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 +1,82 @@
+---
+base_model: csebuetnlp/mT5_multilingual_XLSum
+tags:
+- generated_from_trainer
+model-index:
+- name: SadNews_2_20epochs
+  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. -->
+
+# SadNews_2_20epochs
+
+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: 3.2760
+
+## 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 3.3998        | 0.76  | 500   | 2.8591          |
+| 2.8316        | 1.52  | 1000  | 2.5640          |
+| 2.3969        | 2.29  | 1500  | 2.4411          |
+| 1.8762        | 3.05  | 2000  | 2.4241          |
+| 1.9914        | 3.81  | 2500  | 2.3928          |
+| 1.8294        | 4.57  | 3000  | 2.4093          |
+| 1.7505        | 5.34  | 3500  | 2.4674          |
+| 1.313         | 6.1   | 4000  | 2.5457          |
+| 1.5311        | 6.86  | 4500  | 2.4944          |
+| 1.2645        | 7.62  | 5000  | 2.5876          |
+| 1.0581        | 8.38  | 5500  | 2.6490          |
+| 1.2508        | 9.15  | 6000  | 2.7311          |
+| 1.3671        | 9.91  | 6500  | 2.7163          |
+| 0.9799        | 10.67 | 7000  | 2.7751          |
+| 1.03          | 11.43 | 7500  | 2.8911          |
+| 0.8382        | 12.2  | 8000  | 2.9649          |
+| 1.0784        | 12.96 | 8500  | 2.9205          |
+| 0.7969        | 13.72 | 9000  | 3.0321          |
+| 0.7965        | 14.48 | 9500  | 3.0564          |
+| 0.7737        | 15.24 | 10000 | 3.1322          |
+| 0.591         | 16.01 | 10500 | 3.1051          |
+| 0.8767        | 16.77 | 11000 | 3.1922          |
+| 0.6458        | 17.53 | 11500 | 3.2355          |
+| 0.591         | 18.29 | 12000 | 3.2301          |
+| 0.6428        | 19.05 | 12500 | 3.2603          |
+| 0.7789        | 19.82 | 13000 | 3.2760          |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- 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": "4.38.1",
+  "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": "4.38.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bccd3a29006b89e9bfa7aa056f5f1f988cd86d6f67774146cf44bef5b5c03bbb
+size 2329638768

runs/Mar01_05-28-08_dd2b96e32e6b/events.out.tfevents.1709270890.dd2b96e32e6b.2154.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d4259914fecd80fbe34c181e3a675df6ae652e29494fc3f53393034e64648c
+size 289023

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 sha256:2df3ed82e9d46d38906e9602c98d1f4df93be8ad0cecc63fe1d660d5a90d6600
+size 4856