augustocsc commited on
Commit
e7eaa98
·
verified ·
1 Parent(s): adb6f79

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: Se124M10KInfSimple
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
- # Se124M10KInfSimple
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: 0.5177
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
- | 0.3959 | 1.0 | 237 | 0.9383 |
52
- | 0.2182 | 2.0 | 474 | 0.6835 |
53
- | 0.1772 | 3.0 | 711 | 0.6222 |
54
- | 0.1676 | 4.0 | 948 | 0.5980 |
55
- | 0.1609 | 5.0 | 1185 | 0.5840 |
56
- | 0.1519 | 6.0 | 1422 | 0.5740 |
57
- | 0.1535 | 7.0 | 1659 | 0.5659 |
58
- | 0.1492 | 8.0 | 1896 | 0.5587 |
59
- | 0.1456 | 9.0 | 2133 | 0.5575 |
60
- | 0.1427 | 10.0 | 2370 | 0.5528 |
61
- | 0.1442 | 11.0 | 2607 | 0.5499 |
62
- | 0.1403 | 12.0 | 2844 | 0.5466 |
63
- | 0.1425 | 13.0 | 3081 | 0.5449 |
64
- | 0.1403 | 14.0 | 3318 | 0.5414 |
65
- | 0.1405 | 15.0 | 3555 | 0.5399 |
66
- | 0.1387 | 16.0 | 3792 | 0.5383 |
67
- | 0.1377 | 17.0 | 4029 | 0.5368 |
68
- | 0.1379 | 18.0 | 4266 | 0.5376 |
69
- | 0.1353 | 19.0 | 4503 | 0.5349 |
70
- | 0.1378 | 20.0 | 4740 | 0.5313 |
71
- | 0.1372 | 21.0 | 4977 | 0.5320 |
72
- | 0.135 | 22.0 | 5214 | 0.5286 |
73
- | 0.1361 | 23.0 | 5451 | 0.5282 |
74
- | 0.1357 | 24.0 | 5688 | 0.5287 |
75
- | 0.1372 | 25.0 | 5925 | 0.5269 |
76
- | 0.1343 | 26.0 | 6162 | 0.5271 |
77
- | 0.1321 | 27.0 | 6399 | 0.5255 |
78
- | 0.1341 | 28.0 | 6636 | 0.5240 |
79
- | 0.1346 | 29.0 | 6873 | 0.5235 |
80
- | 0.1327 | 30.0 | 7110 | 0.5239 |
81
- | 0.1335 | 31.0 | 7347 | 0.5230 |
82
- | 0.1332 | 32.0 | 7584 | 0.5228 |
83
- | 0.1317 | 33.0 | 7821 | 0.5234 |
84
- | 0.1331 | 34.0 | 8058 | 0.5220 |
85
- | 0.1327 | 35.0 | 8295 | 0.5213 |
86
- | 0.1338 | 36.0 | 8532 | 0.5204 |
87
- | 0.1306 | 37.0 | 8769 | 0.5206 |
88
- | 0.1317 | 38.0 | 9006 | 0.5208 |
89
- | 0.1327 | 39.0 | 9243 | 0.5196 |
90
- | 0.1337 | 40.0 | 9480 | 0.5195 |
91
- | 0.1325 | 41.0 | 9717 | 0.5187 |
92
- | 0.1308 | 42.0 | 9954 | 0.5189 |
93
- | 0.1304 | 43.0 | 10191 | 0.5184 |
94
- | 0.1305 | 44.0 | 10428 | 0.5185 |
95
- | 0.1316 | 45.0 | 10665 | 0.5179 |
96
- | 0.1298 | 46.0 | 10902 | 0.5182 |
97
- | 0.1334 | 47.0 | 11139 | 0.5179 |
98
- | 0.1315 | 48.0 | 11376 | 0.5178 |
99
- | 0.131 | 49.0 | 11613 | 0.5176 |
100
- | 0.1302 | 50.0 | 11850 | 0.5177 |
101
 
