kietnt0603/vi-coqe-stage2

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: VietAI/vit5-base
+tags:
+- generated_from_trainer
+model-index:
+- name: vi-coqe-stage2
+  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. -->
+
+# vi-coqe-stage2
+
+This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on the None dataset.
+
+## 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: 20
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "VietAI/vit5-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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 36096
+}

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": "4.41.2"
+}

logs/events.out.tfevents.1720061991.c8b0413c7dcb.24.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7c060b14eae5d07fc74e25e01018342c42e542fca574f6c2f9fc985147d153
+size 17321

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d2fe8083e526e477ae0aff47ed4a110b54bfad0b60e882abc07ee58724d4fc
+size 903834408

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:762552cd717f8f7a92fab6500d9e1e8d78b8840a8c738d9129bd66733608aafa
+size 5240