Hugging Face's logo

jpodivin
/
rh_qa_model

Question Answering
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
jpodivin commited on
Commit
730bfa2
•
1 Parent(s): 00770ed

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -111
  2. model.safetensors +1 -1
  3. runs/Jan25_15-06-31_4ea813092d5a/events.out.tfevents.1706195191.4ea813092d5a.30167.2 +2 -2
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,9 +13,14 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # rh_qa_model
15
 
16
- This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.4148
 
 
 
 
 
19
 
20
  ## Model description
21
 
@@ -35,119 +40,13 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
- - train_batch_size: 16
39
- - eval_batch_size: 16
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 | 14 | 3.1715 |
50
- | No log | 2.0 | 28 | 2.2625 |
51
- | No log | 3.0 | 42 | 1.8385 |
52
- | No log | 4.0 | 56 | 1.5586 |
53
- | No log | 5.0 | 70 | 1.3127 |
54
- | No log | 6.0 | 84 | 1.1556 |
55
- | No log | 7.0 | 98 | 1.0699 |
56
- | No log | 8.0 | 112 | 0.8843 |
57
- | No log | 9.0 | 126 | 0.7782 |
58
- | No log | 10.0 | 140 | 0.8645 |
59
- | No log | 11.0 | 154 | 0.6969 |
60
- | No log | 12.0 | 168 | 0.7130 |
61
- | No log | 13.0 | 182 | 0.7346 |
62
- | No log | 14.0 | 196 | 0.6394 |
63
- | No log | 15.0 | 210 | 0.6501 |
64
- | No log | 16.0 | 224 | 0.5198 |
65
- | No log | 17.0 | 238 | 0.6806 |
66
- | No log | 18.0 | 252 | 0.5010 |
67
- | No log | 19.0 | 266 | 0.4730 |
68
- | No log | 20.0 | 280 | 0.4384 |
69
- | No log | 21.0 | 294 | 0.5072 |
70
- | No log | 22.0 | 308 | 0.7052 |
71
- | No log | 23.0 | 322 | 0.5192 |
72
- | No log | 24.0 | 336 | 0.5131 |
73
- | No log | 25.0 | 350 | 0.4587 |
74
- | No log | 26.0 | 364 | 0.5063 |
75
- | No log | 27.0 | 378 | 0.5847 |
76
- | No log | 28.0 | 392 | 0.5687 |
77
- | No log | 29.0 | 406 | 0.4751 |
78
- | No log | 30.0 | 420 | 0.5268 |
79
- | No log | 31.0 | 434 | 0.4624 |
80
- | No log | 32.0 | 448 | 0.6690 |
81
- | No log | 33.0 | 462 | 0.5542 |
82
- | No log | 34.0 | 476 | 0.5325 |
83
- | No log | 35.0 | 490 | 0.4658 |
84
- | 0.6171 | 36.0 | 504 | 0.4740 |
85
- | 0.6171 | 37.0 | 518 | 0.4895 |
86
- | 0.6171 | 38.0 | 532 | 0.4703 |
87
- | 0.6171 | 39.0 | 546 | 0.5297 |
88
- | 0.6171 | 40.0 | 560 | 0.4644 |
89
- | 0.6171 | 41.0 | 574 | 0.4785 |
90
- | 0.6171 | 42.0 | 588 | 0.4762 |
91
- | 0.6171 | 43.0 | 602 | 0.4621 |
92
- | 0.6171 | 44.0 | 616 | 0.5370 |
93
- | 0.6171 | 45.0 | 630 | 0.5178 |
94
- | 0.6171 | 46.0 | 644 | 0.4732 |
95
- | 0.6171 | 47.0 | 658 | 0.4982 |
96
- | 0.6171 | 48.0 | 672 | 0.4894 |
97
- | 0.6171 | 49.0 | 686 | 0.4453 |
98
- | 0.6171 | 50.0 | 700 | 0.5137 |
99
- | 0.6171 | 51.0 | 714 | 0.4349 |
100
- | 0.6171 | 52.0 | 728 | 0.4134 |
101
- | 0.6171 | 53.0 | 742 | 0.4375 |
102
- | 0.6171 | 54.0 | 756 | 0.4453 |
103
- | 0.6171 | 55.0 | 770 | 0.4425 |
104
- | 0.6171 | 56.0 | 784 | 0.3920 |
105
- | 0.6171 | 57.0 | 798 | 0.3902 |
106
- | 0.6171 | 58.0 | 812 | 0.4387 |
