Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-6394/config.json +36 -0
- checkpoint-6394/model.safetensors +3 -0
- checkpoint-6394/optimizer.pt +3 -0
- checkpoint-6394/rng_state.pth +3 -0
- checkpoint-6394/scheduler.pt +3 -0
- checkpoint-6394/trainer_state.json +327 -0
- checkpoint-6394/training_args.bin +3 -0
- config.json +36 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -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 |
+
- autotrain-2t1ic-d661v/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.1272398680448532
|
| 18 |
+
|
| 19 |
+
f1: 0.7869222096956031
|
| 20 |
+
|
| 21 |
+
precision: 0.7949886104783599
|
| 22 |
+
|
| 23 |
+
recall: 0.7790178571428571
|
| 24 |
+
|
| 25 |
+
auc: 0.9779004715847651
|
| 26 |
+
|
| 27 |
+
accuracy: 0.9704364148287189
|
checkpoint-6394/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"activation": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"DistilBertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"dim": 768,
|
| 10 |
+
"dropout": 0.1,
|
| 11 |
+
"finetuning_task": "sst-2",
|
| 12 |
+
"hidden_dim": 3072,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": 0,
|
| 15 |
+
"1": 1
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"0": 0,
|
| 20 |
+
"1": 1
|
| 21 |
+
},
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "distilbert",
|
| 24 |
+
"n_heads": 12,
|
| 25 |
+
"n_layers": 6,
|
| 26 |
+
"output_past": true,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qa_dropout": 0.1,
|
| 30 |
+
"seq_classif_dropout": 0.2,
|
| 31 |
+
"sinusoidal_pos_embds": false,
|
| 32 |
+
"tie_weights_": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.38.2",
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
checkpoint-6394/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df2be0aa3ca51b8edb56d84e6a8c6da754e039f6b7bf8d6c25fb5fbdaf781793
|
| 3 |
+
size 267832560
|
checkpoint-6394/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbcc84bd2a71afb387dfa0d8c57d386a5ba765080888b036563dc0f90ef1c823
|
| 3 |
+
size 535724410
|
checkpoint-6394/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30bee460298c66df58de2c372aef5d75245eec6679733a0717afce6a13f89031
|
| 3 |
+
size 13990
|
checkpoint-6394/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c907b3d4727338c781661950145481de729c08b86ec5bfe250e696d8e100d98
|
| 3 |
+
size 1064
|
checkpoint-6394/trainer_state.json
ADDED
|
@@ -0,0 +1,327 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.1272398680448532,
|
| 3 |
+
"best_model_checkpoint": "autotrain-2t1ic-d661v/checkpoint-6394",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6394,
|
| 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 |
+
"grad_norm": 3.1554582118988037,
|
| 14 |
+
"learning_rate": 8.28125e-06,
|
| 15 |
+
"loss": 0.937,
|
| 16 |
+
"step": 159
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 0.7134726643562317,
|
| 21 |
+
"learning_rate": 1.65625e-05,
|
| 22 |
+
"loss": 0.2178,
|
| 23 |
+
"step": 318
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 3.067269802093506,
|
| 28 |
+
"learning_rate": 2.484375e-05,
|
| 29 |
+
"loss": 0.2279,
|
| 30 |
+
"step": 477
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 3.953152656555176,
|
| 35 |
+
"learning_rate": 3.3125e-05,
|
| 36 |
+
"loss": 0.2313,
|
| 37 |
+
"step": 636
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 19.392597198486328,
|
| 42 |
+
"learning_rate": 4.140625e-05,
|
| 43 |
+
"loss": 0.1997,
