
|
| 291 |
+
"eval_runtime": 499.5722,
|
| 292 |
+
"eval_samples_per_second": 49.731,
|
| 293 |
+
"eval_steps_per_second": 24.865,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.04,
|
| 298 |
+
"learning_rate": 0.000164983164983165,
|
| 299 |
+
"loss": 0.5929,
|
| 300 |
+
"step": 2000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 5.04,
|
| 304 |
+
"eval_accuracy": 0.8974400257607471,
|
| 305 |
+
"eval_loss": 0.4370674192905426,
|
| 306 |
+
"eval_runtime": 499.6245,
|
| 307 |
+
"eval_samples_per_second": 49.725,
|
| 308 |
+
"eval_steps_per_second": 24.863,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 5.29,
|
| 313 |
+
"learning_rate": 0.00015656565656565653,
|
| 314 |
+
"loss": 0.6067,
|
| 315 |
+
"step": 2100
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 5.29,
|
| 319 |
+
"eval_accuracy": 0.8974400257607471,
|
| 320 |
+
"eval_loss": 0.4254782199859619,
|
| 321 |
+
"eval_runtime": 499.8266,
|
| 322 |
+
"eval_samples_per_second": 49.705,
|
| 323 |
+
"eval_steps_per_second": 24.853,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 5.55,
|
| 328 |
+
"learning_rate": 0.00014814814814814812,
|
| 329 |
+
"loss": 0.5944,
|
| 330 |
+
"step": 2200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 5.55,
|
| 334 |
+
"eval_accuracy": 0.8974400257607471,
|
| 335 |
+
"eval_loss": 0.41206374764442444,
|
| 336 |
+
"eval_runtime": 499.9874,
|
| 337 |
+
"eval_samples_per_second": 49.689,
|
| 338 |
+
"eval_steps_per_second": 24.845,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 5.8,
|
| 343 |
+
"learning_rate": 0.0001397306397306397,
|
| 344 |
+
"loss": 0.5926,
|
| 345 |
+
"step": 2300
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 5.8,
|
| 349 |
+
"eval_accuracy": 0.8974400257607471,
|
| 350 |
+
"eval_loss": 0.42098236083984375,
|
| 351 |
+
"eval_runtime": 499.6375,
|
| 352 |
+
"eval_samples_per_second": 49.724,
|
| 353 |
+
"eval_steps_per_second": 24.862,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 6.05,
|
| 358 |
+
"learning_rate": 0.0001313131313131313,
|
| 359 |
+
"loss": 0.594,
|
| 360 |
+
"step": 2400
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 6.05,
|
| 364 |
+
"eval_accuracy": 0.8974400257607471,
|
| 365 |
+
"eval_loss": 0.40572819113731384,
|
| 366 |
+
"eval_runtime": 499.6473,
|
| 367 |
+
"eval_samples_per_second": 49.723,
|
| 368 |
+
"eval_steps_per_second": 24.862,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 6.3,
|
| 373 |
+
"learning_rate": 0.0001228956228956229,
|
| 374 |
+
"loss": 0.6042,
|
| 375 |
+
"step": 2500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 6.3,
|
| 379 |
+
"eval_accuracy": 0.8974400257607471,
|
| 380 |
+
"eval_loss": 0.42515799403190613,
|
| 381 |
+
"eval_runtime": 499.6019,
|
| 382 |
+
"eval_samples_per_second": 49.728,
|
| 383 |
+
"eval_steps_per_second": 24.864,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 6.55,
|
| 388 |
+
"learning_rate": 0.00011447811447811446,
|
| 389 |
+
"loss": 0.5971,
|
| 390 |
+
"step": 2600
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 6.55,
|
| 394 |
+
"eval_accuracy": 0.8974400257607471,
|
| 395 |
+
"eval_loss": 0.395828515291214,
|
| 396 |
+
"eval_runtime": 500.1612,
|
| 397 |
+
"eval_samples_per_second": 49.672,
|
| 398 |
+
