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_01-05-16_indolem-petl-vm/events.out.tfevents.1716600366.indolem-petl-vm.1824897.1 +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": 0.9591076219815164,
|
| 4 |
+
"eval_f1": 0.812483039348711,
|
| 5 |
+
"eval_loss": 0.12664274871349335,
|
| 6 |
+
"eval_precision": 0.7622199592668024,
|
| 7 |
+
"eval_recall": 0.8698431144683324,
|
| 8 |
+
"eval_runtime": 4.5251,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 206.625,
|
| 11 |
+
"eval_steps_per_second": 3.315,
|
| 12 |
+
"predict_accuracy": 0.97166847657462,
|
| 13 |
+
"predict_f1": 0.8423518911078879,
|
| 14 |
+
"predict_loss": 0.0863073393702507,
|
| 15 |
+
"predict_precision": 0.801316068775207,
|
| 16 |
+
"predict_recall": 0.8878174976481655,
|
| 17 |
+
"predict_runtime": 10.5103,
|
| 18 |
+
"predict_samples_per_second": 222.925,
|
| 19 |
+
"predict_steps_per_second": 3.52,
|
| 20 |
+
"train_loss": 0.1550482457334345,
|
| 21 |
+
"train_runtime": 1233.354,
|
| 22 |
+
"train_samples": 8437,
|
| 23 |
+
"train_samples_per_second": 136.814,
|
| 24 |
+
"train_steps_per_second": 8.562
|
| 25 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9591076219815164,
|
| 4 |
+
"eval_f1": 0.812483039348711,
|
| 5 |
+
"eval_loss": 0.12664274871349335,
|
| 6 |
+
"eval_precision": 0.7622199592668024,
|
| 7 |
+
"eval_recall": 0.8698431144683324,
|
| 8 |
+
"eval_runtime": 4.5251,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 206.625,
|
| 11 |
+
"eval_steps_per_second": 3.315
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.97166847657462,
|
| 3 |
+
"predict_f1": 0.8423518911078879,
|
| 4 |
+
"predict_loss": 0.0863073393702507,
|
| 5 |
+
"predict_precision": 0.801316068775207,
|
| 6 |
+
"predict_recall": 0.8878174976481655,
|
| 7 |
+
"predict_runtime": 10.5103,
|
| 8 |
+
"predict_samples_per_second": 222.925,
|
| 9 |
+
"predict_steps_per_second": 3.52
|
| 10 |
+
}
|
predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/May25_01-05-16_indolem-petl-vm/events.out.tfevents.1716600366.indolem-petl-vm.1824897.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69971f9a5fb2f2beb87a5b426f7ac237f5897e0db558eb4dbba7a0f13d695df6
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.1550482457334345,
|
| 4 |
+
"train_runtime": 1233.354,
|
| 5 |
+
"train_samples": 8437,
|
| 6 |
+
"train_samples_per_second": 136.814,
|
| 7 |
+
"train_steps_per_second": 8.562
|
| 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": 1.1869616508483887,
|
| 14 |
+
"learning_rate": 4.75e-05,
|
| 15 |
+
"loss": 0.7039,
|
| 16 |
+
"step": 528
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.9123024942859982,
|
| 21 |
+
"eval_f1": 0.5240871432954894,
|
| 22 |
+
"eval_loss": 0.3293141722679138,
|
| 23 |
+
"eval_precision": 0.5552665799739922,
|
| 24 |
+
"eval_recall": 0.4962231260894829,
|
| 25 |
+
"eval_runtime": 4.4479,
|
| 26 |
+
"eval_samples_per_second": 210.209,
|
| 27 |
+
"eval_steps_per_second": 3.372,
|
| 28 |
+
"step": 528
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 0.910118818283081,
|
| 33 |
+
"learning_rate": 4.5e-05,
|
| 34 |
+
"loss": 0.2536,
|
| 35 |
+
"step": 1056
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9424127993640068,
|
| 40 |
+
"eval_f1": 0.7274131274131275,
|
| 41 |
+
"eval_loss": 0.1835452765226364,
|
| 42 |
+
"eval_precision": 0.6529574861367837,
|
| 43 |
+
"eval_recall": 0.821034282393957,
|
| 44 |
+
"eval_runtime": 4.5463,
|
| 45 |
+
"eval_samples_per_second": 205.661,
|
| 46 |
+
"eval_steps_per_second": 3.299,
|
| 47 |
+
"step": 1056
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 10.446182250976562,
|
| 52 |
+
"learning_rate": 4.25e-05,
|
| 53 |
+
"loss": 0.1831,
|
| 54 |
+
"step": 1584
