Training in progress epoch 0

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-fr
 tags:
 - generated_from_keras_callback
 model-index:
@@ -14,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6846
-- Validation Loss: 0.8045
-- Epoch: 2
+- Train Loss: 1.0609
+- Validation Loss: 0.8949
+- Epoch: 0
 
 ## Model description
 
@@ -35,21 +36,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 17733, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 5911, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 1.0619     | 0.8784          | 0     |
-| 0.7974     | 0.8210          | 1     |
-| 0.6846     | 0.8045          | 2     |
+| 1.0609     | 0.8949          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.30.2
+- Transformers 4.31.0
 - TensorFlow 2.12.0
 - Datasets 2.13.1
 - Tokenizers 0.13.3

config.json

@@ -55,7 +55,7 @@
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 59514
 }

generation_config.json

@@ -12,5 +12,5 @@
   "max_length": 512,
   "num_beams": 4,
   "pad_token_id": 59513,
-  "transformers_version": "4.30.2"
+  "transformers_version": "4.31.0"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d2cabff4de30ffd6fcec98b7f6ea5789d87bd93a44f05bc157253b5e574b19
+oid sha256:f94ed5911ca935087546922886222b40b8ea63703b1cc21a35624394afc02207
 size 301061272