Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-6000/config.json +54 -0
- checkpoint-6000/model.safetensors +3 -0
- checkpoint-6000/optimizer.pt +3 -0
- checkpoint-6000/rng_state.pth +3 -0
- checkpoint-6000/scheduler.pt +3 -0
- checkpoint-6000/trainer_state.json +297 -0
- checkpoint-6000/training_args.bin +3 -0
- config.json +54 -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 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
widget:
|
| 7 |
+
- text: "I love AutoTrain"
|
| 8 |
+
datasets:
|
| 9 |
+
- autotrain-rqsu1-nelrs/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.8727797865867615
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.4743843561639563
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.7148333333333333
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.6973841930196186
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.689196184834718
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.7148333333333333
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.7078896728033317
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.41641019062275997
|
| 32 |
+
|
| 33 |
+
recall_micro: 0.7148333333333333
|
| 34 |
+
|
| 35 |
+
recall_weighted: 0.7148333333333333
|
| 36 |
+
|
| 37 |
+
accuracy: 0.7148333333333333
|
checkpoint-6000/config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 11,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": 0,
|
| 15 |
+
"1": 1,
|
| 16 |
+
"2": 2,
|
| 17 |
+
"3": 3,
|
| 18 |
+
"4": 4,
|
| 19 |
+
"5": 5,
|
| 20 |
+
"6": 6,
|
| 21 |
+
"7": 7,
|
| 22 |
+
"8": 8,
|
| 23 |
+
"9": 9,
|
| 24 |
+
"10": 10
|
| 25 |
+
},
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 3072,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"0": 0,
|
| 30 |
+
"1": 1,
|
| 31 |
+
"2": 2,
|
| 32 |
+
"3": 3,
|
| 33 |
+
"4": 4,
|
| 34 |
+
"5": 5,
|
| 35 |
+
"6": 6,
|
| 36 |
+
"7": 7,
|
| 37 |
+
"8": 8,
|
| 38 |
+
"9": 9,
|
| 39 |
+
"10": 10
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-12,
|
| 42 |
+
"max_position_embeddings": 512,
|
| 43 |
+
"model_type": "bert",
|
| 44 |
+
"num_attention_heads": 12,
|
| 45 |
+
"num_hidden_layers": 12,
|
| 46 |
+
"pad_token_id": 0,
|
| 47 |
+
"position_embedding_type": "absolute",
|
| 48 |
+
"problem_type": "single_label_classification",
|
| 49 |
+
"torch_dtype": "float32",
|
| 50 |
+
"transformers_version": "4.37.0",
|
| 51 |
+
"type_vocab_size": 2,
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 30522
|
| 54 |
+
}
|
checkpoint-6000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d817e81efc74d4b7fc1dcfd07d035502ffc6996789aa45ffd45bcb67e0af4eb
|
| 3 |
+
size 437986332
|
checkpoint-6000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4311cfc2d6326c7ccfda52d87d2b2ce9c9cdbd96a9feb65ec87a2c9003c84697
|
| 3 |
+
size 876093690
|
checkpoint-6000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e8147980a4412e83fcb06adcc8b8b505b05ff43aff4d87d935431085bb0d3c1
|
| 3 |
+
size 14244
|
checkpoint-6000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76f57b12b003374c71fc38620866b4630c864d7d26196f7fb1d285d7f81116c4
|
| 3 |
+
size 1064
|
checkpoint-6000/trainer_state.json
ADDED
|
@@ -0,0 +1,297 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8727797865867615,
|
| 3 |
+
"best_model_checkpoint": "autotrain-rqsu1-nelrs/checkpoint-6000",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6000,
|
| 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": 8.222222222222223e-06,
|
| 14 |
+
"loss": 2.2551,
|
