Hugging Face's logo

Patcas
/
v3-my_awesome

Text2Text Generation
Transformers
TensorBoard
Safetensors
plbart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Patcas commited on
Commit
8c19f7a
•
1 Parent(s): e829d27

End of training

Browse files
Files changed (3) hide show
  1. README.md +155 -0
  2. generation_config.json +8 -0
  3. runs/Dec16_18-30-01_6401e157db00/events.out.tfevents.1702751403.6401e157db00.3288.2 +2 -2
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Patcas/plbart-works
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: v3-my_awesome
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # v3-my_awesome
14
+
15
+ This model is a fine-tuned version of [Patcas/plbart-works](https://huggingface.co/Patcas/plbart-works) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.4256
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 1
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 100
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-----:|:---------------:|
48
+ | No log | 1.0 | 165 | 1.0474 |
49
+ | No log | 2.0 | 330 | 1.0274 |
50
+ | No log | 3.0 | 495 | 1.0536 |
51
+ | 0.2458 | 4.0 | 660 | 1.0316 |
52
+ | 0.2458 | 5.0 | 825 | 1.0409 |
53
+ | 0.2458 | 6.0 | 990 | 1.0534 |
54
+ | 0.1408 | 7.0 | 1155 | 1.0838 |
55
+ | 0.1408 | 8.0 | 1320 | 1.0757 |
56
+ | 0.1408 | 9.0 | 1485 | 1.1114 |
57
+ | 0.0813 | 10.0 | 1650 | 1.1037 |
58
+ | 0.0813 | 11.0 | 1815 | 1.0990 |
59
+ | 0.0813 | 12.0 | 1980 | 1.1385 |
60
+ | 0.0514 | 13.0 | 2145 | 1.1595 |
61
+ | 0.0514 | 14.0 | 2310 | 1.1591 |
62
+ | 0.0514 | 15.0 | 2475 | 1.1526 |
63
+ | 0.0358 | 16.0 | 2640 | 1.1712 |
64
+ | 0.0358 | 17.0 | 2805 | 1.1831 |
65
+ | 0.0358 | 18.0 | 2970 | 1.1991 |
66
+ | 0.027 | 19.0 | 3135 | 1.1804 |
67
+ | 0.027 | 20.0 | 3300 | 1.1840 |
68
+ | 0.027 | 21.0 | 3465 | 1.2039 |
69
+ | 0.0231 | 22.0 | 3630 | 1.2017 |
70
+ | 0.0231 | 23.0 | 3795 | 1.2293 |
71
+ | 0.0231 | 24.0 | 3960 | 1.2377 |
72
+ | 0.0182 | 25.0 | 4125 | 1.2383 |
73
+ | 0.0182 | 26.0 | 4290 | 1.2409 |
74
+ | 0.0182 | 27.0 | 4455 | 1.2399 |
75
+ | 0.0138 | 28.0 | 4620 | 1.2400 |
76
+ | 0.0138 | 29.0 | 4785 | 1.2569 |
77
+ | 0.0138 | 30.0 | 4950 | 1.2861 |
78
+ | 0.0102 | 31.0 | 5115 | 1.2626 |
79
+ | 0.0102 | 32.0 | 5280 | 1.2841 |
80
+ | 0.0102 | 33.0 | 5445 | 1.2767 |
81
+ | 0.0088 | 34.0 | 5610 | 1.2558 |
82
+ | 0.0088 | 35.0 | 5775 | 1.2666 |
83
+ | 0.0088 | 36.0 | 5940 | 1.2852 |
84
+ | 0.0088 | 37.0 | 6105 | 1.2958 |
85
+ | 0.0088 | 38.0 | 6270 | 1.3174 |
86
+ | 0.0088 | 39.0 | 6435 | 1.2938 |
87
+ | 0.0099 | 40.0 | 6600 | 1.3063 |
88
+ | 0.0099 | 41.0 | 6765 | 1.2998 |
89
+ | 0.0099 | 42.0 | 6930 | 1.3176 |
90
+ | 0.0078 | 43.0 | 7095 | 1.3139 |
91
+ | 0.0078 | 44.0 | 7260 | 1.2946 |
92
+ | 0.0078 | 45.0 | 7425 | 1.3100 |
93
+ | 0.0068 | 46.0 | 7590 | 1.3153 |