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.9440027824704362,
|
| 59 |
+
"eval_f1": 0.7365129007036748,
|
| 60 |
+
"eval_loss": 0.18317362666130066,
|
| 61 |
+
"eval_precision": 0.6677693761814745,
|
| 62 |
+
"eval_recall": 0.821034282393957,
|
| 63 |
+
"eval_runtime": 4.5021,
|
| 64 |
+
"eval_samples_per_second": 207.681,
|
| 65 |
+
"eval_steps_per_second": 3.332,
|
| 66 |
+
"step": 1584
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 5.82688045501709,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.1623,
|
| 73 |
+
"step": 2112
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.9535426811090132,
|
| 78 |
+
"eval_f1": 0.7789361133386795,
|
| 79 |
+
"eval_loss": 0.14634285867214203,
|
| 80 |
+
"eval_precision": 0.7212871287128713,
|
| 81 |
+
"eval_recall": 0.8466008134805346,
|
| 82 |
+
"eval_runtime": 4.5242,
|
| 83 |
+
"eval_samples_per_second": 206.664,
|
| 84 |
+
"eval_steps_per_second": 3.315,
|
| 85 |
+
"step": 2112
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 1.118807077407837,
|
| 90 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 91 |
+
"loss": 0.1439,
|
| 92 |
+
"step": 2640
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9541389247739243,
|
| 97 |
+
"eval_f1": 0.7746591820368887,
|
| 98 |
+
"eval_loss": 0.1386542022228241,
|
| 99 |
+
"eval_precision": 0.7173267326732673,
|
| 100 |
+
"eval_recall": 0.841952353282975,
|
| 101 |
+
"eval_runtime": 4.5032,
|
| 102 |
+
"eval_samples_per_second": 207.628,
|
| 103 |
+
"eval_steps_per_second": 3.331,
|
| 104 |
+
"step": 2640
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 1.6887811422348022,
|
| 109 |
+
"learning_rate": 3.5e-05,
|
| 110 |
+
"loss": 0.1348,
|
| 111 |
+
"step": 3168
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.9553314121037464,
|
| 116 |
+
"eval_f1": 0.7892923403127484,
|
| 117 |
+
"eval_loss": 0.1382703185081482,
|
| 118 |
+
"eval_precision": 0.7256335282651072,
|
| 119 |
+
"eval_recall": 0.8651946542707728,
|
| 120 |
+
"eval_runtime": 4.505,
|
| 121 |
+
"eval_samples_per_second": 207.547,
|
| 122 |
+
"eval_steps_per_second": 3.33,
|
| 123 |
+
"step": 3168
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 8.010842323303223,
|
| 128 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 129 |
+
"loss": 0.1293,
|
| 130 |
+
"step": 3696
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.9545364205505317,
|
| 135 |
+
"eval_f1": 0.7884564469155414,
|
| 136 |
+
"eval_loss": 0.1393628716468811,
|
| 137 |
+
"eval_precision": 0.7242217898832685,
|
| 138 |
+
"eval_recall": 0.8651946542707728,
|
| 139 |
+
"eval_runtime": 4.7943,
|
| 140 |
+
"eval_samples_per_second": 195.025,
|
| 141 |
+
"eval_steps_per_second": 3.129,
|
| 142 |
+
"step": 3696
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.8240045309066772,
|
| 147 |
+
"learning_rate": 3e-05,
|
| 148 |
+
"loss": 0.124,
|
| 149 |
+
"step": 4224
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.9569213952101759,
|
| 154 |
+
"eval_f1": 0.7969124301304232,
|
| 155 |
+
"eval_loss": 0.13507381081581116,
|
| 156 |
+
"eval_precision": 0.7352652259332023,
|
| 157 |
+
"eval_recall": 0.8698431144683324,
|
| 158 |
+
"eval_runtime": 4.5318,
|
| 159 |
+
"eval_samples_per_second": 206.319,
|
| 160 |
+
"eval_steps_per_second": 3.31,
|
| 161 |
+
"step": 4224
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 1.0099204778671265,
|
| 166 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 167 |
+
"loss": 0.1176,
|
| 168 |
+
"step": 4752
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.0,
|
| 172 |
+
"eval_accuracy": 0.9561264036569611,
|
| 173 |
+
"eval_f1": 0.7929824561403509,
|
| 174 |
+
"eval_loss": 0.13042420148849487,
|
| 175 |
+
"eval_precision": 0.7404233870967742,
|
| 176 |
+
"eval_recall": 0.8535735037768739,
