End of training

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: google/mt5-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mT5-lithuanian-simplifier
+  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-lithuanian-simplifier
+
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0687
+- Rouge1: 0.7322
+- Rouge2: 0.5833
+- Rougel: 0.7261
+- Gen Len: 34.6325
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:-------:|
+| 23.3756       | 0.48  | 200  | 16.6054         | 0.011  | 0.0006 | 0.0105 | 512.0   |
+| 1.435         | 0.96  | 400  | 0.5767          | 0.1436 | 0.0387 | 0.1307 | 39.0358 |
+| 0.2269        | 1.44  | 600  | 0.1658          | 0.4744 | 0.317  | 0.4631 | 34.6325 |
+| 0.1709        | 1.91  | 800  | 0.1030          | 0.5865 | 0.4231 | 0.577  | 34.6325 |
+| 0.1311        | 2.39  | 1000 | 0.0923          | 0.6245 | 0.4626 | 0.6173 | 34.6325 |
+| 0.1196        | 2.87  | 1200 | 0.0851          | 0.6759 | 0.5159 | 0.6681 | 34.6325 |
+| 0.1156        | 3.35  | 1400 | 0.0761          | 0.6927 | 0.5288 | 0.6845 | 34.6325 |
+| 0.0897        | 3.83  | 1600 | 0.0756          | 0.698  | 0.5352 | 0.6906 | 34.6325 |
+| 0.1149        | 4.31  | 1800 | 0.0738          | 0.7085 | 0.55   | 0.7022 | 34.6325 |
+| 0.0967        | 4.78  | 2000 | 0.0725          | 0.7187 | 0.5632 | 0.712  | 34.6325 |
+| 0.1097        | 5.26  | 2200 | 0.0703          | 0.7214 | 0.5645 | 0.7143 | 34.6325 |
+| 0.0852        | 5.74  | 2400 | 0.0708          | 0.7241 | 0.5724 | 0.7176 | 34.6325 |
+| 0.0537        | 6.22  | 2600 | 0.0693          | 0.7285 | 0.578  | 0.7217 | 34.6325 |
+| 0.0866        | 6.7   | 2800 | 0.0698          | 0.7277 | 0.5795 | 0.7216 | 34.6325 |
+| 0.0692        | 7.18  | 3000 | 0.0685          | 0.7336 | 0.5849 | 0.7274 | 34.6325 |
+| 0.0786        | 7.66  | 3200 | 0.0687          | 0.7322 | 0.5833 | 0.7261 | 34.6325 |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.1
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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,
+  "model_type": "t5",
+  "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": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

logs/events.out.tfevents.1704894198.ESBeastModeOn.10684.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511941aa57114e7236db160c83e77a7d33a7703c394c92b8953346cd5436d255
+size 4521

logs/events.out.tfevents.1704894235.ESBeastModeOn.17524.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dae65638910e1cd053aec0e58f6067943d4a691c1da57221070a45e837cdd8
+size 6215

logs/events.out.tfevents.1704895563.ESBeastModeOn.16636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d01f53d81dda833ce66b2576fe94aa207564a96880a19779394fb15e305df4d
+size 5944

logs/events.out.tfevents.1704896726.ESBeastModeOn.8472.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b680ba13bb90db5cab0df75095c9d7238d8c47152404efc1781d8dce6e24d5fe
+size 5676

logs/events.out.tfevents.1704897981.ESBeastModeOn.33432.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53cb48e7a0f265f34ff22903716bec1a1e4cf52b9f7c735abc082a4ddbbc7aa
+size 64865

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12525e7424a11a92f510abb750e793abcb13350346b77fe129cd08a5b7b0d10
+size 2329638768

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_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:d135115d7ef77740119c78a5378803a65c68d59f93430fb00a4c67a6488f2719
+size 4728