Connor Finley
commited on
Commit
•
9d253d4
1
Parent(s):
a4c9469
add model
Browse files- README.md +1 -1
- all_results.json +14 -14
- eval_results.json +5 -5
- predict_results.json +4 -4
- predictions.txt +0 -0
- pytorch_model.bin +1 -1
- tokenizer.json +0 -0
- train_results.json +5 -5
- trainer_state.json +189 -9
README.md
CHANGED
|
@@ -26,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 26 |
|
| 27 |
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unkown dataset.
|
| 28 |
It achieves the following results on the evaluation set:
|
| 29 |
-
- Loss: 0.
|
| 30 |
- Precision: 1.0
|
| 31 |
- Recall: 1.0
|
| 32 |
- F1: 1.0
|
| 26 |
|
| 27 |
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unkown dataset.
|
| 28 |
It achieves the following results on the evaluation set:
|
| 29 |
+
- Loss: 0.0000
|
| 30 |
- Precision: 1.0
|
| 31 |
- Recall: 1.0
|
| 32 |
- F1: 1.0
|
all_results.json
CHANGED
|
@@ -2,24 +2,24 @@
|
|
| 2 |
"epoch": 3.0,
|
| 3 |
"eval_accuracy": 1.0,
|
| 4 |
"eval_f1": 1.0,
|
| 5 |
-
"eval_loss":
|
| 6 |
"eval_precision": 1.0,
|
| 7 |
"eval_recall": 1.0,
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples":
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second": 69.
|
| 12 |
"predict_accuracy": 1.0,
|
| 13 |
"predict_f1": 1.0,
|
| 14 |
-
"predict_loss":
|
| 15 |
"predict_precision": 1.0,
|
| 16 |
"predict_recall": 1.0,
|
| 17 |
-
"predict_runtime":
|
| 18 |
-
"predict_samples_per_second":
|
| 19 |
-
"predict_steps_per_second":
|
| 20 |
-
"train_loss": 0.
|
| 21 |
-
"train_runtime":
|
| 22 |
-
"train_samples":
|
| 23 |
-
"train_samples_per_second":
|
| 24 |
-
"train_steps_per_second":
|
| 25 |
}
|
| 2 |
"epoch": 3.0,
|
| 3 |
"eval_accuracy": 1.0,
|
| 4 |
"eval_f1": 1.0,
|
| 5 |
+
"eval_loss": 2.2186291971593164e-05,
|
| 6 |
"eval_precision": 1.0,
|
| 7 |
"eval_recall": 1.0,
|
| 8 |
+
"eval_runtime": 18.1044,
|
| 9 |
+
"eval_samples": 10000,
|
| 10 |
+
"eval_samples_per_second": 552.353,
|
| 11 |
+
"eval_steps_per_second": 69.044,
|
| 12 |
"predict_accuracy": 1.0,
|
| 13 |
"predict_f1": 1.0,
|
| 14 |
+
"predict_loss": 2.253339516755659e-05,
|
| 15 |
"predict_precision": 1.0,
|
| 16 |
"predict_recall": 1.0,
|
| 17 |
+
"predict_runtime": 17.21,
|
| 18 |
+
"predict_samples_per_second": 581.057,
|
| 19 |
+
"predict_steps_per_second": 72.632,
|
| 20 |
+
"train_loss": 0.009999158646538853,
|
| 21 |
+
"train_runtime": 1548.4287,
|
| 22 |
+
"train_samples": 80000,
|
| 23 |
+
"train_samples_per_second": 154.996,
|
| 24 |
+
"train_steps_per_second": 9.687
|
| 25 |
}
|
eval_results.json
CHANGED
|
@@ -2,11 +2,11 @@
|
|
| 2 |
"epoch": 3.0,
|
| 3 |
"eval_accuracy": 1.0,
|
| 4 |
"eval_f1": 1.0,
|
| 5 |
-
"eval_loss":
|
| 6 |
"eval_precision": 1.0,
|
| 7 |
"eval_recall": 1.0,
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples":
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second": 69.
|
| 12 |
}
|
| 2 |
"epoch": 3.0,
|
| 3 |
"eval_accuracy": 1.0,
|
| 4 |
"eval_f1": 1.0,
|
| 5 |
+
"eval_loss": 2.2186291971593164e-05,
|
| 6 |
"eval_precision": 1.0,
|
| 7 |
"eval_recall": 1.0,
|
| 8 |
+
"eval_runtime": 18.1044,
|
| 9 |
+
"eval_samples": 10000,
|
| 10 |
+
"eval_samples_per_second": 552.353,
|
| 11 |
+
"eval_steps_per_second": 69.044
|
| 12 |
}
|
predict_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"predict_accuracy": 1.0,
|
| 3 |
"predict_f1": 1.0,
|
| 4 |
-
"predict_loss":
|
| 5 |
"predict_precision": 1.0,
|
| 6 |
"predict_recall": 1.0,
|
| 7 |
-
"predict_runtime":
|
| 8 |
-
"predict_samples_per_second":
|
| 9 |
-
"predict_steps_per_second":
|
| 10 |
}
|
| 1 |
{
|
| 2 |
"predict_accuracy": 1.0,
|
| 3 |
"predict_f1": 1.0,
|
| 4 |
+
"predict_loss": 2.253339516755659e-05,
|
| 5 |
"predict_precision": 1.0,
|
| 6 |
"predict_recall": 1.0,
|
| 7 |
+
"predict_runtime": 17.21,
|
| 8 |
+
"predict_samples_per_second": 581.057,
|
| 9 |
+
"predict_steps_per_second": 72.632
|
| 10 |
}
|
predictions.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440216305
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a70a4e428999b8723bb45ac5a5b4e73d10e6cee6bb0ab493415fa5aa381c3a41
|
| 3 |
size 440216305
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.009999158646538853,
|
| 4 |
+
"train_runtime": 1548.4287,
|
| 5 |
+
"train_samples": 80000,
|
| 6 |
+
"train_samples_per_second": 154.996,
|
| 7 |
+
"train_steps_per_second": 9.687
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -2,24 +2,204 @@
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 3.0,
|
| 12 |
-
"step":
|
| 13 |
-
"total_flos":
|
| 14 |
-
"train_loss": 0.