|
| 44 |
+
"step": 795
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 0.18459168076515198,
|
| 49 |
+
"learning_rate": 4.96875e-05,
|
| 50 |
+
"loss": 0.1585,
|
| 51 |
+
"step": 954
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 0.036189883947372437,
|
| 56 |
+
"learning_rate": 4.9113660062565175e-05,
|
| 57 |
+
"loss": 0.1673,
|
| 58 |
+
"step": 1113
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 20.717161178588867,
|
| 63 |
+
"learning_rate": 4.8192561696211335e-05,
|
| 64 |
+
"loss": 0.1645,
|
| 65 |
+
"step": 1272
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 3.4379196166992188,
|
| 70 |
+
"learning_rate": 4.727146332985749e-05,
|
| 71 |
+
"loss": 0.1448,
|
| 72 |
+
"step": 1431
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 0.0559392012655735,
|
| 77 |
+
"learning_rate": 4.635036496350365e-05,
|
| 78 |
+
"loss": 0.1412,
|
| 79 |
+
"step": 1590
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.55,
|
| 83 |
+
"grad_norm": 0.04697013273835182,
|
| 84 |
+
"learning_rate": 4.5429266597149814e-05,
|
| 85 |
+
"loss": 0.1501,
|
| 86 |
+
"step": 1749
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"grad_norm": 0.027782494202256203,
|
| 91 |
+
"learning_rate": 4.4508168230795974e-05,
|
| 92 |
+
"loss": 0.1596,
|
| 93 |
+
"step": 1908
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"grad_norm": 0.26669323444366455,
|
| 98 |
+
"learning_rate": 4.3587069864442134e-05,
|
| 99 |
+
"loss": 0.1686,
|
| 100 |
+
"step": 2067
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7,
|
| 104 |
+
"grad_norm": 6.07758092880249,
|
| 105 |
+
"learning_rate": 4.266597149808829e-05,
|
| 106 |
+
"loss": 0.1741,
|
| 107 |
+
"step": 2226
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.75,
|
| 111 |
+
"grad_norm": 0.06619926542043686,
|
| 112 |
+
"learning_rate": 4.174487313173445e-05,
|
| 113 |
+
"loss": 0.1287,
|
| 114 |
+
"step": 2385
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"grad_norm": 0.1769120991230011,
|
| 119 |
+
"learning_rate": 4.082377476538061e-05,
|
| 120 |
+
"loss": 0.1629,
|
| 121 |
+
"step": 2544
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.85,
|
| 125 |
+
"grad_norm": 0.7576848864555359,
|
| 126 |
+
"learning_rate": 3.990267639902677e-05,
|
| 127 |
+
"loss": 0.136,
|
| 128 |
+
"step": 2703
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"grad_norm": 0.10874854773283005,
|
| 133 |
+
"learning_rate": 3.8981578032672927e-05,
|
| 134 |
+
"loss": 0.127,
|
| 135 |
+
"step": 2862
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.94,
|
| 139 |
+
"grad_norm": 6.004174709320068,
|
| 140 |
+
"learning_rate": 3.806047966631908e-05,
|
| 141 |
+
"loss": 0.1193,
|
| 142 |
+
"step": 3021
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.99,
|
| 146 |
+
"grad_norm": 0.25709450244903564,
|
| 147 |
+
"learning_rate": 3.713938129996524e-05,
|
| 148 |
+
"loss": 0.1277,
|
| 149 |
+
"step": 3180
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.9488503050211169,
|
| 154 |
+
"eval_auc": 0.9710095518442868,
|
| 155 |
+
"eval_f1": 0.6929577464788733,
|
| 156 |
+
"eval_loss": 0.15181826055049896,
|
| 157 |
+
"eval_precision": 0.5980551053484603,
|
| 158 |
+
"eval_recall": 0.8236607142857143,
|
| 159 |
+
"eval_runtime": 595.045,
|
| 160 |
+
"eval_samples_per_second": 10.744,
|
| 161 |
+
"eval_steps_per_second": 0.672,
|
| 162 |
+
"step": 3197
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.04,
