Commit
·
6e27689
1
Parent(s):
d01e104
End of training
Browse files- README.md +2 -1
- 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 |
- f1
|
|
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
- F1: 0.9459
|
| 21 |
|
| 22 |
## Model description
|
|
|
|
| 1 |
---
|
| 2 |
base_model: microsoft/wavlm-base
|
| 3 |
tags:
|
| 4 |
+
- audio-classification
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- f1
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.3325
|
| 21 |
- F1: 0.9459
|
| 22 |
|
| 23 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"eval_f1": 0.9459482392872296,
|
| 4 |
+
"eval_loss": 0.3324863016605377,
|
| 5 |
+
"eval_runtime": 496.607,
|
| 6 |
+
"eval_samples_per_second": 50.027,
|
| 7 |
+
"eval_steps_per_second": 25.014,
|
| 8 |
+
"train_loss": 0.32019265878080116,
|
| 9 |
+
"train_runtime": 22716.823,
|
| 10 |
+
"train_samples_per_second": 11.172,
|
| 11 |
+
"train_steps_per_second": 0.174
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"eval_f1": 0.9459482392872296,
|
| 4 |
+
"eval_loss": 0.3324863016605377,
|
| 5 |
+
"eval_runtime": 496.607,
|
| 6 |
+
"eval_samples_per_second": 50.027,
|
| 7 |
+
"eval_steps_per_second": 25.014
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"train_loss": 0.32019265878080116,
|
| 4 |
+
"train_runtime": 22716.823,
|
| 5 |
+
"train_samples_per_second": 11.172,
|
| 6 |
+
"train_steps_per_second": 0.174
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,613 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.06379657983779907,
|
| 3 |
+
"best_model_checkpoint": "/home/cloudwalker/ASVmodel/wavlm-base_4/checkpoint-200",
|
| 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": 0.3784,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.25,
|
| 19 |
+
"eval_f1": 0.9905683736634776,
|
| 20 |
+
"eval_loss": 0.07838701456785202,
|
| 21 |
+
"eval_runtime": 494.4493,
|
| 22 |
+
"eval_samples_per_second": 50.246,
|
| 23 |
+
"eval_steps_per_second": 25.123,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.5,
|
| 28 |
+
"learning_rate": 0.00015151515151515152,
|
| 29 |
+
"loss": 0.1125,
|
| 30 |
+
"step": 200
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5,
|
| 34 |
+
"eval_f1": 0.9925361354770335,
|
| 35 |
+
"eval_loss": 0.06379657983779907,
|
| 36 |
+
"eval_runtime": 495.4697,
|
| 37 |
+
"eval_samples_per_second": 50.142,
|
| 38 |
+
"eval_steps_per_second": 25.071,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.76,
|
| 43 |
+
"learning_rate": 0.00022727272727272725,
|
| 44 |
+
"loss": 0.1158,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.76,
|
| 49 |
+
"eval_f1": 0.9773465624725612,
|
| 50 |
+
"eval_loss": 0.1715879738330841,
|
| 51 |
+
"eval_runtime": 495.6685,
|
| 52 |
+
"eval_samples_per_second": 50.122,
|
| 53 |
+
"eval_steps_per_second": 25.061,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.01,
|
| 58 |
+
"learning_rate": 0.00029966329966329963,
|
| 59 |
+
"loss": 0.327,
|
| 60 |
+
"step": 400
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.01,
|
| 64 |
+
"eval_f1": 0.9459482392872296,
|
| 65 |
+
"eval_loss": 0.3308480978012085,
|
| 66 |
+
"eval_runtime": 495.7404,
|
| 67 |
+
"eval_samples_per_second": 50.115,
|
| 68 |
+
"eval_steps_per_second": 25.057,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.26,
|
| 73 |
+
"learning_rate": 0.00029124579124579125,
|
| 74 |
+
"loss": 0.3346,
|
| 75 |
+
"step": 500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.26,
|
| 79 |
+
"eval_f1": 0.9459482392872296,
|
| 80 |
+
"eval_loss": 0.34493646025657654,
|
| 81 |
+
"eval_runtime": 495.7377,
|
| 82 |
+
"eval_samples_per_second": 50.115,
|
| 83 |
+
"eval_steps_per_second": 25.058,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.51,
|
| 88 |
+
"learning_rate": 0.0002828282828282828,
|
| 89 |
+
"loss": 0.3345,
