Askinkaty commited on
Commit
e9d4173
·
verified ·
1 Parent(s): 3e61686

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -35
README.md CHANGED
@@ -45,19 +45,14 @@ This model was trained within the context of a larger system for ABSA, which loo
45
  - **Sentence Transformer body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
46
  - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
47
  - **spaCy Model:** en_core_web_sm
48
- - **SetFitABSA Aspect Model:** [/scratch/project_2006600/fin_experiment/models/setfit-finance-aspect](https://huggingface.co//scratch/project_2006600/fin_experiment/models/setfit-finance-aspect)
49
- - **SetFitABSA Polarity Model:** [/scratch/project_2006600/fin_experiment/models/setfit-finance-polarity](https://huggingface.co//scratch/project_2006600/fin_experiment/models/setfit-finance-polarity)
50
  - **Maximum Sequence Length:** 384 tokens
51
  - **Number of Classes:** 3 classes
52
  <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
53
  <!-- - **Language:** Unknown -->
54
  <!-- - **License:** Unknown -->
55
 
56
- ### Model Sources
57
-
58
- - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
59
- - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
60
- - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
61
 
62
  ### Model Labels
63
  | Label | Examples |
@@ -83,11 +78,11 @@ from setfit import AbsaModel
83
 
84
  # Download from the 🤗 Hub
85
  model = AbsaModel.from_pretrained(
86
- "/scratch/project_2006600/fin_experiment/models/setfit-finance-aspect",
87
- "/scratch/project_2006600/fin_experiment/models/setfit-finance-polarity",
88
  )
89
  # Run inference
90
- preds = model("The food was great, but the venue is just way too busy.")
91
  ```
92
 
93
  <!--
@@ -128,11 +123,11 @@ preds = model("The food was great, but the venue is just way too busy.")
128
  | positive | 703 |
129
 
130
  ### Training Hyperparameters
131
- - batch_size: (64, 64)
132
- - num_epochs: (2, 2)
133
  - max_steps: -1
134
  - sampling_strategy: oversampling
135
- - body_learning_rate: (2e-05, 1e-05)
136
  - head_learning_rate: 0.01
137
  - loss: CosineSimilarityLoss
138
  - distance_metric: cosine_distance
@@ -145,28 +140,6 @@ preds = model("The food was great, but the venue is just way too busy.")
145
  - eval_max_steps: -1
146
  - load_best_model_at_end: True
147
 
148
- ### Training Results
149
- | Epoch | Step | Training Loss | Validation Loss |
150
- |:------:|:----:|:-------------:|:---------------:|
151
- | 0.0000 | 1 | 0.2969 | - |
152
- | 0.0025 | 50 | 0.3201 | - |
153
- | 0.0049 | 100 | 0.2933 | 0.2839 |
154
- | 0.0074 | 150 | 0.262 | - |
155
- | 0.0098 | 200 | 0.2523 | 0.2480 |
156
- | 0.0123 | 250 | 0.2403 | - |
157
- | 0.0147 | 300 | 0.2185 | 0.2199 |
158
- | 0.0172 | 350 | 0.1983 | - |
159
- | 0.0196 | 400 | 0.1874 | 0.2003 |
160
- | 0.0221 | 450 | 0.1727 | - |
161
- | 0.0245 | 500 | 0.1568 | 0.1882 |
162
- | 0.0270 | 550 | 0.1386 | - |
163
- | 0.0294 | 600 | 0.1181 | 0.1742 |
164
- | 0.0319 | 650 | 0.1023 | - |
165
- | 0.0343 | 700 | 0.0877 | 0.1766 |
166
- | 0.0368 | 750 | 0.0717 | - |
167
- | 0.0392 | 800 | 0.0555 | 0.1854 |
168
- | 0.0417 | 850 | 0.0447 | - |
169
- | 0.0441 | 900 | 0.0343 | 0.1841 |
170
 
171
  ### Framework Versions
172
  - Python: 3.11.11
 
45
  - **Sentence Transformer body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
46
  - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
47
  - **spaCy Model:** en_core_web_sm
48
+ - **SetFitABSA Aspect Model:** [/Askinkaty/setfit-finance-aspect](https://huggingface.co/Askinkaty/setfit-finance-aspect)
49
+ - **SetFitABSA Polarity Model:** [/Askinkaty/setfit-finance-polarity](https://huggingface.co/Askinkaty/setfit-finance-polarity)
50
  - **Maximum Sequence Length:** 384 tokens
51
  - **Number of Classes:** 3 classes
52
  <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
53
  <!-- - **Language:** Unknown -->
54
  <!-- - **License:** Unknown -->
55
 
 
 
 
 
 
56
 
57
  ### Model Labels
58
  | Label | Examples |
 
78
 
79
  # Download from the 🤗 Hub
80
  model = AbsaModel.from_pretrained(
81
+ "Askinkaty/setfit-finance-aspect",
82
+ "Askinkaty/setfit-finance-polarity",
83
  )
84
  # Run inference
85
+ preds = model("Banking stocks to see lot of traction: Mitesh Thacker.")
86
  ```
87
 
88
  <!--
 
123
  | positive | 703 |
124
 
125
  ### Training Hyperparameters
126
+ - batch_size: 64
127
+ - num_epochs: 2
128
  - max_steps: -1
129
  - sampling_strategy: oversampling
130
+ - body_learning_rate: 1e-05
131
  - head_learning_rate: 0.01
132
  - loss: CosineSimilarityLoss
133
  - distance_metric: cosine_distance
 
140
  - eval_max_steps: -1
141
  - load_best_model_at_end: True
142
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
143
 
144
  ### Framework Versions
145
  - Python: 3.11.11