Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-1530/config.json +35 -0
- checkpoint-1530/model.safetensors +3 -0
- checkpoint-1530/optimizer.pt +3 -0
- checkpoint-1530/rng_state.pth +3 -0
- checkpoint-1530/scheduler.pt +3 -0
- checkpoint-1530/trainer_state.json +426 -0
- checkpoint-1530/training_args.bin +3 -0
- config.json +35 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
widget:
|
| 7 |
+
- text: "I love AutoTrain"
|
| 8 |
+
datasets:
|
| 9 |
+
- younoger/autotrain-data-autotrain-v2-test3
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.009224997833371162
|
| 18 |
+
|
| 19 |
+
f1: 0.9743589743589743
|
| 20 |
+
|
| 21 |
+
precision: 1.0
|
| 22 |
+
|
| 23 |
+
recall: 0.95
|
| 24 |
+
|
| 25 |
+
auc: 0.9993006993006993
|
| 26 |
+
|
| 27 |
+
accuracy: 0.9990205680705191
|
checkpoint-1530/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-german-cased",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": 0,
|
| 14 |
+
"1": 1
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"0": 0,
|
| 20 |
+
"1": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.36.1",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 30000
|
| 35 |
+
}
|
checkpoint-1530/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9748201a9de130e50719e2f69c1088812bf19d2a7fcd8beac5ab37dad9ca3ad
|
| 3 |
+
size 436355056
|
checkpoint-1530/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e33cf34ac0759c507b22689fd37e4e715d40b2177f63e24dedd8753cb7216ce
|
| 3 |
+
size 872831226
|
checkpoint-1530/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63e8cfa291b48e65bd52c707026a01595ca717129736776b8c1f045fb947f93f
|
| 3 |
+
size 14244
|
checkpoint-1530/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf22211f91eef88cef9fccdae3767c17785752d169dbe6332c6f6589c901a683
|
| 3 |
+
size 1064
|
checkpoint-1530/trainer_state.json
ADDED
|
@@ -0,0 +1,426 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.009224997833371162,
|
| 3 |
+
"best_model_checkpoint": "/tmp/model/checkpoint-1530",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1530,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 8.169934640522877e-06,
|
| 14 |
+
"loss": 0.2238,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 1.6339869281045753e-05,
|
| 20 |
+
"loss": 0.1052,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.15,
|
| 25 |
+
"learning_rate": 2.4509803921568626e-05,
|
| 26 |
+
"loss": 0.0724,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.2,
|
| 31 |
+
"learning_rate": 3.2679738562091506e-05,
|
| 32 |
+
"loss": 0.0251,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.25,
|
| 37 |
+
"learning_rate": 4.084967320261438e-05,
|
| 38 |
+
"loss": 0.0326,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.29,
|
| 43 |
+
"learning_rate": 4.901960784313725e-05,
|
| 44 |
+
"loss": 0.0421,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.34,
|
| 49 |
+
"learning_rate": 4.920116194625999e-05,
|
| 50 |
+
"loss": 0.003,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.39,
|
| 55 |
+
"learning_rate": 4.829339143064633e-05,
|
| 56 |
+
"loss": 0.0415,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.44,
|
| 61 |
+
"learning_rate": 4.742193173565723e-05,
|
| 62 |
+
"loss": 0.0138,
|
| 63 |
+
"step": 225
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.49,
|
| 67 |
+
"learning_rate": 4.651416122004357e-05,
|
| 68 |
+
"loss": 0.0002,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.54,
|
| 73 |
+
"learning_rate": 4.5606390704429926e-05,
|
| 74 |
+
"loss": 0.0015,
|
| 75 |
+
"step": 275
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.59,
|
| 79 |
+
"learning_rate": 4.469862018881627e-05,
|
| 80 |
+
"loss": 0.0002,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.64,
|
| 85 |
+
"learning_rate": 4.379084967320262e-05,
|
| 86 |
+
"loss": 0.0164,
|
| 87 |
+
"step": 325
