End of training

README.md

@@ -1,26 +1,25 @@
 ---
 license: apache-2.0
-base_model: t5-small
+base_model: MubarakB/results
 tags:
 - generated_from_trainer
 metrics:
 - bleu
 model-index:
-- name: ft-t5-small-on-info-lg-formal
+- name: ft-t5-small-on-info-lg-informal-v1
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/Fine-tuning%20t5-small-on-info-lg-formal/runs/ygeghd7j)
-# ft-t5-small-on-info-lg-formal
+# ft-t5-small-on-info-lg-informal-v1
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the Luganda Formal Data dataset.
+This model is a fine-tuned version of [MubarakB/results](https://huggingface.co/MubarakB/results) on the Luganda informal Data dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1835
-- Bleu: 13.1429
-- Gen Len: 11.6875
+- Loss: 0.6113
+- Bleu: 0.3498
+- Gen Len: 15.5287
 
 ## Model description
 
@@ -45,32 +44,67 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 15
+- num_epochs: 50
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
-| 0.5262        | 1.0   | 848   | 0.2851          | 1.1666  | 13.2362 |
-| 0.2935        | 2.0   | 1696  | 0.2537          | 3.5129  | 12.5023 |
-| 0.2618        | 3.0   | 2544  | 0.2336          | 5.6103  | 12.3464 |
-| 0.2477        | 4.0   | 3392  | 0.2212          | 7.2168  | 12.0816 |
-| 0.2316        | 5.0   | 4240  | 0.2108          | 8.234   | 12.1068 |
-| 0.2194        | 6.0   | 5088  | 0.2037          | 9.5519  | 11.8898 |
-| 0.2125        | 7.0   | 5936  | 0.1987          | 10.4096 | 11.6576 |
-| 0.2032        | 8.0   | 6784  | 0.1943          | 10.9817 | 11.8235 |
-| 0.198         | 9.0   | 7632  | 0.1911          | 11.8996 | 11.7366 |
-| 0.1951        | 10.0  | 8480  | 0.1887          | 12.3731 | 11.6503 |
-| 0.1908        | 11.0  | 9328  | 0.1867          | 12.4566 | 11.712  |
-| 0.1866        | 12.0  | 10176 | 0.1851          | 13.0004 | 11.6821 |
-| 0.1846        | 13.0  | 11024 | 0.1841          | 13.2506 | 11.6264 |
-| 0.182         | 14.0  | 11872 | 0.1836          | 13.0856 | 11.6735 |
-| 0.1813        | 15.0  | 12720 | 0.1835          | 13.1429 | 11.6875 |
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| No log        | 1.0   | 177  | 0.5880          | 0.3892 | 14.6975 |
+| No log        | 2.0   | 354  | 0.5876          | 0.3855 | 14.4873 |
+| 0.5524        | 3.0   | 531  | 0.5870          | 0.5974 | 14.8217 |
+| 0.5524        | 4.0   | 708  | 0.5866          | 0.3335 | 14.6975 |
+| 0.5524        | 5.0   | 885  | 0.5867          | 0.3981 | 14.4013 |
+| 0.529         | 6.0   | 1062 | 0.5848          | 0.5378 | 14.4618 |
+| 0.529         | 7.0   | 1239 | 0.5863          | 0.3866 | 14.4618 |
+| 0.529         | 8.0   | 1416 | 0.5861          | 0.3623 | 14.8471 |
+| 0.5145        | 9.0   | 1593 | 0.5882          | 0.3559 | 15.0987 |
+| 0.5145        | 10.0  | 1770 | 0.5875          | 0.3372 | 14.9395 |
+| 0.5145        | 11.0  | 1947 | 0.5865          | 0.324  | 14.7516 |
+| 0.5013        | 12.0  | 2124 | 0.5877          | 0.3969 | 14.5159 |
+| 0.5013        | 13.0  | 2301 | 0.5875          | 0.4127 | 14.9299 |
+| 0.5013        | 14.0  | 2478 | 0.5884          | 0.3532 | 14.5732 |
+| 0.4907        | 15.0  | 2655 | 0.5890          | 0.3113 | 14.5478 |
+| 0.4907        | 16.0  | 2832 | 0.5885          | 0.3364 | 14.8917 |
+| 0.479         | 17.0  | 3009 | 0.5902          | 0.3211 | 14.5541 |
