llewisd/vit5

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: vinai/bartpho-word-base
+license: mit
+base_model: VietAI/vit5-base-vietnews-summarization
 tags:
 - generated_from_trainer
 model-index:
@@ -12,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tmp
 
-This model is a fine-tuned version of [vinai/bartpho-word-base](https://huggingface.co/vinai/bartpho-word-base) on the None dataset.
+This model is a fine-tuned version of [VietAI/vit5-base-vietnews-summarization](https://huggingface.co/VietAI/vit5-base-vietnews-summarization) on the None dataset.
 
 ## Model description
 
@@ -38,7 +39,8 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 5
+- num_epochs: 3
+- mixed_precision_training: Native AMP
 
 ### Training results
 

config.json

@@ -1,37 +1,32 @@
 {
-  "_name_or_path": "vinai/bartpho-word-base",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
+  "_name_or_path": "VietAI/vit5-base-vietnews-summarization",
   "architectures": [
-    "MBartForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
   "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
   "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "init_std": 0.02,
+  "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,
-  "max_position_embeddings": 1024,
-  "model_type": "mbart",
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "scale_embedding": false,
-  "tokenizer_class": "PhobertTokenizer",
+  "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": "4.35.2",
   "use_cache": true,
-  "vocab_size": 64001
+  "vocab_size": 36096
 }

generation_config.json

@@ -1,9 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "pad_token_id": 1,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
   "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e560b2b5ebe6a8c06bf1d815e8d13096b384133ce7ce8c1ff6eff787875662a8
-size 600177236
+oid sha256:5d208c1fc924f82c080bfff1dfa5ee0387e01150e25d889c5bd0ba4fa7154262
+size 903834408

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfb234cb7e301fa702998d7b672b840a2f2a022b3a4d3d02d3d0dce9f485b3f
+oid sha256:ea59f137a2734cf3ad19d146f56684d116e614a4f9fcb3527838480f4d9c7de9
 size 4664