|
| 90 |
+
"step": 600
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.51,
|
| 94 |
+
"eval_f1": 0.9459482392872296,
|
| 95 |
+
"eval_loss": 0.3316415250301361,
|
| 96 |
+
"eval_runtime": 495.8008,
|
| 97 |
+
"eval_samples_per_second": 50.109,
|
| 98 |
+
"eval_steps_per_second": 25.054,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.76,
|
| 103 |
+
"learning_rate": 0.0002744107744107744,
|
| 104 |
+
"loss": 0.3313,
|
| 105 |
+
"step": 700
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.76,
|
| 109 |
+
"eval_f1": 0.9459482392872296,
|
| 110 |
+
"eval_loss": 0.3320470452308655,
|
| 111 |
+
"eval_runtime": 495.8537,
|
| 112 |
+
"eval_samples_per_second": 50.103,
|
| 113 |
+
"eval_steps_per_second": 25.052,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.02,
|
| 118 |
+
"learning_rate": 0.00026599326599326595,
|
| 119 |
+
"loss": 0.3249,
|
| 120 |
+
"step": 800
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.02,
|
| 124 |
+
"eval_f1": 0.9459482392872296,
|
| 125 |
+
"eval_loss": 0.33273717761039734,
|
| 126 |
+
"eval_runtime": 496.067,
|
| 127 |
+
"eval_samples_per_second": 50.082,
|
| 128 |
+
"eval_steps_per_second": 25.041,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.27,
|
| 133 |
+
"learning_rate": 0.00025757575757575756,
|
| 134 |
+
"loss": 0.3403,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.27,
|
| 139 |
+
"eval_f1": 0.9459482392872296,
|
| 140 |
+
"eval_loss": 0.3314824402332306,
|
| 141 |
+
"eval_runtime": 496.0647,
|
| 142 |
+
"eval_samples_per_second": 50.082,
|
| 143 |
+
"eval_steps_per_second": 25.041,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.52,
|
| 148 |
+
"learning_rate": 0.00024915824915824913,
|
| 149 |
+
"loss": 0.3345,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.52,
|
| 154 |
+
"eval_f1": 0.9459482392872296,
|
| 155 |
+
"eval_loss": 0.3381609320640564,
|
| 156 |
+
"eval_runtime": 496.3675,
|
| 157 |
+
"eval_samples_per_second": 50.052,
|
| 158 |
+
"eval_steps_per_second": 25.026,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.77,
|
| 163 |
+
"learning_rate": 0.00024074074074074072,
|
| 164 |
+
"loss": 0.3174,
|
| 165 |
+
"step": 1100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.77,
|
| 169 |
+
"eval_f1": 0.9459482392872296,
|
| 170 |
+
"eval_loss": 0.33755871653556824,
|
| 171 |
+
"eval_runtime": 496.1396,
|
| 172 |
+
"eval_samples_per_second": 50.075,
|
| 173 |
+
"eval_steps_per_second": 25.037,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.02,
|
| 178 |
+
"learning_rate": 0.0002323232323232323,
|
| 179 |
+
"loss": 0.3274,
|
| 180 |
+
"step": 1200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.02,
|
| 184 |
+
"eval_f1": 0.9459482392872296,
|
| 185 |
+
"eval_loss": 0.3353538513183594,
|
| 186 |
+
"eval_runtime": 496.3912,
|
| 187 |
+
"eval_samples_per_second": 50.049,
|
| 188 |
+
"eval_steps_per_second": 25.025,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.28,
|
| 193 |
+
"learning_rate": 0.0002239057239057239,
|
| 194 |
+
"loss": 0.3296,
|
| 195 |
+
"step": 1300
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.28,
|
| 199 |
+
"eval_f1": 0.9459482392872296,
|
| 200 |
+
"eval_loss": 0.33069172501564026,
|
| 201 |
+
"eval_runtime": 496.1466,
|
| 202 |
+
"eval_samples_per_second": 50.074,
|
| 203 |
+
"eval_steps_per_second": 25.037,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.53,
|
| 208 |
+
"learning_rate": 0.00021548821548821544,
|
| 209 |
+
"loss": 0.3175,
|
| 210 |
+
"step": 1400
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.53,
|
| 214 |
+
"eval_f1": 0.9459482392872296,
|
| 215 |
+
"eval_loss": 0.3341147303581238,
|
| 216 |
+
"eval_runtime": 496.5334,
|
| 217 |
+
"eval_samples_per_second": 50.035,
|
| 218 |
+
"eval_steps_per_second": 25.017,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.78,
