End of training
Browse files- README.md +2 -0
- all_results.json +25 -0
- eval_results.json +12 -0
- predict_results.json +10 -0
- predictions.txt +0 -0
- runs/May25_10-40-37_indolem-petl-vm/events.out.tfevents.1716634900.indolem-petl-vm.2110685.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +410 -0
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
base_model: indolem/indobert-base-uncased
|
| 4 |
tags:
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- id
|
| 4 |
license: mit
|
| 5 |
base_model: indolem/indobert-base-uncased
|
| 6 |
tags:
|
all_results.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9449965219119547,
|
| 4 |
+
"eval_f1": 0.7285333333333335,
|
| 5 |
+
"eval_loss": 0.16621001064777374,
|
| 6 |
+
"eval_precision": 0.6732380482996551,
|
| 7 |
+
"eval_recall": 0.7937245787332946,
|
| 8 |
+
"eval_runtime": 4.4648,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 209.418,
|
| 11 |
+
"eval_steps_per_second": 3.36,
|
| 12 |
+
"predict_accuracy": 0.948689109525287,
|
| 13 |
+
"predict_f1": 0.7123558484349258,
|
| 14 |
+
"predict_loss": 0.15243284404277802,
|
| 15 |
+
"predict_precision": 0.6682464454976303,
|
| 16 |
+
"predict_recall": 0.7626999059266227,
|
| 17 |
+
"predict_runtime": 10.3714,
|
| 18 |
+
"predict_samples_per_second": 225.909,
|
| 19 |
+
"predict_steps_per_second": 3.567,
|
| 20 |
+
"train_loss": 0.26384454712723243,
|
| 21 |
+
"train_runtime": 1246.4432,
|
| 22 |
+
"train_samples": 8437,
|
| 23 |
+
"train_samples_per_second": 135.377,
|
| 24 |
+
"train_steps_per_second": 8.472
|
| 25 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9449965219119547,
|
| 4 |
+
"eval_f1": 0.7285333333333335,
|
| 5 |
+
"eval_loss": 0.16621001064777374,
|
| 6 |
+
"eval_precision": 0.6732380482996551,
|
| 7 |
+
"eval_recall": 0.7937245787332946,
|
| 8 |
+
"eval_runtime": 4.4648,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 209.418,
|
| 11 |
+
"eval_steps_per_second": 3.36
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.948689109525287,
|
| 3 |
+
"predict_f1": 0.7123558484349258,
|
| 4 |
+
"predict_loss": 0.15243284404277802,
|
| 5 |
+
"predict_precision": 0.6682464454976303,
|
| 6 |
+
"predict_recall": 0.7626999059266227,
|
| 7 |
+
"predict_runtime": 10.3714,
|
| 8 |
+
"predict_samples_per_second": 225.909,
|
| 9 |
+
"predict_steps_per_second": 3.567
|
| 10 |
+
}
|
predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/May25_10-40-37_indolem-petl-vm/events.out.tfevents.1716634900.indolem-petl-vm.2110685.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f772210b3d346a03124a284fc71b3eada7162b6cfaceb54a75cbd32b4bfad0a0
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.26384454712723243,
|
| 4 |
+
"train_runtime": 1246.4432,
|
| 5 |
+
"train_samples": 8437,
|
| 6 |
+
"train_samples_per_second": 135.377,
|
| 7 |
+
"train_steps_per_second": 8.472
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10560,
|
| 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": 1.263325572013855,
|
| 14 |
+
"learning_rate": 4.75e-05,
|
| 15 |
+
"loss": 0.8173,
|
| 16 |
+
"step": 528
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.8480075524197556,
