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 +1,83 @@
+---
+base_model: Hasanur525/deed-summarization_version_5
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: deed-summarization_version_10
+  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. -->
+
+# deed-summarization_version_10
+
+This model is a fine-tuned version of [Hasanur525/deed-summarization_version_5](https://huggingface.co/Hasanur525/deed-summarization_version_5) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4150
+- Rouge1: 0.3247
+- Rouge2: 0.1432
+- Rougel: 0.3268
+- Rougelsum: 0.3201
+- Gen Len: 98.4206
+
+## 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
+- lr_scheduler_warmup_steps: 5000
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 2.6983        | 1.0   | 529   | 1.8154          | 0.0    | 0.0    | 0.0    | 0.0       | 72.9565 |
+| 2.3213        | 2.0   | 1058  | 1.5403          | 0.0    | 0.0    | 0.0    | 0.0       | 82.2401 |
+| 1.0315        | 3.0   | 1587  | 1.2686          | 0.0    | 0.0    | 0.0    | 0.0       | 88.1635 |
+| 1.7308        | 4.0   | 2116  | 1.0681          | 0.0    | 0.0    | 0.0    | 0.0       | 89.7155 |
+| 1.1384        | 5.0   | 2645  | 0.9338          | 0.0    | 0.0    | 0.0    | 0.0       | 93.0586 |
+| 1.6608        | 6.0   | 3174  | 0.8329          | 0.0199 | 0.0    | 0.0199 | 0.0199    | 95.5454 |
+| 1.8287        | 7.0   | 3703  | 0.7506          | 0.0099 | 0.0    | 0.0099 | 0.0099    | 96.9036 |
+| 0.4304        | 8.0   | 4232  | 0.6827          | 0.0742 | 0.036  | 0.0692 | 0.069     | 96.8894 |
+| 1.1026        | 9.0   | 4761  | 0.6189          | 0.0888 | 0.0516 | 0.0888 | 0.0859    | 97.5312 |
+| 0.8345        | 10.0  | 5290  | 0.5662          | 0.0497 | 0.0189 | 0.0443 | 0.0443    | 96.8025 |
+| 0.3368        | 11.0  | 5819  | 0.5291          | 0.0394 | 0.0258 | 0.0398 | 0.0394    | 97.9783 |
+| 0.2668        | 12.0  | 6348  | 0.5010          | 0.1466 | 0.0379 | 0.1368 | 0.1345    | 97.4386 |
+| 0.8294        | 13.0  | 6877  | 0.4787          | 0.1815 | 0.0683 | 0.1744 | 0.167     | 97.8639 |
+| 0.4896        | 14.0  | 7406  | 0.4603          | 0.1946 | 0.0732 | 0.1948 | 0.1899    | 97.707  |
+| 0.4353        | 15.0  | 7935  | 0.4446          | 0.158  | 0.0664 | 0.1476 | 0.1456    | 97.8837 |
+| 1.8165        | 16.0  | 8464  | 0.4314          | 0.3104 | 0.1119 | 0.3005 | 0.2917    | 98.4329 |
+| 0.3503        | 17.0  | 8993  | 0.4236          | 0.2872 | 0.1234 | 0.2785 | 0.2681    | 98.2259 |
+| 0.5756        | 18.0  | 9522  | 0.4199          | 0.339  | 0.1242 | 0.3348 | 0.3252    | 98.31   |
+| 0.7974        | 19.0  | 10051 | 0.4176          | 0.3437 | 0.1568 | 0.3477 | 0.338     | 98.3932 |
+| 0.224         | 20.0  | 10580 | 0.4150          | 0.3247 | 0.1432 | 0.3268 | 0.3201    | 98.4206 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0.dev20230811+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "Hasanur525/deed-summarization_version_5",
+  "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": 500,
+  "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": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.6,
+  "max_length": 100,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bf9929c4dcbd8606e251870fa23415e629d4f02623e4c688ed47c30d9856f1
+size 2329638768

runs/Feb19_05-39-47_WIN-F8FVB99PGRI/events.out.tfevents.1708350002.WIN-F8FVB99PGRI.18492.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb203dd531d601dad41ee69441118b4506050d37393a8c638aab0e17a952b99
+size 1676393

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:e023441336081dc068f3193421d41ba92bbea7909d5114ab737dc7d9a3a54141
+size 16315478

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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,
+  "max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14e64b8818f92a755ccabb69d5fef714c3ed50f77df75527ade2e5993b4c38cd
+size 4920