Hugging Face's logo

rishavranaut
/
flanT5_large_Fact_U

Text Classification
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
rishavranaut commited on
Commit
1a3b3cb
•
1 Parent(s): 13cd2c6

End of training

Browse files
Files changed (5) hide show
  1. README.md +33 -33
  2. config.json +0 -1
  3. runs/Oct02_19-53-09_iit-p/events.out.tfevents.1727892081.iit-p +3 -0
  4. runs/Oct06_13-21-08_iit-p/events.out.tfevents.1728201150.iit-p +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.5959
24
  - Accuracy: 0.7812
 
25
  - Precision: 0.8048
26
  - Recall: 0.7647
27
- - F1 score: 0.7842
28
 
29
  ## Model description
30
 
@@ -151,37 +151,37 @@ The following hyperparameters were used during training:
151
  | 0.6239 | 2.9499 | 18800 | 0.7812 | 0.7801 | 0.8168 | 0.7466 | 1.0726 |
152
  | 0.6592 | 2.9813 | 19000 | 0.7788 | 0.7773 | 0.8159 | 0.7421 | 1.0731 |
153
  | 0.1354 | 3.0127 | 19200 | 0.7765 | 0.7791 | 0.8014 | 0.7579 | 1.3351 |
154
- | 0.3893 | 3.0755 | 19600 | 1.1745 | 0.7835 | 0.7879 | 0.7986 | 0.7933 |
155
- | 0.4753 | 3.1382 | 20000 | 1.2362 | 0.7882 | 0.8541 | 0.7149 | 0.7783 |
156
- | 0.3696 | 3.2010 | 20400 | 1.2638 | 0.7847 | 0.8166 | 0.7557 | 0.7850 |
157
- | 0.4476 | 3.2638 | 20800 | 1.3415 | 0.7706 | 0.8580 | 0.6697 | 0.7522 |
158
- | 0.4819 | 3.3265 | 21200 | 1.2743 | 0.7776 | 0.8235 | 0.7285 | 0.7731 |
159
- | 0.4361 | 3.3893 | 21600 | 1.1387 | 0.7765 | 0.8198 | 0.7308 | 0.7727 |
160
- | 0.3522 | 3.4521 | 22000 | 1.4823 | 0.7694 | 0.7808 | 0.7738 | 0.7773 |
161
- | 0.4655 | 3.5148 | 22400 | 1.4060 | 0.7529 | 0.7283 | 0.8371 | 0.7789 |
162
- | 0.438 | 3.5776 | 22800 | 1.2310 | 0.7659 | 0.8 | 0.7330 | 0.7651 |
163
- | 0.5766 | 3.6404 | 23200 | 1.2406 | 0.7776 | 0.7843 | 0.7896 | 0.7869 |
164
- | 0.5009 | 3.7031 | 23600 | 1.1521 | 0.7882 | 0.8005 | 0.7896 | 0.7950 |
165
- | 0.4282 | 3.7659 | 24000 | 1.2111 | 0.7765 | 0.7825 | 0.7896 | 0.7860 |
166
- | 0.3733 | 3.8287 | 24400 | 1.3162 | 0.7765 | 0.8043 | 0.7534 | 0.7780 |
167
- | 0.5248 | 3.8914 | 24800 | 1.2680 | 0.7788 | 0.8038 | 0.7602 | 0.7814 |
168
- | 0.4236 | 3.9542 | 25200 | 1.3282 | 0.7706 | 0.7775 | 0.7828 | 0.7802 |
169
- | 0.5013 | 4.0169 | 25600 | 1.2586 | 0.7753 | 0.7967 | 0.7624 | 0.7792 |
170
- | 0.2414 | 4.0797 | 26000 | 1.2782 | 0.7741 | 0.7976 | 0.7579 | 0.7773 |
171
- | 0.1564 | 4.1425 | 26400 | 1.4687 | 0.78 | 0.8133 | 0.7489 | 0.7797 |
172
- | 0.2116 | 4.2052 | 26800 | 1.3950 | 0.7694 | 0.7821 | 0.7715 | 0.7768 |
173
- | 0.288 | 4.2680 | 27200 | 1.3878 | 0.7753 | 0.8039 | 0.7511 | 0.7766 |
174
- | 0.1134 | 4.3308 | 27600 | 1.6678 | 0.7729 | 0.8074 | 0.7398 | 0.7721 |
175
- | 0.1839 | 4.3935 | 28000 | 1.6949 | 0.7729 | 0.8120 | 0.7330 | 0.7705 |
176
- | 0.1831 | 4.4563 | 28400 | 1.5547 | 0.78 | 0.8102 | 0.7534 | 0.7808 |
177
- | 0.2417 | 4.5191 | 28800 | 1.4637 | 0.7847 | 0.8246 | 0.7443 | 0.7824 |
178
- | 0.1922 | 4.5818 | 29200 | 1.5513 | 0.7824 | 0.8157 | 0.7511 | 0.7821 |
179
- | 0.252 | 4.6446 | 29600 | 1.5873 | 0.78 | 0.8102 | 0.7534 | 0.7808 |
180
- | 0.2172 | 4.7074 | 30000 | 1.5172 | 0.7882 | 0.8259 | 0.7511 | 0.7867 |
181
- | 0.1177 | 4.7701 | 30400 | 1.5945 | 0.7824 | 0.8024 | 0.7715 | 0.7866 |
182
- | 0.1921 | 4.8329 | 30800 | 1.6031 | 0.7812 | 0.8048 | 0.7647 | 0.7842 |
183
- | 0.1833 | 4.8957 | 31200 | 1.5854 | 0.7765 | 0.7903 | 0.7760 | 0.7831 |
184
- | 0.243 | 4.9584 | 31600 | 1.5959 | 0.7812 | 0.8048 | 0.7647 | 0.7842 |
185
 
