augustocsc commited on
Commit
d8f4d7f
·
verified ·
1 Parent(s): 6aa4a95

Model save

Browse files
Files changed (3) hide show
  1. README.md +53 -53
  2. all_results.json +5 -5
  3. train_results.json +5 -5
README.md CHANGED
@@ -5,18 +5,18 @@ base_model: gpt2
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
- - name: Se124M100KInfSimple
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
- # Se124M100KInfSimple
16
 
17
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4582
20
 
21
  ## Model description
22
 
@@ -48,56 +48,56 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:------:|:---------------:|
51
- | 0.1445 | 1.0 | 2205 | 0.5442 |
52
- | 0.1358 | 2.0 | 4410 | 0.5179 |
53
- | 0.1317 | 3.0 | 6615 | 0.5090 |
54
- | 0.1297 | 4.0 | 8820 | 0.5015 |
55
- | 0.1299 | 5.0 | 11025 | 0.4954 |
56
- | 0.1301 | 6.0 | 13230 | 0.4917 |
57
- | 0.1258 | 7.0 | 15435 | 0.4875 |
58
- | 0.1254 | 8.0 | 17640 | 0.4834 |
59
- | 0.1231 | 9.0 | 19845 | 0.4816 |
60
- | 0.1254 | 10.0 | 22050 | 0.4798 |
61
- | 0.125 | 11.0 | 24255 | 0.4778 |
62
- | 0.1225 | 12.0 | 26460 | 0.4775 |
63
- | 0.1233 | 13.0 | 28665 | 0.4753 |
64
- | 0.1213 | 14.0 | 30870 | 0.4737 |
65
- | 0.1231 | 15.0 | 33075 | 0.4719 |
66
- | 0.1233 | 16.0 | 35280 | 0.4716 |
67
- | 0.1225 | 17.0 | 37485 | 0.4702 |
68
- | 0.1218 | 18.0 | 39690 | 0.4696 |
69
- | 0.1213 | 19.0 | 41895 | 0.4678 |
70
- | 0.1213 | 20.0 | 44100 | 0.4673 |
71
- | 0.121 | 21.0 | 46305 | 0.4675 |
72
- | 0.122 | 22.0 | 48510 | 0.4663 |
73
- | 0.1195 | 23.0 | 50715 | 0.4657 |
74
- | 0.1221 | 24.0 | 52920 | 0.4647 |
75
- | 0.1212 | 25.0 | 55125 | 0.4647 |
76
- | 0.121 | 26.0 | 57330 | 0.4640 |
77
- | 0.1213 | 27.0 | 59535 | 0.4637 |
78
- | 0.1184 | 28.0 | 61740 | 0.4629 |
79
- | 0.12 | 29.0 | 63945 | 0.4627 |
80
- | 0.1191 | 30.0 | 66150 | 0.4622 |
81
- | 0.1195 | 31.0 | 68355 | 0.4624 |
82
- | 0.1188 | 32.0 | 70560 | 0.4619 |
83
- | 0.1202 | 33.0 | 72765 | 0.4620 |
84
- | 0.119 | 34.0 | 74970 | 0.4605 |
85
- | 0.1206 | 35.0 | 77175 | 0.4608 |
86
- | 0.1197 | 36.0 | 79380 | 0.4601 |
87
- | 0.1199 | 37.0 | 81585 | 0.4597 |
88
- | 0.1204 | 38.0 | 83790 | 0.4601 |
89
- | 0.1185 | 39.0 | 85995 | 0.4596 |
90
- | 0.1184 | 40.0 | 88200 | 0.4591 |
91
- | 0.119 | 41.0 | 90405 | 0.4594 |
92
- | 0.1181 | 42.0 | 92610 | 0.4591 |
93
- | 0.1178 | 43.0 | 94815 | 0.4588 |
94
- | 0.1188 | 44.0 | 97020 | 0.4586 |
95
- | 0.1189 | 45.0 | 99225 | 0.4584 |
96
- | 0.1183 | 46.0 | 101430 | 0.4583 |
97
- | 0.1184 | 47.0 | 103635 | 0.4582 |
98
- | 0.1185 | 48.0 | 105840 | 0.4581 |
99
- | 0.1198 | 49.0 | 108045 | 0.4582 |
100
- | 0.1207 | 50.0 | 110250 | 0.4582 |
101
 
102
 
103
  ### Framework versions
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: Se124M100KInfKeyValue
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
+ # Se124M100KInfKeyValue
16
 
