yujiro/deutsche_mt5small_finetuned

.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 +1,72 @@
+---
+license: cc-by-nc-sa-4.0
+base_model: deutsche-telekom/mt5-small-sum-de-en-v1
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mt5-small-sum-de-en-v1-finetuned-amazon-en-de
+  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-sum-de-en-v1-finetuned-amazon-en-de
+
+This model is a fine-tuned version of [deutsche-telekom/mt5-small-sum-de-en-v1](https://huggingface.co/deutsche-telekom/mt5-small-sum-de-en-v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5661
+- Rouge1: 20.9307
+- Rouge2: 12.3388
+- Rougel: 20.4694
+- Rougelsum: 20.6594
+
+## 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: 10
+- eval_batch_size: 10
+- 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
+| 2.3857        | 1.0   | 1041  | 2.5918          | 19.0955 | 10.5762 | 18.6534 | 18.707    |
+| 2.3597        | 2.0   | 2082  | 2.5887          | 20.2078 | 11.1543 | 19.5663 | 19.7039   |
+| 2.3623        | 3.0   | 3123  | 2.5802          | 20.1696 | 12.0499 | 19.7038 | 19.89     |
+| 2.3815        | 4.0   | 4164  | 2.5498          | 19.9131 | 11.5376 | 19.4158 | 19.5746   |
+| 2.3735        | 5.0   | 5205  | 2.5559          | 20.5713 | 11.8808 | 19.9335 | 20.1211   |
+| 2.3269        | 6.0   | 6246  | 2.5574          | 19.8362 | 11.033  | 19.3193 | 19.5623   |
+| 2.2956        | 7.0   | 7287  | 2.5479          | 19.8859 | 11.5389 | 19.4015 | 19.7004   |
+| 2.2646        | 8.0   | 8328  | 2.5669          | 20.4666 | 12.2804 | 20.0291 | 20.1897   |
+| 2.2618        | 9.0   | 9369  | 2.5703          | 20.9783 | 12.3152 | 20.445  | 20.6735   |
+| 2.236         | 10.0  | 10410 | 2.5661          | 20.9307 | 12.3388 | 20.4694 | 20.6594   |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "deutsche-telekom/mt5-small-sum-de-en-v1",
+  "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": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 250100
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6a9011a0b91b06184034c299ecb28a48c6699d381cf948dfbd7d136aa20e09
+size 1200723906

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:d07d197bb675754e0839f9bc8888740d94b9d89f6050a848d16110b3dcdc6907
+size 16330494

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:f8fbe1fe377fc9b908926affe330c623eda95127b48677440fb5cfc65dba9ca7
+size 4728