| 15 |
+
"step": 150
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 1.65e-05,
|
| 20 |
+
"loss": 1.533,
|
| 21 |
+
"step": 300
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.15,
|
| 25 |
+
"learning_rate": 2.4833333333333335e-05,
|
| 26 |
+
"loss": 1.3785,
|
| 27 |
+
"step": 450
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.2,
|
| 31 |
+
"learning_rate": 3.316666666666667e-05,
|
| 32 |
+
"loss": 1.2836,
|
| 33 |
+
"step": 600
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.25,
|
| 37 |
+
"learning_rate": 4.15e-05,
|
| 38 |
+
"loss": 1.2161,
|
| 39 |
+
"step": 750
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.3,
|
| 43 |
+
"learning_rate": 4.9833333333333336e-05,
|
| 44 |
+
"loss": 1.1853,
|
| 45 |
+
"step": 900
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.35,
|
| 49 |
+
"learning_rate": 4.9092592592592595e-05,
|
| 50 |
+
"loss": 1.1863,
|
| 51 |
+
"step": 1050
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4,
|
| 55 |
+
"learning_rate": 4.8166666666666674e-05,
|
| 56 |
+
"loss": 1.1578,
|
| 57 |
+
"step": 1200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.45,
|
| 61 |
+
"learning_rate": 4.724074074074074e-05,
|
| 62 |
+
"loss": 1.1281,
|
| 63 |
+
"step": 1350
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.5,
|
| 67 |
+
"learning_rate": 4.631481481481481e-05,
|
| 68 |
+
"loss": 1.0885,
|
| 69 |
+
"step": 1500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.55,
|
| 73 |
+
"learning_rate": 4.538888888888889e-05,
|
| 74 |
+
"loss": 1.0728,
|
| 75 |
+
"step": 1650
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.6,
|
| 79 |
+
"learning_rate": 4.4462962962962966e-05,
|
| 80 |
+
"loss": 1.0805,
|
| 81 |
+
"step": 1800
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.65,
|
| 85 |
+
"learning_rate": 4.353703703703704e-05,
|
| 86 |
+
"loss": 1.0485,
|
| 87 |
+
"step": 1950
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7,
|
| 91 |
+
"learning_rate": 4.261111111111111e-05,
|
| 92 |
+
"loss": 1.0415,
|
| 93 |
+
"step": 2100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.75,
|
| 97 |
+
"learning_rate": 4.168518518518519e-05,
|
| 98 |
+
"loss": 0.9634,
|
| 99 |
+
"step": 2250
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.8,
|
| 103 |
+
"learning_rate": 4.0759259259259264e-05,
|
| 104 |
+
"loss": 0.9934,
|
| 105 |
+
"step": 2400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.85,
|
| 109 |
+
"learning_rate": 3.9839506172839506e-05,
|
| 110 |
+
"loss": 0.9743,
|
| 111 |
+
"step": 2550
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.9,
|
| 115 |
+
"learning_rate": 3.8913580246913585e-05,
|
| 116 |
+
"loss": 1.0402,
|
| 117 |
+
"step": 2700
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.95,
|
| 121 |
+
"learning_rate": 3.798765432098765e-05,
|
| 122 |
+
"loss": 0.9291,
|
| 123 |
+
"step": 2850
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0,
|
| 127 |
+
"learning_rate": 3.706172839506173e-05,
|
| 128 |
+
"loss": 0.999,
|
| 129 |
+
"step": 3000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.0,
|
| 133 |
+
"eval_accuracy": 0.6781666666666667,
|
| 134 |
+
"eval_f1_macro": 0.417421299699202,
|
| 135 |
+
"eval_f1_micro": 0.6781666666666667,
|
| 136 |
+
"eval_f1_weighted": 0.6526203782124326,
|
| 137 |
+
"eval_loss": 0.9398497939109802,
|
| 138 |
+
"eval_precision_macro": 0.53233579791898,
|
| 139 |
+
"eval_precision_micro": 0.6781666666666667,
|
| 140 |
+
"eval_precision_weighted": 0.6686669761134056,
|
