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/May24_23-19-08_indolem-petl-vm/events.out.tfevents.1716593997.indolem-petl-vm.1782730.1 +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": 0.9573188909867832,
|
| 4 |
+
"eval_f1": 0.7943148297130599,
|
| 5 |
+
"eval_loss": 0.13019020855426788,
|
| 6 |
+
"eval_precision": 0.7375498007968128,
|
| 7 |
+
"eval_recall": 0.8605461940732132,
|
| 8 |
+
"eval_runtime": 4.4582,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 209.725,
|
| 11 |
+
"eval_steps_per_second": 3.365,
|
| 12 |
+
"predict_accuracy": 0.9678094942600062,
|
| 13 |
+
"predict_f1": 0.8218905472636817,
|
| 14 |
+
"predict_loss": 0.096980020403862,
|
| 15 |
+
"predict_precision": 0.7755059461715001,
|
| 16 |
+
"predict_recall": 0.8741768579492004,
|
| 17 |
+
"predict_runtime": 10.5258,
|
| 18 |
+
"predict_samples_per_second": 222.597,
|
| 19 |
+
"predict_steps_per_second": 3.515,
|
| 20 |
+
"train_loss": 0.17230618686387034,
|
| 21 |
+
"train_runtime": 1231.4857,
|
| 22 |
+
"train_samples": 8437,
|
| 23 |
+
"train_samples_per_second": 137.021,
|
| 24 |
+
"train_steps_per_second": 8.575
|
| 25 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9573188909867832,
|
| 4 |
+
"eval_f1": 0.7943148297130599,
|
| 5 |
+
"eval_loss": 0.13019020855426788,
|
| 6 |
+
"eval_precision": 0.7375498007968128,
|
| 7 |
+
"eval_recall": 0.8605461940732132,
|
| 8 |
+
"eval_runtime": 4.4582,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 209.725,
|
| 11 |
+
"eval_steps_per_second": 3.365
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.9678094942600062,
|
| 3 |
+
"predict_f1": 0.8218905472636817,
|
| 4 |
+
"predict_loss": 0.096980020403862,
|
| 5 |
+
"predict_precision": 0.7755059461715001,
|
| 6 |
+
"predict_recall": 0.8741768579492004,
|
| 7 |
+
"predict_runtime": 10.5258,
|
| 8 |
+
"predict_samples_per_second": 222.597,
|
| 9 |
+
"predict_steps_per_second": 3.515
|
| 10 |
+
}
|
predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/May24_23-19-08_indolem-petl-vm/events.out.tfevents.1716593997.indolem-petl-vm.1782730.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9356f1011a5a8b0f1e596ec54ee03a176429be8b2a232b565d8d87e49fe76970
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.17230618686387034,
|
| 4 |
+
"train_runtime": 1231.4857,
|
| 5 |
+
"train_samples": 8437,
|
| 6 |
+
"train_samples_per_second": 137.021,
|
| 7 |
+
"train_steps_per_second": 8.575
|
| 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": 1.2754160165786743,
|
| 14 |
+
"learning_rate": 4.75e-05,
|
| 15 |
+
"loss": 0.7665,
|
| 16 |
+
"step": 528
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.8710623074629832,
|
| 21 |
+
"eval_f1": 0.1887287024901704,
|
| 22 |
+
"eval_loss": 0.42895129323005676,
|
| 23 |
+
"eval_precision": 0.38028169014084506,
|
| 24 |
+
"eval_recall": 0.12550842533410808,
|
| 25 |
+
"eval_runtime": 4.4252,
|
| 26 |
+
"eval_samples_per_second": 211.289,
|
| 27 |
+
"eval_steps_per_second": 3.39,
|
| 28 |
+
"step": 528
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 0.9667028784751892,
|
| 33 |
+
"learning_rate": 4.5e-05,
|
| 34 |
+
"loss": 0.336,
|
| 35 |
+
"step": 1056
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9335188313624168,
|
| 40 |
+
"eval_f1": 0.6881609491875161,
|
| 41 |
+
"eval_loss": 0.21774514019489288,
|
| 42 |
+
"eval_precision": 0.6187384044526901,
|
| 43 |
+
"eval_recall": 0.7751307379430563,
|
| 44 |
+
"eval_runtime": 4.5416,
|
| 45 |
+
"eval_samples_per_second": 205.875,
|
| 46 |
+
"eval_steps_per_second": 3.303,
|
| 47 |
+
"step": 1056
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 1.0499272346496582,
|
| 52 |
+
"learning_rate": 4.25e-05,
|
| 53 |
+
"loss": 0.2067,
|
| 54 |
+
"step": 1584
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.9410215641458809,
