End of training

README.md

@@ -0,0 +1,89 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- emotion
+metrics:
+- accuracy
+- f1
+model-index:
+- name: distilbert-finetuned
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: emotion
+      type: emotion
+      config: split
+      split: validation
+      args: split
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9385
+    - name: F1
+      type: f1
+      value: 0.9383538787245842
+---
+
+<!-- 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. -->
+
+# distilbert-finetuned
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1775
+- Accuracy: 0.9385
+- F1: 0.9384
+
+## 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: 2e-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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 250  | 0.2451          | 0.9225   | 0.9227 |
+| 0.4827        | 2.0   | 500  | 0.1655          | 0.934    | 0.9335 |
+| 0.4827        | 3.0   | 750  | 0.1558          | 0.9365   | 0.9372 |
+| 0.1191        | 4.0   | 1000 | 0.1482          | 0.9375   | 0.9374 |
+| 0.1191        | 5.0   | 1250 | 0.1599          | 0.9365   | 0.9366 |
+| 0.0775        | 6.0   | 1500 | 0.1539          | 0.9375   | 0.9378 |
+| 0.0775        | 7.0   | 1750 | 0.1657          | 0.937    | 0.9366 |
+| 0.0525        | 8.0   | 2000 | 0.1688          | 0.9385   | 0.9385 |
+| 0.0525        | 9.0   | 2250 | 0.1811          | 0.9405   | 0.9406 |
+| 0.0383        | 10.0  | 2500 | 0.1775          | 0.9385   | 0.9384 |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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": "4.41.1",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b5186a8479513bb594480f6ec5a9bf4069386307aeb085a174a38f4d404338
+size 267844872

runs/May24_00-34-37_nitro-v-15/events.out.tfevents.1716491500.nitro-v-15.13040.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05759c6983be150084687ec1112d01d194d3a003e4b2864920edaf8b1d814e8
+size 13999

runs/May24_00-34-37_nitro-v-15/events.out.tfevents.1716491827.nitro-v-15.13040.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3f652d64525b2b01685dff43974f77d5798d7428252618ccb7b6e18735f799
+size 4725

runs/May24_00-53-16_nitro-v-15/events.out.tfevents.1716492206.nitro-v-15.18248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc05e5fdecc1e45ad559d86ed69350663d48ed05f354434c75048d5ad98f5f15
+size 4971

runs/May24_11-23-13_nitro-v-15/events.out.tfevents.1716530018.nitro-v-15.8976.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ce1007a8599479bd59446400e80c55fa996dc5ab9d48f913f100362349f1a1
+size 19934

runs/May29_11-49-43_nitro-v-15/events.out.tfevents.1716963615.nitro-v-15.33168.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e47d8da8fb7a5ac7520c92247b8cb565b88242f6a337a319427556193bbadf
+size 4971

runs/May29_12-07-15_nitro-v-15/events.out.tfevents.1716964652.nitro-v-15.9684.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da71839a9fee4248efb6c032ef6ca55d3fc717d409472a5151ec6a656ce5846
+size 10070

runs/May29_13-29-01_nitro-v-15/events.out.tfevents.1716969627.nitro-v-15.15692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f358b3a39d9039108d5fc77007d8b618fd8d6a0795bc99d65d2e2bcf54b37b8
+size 10070

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": true,
+  "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:bd7275776ec3515d405eba1d53eb4c0726f5b07ff516978ae6270f69b9d5ff4f
+size 5112