Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +63 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Apr20_14-39-11_b6e0d6a8374c/1650465571.3129137/events.out.tfevents.1650465571.b6e0d6a8374c.80.5 +3 -0
- runs/Apr20_14-39-11_b6e0d6a8374c/events.out.tfevents.1650465571.b6e0d6a8374c.80.4 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/longformer-base-4096",
|
3 |
+
"architectures": [
|
4 |
+
"LongformerForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_mode": "longformer",
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attention_window": [
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512
|
21 |
+
],
|
22 |
+
"bos_token_id": 0,
|
23 |
+
"classifier_dropout": null,
|
24 |
+
"eos_token_id": 2,
|
25 |
+
"gradient_checkpointing": false,
|
26 |
+
"hidden_act": "gelu",
|
27 |
+
"hidden_dropout_prob": 0.1,
|
28 |
+
"hidden_size": 768,
|
29 |
+
"id2label": {
|
30 |
+
"0": "Lead",
|
31 |
+
"1": "Position",
|
32 |
+
"2": "Evidence",
|
33 |
+
"3": "Claim",
|
34 |
+
"4": "Concluding Statement",
|
35 |
+
"5": "Counterclaim",
|
36 |
+
"6": "Rebuttal"
|
37 |
+
},
|
38 |
+
"ignore_attention_mask": false,
|
39 |
+
"initializer_range": 0.02,
|
40 |
+
"intermediate_size": 3072,
|
41 |
+
"label2id": {
|
42 |
+
"Claim": "3",
|
43 |
+
"Concluding Statement": "4",
|
44 |
+
"Counterclaim": "5",
|
45 |
+
"Evidence": "2",
|
46 |
+
"Lead": "0",
|
47 |
+
"Position": "1",
|
48 |
+
"Rebuttal": "6"
|
49 |
+
},
|
50 |
+
"layer_norm_eps": 1e-05,
|
51 |
+
"max_position_embeddings": 4098,
|
52 |
+
"model_type": "longformer",
|
53 |
+
"num_attention_heads": 12,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"pad_token_id": 1,
|
56 |
+
"position_embedding_type": "absolute",
|
57 |
+
"sep_token_id": 2,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.18.0",
|
60 |
+
"type_vocab_size": 1,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 50265
|
63 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:420f4a04811b3c160b8260ae5f3453a59d91f0017dd087048d329b48f8081988
|
3 |
+
size 592422561
|
runs/Apr20_14-39-11_b6e0d6a8374c/1650465571.3129137/events.out.tfevents.1650465571.b6e0d6a8374c.80.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51dc5f64e32466a6601e940d8064385df8c618c2920926a970509addd302ed61
|
3 |
+
size 4825
|
runs/Apr20_14-39-11_b6e0d6a8374c/events.out.tfevents.1650465571.b6e0d6a8374c.80.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fea5ff01160d3c079be857975b26664e32b2f1294f4b69f660a66e726d106d44
|
3 |
+
size 4631
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": true, "trim_offsets": true, "model_max_length": 4096, "special_tokens_map_file": null, "name_or_path": "allenai/longformer-base-4096", "tokenizer_class": "LongformerTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05ade868b5011aabb285559817f1f98991bd94e8161c1110855950c30eae9454
|
3 |
+
size 2991
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|