|
| 21 |
+
"eval_f1": 0.05425143453312468,
|
| 22 |
+
"eval_loss": 0.5014122128486633,
|
| 23 |
+
"eval_precision": 0.2653061224489796,
|
| 24 |
+
"eval_recall": 0.03021499128413713,
|
| 25 |
+
"eval_runtime": 3.9202,
|
| 26 |
+
"eval_samples_per_second": 238.51,
|
| 27 |
+
"eval_steps_per_second": 3.826,
|
| 28 |
+
"step": 528
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 1.040271520614624,
|
| 33 |
+
"learning_rate": 4.5e-05,
|
| 34 |
+
"loss": 0.4808,
|
| 35 |
+
"step": 1056
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.8941170625062109,
|
| 40 |
+
"eval_f1": 0.3863885839736554,
|
| 41 |
+
"eval_loss": 0.3564635217189789,
|
| 42 |
+
"eval_precision": 0.5217391304347826,
|
| 43 |
+
"eval_recall": 0.30679837303893087,
|
| 44 |
+
"eval_runtime": 4.2946,
|
| 45 |
+
"eval_samples_per_second": 217.716,
|
| 46 |
+
"eval_steps_per_second": 3.493,
|
| 47 |
+
"step": 1056
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 1.256822943687439,
|
| 52 |
+
"learning_rate": 4.25e-05,
|
| 53 |
+
"loss": 0.3767,
|
| 54 |
+
"step": 1584
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.919358044320779,
|
| 59 |
+
"eval_f1": 0.5637982195845698,
|
| 60 |
+
"eval_loss": 0.2893461287021637,
|
| 61 |
+
"eval_precision": 0.5761067313523347,
|
| 62 |
+
"eval_recall": 0.5520046484601976,
|
| 63 |
+
"eval_runtime": 4.4845,
|
| 64 |
+
"eval_samples_per_second": 208.498,
|
| 65 |
+
"eval_steps_per_second": 3.345,
|
| 66 |
+
"step": 1584
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 1.3887470960617065,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.3159,
|
| 73 |
+
"step": 2112
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.9279042035178376,
|
| 78 |
+
"eval_f1": 0.6389668725435149,
|
| 79 |
+
"eval_loss": 0.24789083003997803,
|
| 80 |
+
"eval_precision": 0.6181423139598045,
|
| 81 |
+
"eval_recall": 0.6612434631028472,
|
| 82 |
+
"eval_runtime": 4.6339,
|
| 83 |
+
"eval_samples_per_second": 201.774,
|
| 84 |
+
"eval_steps_per_second": 3.237,
|
| 85 |
+
"step": 2112
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 0.7730798125267029,
|
| 90 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 91 |
+
"loss": 0.2785,
|
| 92 |
+
"step": 2640
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9330716486137335,
|
| 97 |
+
"eval_f1": 0.6637314254265273,
|
| 98 |
+
"eval_loss": 0.2236042320728302,
|
| 99 |
+
"eval_precision": 0.6304234187140617,
|
| 100 |
+
"eval_recall": 0.7007553747821035,
|
| 101 |
+
"eval_runtime": 4.6093,
|
| 102 |
+
"eval_samples_per_second": 202.851,
|
| 103 |
+
"eval_steps_per_second": 3.254,
|
| 104 |
+
"step": 2640
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 1.3244330883026123,
|
| 109 |
+
"learning_rate": 3.5e-05,
|
| 110 |
+
"loss": 0.2527,
|
| 111 |
+
"step": 3168
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.9360528669382888,
|
| 116 |
+
"eval_f1": 0.6862425231103861,
|
| 117 |
+
"eval_loss": 0.20973308384418488,
|
| 118 |
+
"eval_precision": 0.6448645886561063,
|
| 119 |
+
"eval_recall": 0.7332945961650204,
|
| 120 |
+
"eval_runtime": 4.5728,
|
| 121 |
+
"eval_samples_per_second": 204.47,
|
| 122 |
+
"eval_steps_per_second": 3.28,
