khanhvy31/baset5_scoring

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: t5-base
+tags:
+- generated_from_trainer
+model-index:
+- name: t5-training
+  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-training
+
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7143
+- Mse: 0.3397
+
+## 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
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Mse    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1.0303        | 1.0   | 392  | 0.7538          | 0.3615 |
+| 0.7436        | 2.0   | 784  | 0.7168          | 0.3378 |
+| 0.7185        | 3.0   | 1176 | 0.7143          | 0.3397 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.0.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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,
+  "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": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6b00f8529f88132bce2b5268096cfb2c8b4b831df9bae24bf7324c7af41934
+size 891644712

runs/Oct28_17-43-36_65d8db04c7cd/events.out.tfevents.1730137418.65d8db04c7cd.2026.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ff7e0159e35c2b221709b019683d654d5bba93e7e8f591df5c9710addc1ea9
+size 7673

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc1ef8fa74d5ea1f2c7a26d851feda0b6975fe138ffb4b1106e93e76ee0f28f
+size 5176