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_03-33-55_indolem-petl-vm/events.out.tfevents.1716609284.indolem-petl-vm.1893306.1 +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": 0.9593063698698201,
|
| 4 |
+
"eval_f1": 0.8162496637072908,
|
| 5 |
+
"eval_loss": 0.12777453660964966,
|
| 6 |
+
"eval_precision": 0.7600200400801603,
|
| 7 |
+
"eval_recall": 0.8814642649622313,
|
| 8 |
+
"eval_runtime": 4.4229,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 211.401,
|
| 11 |
+
"eval_steps_per_second": 3.391,
|
| 12 |
+
"predict_accuracy": 0.9732004343779088,
|
| 13 |
+
"predict_f1": 0.8484713233653203,
|
| 14 |
+
"predict_loss": 0.08305826038122177,
|
| 15 |
+
"predict_precision": 0.8072186836518047,
|
| 16 |
+
"predict_recall": 0.894167450611477,
|
| 17 |
+
"predict_runtime": 10.4574,
|
| 18 |
+
"predict_samples_per_second": 224.053,
|
| 19 |
+
"predict_steps_per_second": 3.538,
|
| 20 |
+
"train_loss": 0.15358480504064848,
|
| 21 |
+
"train_runtime": 1231.8568,
|
| 22 |
+
"train_samples": 8437,
|
| 23 |
+
"train_samples_per_second": 136.98,
|
| 24 |
+
"train_steps_per_second": 8.572
|
| 25 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9593063698698201,
|
| 4 |
+
"eval_f1": 0.8162496637072908,
|
| 5 |
+
"eval_loss": 0.12777453660964966,
|
| 6 |
+
"eval_precision": 0.7600200400801603,
|
| 7 |
+
"eval_recall": 0.8814642649622313,
|
| 8 |
+
"eval_runtime": 4.4229,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 211.401,
|
| 11 |
+
"eval_steps_per_second": 3.391
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.9732004343779088,
|
| 3 |
+
"predict_f1": 0.8484713233653203,
|
| 4 |
+
"predict_loss": 0.08305826038122177,
|
| 5 |
+
"predict_precision": 0.8072186836518047,
|
| 6 |
+
"predict_recall": 0.894167450611477,
|
| 7 |
+
"predict_runtime": 10.4574,
|
| 8 |
+
"predict_samples_per_second": 224.053,
|
| 9 |
+
"predict_steps_per_second": 3.538
|
| 10 |
+
}
|
predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/May25_03-33-55_indolem-petl-vm/events.out.tfevents.1716609284.indolem-petl-vm.1893306.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8469534398782d62215273c984cd85ca117139916e843987df825ca36ccf9fde
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.15358480504064848,
|
| 4 |
+
"train_runtime": 1231.8568,
|
| 5 |
+
"train_samples": 8437,
|
| 6 |
+
"train_samples_per_second": 136.98,
|
| 7 |
+
"train_steps_per_second": 8.572
|
| 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": 1.387133002281189,
|
| 14 |
+
"learning_rate": 4.75e-05,
|
| 15 |
+
"loss": 0.713,
|
| 16 |
+
"step": 528
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.8990360727417271,
|
| 21 |
+
"eval_f1": 0.42582781456953644,
|
| 22 |
+
"eval_loss": 0.3558189868927002,
|
| 23 |
+
"eval_precision": 0.49499615088529636,
|
| 24 |
+
"eval_recall": 0.3736199883788495,
|
| 25 |
+
"eval_runtime": 4.469,
|
| 26 |
+
"eval_samples_per_second": 209.217,
|
| 27 |
+
"eval_steps_per_second": 3.356,
|
| 28 |
+
"step": 528
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 0.8080163598060608,
|
| 33 |
+
"learning_rate": 4.5e-05,
|
| 34 |
+
"loss": 0.2793,
|
| 35 |
+
"step": 1056
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9392328331511478,
|
| 40 |
+
"eval_f1": 0.7174307174307173,
|
| 41 |
+
"eval_loss": 0.19311487674713135,
|
| 42 |
+
"eval_precision": 0.647196261682243,
|
| 43 |
+
"eval_recall": 0.8047646717024985,
|
| 44 |
+
"eval_runtime": 4.5691,
|
| 45 |
+
"eval_samples_per_second": 204.634,
|
| 46 |
+
"eval_steps_per_second": 3.283,
|
| 47 |
+
"step": 1056
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 1.451019287109375,
|
| 52 |
+
"learning_rate": 4.25e-05,
|
| 53 |
+
"loss": 0.1876,
|
| 54 |
+
"step": 1584
