Training complete

.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 +1,73 @@
+---
+license: apache-2.0
+base_model: google/mt5-small
+tags:
+- summarization
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mt5-small-finetuned-xlsum-pt
+  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-small-finetuned-xlsum-pt
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0986
+- Rouge1: 16.5756
+- Rouge2: 13.7639
+- Rougel: 15.7445
+- Rougelsum: 16.5112
+
+## 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
+| 0.7681        | 1.0   | 125  | 0.1393          | 12.9432 | 9.5039  | 12.2871 | 12.7291   |
+| 0.5282        | 2.0   | 250  | 0.1231          | 13.4575 | 10.0697 | 12.6449 | 13.2      |
+| 0.4132        | 3.0   | 375  | 0.1134          | 16.6964 | 14.0187 | 15.7338 | 16.6025   |
+| 0.3534        | 4.0   | 500  | 0.1077          | 16.8961 | 14.2203 | 15.9187 | 16.7712   |
+| 0.3126        | 5.0   | 625  | 0.1039          | 16.993  | 14.0876 | 15.8914 | 16.9277   |
+| 0.283         | 6.0   | 750  | 0.1023          | 16.7431 | 13.9453 | 15.8758 | 16.6413   |
+| 0.2675        | 7.0   | 875  | 0.1008          | 16.6566 | 13.8639 | 15.775  | 16.5481   |
+| 0.2509        | 8.0   | 1000 | 0.0987          | 16.6829 | 13.935  | 15.872  | 16.6222   |
+| 0.2441        | 9.0   | 1125 | 0.0987          | 16.6085 | 13.7884 | 15.7896 | 16.5412   |
+| 0.2401        | 10.0  | 1250 | 0.0986          | 16.5756 | 13.7639 | 15.7445 | 16.5112   |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "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:e03c9a201208265c0e0bcd754be8b4a0253e83d1535e51ba1b3e6dc883a61058
+size 1200729512

runs/Feb23_00-17-26_92ee6bb81a5e/events.out.tfevents.1708647457.92ee6bb81a5e.5245.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb31e513eb63687df7833a55c021f564b1a9c548ca08076fd1205b7c0db85db
+size 21739

runs/Feb23_00-17-26_92ee6bb81a5e/events.out.tfevents.1708649376.92ee6bb81a5e.5245.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e87e6619c35e3727e4bd719af90f9cd62e79272dcddc167c5b2fa62d55f4adee
+size 562

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 sha256:85ba321e55174326871149897696a427dd068c06285e22519c973aa53b8cffde
+size 16330660

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 sha256:03ba8747dae917e11ce847960b972837f507d3a0c757cff9d3f59499db77c52f
+size 4856