|
| 59 |
+
"eval_f1": 0.7261015202267457,
|
| 60 |
+
"eval_loss": 0.17432348430156708,
|
| 61 |
+
"eval_precision": 0.6523148148148148,
|
| 62 |
+
"eval_recall": 0.8187100522951772,
|
| 63 |
+
"eval_runtime": 4.4942,
|
| 64 |
+
"eval_samples_per_second": 208.047,
|
| 65 |
+
"eval_steps_per_second": 3.338,
|
| 66 |
+
"step": 1584
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 1.841440200805664,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.1734,
|
| 73 |
+
"step": 2112
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.9499652191195469,
|
| 78 |
+
"eval_f1": 0.7669569807337029,
|
| 79 |
+
"eval_loss": 0.15249943733215332,
|
| 80 |
+
"eval_precision": 0.7026112185686654,
|
| 81 |
+
"eval_recall": 0.8442765833817548,
|
| 82 |
+
"eval_runtime": 4.5239,
|
| 83 |
+
"eval_samples_per_second": 206.681,
|
| 84 |
+
"eval_steps_per_second": 3.316,
|
| 85 |
+
"step": 2112
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 1.0053447484970093,
|
| 90 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 91 |
+
"loss": 0.1557,
|
| 92 |
+
"step": 2640
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9523501937791911,
|
| 97 |
+
"eval_f1": 0.7757479481069631,
|
| 98 |
+
"eval_loss": 0.14416351914405823,
|
| 99 |
+
"eval_precision": 0.7125486381322957,
|
| 100 |
+
"eval_recall": 0.8512492736780941,
|
| 101 |
+
"eval_runtime": 4.5118,
|
| 102 |
+
"eval_samples_per_second": 207.232,
|
| 103 |
+
"eval_steps_per_second": 3.325,
|
| 104 |
+
"step": 2640
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 1.2348506450653076,
|
| 109 |
+
"learning_rate": 3.5e-05,
|
| 110 |
+
"loss": 0.146,
|
| 111 |
+
"step": 3168
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.9519526980025838,
|
| 116 |
+
"eval_f1": 0.7780979827089337,
|
| 117 |
+
"eval_loss": 0.14452077448368073,
|
| 118 |
+
"eval_precision": 0.7084923664122137,
|
| 119 |
+
"eval_recall": 0.862870424171993,
|
| 120 |
+
"eval_runtime": 4.5381,
|
| 121 |
+
"eval_samples_per_second": 206.032,
|
| 122 |
+
"eval_steps_per_second": 3.305,
|
| 123 |
+
"step": 3168
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 2.4902212619781494,
|
| 128 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 129 |
+
"loss": 0.1397,
|
| 130 |
+
"step": 3696
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.9525489416674948,
|
| 135 |
+
"eval_f1": 0.7873728150273936,
|
| 136 |
+
"eval_loss": 0.14437128603458405,
|
| 137 |
+
"eval_precision": 0.7144886363636364,
|
| 138 |
+
"eval_recall": 0.8768158047646717,
|
| 139 |
+
"eval_runtime": 4.5286,
|
| 140 |
+
"eval_samples_per_second": 206.464,
|
| 141 |
+
"eval_steps_per_second": 3.312,
|
| 142 |
+
"step": 3696
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.4951108992099762,
|
| 147 |
+
"learning_rate": 3e-05,
|
| 148 |
+
"loss": 0.1338,
|
| 149 |
+
"step": 4224
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.9545364205505317,
|
| 154 |
+
"eval_f1": 0.7905745300503045,
|
| 155 |
+
"eval_loss": 0.1385926455259323,
|
| 156 |
+
"eval_precision": 0.7261673151750972,
|
| 157 |
+
"eval_recall": 0.8675188843695526,
|
| 158 |
+
"eval_runtime": 4.5445,
|
| 159 |
+
"eval_samples_per_second": 205.745,
|
| 160 |
+
"eval_steps_per_second": 3.301,
|
| 161 |
+
"step": 4224
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 1.3395795822143555,
|
| 166 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 167 |
+
"loss": 0.1277,
|
| 168 |
+
"step": 4752
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.0,
|
| 172 |
+
"eval_accuracy": 0.9561264036569611,
|
| 173 |
+
"eval_f1": 0.7964601769911505,
|
| 174 |
+
"eval_loss": 0.13648679852485657,
|
| 175 |
+
"eval_precision": 0.7395418326693227,
|
| 176 |
+
"eval_recall": 0.862870424171993,
|
| 177 |
+
"eval_runtime": 4.5645,
|
| 178 |
