Training in progress, epoch 1

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: lxyuan/distilbert-base-multilingual-cased-sentiments-student
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: my_model_1000
+  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. -->
+
+# my_model_1000
+
+This model is a fine-tuned version of [lxyuan/distilbert-base-multilingual-cased-sentiments-student](https://huggingface.co/lxyuan/distilbert-base-multilingual-cased-sentiments-student) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3279
+- Accuracy: 0.9333
+
+## 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: 16
+- eval_batch_size: 16
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 30   | 0.4107          | 0.9333   |
+| No log        | 2.0   | 60   | 0.4412          | 0.9333   |
+| No log        | 3.0   | 90   | 0.5665          | 0.9      |
+| No log        | 4.0   | 120  | 0.3279          | 0.9333   |
+| No log        | 5.0   | 150  | 0.3522          | 0.95     |
+| No log        | 6.0   | 180  | 0.3607          | 0.95     |
+| No log        | 7.0   | 210  | 0.3536          | 0.95     |
+| No log        | 8.0   | 240  | 0.3521          | 0.95     |
+| No log        | 9.0   | 270  | 0.3519          | 0.95     |
+| No log        | 10.0  | 300  | 0.3518          | 0.95     |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "POSITIVO",
+    "1": "NEUTRAL",
+    "2": "NEGATIVO"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVO": 2,
+    "NEUTRAL": 1,
+    "POSITIVO": 0
+  },
+  "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": "4.44.2",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6689fe098c947bbc119a3220f9403780b05921d9ec9a7cc8ef4805a8577df93
+size 541320452

runs/Sep30_19-39-28_f400b371bc4a/events.out.tfevents.1727725169.f400b371bc4a.3675.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da8107dbe9d4c009f28dc8372c051165a93fc603dcd1d9f34dda07d9fb7b6a9
+size 8646

runs/Sep30_19-39-28_f400b371bc4a/events.out.tfevents.1727725314.f400b371bc4a.3675.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec59cb4041f78fc314f1afbc602ac48282ae7ae30e6ce84811ff76475349bd45
+size 411

runs/Sep30_20-11-43_f400b371bc4a/events.out.tfevents.1727727104.f400b371bc4a.3675.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5397c2d883a98feec42423c01cd50715b5c65cf0289c42701dfd053440cd9a43
+size 5403

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8660c78a4a0cee0449097437e9718e78d0f0cc57f43c43875d082443c72d56b
+size 5176