186
 
187
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
22
  It achieves the following results on the evaluation set:
 
23
  - Accuracy: 0.7812
24
+ - F1 score: 0.7842
25
  - Precision: 0.8048
26
  - Recall: 0.7647
27
+ - Loss: 1.5959
28
 
29
  ## Model description
30
 
 
151
  | 0.6239 | 2.9499 | 18800 | 0.7812 | 0.7801 | 0.8168 | 0.7466 | 1.0726 |
152
  | 0.6592 | 2.9813 | 19000 | 0.7788 | 0.7773 | 0.8159 | 0.7421 | 1.0731 |
153
  | 0.1354 | 3.0127 | 19200 | 0.7765 | 0.7791 | 0.8014 | 0.7579 | 1.3351 |
154
+ | 0.3893 | 3.0755 | 19600 | 0.7835 | 0.7933 | 0.7879 | 0.7986 | 1.1745 |
155
+ | 0.4753 | 3.1382 | 20000 | 0.7882 | 0.7783 | 0.8541 | 0.7149 | 1.2362 |
156
+ | 0.3696 | 3.2010 | 20400 | 0.7847 | 0.7850 | 0.8166 | 0.7557 | 1.2638 |
157
+ | 0.4476 | 3.2638 | 20800 | 0.7706 | 0.7522 | 0.8580 | 0.6697 | 1.3415 |
158
+ | 0.4819 | 3.3265 | 21200 | 0.7776 | 0.7731 | 0.8235 | 0.7285 | 1.2743 |
159
+ | 0.4361 | 3.3893 | 21600 | 0.7765 | 0.7727 | 0.8198 | 0.7308 | 1.1387 |
160
+ | 0.3522 | 3.4521 | 22000 | 0.7694 | 0.7773 | 0.7808 | 0.7738 | 1.4823 |
161
+ | 0.4655 | 3.5148 | 22400 | 0.7529 | 0.7789 | 0.7283 | 0.8371 | 1.4060 |
162
+ | 0.438 | 3.5776 | 22800 | 0.7659 | 0.7651 | 0.8 | 0.7330 | 1.2310 |
163
+ | 0.5766 | 3.6404 | 23200 | 0.7776 | 0.7869 | 0.7843 | 0.7896 | 1.2406 |
164
+ | 0.5009 | 3.7031 | 23600 | 0.7882 | 0.7950 | 0.8005 | 0.7896 | 1.1521 |
165
+ | 0.4282 | 3.7659 | 24000 | 0.7765 | 0.7860 | 0.7825 | 0.7896 | 1.2111 |
166
+ | 0.3733 | 3.8287 | 24400 | 0.7765 | 0.7780 | 0.8043 | 0.7534 | 1.3162 |
167
+ | 0.5248 | 3.8914 | 24800 | 0.7788 | 0.7814 | 0.8038 | 0.7602 | 1.2680 |
168
+ | 0.4236 | 3.9542 | 25200 | 0.7706 | 0.7802 | 0.7775 | 0.7828 | 1.3282 |
169
+ | 0.5013 | 4.0169 | 25600 | 0.7753 | 0.7792 | 0.7967 | 0.7624 | 1.2586 |
170
+ | 0.2414 | 4.0797 | 26000 | 0.7741 | 0.7773 | 0.7976 | 0.7579 | 1.2782 |
171
+ | 0.1564 | 4.1425 | 26400 | 0.78 | 0.7797 | 0.8133 | 0.7489 | 1.4687 |
172
+ | 0.2116 | 4.2052 | 26800 | 0.7694 | 0.7768 | 0.7821 | 0.7715 | 1.3950 |
173
+ | 0.288 | 4.2680 | 27200 | 0.7753 | 0.7766 | 0.8039 | 0.7511 | 1.3878 |
