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_01-47-45_indolem-petl-vm/events.out.tfevents.1716602914.indolem-petl-vm.1850316.1 +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": 0.9579151346516943,
|
| 4 |
+
"eval_f1": 0.8007549204637368,
|
| 5 |
+
"eval_loss": 0.12812790274620056,
|
| 6 |
+
"eval_precision": 0.7469818913480886,
|
| 7 |
+
"eval_recall": 0.862870424171993,
|
| 8 |
+
"eval_runtime": 4.4357,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 210.789,
|
| 11 |
+
"eval_steps_per_second": 3.382,
|
| 12 |
+
"predict_accuracy": 0.9712612472851381,
|
| 13 |
+
"predict_f1": 0.8405215646940823,
|
| 14 |
+
"predict_loss": 0.08679515868425369,
|
| 15 |
+
"predict_precision": 0.7987714467273883,
|
| 16 |
+
"predict_recall": 0.8868767638758231,
|
| 17 |
+
"predict_runtime": 10.4912,
|
| 18 |
+
"predict_samples_per_second": 223.33,
|
| 19 |
+
"predict_steps_per_second": 3.527,
|
| 20 |
+
"train_loss": 0.1551312410470211,
|
| 21 |
+
"train_runtime": 1231.1625,
|
| 22 |
+
"train_samples": 8437,
|
| 23 |
+
"train_samples_per_second": 137.057,
|
| 24 |
+
"train_steps_per_second": 8.577
|
| 25 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9579151346516943,
|
| 4 |
+
"eval_f1": 0.8007549204637368,
|
| 5 |
+
"eval_loss": 0.12812790274620056,
|
| 6 |
+
"eval_precision": 0.7469818913480886,
|
| 7 |
+
"eval_recall": 0.862870424171993,
|
| 8 |
+
"eval_runtime": 4.4357,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 210.789,
|
| 11 |
+
"eval_steps_per_second": 3.382
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.9712612472851381,
|
| 3 |
+
"predict_f1": 0.8405215646940823,
|
| 4 |
+
"predict_loss": 0.08679515868425369,
|
| 5 |
+
"predict_precision": 0.7987714467273883,
|
| 6 |
+
"predict_recall": 0.8868767638758231,
|
| 7 |
+
"predict_runtime": 10.4912,
|
| 8 |
+
"predict_samples_per_second": 223.33,
|
| 9 |
+
"predict_steps_per_second": 3.527
|
| 10 |
+
}
|
predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/May25_01-47-45_indolem-petl-vm/events.out.tfevents.1716602914.indolem-petl-vm.1850316.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f248e40ca755260f006772560562bd582459c326bfa66a6ede1013b923418acd
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.1551312410470211,
|
| 4 |
+
"train_runtime": 1231.1625,
|
| 5 |
+
"train_samples": 8437,
|
| 6 |
+
"train_samples_per_second": 137.057,
|
| 7 |
+
"train_steps_per_second": 8.577
|
| 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": 1.3427704572677612,
|
| 14 |
+
"learning_rate": 4.75e-05,
|
| 15 |
+
"loss": 0.7018,
|
| 16 |
+
"step": 528
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.9115075027327835,
|
| 21 |
+
"eval_f1": 0.5138413685847589,
|
| 22 |
+
"eval_loss": 0.33528366684913635,
|
| 23 |
+
"eval_precision": 0.5528781793842035,
|
| 24 |
+
"eval_recall": 0.4799535153980244,
|
| 25 |
+
"eval_runtime": 4.4519,
|
| 26 |
+
"eval_samples_per_second": 210.021,
|
| 27 |
+
"eval_steps_per_second": 3.369,
|
| 28 |
+
"step": 528
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 1.260859727859497,
|
| 33 |
+
"learning_rate": 4.5e-05,
|
| 34 |
+
"loss": 0.2639,
|
| 35 |
+
"step": 1056
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9412203120341847,
|
| 40 |
+
"eval_f1": 0.7251732101616628,
|
| 41 |
+
"eval_loss": 0.1912250965833664,
|
| 42 |
+
"eval_precision": 0.6493566176470589,
|
| 43 |
+
"eval_recall": 0.821034282393957,
|
| 44 |
+
"eval_runtime": 4.5644,
|
| 45 |
+
"eval_samples_per_second": 204.846,
|
| 46 |
+
"eval_steps_per_second": 3.286,
|
| 47 |
+
"step": 1056
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 2.1796255111694336,
|
| 52 |
+
"learning_rate": 4.25e-05,
|
| 53 |
+
"loss": 0.1862,
|
| 54 |
+
"step": 1584
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.9465865050183842,
