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 +1,95 @@
+---
+base_model: csebuetnlp/mT5_multilingual_XLSum
+tags:
+- generated_from_trainer
+model-index:
+- name: GeneralNews_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. -->
+
+# GeneralNews_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: 2.9834
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.1541        | 0.25  | 200  | 3.4209          |
+| 3.5494        | 0.51  | 400  | 3.1702          |
+| 3.2618        | 0.76  | 600  | 3.0273          |
+| 3.5983        | 1.01  | 800  | 2.9550          |
+| 3.3355        | 1.26  | 1000 | 2.8883          |
+| 3.4976        | 1.52  | 1200 | 2.8653          |
+| 3.1001        | 1.77  | 1400 | 2.8543          |
+| 2.282         | 2.02  | 1600 | 2.7953          |
+| 2.5724        | 2.27  | 1800 | 2.7866          |
+| 2.7474        | 2.53  | 2000 | 2.7778          |
+| 3.0323        | 2.78  | 2200 | 2.7901          |
+| 2.3032        | 3.03  | 2400 | 2.7641          |
+| 2.5042        | 3.28  | 2600 | 2.8059          |
+| 1.9857        | 3.54  | 2800 | 2.7847          |
+| 2.5909        | 3.79  | 3000 | 2.8045          |
+| 2.2105        | 4.04  | 3200 | 2.8051          |
+| 2.1151        | 4.29  | 3400 | 2.8331          |
+| 1.9858        | 4.55  | 3600 | 2.8292          |
+| 1.9633        | 4.8   | 3800 | 2.8133          |
+| 2.0282        | 5.05  | 4000 | 2.8317          |
+| 2.0988        | 5.3   | 4200 | 2.8781          |
+| 2.0699        | 5.56  | 4400 | 2.8627          |
+| 2.1769        | 5.81  | 4600 | 2.8388          |
+| 1.7436        | 6.06  | 4800 | 2.8899          |
+| 1.8312        | 6.31  | 5000 | 2.9223          |
+| 1.841         | 6.57  | 5200 | 2.8970          |
+| 2.0157        | 6.82  | 5400 | 2.8754          |
+| 2.1223        | 7.07  | 5600 | 2.8958          |
+| 1.6103        | 7.32  | 5800 | 2.9247          |
+| 1.7702        | 7.58  | 6000 | 2.9562          |
+| 1.537         | 7.83  | 6200 | 2.9597          |
+| 1.933         | 8.08  | 6400 | 2.9585          |
+| 1.3947        | 8.33  | 6600 | 2.9841          |
+| 1.639         | 8.59  | 6800 | 2.9723          |
+| 1.6441        | 8.84  | 7000 | 2.9770          |
+| 1.4509        | 9.09  | 7200 | 2.9865          |
+| 1.6212        | 9.34  | 7400 | 2.9890          |
+| 1.8013        | 9.6   | 7600 | 2.9877          |
+| 1.3722        | 9.85  | 7800 | 2.9834          |
+
+
+### 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 sha256:6fb5fd4da8c033534246d7b4ce2f3b5ca2fc87023efb04abd420c456ed5bda23
+size 2329638768

runs/Feb01_16-29-15_c5f132110a9a/events.out.tfevents.1706804968.c5f132110a9a.944.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea93d08893211ab43c9cfdd7916a60229f3418b111ac715bdb7b4564f537907
+size 139732

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 sha256:39c75673c808a52c7514f9d32b484c7f7fd035ad23e2e5b7be3124b5bd1e2f65
+size 4600