Hugging Face's logo

mtzig
/
lge_tests_prelim

Transformers
Safetensors
nanogpt
Generated from Trainer
Inference Endpoints
Model card Files Community
mtzig commited on
Commit
0994862
·
verified ·
1 Parent(s): 4ed95b0

Model save

Browse files
Files changed (4) hide show
  1. README.md +34 -34
  2. config.json +3 -3
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.8329
20
- - Accuracy: 0.0
21
 
22
  ## Model description
23
 
@@ -49,38 +49,38 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:----:|:---------------:|:--------:|
52
- | No log | 0 | 0 | 2.8542 | 0.0 |
53
- | 1.9753 | 0.0320 | 100 | 2.2451 | 0.0 |
54
- | 1.1255 | 0.0641 | 200 | 2.2519 | 0.0 |
55
- | 0.8756 | 0.0961 | 300 | 3.2185 | 0.0 |
56
- | 0.2727 | 0.1281 | 400 | 2.4786 | 0.0 |
57
- | 0.1232 | 0.1602 | 500 | 2.3917 | 0.0 |
58
- | 0.0938 | 0.1922 | 600 | 2.6180 | 0.0 |
59
- | 0.0172 | 0.2242 | 700 | 2.5046 | 0.0 |
60
- | 0.009 | 0.2562 | 800 | 3.0210 | 0.0 |
61
- | 0.0063 | 0.2883 | 900 | 4.7522 | 0.0 |
62
- | 0.007 | 0.3203 | 1000 | 2.7294 | 0.0 |
63
- | 0.1761 | 0.3523 | 1100 | 4.3269 | 0.0 |
64
- | 0.0049 | 0.3844 | 1200 | 3.0986 | 0.0 |
65
- | 0.0531 | 0.4164 | 1300 | 2.7182 | 0.0 |
66
- | 0.0001 | 0.4484 | 1400 | 2.3752 | 0.0 |
67
- | 0.0003 | 0.4805 | 1500 | 2.1509 | 0.0 |
68
- | 0.0 | 0.5125 | 1600 | 1.9732 | 0.0 |
69
- | 0.0 | 0.5445 | 1700 | 1.9455 | 0.0 |
70
- | 0.0001 | 0.5766 | 1800 | 2.5503 | 0.0 |
71
- | 0.0 | 0.6086 | 1900 | 3.0727 | 0.0 |
72
- | 0.0 | 0.6406 | 2000 | 2.9809 | 0.0 |
73
- | 0.0 | 0.6726 | 2100 | 2.9336 | 0.0 |
74
- | 0.0 | 0.7047 | 2200 | 2.9020 | 0.0 |
75
- | 0.0 | 0.7367 | 2300 | 2.8789 | 0.0 |
76
- | 0.0 | 0.7687 | 2400 | 2.8641 | 0.0 |
77
- | 0.0 | 0.8008 | 2500 | 2.8528 | 0.0 |
78
- | 0.0 | 0.8328 | 2600 | 2.8459 | 0.0 |
79
- | 0.0 | 0.8648 | 2700 | 2.8396 | 0.0 |
80
- | 0.0 | 0.8969 | 2800 | 2.8355 | 0.0 |
81
- | 0.0 | 0.9289 | 2900 | 2.8340 | 0.0 |
82
- | 0.0 | 0.9609 | 3000 | 2.8330 | 0.0 |
83
- | 0.0 | 0.9930 | 3100 | 2.8329 | 0.0 |
84
 
85
 
86
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.4324
20
+ - Accuracy: 0.64
21
 