"eval_steps_per_second": 24.836,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 6.81,
|
| 403 |
+
"learning_rate": 0.00010606060606060605,
|
| 404 |
+
"loss": 0.597,
|
| 405 |
+
"step": 2700
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 6.81,
|
| 409 |
+
"eval_accuracy": 0.8974400257607471,
|
| 410 |
+
"eval_loss": 0.41235631704330444,
|
| 411 |
+
"eval_runtime": 499.5804,
|
| 412 |
+
"eval_samples_per_second": 49.73,
|
| 413 |
+
"eval_steps_per_second": 24.865,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 7.06,
|
| 418 |
+
"learning_rate": 9.764309764309764e-05,
|
| 419 |
+
"loss": 0.5816,
|
| 420 |
+
"step": 2800
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 7.06,
|
| 424 |
+
"eval_accuracy": 0.8974400257607471,
|
| 425 |
+
"eval_loss": 0.41006505489349365,
|
| 426 |
+
"eval_runtime": 499.6536,
|
| 427 |
+
"eval_samples_per_second": 49.722,
|
| 428 |
+
"eval_steps_per_second": 24.861,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 7.31,
|
| 433 |
+
"learning_rate": 8.92255892255892e-05,
|
| 434 |
+
"loss": 0.5944,
|
| 435 |
+
"step": 2900
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 7.31,
|
| 439 |
+
"eval_accuracy": 0.8974400257607471,
|
| 440 |
+
"eval_loss": 0.42578616738319397,
|
| 441 |
+
"eval_runtime": 499.7205,
|
| 442 |
+
"eval_samples_per_second": 49.716,
|
| 443 |
+
"eval_steps_per_second": 24.858,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 7.56,
|
| 448 |
+
"learning_rate": 8.08080808080808e-05,
|
| 449 |
+
"loss": 0.6053,
|
| 450 |
+
"step": 3000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 7.56,
|
| 454 |
+
"eval_accuracy": 0.8974400257607471,
|
| 455 |
+
"eval_loss": 0.4414595365524292,
|
| 456 |
+
"eval_runtime": 499.6011,
|
| 457 |
+
"eval_samples_per_second": 49.728,
|
| 458 |
+
"eval_steps_per_second": 24.864,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 7.81,
|
| 463 |
+
"learning_rate": 7.239057239057239e-05,
|
| 464 |
+
"loss": 0.5894,
|
| 465 |
+
"step": 3100
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 7.81,
|
| 469 |
+
"eval_accuracy": 0.8974400257607471,
|
| 470 |
+
"eval_loss": 0.40666893124580383,
|
| 471 |
+
"eval_runtime": 499.6727,
|
| 472 |
+
"eval_samples_per_second": 49.721,
|
| 473 |
+
"eval_steps_per_second": 24.86,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 8.07,
|
| 478 |
+
"learning_rate": 6.397306397306397e-05,
|
| 479 |
+
"loss": 0.5987,
|
| 480 |
+
"step": 3200
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 8.07,
|
| 484 |
+
"eval_accuracy": 0.8974400257607471,
|
| 485 |
+
"eval_loss": 0.41087645292282104,
|
| 486 |
+
"eval_runtime": 499.5755,
|
| 487 |
+
"eval_samples_per_second": 49.73,
|
| 488 |
+
"eval_steps_per_second": 24.865,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 8.32,
|
| 493 |
+
"learning_rate": 5.5555555555555545e-05,
|
| 494 |
+
"loss": 0.5846,
|
| 495 |
+
"step": 3300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 8.32,
|
| 499 |
+
"eval_accuracy": 0.8974400257607471,
|
| 500 |
+
"eval_loss": 0.4095437824726105,
|
| 501 |
+
"eval_runtime": 499.7301,
|
| 502 |
+
"eval_samples_per_second": 49.715,
|
| 503 |
+
"eval_steps_per_second": 24.857,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 8.57,
|