+
"eval_samples_per_second": 204.841,
|
| 179 |
+
"eval_steps_per_second": 3.286,
|
| 180 |
+
"step": 4752
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 2.1327812671661377,
|
| 185 |
+
"learning_rate": 2.5e-05,
|
| 186 |
+
"loss": 0.1255,
|
| 187 |
+
"step": 5280
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.9562754645731889,
|
| 192 |
+
"eval_f1": 0.7936932121859969,
|
| 193 |
+
"eval_loss": 0.1332310438156128,
|
| 194 |
+
"eval_precision": 0.7347847600197922,
|
| 195 |
+
"eval_recall": 0.862870424171993,
|
| 196 |
+
"eval_runtime": 4.5032,
|
| 197 |
+
"eval_samples_per_second": 207.631,
|
| 198 |
+
"eval_steps_per_second": 3.331,
|
| 199 |
+
"step": 5280
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 11.329936027526855,
|
| 204 |
+
"learning_rate": 2.25e-05,
|
| 205 |
+
"loss": 0.1215,
|
| 206 |
+
"step": 5808
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.9557289078803538,
|
| 211 |
+
"eval_f1": 0.7884564469155414,
|
| 212 |
+
"eval_loss": 0.1330229640007019,
|
| 213 |
+
"eval_precision": 0.7242217898832685,
|
| 214 |
+
"eval_recall": 0.8651946542707728,
|
| 215 |
+
"eval_runtime": 4.5095,
|
| 216 |
+
"eval_samples_per_second": 207.339,
|
| 217 |
+
"eval_steps_per_second": 3.326,
|
| 218 |
+
"step": 5808
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 12.0,
|
| 222 |
+
"grad_norm": 1.500403642654419,
|
| 223 |
+
"learning_rate": 2e-05,
|
| 224 |
+
"loss": 0.1189,
|
| 225 |
+
"step": 6336
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 12.0,
|
| 229 |
+
"eval_accuracy": 0.9561264036569611,
|
| 230 |
+
"eval_f1": 0.794345158708989,
|
| 231 |
+
"eval_loss": 0.13398447632789612,
|
| 232 |
+
"eval_precision": 0.7342209072978304,
|
| 233 |
+
"eval_recall": 0.8651946542707728,
|
| 234 |
+
"eval_runtime": 4.535,
|
| 235 |
+
"eval_samples_per_second": 206.173,
|
| 236 |
+
"eval_steps_per_second": 3.308,
|
| 237 |
+
"step": 6336
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 13.0,
|
| 241 |
+
"grad_norm": 1.2570128440856934,
|
| 242 |
+
"learning_rate": 1.75e-05,
|
| 243 |
+
"loss": 0.1179,
|
| 244 |
+
"step": 6864
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 13.0,
|
| 248 |
+
"eval_accuracy": 0.9571201430984796,
|
| 249 |
+
"eval_f1": 0.7973009446693656,
|
| 250 |
+
"eval_loss": 0.12948381900787354,
|
| 251 |
+
"eval_precision": 0.7444556451612904,
|
| 252 |
+
"eval_recall": 0.8582219639744335,
|
| 253 |
+
"eval_runtime": 4.5144,
|
| 254 |
+
"eval_samples_per_second": 207.115,
|
| 255 |
+
"eval_steps_per_second": 3.323,
|
| 256 |
+
"step": 6864
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 14.0,
|
| 260 |
+
"grad_norm": 0.9663475751876831,
|
| 261 |
+
"learning_rate": 1.5e-05,
|
| 262 |
+
"loss": 0.114,
|
| 263 |
+
"step": 7392
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 14.0,
|
| 267 |
+
"eval_accuracy": 0.9578654476796185,
|
| 268 |
+
"eval_f1": 0.8013955984970478,
|
| 269 |
+
"eval_loss": 0.1294805407524109,
|
| 270 |
+
"eval_precision": 0.7446384039900249,
|
| 271 |
+
"eval_recall": 0.8675188843695526,
|
| 272 |
+
"eval_runtime": 4.4959,
|
| 273 |
+
"eval_samples_per_second": 207.965,
|
| 274 |
+
"eval_steps_per_second": 3.336,
|
| 275 |
+
"step": 7392
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 15.0,
|
| 279 |
+
"grad_norm": 1.1781103610992432,
|
| 280 |
+
"learning_rate": 1.25e-05,
|
| 281 |
+
"loss": 0.1128,
|
| 282 |
+
"step": 7920
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.0,
|
| 286 |
+
"eval_accuracy": 0.9571201430984796,
|
| 287 |
+
"eval_f1": 0.7960438385458433,
|
| 288 |
+
"eval_loss": 0.13167551159858704,
|
| 289 |
+
"eval_precision": 0.7371287128712871,
|
| 290 |
+
"eval_recall": 0.8651946542707728,
|
| 291 |
+
"eval_runtime": 4.5425,
|
| 292 |
+
"eval_samples_per_second": 205.835,
|
| 293 |