|
| 123 |
+
"step": 3168
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 1.106473684310913,
|
| 128 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 129 |
+
"loss": 0.2365,
|
| 130 |
+
"step": 3696
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.9376428500447183,
|
| 135 |
+
"eval_f1": 0.6923488496522204,
|
| 136 |
+
"eval_loss": 0.1997063159942627,
|
| 137 |
+
"eval_precision": 0.6415468517600397,
|
| 138 |
+
"eval_recall": 0.7518884369552585,
|
| 139 |
+
"eval_runtime": 4.5493,
|
| 140 |
+
"eval_samples_per_second": 205.525,
|
| 141 |
+
"eval_steps_per_second": 3.297,
|
| 142 |
+
"step": 3696
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.7820762991905212,
|
| 147 |
+
"learning_rate": 3e-05,
|
| 148 |
+
"loss": 0.2243,
|
| 149 |
+
"step": 4224
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.9394315810394515,
|
| 154 |
+
"eval_f1": 0.703166935050993,
|
| 155 |
+
"eval_loss": 0.19049784541130066,
|
| 156 |
+
"eval_precision": 0.6533665835411472,
|
| 157 |
+
"eval_recall": 0.7611853573503777,
|
| 158 |
+
"eval_runtime": 4.544,
|
| 159 |
+
"eval_samples_per_second": 205.764,
|
| 160 |
+
"eval_steps_per_second": 3.301,
|
| 161 |
+
"step": 4224
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 0.5380152463912964,
|
| 166 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 167 |
+
"loss": 0.2134,
|
| 168 |
+
"step": 4752
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.0,
|
| 172 |
+
"eval_accuracy": 0.9398290768160589,
|
| 173 |
+
"eval_f1": 0.7064464571124135,
|
| 174 |
+
"eval_loss": 0.18573088943958282,
|
| 175 |
+
"eval_precision": 0.6522380718150517,
|
| 176 |
+
"eval_recall": 0.7704822777454968,
|
| 177 |
+
"eval_runtime": 4.499,
|
| 178 |
+
"eval_samples_per_second": 207.826,
|
| 179 |
+
"eval_steps_per_second": 3.334,
|
| 180 |
+
"step": 4752
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 1.0374780893325806,
|
| 185 |
+
"learning_rate": 2.5e-05,
|
| 186 |
+
"loss": 0.2072,
|
| 187 |
+
"step": 5280
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.9418165556990957,
|
| 192 |
+
"eval_f1": 0.7126925119490174,
|
| 193 |
+
"eval_loss": 0.18140505254268646,
|
| 194 |
+
"eval_precision": 0.6562347188264058,
|
| 195 |
+
"eval_recall": 0.7797791981406159,
|
| 196 |
+
"eval_runtime": 4.8822,
|
| 197 |
+
"eval_samples_per_second": 191.511,
|
| 198 |
+
"eval_steps_per_second": 3.072,
|
| 199 |
+
"step": 5280
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 0.8238540291786194,
|
| 204 |
+
"learning_rate": 2.25e-05,
|
| 205 |
+
"loss": 0.2009,
|
| 206 |
+
"step": 5808
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.9426115472523104,
|
| 211 |
+
"eval_f1": 0.7149706979222165,
|
| 212 |
+
"eval_loss": 0.17563943564891815,
|
| 213 |
+
"eval_precision": 0.6601082144613871,
|
| 214 |
+
"eval_recall": 0.7797791981406159,
|
| 215 |
+
"eval_runtime": 4.6573,
|
| 216 |
+
"eval_samples_per_second": 200.759,
|
| 217 |
+
"eval_steps_per_second": 3.221,
|
| 218 |
+
"step": 5808
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 12.0,
|
| 222 |
+
"grad_norm": 1.7851293087005615,
|
| 223 |
+
"learning_rate": 2e-05,
|
| 224 |
+