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.9461890092417768,
|
| 59 |
+
"eval_f1": 0.7516120711890638,
|
| 60 |
+
"eval_loss": 0.161931574344635,
|
| 61 |
+
"eval_precision": 0.6757884972170687,
|
| 62 |
+
"eval_recall": 0.8466008134805346,
|
| 63 |
+
"eval_runtime": 4.5215,
|
| 64 |
+
"eval_samples_per_second": 206.79,
|
| 65 |
+
"eval_steps_per_second": 3.317,
|
| 66 |
+
"step": 1584
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 2.173278570175171,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.1593,
|
| 73 |
+
"step": 2112
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.95553015999205,
|
| 78 |
+
"eval_f1": 0.7947551511907948,
|
| 79 |
+
"eval_loss": 0.14164301753044128,
|
| 80 |
+
"eval_precision": 0.7366071428571429,
|
| 81 |
+
"eval_recall": 0.862870424171993,
|
| 82 |
+
"eval_runtime": 4.5447,
|
| 83 |
+
"eval_samples_per_second": 205.734,
|
| 84 |
+
"eval_steps_per_second": 3.301,
|
| 85 |
+
"step": 2112
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 1.1243175268173218,
|
| 90 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 91 |
+
"loss": 0.1412,
|
| 92 |
+
"step": 2640
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9559276557686575,
|
| 97 |
+
"eval_f1": 0.7968959058067969,
|
| 98 |
+
"eval_loss": 0.13503268361091614,
|
| 99 |
+
"eval_precision": 0.7385912698412699,
|
| 100 |
+
"eval_recall": 0.8651946542707728,
|
| 101 |
+
"eval_runtime": 4.497,
|
| 102 |
+
"eval_samples_per_second": 207.916,
|
| 103 |
+
"eval_steps_per_second": 3.336,
|
| 104 |
+
"step": 2640
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 1.4806779623031616,
|
| 109 |
+
"learning_rate": 3.5e-05,
|
| 110 |
+
"loss": 0.1325,
|
| 111 |
+
"step": 3168
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.95553015999205,
|
| 116 |
+
"eval_f1": 0.795219123505976,
|
| 117 |
+
"eval_loss": 0.13609066605567932,
|
| 118 |
+
"eval_precision": 0.7323874755381604,
|
| 119 |
+
"eval_recall": 0.8698431144683324,
|
| 120 |
+
"eval_runtime": 4.5221,
|
| 121 |
+
"eval_samples_per_second": 206.764,
|
| 122 |
+
"eval_steps_per_second": 3.317,
|
| 123 |
+
"step": 3168
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 2.750013828277588,
|
| 128 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 129 |
+
"loss": 0.126,
|
| 130 |
+
"step": 3696
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.9553314121037464,
|
| 135 |
+
"eval_f1": 0.7943751658264792,
|
| 136 |
+
"eval_loss": 0.13828907907009125,
|
| 137 |
+
"eval_precision": 0.73095703125,
|
| 138 |
+
"eval_recall": 0.8698431144683324,
|
| 139 |
+
"eval_runtime": 4.5248,
|
| 140 |
+
"eval_samples_per_second": 206.637,
|
| 141 |
+
"eval_steps_per_second": 3.315,
|
| 142 |
+
"step": 3696
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.7366927862167358,
|
| 147 |
+
"learning_rate": 3e-05,
|
| 148 |
+
"loss": 0.1194,
|
| 149 |
+
"step": 4224
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.9583126304283017,
|
| 154 |
+
"eval_f1": 0.8088274395107684,
|
| 155 |
+
"eval_loss": 0.13490265607833862,
|
| 156 |
+
"eval_precision": 0.7455882352941177,
|
| 157 |
+
"eval_recall": 0.8837884950610111,
|
| 158 |
+
"eval_runtime": 4.4844,
|
| 159 |
+
"eval_samples_per_second": 208.499,
|
| 160 |
+
"eval_steps_per_second": 3.345,
|
| 161 |
+
"step": 4224
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 1.5051740407943726,
|
| 166 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 167 |
+
"loss": 0.1137,
|
| 168 |
+
"step": 4752
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.0,
|
| 172 |
+
"eval_accuracy": 0.9583126304283017,
|
| 173 |
+
"eval_f1": 0.8071869133816038,
|
| 174 |
+
"eval_loss": 0.12994244694709778,
|
| 175 |
+
"eval_precision": 0.7495019920318725,
|
| 176 |
+
"eval_recall": 0.8744915746658919,
