Commit ·
131f264
1
Parent(s): e143852
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +75 -0
- pytorch_model.bin +3 -0
- runs/Oct27_17-44-27_47972f860fae/1666892684.163216/events.out.tfevents.1666892684.47972f860fae.105.1 +3 -0
- runs/Oct27_17-44-27_47972f860fae/events.out.tfevents.1666892684.47972f860fae.105.0 +3 -0
- runs/Oct27_17-48-35_47972f860fae/1666892922.069158/events.out.tfevents.1666892922.47972f860fae.105.3 +3 -0
- runs/Oct27_17-48-35_47972f860fae/events.out.tfevents.1666892922.47972f860fae.105.2 +3 -0
- runs/Oct27_17-53-11_47972f860fae/1666893198.2652752/events.out.tfevents.1666893198.47972f860fae.105.5 +3 -0
- runs/Oct27_17-53-11_47972f860fae/events.out.tfevents.1666893198.47972f860fae.105.4 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/sbert_longformer_ecthr_b_simcse/train_simcse-_root_.local_share_jupyter_runtime_kernel-702ca39d-5545-4b00-b884-05176c135763.json-2022-10-21_08-44-17/1500",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongformerForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_mode": "longformer",
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"attention_window": [
|
| 9 |
+
128,
|
| 10 |
+
128,
|
| 11 |
+
128,
|
| 12 |
+
128,
|
| 13 |
+
128,
|
| 14 |
+
128
|
| 15 |
+
],
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"classifier_dropout": null,
|
| 18 |
+
"cls_token_id": 101,
|
| 19 |
+
"eos_token_id": null,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_act": "gelu",
|
| 22 |
+
"hidden_dropout_prob": 0.1,
|
| 23 |
+
"hidden_size": 512,
|
| 24 |
+
"id2label": {
|
| 25 |
+
"0": "LABEL_0",
|
| 26 |
+
"1": "LABEL_1",
|
| 27 |
+
"2": "LABEL_2",
|
| 28 |
+
"3": "LABEL_3",
|
| 29 |
+
"4": "LABEL_4",
|
| 30 |
+
"5": "LABEL_5",
|
| 31 |
+
"6": "LABEL_6",
|
| 32 |
+
"7": "LABEL_7",
|
| 33 |
+
"8": "LABEL_8",
|
| 34 |
+
"9": "LABEL_9",
|
| 35 |
+
"10": "LABEL_10",
|
| 36 |
+
"11": "LABEL_11",
|
| 37 |
+
"12": "LABEL_12",
|
| 38 |
+
"13": "LABEL_13"
|
| 39 |
+
},
|
| 40 |
+
"ignore_attention_mask": false,
|
| 41 |
+
"initializer_range": 0.02,
|
| 42 |
+
"intermediate_size": 2048,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1,
|
| 46 |
+
"LABEL_10": 10,
|
| 47 |
+
"LABEL_11": 11,
|
| 48 |
+
"LABEL_12": 12,
|
| 49 |
+
"LABEL_13": 13,
|
| 50 |
+
"LABEL_2": 2,
|
| 51 |
+
"LABEL_3": 3,
|
| 52 |
+
"LABEL_4": 4,
|
| 53 |
+
"LABEL_5": 5,
|
| 54 |
+
"LABEL_6": 6,
|
| 55 |
+
"LABEL_7": 7,
|
| 56 |
+
"LABEL_8": 8,
|
| 57 |
+
"LABEL_9": 9
|
| 58 |
+
},
|
| 59 |
+
"layer_norm_eps": 1e-05,
|
| 60 |
+
"max_position_embeddings": 4098,
|
| 61 |
+
"model_max_length": 4096,
|
| 62 |
+
"model_type": "longformer",
|
| 63 |
+
"num_attention_heads": 8,
|
| 64 |
+
"num_hidden_layers": 6,
|
| 65 |
+
"onnx_export": false,
|
| 66 |
+
"pad_token_id": 0,
|
| 67 |
+
"position_embedding_type": "absolute",
|
| 68 |
+
"problem_type": "single_label_classification",
|
| 69 |
+
"sep_token_id": 102,
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.23.1",
|
| 72 |
+
"type_vocab_size": 2,
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 30522
|
| 75 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8bf73ccb31204af44dda1c6a4530312806cb68e067232102645ddf642dfec9e
|
| 3 |
+
size 166605159
|
runs/Oct27_17-44-27_47972f860fae/1666892684.163216/events.out.tfevents.1666892684.47972f860fae.105.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f3995011bf3f860dcb3b92e4ba89882fb5bb68d9a8f8f2fedb79e3b1105fa86
|
| 3 |
+
size 5508
|
runs/Oct27_17-44-27_47972f860fae/events.out.tfevents.1666892684.47972f860fae.105.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7d9e88302ce977e1644248f5307c316c180b8f7407d4133c4686e488be59d8e
|
| 3 |
+
size 6273
|
runs/Oct27_17-48-35_47972f860fae/1666892922.069158/events.out.tfevents.1666892922.47972f860fae.105.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11c2ddf0e1a2850525ebd7b39afd63dce48c091ffe821c27601797b8e7cc3911
|
| 3 |
+
size 5508
|
runs/Oct27_17-48-35_47972f860fae/events.out.tfevents.1666892922.47972f860fae.105.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e650e9d75bd3f1a1548126b0207886793191149bb83445ba320a0f818d0a70f
|
| 3 |
+
size 5226
|
runs/Oct27_17-53-11_47972f860fae/1666893198.2652752/events.out.tfevents.1666893198.47972f860fae.105.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad974562c44c50e69f8878f7e6256c65c763bbd1003d249f64f9654b5a2bbf40
|
| 3 |
+
size 5514
|
runs/Oct27_17-53-11_47972f860fae/events.out.tfevents.1666893198.47972f860fae.105.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10ee8b23c5a5a6520e2b0dc87413c0b3d13fce600987c606b310510139e7455c
|
| 3 |
+
size 5252
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 4096,
|
| 7 |
+
"name_or_path": "/content/drive/MyDrive/sbert_longformer_ecthr_b_simcse/train_simcse-_root_.local_share_jupyter_runtime_kernel-702ca39d-5545-4b00-b884-05176c135763.json-2022-10-21_08-44-17/1500",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dea01bfb0cad42bf0959eaffe75594f88bdf150de5c5966bb613206b71d68da8
|
| 3 |
+
size 3439
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|