Upload 7 files
Browse files- Training.txt +88 -0
- config.json +27 -0
- merges.txt +0 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.json +0 -0
Training.txt
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Ref: 'tensor([[0.2258],\n [0.5443],\n [0.1691],\n [0.9322],\n [0.8455]])'
|
2 |
+
|
3 |
+
Batch 16 / 3e-5 / 3 epochs / Warmup 500
|
4 |
+
|
5 |
+
Sentence: The quarterly financial report are showing an increase.
|
6 |
+
Predicted Rating: 0.12151668965816498
|
7 |
+
|
8 |
+
Sentence: Him has completed the audit for last fiscal year.
|
9 |
+
Predicted Rating: 0.530194878578186
|
10 |
+
|
11 |
+
Sentence: Please to inform the board about the recent developments.
|
12 |
+
Predicted Rating: 0.22146113216876984
|
13 |
+
|
14 |
+
Sentence: The team successfully achieved all its targets for the last quarter.
|
15 |
+
Predicted Rating: 0.8573371767997742
|
16 |
+
|
17 |
+
Sentence: Our company is exploring new ventures in the European market.
|
18 |
+
Predicted Rating: 0.8724232316017151
|
19 |
+
|
20 |
+
|
21 |
+
Batch 16 / 3e-5 / 5 epochs / Warmup 500
|
22 |
+
|
23 |
+
Sentence: The quarterly financial report are showing an increase.
|
24 |
+
Predicted Rating: 0.15253500640392303
|
25 |
+
|
26 |
+
Sentence: Him has completed the audit for last fiscal year.
|
27 |
+
Predicted Rating: 0.5656167268753052
|
28 |
+
|
29 |
+
Sentence: Please to inform the board about the recent developments.
|
30 |
+
Predicted Rating: 0.14064954221248627
|
31 |
+
|
32 |
+
Sentence: The team successfully achieved all its targets for the last quarter.
|
33 |
+
Predicted Rating: 0.8768936395645142
|
34 |
+
|
35 |
+
Sentence: Our company is exploring new ventures in the European market.
|
36 |
+
Predicted Rating: 0.9061842560768127
|
37 |
+
|
38 |
+
|
39 |
+
Batch 16 / 2e-5 / 5 epochs / Warmup 500
|
40 |
+
|
41 |
+
[{'test_loss': 0.0644223615527153,
|
42 |
+
'test_mse': 0.0644223615527153,
|
43 |
+
'test_r2': 0.5548150539398193,
|
44 |
+
'test_mae': 0.1857408732175827}]
|
45 |
+
|
46 |
+
Sentence: The quarterly financial report are showing an increase.
|
47 |
+
Predicted Rating: 0.14678220450878143
|
48 |
+
|
49 |
+
Sentence: Him has completed the audit for last fiscal year.
|
50 |
+
Predicted Rating: 0.5861627459526062
|
51 |
+
|
52 |
+
Sentence: Please to inform the board about the recent developments.
|
53 |
+
Predicted Rating: 0.18201778829097748
|
54 |
+
|
55 |
+
Sentence: The team successfully achieved all its targets for the last quarter.
|
56 |
+
Predicted Rating: 0.9556146264076233
|
57 |
+
|
58 |
+
Sentence: Our company is exploring new ventures in the European market.
|
59 |
+
Predicted Rating: 0.965653121471405
|
60 |
+
|
61 |
+
|
62 |
+
Batch 16 / 1e-5 / 5 epochs / Warmup 500
|
63 |
+
|
64 |
+
[{'test_loss': 0.06383358687162399,
|
65 |
+
'test_mse': 0.06383358687162399,
|
66 |
+
'test_r2': 0.5588837265968323,
|
67 |
+
'test_mae': 0.18667960166931152}]
|
68 |
+
|
69 |
+
|
70 |
+
Sentence: The quarterly financial report are showing an increase.
|
71 |
+
Predicted Rating: 0.18816125392913818
|
72 |
+
|
73 |
+
Sentence: Him has completed the audit for last fiscal year.
|
74 |
+
Predicted Rating: 0.49415794014930725
|
75 |
+
|
76 |
+
Sentence: Please to inform the board about the recent developments.
|
77 |
+
Predicted Rating: 0.1862858533859253
|
78 |
+
|
79 |
+
Sentence: The team successfully achieved all its targets for the last quarter.
|
80 |
+
Predicted Rating: 0.8290681838989258
|
81 |
+
|
82 |
+
Sentence: Our company is exploring new ventures in the European market.
|
83 |
+
Predicted Rating: 0.8932080268859863
|
84 |
+
|
85 |
+
|
86 |
+
Very bad at 1e-6 ~0.44 test_r2 (batch 16 / 5 epoch / warmup 500)
|
87 |
+
|
88 |
+
5e-6 r2 ~0.536
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilroberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
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 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 6,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.34.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|