94
+ | 0.0068 | 47.0 | 7755 | 1.3185 |
95
+ | 0.0068 | 48.0 | 7920 | 1.3339 |
96
+ | 0.0063 | 49.0 | 8085 | 1.3284 |
97
+ | 0.0063 | 50.0 | 8250 | 1.3353 |
98
+ | 0.0063 | 51.0 | 8415 | 1.3271 |
99
+ | 0.0045 | 52.0 | 8580 | 1.3470 |
100
+ | 0.0045 | 53.0 | 8745 | 1.3348 |
101
+ | 0.0045 | 54.0 | 8910 | 1.3485 |
102
+ | 0.0038 | 55.0 | 9075 | 1.3368 |
103
+ | 0.0038 | 56.0 | 9240 | 1.3429 |
104
+ | 0.0038 | 57.0 | 9405 | 1.3564 |
105
+ | 0.0041 | 58.0 | 9570 | 1.3642 |
106
+ | 0.0041 | 59.0 | 9735 | 1.3657 |
107
+ | 0.0041 | 60.0 | 9900 | 1.3540 |
108
+ | 0.0033 | 61.0 | 10065 | 1.3671 |
109
+ | 0.0033 | 62.0 | 10230 | 1.3632 |
110
+ | 0.0033 | 63.0 | 10395 | 1.3698 |
111
+ | 0.0029 | 64.0 | 10560 | 1.3805 |
112
+ | 0.0029 | 65.0 | 10725 | 1.3878 |
113
+ | 0.0029 | 66.0 | 10890 | 1.3864 |
114
+ | 0.0026 | 67.0 | 11055 | 1.3906 |
115
+ | 0.0026 | 68.0 | 11220 | 1.3981 |
116
+ | 0.0026 | 69.0 | 11385 | 1.3931 |
117
+ | 0.0027 | 70.0 | 11550 | 1.3868 |
118
+ | 0.0027 | 71.0 | 11715 | 1.3873 |
119
+ | 0.0027 | 72.0 | 11880 | 1.3857 |
120
+ | 0.0025 | 73.0 | 12045 | 1.3879 |
121
+ | 0.0025 | 74.0 | 12210 | 1.3871 |
122
+ | 0.0025 | 75.0 | 12375 | 1.3937 |
123
+ | 0.002 | 76.0 | 12540 | 1.4003 |
124
+ | 0.002 | 77.0 | 12705 | 1.4048 |
125
+ | 0.002 | 78.0 | 12870 | 1.4056 |
126
+ | 0.0022 | 79.0 | 13035 | 1.4074 |
127
+ | 0.0022 | 80.0 | 13200 | 1.4064 |
128
+ | 0.0022 | 81.0 | 13365 | 1.4059 |
129
+ | 0.0016 | 82.0 | 13530 | 1.4160 |
130
+ | 0.0016 | 83.0 | 13695 | 1.4078 |
131
+ | 0.0016 | 84.0 | 13860 | 1.4132 |
132
+ | 0.0015 | 85.0 | 14025 | 1.4119 |
133
+ | 0.0015 | 86.0 | 14190 | 1.4147 |
134
+ | 0.0015 | 87.0 | 14355 | 1.4131 |
135
+ | 0.0014 | 88.0 | 14520 | 1.4131 |
136
+ | 0.0014 | 89.0 | 14685 | 1.4118 |
137
+ | 0.0014 | 90.0 | 14850 | 1.4152 |
138
+ | 0.0013 | 91.0 | 15015 | 1.4211 |
139
+ | 0.0013 | 92.0 | 15180 | 1.4213 |
140
+ | 0.0013 | 93.0 | 15345 | 1.4238 |
141
+ | 0.0012 | 94.0 | 15510 | 1.4222 |
142
+ | 0.0012 | 95.0 | 15675 | 1.4246 |
143
+ | 0.0012 | 96.0 | 15840 | 1.4247 |
144
+ | 0.0011 | 97.0 | 16005 | 1.4261 |
145
+ | 0.0011 | 98.0 | 16170 | 1.4259 |
146
+ | 0.0011 | 99.0 | 16335 | 1.4255 |
147
+ | 0.0011 | 100.0 | 16500 | 1.4256 |
148
+
149
+
150
+ ### Framework versions
151
+
152
+ - Transformers 4.35.2
153
+ - Pytorch 2.1.0+cu121
154
+ - Datasets 2.15.0
155
+ - Tokenizers 0.15.0
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.35.2"
8
+ }
runs/Dec16_18-30-01_6401e157db00/events.out.tfevents.1702751403.6401e157db00.3288.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a50dda7f051236d9b495477d6b52186cb7025ac5b820ec812026a67dceca9ed7
3
- size 36571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a384068075a3f31f448967fef7d0117b8a8d8cfa5097972ca161107a36c2f4c
3
+ size 37207