|
| 177 |
+
"eval_runtime": 4.5435,
|
| 178 |
+
"eval_samples_per_second": 205.786,
|
| 179 |
+
"eval_steps_per_second": 3.301,
|
| 180 |
+
"step": 4752
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 1.6231740713119507,
|
| 185 |
+
"learning_rate": 2.5e-05,
|
| 186 |
+
"loss": 0.1153,
|
| 187 |
+
"step": 5280
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.9585113783166054,
|
| 192 |
+
"eval_f1": 0.8051240119923686,
|
| 193 |
+
"eval_loss": 0.1277889907360077,
|
| 194 |
+
"eval_precision": 0.7582135523613963,
|
| 195 |
+
"eval_recall": 0.8582219639744335,
|
| 196 |
+
"eval_runtime": 4.5323,
|
| 197 |
+
"eval_samples_per_second": 206.296,
|
| 198 |
+
"eval_steps_per_second": 3.31,
|
| 199 |
+
"step": 5280
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 2.4694974422454834,
|
| 204 |
+
"learning_rate": 2.25e-05,
|
| 205 |
+
"loss": 0.111,
|
| 206 |
+
"step": 5808
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.9579151346516943,
|
| 211 |
+
"eval_f1": 0.7968959058067969,
|
| 212 |
+
"eval_loss": 0.13041619956493378,
|
| 213 |
+
"eval_precision": 0.7385912698412699,
|
| 214 |
+
"eval_recall": 0.8651946542707728,
|
| 215 |
+
"eval_runtime": 4.5215,
|
| 216 |
+
"eval_samples_per_second": 206.789,
|
| 217 |
+
"eval_steps_per_second": 3.317,
|
| 218 |
+
"step": 5808
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 12.0,
|
| 222 |
+
"grad_norm": 1.5000303983688354,
|
| 223 |
+
"learning_rate": 2e-05,
|
| 224 |
+
"loss": 0.109,
|
| 225 |
+
"step": 6336
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 12.0,
|
| 229 |
+
"eval_accuracy": 0.9565238994335685,
|
| 230 |
+
"eval_f1": 0.7986055242692411,
|
| 231 |
+
"eval_loss": 0.13234680891036987,
|
| 232 |
+
"eval_precision": 0.7415338645418327,
|
| 233 |
+
"eval_recall": 0.8651946542707728,
|
| 234 |
+
"eval_runtime": 4.5203,
|
| 235 |
+
"eval_samples_per_second": 206.846,
|
| 236 |
+
"eval_steps_per_second": 3.318,
|
| 237 |
+
"step": 6336
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 13.0,
|
| 241 |
+
"grad_norm": 1.91750168800354,
|
| 242 |
+
"learning_rate": 1.75e-05,
|
| 243 |
+
"loss": 0.1077,
|
| 244 |
+
"step": 6864
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 13.0,
|
| 248 |
+
"eval_accuracy": 0.9597038656464275,
|
| 249 |
+
"eval_f1": 0.812959433705418,
|
| 250 |
+
"eval_loss": 0.12529084086418152,
|
| 251 |
+
"eval_precision": 0.7648565573770492,
|
| 252 |
+
"eval_recall": 0.8675188843695526,
|
| 253 |
+
"eval_runtime": 4.4871,
|
| 254 |
+
"eval_samples_per_second": 208.377,
|
| 255 |
+
"eval_steps_per_second": 3.343,
|
| 256 |
+
"step": 6864
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 14.0,
|
| 260 |
+
"grad_norm": 1.4095473289489746,
|
| 261 |
+
"learning_rate": 1.5e-05,
|
| 262 |
+
"loss": 0.1032,
|
| 263 |
+
"step": 7392
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 14.0,
|
| 267 |
+
"eval_accuracy": 0.9593063698698201,
|
| 268 |
+
"eval_f1": 0.8103683492496588,
|
| 269 |
+
"eval_loss": 0.1242511197924614,
|
| 270 |
+
"eval_precision": 0.7638888888888888,
|
| 271 |
+
"eval_recall": 0.862870424171993,
|
| 272 |
+
"eval_runtime": 4.5214,
|
| 273 |
+
"eval_samples_per_second": 206.795,
|
| 274 |
+
"eval_steps_per_second": 3.318,
|
| 275 |
+
"step": 7392
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 15.0,
|
| 279 |
+
"grad_norm": 1.268137812614441,
|
| 280 |
+
"learning_rate": 1.25e-05,
|
| 281 |
+
"loss": 0.1035,
|
| 282 |
+
"step": 7920
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.0,
|
| 286 |
+
"eval_accuracy": 0.9597038656464275,
|
| 287 |
+
"eval_f1": 0.8138457345325703,
|
| 288 |
+
"eval_loss": 0.1261007934808731,
|
| 289 |
+
"eval_precision": 0.7664271047227926,
|
| 290 |
+
"eval_recall": 0.8675188843695526,
