Iiro/bert_reviews

README.md

@@ -1,27 +1,11 @@
 ---
-license: apache-2.0
 tags:
 - generated_from_trainer
 datasets:
 - amazon_reviews_multi
-metrics:
-- accuracy
 model-index:
 - name: bert_reviews
-  results:
-  - task:
-      name: Text Classification
-      type: text-classification
-    dataset:
-      name: amazon_reviews_multi
-      type: amazon_reviews_multi
-      config: en
-      split: test
-      args: en
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.6408
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_reviews
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the amazon_reviews_multi dataset.
+This model was trained from scratch on the amazon_reviews_multi dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8312
-- Accuracy: 0.6408
+- eval_loss: 0.9163
+- eval_accuracy: 0.622
+- eval_runtime: 40.4603
+- eval_samples_per_second: 123.578
+- eval_steps_per_second: 15.447
+- epoch: 0.04
+- step: 1000
 
 ## Model description
 
@@ -51,63 +40,17 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 1.2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - training_steps: 20000
 
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 1.1326        | 0.04  | 500   | 1.0019          | 0.5832   |
-| 0.9786        | 0.08  | 1000  | 0.9387          | 0.6086   |
-| 0.9481        | 0.12  | 1500  | 0.9117          | 0.6132   |
-| 0.9334        | 0.16  | 2000  | 0.9440          | 0.5744   |
-| 0.9036        | 0.2   | 2500  | 0.9085          | 0.6034   |
-| 0.9065        | 0.24  | 3000  | 0.9250          | 0.5982   |
-| 0.8821        | 0.28  | 3500  | 0.8917          | 0.6232   |
-| 0.9047        | 0.32  | 4000  | 0.8850          | 0.6258   |
-| 0.8838        | 0.36  | 4500  | 0.8814          | 0.6236   |
-| 0.8732        | 0.4   | 5000  | 0.8874          | 0.6198   |
-| 0.8845        | 0.44  | 5500  | 0.8886          | 0.6164   |
-| 0.874         | 0.48  | 6000  | 0.8665          | 0.634    |
-| 0.8693        | 0.52  | 6500  | 0.8985          | 0.6126   |
-| 0.8502        | 0.56  | 7000  | 0.8992          | 0.6248   |
-| 0.8752        | 0.6   | 7500  | 0.8620          | 0.6326   |
-| 0.8477        | 0.64  | 8000  | 0.8586          | 0.6382   |
-| 0.8456        | 0.68  | 8500  | 0.8603          | 0.631    |
-| 0.861         | 0.72  | 9000  | 0.8536          | 0.628    |
-| 0.8605        | 0.76  | 9500  | 0.8478          | 0.6338   |
-| 0.8159        | 0.8   | 10000 | 0.8569          | 0.6324   |
-| 0.8397        | 0.84  | 10500 | 0.8519          | 0.626    |
-| 0.8424        | 0.88  | 11000 | 0.8753          | 0.6302   |
-| 0.8332        | 0.92  | 11500 | 0.8453          | 0.6326   |
-| 0.8286        | 0.96  | 12000 | 0.8334          | 0.6414   |
-| 0.8166        | 1.0   | 12500 | 0.8508          | 0.633    |
-| 0.7656        | 1.04  | 13000 | 0.8393          | 0.646    |
-| 0.749         | 1.08  | 13500 | 0.8339          | 0.643    |
-| 0.7554        | 1.12  | 14000 | 0.8325          | 0.6486   |
-| 0.734         | 1.16  | 14500 | 0.8467          | 0.6524   |
-| 0.7581        | 1.2   | 15000 | 0.8228          | 0.6434   |
-| 0.7413        | 1.24  | 15500 | 0.8339          | 0.6446   |
-| 0.7429        | 1.28  | 16000 | 0.8331          | 0.6448   |
-| 0.7436        | 1.32  | 16500 | 0.8285          | 0.6472   |
-| 0.7343        | 1.36  | 17000 | 0.8381          | 0.6532   |
-| 0.7225        | 1.4   | 17500 | 0.8327          | 0.6476   |
-| 0.7311        | 1.44  | 18000 | 0.8281          | 0.6506   |
-| 0.7298        | 1.48  | 18500 | 0.8324          | 0.6468   |
-| 0.7409        | 1.52  | 19000 | 0.8180          | 0.648    |
-| 0.732         | 1.56  | 19500 | 0.8209          | 0.6464   |
-| 0.7352        | 1.6   | 20000 | 0.8195          | 0.6468   |
-
-
 ### Framework versions
 
-- Transformers 4.28.1
-- Pytorch 2.0.0+cu118
-- Datasets 2.11.0
-- Tokenizers 0.13.3
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -1,13 +1,9 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "Bert"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "hidden_bert": 768,
+  "hidden_size": 50,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -15,7 +11,6 @@
     "3": "LABEL_3",
     "4": "LABEL_4"
   },
-  "initializer_range": 0.02,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -23,17 +18,6 @@
     "LABEL_3": 3,
     "LABEL_4": 4
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
-  "vocab_size": 30522
+  "transformers_version": "4.34.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3f7957c028e5a0e259ef9e717f10ed1768ef64b574c4d3583b43775558ebb8
-size 267864749
+oid sha256:cc9b7adfcf1b7423c3f58feb4fe3fb41bf427fc20a537453a536f99bfce7b39b
+size 433465270

tokenizer_config.json

@@ -1,13 +1,55 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "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 sha256:74bad4d69ffc58615dab2bdadb1a39e5447b3514ce6da70b99101db4db76d29b
-size 3579
+oid sha256:8aed5972a1a70530610473db50619f0469b4eaa95f2008e246fb192c9061beb0
+size 4472