Hugging Face's logo

vinnyy
/
results

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
vinnyy commited on
Commit
8e2d74f
·
verified ·
1 Parent(s): a622328

vinnyy/codet5-finetuned-47epochs

Browse files
Files changed (7) hide show
  1. README.md +22 -27
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
  5. tokenizer.json +16 -2
  6. tokenizer_config.json +1 -0
  7. training_args.bin +2 -2
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 [vinnyy/results](https://huggingface.co/vinnyy/results) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4479
20
 
21
  ## Model description
22
 
@@ -39,41 +39,36 @@ The following hyperparameters were used during training:
39
  - train_batch_size: 2
40
  - eval_batch_size: 2
41
  - seed: 42
42
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 25
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | No log | 1.0 | 87 | 0.5600 |
51
- | 0.6043 | 2.0 | 174 | 0.5312 |
52
- | 0.5608 | 3.0 | 261 | 0.4930 |
53
- | 0.4626 | 4.0 | 348 | 0.4837 |
54
- | 0.4311 | 5.0 | 435 | 0.4736 |
55
- | 0.4456 | 6.0 | 522 | 0.4793 |
56
- | 0.391 | 7.0 | 609 | 0.4676 |
57
- | 0.391 | 8.0 | 696 | 0.4674 |
58
- | 0.383 | 9.0 | 783 | 0.4656 |
59
- | 0.3735 | 10.0 | 870 | 0.4637 |
60
- | 0.4062 | 11.0 | 957 | 0.4614 |
61
- | 0.3528 | 12.0 | 1044 | 0.4588 |
62
- | 0.3622 | 13.0 | 1131 | 0.4592 |
63
- | 0.3245 | 14.0 | 1218 | 0.4574 |
64
- | 0.3267 | 15.0 | 1305 | 0.4564 |
65
- | 0.3267 | 16.0 | 1392 | 0.4479 |
66
- | 0.3176 | 17.0 | 1479 | 0.4500 |
67
- | 0.3127 | 18.0 | 1566 | 0.4499 |
68
- | 0.3053 | 19.0 | 1653 | 0.4506 |
69
- | 0.2925 | 20.0 | 1740 | 0.4506 |
70
- | 0.3064 | 21.0 | 1827 | 0.4498 |
71
- | 0.2953 | 22.0 | 1914 | 0.4503 |
72
 
73
 
74
  ### Framework versions
75
 
76
- - Transformers 4.46.3
77
  - Pytorch 2.5.1+cu121
78
  - Datasets 3.2.0
79
- - Tokenizers 0.20.3
 
16
 
17
  This model is a fine-tuned version of [vinnyy/results](https://huggingface.co/vinnyy/results) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1629
20
 
21
  ## Model description
22
 
 
39
  - train_batch_size: 2
40
  - eval_batch_size: 2
41
  - seed: 42
42
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 20
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 1.0 | 88 | 0.3299 |
51
+ | 0.4815 | 2.0 | 176 | 0.3328 |
52
+ | 0.412 | 3.0 | 264 | 0.3244 |
53
+ | 0.3947 | 4.0 | 352 | 0.3275 |
54
+ | 0.3544 | 5.0 | 440 | 0.3254 |
55
+ | 0.3397 | 6.0 | 528 | 0.3244 |
56
+ | 0.3186 | 7.0 | 616 | 0.3239 |
57
+ | 0.308 | 8.0 | 704 | 0.3261 |
58
+ | 0.308 | 9.0 | 792 | 0.3262 |
59
+ | 0.3061 | 10.0 | 880 | 0.3257 |
60
+ | 0.316 | 11.0 | 968 | 0.1395 |
61
+ | 0.3127 | 12.0 | 1056 | 0.1427 |
62
+ | 0.3107 | 13.0 | 1144 | 0.1409 |
63
+ | 0.2919 | 14.0 | 1232 | 0.1438 |
64
+ | 0.2797 | 15.0 | 1320 | 0.1621 |
65
+ | 0.265 | 16.0 | 1408 | 0.1629 |
66
+ | 0.265 | 17.0 | 1496 | 0.1629 |
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
70
 
71
+ - Transformers 4.47.1
72
  - Pytorch 2.5.1+cu121
73
  - Datasets 3.2.0
74
+ - Tokenizers 0.21.0
config.json CHANGED
@@ -63,7 +63,7 @@
63
  }
64
  },
65
  "torch_dtype": "float32",
66
- "transformers_version": "4.46.3",
67
  "use_cache": true,
68
  "vocab_size": 32100
69
  }
 
63
  }
64
  },
65
  "torch_dtype": "float32",
66
+ "transformers_version": "4.47.1",
67
  "use_cache": true,
68
  "vocab_size": 32100
69
  }
generation_config.json CHANGED
@@ -4,5 +4,5 @@
4
  "decoder_start_token_id": 0,
5
  "eos_token_id": 2,
6
  "pad_token_id": 0,
7
- "transformers_version": "4.46.3"
8
  }
 
4
  "decoder_start_token_id": 0,
5
  "eos_token_id": 2,
6
  "pad_token_id": 0,
7
+ "transformers_version": "4.47.1"
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d4ac4c24da1d5a48e4fbca581dd5f4772ac1ae58f7a3a26c0fd39b30c0e1a34
3
  size 891558696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c129cc37a096af5c03830a4d0f9d54c57351a81d821edd08b298cbe6217a26
3
  size 891558696
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 512
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "<pad>"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,
tokenizer_config.json CHANGED
@@ -949,6 +949,7 @@
949
  "cls_token": "<s>",
950
  "eos_token": "</s>",
951
  "errors": "replace",
 
952
  "mask_token": "<mask>",
953
  "model_max_length": 512,
954
  "pad_token": "<pad>",
 
949
  "cls_token": "<s>",
950
  "eos_token": "</s>",
951
  "errors": "replace",
952
+ "extra_special_tokens": {},
953
  "mask_token": "<mask>",
954
  "model_max_length": 512,
955
  "pad_token": "<pad>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc5c8409fd8d48c62aa8892279f6ad90a5898c36e3701a6ec2d0c09028d28854
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb933b813e945678a4e78dfff9d8ca0f7ba7e3c03ad05568b855bb258edc970
3
+ size 5304