DedeProGames commited on
Commit
e4f169d
·
verified ·
1 Parent(s): 56de2bc

Model save

Browse files
Files changed (1) hide show
  1. README.md +78 -0
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: EleutherAI/pythia-14m
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: mini-chennus
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # mini-chennus
17
+
18
+ This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.9861
21
+ - Accuracy: 0.0
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 1.4394 | 0.1616 | 200 | 1.4008 | 0.0 |
54
+ | 1.2966 | 0.3231 | 400 | 1.2502 | 0.0 |
55
+ | 1.2088 | 0.4847 | 600 | 1.1922 | 0.0 |
56
+ | 1.1689 | 0.6462 | 800 | 1.1538 | 0.0001 |
57
+ | 1.1303 | 0.8078 | 1000 | 1.1333 | 0.0 |
58
+ | 1.1094 | 0.9693 | 1200 | 1.1012 | 0.0 |
59
+ | 1.0967 | 1.1309 | 1400 | 1.0750 | 0.0 |
60
+ | 1.0621 | 1.2924 | 1600 | 1.0659 | 0.0 |
61
+ | 1.0647 | 1.4540 | 1800 | 1.0566 | 0.0 |
62
+ | 1.0388 | 1.6155 | 2000 | 1.0452 | 0.0 |
63
+ | 1.0465 | 1.7771 | 2200 | 1.0266 | 0.0 |
64
+ | 1.0274 | 1.9386 | 2400 | 1.0119 | 0.0 |
65
+ | 1.0125 | 2.1002 | 2600 | 1.0084 | 0.0 |
66
+ | 1.0023 | 2.2617 | 2800 | 1.0002 | 0.0 |
67
+ | 1.0001 | 2.4233 | 3000 | 0.9968 | 0.0 |
68
+ | 0.9954 | 2.5848 | 3200 | 0.9912 | 0.0 |
69
+ | 0.9865 | 2.7464 | 3400 | 0.9853 | 0.0 |
70
+ | 0.9913 | 2.9079 | 3600 | 0.9861 | 0.0 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.57.2
76
+ - Pytorch 2.9.0+cu126
77
+ - Datasets 4.0.0
78
+ - Tokenizers 0.22.1