22
  ## Model description
23
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:----:|:---------------:|:--------:|
52
+ | No log | 0 | 0 | 2.6277 | 0.0 |
53
+ | 2.487 | 0.0320 | 100 | 2.4830 | 0.0 |
54
+ | 2.3341 | 0.0641 | 200 | 2.3221 | 0.0 |
55
+ | 2.2138 | 0.0961 | 300 | 2.2363 | 0.0 |
56
+ | 2.0317 | 0.1281 | 400 | 2.0567 | 0.0 |
57
+ | 1.8181 | 0.1602 | 500 | 1.7764 | 0.005 |
58
+ | 1.5427 | 0.1922 | 600 | 1.5209 | 0.015 |
59
+ | 1.3683 | 0.2242 | 700 | 1.3421 | 0.015 |
60
+ | 1.1867 | 0.2562 | 800 | 1.1883 | 0.045 |
61
+ | 1.1158 | 0.2883 | 900 | 1.1456 | 0.035 |
62
+ | 1.1237 | 0.3203 | 1000 | 1.0221 | 0.04 |
63
+ | 0.9856 | 0.3523 | 1100 | 0.9365 | 0.14 |
64
+ | 0.8885 | 0.3844 | 1200 | 0.8694 | 0.16 |
65
+ | 0.8273 | 0.4164 | 1300 | 0.8421 | 0.115 |
66
+ | 0.8084 | 0.4484 | 1400 | 0.8112 | 0.14 |
67
+ | 0.7671 | 0.4805 | 1500 | 0.7577 | 0.145 |
68
+ | 0.6999 | 0.5125 | 1600 | 0.6785 | 0.33 |
69
+ | 0.6531 | 0.5445 | 1700 | 0.6651 | 0.325 |
70
+ | 0.6251 | 0.5766 | 1800 | 0.6239 | 0.365 |
71
+ | 0.5899 | 0.6086 | 1900 | 0.5955 | 0.375 |
72
+ | 0.5622 | 0.6406 | 2000 | 0.5660 | 0.42 |
73
+ | 0.5719 | 0.6726 | 2100 | 0.5642 | 0.365 |
74
+ | 0.5585 | 0.7047 | 2200 | 0.5228 | 0.495 |
75
+ | 0.514 | 0.7367 | 2300 | 0.4972 | 0.575 |
76
+ | 0.5052 | 0.7687 | 2400 | 0.4992 | 0.49 |
77
+ | 0.4651 | 0.8008 | 2500 | 0.4654 | 0.585 |
78
+ | 0.4473 | 0.8328 | 2600 | 0.4556 | 0.65 |
79
+ | 0.4548 | 0.8648 | 2700 | 0.4506 | 0.575 |
80
+ | 0.4576 | 0.8969 | 2800 | 0.4450 | 0.57 |
81
+ | 0.4343 | 0.9289 | 2900 | 0.4344 | 0.67 |
82
+ | 0.4262 | 0.9609 | 3000 | 0.4328 | 0.67 |
83
+ | 0.4298 | 0.9930 | 3100 | 0.4324 | 0.64 |
84
 
85
 
86
  ### Framework versions
config.json CHANGED
@@ -6,9 +6,9 @@
6
  "block_size": 256,
7
  "dropout": 0.0,
8
  "model_type": "nanogpt",
9
- "n_embd": 384,
10
- "n_head": 6,
11
- "n_layer": 6,
12
  "nonlinearity": "RELU",
13
  "torch_dtype": "float32",
14
  "transformers_version": "4.46.0",
 
6
  "block_size": 256,
7
  "dropout": 0.0,
8
  "model_type": "nanogpt",
9
+ "n_embd": 16,
10
+ "n_head": 1,
11
+ "n_layer": 2,
12
  "nonlinearity": "RELU",
13
  "torch_dtype": "float32",
14
  "transformers_version": "4.46.0",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e94dac8d663e1019ac212fa2ea49c278fd468125fa27410e4e9dd16aba6cac3
3
- size 42640744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:610bf6eac23addb819d196ef1300e6f84121a2610c7e871634f0419f4aed5bca
3
+ size 30712
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d3eb12253341fe6cf9e9b40fd8a4a25f8151ca5e9c58ae2d8abd37ac3060913
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c960fa37bea3e8290d8b693e02b79c2bd8cc974c2284e1434bc6742f516023
3
  size 5240