|
| 223 |
+
"learning_rate": 0.00020707070707070703,
|
| 224 |
+
"loss": 0.3416,
|
| 225 |
+
"step": 1500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.78,
|
| 229 |
+
"eval_f1": 0.9459482392872296,
|
| 230 |
+
"eval_loss": 0.3344402611255646,
|
| 231 |
+
"eval_runtime": 496.2158,
|
| 232 |
+
"eval_samples_per_second": 50.067,
|
| 233 |
+
"eval_steps_per_second": 25.033,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.03,
|
| 238 |
+
"learning_rate": 0.00019865319865319862,
|
| 239 |
+
"loss": 0.3412,
|
| 240 |
+
"step": 1600
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 4.03,
|
| 244 |
+
"eval_f1": 0.9459482392872296,
|
| 245 |
+
"eval_loss": 0.3307790160179138,
|
| 246 |
+
"eval_runtime": 496.5097,
|
| 247 |
+
"eval_samples_per_second": 50.037,
|
| 248 |
+
"eval_steps_per_second": 25.019,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.28,
|
| 253 |
+
"learning_rate": 0.00019023569023569022,
|
| 254 |
+
"loss": 0.3293,
|
| 255 |
+
"step": 1700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.28,
|
| 259 |
+
"eval_f1": 0.9459482392872296,
|
| 260 |
+
"eval_loss": 0.3313847482204437,
|
| 261 |
+
"eval_runtime": 496.395,
|
| 262 |
+
"eval_samples_per_second": 50.049,
|
| 263 |
+
"eval_steps_per_second": 25.024,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.54,
|
| 268 |
+
"learning_rate": 0.0001818181818181818,
|
| 269 |
+
"loss": 0.3346,
|
| 270 |
+
"step": 1800
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.54,
|
| 274 |
+
"eval_f1": 0.9459482392872296,
|
| 275 |
+
"eval_loss": 0.33080053329467773,
|
| 276 |
+
"eval_runtime": 496.4252,
|
| 277 |
+
"eval_samples_per_second": 50.046,
|
| 278 |
+
"eval_steps_per_second": 25.023,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 4.79,
|
| 283 |
+
"learning_rate": 0.0001734006734006734,
|
| 284 |
+
"loss": 0.3279,
|
| 285 |
+
"step": 1900
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 4.79,
|
| 289 |
+
"eval_f1": 0.9459482392872296,
|
| 290 |
+
"eval_loss": 0.3317018449306488,
|
| 291 |
+
"eval_runtime": 496.5163,
|
| 292 |
+
"eval_samples_per_second": 50.037,
|
| 293 |
+
"eval_steps_per_second": 25.018,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.04,
|
| 298 |
+
"learning_rate": 0.000164983164983165,
|
| 299 |
+
"loss": 0.3246,
|
| 300 |
+
"step": 2000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 5.04,
|
| 304 |
+
"eval_f1": 0.9459482392872296,
|
| 305 |
+
"eval_loss": 0.33184757828712463,
|
| 306 |
+
"eval_runtime": 496.5592,
|
| 307 |
+
"eval_samples_per_second": 50.032,
|
| 308 |
+
"eval_steps_per_second": 25.016,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 5.29,
|
| 313 |
+
"learning_rate": 0.00015656565656565653,
|
| 314 |
+
"loss": 0.3373,
|
| 315 |
+
"step": 2100
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 5.29,
|
| 319 |
+
"eval_f1": 0.9459482392872296,
|
| 320 |
+
"eval_loss": 0.33109256625175476,
|
| 321 |
+
"eval_runtime": 496.5149,
|
| 322 |
+
"eval_samples_per_second": 50.037,
|
| 323 |
+
"eval_steps_per_second": 25.018,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 5.55,
|
| 328 |
+
"learning_rate": 0.00014814814814814812,
|
| 329 |
+
"loss": 0.3262,
|
| 330 |
+
"step": 2200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 5.55,
|
| 334 |
+
"eval_f1": 0.9459482392872296,
|
| 335 |
+
"eval_loss": 0.33351102471351624,
|
| 336 |
+
"eval_runtime": 496.6308,
|
| 337 |
+
"eval_samples_per_second": 50.025,
|
| 338 |
+
"eval_steps_per_second": 25.013,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 5.8,
|
| 343 |
+
"learning_rate": 0.0001397306397306397,
|
| 344 |
+
"loss": 0.3279,
|
| 345 |
+
"step": 2300
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 5.8,
|
| 349 |
+
"eval_f1": 0.9459482392872296,
|
| 350 |
+
"eval_loss": 0.3326103985309601,
