Training complete.

README.md

@@ -1,8 +1,11 @@
 ---
 license: mit
-base_model: racai/distilbert-base-romanian-cased
+base_model: dumitrescustefan/bert-base-romanian-cased-v1
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
 model-index:
 - name: sentiment-analysis-model
   results: []
@@ -13,9 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sentiment-analysis-model
 
-This model is a fine-tuned version of [racai/distilbert-base-romanian-cased](https://huggingface.co/racai/distilbert-base-romanian-cased) on an unknown dataset.
+This model is a fine-tuned version of [dumitrescustefan/bert-base-romanian-cased-v1](https://huggingface.co/dumitrescustefan/bert-base-romanian-cased-v1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2801
+- Loss: 0.2753
+- Accuracy: 0.8974
+- F1: 0.8976
 
 ## Model description
 
@@ -34,21 +39,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 113  | 0.2683          |
-| No log        | 2.0   | 226  | 0.3323          |
-| No log        | 3.0   | 339  | 0.2801          |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 57   | 0.3388          | 0.8656   | 0.8639 |
+| No log        | 2.0   | 114  | 0.2753          | 0.8974   | 0.8976 |
 
 
 ### Framework versions

config.json

@@ -1,26 +1,26 @@
 {
-  "_name_or_path": "racai/distilbert-base-romanian-cased",
-  "activation": "gelu",
+  "_name_or_path": "dumitrescustefan/bert-base-romanian-cased-v1",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_hidden_states": true,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": true,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.39.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 50000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a8d20b9c94d6be38d4d7a96482f72c61ac8b0e011a14cd5abcc3663a65a3cb
-size 327668984
+oid sha256:f784c4f129ba71afaf6f738d74c85041fb3d7fd9d72da9f1a082185da4211320
+size 497795072

runs/Apr01_22-16-46_Asus-ProArt-H7600ZX/events.out.tfevents.1712006206.Asus-ProArt-H7600ZX.40410.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:309a79080d95b70337f72ffd314475003fb385091d0570b5fb858a59556950f4
+size 4184

runs/Apr01_22-19-09_Asus-ProArt-H7600ZX/events.out.tfevents.1712006349.Asus-ProArt-H7600ZX.42172.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34422d4ef1a6135aae013516f77ad25fb4514ca8a8a9bc4009ecbf9e6f9b061a
+size 4562

runs/Apr01_22-19-50_Asus-ProArt-H7600ZX/events.out.tfevents.1712006391.Asus-ProArt-H7600ZX.42631.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1524492dc59e40a45474a0f626453eab3bd52e07d344b668df9970bdfee50f61
+size 4184

runs/Apr01_22-20-26_Asus-ProArt-H7600ZX/events.out.tfevents.1712006427.Asus-ProArt-H7600ZX.43108.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef0f76d792b2a2b47f7d096d5e728b908f90b1daa45bc303e8e8372ada4fd28
+size 5634

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -52,6 +52,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d159864a4ad95d0566b6272d55504dd224b5a1cc33da28a2556662f51c8a323
+oid sha256:48b162ff6413de2ca7f8c24e7c67771d9aef10261758bd3bf39070b67e0d14d0
 size 4920