Hugging Face's logo

mtzig
/
eo_train1-10_eval11

Transformers
Safetensors
nanogpt
Generated from Trainer
Model card Files
xet
Community
mtzig commited on
Commit
444df4c
·
verified ·
1 Parent(s): 9eb9ae8

Model save

Browse files
Files changed (4) hide show
  1. README.md +32 -32
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ 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: 0.6988
20
  - Accuracy: 0.5
21
 
22
  ## Model description
@@ -49,37 +49,37 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:----:|:---------------:|:--------:|
52
- | No log | 0 | 0 | 2.6204 | 0.5 |
53
- | 2.238 | 100.0 | 100 | 2.2317 | 0.5 |
54
- | 1.385 | 200.0 | 200 | 1.3755 | 0.5 |
55
- | 0.7896 | 300.0 | 300 | 0.7889 | 0.5 |
56
- | 0.7045 | 400.0 | 400 | 0.7206 | 0.5 |
57
- | 0.6393 | 500.0 | 500 | 0.7111 | 0.5 |
58
- | 0.5873 | 600.0 | 600 | 0.7019 | 0.5 |
59
- | 0.5542 | 700.0 | 700 | 0.7062 | 0.5 |
60
- | 0.534 | 800.0 | 800 | 0.7026 | 0.5 |
61
- | 0.5172 | 900.0 | 900 | 0.6992 | 0.5 |
62
- | 0.4871 | 1000.0 | 1000 | 0.7067 | 0.5 |
63
- | 0.4678 | 1100.0 | 1100 | 0.7070 | 0.5 |
64
- | 0.4786 | 1200.0 | 1200 | 0.7006 | 0.5 |
65
- | 0.4645 | 1300.0 | 1300 | 0.7031 | 0.5 |
66
- | 0.466 | 1400.0 | 1400 | 0.6975 | 0.5 |
67
- | 0.4574 | 1500.0 | 1500 | 0.7013 | 0.5 |
68
- | 0.4636 | 1600.0 | 1600 | 0.7017 | 0.5 |
69
- | 0.4612 | 1700.0 | 1700 | 0.7028 | 0.5 |
70
- | 0.4659 | 1800.0 | 1800 | 0.6999 | 0.5 |
71
- | 0.457 | 1900.0 | 1900 | 0.7002 | 0.5 |
72
- | 0.4562 | 2000.0 | 2000 | 0.7004 | 0.5 |
73
- | 0.4541 | 2100.0 | 2100 | 0.6999 | 0.5 |
74
- | 0.4535 | 2200.0 | 2200 | 0.6995 | 0.5 |
75
- | 0.4533 | 2300.0 | 2300 | 0.6995 | 0.5 |
76
- | 0.453 | 2400.0 | 2400 | 0.6991 | 0.5 |
77
- | 0.453 | 2500.0 | 2500 | 0.6990 | 0.5 |
78
- | 0.4528 | 2600.0 | 2600 | 0.6988 | 0.5 |
79
- | 0.4527 | 2700.0 | 2700 | 0.6988 | 0.5 |
80
- | 0.4527 | 2800.0 | 2800 | 0.6988 | 0.5 |
81
- | 0.4527 | 2900.0 | 2900 | 0.6988 | 0.5 |
82
- | 0.4527 | 3000.0 | 3000 | 0.6988 | 0.5 |
83
 
84
 
85
  ### 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: 0.6932
20
  - Accuracy: 0.5
21
 
22
  ## Model description
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:----:|:---------------:|:--------:|
52
+ | No log | 0 | 0 | 2.6863 | 0.0 |
53
+ | 0.6284 | 100.0 | 100 | 0.7859 | 0.5 |
54
+ | 0.548 | 200.0 | 200 | 0.7353 | 0.5 |
55
+ | 0.5022 | 300.0 | 300 | 0.6964 | 0.5 |
56
+ | 0.6935 | 400.0 | 400 | 0.6936 | 0.5 |
57
+ | 0.6933 | 500.0 | 500 | 0.6933 | 0.5 |
58
+ | 0.6932 | 600.0 | 600 | 0.6932 | 0.5 |
59
+ | 0.6932 | 700.0 | 700 | 0.6932 | 0.5 |
60
+ | 0.6932 | 800.0 | 800 | 0.6932 | 0.5 |
61
+ | 0.6932 | 900.0 | 900 | 0.6932 | 0.5 |
62
+ | 0.6932 | 1000.0 | 1000 | 0.6932 | 0.5 |
63
+ | 0.6932 | 1100.0 | 1100 | 0.6932 | 0.5 |
64
+ | 0.6932 | 1200.0 | 1200 | 0.6932 | 0.5 |
65
+ | 0.6932 | 1300.0 | 1300 | 0.6932 | 0.5 |
66
+ | 0.6932 | 1400.0 | 1400 | 0.6932 | 0.5 |
67
+ | 0.6932 | 1500.0 | 1500 | 0.6932 | 0.5 |
68
+ | 0.6932 | 1600.0 | 1600 | 0.6932 | 0.5 |
69
+ | 0.6932 | 1700.0 | 1700 | 0.6932 | 0.5 |
70
+ | 0.6932 | 1800.0 | 1800 | 0.6932 | 0.5 |
71
+ | 0.6932 | 1900.0 | 1900 | 0.6932 | 0.5 |
72
+ | 0.6932 | 2000.0 | 2000 | 0.6932 | 0.5 |
73
+ | 0.6932 | 2100.0 | 2100 | 0.6932 | 0.5 |
74
+ | 0.6932 | 2200.0 | 2200 | 0.6932 | 0.5 |
75
+ | 0.6932 | 2300.0 | 2300 | 0.6932 | 0.5 |
76
+ | 0.6932 | 2400.0 | 2400 | 0.6932 | 0.5 |
77
+ | 0.6932 | 2500.0 | 2500 | 0.6932 | 0.5 |
78
+ | 0.6932 | 2600.0 | 2600 | 0.6932 | 0.5 |
79
+ | 0.6932 | 2700.0 | 2700 | 0.6932 | 0.5 |
80
+ | 0.6932 | 2800.0 | 2800 | 0.6932 | 0.5 |
81
+ | 0.6932 | 2900.0 | 2900 | 0.6932 | 0.5 |
82
+ | 0.6932 | 3000.0 | 3000 | 0.6932 | 0.5 |
83
 
84
 
85
  ### Framework versions
config.json CHANGED
@@ -7,8 +7,8 @@
7
  "dropout": 0.0,
8
  "mlp_dim": 4,
9
  "model_type": "nanogpt",
10
- "n_embd": 10,
11
- "n_head": 1,
12
  "n_layer": 1,
13
  "nonlinearity": "RELU",
14
  "torch_dtype": "float32",
 
7
  "dropout": 0.0,
8
  "mlp_dim": 4,
9
  "model_type": "nanogpt",
10
+ "n_embd": 256,
11
+ "n_head": 2,
12
  "n_layer": 1,
13
  "nonlinearity": "RELU",
14
  "torch_dtype": "float32",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc9272f2f11d1bffa8cde1561732a72d1d06a66ffd12f9739d09498436dfefef
3
- size 7960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ac703f8010d0271acff2661a76318f2b066834608b847fc9891cb35d8ea303
3
+ size 3191304
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce76ded3b57604f010f1fe39515031358869e9644c0dc7bac82686ec8a363c76
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f62103a696cce8142414c8dfbb699763f3b575f93f668d3861669f360183c314
3
  size 5240