Hugging Face's logo

augustocsc
/
Se124M500KInfSimple

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
augustocsc commited on
Commit
ccb5776
·
verified ·
1 Parent(s): ddad8eb

Model save

Browse files
Files changed (3) hide show
  1. README.md +9 -44
  2. all_results.json +6 -6
  3. train_results.json +6 -6
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: 0.5204
20
 
21
  ## Model description
22
 
@@ -41,51 +41,16 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 50
45
  - mixed_precision_training: Native AMP
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
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: Se124M500KInfSimple
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
+ # Se124M500KInfSimple
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: 0.4881
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 3
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.1297 | 1.0 | 8317 | 0.5045 |
52
+ | 0.1268 | 2.0 | 16634 | 0.4917 |
53
+ | 0.1248 | 3.0 | 24951 | 0.4881 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
all_results.json CHANGED
@@ -1,13 +1,13 @@
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
  }
 
1
  {
2
+ "epoch": 3.0,
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": 5.233249244912026e+16,
9
+ "train_loss": 0.13553106638144063,
10
+ "train_runtime": 2552.5753,
11
+ "train_samples_per_second": 312.769,
12
+ "train_steps_per_second": 9.775
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
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
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "total_flos": 5.233249244912026e+16,
4
+ "train_loss": 0.13553106638144063,
5
+ "train_runtime": 2552.5753,
6
+ "train_samples_per_second": 312.769,
7
+ "train_steps_per_second": 9.775
8
  }