Hugging Face's logo

augustocsc
/
Se124M500KInfSimple

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
augustocsc commited on
Commit
50a364f
·
verified ·
1 Parent(s): acfba18

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. README.md +43 -55
  2. adapter_model.safetensors +1 -1
  3. all_results.json +11 -11
  4. eval_results.json +6 -6
  5. tokenizer.json +1 -6
  6. train_results.json +6 -6
  7. training_args.bin +2 -2
README.md CHANGED
@@ -5,18 +5,18 @@ base_model: gpt2
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
 
@@ -46,58 +46,46 @@ The following hyperparameters were used during training:
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
 
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: 0.5204
20
 
21
  ## Model description
22
 
 
46
 
47
  ### Training results
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
 
90
 
91
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ed3f57f2acfde18959030e0b27638eae2b1ec5e94d02eab7e71bb065955c7a1
3
  size 309974336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1a68a7edfa788d730134e4ab6466ecc272829d11c502d36084ef6f3b919790
3
  size 309974336
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 50.0,
3
- "eval_loss": 0.5392394065856934,
4
- "eval_runtime": 80.8454,
5
- "eval_samples_per_second": 158.154,
6
- "eval_steps_per_second": 4.948,
7
- "perplexity": 1.7147021748977518,
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
  }
 
1
  {
2
+ "epoch": 38.0,
3
+ "eval_loss": 0.5203976631164551,
4
+ "eval_runtime": 9.8245,
5
+ "eval_samples_per_second": 161.535,
6
+ "eval_steps_per_second": 5.089,
7
+ "perplexity": 1.6826966630681837,
8
+ "total_flos": 1.886593281372979e+16,
9
+ "train_loss": 0.15147609674822032,
10
+ "train_runtime": 971.6736,
11
+ "train_samples_per_second": 389.74,
12
+ "train_steps_per_second": 12.195
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 50.0,
3
- "eval_loss": 0.5392394065856934,
4
- "eval_runtime": 80.8454,
5
- "eval_samples_per_second": 158.154,
6
- "eval_steps_per_second": 4.948,
7
- "perplexity": 1.7147021748977518
8
  }
 
1
  {
2
+ "epoch": 38.0,
3
+ "eval_loss": 0.5203976631164551,
4
+ "eval_runtime": 9.8245,
5
+ "eval_samples_per_second": 161.535,
6
+ "eval_steps_per_second": 5.089,
7
+ "perplexity": 1.6826966630681837
8
  }
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 1024,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
train_results.json CHANGED
@@ -1,8 +1,8 @@
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
  }
 
1
  {
2
+ "epoch": 38.0,
3
+ "total_flos": 1.886593281372979e+16,
4
+ "train_loss": 0.15147609674822032,
5
+ "train_runtime": 971.6736,
6
+ "train_samples_per_second": 389.74,
7
+ "train_steps_per_second": 12.195
8
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0426832942c50610ac436828fa8c166ebacacdf1b75d24835dff50e7467b4f5
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e7e48074b9d4a9223c7ec1f8f3c14b6667da1c3552646e4edae6dada307e73
3
+ size 5432