|
| 59 |
+
"eval_f1": 0.7531402204562931,
|
| 60 |
+
"eval_loss": 0.1671685427427292,
|
| 61 |
+
"eval_precision": 0.6738532110091743,
|
| 62 |
+
"eval_recall": 0.8535735037768739,
|
| 63 |
+
"eval_runtime": 4.5056,
|
| 64 |
+
"eval_samples_per_second": 207.52,
|
| 65 |
+
"eval_steps_per_second": 3.329,
|
| 66 |
+
"step": 1584
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 2.1285958290100098,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.1612,
|
| 73 |
+
"step": 2112
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.9539401768856206,
|
| 78 |
+
"eval_f1": 0.7823765020026703,
|
| 79 |
+
"eval_loss": 0.14461010694503784,
|
| 80 |
+
"eval_precision": 0.7238142292490118,
|
| 81 |
+
"eval_recall": 0.8512492736780941,
|
| 82 |
+
"eval_runtime": 4.5298,
|
| 83 |
+
"eval_samples_per_second": 206.41,
|
| 84 |
+
"eval_steps_per_second": 3.311,
|
| 85 |
+
"step": 2112
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 1.1812392473220825,
|
| 90 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 91 |
+
"loss": 0.1439,
|
| 92 |
+
"step": 2640
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9545364205505317,
|
| 97 |
+
"eval_f1": 0.7862656374767102,
|
| 98 |
+
"eval_loss": 0.13903872668743134,
|
| 99 |
+
"eval_precision": 0.7254420432220039,
|
| 100 |
+
"eval_recall": 0.8582219639744335,
|
| 101 |
+
"eval_runtime": 4.6125,
|
| 102 |
+
"eval_samples_per_second": 202.712,
|
| 103 |
+
"eval_steps_per_second": 3.252,
|
| 104 |
+
"step": 2640
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 1.9920209646224976,
|
| 109 |
+
"learning_rate": 3.5e-05,
|
| 110 |
+
"loss": 0.1358,
|
| 111 |
+
"step": 3168
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.9551326642154427,
|
| 116 |
+
"eval_f1": 0.7892923403127484,
|
| 117 |
+
"eval_loss": 0.1392282098531723,
|
| 118 |
+
"eval_precision": 0.7256335282651072,
|
| 119 |
+
"eval_recall": 0.8651946542707728,
|
| 120 |
+
"eval_runtime": 4.8436,
|
| 121 |
+
"eval_samples_per_second": 193.037,
|
| 122 |
+
"eval_steps_per_second": 3.097,
|
| 123 |
+
"step": 3168
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 2.6399483680725098,
|
| 128 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 129 |
+
"loss": 0.129,
|
| 130 |
+
"step": 3696
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.9561264036569611,
|
| 135 |
+
"eval_f1": 0.7918540068764879,
|
| 136 |
+
"eval_loss": 0.13837336003780365,
|
| 137 |
+
"eval_precision": 0.7266990291262136,
|
| 138 |
+
"eval_recall": 0.8698431144683324,
|
| 139 |
+
"eval_runtime": 4.5425,
|
| 140 |
+
"eval_samples_per_second": 205.834,
|
| 141 |
+
"eval_steps_per_second": 3.302,
|
| 142 |
+
"step": 3696
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.901687741279602,
|
| 147 |
+
"learning_rate": 3e-05,
|
| 148 |
+
"loss": 0.1228,
|
| 149 |
+
"step": 4224
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.957517638875087,
|
| 154 |
+
"eval_f1": 0.7969124301304232,
|
| 155 |
+
"eval_loss": 0.13390584290027618,
|
| 156 |
+
"eval_precision": 0.7352652259332023,
|
| 157 |
+
"eval_recall": 0.8698431144683324,
|
| 158 |
+
"eval_runtime": 4.5586,
|
| 159 |
+
"eval_samples_per_second": 205.105,
|
| 160 |
+
"eval_steps_per_second": 3.29,
|
| 161 |
+
"step": 4224
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 1.3437026739120483,
|
| 166 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 167 |
+
"loss": 0.1168,
|
| 168 |
+
"step": 4752
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.0,
|
| 172 |
+
"eval_accuracy": 0.9577163867633907,
|
| 173 |
+
"eval_f1": 0.7960010807889759,
|
| 174 |
+
"eval_loss": 0.13209262490272522,
|
| 175 |
+
"eval_precision": 0.7439393939393939,
|
| 176 |
+
"eval_recall": 0.8558977338756537,
|
| 177 |
+
"eval_runtime": 4.5415,
|
| 178 |
+
