willbui256 commited on
Commit
19c8ff8
·
verified ·
1 Parent(s): 675b3f7

Upload model and optimizer

Browse files
checkpoint-2496/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "willbui256/tiny-random-XLMRobertaXLForSequenceClassification-regression-1",
3
+ "architectures": [
4
+ "XLMRobertaXLForSequenceClassification"
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": 32,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 37,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "xlm-roberta-xl",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 5,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "regression",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.44.2",
31
+ "type_vocab_size": 16,
32
+ "use_cache": true,
33
+ "vocab_size": 250002
34
+ }
checkpoint-2496/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da62e34bf39643192b713a993296812dacf5bdb62ca9eb0d92e1b5b071d55249
3
+ size 32218472
checkpoint-2496/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4149d6b11757fe4d665fb3659048f47b7d419c3ab5c6afc07801639fd9f0186b
3
+ size 64490490
checkpoint-2496/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c955f8479b8d5dda330ee71abc27d82cda67720e52cba6eac0521c5dd5f444
3
+ size 14244
checkpoint-2496/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cfa394c93e3916ec2541999af4a5b4fad6984fb94e65a8e8a9da4753033ad73
3
+ size 1064
checkpoint-2496/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-2496/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-2496/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93455e1eee0ad4a32b60111baf2d57c95f2edfcadfc77419384c338d541f4d6d
3
+ size 17083063
checkpoint-2496/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 510,
50
+ "model_max_length": 510,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "sp_model_kwargs": {},
57
+ "stride": 0,
58
+ "tokenizer_class": "XLMRobertaTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
+ }
checkpoint-2496/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2496/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8923094143d0ab6ccd9fa3e48560db08bd6095b904398169cb109d07ebd3e3d3
3
+ size 5240
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93c82ad74e92877b57fdc08ed69ea5a2f9df54717e5f341b2bf4e395511d32c0
3
  size 32218472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da62e34bf39643192b713a993296812dacf5bdb62ca9eb0d92e1b5b071d55249
3
  size 32218472
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a6d20886e24a85e1ba3b5644b4fe12c21adaa43bbaa6f08aa84b4c6fa01dce2
3
  size 64490490
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4149d6b11757fe4d665fb3659048f47b7d419c3ab5c6afc07801639fd9f0186b
3
  size 64490490
tokenizer_config.json CHANGED
@@ -46,10 +46,17 @@
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "mask_token": "<mask>",
 
49
  "model_max_length": 510,
 
50
  "pad_token": "<pad>",
 
 
51
  "sep_token": "</s>",
52
  "sp_model_kwargs": {},
 
53
  "tokenizer_class": "XLMRobertaTokenizer",
 
 
54
  "unk_token": "<unk>"
55
  }
 
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "mask_token": "<mask>",
49
+ "max_length": 510,
50
  "model_max_length": 510,
51
+ "pad_to_multiple_of": null,
52
  "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
  "sep_token": "</s>",
56
  "sp_model_kwargs": {},
57
+ "stride": 0,
58
  "tokenizer_class": "XLMRobertaTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
  "unk_token": "<unk>"
62
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8b352639b0419853a409dbcc4dda94566af46b48b6cc8ee73ffb128c8661270
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8923094143d0ab6ccd9fa3e48560db08bd6095b904398169cb109d07ebd3e3d3
3
  size 5240