End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: cc-by-nc-4.0
-base_model: facebook/nllb-200-distilled-600M
+base_model: SalomonMetre13/nllb_fra_shr_bidir
 tags:
 - generated_from_trainer
 model-index:
@@ -14,16 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # nllb_fra_shr_bidir
 
-This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset.
+This model is a fine-tuned version of [SalomonMetre13/nllb_fra_shr_bidir](https://huggingface.co/SalomonMetre13/nllb_fra_shr_bidir) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 6.9592
-- eval_bleu: 0.262
-- eval_gen_len: 59.5109
-- eval_runtime: 856.0303
-- eval_samples_per_second: 3.652
-- eval_steps_per_second: 0.229
-- epoch: 0.2843
-- step: 1000
+- eval_loss: 1.4691
+- eval_runtime: 48.8956
+- eval_samples_per_second: 63.932
+- eval_steps_per_second: 7.997
+- epoch: 0.8531
+- step: 6000
 
 ## Model description
 
@@ -43,12 +41,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aefbb292c9bb5b1d36ee2286e58a29c86838245c31a1eeef209ddef727da04cd
+oid sha256:c2547f3eea979a426727993487b8470bd936747d4e0c2ec7b2133c3a29f21c33
 size 1542007136