17
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.4826
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:------:|:---------------:|
51
+ | 0.1533 | 1.0 | 2090 | 0.5677 |
52
+ | 0.141 | 2.0 | 4180 | 0.5401 |
53
+ | 0.1401 | 3.0 | 6270 | 0.5321 |
54
+ | 0.1351 | 4.0 | 8360 | 0.5224 |
55
+ | 0.1361 | 5.0 | 10450 | 0.5209 |
56
+ | 0.134 | 6.0 | 12540 | 0.5155 |
57
+ | 0.1315 | 7.0 | 14630 | 0.5118 |
58
+ | 0.1304 | 8.0 | 16720 | 0.5085 |
59
+ | 0.1299 | 9.0 | 18810 | 0.5067 |
60
+ | 0.1294 | 10.0 | 20900 | 0.5066 |
61
+ | 0.1309 | 11.0 | 22990 | 0.5030 |
62
+ | 0.129 | 12.0 | 25080 | 0.5004 |
63
+ | 0.1292 | 13.0 | 27170 | 0.4999 |
64
+ | 0.1309 | 14.0 | 29260 | 0.4985 |
65
+ | 0.1312 | 15.0 | 31350 | 0.4974 |
66
+ | 0.1275 | 16.0 | 33440 | 0.4963 |
67
+ | 0.1265 | 17.0 | 35530 | 0.4950 |
68
+ | 0.1276 | 18.0 | 37620 | 0.4936 |
69
+ | 0.1247 | 19.0 | 39710 | 0.4931 |
70
+ | 0.1268 | 20.0 | 41800 | 0.4919 |
71
+ | 0.1273 | 21.0 | 43890 | 0.4914 |
72
+ | 0.1284 | 22.0 | 45980 | 0.4907 |
73
+ | 0.1276 | 23.0 | 48070 | 0.4898 |
74
+ | 0.1284 | 24.0 | 50160 | 0.4894 |
75
+ | 0.1263 | 25.0 | 52250 | 0.4894 |
76
+ | 0.1264 | 26.0 | 54340 | 0.4888 |
77
+ | 0.1257 | 27.0 | 56430 | 0.4881 |
78
+ | 0.1292 | 28.0 | 58520 | 0.4875 |
79
+ | 0.1262 | 29.0 | 60610 | 0.4874 |
80
+ | 0.1272 | 30.0 | 62700 | 0.4867 |
81
+ | 0.1252 | 31.0 | 64790 | 0.4864 |
82
+ | 0.1261 | 32.0 | 66880 | 0.4859 |
83
+ | 0.1262 | 33.0 | 68970 | 0.4858 |
84
+ | 0.1256 | 34.0 | 71060 | 0.4849 |
85
+ | 0.1251 | 35.0 | 73150 | 0.4847 |
86
+ | 0.1263 | 36.0 | 75240 | 0.4843 |
87
+ | 0.1266 | 37.0 | 77330 | 0.4843 |
88
+ | 0.125 | 38.0 | 79420 | 0.4842 |
89
+ | 0.1248 | 39.0 | 81510 | 0.4840 |
90
+ | 0.126 | 40.0 | 83600 | 0.4837 |
91
+ | 0.1239 | 41.0 | 85690 | 0.4831 |
92
+ | 0.1246 | 42.0 | 87780 | 0.4837 |
93
+ | 0.1241 | 43.0 | 89870 | 0.4830 |
94
+ | 0.1259 | 44.0 | 91960 | 0.4829 |
95
+ | 0.1275 | 45.0 | 94050 | 0.4828 |
96
+ | 0.1258 | 46.0 | 96140 | 0.4826 |
97
+ | 0.1265 | 47.0 | 98230 | 0.4828 |
98
+ | 0.1235 | 48.0 | 100320 | 0.4827 |
99
+ | 0.1255 | 49.0 | 102410 | 0.4827 |
100
+ | 0.1245 | 50.0 | 104500 | 0.4826 |
101
 
102
 
103
  ### Framework versions
all_results.json CHANGED
@@ -5,9 +5,9 @@
5
  "eval_samples_per_second": 158.911,
6
  "eval_steps_per_second": 4.972,
7
  "perplexity": 1.5811901214941453,
8
- "total_flos": 2.31193087967232e+17,
9
- "train_loss": 0.1232609451103643,
10
- "train_runtime": 11754.4686,
11
- "train_samples_per_second": 300.056,
12
- "train_steps_per_second": 9.379
13
  }
 
5
  "eval_samples_per_second": 158.911,
6
  "eval_steps_per_second": 4.972,
7
  "perplexity": 1.5811901214941453,
8
+ "total_flos": 2.191516447408128e+17,
9
+ "train_loss": 0.12956011656254673,
10
+ "train_runtime": 10667.5849,
11
+ "train_samples_per_second": 313.407,
12
+ "train_steps_per_second": 9.796
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 50.0,
3
- "total_flos": 2.31193087967232e+17,
4
- "train_loss": 0.1232609451103643,
5
- "train_runtime": 11754.4686,
6
- "train_samples_per_second": 300.056,
7
- "train_steps_per_second": 9.379
8
  }
 
1
  {
2
  "epoch": 50.0,
3
+ "total_flos": 2.191516447408128e+17,
4
+ "train_loss": 0.12956011656254673,
5
+ "train_runtime": 10667.5849,
6
+ "train_samples_per_second": 313.407,
7
+ "train_steps_per_second": 9.796
8
  }