| 141 |
+
"eval_recall_macro": 0.37103282997495,
|
| 142 |
+
"eval_recall_micro": 0.6781666666666667,
|
| 143 |
+
"eval_recall_weighted": 0.6781666666666667,
|
| 144 |
+
"eval_runtime": 13.8601,
|
| 145 |
+
"eval_samples_per_second": 432.897,
|
| 146 |
+
"eval_steps_per_second": 27.056,
|
| 147 |
+
"step": 3000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.05,
|
| 151 |
+
"learning_rate": 3.6135802469135804e-05,
|
| 152 |
+
"loss": 0.8418,
|
| 153 |
+
"step": 3150
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.1,
|
| 157 |
+
"learning_rate": 3.520987654320988e-05,
|
| 158 |
+
"loss": 0.7844,
|
| 159 |
+
"step": 3300
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.15,
|
| 163 |
+
"learning_rate": 3.428395061728395e-05,
|
| 164 |
+
"loss": 0.853,
|
| 165 |
+
"step": 3450
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.2,
|
| 169 |
+
"learning_rate": 3.335802469135802e-05,
|
| 170 |
+
"loss": 0.8219,
|
| 171 |
+
"step": 3600
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.25,
|
| 175 |
+
"learning_rate": 3.24320987654321e-05,
|
| 176 |
+
"loss": 0.8721,
|
| 177 |
+
"step": 3750
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.3,
|
| 181 |
+
"learning_rate": 3.1506172839506175e-05,
|
| 182 |
+
"loss": 0.7844,
|
| 183 |
+
"step": 3900
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.35,
|
| 187 |
+
"learning_rate": 3.058024691358025e-05,
|
| 188 |
+
"loss": 0.8645,
|
| 189 |
+
"step": 4050
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.4,
|
| 193 |
+
"learning_rate": 2.965432098765432e-05,
|
| 194 |
+
"loss": 0.7823,
|
| 195 |
+
"step": 4200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.45,
|
| 199 |
+
"learning_rate": 2.8728395061728397e-05,
|
| 200 |
+
"loss": 0.7494,
|
| 201 |
+
"step": 4350
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.5,
|
| 205 |
+
"learning_rate": 2.7802469135802474e-05,
|
| 206 |
+
"loss": 0.8125,
|
| 207 |
+
"step": 4500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.55,
|
| 211 |
+
"learning_rate": 2.6876543209876543e-05,
|
| 212 |
+
"loss": 0.7879,
|
| 213 |
+
"step": 4650
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.6,
|
| 217 |
+
"learning_rate": 2.595061728395062e-05,
|
| 218 |
+
"loss": 0.8092,
|
| 219 |
+
"step": 4800
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.65,
|
| 223 |
+
"learning_rate": 2.5024691358024692e-05,
|
| 224 |
+
"loss": 0.7535,
|
| 225 |
+
"step": 4950
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.7,
|
| 229 |
+
"learning_rate": 2.4098765432098765e-05,
|
| 230 |
+
"loss": 0.7787,
|
| 231 |
+
"step": 5100
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.75,
|
| 235 |
+
"learning_rate": 2.317283950617284e-05,
|
| 236 |
+
"loss": 0.8109,
|
| 237 |
+
"step": 5250
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.8,
|
| 241 |
+
"learning_rate": 2.2246913580246914e-05,
|
| 242 |
+
"loss": 0.7853,
|
| 243 |
+
"step": 5400
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.85,
|
| 247 |
+
"learning_rate": 2.132098765432099e-05,
|
| 248 |
+
"loss": 0.7999,
|
| 249 |
+
"step": 5550
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.9,
|
| 253 |
+
"learning_rate": 2.0395061728395064e-05,
|
| 254 |
+
"loss": 0.7545,
|
| 255 |
+
"step": 5700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.95,
|
| 259 |
+
"learning_rate": 1.9469135802469137e-05,
|
| 260 |
+
"loss": 0.7805,
|
| 261 |
+
"step": 5850
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.0,
|
| 265 |
+
