bert-base-case-financial-news-twitter-sentiment

README.md

@@ -1,12 +1,9 @@
 ---
 library_name: transformers
-license: mit
-base_model: roberta-large
+license: apache-2.0
+base_model: bert-base-cased
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
-- f1
 model-index:
 - name: twitter_trainer
   results: []
@@ -17,13 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # twitter_trainer
 
-This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6659
-- Accuracy: 72.8
-- P: 94.8793
-- R: 109.0833
-- F1: 101.4867
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 
 ## Model description
 
@@ -51,17 +42,13 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 5
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | P       | R        | F1       |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:|:--------:|:--------:|
-| No log        | 1.0   | 63   | 0.9032          | 64.3     | 89.9301 | 138.4284 | 109.0292 |
-| No log        | 2.0   | 126  | 0.9033          | 64.3     | 89.9301 | 138.4284 | 109.0292 |
-| No log        | 3.0   | 189  | 0.7329          | 71.5     | 91.8044 | 118.0691 | 103.2933 |
-| No log        | 4.0   | 252  | 0.6866          | 72.5     | 95.0663 | 109.1293 | 101.6135 |
-| No log        | 4.928 | 310  | 0.6659          | 72.8     | 94.8793 | 109.0833 | 101.4867 |
+| No log        | 0.992 | 62   | 0.9867          | 66.5     | 90.1379 | 132.1537 | 107.1751 |
 
 
 ### Framework versions

config.json

@@ -1,15 +1,14 @@
 {
-  "_name_or_path": "roberta-large",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -18,7 +17,7 @@
     "4": "LABEL_4"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -26,17 +25,17 @@
     "LABEL_3": 3,
     "LABEL_4": 4
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 1,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc25227e6ed9fe79363dc88de349c0b44118587a9a2662839288e4774408872
-size 1421507716
+oid sha256:3da953ba079b14638c11b1aa95e4a1bba20744c7cc75dc13e2a09a8997c24d70
+size 433279996

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed71a0cf746d4ebd96eceb81361ed9b920afe1ae8eea8e2a79032bf2ce50aaf3
+oid sha256:44962e8da4e7626306f98cdf9639ba3704847d2af1070260ff650b9f6504ad1e
 size 5304