dmargutierrez
commited on
Commit
•
1c56a86
1
Parent(s):
37ac37b
Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +58 -0
- pytorch_model.bin +3 -0
- runs/Mar21_09-06-51_t1-45-bhs5/1679389618.8304272/events.out.tfevents.1679389618.t1-45-bhs5.19484.1 +3 -0
- runs/Mar21_09-06-51_t1-45-bhs5/events.out.tfevents.1679389618.t1-45-bhs5.19484.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +21 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "B-ORGANISATION",
|
16 |
+
"2": "I-ORGANISATION",
|
17 |
+
"3": "B-ADDRESS",
|
18 |
+
"4": "I-ADDRESS",
|
19 |
+
"5": "B-DATE",
|
20 |
+
"6": "I-DATE",
|
21 |
+
"7": "B-PERSON",
|
22 |
+
"8": "I-PERSON",
|
23 |
+
"9": "B-AMOUNT",
|
24 |
+
"10": "I-AMOUNT",
|
25 |
+
"11": "B-TIME",
|
26 |
+
"12": "I-TIME"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"label2id": {
|
31 |
+
"B-ADDRESS": 3,
|
32 |
+
"B-AMOUNT": 9,
|
33 |
+
"B-DATE": 5,
|
34 |
+
"B-ORGANISATION": 1,
|
35 |
+
"B-PERSON": 7,
|
36 |
+
"B-TIME": 11,
|
37 |
+
"I-ADDRESS": 4,
|
38 |
+
"I-AMOUNT": 10,
|
39 |
+
"I-DATE": 6,
|
40 |
+
"I-ORGANISATION": 2,
|
41 |
+
"I-PERSON": 8,
|
42 |
+
"I-TIME": 12,
|
43 |
+
"O": 0
|
44 |
+
},
|
45 |
+
"layer_norm_eps": 1e-05,
|
46 |
+
"max_position_embeddings": 514,
|
47 |
+
"model_type": "xlm-roberta",
|
48 |
+
"num_attention_heads": 12,
|
49 |
+
"num_hidden_layers": 12,
|
50 |
+
"output_past": true,
|
51 |
+
"pad_token_id": 1,
|
52 |
+
"position_embedding_type": "absolute",
|
53 |
+
"torch_dtype": "bfloat16",
|
54 |
+
"transformers_version": "4.26.0",
|
55 |
+
"type_vocab_size": 1,
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 250002
|
58 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca54cb6e8b1e989994446794171f3530671d6b261a28c271e1accdfb3790b104
|
3 |
+
size 554998829
|
runs/Mar21_09-06-51_t1-45-bhs5/1679389618.8304272/events.out.tfevents.1679389618.t1-45-bhs5.19484.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bed2627639404d568e5be72446e9bd9215e1304ba8dedc3abd445fc913a0391
|
3 |
+
size 5710
|
runs/Mar21_09-06-51_t1-45-bhs5/events.out.tfevents.1679389618.t1-45-bhs5.19484.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc6bb88701f746a878bb30cff6dedd187197575a197a5eac9eab4b94efe2274c
|
3 |
+
size 5430
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46afe88da5fd71bdbab5cfab5e84c1adce59c246ea5f9341bbecef061891d0a7
|
3 |
+
size 17082913
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 512,
|
15 |
+
"name_or_path": "xlm-roberta-base",
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"special_tokens_map_file": null,
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24a36493f7a8caf95d0b682a6cd75332ca9e43829ae035f2481c97e8f9085582
|
3 |
+
size 3515
|