End of training

README.md

@@ -1,10 +1,8 @@
 ---
-license: apache-2.0
-base_model: google/flan-t5-base
 tags:
 - generated_from_trainer
 metrics:
-- rouge
+- bleu
 model-index:
 - name: morbius
   results: []
@@ -15,14 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # morbius
 
-This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Rouge1: 2.1823
-- Rouge2: 0.226
-- Rougel: 2.1188
-- Rougelsum: 2.1216
-- Gen Len: 8.9152
+- Loss: 2.3311
+- Bleu: 0.0490
+- Precisions: [0.12658339197748064, 0.058000714881448825, 0.031020853918560506, 0.0276665140764477]
+- Brevity Penalty: 0.9781
+- Length Ratio: 0.9783
+- Translation Length: 45472
+- Reference Length: 46479
 
 ## Model description
 
@@ -42,8 +41,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 12
+- eval_batch_size: 12
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -51,18 +50,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 0.0           | 1.0   | 7626  | nan             | 2.1823 | 0.226  | 2.1188 | 2.1216    | 8.9152  |
-| 0.0           | 2.0   | 15252 | nan             | 2.1823 | 0.226  | 2.1188 | 2.1216    | 8.9152  |
-| 0.0           | 3.0   | 22878 | nan             | 2.1823 | 0.226  | 2.1188 | 2.1216    | 8.9152  |
-| 0.0           | 4.0   | 30504 | nan             | 2.1823 | 0.226  | 2.1188 | 2.1216    | 8.9152  |
-| 0.0           | 5.0   | 38130 | nan             | 2.1823 | 0.226  | 2.1188 | 2.1216    | 8.9152  |
+| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Precisions                                                                             | Brevity Penalty | Length Ratio | Translation Length | Reference Length |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:--------------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|
+| 2.6085        | 1.0   | 2630  | 2.3793          | 0.0398 | [0.11484440108136675, 0.05086452177719413, 0.022402389588222743, 0.019262093750807972] | 1.0             | 1.0585       | 49197              | 46479            |
+| 2.5537        | 2.0   | 5260  | 2.3538          | 0.0451 | [0.12435074854873206, 0.053338059789672695, 0.02736549165120594, 0.024163621427155037] | 0.9858          | 0.9859       | 45822              | 46479            |
+| 2.427         | 3.0   | 7890  | 2.3412          | 0.0478 | [0.12566410537870473, 0.05610922151130985, 0.029971974257836827, 0.026891236083357122] | 0.9798          | 0.9800       | 45550              | 46479            |
+| 2.3716        | 4.0   | 10520 | 2.3347          | 0.0487 | [0.12663965838169275, 0.0574505431946487, 0.030477866031926728, 0.027230821761893922]  | 0.9823          | 0.9825       | 45665              | 46479            |
+| 2.3494        | 5.0   | 13150 | 2.3311          | 0.0490 | [0.12658339197748064, 0.058000714881448825, 0.031020853918560506, 0.0276665140764477]  | 0.9781          | 0.9783       | 45472              | 46479            |
 
 
 ### Framework versions
 
-- Transformers 4.33.3
+- Transformers 4.34.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.14.0

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.33.3"
+  "transformers_version": "4.34.0"
 }