|
| 166 |
+
"grad_norm": 0.4182649850845337,
|
| 167 |
+
"learning_rate": 3.62182829336114e-05,
|
| 168 |
+
"loss": 0.1071,
|
| 169 |
+
"step": 3339
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.09,
|
| 173 |
+
"grad_norm": 0.09685356914997101,
|
| 174 |
+
"learning_rate": 3.5297184567257566e-05,
|
| 175 |
+
"loss": 0.0737,
|
| 176 |
+
"step": 3498
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.14,
|
| 180 |
+
"grad_norm": 44.25665283203125,
|
| 181 |
+
"learning_rate": 3.4376086200903726e-05,
|
| 182 |
+
"loss": 0.0923,
|
| 183 |
+
"step": 3657
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.19,
|
| 187 |
+
"grad_norm": 0.017466088756918907,
|
| 188 |
+
"learning_rate": 3.345498783454988e-05,
|
| 189 |
+
"loss": 0.0972,
|
| 190 |
+
"step": 3816
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.24,
|
| 194 |
+
"grad_norm": 0.06699241697788239,
|
| 195 |
+
"learning_rate": 3.253388946819604e-05,
|
| 196 |
+
"loss": 0.0743,
|
| 197 |
+
"step": 3975
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.29,
|
| 201 |
+
"grad_norm": 0.028020156547427177,
|
| 202 |
+
"learning_rate": 3.16127911018422e-05,
|
| 203 |
+
"loss": 0.0872,
|
| 204 |
+
"step": 4134
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.34,
|
| 208 |
+
"grad_norm": 19.901599884033203,
|
| 209 |
+
"learning_rate": 3.069169273548836e-05,
|
| 210 |
+
"loss": 0.0947,
|
| 211 |
+
"step": 4293
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.39,
|
| 215 |
+
"grad_norm": 0.458806574344635,
|
| 216 |
+
"learning_rate": 2.977059436913452e-05,
|
| 217 |
+
"loss": 0.0837,
|
| 218 |
+
"step": 4452
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.44,
|
| 222 |
+
"grad_norm": 1.4870176315307617,
|
| 223 |
+
"learning_rate": 2.8849496002780675e-05,
|
| 224 |
+
"loss": 0.0793,
|
| 225 |
+
"step": 4611
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.49,
|
| 229 |
+
"grad_norm": 0.014602471143007278,
|
| 230 |
+
"learning_rate": 2.7928397636426835e-05,
|
| 231 |
+
"loss": 0.0917,
|
| 232 |
+
"step": 4770
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.54,
|
| 236 |
+
"grad_norm": 0.010597724467515945,
|
| 237 |
+
"learning_rate": 2.7007299270072995e-05,
|
| 238 |
+
"loss": 0.0761,
|
| 239 |
+
"step": 4929
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.59,
|
| 243 |
+
"grad_norm": 0.01183533389121294,
|
| 244 |
+
"learning_rate": 2.6086200903719154e-05,
|
| 245 |
+
"loss": 0.0607,
|
| 246 |
+
"step": 5088
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.64,
|
| 250 |
+
"grad_norm": 0.050857510417699814,
|
| 251 |
+
"learning_rate": 2.5165102537365314e-05,
|
| 252 |
+
"loss": 0.0698,
|
| 253 |
+
"step": 5247
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.69,
|
| 257 |
+
"grad_norm": 0.059834353625774384,
|
| 258 |
+
"learning_rate": 2.424400417101147e-05,
|
| 259 |
+
"loss": 0.0907,
|
| 260 |
+
"step": 5406
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.74,
|
| 264 |
+
"grad_norm": 0.04689362645149231,
|
| 265 |
+
"learning_rate": 2.332290580465763e-05,
|
| 266 |
+
"loss": 0.0715,
|
| 267 |
+
"step": 5565
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.79,
|
| 271 |
+
"grad_norm": 0.02181609719991684,
|
| 272 |
+
"learning_rate": 2.240180743830379e-05,
|
| 273 |
+
"loss": 0.0777,
|
| 274 |
+
"step": 5724
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.84,
|
| 278 |
+
"grad_norm": 0.010604546405375004,
|
| 279 |
+