"loss": 0.1962,
|
| 225 |
+
"step": 6336
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 12.0,
|
| 229 |
+
"eval_accuracy": 0.9436052866938289,
|
| 230 |
+
"eval_f1": 0.7161803713527852,
|
| 231 |
+
"eval_loss": 0.1738174557685852,
|
| 232 |
+
"eval_precision": 0.6588579795021962,
|
| 233 |
+
"eval_recall": 0.7844276583381755,
|
| 234 |
+
"eval_runtime": 4.5908,
|
| 235 |
+
"eval_samples_per_second": 203.669,
|
| 236 |
+
"eval_steps_per_second": 3.267,
|
| 237 |
+
"step": 6336
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 13.0,
|
| 241 |
+
"grad_norm": 1.3740888833999634,
|
| 242 |
+
"learning_rate": 1.75e-05,
|
| 243 |
+
"loss": 0.1921,
|
| 244 |
+
"step": 6864
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 13.0,
|
| 248 |
+
"eval_accuracy": 0.94420153035874,
|
| 249 |
+
"eval_f1": 0.7210164107993647,
|
| 250 |
+
"eval_loss": 0.17201030254364014,
|
| 251 |
+
"eval_precision": 0.6621293145357317,
|
| 252 |
+
"eval_recall": 0.7914003486345148,
|
| 253 |
+
"eval_runtime": 4.584,
|
| 254 |
+
"eval_samples_per_second": 203.972,
|
| 255 |
+
"eval_steps_per_second": 3.272,
|
| 256 |
+
"step": 6864
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 14.0,
|
| 260 |
+
"grad_norm": 0.6247196197509766,
|
| 261 |
+
"learning_rate": 1.5e-05,
|
| 262 |
+
"loss": 0.1887,
|
| 263 |
+
"step": 7392
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 14.0,
|
| 267 |
+
"eval_accuracy": 0.94420153035874,
|
| 268 |
+
"eval_f1": 0.7210164107993647,
|
| 269 |
+
"eval_loss": 0.1705305576324463,
|
| 270 |
+
"eval_precision": 0.6621293145357317,
|
| 271 |
+
"eval_recall": 0.7914003486345148,
|
| 272 |
+
"eval_runtime": 4.5864,
|
| 273 |
+
"eval_samples_per_second": 203.864,
|
| 274 |
+
"eval_steps_per_second": 3.271,
|
| 275 |
+
"step": 7392
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 15.0,
|
| 279 |
+
"grad_norm": 0.5709086060523987,
|
| 280 |
+
"learning_rate": 1.25e-05,
|
| 281 |
+
"loss": 0.1857,
|
| 282 |
+
"step": 7920
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.0,
|
| 286 |
+
"eval_accuracy": 0.944797774023651,
|
| 287 |
+
"eval_f1": 0.7254381306425917,
|
| 288 |
+
"eval_loss": 0.16876670718193054,
|
| 289 |
+
"eval_precision": 0.6679706601466993,
|
| 290 |
+
"eval_recall": 0.7937245787332946,
|
| 291 |
+
"eval_runtime": 4.4753,
|
| 292 |
+
"eval_samples_per_second": 208.925,
|
| 293 |
+
"eval_steps_per_second": 3.352,
|
| 294 |
+
"step": 7920
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.0,
|
| 298 |
+
"grad_norm": 0.8432120680809021,
|
| 299 |
+
"learning_rate": 1e-05,
|
| 300 |
+
"loss": 0.1846,
|
| 301 |
+
"step": 8448
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 16.0,
|
| 305 |
+
"eval_accuracy": 0.9449965219119547,
|
| 306 |
+
"eval_f1": 0.7283359914938863,
|
| 307 |
+
"eval_loss": 0.16835170984268188,
|
| 308 |
+
"eval_precision": 0.6712395884370407,
|
| 309 |
+
"eval_recall": 0.7960488088320744,
|
| 310 |
+
"eval_runtime": 4.493,
|
| 311 |
+
"eval_samples_per_second": 208.103,
|
| 312 |
+
"eval_steps_per_second": 3.339,
|
| 313 |
+
"step": 8448
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 17.0,
|
| 317 |
+
"grad_norm": 0.8022745251655579,
