gatortron-base Versione dopo 10 epochs

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: UFNLP/gatortron-base
+tags:
+- generated_from_trainer
+model-index:
+- name: ICU_Returns_Gatortron
+  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. -->
+
+# ICU_Returns_Gatortron
+
+This model is a fine-tuned version of [UFNLP/gatortron-base](https://huggingface.co/UFNLP/gatortron-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7852
+- F1:: 0.7203
+- Roc Auc: 0.7335
+- Precision with 0:: 0.9126
+- Precision with 1:: 0.6628
+- Recall with 0:: 0.5165
+- Recal  with 1:: 0.9505
+- Accuracy:: 0.7335
+
+## 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: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 16
+- 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 | F1:    | Roc Auc | Precision with 0: | Precision with 1: | Recall with 0: | Recal  with 1: | Accuracy: |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:-----------------:|:-----------------:|:--------------:|:--------------:|:---------:|
+| No log        | 1.0   | 46   | 0.6889          | 0.6965 | 0.7115  | 0.8812            | 0.6464            | 0.4890         | 0.9341         | 0.7115    |
+| No log        | 2.0   | 92   | 0.7628          | 0.7287 | 0.7390  | 0.8919            | 0.6719            | 0.5440         | 0.9341         | 0.7390    |
+| No log        | 3.0   | 138  | 1.8927          | 0.6372 | 0.6703  | 0.9306            | 0.6062            | 0.3681         | 0.9725         | 0.6703    |
+| No log        | 4.0   | 184  | 1.7208          | 0.7236 | 0.7363  | 0.9135            | 0.6654            | 0.5220         | 0.9505         | 0.7363    |
+| No log        | 5.0   | 230  | 1.7852          | 0.7203 | 0.7335  | 0.9126            | 0.6628            | 0.5165         | 0.9505         | 0.7335    |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "UFNLP/gatortron-base",
+  "architectures": [
+    "MegatronBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "megatron-bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_type": "BertWordPieceCase",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50176
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3029f23795d4e9ffb8a6eb96aae0d5dcda96b91b24000d8613b99a498dc3abdd
+size 1421212014

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692e7e71db38aeaf9be42dc4da8ff10912a84f1dfe121b1b419ccc06a062a60c
+size 4536