Hugging Face's logo

ypl
/
bart_test_p2

Text2Text Generation
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
ypl commited on
Commit
0a5b46d
·
verified ·
1 Parent(s): 9784007

ypl/bart_game_clean

Browse files
Files changed (4) hide show
  1. README.md +23 -42
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
  model-index:
@@ -11,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
11
 
12
  # bart_test_p2
13
 
14
- This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.0194
17
 
18
  ## Model description
19
 
@@ -42,46 +44,25 @@ The following hyperparameters were used during training:
42
 
43
  ### Training results
44
 
45
- | Training Loss | Epoch | Step | Validation Loss |
46
- |:-------------:|:-----:|:-----:|:---------------:|
47
- | 0.0273 | 0.08 | 500 | 0.0224 |
48
- | 0.0255 | 0.16 | 1000 | 0.0215 |
49
- | 0.0245 | 0.24 | 1500 | 0.0213 |
50
- | 0.0234 | 0.32 | 2000 | 0.0211 |
51
- | 0.025 | 0.39 | 2500 | 0.0207 |
52
- | 0.0243 | 0.47 | 3000 | 0.0208 |
53
- | 0.0236 | 0.55 | 3500 | 0.0206 |
54
- | 0.0246 | 0.63 | 4000 | 0.0204 |
55
- | 0.0235 | 0.71 | 4500 | 0.0202 |
56
- | 0.0231 | 0.79 | 5000 | 0.0203 |
57
- | 0.0221 | 0.87 | 5500 | 0.0201 |
58
- | 0.0239 | 0.95 | 6000 | 0.0199 |
59
- | 0.0209 | 1.03 | 6500 | 0.0200 |
60
- | 0.0193 | 1.1 | 7000 | 0.0198 |
61
- | 0.0207 | 1.18 | 7500 | 0.0199 |
62
- | 0.0189 | 1.26 | 8000 | 0.0201 |
63
- | 0.0193 | 1.34 | 8500 | 0.0200 |
64
- | 0.0186 | 1.42 | 9000 | 0.0197 |
65
- | 0.0199 | 1.5 | 9500 | 0.0197 |
66
- | 0.0207 | 1.58 | 10000 | 0.0195 |
67
- | 0.0199 | 1.66 | 10500 | 0.0196 |
68
- | 0.0188 | 1.74 | 11000 | 0.0195 |
69
- | 0.0194 | 1.81 | 11500 | 0.0194 |
70
- | 0.0201 | 1.89 | 12000 | 0.0195 |
71
- | 0.0181 | 1.97 | 12500 | 0.0194 |
72
- | 0.0177 | 2.05 | 13000 | 0.0194 |
73
- | 0.0161 | 2.13 | 13500 | 0.0196 |
74
- | 0.0172 | 2.21 | 14000 | 0.0195 |
75
- | 0.0184 | 2.29 | 14500 | 0.0195 |
76
- | 0.0168 | 2.37 | 15000 | 0.0195 |
77
- | 0.0176 | 2.44 | 15500 | 0.0194 |
78
- | 0.0177 | 2.52 | 16000 | 0.0194 |
79
- | 0.0158 | 2.6 | 16500 | 0.0194 |
80
- | 0.0177 | 2.68 | 17000 | 0.0193 |
81
- | 0.0179 | 2.76 | 17500 | 0.0193 |
82
- | 0.0167 | 2.84 | 18000 | 0.0194 |
83
- | 0.0177 | 2.92 | 18500 | 0.0193 |
84
- | 0.0171 | 3.0 | 19000 | 0.0194 |
85
 
86
 
87
  ### Framework versions
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: facebook/bart-base
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # bart_test_p2
15
 
16
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0306
19
 
20
  ## Model description
21
 
 
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 1.5336 | 0.18 | 500 | 0.1004 |
50
+ | 0.1089 | 0.35 | 1000 | 0.0755 |
51
+ | 0.0923 | 0.53 | 1500 | 0.0637 |
52
+ | 0.0747 | 0.7 | 2000 | 0.0554 |
53
+ | 0.0719 | 0.88 | 2500 | 0.0498 |
54
+ | 0.0653 | 1.05 | 3000 | 0.0470 |
55
+ | 0.0557 | 1.23 | 3500 | 0.0425 |
56
+ | 0.0505 | 1.4 | 4000 | 0.0403 |
57
+ | 0.05 | 1.58 | 4500 | 0.0378 |
58
+ | 0.0477 | 1.75 | 5000 | 0.0362 |
59
+ | 0.0451 | 1.93 | 5500 | 0.0343 |
60
+ | 0.0443 | 2.1 | 6000 | 0.0327 |
61
+ | 0.0372 | 2.28 | 6500 | 0.0326 |
62
+ | 0.0384 | 2.45 | 7000 | 0.0316 |
63
+ | 0.0371 | 2.63 | 7500 | 0.0311 |
64
+ | 0.0363 | 2.8 | 8000 | 0.0306 |
65
+ | 0.0345 | 2.98 | 8500 | 0.0306 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "./bart_test_p2/backup_checkpoint-12000",
3
  "activation_dropout": 0.1,
4
  "activation_function": "gelu",
5
  "add_bias_logits": false,
 
1
  {
2
+ "_name_or_path": "facebook/bart-base",
3
  "activation_dropout": 0.1,
4
  "activation_function": "gelu",
5
  "add_bias_logits": false,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd2d4cc6d9060405892bbe3e531d4520c68bd9a3a2fbf019f9e89cb820504c2f
3
  size 557912620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2558d47436667ae1b8a797015805d813c8d89be3b9c41971ba494d8ff97ee0f
3
  size 557912620
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da19c72832637aa9b262dfd4f56dcc1ff2faa4b4d65254eee1a7a257ba33f327
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73dae393b2d260a70f60ef338ffd292b5f213775449dfde701757ecec893be35
3
  size 4664