Hugging Face's logo

trungpq
/
rlcc-palate-upsample_replacement-absa-min

Transformers
Safetensors
bert_with_absa
Generated from Trainer
Model card Files
xet
Community
trungpq commited on
Commit
8e9b29c
·
verified ·
1 Parent(s): c57edb7

End of training

Browse files
Files changed (4) hide show
  1. README.md +17 -22
  2. config.json +1 -1
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.6411
20
- - Accuracy: 0.8244
21
- - F1 Macro: 0.5603
22
- - Precision Macro: 0.5611
23
- - Recall Macro: 0.5616
24
- - Total Tf: [338, 72, 1158, 72]
25
 
26
  ## Model description
27
 
@@ -46,30 +46,25 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_steps: 28
50
  - num_epochs: 25
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | Total Tf |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:-------------------:|
56
- | 1.1212 | 1.0 | 29 | 1.0654 | 0.8049 | 0.4364 | 0.4302 | 0.4492 | [330, 80, 1150, 80] |
57
- | 1.0783 | 2.0 | 58 | 1.1219 | 0.7610 | 0.4790 | 0.5533 | 0.5231 | [312, 98, 1132, 98] |
58
- | 0.9506 | 3.0 | 87 | 1.0906 | 0.7976 | 0.5571 | 0.5771 | 0.6078 | [327, 83, 1147, 83] |
59
- | 0.6871 | 4.0 | 116 | 1.1775 | 0.7707 | 0.5053 | 0.5378 | 0.5684 | [316, 94, 1136, 94] |
60
- | 0.5737 | 5.0 | 145 | 0.9718 | 0.8366 | 0.5432 | 0.5595 | 0.5405 | [343, 67, 1163, 67] |
61
- | 0.4436 | 6.0 | 174 | 1.0718 | 0.8244 | 0.5670 | 0.5657 | 0.5686 | [338, 72, 1158, 72] |
62
- | 0.3134 | 7.0 | 203 | 1.2147 | 0.8220 | 0.5789 | 0.5745 | 0.5869 | [337, 73, 1157, 73] |
63
- | 0.2358 | 8.0 | 232 | 1.3822 | 0.8146 | 0.5581 | 0.5588 | 0.5693 | [334, 76, 1154, 76] |
64
- | 0.1775 | 9.0 | 261 | 1.4343 | 0.8195 | 0.5541 | 0.5553 | 0.5530 | [336, 74, 1156, 74] |
65
- | 0.1638 | 10.0 | 290 | 1.5627 | 0.8317 | 0.5555 | 0.5603 | 0.5563 | [341, 69, 1161, 69] |
66
- | 0.1151 | 11.0 | 319 | 1.5977 | 0.8220 | 0.5704 | 0.5675 | 0.5749 | [337, 73, 1157, 73] |
67
- | 0.0761 | 12.0 | 348 | 1.6411 | 0.8244 | 0.5603 | 0.5611 | 0.5616 | [338, 72, 1158, 72] |
68
 
69
 
70
  ### Framework versions
71
 
72
- - Transformers 4.47.0
73
- - Pytorch 2.5.1+cu121
74
- - Datasets 3.2.0
75
  - Tokenizers 0.21.0
 
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.4198
20
+ - Accuracy: 0.7976
21
+ - F1 Macro: 0.5680
22
+ - Precision Macro: 0.6274
23
+ - Recall Macro: 0.6648
24
+ - Total Tf: [327, 83, 1147, 83]
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 36
50
  - num_epochs: 25
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | Total Tf |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:-------------------:|
56
+ | 1.1114 | 1.0 | 37 | 1.0849 | 0.8073 | 0.4646 | 0.4699 | 0.4711 | [331, 79, 1151, 79] |
57
+ | 1.0656 | 2.0 | 74 | 1.1060 | 0.8 | 0.4744 | 0.4575 | 0.5394 | [328, 82, 1148, 82] |
58
+ | 0.9251 | 3.0 | 111 | 1.0360 | 0.8024 | 0.5730 | 0.5780 | 0.5942 | [329, 81, 1149, 81] |
59
+ | 0.8019 | 4.0 | 148 | 1.1099 | 0.8341 | 0.5423 | 0.5462 | 0.5925 | [342, 68, 1162, 68] |
60
+ | 0.7155 | 5.0 | 185 | 1.2333 | 0.7976 | 0.5602 | 0.5848 | 0.6127 | [327, 83, 1147, 83] |
61
+ | 0.5969 | 6.0 | 222 | 1.2154 | 0.8341 | 0.5266 | 0.4951 | 0.5735 | [342, 68, 1162, 68] |
62
+ | 0.5489 | 7.0 | 259 | 1.3377 | 0.8 | 0.5650 | 0.5661 | 0.6076 | [328, 82, 1148, 82] |
63
+ | 0.584 | 8.0 | 296 | 1.4198 | 0.7976 | 0.5680 | 0.6274 | 0.6648 | [327, 83, 1147, 83] |
 
 
 
 
64
 
65
 
66
  ### Framework versions
67
 
68
+ - Transformers 4.48.3
69
+ - Pytorch 2.1.0+cu118
 
70
  - Tokenizers 0.21.0
config.json CHANGED
@@ -8,5 +8,5 @@
8
  "model_type": "bert_with_absa",
9
  "num_classes": 3,
10
  "torch_dtype": "float32",
11
- "transformers_version": "4.47.0"
12
  }
 
8
  "model_type": "bert_with_absa",
9
  "num_classes": 3,
10
  "torch_dtype": "float32",
11
+ "transformers_version": "4.48.3"
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f35e3f2f2d391bc85c9ee9beeba3cce1bdb6f1dd4bed4ea2d4ac0181cdfe726
3
- size 875933728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271816aabb5db8c96a33d7bfbff0a7291df1eb3fd1915bc2ad4b975f8e242e8d
3
+ size 875933980
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57e3e12f973c2ed9b45820811c12bb6d9ab48d83770009321f8d7d6a5ac72bba
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02f45392fc76cd63e81e89e3996cad5a297be6ee279bba95b09f65a720525f0
3
  size 5368