|
| 177 |
+
"eval_runtime": 4.8571,
|
| 178 |
+
"eval_samples_per_second": 192.501,
|
| 179 |
+
"eval_steps_per_second": 3.088,
|
| 180 |
+
"step": 4752
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 1.5836716890335083,
|
| 185 |
+
"learning_rate": 2.5e-05,
|
| 186 |
+
"loss": 0.1112,
|
| 187 |
+
"step": 5280
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.9579151346516943,
|
| 192 |
+
"eval_f1": 0.8028962188254224,
|
| 193 |
+
"eval_loss": 0.1285104751586914,
|
| 194 |
+
"eval_precision": 0.7455179282868526,
|
| 195 |
+
"eval_recall": 0.8698431144683324,
|
| 196 |
+
"eval_runtime": 4.5129,
|
| 197 |
+
"eval_samples_per_second": 207.185,
|
| 198 |
+
"eval_steps_per_second": 3.324,
|
| 199 |
+
"step": 5280
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 2.5579893589019775,
|
| 204 |
+
"learning_rate": 2.25e-05,
|
| 205 |
+
"loss": 0.1065,
|
| 206 |
+
"step": 5808
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.958710126204909,
|
| 211 |
+
"eval_f1": 0.8118811881188118,
|
| 212 |
+
"eval_loss": 0.13038235902786255,
|
| 213 |
+
"eval_precision": 0.7524801587301587,
|
| 214 |
+
"eval_recall": 0.8814642649622313,
|
| 215 |
+
"eval_runtime": 4.5151,
|
| 216 |
+
"eval_samples_per_second": 207.083,
|
| 217 |
+
"eval_steps_per_second": 3.322,
|
| 218 |
+
"step": 5808
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 12.0,
|
| 222 |
+
"grad_norm": 1.483597993850708,
|
| 223 |
+
"learning_rate": 2e-05,
|
| 224 |
+
"loss": 0.1044,
|
| 225 |
+
"step": 6336
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 12.0,
|
| 229 |
+
"eval_accuracy": 0.9577163867633907,
|
| 230 |
+
"eval_f1": 0.8106080900080364,
|
| 231 |
+
"eval_loss": 0.1328919380903244,
|
| 232 |
+
"eval_precision": 0.7519880715705766,
|
| 233 |
+
"eval_recall": 0.8791400348634515,
|
| 234 |
+
"eval_runtime": 4.5418,
|
| 235 |
+
"eval_samples_per_second": 205.867,
|
| 236 |
+
"eval_steps_per_second": 3.303,
|
| 237 |
+
"step": 6336
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 13.0,
|
| 241 |
+
"grad_norm": 2.8680760860443115,
|
| 242 |
+
"learning_rate": 1.75e-05,
|
| 243 |
+
"loss": 0.1026,
|
| 244 |
+
"step": 6864
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 13.0,
|
| 248 |
+
"eval_accuracy": 0.9585113783166054,
|
| 249 |
+
"eval_f1": 0.8076405703524348,
|
| 250 |
+
"eval_loss": 0.1257127821445465,
|
| 251 |
+
"eval_precision": 0.7520040080160321,
|
| 252 |
+
"eval_recall": 0.8721673445671121,
|
| 253 |
+
"eval_runtime": 4.5829,
|
| 254 |
+
"eval_samples_per_second": 204.019,
|
| 255 |
+
"eval_steps_per_second": 3.273,
|
| 256 |
+
"step": 6864
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 14.0,
|
| 260 |
+
"grad_norm": 0.6697184443473816,
|
| 261 |
+
"learning_rate": 1.5e-05,
|
| 262 |
+
"loss": 0.0989,
|
| 263 |
+
"step": 7392
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 14.0,
|
| 267 |
+
"eval_accuracy": 0.9599026135347312,
|
| 268 |
+
"eval_f1": 0.8167341430499325,
|
| 269 |
+
"eval_loss": 0.12645690143108368,
|
| 270 |
+
"eval_precision": 0.7626008064516129,
|
| 271 |
+
"eval_recall": 0.8791400348634515,
|
| 272 |
+
"eval_runtime": 4.5334,
|
| 273 |
+
"eval_samples_per_second": 206.248,
|
| 274 |
+
"eval_steps_per_second": 3.309,
|
| 275 |
+
"step": 7392
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 15.0,
|
| 279 |
+
"grad_norm": 1.7948130369186401,
|
| 280 |
+
"learning_rate": 1.25e-05,
|
| 281 |
+
"loss": 0.0982,
|
| 282 |
+
"step": 7920
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.0,
|
| 286 |
+
"eval_accuracy": 0.9597038656464275,
|
| 287 |
+
"eval_f1": 0.8180102453491508,
|
| 288 |
+
"eval_loss": 0.1280616968870163,
|
| 289 |
+
"eval_precision": 0.7630784708249497,
|
| 290 |
+
"eval_recall": 0.8814642649622313,
