Hugging Face's logo

kanishka
/
smolm-autoreg-bpe-seed_1709

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
opt
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
kanishka commited on
Commit
d9f4fb1
•
1 Parent(s): f2363d3

Model save

Browse files
Files changed (4) hide show
  1. README.md +21 -22
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Mar25_21-58-56_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1711421956.phyl-ling-p01.la.utexas.edu.1059164.0 +2 -2
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- base_model: models/smolm-autoreg-bpe-seed_1709/config.json
3
  tags:
4
  - generated_from_trainer
5
  metrics:
@@ -14,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # smolm-autoreg-bpe-seed_1709
16
 
17
- This model is a fine-tuned version of [models/smolm-autoreg-bpe-seed_1709/config.json](https://huggingface.co/models/smolm-autoreg-bpe-seed_1709/config.json) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.5577
20
- - Accuracy: 0.4866
21
 
22
  ## Model description
23
 
@@ -37,8 +36,8 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.003
40
- - train_batch_size: 64
41
- - eval_batch_size: 512
42
  - seed: 1709
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
@@ -47,23 +46,23 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | 6.0628 | 1.0 | 732 | 3.5374 | 0.3935 |
53
- | 3.4842 | 2.0 | 1464 | 3.1207 | 0.4323 |
54
- | 2.936 | 3.0 | 2196 | 2.9167 | 0.4498 |
55
- | 2.8046 | 4.0 | 2928 | 2.7875 | 0.4619 |
56
- | 2.6126 | 5.0 | 3660 | 2.6935 | 0.4712 |
57
- | 2.5385 | 6.0 | 4392 | 2.6369 | 0.4776 |
58
- | 2.4478 | 7.0 | 5124 | 2.6066 | 0.4800 |
59
- | 2.4023 | 8.0 | 5856 | 2.5840 | 0.4829 |
60
- | 2.3613 | 9.0 | 6588 | 2.5709 | 0.4849 |
61
- | 2.3271 | 10.0 | 7320 | 2.5577 | 0.4866 |
62
 
63
 
64
  ### Framework versions
65
 
66
- - Transformers 4.32.1
67
- - Pytorch 2.0.1+cu117
68
- - Datasets 2.12.0
69
- - Tokenizers 0.13.3
 
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
 
13
 
14
  # smolm-autoreg-bpe-seed_1709
15
 
16
+ This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.4752
19
+ - Accuracy: 0.4999
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.003
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 128
41
  - seed: 1709
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
51
+ | 3.0397 | 1.0 | 2928 | 3.0117 | 0.4386 |
52
+ | 2.7146 | 2.0 | 5856 | 2.7775 | 0.4594 |
53
+ | 2.5805 | 3.0 | 8784 | 2.6824 | 0.4712 |
54
+ | 2.5051 | 4.0 | 11712 | 2.6318 | 0.4774 |
55
+ | 2.4548 | 5.0 | 14640 | 2.6045 | 0.4802 |
56
+ | 2.42 | 6.0 | 17568 | 2.5772 | 0.4842 |
57
+ | 2.3902 | 7.0 | 20496 | 2.5665 | 0.4853 |
58
+ | 2.357 | 8.0 | 23424 | 2.5599 | 0.4866 |
59
+ | 2.2797 | 9.0 | 26352 | 2.5077 | 0.4932 |
60
+ | 2.1365 | 10.0 | 29280 | 2.4752 | 0.4999 |
61
 
62
 
63
  ### Framework versions
64
 
65
+ - Transformers 4.38.2
66
+ - Pytorch 2.1.0+cu121
67
+ - Datasets 2.16.1
68
+ - Tokenizers 0.15.1
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.32.1"
7
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.38.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44b49433d915ec2114f1d00f934bb3a923045b8a7d8fd8a95cf737eadbdb2d5b
3
  size 33810896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e718102854f09658e752d15035a07babb6e9e71f5fa8a0f45bd5637e15028927
3
  size 33810896
runs/Mar25_21-58-56_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1711421956.phyl-ling-p01.la.utexas.edu.1059164.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:460388bc4dcab92e908bccd63788e32a430b443677e090546488718a5903ae15
3
- size 19620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:938cc011ae02096c011ac5cde38c21b80cea38810c7731323036dc426c6485c9
3
+ size 20739