End of training

README.md

@@ -1,11 +1,13 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: distilbert-base-cased
 tags:
 - generated_from_trainer
 metrics:
-- accuracy
+- precision
+- recall
 - f1
+- accuracy
 model-index:
 - name: trainer2
   results: []
@@ -16,11 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # trainer2
 
-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: 0.0234
-- Accuracy: 1.0
+- Loss: 0.0083
+- Precision: 1.0
+- Recall: 1.0
 - F1: 1.0
+- Accuracy: 1.0
 
 ## Model description
 
@@ -45,42 +49,25 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 30
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 2.0054        | 1.2   | 30   | 1.9498          | 0.1429   | 0.0381 |
-| 1.9675        | 2.4   | 60   | 1.9430          | 0.1429   | 0.0357 |
-| 1.8674        | 3.6   | 90   | 1.8505          | 0.2619   | 0.1697 |
-| 1.6168        | 4.8   | 120  | 1.5603          | 0.2857   | 0.1653 |
-| 1.4081        | 6.0   | 150  | 1.4562          | 0.4762   | 0.3593 |
-| 1.0441        | 7.2   | 180  | 1.0784          | 0.7143   | 0.6980 |
-| 0.647         | 8.4   | 210  | 0.7278          | 0.7857   | 0.7618 |
-| 0.4592        | 9.6   | 240  | 0.4725          | 0.9048   | 0.9018 |
-| 0.2154        | 10.8  | 270  | 0.3315          | 0.9048   | 0.9032 |
-| 0.1011        | 12.0  | 300  | 0.3818          | 0.8095   | 0.7946 |
-| 0.0543        | 13.2  | 330  | 0.1302          | 1.0      | 1.0    |
-| 0.0265        | 14.4  | 360  | 0.1574          | 0.9524   | 0.9536 |
-| 0.0154        | 15.6  | 390  | 0.0577          | 1.0      | 1.0    |
-| 0.0106        | 16.8  | 420  | 0.0895          | 0.9762   | 0.9760 |
-| 0.0073        | 18.0  | 450  | 0.0355          | 1.0      | 1.0    |
-| 0.0058        | 19.2  | 480  | 0.0256          | 1.0      | 1.0    |
-| 0.005         | 20.4  | 510  | 0.0259          | 1.0      | 1.0    |
-| 0.0041        | 21.6  | 540  | 0.0258          | 1.0      | 1.0    |
-| 0.0039        | 22.8  | 570  | 0.0260          | 1.0      | 1.0    |
-| 0.0039        | 24.0  | 600  | 0.0260          | 1.0      | 1.0    |
-| 0.0037        | 25.2  | 630  | 0.0253          | 1.0      | 1.0    |
-| 0.0034        | 26.4  | 660  | 0.0254          | 1.0      | 1.0    |
-| 0.0033        | 27.6  | 690  | 0.0258          | 1.0      | 1.0    |
-| 0.0034        | 28.8  | 720  | 0.0239          | 1.0      | 1.0    |
-| 0.0032        | 30.0  | 750  | 0.0234          | 1.0      | 1.0    |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| 0.2385        | 0.57  | 30   | 0.0803          | 1.0       | 1.0    | 1.0 | 1.0      |
+| 0.0738        | 1.13  | 60   | 0.0324          | 1.0       | 1.0    | 1.0 | 1.0      |
+| 0.0382        | 1.7   | 90   | 0.0195          | 1.0       | 1.0    | 1.0 | 1.0      |
+| 0.0263        | 2.26  | 120  | 0.0142          | 1.0       | 1.0    | 1.0 | 1.0      |
+| 0.0204        | 2.83  | 150  | 0.0115          | 1.0       | 1.0    | 1.0 | 1.0      |
+| 0.0172        | 3.4   | 180  | 0.0099          | 1.0       | 1.0    | 1.0 | 1.0      |
+| 0.0148        | 3.96  | 210  | 0.0090          | 1.0       | 1.0    | 1.0 | 1.0      |
+| 0.014         | 4.53  | 240  | 0.0085          | 1.0       | 1.0    | 1.0 | 1.0      |
 
 
 ### 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 sha256:5390cacf65ac2d3a5d92f57aece923d6fc3a1264776a5a2e288afd269cd05a37
-size 437968636
+oid sha256:eaf076e00c230d37737375d0832ca1f479a53f846b4cd7383bebb5c70d724136
+size 263160068

runs/Mar14_20-18-47_18c119a900f6/events.out.tfevents.1710447532.18c119a900f6.18759.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f865a42cc47b6d5679751c2497091afdc297cd5317d330b7b344e6b76dc36f
+size 10601

runs/Mar14_20-18-47_18c119a900f6/events.out.tfevents.1710449022.18c119a900f6.18759.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc3752aadac188bd26e7af2bfcaf83b9fb65dd3d5f9c55ea04c6ac9a6e9e330
+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:a3c0e526ec375f78412c93ec997e21c05241ce4686c1be9f21de2d516e1fc3e7
+oid sha256:6db5283265949e3cb0699ae54c4b628d0366514705edb3f0a43ffb098c2b3b85
 size 4856