102
 
103
  ### Framework versions
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: Se124M10KInfKeyValue
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
+ # Se124M10KInfKeyValue
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: 0.5416
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.3613 | 1.0 | 225 | 0.9669 |
52
+ | 0.2223 | 2.0 | 450 | 0.7171 |
53
+ | 0.1879 | 3.0 | 675 | 0.6545 |
54
+ | 0.1715 | 4.0 | 900 | 0.6227 |
55
+ | 0.1658 | 5.0 | 1125 | 0.6118 |
56
+ | 0.1606 | 6.0 | 1350 | 0.6041 |
57
+ | 0.1571 | 7.0 | 1575 | 0.5922 |
58
+ | 0.1547 | 8.0 | 1800 | 0.5869 |
59
+ | 0.1541 | 9.0 | 2025 | 0.5817 |
60
+ | 0.1499 | 10.0 | 2250 | 0.5814 |
61
+ | 0.1511 | 11.0 | 2475 | 0.5738 |
62
+ | 0.1479 | 12.0 | 2700 | 0.5730 |
63
+ | 0.1487 | 13.0 | 2925 | 0.5697 |
64
+ | 0.1449 | 14.0 | 3150 | 0.5665 |
65
+ | 0.1448 | 15.0 | 3375 | 0.5653 |
66
+ | 0.1435 | 16.0 | 3600 | 0.5645 |
67
+ | 0.1455 | 17.0 | 3825 | 0.5612 |
68
+ | 0.1437 | 18.0 | 4050 | 0.5586 |
69
+ | 0.1417 | 19.0 | 4275 | 0.5565 |
70
+ | 0.1434 | 20.0 | 4500 | 0.5580 |
71
+ | 0.1439 | 21.0 | 4725 | 0.5561 |
72
+ | 0.1421 | 22.0 | 4950 | 0.5552 |
73
+ | 0.1414 | 23.0 | 5175 | 0.5532 |
74
+ | 0.1396 | 24.0 | 5400 | 0.5505 |
75
+ | 0.1392 | 25.0 | 5625 | 0.5521 |
76
+ | 0.1413 | 26.0 | 5850 | 0.5517 |
77
+ | 0.1385 | 27.0 | 6075 | 0.5478 |
78
+ | 0.1413 | 28.0 | 6300 | 0.5485 |
79
+ | 0.1411 | 29.0 | 6525 | 0.5500 |
80
+ | 0.139 | 30.0 | 6750 | 0.5482 |
81
+ | 0.1402 | 31.0 | 6975 | 0.5480 |
82
+ | 0.1397 | 32.0 | 7200 | 0.5462 |
83
+ | 0.1402 | 33.0 | 7425 | 0.5448 |
84
+ | 0.1405 | 34.0 | 7650 | 0.5472 |
85
+ | 0.1374 | 35.0 | 7875 | 0.5437 |
86
+ | 0.1373 | 36.0 | 8100 | 0.5446 |
87
+ | 0.1386 | 37.0 | 8325 | 0.5439 |
88
+ | 0.1372 | 38.0 | 8550 | 0.5438 |
89
+ | 0.1383 | 39.0 | 8775 | 0.5431 |
90
+ | 0.1375 | 40.0 | 9000 | 0.5428 |
91
+ | 0.1398 | 41.0 | 9225 | 0.5431 |
92
+ | 0.1394 | 42.0 | 9450 | 0.5418 |
93
+ | 0.1395 | 43.0 | 9675 | 0.5423 |
94
+ | 0.1377 | 44.0 | 9900 | 0.5423 |
95
+ | 0.1366 | 45.0 | 10125 | 0.5422 |
96
+ | 0.138 | 46.0 | 10350 | 0.5419 |
97
+ | 0.136 | 47.0 | 10575 | 0.5416 |
98
+ | 0.138 | 48.0 | 10800 | 0.5418 |
99
+ | 0.1373 | 49.0 | 11025 | 0.5417 |
100
+ | 0.1365 | 50.0 | 11250 | 0.5416 |
101
 
102
 
103
  ### Framework versions
all_results.json CHANGED
@@ -5,9 +5,9 @@
5
  "eval_samples_per_second": 158.647,
6
  "eval_steps_per_second": 4.998,
7
  "perplexity": 1.678217974585131,
8
- "total_flos": 2.48235958075392e+16,
9
- "train_loss": 0.14677102237814085,
10
- "train_runtime": 1298.068,
11
- "train_samples_per_second": 291.741,
12
- "train_steps_per_second": 9.129
13
  }
 
5
  "eval_samples_per_second": 158.647,
6
  "eval_steps_per_second": 4.998,
7
  "perplexity": 1.678217974585131,
8
+ "total_flos": 2.35191607492608e+16,
9
+ "train_loss": 0.15202610808478462,
10
+ "train_runtime": 1233.6469,
11
+ "train_samples_per_second": 290.845,
12
+ "train_steps_per_second": 9.119
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 50.0,
3
- "total_flos": 2.48235958075392e+16,
4
- "train_loss": 0.14677102237814085,
5
- "train_runtime": 1298.068,
6
- "train_samples_per_second": 291.741,
7
- "train_steps_per_second": 9.129
8
  }
 
1
  {
2
  "epoch": 50.0,
3
+ "total_flos": 2.35191607492608e+16,
4
+ "train_loss": 0.15202610808478462,
5
+ "train_runtime": 1233.6469,
6
+ "train_samples_per_second": 290.845,
7
+ "train_steps_per_second": 9.119
8
  }