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 +1,67 @@
+---
+base_model: csebuetnlp/mT5_multilingual_XLSum
+tags:
+- generated_from_trainer
+model-index:
+- name: type2_general_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. -->
+
+# type2_general_1
+
+This model is a fine-tuned version of [csebuetnlp/mT5_multilingual_XLSum](https://huggingface.co/csebuetnlp/mT5_multilingual_XLSum) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.0966
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.634         | 0.87  | 500  | 2.9991          |
+| 3.1251        | 1.74  | 1000 | 2.8423          |
+| 2.5868        | 2.61  | 1500 | 2.8272          |
+| 2.3594        | 3.48  | 2000 | 2.8389          |
+| 2.0565        | 4.35  | 2500 | 2.8995          |
+| 2.1545        | 5.22  | 3000 | 2.9175          |
+| 1.6546        | 6.09  | 3500 | 2.9527          |
+| 1.4673        | 6.96  | 4000 | 2.9956          |
+| 1.7318        | 7.83  | 4500 | 3.0638          |
+| 1.3006        | 8.7   | 5000 | 3.0805          |
+| 1.5979        | 9.57  | 5500 | 3.0966          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "csebuetnlp/mT5_multilingual_XLSum",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 84,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "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,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.6,
+  "max_length": 84,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6258ccd0469b8ba43cd9aa34ad012d4923ba955f04b180bde9f0d7c1d18df626
+size 2329638768

runs/Apr10_12-46-09_b94d93c0e033/events.out.tfevents.1712753171.b94d93c0e033.1945.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49cae5243657754aed70816abd866ab1c8c842d7dbd8157b44c1d507245f194b
+size 129442

runs/Apr10_14-55-25_b94d93c0e033/events.out.tfevents.1712760929.b94d93c0e033.34240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f02060668b785dc5955d8eda72f7e77285319795bc00122ece4d040a9399a53
+size 129442

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:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ed906f49856e1865d41533458529a617d59265468fdb21c52b21294ddfc9b0
+size 16330660

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
+    },
+    "2": {
+      "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 sha256:96e09c3ab133f059a7e6638c782d5dee4dbe1480e5b69bb4394385424bdc3e56
+size 4856