|
| 15 |
-
"train_runtime":
|
| 16 |
-
"train_samples_per_second":
|
| 17 |
-
"train_steps_per_second":
|
| 18 |
}
|
| 19 |
],
|
| 20 |
-
"max_steps":
|
| 21 |
"num_train_epochs": 3,
|
| 22 |
-
"total_flos":
|
| 23 |
"trial_name": null,
|
| 24 |
"trial_params": null
|
| 25 |
}
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
+
"global_step": 15000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 13 |
+
"loss": 0.0826,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 4.666666666666667e-05,
|
| 19 |
+
"loss": 0.0497,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.3,
|
| 24 |
+
"learning_rate": 4.5e-05,
|
| 25 |
+
"loss": 0.0453,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.4,
|
| 30 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 31 |
+
"loss": 0.0482,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.5,
|
| 36 |
+
"learning_rate": 4.166666666666667e-05,
|
| 37 |
+
"loss": 0.0122,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.6,
|
| 42 |
+
"learning_rate": 4e-05,
|
| 43 |
+
"loss": 0.0054,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.7,
|
| 48 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 49 |
+
"loss": 0.0031,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.8,
|
| 54 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 55 |
+
"loss": 0.003,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.9,
|
| 60 |
+
"learning_rate": 3.5e-05,
|
| 61 |
+
"loss": 0.0037,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.0,
|
| 66 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 67 |
+
"loss": 0.0055,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.1,
|
| 72 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 73 |
+
"loss": 0.0004,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.2,
|
| 78 |
+
"learning_rate": 3e-05,
|
| 79 |
+
"loss": 0.0071,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.3,
|
| 84 |
+
"learning_rate": 2.8333333333333335e-05,
|
| 85 |
+
"loss": 0.0016,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.4,
|
| 90 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 91 |
+
"loss": 0.0025,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.5,
|
| 96 |
+
"learning_rate": 2.5e-05,
|
| 97 |
+
"loss": 0.0051,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.6,
|
| 102 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 103 |
+
"loss": 0.0054,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.7,
|
| 108 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 109 |
+
"loss": 0.0039,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.8,
|
| 114 |
+
"learning_rate": 2e-05,
|
| 115 |
+
"loss": 0.0042,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.9,
|
| 120 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 121 |
+
"loss": 0.0049,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.0,
|
| 126 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 127 |
+
"loss": 0.0045,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.1,
|
| 132 |
+
"learning_rate": 1.5e-05,
|
| 133 |
+
"loss": 0.0003,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.2,
|
| 138 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 139 |
+
"loss": 0.0004,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.3,
|
| 144 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 145 |
+
"loss": 0.0001,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.4,
|
| 150 |
+
"learning_rate": 1e-05,
|
| 151 |
+
"loss": 0.0001,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.5,
|
| 156 |
+
"learning_rate": 8.333333333333334e-06,
|
| 157 |
+
"loss": 0.0,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.6,
|
| 162 |
+
"learning_rate": 6.666666666666667e-06,
|
| 163 |
+
"loss": 0.0002,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.7,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.0,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.8,
|
| 174 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 175 |
+
"loss": 0.0001,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.9,
|
| 180 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 181 |
+
"loss": 0.0,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.0,
|
| 186 |
+
"learning_rate": 0.0,
|
| 187 |
+
"loss": 0.0005,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
{
|
| 191 |
"epoch": 3.0,
|
| 192 |
+
"step": 15000,
|
| 193 |
+
"total_flos": 3352746415219200.0,
|
| 194 |
+
"train_loss": 0.009999158646538853,
|
| 195 |
+
"train_runtime": 1548.4287,
|
| 196 |
+
"train_samples_per_second": 154.996,
|
| 197 |
+
"train_steps_per_second": 9.687
|
| 198 |
}
|
| 199 |
],
|
| 200 |
+
"max_steps": 15000,
|
| 201 |
"num_train_epochs": 3,
|
| 202 |
+
"total_flos": 3352746415219200.0,
|
| 203 |
"trial_name": null,
|
| 204 |
"trial_params": null
|
| 205 |
}
|