Hugging Face's logo

abvijaykumar
/
finetuned-model

PEFT
Safetensors
Generated from Trainer
Model card Files Community
abvijaykumar commited on
Commit
9215d32
•
1 Parent(s): d73b9ad

Model save

Browse files
Files changed (4) hide show
  1. README.md +15 -105
  2. adapter_config.json +5 -5
  3. adapter_model.bin +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: apache-2.0
3
- base_model: distilgpt2
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # finetuned-model
15
 
16
- This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 6.1626
19
 
20
  ## Model description
21
 
@@ -40,112 +40,22 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 100
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 6 | 6.6915 |
50
- | No log | 2.0 | 12 | 6.6732 |
51
- | No log | 3.0 | 18 | 6.6555 |
52
- | No log | 4.0 | 24 | 6.6385 |
53
- | No log | 5.0 | 30 | 6.6222 |
54
- | No log | 6.0 | 36 | 6.6063 |
55
- | No log | 7.0 | 42 | 6.5910 |
56
- | No log | 8.0 | 48 | 6.5760 |
57
- | No log | 9.0 | 54 | 6.5617 |
58
- | No log | 10.0 | 60 | 6.5482 |
59
- | No log | 11.0 | 66 | 6.5351 |
60
- | No log | 12.0 | 72 | 6.5223 |
61
- | No log | 13.0 | 78 | 6.5101 |
62
- | No log | 14.0 | 84 | 6.4982 |
63
- | No log | 15.0 | 90 | 6.4869 |
64
- | No log | 16.0 | 96 | 6.4758 |
65
- | No log | 17.0 | 102 | 6.4653 |
66
- | No log | 18.0 | 108 | 6.4551 |
67
- | No log | 19.0 | 114 | 6.4453 |
68
- | No log | 20.0 | 120 | 6.4357 |
69
- | No log | 21.0 | 126 | 6.4266 |
70
- | No log | 22.0 | 132 | 6.4177 |
71
- | No log | 23.0 | 138 | 6.4090 |
72
- | No log | 24.0 | 144 | 6.4006 |
73
- | No log | 25.0 | 150 | 6.3924 |
74
- | No log | 26.0 | 156 | 6.3845 |
75
- | No log | 27.0 | 162 | 6.3768 |
76
- | No log | 28.0 | 168 | 6.3696 |
77
- | No log | 29.0 | 174 | 6.3625 |
78
- | No log | 30.0 | 180 | 6.3557 |
79
- | No log | 31.0 | 186 | 6.3489 |
80
- | No log | 32.0 | 192 | 6.3423 |
81
- | No log | 33.0 | 198 | 6.3357 |
82
- | No log | 34.0 | 204 | 6.3294 |
83
- | No log | 35.0 | 210 | 6.3235 |
84
- | No log | 36.0 | 216 | 6.3176 |
85
- | No log | 37.0 | 222 | 6.3119 |
86
- | No log | 38.0 | 228 | 6.3064 |
87
- | No log | 39.0 | 234 | 6.3010 |
88
- | No log | 40.0 | 240 | 6.2957 |
89
- | No log | 41.0 | 246 | 6.2907 |
90
- | No log | 42.0 | 252 | 6.2859 |
91
- | No log | 43.0 | 258 | 6.2811 |
92
- | No log | 44.0 | 264 | 6.2765 |
93
- | No log | 45.0 | 270 | 6.2720 |
94
- | No log | 46.0 | 276 | 6.2675 |
95
- | No log | 47.0 | 282 | 6.2632 |
96
- | No log | 48.0 | 288 | 6.2590 |
97
- | No log | 49.0 | 294 | 6.2550 |
98
- | No log | 50.0 | 300 | 6.2511 |
99
- | No log | 51.0 | 306 | 6.2473 |
100
- | No log | 52.0 | 312 | 6.2437 |
101
- | No log | 53.0 | 318 | 6.2400 |
102
- | No log | 54.0 | 324 | 6.2365 |
103
- | No log | 55.0 | 330 | 6.2331 |
104
- | No log | 56.0 | 336 | 6.2298 |
105
- | No log | 57.0 | 342 | 6.2267 |
106
- | No log | 58.0 | 348 | 6.2237 |
107
- | No log | 59.0 | 354 | 6.2206 |
108
- | No log | 60.0 | 360 | 6.2177 |
109
- | No log | 61.0 | 366 | 6.2149 |
110
- | No log | 62.0 | 372 | 6.2121 |
111
- | No log | 63.0 | 378 | 6.2095 |
112
- | No log | 64.0 | 384 | 6.2068 |
113
- | No log | 65.0 | 390 | 6.2043 |
114
- | No log | 66.0 | 396 | 6.2019 |
115
- | No log | 67.0 | 402 | 6.1995 |
116
- | No log | 68.0 | 408 | 6.1973 |
117
- | No log | 69.0 | 414 | 6.1950 |
118
- | No log | 70.0 | 420 | 6.1929 |
119
- | No log | 71.0 | 426 | 6.1909 |
120
- | No log | 72.0 | 432 | 6.1889 |
121
- | No log | 73.0 | 438 | 6.1870 |
122
- | No log | 74.0 | 444 | 6.1851 |
123
- | No log | 75.0 | 450 | 6.1834 |
124
- | No log | 76.0 | 456 | 6.1817 |
125
- | No log | 77.0 | 462 | 6.1801 |
126
- | No log | 78.0 | 468 | 6.1786 |
127
- | No log | 79.0 | 474 | 6.1772 |
128
- | No log | 80.0 | 480 | 6.1758 |
129
- | No log | 81.0 | 486 | 6.1745 |
130
- | No log | 82.0 | 492 | 6.1733 |
131
- | No log | 83.0 | 498 | 6.1722 |
132
- | 6.7021 | 84.0 | 504 | 6.1711 |
133
- | 6.7021 | 85.0 | 510 | 6.1701 |
134
- | 6.7021 | 86.0 | 516 | 6.1691 |
135
- | 6.7021 | 87.0 | 522 | 6.1683 |
136
- | 6.7021 | 88.0 | 528 | 6.1674 |
137
- | 6.7021 | 89.0 | 534 | 6.1666 |
138
- | 6.7021 | 90.0 | 540 | 6.1660 |
139
- | 6.7021 | 91.0 | 546 | 6.1653 |
140
- | 6.7021 | 92.0 | 552 | 6.1647 |
141
- | 6.7021 | 93.0 | 558 | 6.1642 |
142
- | 6.7021 | 94.0 | 564 | 6.1638 |
143
- | 6.7021 | 95.0 | 570 | 6.1634 |
144
- | 6.7021 | 96.0 | 576 | 6.1631 |
145
- | 6.7021 | 97.0 | 582 | 6.1629 |
146
- | 6.7021 | 98.0 | 588 | 6.1627 |
147
- | 6.7021 | 99.0 | 594 | 6.1626 |
148
- | 6.7021 | 100.0 | 600 | 6.1626 |
149
 