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.69,
|
| 91 |
+
"learning_rate": 4.295570079883805e-05,
|
| 92 |
+
"loss": 0.039,
|
| 93 |
+
"step": 350
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.74,
|
| 97 |
+
"learning_rate": 4.20479302832244e-05,
|
| 98 |
+
"loss": 0.0115,
|
| 99 |
+
"step": 375
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.78,
|
| 103 |
+
"learning_rate": 4.1140159767610744e-05,
|
| 104 |
+
"loss": 0.0002,
|
| 105 |
+
"step": 400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.83,
|
| 109 |
+
"learning_rate": 4.02323892519971e-05,
|
| 110 |
+
"loss": 0.0001,
|
| 111 |
+
"step": 425
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.88,
|
| 115 |
+
"learning_rate": 3.932461873638344e-05,
|
| 116 |
+
"loss": 0.0,
|
| 117 |
+
"step": 450
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.93,
|
| 121 |
+
"learning_rate": 3.841684822076979e-05,
|
| 122 |
+
"loss": 0.0,
|
| 123 |
+
"step": 475
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.98,
|
| 127 |
+
"learning_rate": 3.7509077705156135e-05,
|
| 128 |
+
"loss": 0.0,
|
| 129 |
+
"step": 500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.0,
|
| 133 |
+
"eval_accuracy": 0.9980411361410382,
|
| 134 |
+
"eval_auc": 0.9945804195804195,
|
| 135 |
+
"eval_f1": 0.9473684210526316,
|
| 136 |
+
"eval_loss": 0.016766857355833054,
|
| 137 |
+
"eval_precision": 1.0,
|
| 138 |
+
"eval_recall": 0.9,
|
| 139 |
+
"eval_runtime": 1.4347,
|
| 140 |
+
"eval_samples_per_second": 711.629,
|
| 141 |
+
"eval_steps_per_second": 44.608,
|
| 142 |
+
"step": 510
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.03,
|
| 146 |
+
"learning_rate": 3.6601307189542484e-05,
|
| 147 |
+
"loss": 0.0066,
|
| 148 |
+
"step": 525
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.08,
|
| 152 |
+
"learning_rate": 3.5693536673928834e-05,
|
| 153 |
+
"loss": 0.0093,
|
| 154 |
+
"step": 550
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.13,
|
| 158 |
+
"learning_rate": 3.478576615831518e-05,
|
| 159 |
+
"loss": 0.0001,
|
| 160 |
+
"step": 575
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.18,
|
| 164 |
+
"learning_rate": 3.3877995642701525e-05,
|
| 165 |
+
"loss": 0.0,
|
| 166 |
+
"step": 600
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.23,
|
| 170 |
+
"learning_rate": 3.2970225127087875e-05,
|
| 171 |
+
"loss": 0.0,
|
| 172 |
+
"step": 625
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.27,
|
| 176 |
+
"learning_rate": 3.206245461147422e-05,
|
| 177 |
+
"loss": 0.0,
|
| 178 |
+
"step": 650
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.32,
|
| 182 |
+
"learning_rate": 3.115468409586057e-05,
|
| 183 |
+
"loss": 0.0,
|
| 184 |
+
"step": 675
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.37,
|
| 188 |
+
"learning_rate": 3.0246913580246916e-05,
|
| 189 |
+
"loss": 0.0,
|
| 190 |
+
"step": 700
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.42,
|
| 194 |
+
"learning_rate": 2.9339143064633262e-05,
|
| 195 |
+
"loss": 0.0,
|
| 196 |
+
"step": 725
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.47,
|
| 200 |
+
"learning_rate": 2.8431372549019608e-05,
|
| 201 |
+
"loss": 0.0457,
|
| 202 |
+
"step": 750
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.52,
|
| 206 |
+
"learning_rate": 2.7523602033405954e-05,
|
| 207 |
+
"loss": 0.0,
|
| 208 |
+
"step": 775
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.57,
|
| 212 |
+
"learning_rate": 2.6615831517792306e-05,
|
| 213 |
+
"loss": 0.0471,
|
| 214 |
+
"step": 800
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.62,
|
| 218 |
+
"learning_rate": 2.5708061002178652e-05,
|
| 219 |
+
"loss": 0.0008,
|
| 220 |
+
"step": 825
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.67,
|
| 224 |
+
"learning_rate": 2.4800290486564998e-05,
|
| 225 |
+
"loss": 0.0001,
|
| 226 |
+
"step": 850
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.72,
