augustocsc commited on
Commit
1cd801f
·
verified ·
1 Parent(s): cb0ab0e

Model save

Browse files
Files changed (3) hide show
  1. README.md +55 -55
  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: Se124M100KInfDelimiter
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
- # Se124M100KInfDelimiter
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: 0.4823
20
 
21
  ## Model description
22
 
@@ -46,58 +46,58 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:------:|:---------------:|
51
- | 0.1538 | 1.0 | 2090 | 0.5678 |
52
- | 0.1412 | 2.0 | 4180 | 0.5413 |
53
- | 0.1405 | 3.0 | 6270 | 0.5325 |
54
- | 0.1355 | 4.0 | 8360 | 0.5241 |
55
- | 0.1364 | 5.0 | 10450 | 0.5211 |
56
- | 0.1341 | 6.0 | 12540 | 0.5170 |
57
- | 0.1312 | 7.0 | 14630 | 0.5123 |
58
- | 0.1304 | 8.0 | 16720 | 0.5078 |
59
- | 0.1301 | 9.0 | 18810 | 0.5064 |
60
- | 0.1286 | 10.0 | 20900 | 0.5058 |
61
- | 0.1308 | 11.0 | 22990 | 0.5022 |
62
- | 0.1292 | 12.0 | 25080 | 0.5007 |
63
- | 0.1287 | 13.0 | 27170 | 0.5005 |
64
- | 0.1306 | 14.0 | 29260 | 0.4976 |
65
- | 0.1312 | 15.0 | 31350 | 0.4975 |
66
- | 0.1268 | 16.0 | 33440 | 0.4963 |
67
- | 0.1267 | 17.0 | 35530 | 0.4944 |
68
- | 0.1273 | 18.0 | 37620 | 0.4932 |
69
- | 0.1243 | 19.0 | 39710 | 0.4925 |
70
- | 0.1266 | 20.0 | 41800 | 0.4912 |
71
- | 0.127 | 21.0 | 43890 | 0.4914 |
72
- | 0.1278 | 22.0 | 45980 | 0.4905 |
73
- | 0.1276 | 23.0 | 48070 | 0.4899 |
74
- | 0.1285 | 24.0 | 50160 | 0.4888 |
75
- | 0.1264 | 25.0 | 52250 | 0.4889 |
76
- | 0.1256 | 26.0 | 54340 | 0.4881 |
77
- | 0.1251 | 27.0 | 56430 | 0.4876 |
78
- | 0.1291 | 28.0 | 58520 | 0.4869 |
79
- | 0.1254 | 29.0 | 60610 | 0.4867 |
80
- | 0.1268 | 30.0 | 62700 | 0.4863 |
81
- | 0.1247 | 31.0 | 64790 | 0.4857 |
82
- | 0.126 | 32.0 | 66880 | 0.4855 |
83
- | 0.1262 | 33.0 | 68970 | 0.4852 |
84
- | 0.1257 | 34.0 | 71060 | 0.4848 |
85
- | 0.1246 | 35.0 | 73150 | 0.4846 |
86
- | 0.1261 | 36.0 | 75240 | 0.4839 |
87
- | 0.1269 | 37.0 | 77330 | 0.4839 |
88
- | 0.1244 | 38.0 | 79420 | 0.4836 |
89
- | 0.1243 | 39.0 | 81510 | 0.4836 |
90
- | 0.1256 | 40.0 | 83600 | 0.4834 |
91
- | 0.1237 | 41.0 | 85690 | 0.4827 |
92
- | 0.1244 | 42.0 | 87780 | 0.4833 |
93
- | 0.1234 | 43.0 | 89870 | 0.4828 |
94
- | 0.1255 | 44.0 | 91960 | 0.4824 |
95
- | 0.1272 | 45.0 | 94050 | 0.4826 |
96
- | 0.1258 | 46.0 | 96140 | 0.4824 |
97
- | 0.1264 | 47.0 | 98230 | 0.4825 |
98
- | 0.1236 | 48.0 | 100320 | 0.4824 |
99
- | 0.1254 | 49.0 | 102410 | 0.4825 |
100
- | 0.1242 | 50.0 | 104500 | 0.4823 |
101
 
102
 
103
  ### Framework versions
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: Se124M100KInfMinimalist
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
+ # Se124M100KInfMinimalist
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: 0.5392
20
 
