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 +1,90 @@
+---
+base_model: csebuetnlp/mT5_multilingual_XLSum
+tags:
+- generated_from_trainer
+model-index:
+- name: HappyNews_1_loadbest
+  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. -->
+
+# HappyNews_1_loadbest
+
+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: 3.1967
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.1092        | 0.29  | 100  | 4.0260          |
+| 4.3545        | 0.58  | 200  | 3.6022          |
+| 3.818         | 0.87  | 300  | 3.3815          |
+| 3.2577        | 1.16  | 400  | 3.2590          |
+| 3.1005        | 1.45  | 500  | 3.1290          |
+| 3.0309        | 1.73  | 600  | 3.0690          |
+| 3.0128        | 2.02  | 700  | 3.0172          |
+| 2.4054        | 2.31  | 800  | 3.0086          |
+| 2.7848        | 2.6   | 900  | 3.0103          |
+| 2.4307        | 2.89  | 1000 | 2.9606          |
+| 2.3408        | 3.18  | 1100 | 2.9490          |
+| 2.4232        | 3.47  | 1200 | 2.9333          |
+| 2.5301        | 3.76  | 1300 | 2.9138          |
+| 1.9984        | 4.05  | 1400 | 2.9422          |
+| 2.1215        | 4.34  | 1500 | 2.9620          |
+| 1.859         | 4.62  | 1600 | 2.9550          |
+| 1.8986        | 4.91  | 1700 | 2.9654          |
+| 1.847         | 5.2   | 1800 | 3.0660          |
+| 1.7843        | 5.49  | 1900 | 3.0169          |
+| 1.9724        | 5.78  | 2000 | 3.0131          |
+| 1.6603        | 6.07  | 2100 | 3.0816          |
+| 1.4024        | 6.36  | 2200 | 3.0947          |
+| 1.2758        | 6.65  | 2300 | 3.0688          |
+| 1.7435        | 6.94  | 2400 | 3.0203          |
+| 1.2973        | 7.23  | 2500 | 3.1221          |
+| 1.282         | 7.51  | 2600 | 3.1566          |
+| 1.4837        | 7.8   | 2700 | 3.1047          |
+| 1.6313        | 8.09  | 2800 | 3.1343          |
+| 1.4611        | 8.38  | 2900 | 3.1634          |
+| 1.0115        | 8.67  | 3000 | 3.1751          |
+| 1.4337        | 8.96  | 3100 | 3.1701          |
+| 1.1845        | 9.25  | 3200 | 3.1881          |
+| 1.2019        | 9.54  | 3300 | 3.1998          |
+| 1.1448        | 9.83  | 3400 | 3.1967          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

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": "4.35.2",
+  "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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b8a9005698a13c1e95aa51ebc28d0019431fa6512c7bf6c395412ff7e93377
+size 2329638768

runs/Feb01_15-54-27_82187ca24ee5/events.out.tfevents.1706802872.82187ca24ee5.3453.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93a8c9911516af0eb7f29599d68bd6b0e1f8867b674fd4c2065079e84ce4bef
+size 68344

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:c6159d7ec2f2ff06356659536274e669822a98188a9cf7f009f92a264ab5abf4
+size 16330559

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "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 sha256:2393751e0866ffedd70b7fba314dbc22bc8c9c791984a74c632251266d979214
+size 4600