|
| 230 |
+
"learning_rate": 2.3892519970951344e-05,
|
| 231 |
+
"loss": 0.0001,
|
| 232 |
+
"step": 875
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.76,
|
| 236 |
+
"learning_rate": 2.2984749455337693e-05,
|
| 237 |
+
"loss": 0.0001,
|
| 238 |
+
"step": 900
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.81,
|
| 242 |
+
"learning_rate": 2.207697893972404e-05,
|
| 243 |
+
"loss": 0.0333,
|
| 244 |
+
"step": 925
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.86,
|
| 248 |
+
"learning_rate": 2.116920842411039e-05,
|
| 249 |
+
"loss": 0.0003,
|
| 250 |
+
"step": 950
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.91,
|
| 254 |
+
"learning_rate": 2.0261437908496734e-05,
|
| 255 |
+
"loss": 0.0002,
|
| 256 |
+
"step": 975
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.96,
|
| 260 |
+
"learning_rate": 1.935366739288308e-05,
|
| 261 |
+
"loss": 0.0001,
|
| 262 |
+
"step": 1000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.0,
|
| 266 |
+
"eval_accuracy": 0.9990205680705191,
|
| 267 |
+
"eval_auc": 0.9973276723276723,
|
| 268 |
+
"eval_f1": 0.9743589743589743,
|
| 269 |
+
"eval_loss": 0.010454983450472355,
|
| 270 |
+
"eval_precision": 1.0,
|
| 271 |
+
"eval_recall": 0.95,
|
| 272 |
+
"eval_runtime": 1.4324,
|
| 273 |
+
"eval_samples_per_second": 712.791,
|
| 274 |
+
"eval_steps_per_second": 44.68,
|
| 275 |
+
"step": 1020
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.01,
|
| 279 |
+
"learning_rate": 1.844589687726943e-05,
|
| 280 |
+
"loss": 0.0001,
|
| 281 |
+
"step": 1025
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.06,
|
| 285 |
+
"learning_rate": 1.7538126361655776e-05,
|
| 286 |
+
"loss": 0.0001,
|
| 287 |
+
"step": 1050
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.11,
|
| 291 |
+
"learning_rate": 1.663035584604212e-05,
|
| 292 |
+
"loss": 0.0,
|
| 293 |
+
"step": 1075
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.16,
|
| 297 |
+
"learning_rate": 1.5722585330428467e-05,
|
| 298 |
+
"loss": 0.0001,
|
| 299 |
+
"step": 1100
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.21,
|
| 303 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 304 |
+
"loss": 0.0,
|
| 305 |
+
"step": 1125
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.25,
|
| 309 |
+
"learning_rate": 1.3907044299201164e-05,
|
| 310 |
+
"loss": 0.0001,
|
| 311 |
+
"step": 1150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.3,
|
| 315 |
+
"learning_rate": 1.299927378358751e-05,
|
| 316 |
+
"loss": 0.0001,
|
| 317 |
+
"step": 1175
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.35,
|
| 321 |
+
"learning_rate": 1.2091503267973856e-05,
|
| 322 |
+
"loss": 0.0373,
|
| 323 |
+
"step": 1200
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.4,
|
| 327 |
+
"learning_rate": 1.1183732752360204e-05,
|
| 328 |
+
"loss": 0.0547,
|
| 329 |
+
"step": 1225
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.45,
|
| 333 |
+
"learning_rate": 1.0275962236746551e-05,
|
| 334 |
+
"loss": 0.0002,
|
| 335 |
+
"step": 1250
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.5,
|
| 339 |
+
"learning_rate": 9.368191721132897e-06,
|
| 340 |
+
"loss": 0.0005,
|
| 341 |
+
"step": 1275
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.55,
|
| 345 |
+
"learning_rate": 8.460421205519245e-06,
|
| 346 |
+
"loss": 0.0001,
|
| 347 |
+
"step": 1300
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.6,
|
| 351 |
+
"learning_rate": 7.5526506899055924e-06,
|
| 352 |
+
"loss": 0.0001,
|
| 353 |
+
"step": 1325
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.65,
|
| 357 |
+
"learning_rate": 6.64488017429194e-06,
|
| 358 |
+
"loss": 0.0028,
|
| 359 |
+
"step": 1350
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.7,
|
| 363 |
+
"learning_rate": 5.737109658678287e-06,
|
| 364 |
+
"loss": 0.0,
|
| 365 |
+
"step": 1375