21
  ## Model description
22
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.1691 | 1.0 | 1860 | 0.6314 |
52
+ | 0.1598 | 2.0 | 3720 | 0.6036 |
53
+ | 0.1539 | 3.0 | 5580 | 0.5906 |
54
+ | 0.153 | 4.0 | 7440 | 0.5836 |
55
+ | 0.1507 | 5.0 | 9300 | 0.5790 |
56
+ | 0.1483 | 6.0 | 11160 | 0.5746 |
57
+ | 0.149 | 7.0 | 13020 | 0.5703 |
58
+ | 0.1485 | 8.0 | 14880 | 0.5684 |
59
+ | 0.1462 | 9.0 | 16740 | 0.5656 |
60
+ | 0.1469 | 10.0 | 18600 | 0.5630 |
61
+ | 0.1449 | 11.0 | 20460 | 0.5617 |
62
+ | 0.1469 | 12.0 | 22320 | 0.5581 |
63
+ | 0.1456 | 13.0 | 24180 | 0.5575 |
64
+ | 0.1459 | 14.0 | 26040 | 0.5547 |
65
+ | 0.1432 | 15.0 | 27900 | 0.5544 |
66
+ | 0.1429 | 16.0 | 29760 | 0.5540 |
67
+ | 0.1431 | 17.0 | 31620 | 0.5523 |
68
+ | 0.1432 | 18.0 | 33480 | 0.5512 |
69
+ | 0.1423 | 19.0 | 35340 | 0.5519 |
70
+ | 0.1429 | 20.0 | 37200 | 0.5506 |
71
+ | 0.1429 | 21.0 | 39060 | 0.5490 |
72
+ | 0.1441 | 22.0 | 40920 | 0.5477 |
73
+ | 0.1426 | 23.0 | 42780 | 0.5476 |
74
+ | 0.1436 | 24.0 | 44640 | 0.5463 |
75
+ | 0.1419 | 25.0 | 46500 | 0.5462 |
76
+ | 0.1399 | 26.0 | 48360 | 0.5449 |
77
+ | 0.1412 | 27.0 | 50220 | 0.5452 |
78
+ | 0.14 | 28.0 | 52080 | 0.5440 |
79
+ | 0.1396 | 29.0 | 53940 | 0.5440 |
80
+ | 0.1402 | 30.0 | 55800 | 0.5440 |
81
+ | 0.1404 | 31.0 | 57660 | 0.5437 |
82
+ | 0.1415 | 32.0 | 59520 | 0.5427 |
83
+ | 0.1406 | 33.0 | 61380 | 0.5420 |
84
+ | 0.1387 | 34.0 | 63240 | 0.5422 |
85
+ | 0.1392 | 35.0 | 65100 | 0.5420 |
86
+ | 0.1404 | 36.0 | 66960 | 0.5420 |
87
+ | 0.1436 | 37.0 | 68820 | 0.5411 |
88
+ | 0.1424 | 38.0 | 70680 | 0.5415 |
89
+ | 0.141 | 39.0 | 72540 | 0.5407 |
90
+ | 0.1402 | 40.0 | 74400 | 0.5403 |
91
+ | 0.1412 | 41.0 | 76260 | 0.5407 |
92
+ | 0.139 | 42.0 | 78120 | 0.5403 |
93
+ | 0.1357 | 43.0 | 79980 | 0.5401 |
94
+ | 0.1396 | 44.0 | 81840 | 0.5397 |
95
+ | 0.1398 | 45.0 | 83700 | 0.5394 |
96
+ | 0.1385 | 46.0 | 85560 | 0.5395 |
97
+ | 0.1408 | 47.0 | 87420 | 0.5396 |
98
+ | 0.1371 | 48.0 | 89280 | 0.5392 |
99
+ | 0.1418 | 49.0 | 91140 | 0.5393 |
100
+ | 0.1382 | 50.0 | 93000 | 0.5392 |
101
 
102
 
103
  ### Framework versions
all_results.json CHANGED
@@ -5,9 +5,9 @@
5
  "eval_samples_per_second": 160.588,
6
  "eval_steps_per_second": 5.02,
7
  "perplexity": 1.619794707189944,
8
- "total_flos": 2.191516447408128e+17,
9
- "train_loss": 0.12940116086530914,
10
- "train_runtime": 10778.4774,
11
- "train_samples_per_second": 310.183,
12
- "train_steps_per_second": 9.695
13
  }
 
5
  "eval_samples_per_second": 160.588,
6
  "eval_steps_per_second": 5.02,
7
  "perplexity": 1.619794707189944,
8
+ "total_flos": 1.950556483878912e+17,
9
+ "train_loss": 0.14462488290315034,
10
+ "train_runtime": 9614.4477,
11
+ "train_samples_per_second": 309.503,
12
+ "train_steps_per_second": 9.673
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 50.0,
3
- "total_flos": 2.191516447408128e+17,
4
- "train_loss": 0.12940116086530914,
5
- "train_runtime": 10778.4774,
6
- "train_samples_per_second": 310.183,
7
- "train_steps_per_second": 9.695
8
  }
 
1
  {
2
  "epoch": 50.0,
3
+ "total_flos": 1.950556483878912e+17,
4
+ "train_loss": 0.14462488290315034,
5
+ "train_runtime": 9614.4477,
6
+ "train_samples_per_second": 309.503,
7
+ "train_steps_per_second": 9.673
8
  }