174
+ | 0.1134 | 4.3308 | 27600 | 0.7729 | 0.7721 | 0.8074 | 0.7398 | 1.6678 |
175
+ | 0.1839 | 4.3935 | 28000 | 0.7729 | 0.7705 | 0.8120 | 0.7330 | 1.6949 |
176
+ | 0.1831 | 4.4563 | 28400 | 0.78 | 0.7808 | 0.8102 | 0.7534 | 1.5547 |
177
+ | 0.2417 | 4.5191 | 28800 | 0.7847 | 0.7824 | 0.8246 | 0.7443 | 1.4637 |
178
+ | 0.1922 | 4.5818 | 29200 | 0.7824 | 0.7821 | 0.8157 | 0.7511 | 1.5513 |
179
+ | 0.252 | 4.6446 | 29600 | 0.78 | 0.7808 | 0.8102 | 0.7534 | 1.5873 |
180
+ | 0.2172 | 4.7074 | 30000 | 0.7882 | 0.7867 | 0.8259 | 0.7511 | 1.5172 |
181
+ | 0.1177 | 4.7701 | 30400 | 0.7824 | 0.7866 | 0.8024 | 0.7715 | 1.5945 |
182
+ | 0.1921 | 4.8329 | 30800 | 0.7812 | 0.7842 | 0.8048 | 0.7647 | 1.6031 |
183
+ | 0.1833 | 4.8957 | 31200 | 0.7765 | 0.7831 | 0.7903 | 0.7760 | 1.5854 |
184
+ | 0.243 | 4.9584 | 31600 | 0.7812 | 0.7842 | 0.8048 | 0.7647 | 1.5959 |
185
 
186
 
187
  ### Framework versions
config.json CHANGED
@@ -31,7 +31,6 @@
31
  "num_layers": 24,
32
  "output_past": true,
33
  "pad_token_id": 0,
34
- "problem_type": "single_label_classification",
35
  "relative_attention_max_distance": 128,
36
  "relative_attention_num_buckets": 32,
37
  "tie_word_embeddings": false,
 
31
  "num_layers": 24,
32
  "output_past": true,
33
  "pad_token_id": 0,
 
34
  "relative_attention_max_distance": 128,
35
  "relative_attention_num_buckets": 32,
36
  "tie_word_embeddings": false,
runs/Oct02_19-53-09_iit-p/events.out.tfevents.1727892081.iit-p ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae4bfe60a4d6b627c1a3d2c7f727d251d2ff7f71aa462bf499179381b9910c5
3
+ size 527
runs/Oct06_13-21-08_iit-p/events.out.tfevents.1728201150.iit-p ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd8f0b51fb17d7db9b84f8eececc0a166a07eb57b95df8ca5def2d94948a8a2
3
+ size 5521
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2442c8093c8ad32fa32e1e0ade766d0492ba2802bc19029e53932378b361fe0b
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9697cb8449b222a8ea1c9449b013cf32d940dcba43c0624fc75b40cb7a141202
3
  size 5240