End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # trainer6
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5569
-- Precision: 0.5963
-- Recall: 0.5952
-- F1: 0.5950
-- Accuracy: 0.5952
+- Loss: 0.8990
+- Precision: 0.8531
+- Recall: 0.8519
+- F1: 0.8521
+- Accuracy: 0.8519
 
 ## Model description
 
@@ -43,21 +43,36 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 30
 
 ### Training results
 
+| Training Loss | Epoch   | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 1.0015        | 2.2222  | 100  | 0.5893          | 0.8219    | 0.8183 | 0.8179 | 0.8183   |
+| 0.1719        | 4.4444  | 200  | 0.6665          | 0.8264    | 0.8201 | 0.8209 | 0.8201   |
+| 0.0505        | 6.6667  | 300  | 0.7009          | 0.8474    | 0.8430 | 0.8439 | 0.8430   |
+| 0.0182        | 8.8889  | 400  | 0.7909          | 0.8481    | 0.8413 | 0.8425 | 0.8413   |
+| 0.0124        | 11.1111 | 500  | 0.8725          | 0.8401    | 0.8377 | 0.8377 | 0.8377   |
+| 0.0075        | 13.3333 | 600  | 0.8820          | 0.8469    | 0.8430 | 0.8426 | 0.8430   |
+| 0.0081        | 15.5556 | 700  | 0.8637          | 0.8396    | 0.8360 | 0.8362 | 0.8360   |
+| 0.0051        | 17.7778 | 800  | 0.8981          | 0.8471    | 0.8448 | 0.8447 | 0.8448   |
+| 0.0047        | 20.0    | 900  | 0.8829          | 0.8549    | 0.8536 | 0.8539 | 0.8536   |
+| 0.0027        | 22.2222 | 1000 | 0.8943          | 0.8522    | 0.8501 | 0.8504 | 0.8501   |
+| 0.0026        | 24.4444 | 1100 | 0.8910          | 0.8531    | 0.8519 | 0.8521 | 0.8519   |
+| 0.0027        | 26.6667 | 1200 | 0.8933          | 0.8532    | 0.8519 | 0.8520 | 0.8519   |
+| 0.0028        | 28.8889 | 1300 | 0.8990          | 0.8531    | 0.8519 | 0.8521 | 0.8519   |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.40.0
 - Pytorch 2.2.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "anger",
     "1": "fear",
@@ -19,7 +18,6 @@
     "6": "surprise"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -29,17 +27,17 @@
     "LABEL_5": 5,
     "LABEL_6": 6
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "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": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
+  "transformers_version": "4.40.0",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5581ff57a6a2951e9092a7453ceb9fbb0b6171e2588a789c7a90b4e271c7adcd
-size 437974028
+oid sha256:f2a372ee7f96d4b09a0986f8203d36bd942893a1490a4b43f6c11146317b9b95
+size 267847948

runs/Apr21_10-40-37_7c6a6620afc9/events.out.tfevents.1713696045.7c6a6620afc9.602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3325fd606e2c2de653bcee75a97432b1654f75ee9ab6236148e6a41acb5a1e2b
+size 5508

runs/Apr21_10-43-19_7c6a6620afc9/events.out.tfevents.1713696203.7c6a6620afc9.602.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc47f1fbd2b1f8c3bef1a5dc873fa19eb61a449be9455fc4bafe02e11311d4f
+size 14790

runs/Apr21_11-03-28_7c6a6620afc9/events.out.tfevents.1713697412.7c6a6620afc9.602.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ee4d97e8ff8f7d78c8d4ddf95b46f73fe1eaeec8309579441f4290fdf4d8fc
+size 14056

tokenizer_config.json

@@ -43,13 +43,15 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028d6e8ef0d9b78668ad615028f40eccfddc498a05435a4de230b299097e251b
-size 4920
+oid sha256:f1bd6ec0c8864e9602f2156c5092a9b0839dcbb1f8341753f228a5da77fdab42
+size 4984