Hugging Face's logo

tcapelle
/
toxicity-scorer-smollm2-360m-freeze

Text Classification
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
tcapelle commited on
Commit
c2a2a2e
·
verified ·
1 Parent(s): 3bd78f7

Model save

Browse files
Files changed (2) hide show
  1. README.md +17 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.2347
25
- - F1: 0.9013
26
- - Accuracy: 0.9033
27
- - Precision: 0.9006
28
- - Recall: 0.9033
29
 
30
  ## Model description
31
 
@@ -44,10 +44,14 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 0.0001
48
- - train_batch_size: 32
49
- - eval_batch_size: 32
50
  - seed: 42
 
 
 
 
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: cosine
53
  - lr_scheduler_warmup_ratio: 0.1
@@ -55,26 +59,15 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | Precision | Recall |
59
- |:-------------:|:------:|:-----:|:---------------:|:------:|:--------:|:---------:|:------:|
60
- | No log | 0 | 0 | 0.8130 | 0.5487 | 0.5049 | 0.6645 | 0.5049 |
61
- | 0.2957 | 0.2340 | 5000 | 0.2896 | 0.8803 | 0.8841 | 0.8795 | 0.8841 |
62
- | 0.2451 | 0.4680 | 10000 | 0.2443 | 0.8976 | 0.8995 | 0.8968 | 0.8995 |
63
- | 0.2349 | 0.7020 | 15000 | 0.2383 | 0.8994 | 0.9020 | 0.8989 | 0.9020 |
64
- | 0.2277 | 0.9360 | 20000 | 0.2363 | 0.9006 | 0.9027 | 0.8999 | 0.9027 |
65
- | 0.2414 | 1.1700 | 25000 | 0.2352 | 0.9013 | 0.9035 | 0.9007 | 0.9035 |
66
- | 0.2361 | 1.4040 | 30000 | 0.2349 | 0.9013 | 0.9035 | 0.9007 | 0.9035 |
67
- | 0.2312 | 1.6380 | 35000 | 0.2348 | 0.9013 | 0.9033 | 0.9007 | 0.9033 |
68
- | 0.2207 | 1.8720 | 40000 | 0.2348 | 0.9014 | 0.9035 | 0.9007 | 0.9035 |
69
- | 0.2645 | 2.1060 | 45000 | 0.2347 | 0.9012 | 0.9033 | 0.9005 | 0.9033 |
70
- | 0.2369 | 2.3399 | 50000 | 0.2347 | 0.9012 | 0.9033 | 0.9005 | 0.9033 |
71
- | 0.2329 | 2.5739 | 55000 | 0.2347 | 0.9013 | 0.9034 | 0.9006 | 0.9034 |
72
- | 0.2253 | 2.8079 | 60000 | 0.2347 | 0.9013 | 0.9033 | 0.9006 | 0.9033 |
73
 
74
 
75
  ### Framework versions
76
 
77
  - Transformers 4.46.3
78
- - Pytorch 2.5.1+cu124
79
  - Datasets 3.1.0
80
  - Tokenizers 0.20.3
 
21
 
22
  This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.7434
25
+ - F1: 0.6049
26
+ - Accuracy: 0.5261
27
+ - Precision: 0.7390
28
+ - Recall: 0.5261
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 1e-06
48
+ - train_batch_size: 44
49
+ - eval_batch_size: 44
50
  - seed: 42
51
+ - distributed_type: multi-GPU
52
+ - num_devices: 8
53
+ - total_train_batch_size: 352
54
+ - total_eval_batch_size: 352
55
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
56
  - lr_scheduler_type: cosine
57
  - lr_scheduler_warmup_ratio: 0.1
 
59
 
60
  ### Training results
61
 
62
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | Precision | Recall |
63
+ |:-------------:|:------:|:----:|:---------------:|:------:|:--------:|:---------:|:------:|
64
+ | No log | 0 | 0 | 0.7481 | 0.6025 | 0.5231 | 0.7383 | 0.5231 |
65
+ | 0.7489 | 1.5277 | 5000 | 0.7434 | 0.6049 | 0.5261 | 0.7390 | 0.5261 |
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
69
 
70
  - Transformers 4.46.3
71
+ - Pytorch 2.5.1
72
  - Datasets 3.1.0
73
  - Tokenizers 0.20.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36991ac561d8afab83ef4517308065fe29f56ffdee42ebcb69671dfed5a4f253
3
  size 723684600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c44bb9ae9194ed10a8af20d6e1b5e91758260ebd3b9a48917d712ab9cf1feba
3
  size 723684600