tym24/Model

.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 +1,79 @@
+---
+license: apache-2.0
+base_model: google/mt5-small
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mt5-summarize-ja
+  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-summarize-ja
+
+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: 2.0695
+- Rouge1: 0.3667
+- Rouge2: 0.1678
+- Rougel: 0.2998
+- Rougelsum: 0.3123
+
+## 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: 0.0005
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 90
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
+| 3.3241        | 0.7   | 100  | 2.4795          | 0.2943 | 0.1245 | 0.2472 | 0.2471    |
+| 2.7583        | 1.4   | 200  | 2.2710          | 0.3054 | 0.1152 | 0.2539 | 0.2576    |
+| 2.5469        | 2.1   | 300  | 2.2936          | 0.3446 | 0.1493 | 0.2808 | 0.2887    |
+| 2.5335        | 2.8   | 400  | 2.1913          | 0.3228 | 0.1270 | 0.2665 | 0.2725    |
+| 2.4383        | 3.5   | 500  | 2.1507          | 0.3630 | 0.1671 | 0.3082 | 0.3144    |
+| 2.3671        | 4.2   | 600  | 2.1338          | 0.3388 | 0.1493 | 0.2814 | 0.2880    |
+| 2.349         | 4.9   | 700  | 2.1089          | 0.3621 | 0.1576 | 0.2980 | 0.3079    |
+| 2.264         | 5.6   | 800  | 2.1353          | 0.3740 | 0.1784 | 0.3083 | 0.3157    |
+| 2.1577        | 6.3   | 900  | 2.1101          | 0.3711 | 0.1716 | 0.3107 | 0.3166    |
+| 2.1315        | 7.0   | 1000 | 2.0905          | 0.3862 | 0.1826 | 0.3198 | 0.3269    |
+| 2.1418        | 7.7   | 1100 | 2.0893          | 0.3433 | 0.1621 | 0.2895 | 0.2963    |
+| 2.0744        | 8.4   | 1200 | 2.0881          | 0.3778 | 0.1834 | 0.3130 | 0.3242    |
+| 2.0944        | 9.1   | 1300 | 2.0709          | 0.3676 | 0.1688 | 0.3024 | 0.3140    |
+| 2.1015        | 9.8   | 1400 | 2.0695          | 0.3667 | 0.1678 | 0.2998 | 0.3123    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,36 @@
+{
+  "_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,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "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": "4.35.2",
+  "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": 128,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "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:bd7fbfbee3d032d6bfeea8578310577cead733a4e1dbb50e6bccceb13f3c845d
+size 1200729512

runs/Feb19_04-38-28_44c8b26f9f0d/events.out.tfevents.1708317508.44c8b26f9f0d.1239.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b593d806e6bda9219c924b95af049995e3b66c5e079e5e911a1c3ad674040303
+size 33825

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 sha256:3c9b5296bb1bdbcc33ccb40be1c81db3a36335a1c2b080a5368b48fb7a9eaa66
+size 16330461

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:dc3803913e344b03e3f92d8729d0d9fbf7e775e5faefcb2355bc55ba15c999f3
+size 4664