Training in progress, epoch 1
Browse files- config.json +18 -16
- model.safetensors +2 -2
- runs/Dec06_12-03-07_d7de64af26e3/events.out.tfevents.1733486589.d7de64af26e3.23.0 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +3 -2
- training_args.bin +2 -2
- vocab.txt +0 -0
config.json
CHANGED
|
@@ -1,13 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
|
|
|
|
|
|
| 11 |
"id2label": {
|
| 12 |
"0": "LABEL_0",
|
| 13 |
"1": "LABEL_1",
|
|
@@ -17,6 +18,7 @@
|
|
| 17 |
"5": "LABEL_5"
|
| 18 |
},
|
| 19 |
"initializer_range": 0.02,
|
|
|
|
| 20 |
"label2id": {
|
| 21 |
"LABEL_0": 0,
|
| 22 |
"LABEL_1": 1,
|
|
@@ -25,17 +27,17 @@
|
|
| 25 |
"LABEL_4": 4,
|
| 26 |
"LABEL_5": 5
|
| 27 |
},
|
|
|
|
| 28 |
"max_position_embeddings": 512,
|
| 29 |
-
"model_type": "
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
"pad_token_id": 0,
|
|
|
|
| 33 |
"problem_type": "single_label_classification",
|
| 34 |
-
"qa_dropout": 0.1,
|
| 35 |
-
"seq_classif_dropout": 0.2,
|
| 36 |
-
"sinusoidal_pos_embds": false,
|
| 37 |
-
"tie_weights_": true,
|
| 38 |
"torch_dtype": "float32",
|
| 39 |
-
"transformers_version": "4.
|
| 40 |
-
"
|
|
|
|
|
|
|
| 41 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "bert-base-cased",
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
"id2label": {
|
| 13 |
"0": "LABEL_0",
|
| 14 |
"1": "LABEL_1",
|
|
|
|
| 18 |
"5": "LABEL_5"
|
| 19 |
},
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
"label2id": {
|
| 23 |
"LABEL_0": 0,
|
| 24 |
"LABEL_1": 1,
|
|
|
|
| 27 |
"LABEL_4": 4,
|
| 28 |
"LABEL_5": 5
|
| 29 |
},
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
"max_position_embeddings": 512,
|
| 32 |
+
"model_type": "bert",
|
| 33 |
+
"num_attention_heads": 12,
|
| 34 |
+
"num_hidden_layers": 12,
|
| 35 |
"pad_token_id": 0,
|
| 36 |
+
"position_embedding_type": "absolute",
|
| 37 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.47.0",
|
| 40 |
+
"type_vocab_size": 2,
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 28996
|
| 43 |
}
|
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 sha256:0b9b13ecaea6dbddb702aa136484ea79a5e5b32faaa0bfc760f56cc298526de0
|
| 3 |
+
size 433283072
|
runs/Dec06_12-03-07_d7de64af26e3/events.out.tfevents.1733486589.d7de64af26e3.23.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cf5dea3a3c25ddbccfced77aa18ae964200a815efb423cc9836c51cb20da81c
|
| 3 |
+
size 5646
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -43,13 +43,14 @@
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": false,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
-
"do_lower_case":
|
|
|
|
| 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": "
|
| 54 |
"unk_token": "[UNK]"
|
| 55 |
}
|
|
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": false,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 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": "BertTokenizer",
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24b7255ef06cae714577c20cfba169729ac910cad4d8eda6c469c7229f966cb6
|
| 3 |
+
size 5368
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|