150
 
151
  ### Framework versions
 
1
  ---
2
+ license: bigscience-bloom-rail-1.0
3
+ base_model: bigscience/bloom-560m
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # finetuned-model
15
 
16
+ This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 7.8626
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 10
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 6 | 7.9789 |
50
+ | No log | 2.0 | 12 | 7.9410 |
51
+ | No log | 3.0 | 18 | 7.9208 |
52
+ | No log | 4.0 | 24 | 7.9045 |
53
+ | No log | 5.0 | 30 | 7.8931 |
54
+ | No log | 6.0 | 36 | 7.8828 |
55
+ | No log | 7.0 | 42 | 7.8742 |
56
+ | No log | 8.0 | 48 | 7.8679 |
57
+ | No log | 9.0 | 54 | 7.8640 |
58
+ | No log | 10.0 | 60 | 7.8626 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
adapter_config.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
  "auto_mapping": null,
3
- "base_model_name_or_path": "distilgpt2",
4
- "encoder_hidden_size": 768,
5
  "inference_mode": true,
6
- "num_attention_heads": 12,
7
- "num_layers": 6,
8
  "num_transformer_submodules": 1,
9
  "num_virtual_tokens": 20,
10
  "peft_type": "PREFIX_TUNING",
11
  "prefix_projection": false,
12
  "revision": null,
13
  "task_type": "CAUSAL_LM",
14
- "token_dim": 768
15
  }
 
1
  {
2
  "auto_mapping": null,
3
+ "base_model_name_or_path": "bigscience/bloom-560m",
4
+ "encoder_hidden_size": 1024,
5
  "inference_mode": true,
6
+ "num_attention_heads": 16,
7
+ "num_layers": 24,
8
  "num_transformer_submodules": 1,
9
  "num_virtual_tokens": 20,
10
  "peft_type": "PREFIX_TUNING",
11
  "prefix_projection": false,
12
  "revision": null,
13
  "task_type": "CAUSAL_LM",
14
+ "token_dim": 1024
15
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f32e98ed5ddef08c743ab5ec8dc69cf7050f95315da9617fcaec0d20de769974
3
- size 738109
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2bd4f15dc9d3306f73c25082dfcf5b569499a7ab268dd4ed8a60159720778b6
3
+ size 3932989
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aae41de0076419f6964e3ee0116e08f40d835ec357ee20b45063d63faca8a1c9
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef1de0603d3779f6dd7ab8794efd62c6de80dcb6eae98ed9be7d8125b3991c9d
3
  size 4027