CatBarks/t5_bce_farshad_half_4_1

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: google-t5/t5-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: t5_es_farshad_half_4_1
+  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. -->
+
+# t5_es_farshad_half_4_1
+
+This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0490
+- Accuracy: 0.9916
+- F1: 0.9919
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 4096
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 100
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| 0.6889        | 5.8501  | 50   | 0.6724          | 0.6073   | 0.5334 |
+| 0.6445        | 11.7002 | 100  | 0.5323          | 0.8022   | 0.8091 |
+| 0.3119        | 17.5503 | 150  | 0.1187          | 0.9649   | 0.9656 |
+| 0.0967        | 23.4004 | 200  | 0.0648          | 0.9794   | 0.9800 |
+| 0.0549        | 29.2505 | 250  | 0.0500          | 0.9858   | 0.9862 |
+| 0.0359        | 35.1005 | 300  | 0.0465          | 0.9884   | 0.9888 |
+| 0.0248        | 40.9506 | 350  | 0.0443          | 0.9887   | 0.9891 |
+| 0.0183        | 46.8007 | 400  | 0.0404          | 0.9898   | 0.9902 |
+| 0.0139        | 52.6508 | 450  | 0.0445          | 0.9890   | 0.9893 |
+| 0.0111        | 58.5009 | 500  | 0.0559          | 0.9887   | 0.9890 |
+| 0.0087        | 64.3510 | 550  | 0.0486          | 0.9893   | 0.9896 |
+| 0.0081        | 70.2011 | 600  | 0.0440          | 0.9910   | 0.9913 |
+| 0.0065        | 76.0512 | 650  | 0.0410          | 0.9919   | 0.9921 |
+| 0.0045        | 81.9013 | 700  | 0.0596          | 0.9893   | 0.9896 |
+| 0.0042        | 87.7514 | 750  | 0.0475          | 0.9898   | 0.9902 |
+| 0.0036        | 93.6015 | 800  | 0.0490          | 0.9916   | 0.9919 |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "google-t5/t5-base",
+  "architectures": [
+    "T5ForSequenceClassification"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7f8cc59f294e3b994d13893b3397dc467878ac9b3dd8200d2a034f405efab4
+size 894016712

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:264159f04e2e83cb8fae9396a6ab922d7e1e7af17306e51e1751fec06675419e
+size 4984