"learning_rate": 1.854320987654321e-05,
|
| 266 |
+
"loss": 0.741,
|
| 267 |
+
"step": 6000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.0,
|
| 271 |
+
"eval_accuracy": 0.7148333333333333,
|
| 272 |
+
"eval_f1_macro": 0.4743843561639563,
|
| 273 |
+
"eval_f1_micro": 0.7148333333333333,
|
| 274 |
+
"eval_f1_weighted": 0.6973841930196186,
|
| 275 |
+
"eval_loss": 0.8727797865867615,
|
| 276 |
+
"eval_precision_macro": 0.689196184834718,
|
| 277 |
+
"eval_precision_micro": 0.7148333333333333,
|
| 278 |
+
"eval_precision_weighted": 0.7078896728033317,
|
| 279 |
+
"eval_recall_macro": 0.41641019062275997,
|
| 280 |
+
"eval_recall_micro": 0.7148333333333333,
|
| 281 |
+
"eval_recall_weighted": 0.7148333333333333,
|
| 282 |
+
"eval_runtime": 13.8166,
|
| 283 |
+
"eval_samples_per_second": 434.26,
|
| 284 |
+
"eval_steps_per_second": 27.141,
|
| 285 |
+
"step": 6000
|
| 286 |
+
}
|
| 287 |
+
],
|
| 288 |
+
"logging_steps": 150,
|
| 289 |
+
"max_steps": 9000,
|
| 290 |
+
"num_input_tokens_seen": 0,
|
| 291 |
+
"num_train_epochs": 3,
|
| 292 |
+
"save_steps": 500,
|
| 293 |
+
"total_flos": 3157587800064000.0,
|
| 294 |
+
"train_batch_size": 8,
|
| 295 |
+
"trial_name": null,
|
| 296 |
+
"trial_params": null
|
| 297 |
+
}
|
checkpoint-6000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6da5e30a3ef2a7c8718bce9ea0feed3aea75852257f56c9940fa20993d1343c2
|
| 3 |
+
size 4728
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 11,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": 0,
|
| 15 |
+
"1": 1,
|
| 16 |
+
"2": 2,
|
| 17 |
+
"3": 3,
|
| 18 |
+
"4": 4,
|
| 19 |
+
"5": 5,
|
| 20 |
+
"6": 6,
|
| 21 |
+
"7": 7,
|
| 22 |
+
"8": 8,
|
| 23 |
+
"9": 9,
|
| 24 |
+
"10": 10
|
| 25 |
+
},
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 3072,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"0": 0,
|
| 30 |
+
"1": 1,
|
| 31 |
+
"2": 2,
|
| 32 |
+
"3": 3,
|
| 33 |
+
"4": 4,
|
| 34 |
+
"5": 5,
|
| 35 |
+
"6": 6,
|
| 36 |
+
"7": 7,
|
| 37 |
+
"8": 8,
|
| 38 |
+
"9": 9,
|
| 39 |
+
"10": 10
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-12,
|
| 42 |
+
"max_position_embeddings": 512,
|
| 43 |
+
"model_type": "bert",
|
| 44 |
+
"num_attention_heads": 12,
|
| 45 |
+
"num_hidden_layers": 12,
|
| 46 |
+
"pad_token_id": 0,
|
| 47 |
+
"position_embedding_type": "absolute",
|
| 48 |
+
"problem_type": "single_label_classification",
|
| 49 |
+
"torch_dtype": "float32",
|
| 50 |
+
"transformers_version": "4.37.0",
|
| 51 |
+
"type_vocab_size": 2,
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 30522
|
| 54 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d817e81efc74d4b7fc1dcfd07d035502ffc6996789aa45ffd45bcb67e0af4eb
|
| 3 |
+
size 437986332
|
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 |
+
"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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 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 sha256:6da5e30a3ef2a7c8718bce9ea0feed3aea75852257f56c9940fa20993d1343c2
|
| 3 |
+
size 4728
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-rqsu1-nelrs/autotrain-data",
|
| 3 |
+
"model": "google-bert/bert-base-uncased",
|
| 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-rqsu1-nelrs",
|
| 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": "pruhtopia/autotrain-rqsu1-nelrs",
|
| 27 |
+
"evaluation_strategy": "epoch",
|
| 28 |
+
"username": "pruhtopia",
|
| 29 |
+
"log": "none"
|
| 30 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|