|
| 351 |
+
"eval_runtime": 496.8717,
|
| 352 |
+
"eval_samples_per_second": 50.001,
|
| 353 |
+
"eval_steps_per_second": 25.0,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 6.05,
|
| 358 |
+
"learning_rate": 0.0001313131313131313,
|
| 359 |
+
"loss": 0.3298,
|
| 360 |
+
"step": 2400
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 6.05,
|
| 364 |
+
"eval_f1": 0.9459482392872296,
|
| 365 |
+
"eval_loss": 0.3322770297527313,
|
| 366 |
+
"eval_runtime": 496.7239,
|
| 367 |
+
"eval_samples_per_second": 50.016,
|
| 368 |
+
"eval_steps_per_second": 25.008,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 6.3,
|
| 373 |
+
"learning_rate": 0.0001228956228956229,
|
| 374 |
+
"loss": 0.3397,
|
| 375 |
+
"step": 2500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 6.3,
|
| 379 |
+
"eval_f1": 0.9459482392872296,
|
| 380 |
+
"eval_loss": 0.3311246633529663,
|
| 381 |
+
"eval_runtime": 496.772,
|
| 382 |
+
"eval_samples_per_second": 50.011,
|
| 383 |
+
"eval_steps_per_second": 25.005,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 6.55,
|
| 388 |
+
"learning_rate": 0.00011447811447811446,
|
| 389 |
+
"loss": 0.3312,
|
| 390 |
+
"step": 2600
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 6.55,
|
| 394 |
+
"eval_f1": 0.9459482392872296,
|
| 395 |
+
"eval_loss": 0.33860132098197937,
|
| 396 |
+
"eval_runtime": 496.8085,
|
| 397 |
+
"eval_samples_per_second": 50.007,
|
| 398 |
+
"eval_steps_per_second": 25.004,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 6.81,
|
| 403 |
+
"learning_rate": 0.00010606060606060605,
|
| 404 |
+
"loss": 0.3291,
|
| 405 |
+
"step": 2700
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 6.81,
|
| 409 |
+
"eval_f1": 0.9459482392872296,
|
| 410 |
+
"eval_loss": 0.3316628634929657,
|
| 411 |
+
"eval_runtime": 496.6873,
|
| 412 |
+
"eval_samples_per_second": 50.019,
|
| 413 |
+
"eval_steps_per_second": 25.01,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 7.06,
|
| 418 |
+
"learning_rate": 9.764309764309764e-05,
|
| 419 |
+
"loss": 0.3146,
|
| 420 |
+
"step": 2800
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 7.06,
|
| 424 |
+
"eval_f1": 0.9459482392872296,
|
| 425 |
+
"eval_loss": 0.33230647444725037,
|
| 426 |
+
"eval_runtime": 496.6634,
|
| 427 |
+
"eval_samples_per_second": 50.022,
|
| 428 |
+
"eval_steps_per_second": 25.011,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 7.31,
|
| 433 |
+
"learning_rate": 8.92255892255892e-05,
|
| 434 |
+
"loss": 0.3296,
|
| 435 |
+
"step": 2900
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 7.31,
|
| 439 |
+
"eval_f1": 0.9459482392872296,
|
| 440 |
+
"eval_loss": 0.3313485085964203,
|
| 441 |
+
"eval_runtime": 496.6247,
|
| 442 |
+
"eval_samples_per_second": 50.026,
|
| 443 |
+
"eval_steps_per_second": 25.013,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 7.56,
|
| 448 |
+
"learning_rate": 8.08080808080808e-05,
|
| 449 |
+
"loss": 0.3367,
|
| 450 |
+
"step": 3000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 7.56,
|
| 454 |
+
"eval_f1": 0.9459482392872296,
|
| 455 |
+
"eval_loss": 0.33174964785575867,
|
| 456 |
+
"eval_runtime": 496.735,
|
| 457 |
+
"eval_samples_per_second": 50.015,
|
| 458 |
+
"eval_steps_per_second": 25.007,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 7.81,
|
| 463 |
+
"learning_rate": 7.239057239057239e-05,
|
| 464 |
+
"loss": 0.3232,
|
| 465 |
+
"step": 3100
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 7.81,
|
| 469 |
+
"eval_f1": 0.9459482392872296,
|
| 470 |
+
"eval_loss": 0.3318324387073517,
|
| 471 |
+
"eval_runtime": 496.5843,
|
| 472 |
+
"eval_samples_per_second": 50.03,
|
| 473 |
+
"eval_steps_per_second": 25.015,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 8.07,
|
| 478 |
+
"learning_rate": 6.397306397306397e-05,
|
| 479 |
+