|
| 291 |
+
"eval_runtime": 4.5469,
|
| 292 |
+
"eval_samples_per_second": 205.635,
|
| 293 |
+
"eval_steps_per_second": 3.299,
|
| 294 |
+
"step": 7920
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.0,
|
| 298 |
+
"grad_norm": 1.6868817806243896,
|
| 299 |
+
"learning_rate": 1e-05,
|
| 300 |
+
"loss": 0.1017,
|
| 301 |
+
"step": 8448
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 16.0,
|
| 305 |
+
"eval_accuracy": 0.9577163867633907,
|
| 306 |
+
"eval_f1": 0.7977254264825344,
|
| 307 |
+
"eval_loss": 0.12578710913658142,
|
| 308 |
+
"eval_precision": 0.7469574036511156,
|
| 309 |
+
"eval_recall": 0.8558977338756537,
|
| 310 |
+
"eval_runtime": 4.5126,
|
| 311 |
+
"eval_samples_per_second": 207.2,
|
| 312 |
+
"eval_steps_per_second": 3.324,
|
| 313 |
+
"step": 8448
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 17.0,
|
| 317 |
+
"grad_norm": 1.2091130018234253,
|
| 318 |
+
"learning_rate": 7.5e-06,
|
| 319 |
+
"loss": 0.1004,
|
| 320 |
+
"step": 8976
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 17.0,
|
| 324 |
+
"eval_accuracy": 0.9589088740932128,
|
| 325 |
+
"eval_f1": 0.809845820935894,
|
| 326 |
+
"eval_loss": 0.12778569757938385,
|
| 327 |
+
"eval_precision": 0.7575910931174089,
|
| 328 |
+
"eval_recall": 0.8698431144683324,
|
| 329 |
+
"eval_runtime": 4.4936,
|
| 330 |
+
"eval_samples_per_second": 208.074,
|
| 331 |
+
"eval_steps_per_second": 3.338,
|
| 332 |
+
"step": 8976
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.0,
|
| 336 |
+
"grad_norm": 1.5732147693634033,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.099,
|
| 339 |
+
"step": 9504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.0,
|
| 343 |
+
"eval_accuracy": 0.9585113783166054,
|
| 344 |
+
"eval_f1": 0.8050687516850902,
|
| 345 |
+
"eval_loss": 0.12837953865528107,
|
| 346 |
+
"eval_precision": 0.7510060362173038,
|
| 347 |
+
"eval_recall": 0.8675188843695526,
|
| 348 |
+
"eval_runtime": 4.555,
|
| 349 |
+
"eval_samples_per_second": 205.267,
|
| 350 |
+
"eval_steps_per_second": 3.293,
|
| 351 |
+
"step": 9504
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 19.0,
|
| 355 |
+
"grad_norm": 0.611748218536377,
|
| 356 |
+
"learning_rate": 2.5e-06,
|
| 357 |
+
"loss": 0.0991,
|
| 358 |
+
"step": 10032
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 19.0,
|
| 362 |
+
"eval_accuracy": 0.958113882539998,
|
| 363 |
+
"eval_f1": 0.8055480010878433,
|
| 364 |
+
"eval_loss": 0.12564244866371155,
|
| 365 |
+
"eval_precision": 0.7571574642126789,
|
| 366 |
+
"eval_recall": 0.8605461940732132,
|
| 367 |
+
"eval_runtime": 4.5578,
|
| 368 |
+
"eval_samples_per_second": 205.145,
|
| 369 |
+
"eval_steps_per_second": 3.291,
|
| 370 |
+
"step": 10032
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 20.0,
|
| 374 |
+
"grad_norm": 1.8662045001983643,
|
| 375 |
+
"learning_rate": 0.0,
|
| 376 |
+
"loss": 0.0984,
|
| 377 |
+
"step": 10560
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 20.0,
|
| 381 |
+
"eval_accuracy": 0.9591076219815164,
|
| 382 |
+
"eval_f1": 0.812483039348711,
|
| 383 |
+
"eval_loss": 0.12664274871349335,
|
| 384 |
+
"eval_precision": 0.7622199592668024,
|
| 385 |
+
"eval_recall": 0.8698431144683324,
|
| 386 |
+
"eval_runtime": 4.5462,
|
| 387 |
+
"eval_samples_per_second": 205.667,
|
| 388 |
+
"eval_steps_per_second": 3.299,
|
| 389 |
+
"step": 10560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 20.0,
|
| 393 |
+
"step": 10560,
|
| 394 |
+
"total_flos": 4552961808488766.0,
|
| 395 |
+
"train_loss": 0.1550482457334345,
|
| 396 |
+
"train_runtime": 1233.354,
|
| 397 |
+
"train_samples_per_second": 136.814,
|
| 398 |
+
"train_steps_per_second": 8.562
|
| 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 |
+
}
|