|
| 291 |
+
"eval_runtime": 4.5387,
|
| 292 |
+
"eval_samples_per_second": 206.008,
|
| 293 |
+
"eval_steps_per_second": 3.305,
|
| 294 |
+
"step": 7920
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.0,
|
| 298 |
+
"grad_norm": 2.107656717300415,
|
| 299 |
+
"learning_rate": 1e-05,
|
| 300 |
+
"loss": 0.0974,
|
| 301 |
+
"step": 8448
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 16.0,
|
| 305 |
+
"eval_accuracy": 0.9597038656464275,
|
| 306 |
+
"eval_f1": 0.8093322606596943,
|
| 307 |
+
"eval_loss": 0.12642435729503632,
|
| 308 |
+
"eval_precision": 0.7514940239043825,
|
| 309 |
+
"eval_recall": 0.8768158047646717,
|
| 310 |
+
"eval_runtime": 4.5132,
|
| 311 |
+
"eval_samples_per_second": 207.172,
|
| 312 |
+
"eval_steps_per_second": 3.324,
|
| 313 |
+
"step": 8448
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 17.0,
|
| 317 |
+
"grad_norm": 0.980239748954773,
|
| 318 |
+
"learning_rate": 7.5e-06,
|
| 319 |
+
"loss": 0.0966,
|
| 320 |
+
"step": 8976
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 17.0,
|
| 324 |
+
"eval_accuracy": 0.9589088740932128,
|
| 325 |
+
"eval_f1": 0.814021942734814,
|
| 326 |
+
"eval_loss": 0.12821656465530396,
|
| 327 |
+
"eval_precision": 0.7544642857142857,
|
| 328 |
+
"eval_recall": 0.8837884950610111,
|
| 329 |
+
"eval_runtime": 4.5105,
|
| 330 |
+
"eval_samples_per_second": 207.293,
|
| 331 |
+
"eval_steps_per_second": 3.326,
|
| 332 |
+
"step": 8976
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.0,
|
| 336 |
+
"grad_norm": 1.8313038349151611,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.095,
|
| 339 |
+
"step": 9504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.0,
|
| 343 |
+
"eval_accuracy": 0.9589088740932128,
|
| 344 |
+
"eval_f1": 0.8144966442953021,
|
| 345 |
+
"eval_loss": 0.12922193109989166,
|
| 346 |
+
"eval_precision": 0.7569860279441117,
|
| 347 |
+
"eval_recall": 0.8814642649622313,
|
| 348 |
+
"eval_runtime": 4.5244,
|
| 349 |
+
"eval_samples_per_second": 206.658,
|
| 350 |
+
"eval_steps_per_second": 3.315,
|
| 351 |
+
"step": 9504
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 19.0,
|
| 355 |
+
"grad_norm": 0.775888204574585,
|
| 356 |
+
"learning_rate": 2.5e-06,
|
| 357 |
+
"loss": 0.0941,
|
| 358 |
+
"step": 10032
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 19.0,
|
| 362 |
+
"eval_accuracy": 0.9595051177581239,
|
| 363 |
+
"eval_f1": 0.8153722117710293,
|
| 364 |
+
"eval_loss": 0.12684974074363708,
|
| 365 |
+
"eval_precision": 0.7585,
|
| 366 |
+
"eval_recall": 0.8814642649622313,
|
| 367 |
+
"eval_runtime": 4.5294,
|
| 368 |
+
"eval_samples_per_second": 206.429,
|
| 369 |
+
"eval_steps_per_second": 3.312,
|
| 370 |
+
"step": 10032
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 20.0,
|
| 374 |
+
"grad_norm": 2.084799289703369,
|
| 375 |
+
"learning_rate": 0.0,
|
| 376 |
+
"loss": 0.0948,
|
| 377 |
+
"step": 10560
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 20.0,
|
| 381 |
+
"eval_accuracy": 0.9593063698698201,
|
| 382 |
+
"eval_f1": 0.8162496637072908,
|
| 383 |
+
"eval_loss": 0.12777453660964966,
|
| 384 |
+
"eval_precision": 0.7600200400801603,
|
| 385 |
+
"eval_recall": 0.8814642649622313,
|
| 386 |
+
"eval_runtime": 4.4979,
|
| 387 |
+
"eval_samples_per_second": 207.876,
|
| 388 |
+
"eval_steps_per_second": 3.335,
|
| 389 |
+
"step": 10560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 20.0,
|
| 393 |
+
"step": 10560,
|
| 394 |
+
"total_flos": 4552961808488766.0,
|
| 395 |
+
"train_loss": 0.15358480504064848,
|
| 396 |
+
"train_runtime": 1231.8568,
|
| 397 |
+
"train_samples_per_second": 136.98,
|
| 398 |
+
"train_steps_per_second": 8.572
|
| 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 |
+
}
|