End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: distilbert-base-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # trainer7
 
-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-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0154
-- Precision: 0.9890
-- Recall: 0.9881
-- F1: 0.9881
-- Accuracy: 0.9881
+- Loss: 1.3387
+- Precision: 0.7247
+- Recall: 0.6905
+- F1: 0.6847
+- Accuracy: 0.6905
 
 ## Model description
 
@@ -43,35 +43,40 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 5e-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
-- num_epochs: 7
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 1.1015        | 0.57  | 30   | 1.1096          | 0.6052    | 0.6548 | 0.5979 | 0.6548   |
-| 0.9825        | 1.13  | 60   | 0.8476          | 0.7941    | 0.7381 | 0.7057 | 0.7381   |
-| 0.6428        | 1.7   | 90   | 0.5846          | 0.9313    | 0.9167 | 0.9152 | 0.9167   |
-| 0.3817        | 2.26  | 120  | 0.3105          | 0.9576    | 0.9524 | 0.9527 | 0.9524   |
-| 0.1681        | 2.83  | 150  | 0.0990          | 0.9890    | 0.9881 | 0.9881 | 0.9881   |
-| 0.077         | 3.4   | 180  | 0.0482          | 0.9890    | 0.9881 | 0.9881 | 0.9881   |
-| 0.0362        | 3.96  | 210  | 0.0204          | 1.0       | 1.0    | 1.0    | 1.0      |
-| 0.0221        | 4.53  | 240  | 0.0144          | 1.0       | 1.0    | 1.0    | 1.0      |
-| 0.0107        | 5.09  | 270  | 0.0115          | 1.0       | 1.0    | 1.0    | 1.0      |
-| 0.007         | 5.66  | 300  | 0.0142          | 0.9890    | 0.9881 | 0.9881 | 0.9881   |
-| 0.0188        | 6.23  | 330  | 0.0177          | 0.9890    | 0.9881 | 0.9881 | 0.9881   |
-| 0.0159        | 6.79  | 360  | 0.0147          | 0.9890    | 0.9881 | 0.9881 | 0.9881   |
+| 1.8743        | 0.57  | 30   | 1.7616          | 0.1668    | 0.2857 | 0.1788 | 0.2857   |
+| 1.7125        | 1.13  | 60   | 1.6249          | 0.2572    | 0.3810 | 0.2914 | 0.3810   |
+| 1.4398        | 1.7   | 90   | 1.3244          | 0.4911    | 0.4881 | 0.4326 | 0.4881   |
+| 1.0265        | 2.26  | 120  | 1.0496          | 0.6570    | 0.6429 | 0.6197 | 0.6429   |
+| 0.6366        | 2.83  | 150  | 0.9035          | 0.6304    | 0.5952 | 0.5764 | 0.5952   |
+| 0.3959        | 3.4   | 180  | 0.8226          | 0.6881    | 0.6667 | 0.6557 | 0.6667   |
+| 0.2172        | 3.96  | 210  | 1.0152          | 0.6932    | 0.6429 | 0.6356 | 0.6429   |
+| 0.0946        | 4.53  | 240  | 1.0485          | 0.7357    | 0.6786 | 0.6913 | 0.6786   |
+| 0.0416        | 5.09  | 270  | 1.1458          | 0.6983    | 0.6548 | 0.6565 | 0.6548   |
+| 0.0238        | 5.66  | 300  | 1.4215          | 0.6839    | 0.6310 | 0.6272 | 0.6310   |
+| 0.0132        | 6.23  | 330  | 1.2009          | 0.7481    | 0.7024 | 0.7090 | 0.7024   |
+| 0.0077        | 6.79  | 360  | 1.2686          | 0.6968    | 0.6548 | 0.6538 | 0.6548   |
+| 0.0064        | 7.36  | 390  | 1.2725          | 0.7128    | 0.6786 | 0.6717 | 0.6786   |
+| 0.0057        | 7.92  | 420  | 1.3092          | 0.7161    | 0.6786 | 0.6731 | 0.6786   |
+| 0.0053        | 8.49  | 450  | 1.3306          | 0.7065    | 0.6667 | 0.6640 | 0.6667   |
+| 0.0046        | 9.06  | 480  | 1.3377          | 0.7156    | 0.6786 | 0.6749 | 0.6786   |
+| 0.0044        | 9.62  | 510  | 1.3387          | 0.7247    | 0.6905 | 0.6847 | 0.6905   |
 
 
 ### Framework versions
 
 - Transformers 4.38.2
-- Pytorch 2.1.0+cu121
+- Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

config.json

@@ -1,17 +1,13 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-cased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
-  "attention_probs_dropout_prob": 0.1,
   "dim": 768,
   "dropout": 0.1,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
   "hidden_dim": 3072,
-  "hidden_dropout_prob": 0.1,
   "id2label": {
     "0": "anger",
     "1": "fear",
@@ -22,7 +18,6 @@
     "6": "surprise"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -32,20 +27,18 @@
     "LABEL_5": 5,
     "LABEL_6": 6
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,
-  "n_layers": 12,
+  "n_layers": 6,
+  "output_past": true,
   "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,
-  "vocab_size": 30522
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f670fc0f3b7d4e901c230f9352beed3f90c0028a74e58f50cbd3aea44b1b41c9
-size 437968636
+oid sha256:6a759aec30808f05c7003b4d5cfbff0ec601ab6eee6a8ba3975e8cd010f9e081
+size 263160068

runs/Mar15_15-58-13_f43bf2842da2/events.out.tfevents.1710518305.f43bf2842da2.238.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce58e17fc48cab258294861f65c362e12a7af813afe0f07f3e257981009120d
+size 16658

runs/Mar15_15-58-13_f43bf2842da2/events.out.tfevents.1710518694.f43bf2842da2.238.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a0eb73fce6dc0cc7a74b9f79fd839f5006cfb17ab61a05fcd7cdf22efce7f3
+size 560

tokenizer_config.json

@@ -44,7 +44,7 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "never_split": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8dd77712fcfd41d4e807a797e7348322b6017bd6defd6910d4aa5cfabb6be1
+oid sha256:6415c46dd6be9e0b256070d9c7f5cb0750df48b699ca64ca2e23396bd4818e38
 size 4856