Hugging Face's logo

fpadovani
/
german_clm_childes_42

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files Community
fpadovani commited on
Commit
0bf994f
·
verified ·
1 Parent(s): 51fe2a2

Model save

Browse files
Files changed (3) hide show
  1. README.md +109 -0
  2. generation_config.json +6 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: childes_42
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # childes_42
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 4.3348
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.0001
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 16
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 2
41
+ - total_train_batch_size: 32
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 40000
45
+ - training_steps: 100000
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-------:|:------:|:---------------:|
52
+ | No log | 1.3276 | 2000 | 6.8111 |
53
+ | 6.7052 | 2.6552 | 4000 | 5.2489 |
54
+ | 6.7052 | 3.9827 | 6000 | 4.8334 |
55
+ | 4.6011 | 5.3103 | 8000 | 4.5945 |
56
+ | 4.6011 | 6.6379 | 10000 | 4.4471 |
57
+ | 4.1311 | 7.9655 | 12000 | 4.3496 |
58
+ | 4.1311 | 9.2931 | 14000 | 4.2791 |
59
+ | 3.8551 | 10.6206 | 16000 | 4.2176 |
60
+ | 3.8551 | 11.9482 | 18000 | 4.1808 |
61
+ | 3.6553 | 13.2758 | 20000 | 4.1480 |
62
+ | 3.6553 | 14.6034 | 22000 | 4.1244 |
63
+ | 3.4944 | 15.9310 | 24000 | 4.1036 |
64
+ | 3.4944 | 17.2585 | 26000 | 4.0837 |
65
+ | 3.3589 | 18.5861 | 28000 | 4.0664 |
66
+ | 3.3589 | 19.9137 | 30000 | 4.0494 |
67
+ | 3.2511 | 21.2413 | 32000 | 4.0538 |
68
+ | 3.2511 | 22.5689 | 34000 | 4.0513 |
69
+ | 3.1592 | 23.8964 | 36000 | 4.0287 |
70
+ | 3.1592 | 25.2240 | 38000 | 4.0395 |
71
+ | 3.0779 | 26.5516 | 40000 | 4.0467 |
72
+ | 3.0779 | 27.8792 | 42000 | 4.0412 |
73
+ | 3.0034 | 29.2068 | 44000 | 4.0514 |
74
+ | 3.0034 | 30.5344 | 46000 | 4.0581 |
75
+ | 2.9282 | 31.8619 | 48000 | 4.0613 |
76
+ | 2.9282 | 33.1895 | 50000 | 4.0739 |
77
+ | 2.8601 | 34.5171 | 52000 | 4.0870 |
78
+ | 2.8601 | 35.8447 | 54000 | 4.0898 |
79
+ | 2.8037 | 37.1723 | 56000 | 4.1204 |
80
+ | 2.8037 | 38.4998 | 58000 | 4.1324 |
81
+ | 2.751 | 39.8274 | 60000 | 4.1339 |
82
+ | 2.751 | 41.1550 | 62000 | 4.1532 |
83
+ | 2.7015 | 42.4826 | 64000 | 4.1742 |
84
+ | 2.7015 | 43.8102 | 66000 | 4.1717 |
85
+ | 2.6626 | 45.1377 | 68000 | 4.1888 |
86
+ | 2.6626 | 46.4653 | 70000 | 4.2004 |
87
+ | 2.6203 | 47.7929 | 72000 | 4.2134 |
88
+ | 2.6203 | 49.1205 | 74000 | 4.2247 |
89
+ | 2.585 | 50.4481 | 76000 | 4.2420 |
90
+ | 2.585 | 51.7756 | 78000 | 4.2502 |
91
+ | 2.5544 | 53.1032 | 80000 | 4.2732 |
92
+ | 2.5544 | 54.4308 | 82000 | 4.2792 |
93
+ | 2.5223 | 55.7584 | 84000 | 4.2878 |
94
+ | 2.5223 | 57.0860 | 86000 | 4.2994 |
95
+ | 2.496 | 58.4135 | 88000 | 4.3056 |
96
+ | 2.496 | 59.7411 | 90000 | 4.3080 |
97
+ | 2.4733 | 61.0687 | 92000 | 4.3204 |
98
+ | 2.4733 | 62.3963 | 94000 | 4.3243 |
99
+ | 2.4503 | 63.7239 | 96000 | 4.3270 |
100
+ | 2.4503 | 65.0514 | 98000 | 4.3339 |
101
+ | 2.4342 | 66.3790 | 100000 | 4.3348 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.45.2
107
+ - Pytorch 2.5.1+cu124
108
+ - Datasets 3.0.1
109
+ - Tokenizers 0.20.1
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "transformers_version": "4.45.2"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdc1093c3d26d52186b8ab698bace69116a613000867c85197e2787b5d5fde17
3
  size 51007160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd992d12f49ddc814383784312f40db18a08227d3eb4035e0d221b289680a03
3
  size 51007160