Training in progress epoch 0

README.md

@@ -1,6 +1,5 @@
 ---
 license: mit
-base_model: almanach/camembert-base
 tags:
 - generated_from_keras_callback
 model-index:
@@ -15,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [almanach/camembert-base](https://huggingface.co/almanach/camembert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.1159
-- Validation Loss: 3.0460
+- Train Loss: 3.0945
+- Validation Loss: 3.0510
 - Train Accuracy: 0.2105
 - Epoch: 0
 
@@ -37,19 +36,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 55, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 55, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 3.1159     | 3.0460          | 0.2105         | 0     |
+| 3.0945     | 3.0510          | 0.2105         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.41.2
-- TensorFlow 2.15.0
+- Transformers 4.28.0
+- TensorFlow 2.11.0
 - Datasets 2.19.2
-- Tokenizers 0.19.1
+- Tokenizers 0.13.3

config.json

@@ -72,7 +72,7 @@
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.28.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 32005

special_tokens_map.json

@@ -1,8 +1,7 @@
 {
   "additional_special_tokens": [
     "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<unk>NOTUSED"
+    "</s>NOTUSED"
   ],
   "bos_token": "<s>",
   "cls_token": "<s>",

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d3487e1b694039d6c3e240c0640408c63842fc189ba201281ccdd3e4466198
+oid sha256:8f9ce6fa61cd981732c482b86ed78861d79e3bf82c5f7462f6a6cf4a9631ae69
 size 442851136

tokenizer.json

@@ -70,15 +70,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 32005,
-      "content": "<unk>NOTUSED",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {
@@ -94,8 +85,7 @@
       {
         "type": "Metaspace",
         "replacement": "▁",
-        "prepend_scheme": "always",
-        "split": true
+        "add_prefix_space": true
       }
     ]
   },
@@ -183,8 +173,7 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "prepend_scheme": "always",
-    "split": true
+    "add_prefix_space": true
   },
   "model": {
     "type": "Unigram",
@@ -128210,7 +128199,6 @@
         "<mask>",
         0.0
       ]
-    ],
-    "byte_fallback": false
+    ]
   }
 }

tokenizer_config.json

@@ -1,80 +1,20 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<s>NOTUSED",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>NOTUSED",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "<unk>NOTUSED",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
   "additional_special_tokens": [
     "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<unk>NOTUSED"
+    "</s>NOTUSED"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",