"learning_rate": 2.1480709071949947e-05,
|
| 280 |
+
"loss": 0.061,
|
| 281 |
+
"step": 5883
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.89,
|
| 285 |
+
"grad_norm": 0.044349148869514465,
|
| 286 |
+
"learning_rate": 2.0559610705596107e-05,
|
| 287 |
+
"loss": 0.0648,
|
| 288 |
+
"step": 6042
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.94,
|
| 292 |
+
"grad_norm": 74.56462860107422,
|
| 293 |
+
"learning_rate": 1.9638512339242267e-05,
|
| 294 |
+
"loss": 0.0816,
|
| 295 |
+
"step": 6201
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.99,
|
| 299 |
+
"grad_norm": 0.01588965579867363,
|
| 300 |
+
"learning_rate": 1.8717413972888427e-05,
|
| 301 |
+
"loss": 0.0619,
|
| 302 |
+
"step": 6360
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"eval_accuracy": 0.9704364148287189,
|
| 307 |
+
"eval_auc": 0.9779004715847651,
|
| 308 |
+
"eval_f1": 0.7869222096956031,
|
| 309 |
+
"eval_loss": 0.1272398680448532,
|
| 310 |
+
"eval_precision": 0.7949886104783599,
|
| 311 |
+
"eval_recall": 0.7790178571428571,
|
| 312 |
+
"eval_runtime": 543.9479,
|
| 313 |
+
"eval_samples_per_second": 11.753,
|
| 314 |
+
"eval_steps_per_second": 0.735,
|
| 315 |
+
"step": 6394
|
| 316 |
+
}
|
| 317 |
+
],
|
| 318 |
+
"logging_steps": 159,
|
| 319 |
+
"max_steps": 9591,
|
| 320 |
+
"num_input_tokens_seen": 0,
|
| 321 |
+
"num_train_epochs": 3,
|
| 322 |
+
"save_steps": 500,
|
| 323 |
+
"total_flos": 1693529458117632.0,
|
| 324 |
+
"train_batch_size": 8,
|
| 325 |
+
"trial_name": null,
|
| 326 |
+
"trial_params": null
|
| 327 |
+
}
|
checkpoint-6394/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d739182b7976fff686e822a701fb96816beb8f24420446af5b91a50057cfb60
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"activation": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"DistilBertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"dim": 768,
|
| 10 |
+
"dropout": 0.1,
|
| 11 |
+
"finetuning_task": "sst-2",
|
| 12 |
+
"hidden_dim": 3072,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": 0,
|
| 15 |
+
"1": 1
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"0": 0,
|
| 20 |
+
"1": 1
|
| 21 |
+
},
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "distilbert",
|
| 24 |
+
"n_heads": 12,
|
| 25 |
+
"n_layers": 6,
|
| 26 |
+
"output_past": true,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qa_dropout": 0.1,
|
| 30 |
+
"seq_classif_dropout": 0.2,
|
| 31 |
+
"sinusoidal_pos_embds": false,
|
| 32 |
+
"tie_weights_": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.38.2",
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df2be0aa3ca51b8edb56d84e6a8c6da754e039f6b7bf8d6c25fb5fbdaf781793
|
| 3 |
+
size 267832560
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d739182b7976fff686e822a701fb96816beb8f24420446af5b91a50057cfb60
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-2t1ic-d661v/autotrain-data",
|
| 3 |
+
"model": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
|
| 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": "autotrain-2t1ic-d661v",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": null,
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"save_strategy": "epoch",
|
| 25 |
+
"push_to_hub": true,
|
| 26 |
+
"repo_id": "mykahh/autotrain-2t1ic-d661v",
|
| 27 |
+
"evaluation_strategy": "epoch",
|
| 28 |
+
"username": "mykahh",
|
| 29 |
+
"log": "none"
|
| 30 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|