+
"eval_steps_per_second": 3.302,
|
| 294 |
+
"step": 7920
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.0,
|
| 298 |
+
"grad_norm": 1.9357908964157104,
|
| 299 |
+
"learning_rate": 1e-05,
|
| 300 |
+
"loss": 0.1115,
|
| 301 |
+
"step": 8448
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 16.0,
|
| 305 |
+
"eval_accuracy": 0.957517638875087,
|
| 306 |
+
"eval_f1": 0.7973297730307075,
|
| 307 |
+
"eval_loss": 0.12998828291893005,
|
| 308 |
+
"eval_precision": 0.7376482213438735,
|
| 309 |
+
"eval_recall": 0.8675188843695526,
|
| 310 |
+
"eval_runtime": 4.9608,
|
| 311 |
+
"eval_samples_per_second": 188.477,
|
| 312 |
+
"eval_steps_per_second": 3.024,
|
| 313 |
+
"step": 8448
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 17.0,
|
| 317 |
+
"grad_norm": 1.123679280281067,
|
| 318 |
+
"learning_rate": 7.5e-06,
|
| 319 |
+
"loss": 0.1109,
|
| 320 |
+
"step": 8976
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 17.0,
|
| 324 |
+
"eval_accuracy": 0.9577163867633907,
|
| 325 |
+
"eval_f1": 0.7951935914552738,
|
| 326 |
+
"eval_loss": 0.13070179522037506,
|
| 327 |
+
"eval_precision": 0.7356719367588933,
|
| 328 |
+
"eval_recall": 0.8651946542707728,
|
| 329 |
+
"eval_runtime": 4.4894,
|
| 330 |
+
"eval_samples_per_second": 208.267,
|
| 331 |
+
"eval_steps_per_second": 3.341,
|
| 332 |
+
"step": 8976
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.0,
|
| 336 |
+
"grad_norm": 1.571700096130371,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.1097,
|
| 339 |
+
"step": 9504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.0,
|
| 343 |
+
"eval_accuracy": 0.957517638875087,
|
| 344 |
+
"eval_f1": 0.7968959058067969,
|
| 345 |
+
"eval_loss": 0.1318700611591339,
|
| 346 |
+
"eval_precision": 0.7385912698412699,
|
| 347 |
+
"eval_recall": 0.8651946542707728,
|
| 348 |
+
"eval_runtime": 4.5298,
|
| 349 |
+
"eval_samples_per_second": 206.413,
|
| 350 |
+
"eval_steps_per_second": 3.311,
|
| 351 |
+
"step": 9504
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 19.0,
|
| 355 |
+
"grad_norm": 2.028625726699829,
|
| 356 |
+
"learning_rate": 2.5e-06,
|
| 357 |
+
"loss": 0.1086,
|
| 358 |
+
"step": 10032
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 19.0,
|
| 362 |
+
"eval_accuracy": 0.9573188909867832,
|
| 363 |
+
"eval_f1": 0.7943148297130599,
|
| 364 |
+
"eval_loss": 0.12963609397411346,
|
| 365 |
+
"eval_precision": 0.7375498007968128,
|
| 366 |
+
"eval_recall": 0.8605461940732132,
|
| 367 |
+
"eval_runtime": 4.5109,
|
| 368 |
+
"eval_samples_per_second": 207.276,
|
| 369 |
+
"eval_steps_per_second": 3.325,
|
| 370 |
+
"step": 10032
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 20.0,
|
| 374 |
+
"grad_norm": 1.7686336040496826,
|
| 375 |
+
"learning_rate": 0.0,
|
| 376 |
+
"loss": 0.1094,
|
| 377 |
+
"step": 10560
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 20.0,
|
| 381 |
+
"eval_accuracy": 0.9573188909867832,
|
| 382 |
+
"eval_f1": 0.7943148297130599,
|
| 383 |
+
"eval_loss": 0.13019020855426788,
|
| 384 |
+
"eval_precision": 0.7375498007968128,
|
| 385 |
+
"eval_recall": 0.8605461940732132,
|
| 386 |
+
"eval_runtime": 4.5282,
|
| 387 |
+
"eval_samples_per_second": 206.485,
|
| 388 |
+
"eval_steps_per_second": 3.313,
|
| 389 |
+
"step": 10560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 20.0,
|
| 393 |
+
"step": 10560,
|
| 394 |
+
"total_flos": 4545096690358590.0,
|
| 395 |
+
"train_loss": 0.17230618686387034,
|
| 396 |
+
"train_runtime": 1231.4857,
|
| 397 |
+
"train_samples_per_second": 137.021,
|
| 398 |
+
"train_steps_per_second": 8.575
|
| 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": 4545096690358590.0,
|
| 407 |
+
"train_batch_size": 16,
|
| 408 |
+
"trial_name": null,
|
| 409 |
+
"trial_params": null
|
| 410 |
+
}
|