Upload folder using huggingface_hub
Browse files- config.json +32 -0
- evaluation_results_notebook.json +46 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- special_tokens_map.json +7 -0
- test_metrics.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 5,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pooler_fc_size": 768,
|
| 22 |
+
"pooler_num_attention_heads": 12,
|
| 23 |
+
"pooler_num_fc_layers": 3,
|
| 24 |
+
"pooler_size_per_head": 128,
|
| 25 |
+
"pooler_type": "first_token_transform",
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.50.3",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 50000
|
| 32 |
+
}
|
evaluation_results_notebook.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_samples": 13877,
|
| 3 |
+
"accuracy": 0.8191972328313036,
|
| 4 |
+
"macro_precision": 0.7790829047956884,
|
| 5 |
+
"macro_recall": 0.7866806876855881,
|
| 6 |
+
"macro_f1": 0.7826562208743693,
|
| 7 |
+
"average_loss": 0.837552914252506,
|
| 8 |
+
"classification_report": {
|
| 9 |
+
"label_0": {
|
| 10 |
+
"precision": 0.880276602332542,
|
| 11 |
+
"recall": 0.8634338935007086,
|
| 12 |
+
"f1-score": 0.871773905044207,
|
| 13 |
+
"support": 9878.0
|
| 14 |
+
},
|
| 15 |
+
"label_1": {
|
| 16 |
+
"precision": 0.6778892072588347,
|
| 17 |
+
"recall": 0.7099274818704676,
|
| 18 |
+
"f1-score": 0.6935385367045316,
|
| 19 |
+
"support": 3999.0
|
| 20 |
+
},
|
| 21 |
+
"accuracy": 0.8191972328313036,
|
| 22 |
+
"macro avg": {
|
| 23 |
+
"precision": 0.7790829047956884,
|
| 24 |
+
"recall": 0.7866806876855881,
|
| 25 |
+
"f1-score": 0.7826562208743693,
|
| 26 |
+
"support": 13877.0
|
| 27 |
+
},
|
| 28 |
+
"weighted avg": {
|
| 29 |
+
"precision": 0.8219536800222621,
|
| 30 |
+
"recall": 0.8191972328313036,
|
| 31 |
+
"f1-score": 0.8204109852495568,
|
| 32 |
+
"support": 13877.0
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"confusion_matrix": [
|
| 36 |
+
[
|
| 37 |
+
8529,
|
| 38 |
+
1349
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
1160,
|
| 42 |
+
2839
|
| 43 |
+
]
|
| 44 |
+
],
|
| 45 |
+
"evaluation_duration_seconds": 177.72954201698303
|
| 46 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:216e88b4e2e1f65e016576d7dfb5837d7edc346b9ab614c0047bbdef4691d82a
|
| 3 |
+
size 497795072
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9336ace4396989ba2f8fb0864fc01d75566dde06161ac43f930f538278bbdfd9
|
| 3 |
+
size 995711034
|
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 |
+
}
|
test_metrics.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"accuracy": 0.8865733849359928,
|
| 3 |
+
"macro_precision": 0.8772256008206331,
|
| 4 |
+
"macro_recall": 0.8361628900067384,
|
| 5 |
+
"macro_f1": 0.8531230288690632,
|
| 6 |
+
"average_loss": 0.5036396079513776,
|
| 7 |
+
"train_loss_sample_weighted": 0.17769948870748825,
|
| 8 |
+
"classification_report_str": " precision recall f1-score support\n\n label_0 0.90 0.95 0.92 4806\n label_1 0.86 0.72 0.78 1912\n\n accuracy 0.89 6718\n macro avg 0.88 0.84 0.85 6718\nweighted avg 0.88 0.89 0.88 6718\n"
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 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 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|