| 508 |
+
"learning_rate": 4.7138047138047136e-05,
|
| 509 |
+
"loss": 0.5982,
|
| 510 |
+
"step": 3400
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 8.57,
|
| 514 |
+
"eval_accuracy": 0.8974400257607471,
|
| 515 |
+
"eval_loss": 0.41868552565574646,
|
| 516 |
+
"eval_runtime": 499.638,
|
| 517 |
+
"eval_samples_per_second": 49.724,
|
| 518 |
+
"eval_steps_per_second": 24.862,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 8.82,
|
| 523 |
+
"learning_rate": 3.8720538720538714e-05,
|
| 524 |
+
"loss": 0.5932,
|
| 525 |
+
"step": 3500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 8.82,
|
| 529 |
+
"eval_accuracy": 0.8974400257607471,
|
| 530 |
+
"eval_loss": 0.4124181866645813,
|
| 531 |
+
"eval_runtime": 499.6303,
|
| 532 |
+
"eval_samples_per_second": 49.725,
|
| 533 |
+
"eval_steps_per_second": 24.862,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 9.07,
|
| 538 |
+
"learning_rate": 3.03030303030303e-05,
|
| 539 |
+
"loss": 0.6007,
|
| 540 |
+
"step": 3600
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 9.07,
|
| 544 |
+
"eval_accuracy": 0.8974400257607471,
|
| 545 |
+
"eval_loss": 0.42121654748916626,
|
| 546 |
+
"eval_runtime": 499.864,
|
| 547 |
+
"eval_samples_per_second": 49.702,
|
| 548 |
+
"eval_steps_per_second": 24.851,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 9.33,
|
| 553 |
+
"learning_rate": 2.1885521885521884e-05,
|
| 554 |
+
"loss": 0.6041,
|
| 555 |
+
"step": 3700
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 9.33,
|
| 559 |
+
"eval_accuracy": 0.8974400257607471,
|
| 560 |
+
"eval_loss": 0.4257338345050812,
|
| 561 |
+
"eval_runtime": 499.3339,
|
| 562 |
+
"eval_samples_per_second": 49.754,
|
| 563 |
+
"eval_steps_per_second": 24.877,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 9.58,
|
| 568 |
+
"learning_rate": 1.3468013468013465e-05,
|
| 569 |
+
"loss": 0.5859,
|
| 570 |
+
"step": 3800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 9.58,
|
| 574 |
+
"eval_accuracy": 0.8974400257607471,
|
| 575 |
+
"eval_loss": 0.4176446497440338,
|
| 576 |
+
"eval_runtime": 499.7293,
|
| 577 |
+
"eval_samples_per_second": 49.715,
|
| 578 |
+
"eval_steps_per_second": 24.857,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 9.83,
|
| 583 |
+
"learning_rate": 5.05050505050505e-06,
|
| 584 |
+
"loss": 0.5842,
|
| 585 |
+
"step": 3900
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 9.83,
|
| 589 |
+
"eval_accuracy": 0.8974400257607471,
|
| 590 |
+
"eval_loss": 0.41514307260513306,
|
| 591 |
+
"eval_runtime": 499.5922,
|
| 592 |
+
"eval_samples_per_second": 49.729,
|
| 593 |
+
"eval_steps_per_second": 24.864,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 9.98,
|
| 598 |
+
"step": 3960,
|
| 599 |
+
"total_flos": 1.506420070651024e+19,
|
| 600 |
+
"train_loss": 0.5747933341999246,
|
| 601 |
+
"train_runtime": 22880.3496,
|
| 602 |
+
"train_samples_per_second": 11.092,
|
| 603 |
+
"train_steps_per_second": 0.173
|
| 604 |
+
}
|
| 605 |
+
],
|
| 606 |
+
"logging_steps": 100,
|
| 607 |
+
"max_steps": 3960,
|
| 608 |
+
"num_train_epochs": 10,
|
| 609 |
+
"save_steps": 100,
|
| 610 |
+
"total_flos": 1.506420070651024e+19,
|
| 611 |
+
"trial_name": null,
|
| 612 |
+
"trial_params": null
|
| 613 |
+
}
|