End of training

README.md

@@ -0,0 +1,61 @@
+---
+license: mit
+base_model: microsoft/MiniLM-L12-H384-uncased
+tags:
+- generated_from_trainer
+datasets:
+- emotion
+model-index:
+- name: emotion-guesser2
+ 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. -->
+
+# emotion-guesser2
+
+This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the emotion dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2428
+
+## 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: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log | 1.0 | 125 | 1.5836 |
+| No log | 2.0 | 250 | 1.3238 |
+| No log | 3.0 | 375 | 1.2428 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.4.0.dev20240317
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,42 @@
+{
+ "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
+ "architectures": [
+ "BertForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 384,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1",
+ "2": "LABEL_2",
+ "3": "LABEL_3",
+ "4": "LABEL_4",
+ "5": "LABEL_5"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 1536,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1,
+ "LABEL_2": 2,
+ "LABEL_3": 3,
+ "LABEL_4": 4,
+ "LABEL_5": 5
+ },
+ "layer_norm_eps": 1e-12,
+ "max_position_embeddings": 512,
+ "model_type": "bert",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "pad_token_id": 0,
+ "position_embedding_type": "absolute",
+ "problem_type": "single_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.38.2",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f266e592b1b66a8ead2cf7dd8905a702eddc594a2c3ff55bff0dae0746e1e61
+size 133472536

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8805d44f22f9b1c7f2b1c1884679ba725c42f0fe39f8cfa91b87ce2ede499937
+size 4920