Hugging Face's logo

augustocsc
/
Se124M10KInfPrompt

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
augustocsc commited on
Commit
ea34a79
·
verified ·
1 Parent(s): e8a12d7

Model save

Browse files
Files changed (4) hide show
  1. README.md +32 -34
  2. adapter_model.safetensors +1 -1
  3. all_results.json +6 -6
  4. 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: 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: 0.4475
20
 
21
  ## Model description
22
 
@@ -46,37 +46,35 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:------:|:---------------:|
51
- | 0.1287 | 1.0 | 8317 | 0.5023 |
52
- | 0.1249 | 2.0 | 16634 | 0.4836 |
53
- | 0.1214 | 3.0 | 24951 | 0.4746 |
54
- | 0.1225 | 4.0 | 33268 | 0.4691 |
55
- | 0.1212 | 5.0 | 41585 | 0.4653 |
56
- | 0.1192 | 6.0 | 49902 | 0.4625 |
57
- | 0.1203 | 7.0 | 58219 | 0.4595 |
58
- | 0.1182 | 8.0 | 66536 | 0.4579 |
59
- | 0.117 | 9.0 | 74853 | 0.4565 |
60
- | 0.1184 | 10.0 | 83170 | 0.4543 |
61
- | 0.1165 | 11.0 | 91487 | 0.4539 |
62
- | 0.116 | 12.0 | 99804 | 0.4528 |
63
- | 0.117 | 13.0 | 108121 | 0.4515 |
64
- | 0.1161 | 14.0 | 116438 | 0.4512 |
65
- | 0.1149 | 15.0 | 124755 | 0.4510 |
66
- | 0.1157 | 16.0 | 133072 | 0.4503 |
67
- | 0.1162 | 17.0 | 141389 | 0.4497 |
68
- | 0.1155 | 18.0 | 149706 | 0.4497 |
69
- | 0.115 | 19.0 | 158023 | 0.4496 |
70
- | 0.1156 | 20.0 | 166340 | 0.4488 |
71
- | 0.1156 | 21.0 | 174657 | 0.4492 |
72
- | 0.114 | 22.0 | 182974 | 0.4483 |
73
- | 0.1122 | 23.0 | 191291 | 0.4488 |
74
- | 0.1134 | 24.0 | 199608 | 0.4480 |
75
- | 0.114 | 25.0 | 207925 | 0.4476 |
76
- | 0.1159 | 26.0 | 216242 | 0.4481 |
77
- | 0.115 | 27.0 | 224559 | 0.4475 |
78
- | 0.1145 | 28.0 | 232876 | 0.4475 |
79
- | 0.1141 | 29.0 | 241193 | 0.4477 |
80
 
81
 
82
  ### Framework versions
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: Se124M10KInfPrompt
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
+ # Se124M10KInfPrompt
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: 0.4232
20
 
21
  ## Model description
22
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.5306 | 1.0 | 169 | 0.9535 |
52
+ | 0.2161 | 2.0 | 338 | 0.6077 |
53
+ | 0.1624 | 3.0 | 507 | 0.5296 |
54
+ | 0.1515 | 4.0 | 676 | 0.4989 |
55
+ | 0.1434 | 5.0 | 845 | 0.4825 |
56
+ | 0.1366 | 6.0 | 1014 | 0.4712 |
57
+ | 0.1328 | 7.0 | 1183 | 0.4663 |
58
+ | 0.1294 | 8.0 | 1352 | 0.4613 |
59
+ | 0.1258 | 9.0 | 1521 | 0.4544 |
60
+ | 0.1259 | 10.0 | 1690 | 0.4544 |
61
+ | 0.1238 | 11.0 | 1859 | 0.4471 |
62
+ | 0.1216 | 12.0 | 2028 | 0.4424 |
63
+ | 0.1214 | 13.0 | 2197 | 0.4420 |
64
+ | 0.1194 | 14.0 | 2366 | 0.4382 |
65
+ | 0.1191 | 15.0 | 2535 | 0.4363 |
66
+ | 0.1183 | 16.0 | 2704 | 0.4350 |
67
+ | 0.1181 | 17.0 | 2873 | 0.4336 |
68
+ | 0.1168 | 18.0 | 3042 | 0.4298 |
69
+ | 0.1165 | 19.0 | 3211 | 0.4292 |
70
+ | 0.1158 | 20.0 | 3380 | 0.4277 |
71
+ | 0.1157 | 21.0 | 3549 | 0.4296 |
72
+ | 0.1144 | 22.0 | 3718 | 0.4256 |
73
+ | 0.113 | 23.0 | 3887 | 0.4253 |
74
+ | 0.1136 | 24.0 | 4056 | 0.4239 |
75
+ | 0.1143 | 25.0 | 4225 | 0.4227 |
76
+ | 0.1143 | 26.0 | 4394 | 0.4235 |
77
+ | 0.1126 | 27.0 | 4563 | 0.4232 |
 
 
78
 
79
 
80
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b001548559b2a3c510883940cee194b22165bc59b5e546a23a96880e30518744
3
  size 309974336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe15433e25d5d1a4330d286e7867a8fd46a167aab6e8090f78279ae921a633e0
3
  size 309974336
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 29.0,
3
  "eval_loss": 0.4475274682044983,
4
  "eval_runtime": 362.3481,
5
  "eval_samples_per_second": 157.114,
6
  "eval_steps_per_second": 4.912,
7
  "perplexity": 1.5644392736681412,
8
- "total_flos": 5.058807603414958e+17,
9
- "train_loss": 0.11824046083851339,
10
- "train_runtime": 25872.5126,
11
- "train_samples_per_second": 514.295,
12
- "train_steps_per_second": 16.073
13
  }
 
1
  {
2
+ "epoch": 27.0,
3
  "eval_loss": 0.4475274682044983,
4
  "eval_runtime": 362.3481,
5
  "eval_samples_per_second": 157.114,
6
  "eval_steps_per_second": 4.912,
7
  "perplexity": 1.5644392736681412,
8
+ "total_flos": 9564196506697728.0,
9
+ "train_loss": 0.13943315686140828,
10
+ "train_runtime": 711.1376,
11
+ "train_samples_per_second": 379.955,
12
+ "train_steps_per_second": 11.882
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 29.0,
3
- "total_flos": 5.058807603414958e+17,
4
- "train_loss": 0.11824046083851339,
5
- "train_runtime": 25872.5126,
6
- "train_samples_per_second": 514.295,
7
- "train_steps_per_second": 16.073
8
  }
 
1
  {
2
+ "epoch": 27.0,
3
+ "total_flos": 9564196506697728.0,
4
+ "train_loss": 0.13943315686140828,
5
+ "train_runtime": 711.1376,
6
+ "train_samples_per_second": 379.955,
7
+ "train_steps_per_second": 11.882
8
  }