End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: distilbert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: trainer_4f
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# trainer_4f
+
+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: 0.7939
+- Precision: 0.8636
+- Recall: 0.8607
+- F1: 0.8608
+- Accuracy: 0.8607
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 1.5222        | 0.28  | 100  | 1.0684          | 0.7086    | 0.6526 | 0.6336 | 0.6526   |
+| 0.8107        | 0.56  | 200  | 0.7004          | 0.8212    | 0.8060 | 0.8026 | 0.8060   |
+| 0.6093        | 0.84  | 300  | 0.5823          | 0.8297    | 0.8254 | 0.8257 | 0.8254   |
+| 0.4046        | 1.12  | 400  | 0.6403          | 0.8250    | 0.8166 | 0.8171 | 0.8166   |
+| 0.3709        | 1.4   | 500  | 0.6518          | 0.8333    | 0.8289 | 0.8288 | 0.8289   |
+| 0.3679        | 1.69  | 600  | 0.6604          | 0.8456    | 0.8395 | 0.8405 | 0.8395   |
+| 0.2618        | 1.97  | 700  | 0.6579          | 0.8555    | 0.8536 | 0.8539 | 0.8536   |
+| 0.1754        | 2.25  | 800  | 0.7240          | 0.8587    | 0.8536 | 0.8542 | 0.8536   |
+| 0.1913        | 2.53  | 900  | 0.7884          | 0.8393    | 0.8360 | 0.8368 | 0.8360   |
+| 0.1894        | 2.81  | 1000 | 0.7356          | 0.8684    | 0.8660 | 0.8657 | 0.8660   |
+| 0.1474        | 3.09  | 1100 | 0.7551          | 0.8529    | 0.8519 | 0.8513 | 0.8519   |
+| 0.0741        | 3.37  | 1200 | 0.7738          | 0.8618    | 0.8554 | 0.8562 | 0.8554   |
+| 0.0894        | 3.65  | 1300 | 0.7591          | 0.8648    | 0.8607 | 0.8606 | 0.8607   |
+| 0.046         | 3.93  | 1400 | 0.7922          | 0.8601    | 0.8554 | 0.8554 | 0.8554   |
+| 0.0379        | 4.21  | 1500 | 0.7806          | 0.8695    | 0.8660 | 0.8662 | 0.8660   |
+| 0.0354        | 4.49  | 1600 | 0.7838          | 0.8760    | 0.8730 | 0.8731 | 0.8730   |
+| 0.0198        | 4.78  | 1700 | 0.7936          | 0.8650    | 0.8607 | 0.8611 | 0.8607   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "anger",
+    "1": "fear",
+    "2": "joy",
+    "3": "love",
+    "4": "neutral",
+    "5": "sadness",
+    "6": "surprise"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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": "4.39.3",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4da5f5ba30dc541ca883e21298a269f021f07c4a208056d688132d14b4f9c62
+size 263160068

runs/Apr07_15-47-57_b6630175ab9e/events.out.tfevents.1712504879.b6630175ab9e.818.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eabf1378ab2f408be88879fffd3e4356c361520c7407d2f3d56d4e4a07bee14a
+size 4782

runs/Apr07_15-49-59_b6630175ab9e/events.out.tfevents.1712505004.b6630175ab9e.818.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f8e68997c8a0a475f8f4bf045fb3e42623da98b075672c07957480e628672eb
+size 4782

runs/Apr07_15-51-14_b6630175ab9e/events.out.tfevents.1712505078.b6630175ab9e.818.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32362a79fa40cf959161a36f54acfbabb5fe07ad2e4f82549b29c333d23dbfe
+size 4833

runs/Apr07_15-52-17_b6630175ab9e/events.out.tfevents.1712505141.b6630175ab9e.818.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f29e1b60805252d25f9321515cd5ab3767ef132353c536e75332a57f172540e
+size 16785

runs/Apr07_15-52-17_b6630175ab9e/events.out.tfevents.1712517477.b6630175ab9e.818.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4c7b12d25c34f5d663120a8151d0849193dfc7e9eb045d90dac4f71bc1ce39
+size 560

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e057c7ca275fc3aad2ec4effa098c08cbaf25c2857fac9ae667246544f7935dc
+size 4920