+| 0.479         | 18.0  | 3186 | 0.5915          | 0.3916 | 14.8917 |
+| 0.479         | 19.0  | 3363 | 0.5922          | 0.4469 | 15.1019 |
+| 0.47          | 20.0  | 3540 | 0.5932          | 0.3724 | 14.5414 |
+| 0.47          | 21.0  | 3717 | 0.5931          | 0.3376 | 15.3471 |
+| 0.47          | 22.0  | 3894 | 0.5939          | 0.3501 | 14.4936 |
+| 0.4546        | 23.0  | 4071 | 0.5964          | 0.4757 | 15.0287 |
+| 0.4546        | 24.0  | 4248 | 0.5969          | 0.4039 | 14.8217 |
+| 0.4546        | 25.0  | 4425 | 0.5976          | 0.4478 | 14.9777 |
+| 0.4483        | 26.0  | 4602 | 0.5998          | 0.4097 | 15.0573 |
+| 0.4483        | 27.0  | 4779 | 0.5997          | 0.4217 | 15.0223 |
+| 0.4483        | 28.0  | 4956 | 0.5998          | 0.4428 | 15.0032 |
+| 0.4396        | 29.0  | 5133 | 0.6014          | 0.4109 | 15.0032 |
+| 0.4396        | 30.0  | 5310 | 0.6033          | 0.4391 | 15.2611 |
+| 0.4396        | 31.0  | 5487 | 0.6024          | 0.4444 | 14.9459 |
+| 0.4359        | 32.0  | 5664 | 0.6030          | 0.4984 | 15.1401 |
+| 0.4359        | 33.0  | 5841 | 0.6055          | 0.4665 | 15.4045 |
+| 0.4261        | 34.0  | 6018 | 0.6056          | 0.4444 | 15.2994 |
+| 0.4261        | 35.0  | 6195 | 0.6064          | 0.4323 | 15.1497 |
+| 0.4261        | 36.0  | 6372 | 0.6065          | 0.458  | 15.172  |
+| 0.4222        | 37.0  | 6549 | 0.6077          | 0.4317 | 15.2134 |
+| 0.4222        | 38.0  | 6726 | 0.6080          | 0.3233 | 15.0764 |
+| 0.4222        | 39.0  | 6903 | 0.6084          | 0.3266 | 15.4299 |
+| 0.4158        | 40.0  | 7080 | 0.6081          | 0.3278 | 15.2197 |
+| 0.4158        | 41.0  | 7257 | 0.6097          | 0.333  | 15.2675 |
+| 0.4158        | 42.0  | 7434 | 0.6092          | 0.3557 | 15.3599 |
+| 0.4121        | 43.0  | 7611 | 0.6098          | 0.3214 | 15.3185 |
+| 0.4121        | 44.0  | 7788 | 0.6110          | 0.3224 | 15.3025 |
+| 0.4121        | 45.0  | 7965 | 0.6105          | 0.3159 | 15.2994 |
+| 0.4108        | 46.0  | 8142 | 0.6113          | 0.3109 | 15.3726 |
+| 0.4108        | 47.0  | 8319 | 0.6112          | 0.3205 | 15.4904 |
+| 0.4108        | 48.0  | 8496 | 0.6114          | 0.44   | 15.6433 |
+| 0.4105        | 49.0  | 8673 | 0.6113          | 0.4321 | 15.6242 |
+| 0.4105        | 50.0  | 8850 | 0.6113          | 0.3498 | 15.5287 |
 
 
 ### Framework versions
 
-- Transformers 4.42.3
-- Pytorch 2.1.2
-- Datasets 2.20.0
+- Transformers 4.44.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.21.0
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "MubarakB/results",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -55,7 +55,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.42.3",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.42.3"
+  "transformers_version": "4.44.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ac614141fc6cb260f8494f5b829d477afed1487002cdf35632adec974c8a2d
+oid sha256:69b193b0d61185f60ff6c5b6a01a2cb59e46ced4a0e34b56178cc177bbf3780d
 size 242041896

tokenizer_config.json

@@ -930,8 +930,15 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
+  "max_length": 128,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:952ea275baecca372ce298c1bcdbb8afbbd5ad787e37799a00eed7443d0ef7cb
+oid sha256:d8bf1e52a0538c1ed107fe15f7a641bbf53e57743b204022d2998b9b05957516
 size 5240