107
- | 0.6171 | 59.0 | 826 | 0.4759 |
108
- | 0.6171 | 60.0 | 840 | 0.4824 |
109
- | 0.6171 | 61.0 | 854 | 0.4481 |
110
- | 0.6171 | 62.0 | 868 | 0.4206 |
111
- | 0.6171 | 63.0 | 882 | 0.4524 |
112
- | 0.6171 | 64.0 | 896 | 0.3694 |
113
- | 0.6171 | 65.0 | 910 | 0.4345 |
114
- | 0.6171 | 66.0 | 924 | 0.4957 |
115
- | 0.6171 | 67.0 | 938 | 0.4407 |
116
- | 0.6171 | 68.0 | 952 | 0.4615 |
117
- | 0.6171 | 69.0 | 966 | 0.4300 |
118
- | 0.6171 | 70.0 | 980 | 0.4805 |
119
- | 0.6171 | 71.0 | 994 | 0.4524 |
120
- | 0.2178 | 72.0 | 1008 | 0.4411 |
121
- | 0.2178 | 73.0 | 1022 | 0.3767 |
122
- | 0.2178 | 74.0 | 1036 | 0.4178 |
123
- | 0.2178 | 75.0 | 1050 | 0.4271 |
124
- | 0.2178 | 76.0 | 1064 | 0.4397 |
125
- | 0.2178 | 77.0 | 1078 | 0.4461 |
126
- | 0.2178 | 78.0 | 1092 | 0.4313 |
127
- | 0.2178 | 79.0 | 1106 | 0.4162 |
128
- | 0.2178 | 80.0 | 1120 | 0.4404 |
129
- | 0.2178 | 81.0 | 1134 | 0.4549 |
130
- | 0.2178 | 82.0 | 1148 | 0.4421 |
131
- | 0.2178 | 83.0 | 1162 | 0.4219 |
132
- | 0.2178 | 84.0 | 1176 | 0.4328 |
133
- | 0.2178 | 85.0 | 1190 | 0.4168 |
134
- | 0.2178 | 86.0 | 1204 | 0.4724 |
135
- | 0.2178 | 87.0 | 1218 | 0.4334 |
136
- | 0.2178 | 88.0 | 1232 | 0.4430 |
137
- | 0.2178 | 89.0 | 1246 | 0.4263 |
138
- | 0.2178 | 90.0 | 1260 | 0.4126 |
139
- | 0.2178 | 91.0 | 1274 | 0.4021 |
140
- | 0.2178 | 92.0 | 1288 | 0.4027 |
141
- | 0.2178 | 93.0 | 1302 | 0.4110 |
142
- | 0.2178 | 94.0 | 1316 | 0.4199 |
143
- | 0.2178 | 95.0 | 1330 | 0.4182 |
144
- | 0.2178 | 96.0 | 1344 | 0.4171 |
145
- | 0.2178 | 97.0 | 1358 | 0.4198 |
146
- | 0.2178 | 98.0 | 1372 | 0.4200 |
147
- | 0.2178 | 99.0 | 1386 | 0.4157 |
148
- | 0.2178 | 100.0 | 1400 | 0.4148 |
149
-
150
-
151
  ### Framework versions
152
 
153
  - Transformers 4.35.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-cased
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # rh_qa_model
15
 
16
+ This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - eval_loss: 0.3264
19
+ - eval_runtime: 0.672
20
+ - eval_samples_per_second: 78.866
21
+ - eval_steps_per_second: 10.416
22
+ - epoch: 38.0
23
+ - step: 1026
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 2e-05
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - num_epochs: 100
49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  ### Framework versions
51
 
52
  - Transformers 4.35.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33e5575ce07c5d2abefd121f85251adae76937aeb41705b9b6a8c77a92e46082
3
  size 260782152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a4bc757bc440c99ae9a52cfef93f2f14943fbd35a24f30b1db19fd3eb897b93
3
  size 260782152
runs/Jan25_15-06-31_4ea813092d5a/events.out.tfevents.1706195191.4ea813092d5a.30167.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ff6954f615bc6eef28a6ef0718b52cdcb922bcbcc0d4eff7107d92141ab23ef
3
- size 13991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b76d92b89a7c409a5fc71d3f461027361aa754c2a1fec582c61e08212fcdb2
3
+ size 14690