End of training

README.md

@@ -1,8 +1,8 @@
 ---
-license: apache-2.0
-base_model: t5-small
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: Translation_Grammer_Jan_2024
   results: []
@@ -13,16 +13,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Translation_Grammer_Jan_2024
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
+This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0269
-- eval_bleu: 19.9909
-- eval_gen_len: 18.2914
-- eval_runtime: 864.0001
-- eval_samples_per_second: 115.741
-- eval_steps_per_second: 3.617
-- epoch: 20.0
-- step: 250000
+- Loss: 0.0440
+- Bleu: 20.0
+- Gen Len: 18.2937
 
 ## Model description
 
@@ -42,16 +37,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 30
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Bleu | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:----:|:-------:|
+| 0.0618        | 1.0   | 12530 | 0.0440          | 20.0 | 18.2937 |
+
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
+- Transformers 4.36.2
+- Pytorch 2.1.1+cu118
 - Datasets 2.16.1
-- Tokenizers 0.15.1
+- Tokenizers 0.15.0

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.36.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c7a3655e2e34bc538d7ca5506d00eb5556e5419411cb460d90b8cc3cf76c74
+oid sha256:fbd5a2128e7aeed55890a1adea86e427487f0eb2ceb022f55cade0a0b09896e9
 size 242041896

runs/Jan31_00-14-06_sirius-1.lyon.grid5000.fr/events.out.tfevents.1706656447.sirius-1.lyon.grid5000.fr.10797.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79bbc1643d245c034f8d32e8359559da321fb42261ab6206e674665b6fb10cb5
-size 9421
+oid sha256:f8d03af83b2fbc4ca3490bafd96dc5d5a97bcd2ec812bd1c2c587c1a35fa9e9f
+size 10145