Training in progress, step 250
Browse files- config.json +13 -14
- model.safetensors +2 -2
- tokenizer_config.json +3 -5
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,25 +1,24 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
-
"
|
| 6 |
-
"
|
|
|
|
| 7 |
"dtype": "float32",
|
| 8 |
-
"
|
| 9 |
-
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size": 128,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size": 512,
|
| 13 |
-
"layer_norm_eps": 1e-12,
|
| 14 |
"max_position_embeddings": 512,
|
| 15 |
-
"model_type": "
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
"pad_token_id": 0,
|
| 19 |
-
"position_embedding_type": "absolute",
|
| 20 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"transformers_version": "4.56.2",
|
| 22 |
-
"type_vocab_size": 2,
|
| 23 |
-
"use_cache": true,
|
| 24 |
"vocab_size": 30522
|
| 25 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
"dtype": "float32",
|
| 10 |
+
"hidden_dim": 3072,
|
|
|
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
| 12 |
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
"pad_token_id": 0,
|
|
|
|
| 17 |
"problem_type": "single_label_classification",
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": false,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
"transformers_version": "4.56.2",
|
|
|
|
|
|
|
| 23 |
"vocab_size": 30522
|
| 24 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9be830dfdc79c33f0147d3f2e60bcb77f81a225c018286ee5aaba8d46473675e
|
| 3 |
+
size 267832560
|
tokenizer_config.json
CHANGED
|
@@ -41,18 +41,16 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"clean_up_tokenization_spaces":
|
| 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":
|
| 51 |
-
"never_split": null,
|
| 52 |
"pad_token": "[PAD]",
|
| 53 |
"sep_token": "[SEP]",
|
| 54 |
"strip_accents": null,
|
| 55 |
"tokenize_chinese_chars": true,
|
| 56 |
-
"tokenizer_class": "
|
| 57 |
"unk_token": "[UNK]"
|
| 58 |
}
|
|
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
"cls_token": "[CLS]",
|
|
|
|
| 46 |
"do_lower_case": true,
|
| 47 |
"extra_special_tokens": {},
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
|
|
|
| 50 |
"pad_token": "[PAD]",
|
| 51 |
"sep_token": "[SEP]",
|
| 52 |
"strip_accents": null,
|
| 53 |
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
"unk_token": "[UNK]"
|
| 56 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5713
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fd76c62e41f6e2ce58b11c811651bd3fae308fced154e3433c2be39a4ebc0f1
|
| 3 |
size 5713
|