"loss": 0.3314,
|
| 480 |
+
"step": 3200
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 8.07,
|
| 484 |
+
"eval_f1": 0.9459482392872296,
|
| 485 |
+
"eval_loss": 0.3325050175189972,
|
| 486 |
+
"eval_runtime": 496.7125,
|
| 487 |
+
"eval_samples_per_second": 50.017,
|
| 488 |
+
"eval_steps_per_second": 25.008,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 8.32,
|
| 493 |
+
"learning_rate": 5.5555555555555545e-05,
|
| 494 |
+
"loss": 0.3201,
|
| 495 |
+
"step": 3300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 8.32,
|
| 499 |
+
"eval_f1": 0.9459482392872296,
|
| 500 |
+
"eval_loss": 0.33225715160369873,
|
| 501 |
+
"eval_runtime": 496.6425,
|
| 502 |
+
"eval_samples_per_second": 50.024,
|
| 503 |
+
"eval_steps_per_second": 25.012,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 8.57,
|
| 508 |
+
"learning_rate": 4.7138047138047136e-05,
|
| 509 |
+
"loss": 0.3301,
|
| 510 |
+
"step": 3400
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 8.57,
|
| 514 |
+
"eval_f1": 0.9459482392872296,
|
| 515 |
+
"eval_loss": 0.3346656262874603,
|
| 516 |
+
"eval_runtime": 496.595,
|
| 517 |
+
"eval_samples_per_second": 50.029,
|
| 518 |
+
"eval_steps_per_second": 25.014,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 8.82,
|
| 523 |
+
"learning_rate": 3.8720538720538714e-05,
|
| 524 |
+
"loss": 0.3268,
|
| 525 |
+
"step": 3500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 8.82,
|
| 529 |
+
"eval_f1": 0.9459482392872296,
|
| 530 |
+
"eval_loss": 0.33254188299179077,
|
| 531 |
+
"eval_runtime": 496.5109,
|
| 532 |
+
"eval_samples_per_second": 50.037,
|
| 533 |
+
"eval_steps_per_second": 25.019,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 9.07,
|
| 538 |
+
"learning_rate": 3.03030303030303e-05,
|
| 539 |
+
"loss": 0.3361,
|
| 540 |
+
"step": 3600
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 9.07,
|
| 544 |
+
"eval_f1": 0.9459482392872296,
|
| 545 |
+
"eval_loss": 0.33214762806892395,
|
| 546 |
+
"eval_runtime": 496.8406,
|
| 547 |
+
"eval_samples_per_second": 50.004,
|
| 548 |
+
"eval_steps_per_second": 25.002,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 9.33,
|
| 553 |
+
"learning_rate": 2.1885521885521884e-05,
|
| 554 |
+
"loss": 0.3395,
|
| 555 |
+
"step": 3700
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 9.33,
|
| 559 |
+
"eval_f1": 0.9459482392872296,
|
| 560 |
+
"eval_loss": 0.3312663733959198,
|
| 561 |
+
"eval_runtime": 496.7467,
|
| 562 |
+
"eval_samples_per_second": 50.013,
|
| 563 |
+
"eval_steps_per_second": 25.007,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 9.58,
|
| 568 |
+
"learning_rate": 1.3468013468013465e-05,
|
| 569 |
+
"loss": 0.3231,
|
| 570 |
+
"step": 3800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 9.58,
|
| 574 |
+
"eval_f1": 0.9459482392872296,
|
| 575 |
+
"eval_loss": 0.3319169878959656,
|
| 576 |
+
"eval_runtime": 496.7702,
|
| 577 |
+
"eval_samples_per_second": 50.011,
|
| 578 |
+
"eval_steps_per_second": 25.006,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 9.83,
|
| 583 |
+
"learning_rate": 5.05050505050505e-06,
|
| 584 |
+
"loss": 0.3197,
|
| 585 |
+
"step": 3900
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 9.83,
|
| 589 |
+
"eval_f1": 0.9459482392872296,
|
| 590 |
+
"eval_loss": 0.3325766921043396,
|
| 591 |
+
"eval_runtime": 496.6934,
|
| 592 |
+
"eval_samples_per_second": 50.019,
|
| 593 |
+
"eval_steps_per_second": 25.009,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 9.98,
|
| 598 |
+
"step": 3960,
|
| 599 |
+
"total_flos": 1.506420070651024e+19,
|
| 600 |
+
"train_loss": 0.32019265878080116,
|
| 601 |
+
"train_runtime": 22716.823,
|
| 602 |
+
"train_samples_per_second": 11.172,
|
| 603 |
+
"train_steps_per_second": 0.174
|
| 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 |
+
}
|