"eval_samples_per_second": 205.88,
|
| 179 |
+
"eval_steps_per_second": 3.303,
|
| 180 |
+
"step": 4752
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 3.851469039916992,
|
| 185 |
+
"learning_rate": 2.5e-05,
|
| 186 |
+
"loss": 0.1146,
|
| 187 |
+
"step": 5280
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.958113882539998,
|
| 192 |
+
"eval_f1": 0.7973009446693656,
|
| 193 |
+
"eval_loss": 0.12995323538780212,
|
| 194 |
+
"eval_precision": 0.7444556451612904,
|
| 195 |
+
"eval_recall": 0.8582219639744335,
|
| 196 |
+
"eval_runtime": 4.5491,
|
| 197 |
+
"eval_samples_per_second": 205.534,
|
| 198 |
+
"eval_steps_per_second": 3.297,
|
| 199 |
+
"step": 5280
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 2.413081645965576,
|
| 204 |
+
"learning_rate": 2.25e-05,
|
| 205 |
+
"loss": 0.1105,
|
| 206 |
+
"step": 5808
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.9571201430984796,
|
| 211 |
+
"eval_f1": 0.7947830715996806,
|
| 212 |
+
"eval_loss": 0.13270916044712067,
|
| 213 |
+
"eval_precision": 0.7333005893909627,
|
| 214 |
+
"eval_recall": 0.8675188843695526,
|
| 215 |
+
"eval_runtime": 4.536,
|
| 216 |
+
"eval_samples_per_second": 206.127,
|
| 217 |
+
"eval_steps_per_second": 3.307,
|
| 218 |
+
"step": 5808
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 12.0,
|
| 222 |
+
"grad_norm": 1.1331512928009033,
|
| 223 |
+
"learning_rate": 2e-05,
|
| 224 |
+
"loss": 0.1083,
|
| 225 |
+
"step": 6336
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 12.0,
|
| 229 |
+
"eval_accuracy": 0.9569213952101759,
|
| 230 |
+
"eval_f1": 0.794345158708989,
|
| 231 |
+
"eval_loss": 0.1333465278148651,
|
| 232 |
+
"eval_precision": 0.7342209072978304,
|
| 233 |
+
"eval_recall": 0.8651946542707728,
|
| 234 |
+
"eval_runtime": 4.5053,
|
| 235 |
+
"eval_samples_per_second": 207.533,
|
| 236 |
+
"eval_steps_per_second": 3.329,
|
| 237 |
+
"step": 6336
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 13.0,
|
| 241 |
+
"grad_norm": 1.8731575012207031,
|
| 242 |
+
"learning_rate": 1.75e-05,
|
| 243 |
+
"loss": 0.106,
|
| 244 |
+
"step": 6864
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 13.0,
|
| 248 |
+
"eval_accuracy": 0.9591076219815164,
|
| 249 |
+
"eval_f1": 0.7998916869753587,
|
| 250 |
+
"eval_loss": 0.12651574611663818,
|
| 251 |
+
"eval_precision": 0.7489858012170385,
|
| 252 |
+
"eval_recall": 0.8582219639744335,
|
| 253 |
+
"eval_runtime": 4.4726,
|
| 254 |
+
"eval_samples_per_second": 209.052,
|
| 255 |
+
"eval_steps_per_second": 3.354,
|
| 256 |
+
"step": 6864
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 14.0,
|
| 260 |
+
"grad_norm": 0.8700233697891235,
|
| 261 |
+
"learning_rate": 1.5e-05,
|
| 262 |
+
"loss": 0.1032,
|
| 263 |
+
"step": 7392
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 14.0,
|
| 267 |
+
"eval_accuracy": 0.9589088740932128,
|
| 268 |
+
"eval_f1": 0.7973009446693656,
|
| 269 |
+
"eval_loss": 0.12690864503383636,
|
| 270 |
+
"eval_precision": 0.7444556451612904,
|
| 271 |
+
"eval_recall": 0.8582219639744335,
|
| 272 |
+
"eval_runtime": 4.5513,
|
| 273 |
+
"eval_samples_per_second": 205.436,
|
| 274 |
+
"eval_steps_per_second": 3.296,
|
| 275 |
+
"step": 7392
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 15.0,
|
| 279 |
+
"grad_norm": 1.2827842235565186,
|
| 280 |
+
"learning_rate": 1.25e-05,
|
| 281 |
+
"loss": 0.1023,
|
| 282 |
+
"step": 7920
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.0,
|
| 286 |
+
"eval_accuracy": 0.9585113783166054,
|
| 287 |
+
"eval_f1": 0.7998922704012928,
|
| 288 |
+
"eval_loss": 0.12912563979625702,
|
| 289 |
+
"eval_precision": 0.7454819277108434,
|
| 290 |
+
"eval_recall": 0.862870424171993,
|
| 291 |
+
"eval_runtime": 4.5324,
|
| 292 |
+
"eval_samples_per_second": 206.293,
|
| 293 |