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.75,
|
| 369 |
+
"learning_rate": 4.8293391430646336e-06,
|
| 370 |
+
"loss": 0.0001,
|
| 371 |
+
"step": 1400
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.79,
|
| 375 |
+
"learning_rate": 3.92156862745098e-06,
|
| 376 |
+
"loss": 0.0001,
|
| 377 |
+
"step": 1425
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.84,
|
| 381 |
+
"learning_rate": 3.0137981118373275e-06,
|
| 382 |
+
"loss": 0.0001,
|
| 383 |
+
"step": 1450
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.89,
|
| 387 |
+
"learning_rate": 2.1060275962236747e-06,
|
| 388 |
+
"loss": 0.0001,
|
| 389 |
+
"step": 1475
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.94,
|
| 393 |
+
"learning_rate": 1.1982570806100219e-06,
|
| 394 |
+
"loss": 0.0001,
|
| 395 |
+
"step": 1500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.99,
|
| 399 |
+
"learning_rate": 2.904865649963689e-07,
|
| 400 |
+
"loss": 0.0,
|
| 401 |
+
"step": 1525
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.0,
|
| 405 |
+
"eval_accuracy": 0.9990205680705191,
|
| 406 |
+
"eval_auc": 0.9993006993006993,
|
| 407 |
+
"eval_f1": 0.9743589743589743,
|
| 408 |
+
"eval_loss": 0.009224997833371162,
|
| 409 |
+
"eval_precision": 1.0,
|
| 410 |
+
"eval_recall": 0.95,
|
| 411 |
+
"eval_runtime": 1.4372,
|
| 412 |
+
"eval_samples_per_second": 710.404,
|
| 413 |
+
"eval_steps_per_second": 44.531,
|
| 414 |
+
"step": 1530
|
| 415 |
+
}
|
| 416 |
+
],
|
| 417 |
+
"logging_steps": 25,
|
| 418 |
+
"max_steps": 1530,
|
| 419 |
+
"num_input_tokens_seen": 0,
|
| 420 |
+
"num_train_epochs": 3,
|
| 421 |
+
"save_steps": 500,
|
| 422 |
+
"total_flos": 805119829401600.0,
|
| 423 |
+
"train_batch_size": 8,
|
| 424 |
+
"trial_name": null,
|
| 425 |
+
"trial_params": null
|
| 426 |
+
}
|
checkpoint-1530/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b5eed36c96f038a95a5f9661aa7b44653ae66c6fef94efcc9ceb31dcd9bdc82
|
| 3 |
+
size 4728
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-german-cased",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": 0,
|
| 14 |
+
"1": 1
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"0": 0,
|
| 20 |
+
"1": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.36.1",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 30000
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9748201a9de130e50719e2f69c1088812bf19d2a7fcd8beac5ab37dad9ca3ad
|
| 3 |
+
size 436355056
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"2": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"3": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"4": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"5": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b5eed36c96f038a95a5f9661aa7b44653ae66c6fef94efcc9ceb31dcd9bdc82
|
| 3 |
+
size 4728
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "younoger/autotrain-data-autotrain-v2-test3",
|
| 3 |
+
"model": "bert-base-german-cased",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 3,
|
| 6 |
+
"max_seq_length": 128,
|
| 7 |
+
"batch_size": 8,
|
| 8 |
+
"warmup_ratio": 0.1,
|
| 9 |
+
"gradient_accumulation": 1,
|
| 10 |
+
"optimizer": "adamw_torch",
|
| 11 |
+
"scheduler": "linear",
|
| 12 |
+
"weight_decay": 0.0,
|
| 13 |
+
"max_grad_norm": 1.0,
|
| 14 |
+
"seed": 42,
|
| 15 |
+
"train_split": "train",
|
| 16 |
+
"valid_split": "validation",
|
| 17 |
+
"text_column": "autotrain_text",
|
| 18 |
+
"target_column": "autotrain_label",
|
| 19 |
+
"logging_steps": -1,
|
| 20 |
+
"project_name": "/tmp/model",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"save_strategy": "epoch",
|
| 25 |
+
"push_to_hub": true,
|
| 26 |
+
"repo_id": "younoger/autotrain-v2-test3",
|
| 27 |
+
"evaluation_strategy": "epoch",
|
| 28 |
+
"username": "younoger",
|
| 29 |
+
"log": "none"
|
| 30 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|