Model save

.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 @@
+---
+license: apache-2.0
+base_model: google/mt5-large
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mt5-large-finetuned-scope-summarization
+  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. -->
+
+# mt5-large-finetuned-scope-summarization
+
+This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 7.7968
+- Rouge1: 8.9288
+- Rouge2: 2.5195
+- Rougel: 8.1326
+- Rougelsum: 8.2266
+
+## 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: 5.6e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
+| 24.9681       | 1.0   | 13   | 14.1263         | 9.679   | 1.2781 | 9.2044  | 9.2028    |
+| 19.4912       | 2.0   | 26   | 13.8332         | 10.3322 | 2.2934 | 10.0898 | 9.9917    |
+| 18.9675       | 3.0   | 39   | 14.5743         | 10.644  | 2.4553 | 10.4176 | 10.3855   |
+| 23.2647       | 4.0   | 52   | 16.1424         | 9.4387  | 1.9352 | 8.8508  | 8.8573    |
+| 25.5379       | 5.0   | 65   | 16.1511         | 8.9967  | 2.3549 | 8.6046  | 8.666     |
+| 23.0787       | 6.0   | 78   | 15.0432         | 9.4838  | 2.3778 | 9.0507  | 9.1552    |
+| 20.5359       | 7.0   | 91   | 12.4876         | 8.9692  | 2.5655 | 8.5533  | 8.6442    |
+| 18.6638       | 8.0   | 104  | 10.5506         | 10.5377 | 2.5387 | 9.4585  | 9.3817    |
+| 15.6668       | 9.0   | 117  | 10.4213         | 11.1515 | 2.3781 | 10.5545 | 10.6241   |
+| 16.0823       | 10.0  | 130  | 9.7474          | 11.3564 | 2.6133 | 10.5169 | 10.5736   |
+| 16.189        | 11.0  | 143  | 9.3992          | 10.5378 | 3.3175 | 9.2739  | 9.4737    |
+| 14.6943       | 12.0  | 156  | 9.1679          | 9.8364  | 2.942  | 8.991   | 9.0988    |
+| 13.9725       | 13.0  | 169  | 9.4899          | 9.1523  | 2.6655 | 8.499   | 8.6962    |
+| 14.0998       | 14.0  | 182  | 8.4480          | 9.7567  | 2.9029 | 8.2077  | 8.3139    |
+| 13.2          | 15.0  | 195  | 8.2385          | 9.9148  | 2.9029 | 8.1975  | 8.3074    |
+| 13.1084       | 16.0  | 208  | 8.0442          | 8.1004  | 2.2435 | 7.4792  | 7.5977    |
+| 13.6186       | 17.0  | 221  | 7.9349          | 8.2995  | 2.2435 | 7.4792  | 7.5977    |
+| 12.6013       | 18.0  | 234  | 7.8921          | 8.5692  | 2.5238 | 7.7018  | 7.8229    |
+| 12.8011       | 19.0  | 247  | 7.8561          | 8.5692  | 2.5238 | 7.7018  | 7.8229    |
+| 12.9507       | 20.0  | 260  | 7.7968          | 8.9288  | 2.5195 | 8.1326  | 8.2266    |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/mt5-large",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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,
+  "model_type": "mt5",
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "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": false,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d2c5abffec91d11dff133bd54297ebc2dbaefb9f1e73abd410f92aeb7db9bde
+size 4918393736

runs/Feb25_17-25-21_nbqbdwuqbg/events.out.tfevents.1708881925.nbqbdwuqbg.1417.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c5a2a745ba8d2b0b4a185b52b74e8760bb5f859089bd13e6bb338f3bf2e7ea
+size 19093

runs/Feb25_17-25-21_nbqbdwuqbg/events.out.tfevents.1708882306.nbqbdwuqbg.1417.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa60abdeabc3cc232a3c5a2b385b34bcb2287ad8bdee02741a07ddc31ce0945
+size 514

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "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 sha256:896dd34aaf0cdc200ceadaf33d83393d41f46b603b48f05fba3f75620efc725e
+size 16330826

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": "</s>",
+  "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 sha256:65a6d6b8acd3b2ffc2ec69f42254d701e075cf3d4af882b4046e18d6e8d6ae4d
+size 5112