+
"eval_steps_per_second": 3.31,
|
| 294 |
+
"step": 7920
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.0,
|
| 298 |
+
"grad_norm": 1.694359302520752,
|
| 299 |
+
"learning_rate": 1e-05,
|
| 300 |
+
"loss": 0.1014,
|
| 301 |
+
"step": 8448
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 16.0,
|
| 305 |
+
"eval_accuracy": 0.957517638875087,
|
| 306 |
+
"eval_f1": 0.7947269303201507,
|
| 307 |
+
"eval_loss": 0.12707427144050598,
|
| 308 |
+
"eval_precision": 0.7399799599198397,
|
| 309 |
+
"eval_recall": 0.8582219639744335,
|
| 310 |
+
"eval_runtime": 4.562,
|
| 311 |
+
"eval_samples_per_second": 204.955,
|
| 312 |
+
"eval_steps_per_second": 3.288,
|
| 313 |
+
"step": 8448
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 17.0,
|
| 317 |
+
"grad_norm": 1.139172911643982,
|
| 318 |
+
"learning_rate": 7.5e-06,
|
| 319 |
+
"loss": 0.1002,
|
| 320 |
+
"step": 8976
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 17.0,
|
| 324 |
+
"eval_accuracy": 0.9589088740932128,
|
| 325 |
+
"eval_f1": 0.8041789445486203,
|
| 326 |
+
"eval_loss": 0.12810933589935303,
|
| 327 |
+
"eval_precision": 0.7460238568588469,
|
| 328 |
+
"eval_recall": 0.8721673445671121,
|
| 329 |
+
"eval_runtime": 4.5254,
|
| 330 |
+
"eval_samples_per_second": 206.614,
|
| 331 |
+
"eval_steps_per_second": 3.315,
|
| 332 |
+
"step": 8976
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.0,
|
| 336 |
+
"grad_norm": 1.6876777410507202,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.0986,
|
| 339 |
+
"step": 9504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.0,
|
| 343 |
+
"eval_accuracy": 0.9573188909867832,
|
| 344 |
+
"eval_f1": 0.8016021361815754,
|
| 345 |
+
"eval_loss": 0.13038571178913116,
|
| 346 |
+
"eval_precision": 0.741600790513834,
|
| 347 |
+
"eval_recall": 0.8721673445671121,
|
| 348 |
+
"eval_runtime": 4.5245,
|
| 349 |
+
"eval_samples_per_second": 206.653,
|
| 350 |
+
"eval_steps_per_second": 3.315,
|
| 351 |
+
"step": 9504
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 19.0,
|
| 355 |
+
"grad_norm": 0.5088372230529785,
|
| 356 |
+
"learning_rate": 2.5e-06,
|
| 357 |
+
"loss": 0.0978,
|
| 358 |
+
"step": 10032
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 19.0,
|
| 362 |
+
"eval_accuracy": 0.9589088740932128,
|
| 363 |
+
"eval_f1": 0.8046473925965956,
|
| 364 |
+
"eval_loss": 0.1270894557237625,
|
| 365 |
+
"eval_precision": 0.752020202020202,
|
| 366 |
+
"eval_recall": 0.8651946542707728,
|
| 367 |
+
"eval_runtime": 4.5248,
|
| 368 |
+
"eval_samples_per_second": 206.64,
|
| 369 |
+
"eval_steps_per_second": 3.315,
|
| 370 |
+
"step": 10032
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 20.0,
|
| 374 |
+
"grad_norm": 2.988950490951538,
|
| 375 |
+
"learning_rate": 0.0,
|
| 376 |
+
"loss": 0.0984,
|
| 377 |
+
"step": 10560
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 20.0,
|
| 381 |
+
"eval_accuracy": 0.9579151346516943,
|
| 382 |
+
"eval_f1": 0.8007549204637368,
|
| 383 |
+
"eval_loss": 0.12812790274620056,
|
| 384 |
+
"eval_precision": 0.7469818913480886,
|
| 385 |
+
"eval_recall": 0.862870424171993,
|
| 386 |
+
"eval_runtime": 4.5277,
|
| 387 |
+
"eval_samples_per_second": 206.507,
|
| 388 |
+
"eval_steps_per_second": 3.313,
|
| 389 |
+
"step": 10560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 20.0,
|
| 393 |
+
"step": 10560,
|
| 394 |
+
"total_flos": 4552961808488766.0,
|
| 395 |
+
"train_loss": 0.1551312410470211,
|
| 396 |
+
"train_runtime": 1231.1625,
|
| 397 |
+
"train_samples_per_second": 137.057,
|
| 398 |
+
"train_steps_per_second": 8.577
|
| 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": 4552961808488766.0,
|
| 407 |
+
"train_batch_size": 16,
|
| 408 |
+
"trial_name": null,
|
| 409 |
+
"trial_params": null
|
| 410 |
+
}
|