sharmadhruv commited on
Commit
5116b14
1 Parent(s): c34b605

End of training

Browse files
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- base_model: baidu/ernie-code-560m
3
  library_name: peft
4
- license: mit
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # qa_by_bird_lora_weights
16
 
17
- This model is a fine-tuned version of [baidu/ernie-code-560m](https://huggingface.co/baidu/ernie-code-560m) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 3.9151
20
 
21
  ## Model description
22
 
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 4.9165 | 1.0 | 1000 | 4.2814 |
51
- | 4.5737 | 2.0 | 2000 | 3.9608 |
52
- | 4.3832 | 3.0 | 3000 | 3.9151 |
53
 
54
 
55
  ### Framework versions
 
1
  ---
2
+ base_model: facebook/bart-large
3
  library_name: peft
4
+ license: apache-2.0
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
14
 
15
  # qa_by_bird_lora_weights
16
 
17
+ This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 3.9138
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 13.5625 | 1.0 | 1000 | 13.2137 |
51
+ | 7.6866 | 2.0 | 2000 | 5.8546 |
52
+ | 4.8758 | 3.0 | 3000 | 3.9138 |
53
 
54
 
55
  ### Framework versions
adapter_config.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "auto_mapping": null,
3
- "base_model_name_or_path": "baidu/ernie-code-560m",
4
  "inference_mode": true,
5
- "num_attention_heads": 12,
6
  "num_layers": 12,
7
  "num_transformer_submodules": 1,
8
  "num_virtual_tokens": 10,
@@ -11,7 +11,7 @@
11
  "prompt_tuning_init_text": null,
12
  "revision": null,
13
  "task_type": "QUESTION_ANS",
14
- "token_dim": 768,
15
  "tokenizer_kwargs": null,
16
- "tokenizer_name_or_path": "baidu/ernie-code-560m"
17
  }
 
1
  {
2
  "auto_mapping": null,
3
+ "base_model_name_or_path": "facebook/bart-large",
4
  "inference_mode": true,
5
+ "num_attention_heads": 16,
6
  "num_layers": 12,
7
  "num_transformer_submodules": 1,
8
  "num_virtual_tokens": 10,
 
11
  "prompt_tuning_init_text": null,
12
  "revision": null,
13
  "task_type": "QUESTION_ANS",
14
+ "token_dim": 1024,
15
  "tokenizer_kwargs": null,
16
+ "tokenizer_name_or_path": "facebook/bart-large"
17
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33cc77143b425a946dcae3834254329e729cabac2a19bb410ab382778162fe51
3
- size 34100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ed412a345f60ba7956ddb5a22605eac41b79db6d9c7d6030263f54fdd9fca8
3
+ size 45364
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,61 +1,15 @@
1
  {
2
- "additional_special_tokens": [
3
- {
4
- "content": "\n",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "\t",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- {
18
- "content": "<|space|><|space|><|space|><|space|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- {
25
- "content": "<|space|><|space|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- {
32
- "content": "<|space|>",
33
- "lstrip": false,
34
- "normalized": false,
35
- "rstrip": false,
36
- "single_word": false
37
- }
38
- ],
39
- "bos_token": "▁start",
40
- "eos_token": {
41
- "content": "</s>",
42
- "lstrip": false,
43
- "normalized": false,
44
  "rstrip": false,
45
  "single_word": false
46
  },
47
- "pad_token": {
48
- "content": "<pad>",
49
- "lstrip": false,
50
- "normalized": false,
51
- "rstrip": false,
52
- "single_word": false
53
- },
54
- "unk_token": {
55
- "content": "<unk>",
56
- "lstrip": false,
57
- "normalized": false,
58
- "rstrip": false,
59
- "single_word": false
60
- }
61
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
15
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f79b968b0d938c1ac96ebb93289889dd669beb3f89ea9d3821bcd7e08547a449
3
- size 16316406
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189a504b3e13b6086930ed9e06c6f44e038445eb817b223c8d3058326f1cc0b1
3
+ size 2108905
tokenizer_config.json CHANGED
@@ -1,88 +1,57 @@
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<pad>",
5
  "lstrip": false,
6
- "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
  "1": {
12
- "content": "</s>",
13
  "lstrip": false,
14
- "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
  "2": {
20
- "content": "<unk>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "250100": {
28
- "content": "\n",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "250101": {
36
- "content": "\t",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "250102": {
44
- "content": "<|space|><|space|><|space|><|space|>",
45
  "lstrip": false,
46
- "normalized": false,
47
  "rstrip": false,
48
  "single_word": false,
49
  "special": true
50
  },
51
- "250103": {
52
- "content": "<|space|><|space|>",
53
  "lstrip": false,
54
- "normalized": false,
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
58
  },
59
- "250104": {
60
- "content": "<|space|>",
61
- "lstrip": false,
62
- "normalized": false,
63
  "rstrip": false,
64
  "single_word": false,
65
  "special": true
66
  }
67
  },
68
- "additional_special_tokens": [
69
- "\n",
70
- "\t",
71
- "<|space|><|space|><|space|><|space|>",
72
- "<|space|><|space|>",
73
- "<|space|>"
74
- ],
75
- "bos_token": "▁start",
76
  "clean_up_tokenization_spaces": true,
 
77
  "eos_token": "</s>",
78
- "extra_ids": 0,
79
- "max_length": 1024,
80
- "model_max_length": 1000000000000000019884624838656,
81
  "pad_token": "<pad>",
82
- "sp_model_kwargs": {},
83
- "stride": 0,
84
- "tokenizer_class": "T5Tokenizer",
85
- "truncation_side": "right",
86
- "truncation_strategy": "longest_first",
87
  "unk_token": "<unk>"
88
  }
 
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": true,
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": 1024,
52
  "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
 
 
56
  "unk_token": "<unk>"
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aef19e8d9bf68590715e742f5d9b7efc5de61c4ad4697c08477d01af7a9748bb
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b0fb6c62ce8360dc86aab758018502c60a2acbc086317c594f93715eaf15da
3
  size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff