Model save

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: badokorach/flan-t5-small-qa
+base_model: google/flan-t5-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # flan-t5-small-qa
 
-This model is a fine-tuned version of [badokorach/flan-t5-small-qa](https://huggingface.co/badokorach/flan-t5-small-qa) on an unknown dataset.
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0862
+- Loss: 0.0634
 
 ## Model description
 
@@ -34,42 +34,27 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 20
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 0.0486        | 1.0   | 609   | 0.0792          |
-| 0.0487        | 2.0   | 1218  | 0.0810          |
-| 0.0461        | 3.0   | 1827  | 0.0837          |
-| 0.0454        | 4.0   | 2436  | 0.0850          |
-| 0.045         | 5.0   | 3045  | 0.0834          |
-| 0.0442        | 6.0   | 3654  | 0.0852          |
-| 0.044         | 7.0   | 4263  | 0.0836          |
-| 0.0435        | 8.0   | 4872  | 0.0836          |
-| 0.0442        | 9.0   | 5481  | 0.0840          |
-| 0.0437        | 10.0  | 6090  | 0.0858          |
-| 0.0423        | 11.0  | 6699  | 0.0850          |
-| 0.0435        | 12.0  | 7308  | 0.0857          |
-| 0.0433        | 13.0  | 7917  | 0.0855          |
-| 0.0423        | 14.0  | 8526  | 0.0856          |
-| 0.0425        | 15.0  | 9135  | 0.0859          |
-| 0.0423        | 16.0  | 9744  | 0.0860          |
-| 0.0412        | 17.0  | 10353 | 0.0861          |
-| 0.0426        | 18.0  | 10962 | 0.0861          |
-| 0.0419        | 19.0  | 11571 | 0.0861          |
-| 0.0414        | 20.0  | 12180 | 0.0862          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 305  | 0.0540          |
+| 3.6654        | 2.0   | 610  | 0.0568          |
+| 3.6654        | 3.0   | 915  | 0.0618          |
+| 0.073         | 4.0   | 1220 | 0.0627          |
+| 0.0674        | 5.0   | 1525 | 0.0634          |
 
 
 ### Framework versions
 
-- Transformers 4.33.2
+- Transformers 4.33.3
 - Pytorch 2.0.1+cu118
 - Tokenizers 0.13.3

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.33.2"
+  "transformers_version": "4.33.3"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f957d96ebbe8a73e21feab0da99b9fe49a40d2dbe9f719c72d07d32141dee82
+oid sha256:82187a34ca31c95a368faf481fecb553efa03bbb25e626161615a624c33c5378
 size 990408885