|
| 318 |
+
"learning_rate": 7.5e-06,
|
| 319 |
+
"loss": 0.1833,
|
| 320 |
+
"step": 8976
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 17.0,
|
| 324 |
+
"eval_accuracy": 0.9445990261353473,
|
| 325 |
+
"eval_f1": 0.7269824374667376,
|
| 326 |
+
"eval_loss": 0.16759617626667023,
|
| 327 |
+
"eval_precision": 0.6705940108001963,
|
| 328 |
+
"eval_recall": 0.7937245787332946,
|
| 329 |
+
"eval_runtime": 4.5329,
|
| 330 |
+
"eval_samples_per_second": 206.268,
|
| 331 |
+
"eval_steps_per_second": 3.309,
|
| 332 |
+
"step": 8976
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.0,
|
| 336 |
+
"grad_norm": 0.9574353694915771,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.1804,
|
| 339 |
+
"step": 9504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.0,
|
| 343 |
+
"eval_accuracy": 0.9445990261353473,
|
| 344 |
+
"eval_f1": 0.7277570591369206,
|
| 345 |
+
"eval_loss": 0.1666666567325592,
|
| 346 |
+
"eval_precision": 0.6719134284308903,
|
| 347 |
+
"eval_recall": 0.7937245787332946,
|
| 348 |
+
"eval_runtime": 4.5749,
|
| 349 |
+
"eval_samples_per_second": 204.377,
|
| 350 |
+
"eval_steps_per_second": 3.279,
|
| 351 |
+
"step": 9504
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 19.0,
|
| 355 |
+
"grad_norm": 0.7483543157577515,
|
| 356 |
+
"learning_rate": 2.5e-06,
|
| 357 |
+
"loss": 0.1816,
|
| 358 |
+
"step": 10032
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 19.0,
|
| 362 |
+
"eval_accuracy": 0.944797774023651,
|
| 363 |
+
"eval_f1": 0.7277570591369206,
|
| 364 |
+
"eval_loss": 0.1664123684167862,
|
| 365 |
+
"eval_precision": 0.6719134284308903,
|
| 366 |
+
"eval_recall": 0.7937245787332946,
|
| 367 |
+
"eval_runtime": 4.5817,
|
| 368 |
+
"eval_samples_per_second": 204.074,
|
| 369 |
+
"eval_steps_per_second": 3.274,
|
| 370 |
+
"step": 10032
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 20.0,
|
| 374 |
+
"grad_norm": 1.1839972734451294,
|
| 375 |
+
"learning_rate": 0.0,
|
| 376 |
+
"loss": 0.1801,
|
| 377 |
+
"step": 10560
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 20.0,
|
| 381 |
+
"eval_accuracy": 0.9449965219119547,
|
| 382 |
+
"eval_f1": 0.7285333333333335,
|
| 383 |
+
"eval_loss": 0.16621001064777374,
|
| 384 |
+
"eval_precision": 0.6732380482996551,
|
| 385 |
+
"eval_recall": 0.7937245787332946,
|
| 386 |
+
"eval_runtime": 4.5007,
|
| 387 |
+
"eval_samples_per_second": 207.747,
|
| 388 |
+
"eval_steps_per_second": 3.333,
|
| 389 |
+
"step": 10560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 20.0,
|
| 393 |
+
"step": 10560,
|
| 394 |
+
"total_flos": 4540180991527230.0,
|
| 395 |
+
"train_loss": 0.26384454712723243,
|
| 396 |
+
"train_runtime": 1246.4432,
|
| 397 |
+
"train_samples_per_second": 135.377,
|
| 398 |
+
"train_steps_per_second": 8.472
|
| 399 |
+
}
|
| 400 |
+
],
|
| 401 |
+
"logging_steps": 500,
|
| 402 |
+
"max_steps": 10560,
|
| 403 |
+
"num_input_tokens_seen": 0,
|
| 404 |
+
"num_train_epochs": 20,
|
| 405 |
+
"save_steps": 500,
|
| 406 |
+
"total_flos": 4540180991527230.0,
|
| 407 |
+
"train_batch_size": 16,
|
| 408 |
+
"trial_name": null,
|
| 409 |
+
"trial_params": null
|
| 410 |
+
}
|