End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: agemagician/mlong-t5-tglobal-base
+tags:
+- generated_from_trainer
+model-index:
+- name: mlong-t5-tglobal-base-raw-vietnamese
+  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. -->
+
+# mlong-t5-tglobal-base-raw-vietnamese
+
+This model is a fine-tuned version of [agemagician/mlong-t5-tglobal-base](https://huggingface.co/agemagician/mlong-t5-tglobal-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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "agemagician/mlong-t5-tglobal-base",
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "encoder_attention_type": "transient-global",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "local_radius": 127,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 256384
+}

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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050ad9348d3e96501f644bafd5e9ea54cc19322f5a582f0e7f56eca715cf72de
+size 2368215072

runs/Jun03_00-25-32_ip-10-192-12-103/events.out.tfevents.1717374339.ip-10-192-12-103.16805.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e13e76b7b219a6691c6a074caa9ba6e236b6556f707e3f1b5a523cf47bd50b
+size 5282

runs/Jun03_00-28-17_ip-10-192-12-103/events.out.tfevents.1717374497.ip-10-192-12-103.20282.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af12b6153dbf6e112f6da05113cc3b81b822e167836cb719154a38eae352416
+size 5282

runs/Jun03_00-29-47_ip-10-192-12-103/events.out.tfevents.1717374588.ip-10-192-12-103.22809.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9afa0b941262435d44c7c64ab002ac7e705795e6f09699799c661be381a9df
+size 5282

runs/Jun03_00-33-36_ip-10-192-12-103/events.out.tfevents.1717374818.ip-10-192-12-103.25653.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afafe7db83daa5034fe2fb605ca51c71c0110b4e6df98957ce7d74559bae2f8f
+size 9434

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df39d1fc39c686038078faca93a76cbae9e199a3b652997417ef370ad8c5677
+size 4555103

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b8cecbcb331a2f0b2de4dc7d82d52151a6d25981dfa3f3c66cd05651ae872c
+size 16796056

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a350f061a43e7529aec7587d06dbeb7d8c9b60d58f60e5795ca4381e8350ffe
+size 5304