Training complete

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: mit
+base_model: jhu-clsp/mmBERT-base
+tags:
+- classification
+- generated_from_trainer
+model-index:
+- name: finetuned_model_emotion_detection
+  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. -->
+
+# finetuned_model_emotion_detection
+
+This model is a fine-tuned version of [jhu-clsp/mmBERT-base](https://huggingface.co/jhu-clsp/mmBERT-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3275
+- F1 Macro: 0.5078
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1 Macro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 223  | 0.2786          | 0.3914   |
+| No log        | 2.0   | 446  | 0.2703          | 0.4524   |
+| 0.2589        | 3.0   | 669  | 0.3275          | 0.5078   |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.2.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,73 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 1,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 1,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 160000,
+  "mask_token_id": 4,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 0,
+  "position_embedding_type": "sans_pos",
+  "problem_type": "multi_label_classification",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 1,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.57.1",
+  "vocab_size": 256000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98165310598d4747ffc3086aae772e0cad12cb1fffcb55fcb16aaea4551f2869
+size 1230169116

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e908bfd541fbc1dfd0426ce81d6fb25a161bb5cd65130de4fa4e633d89d386
+size 5841