End of training

.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 +1,110 @@
+---
+license: apache-2.0
+base_model: google/mt5-base
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: cs_mT5_0.01_50_v0.1
+  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. -->
+
+# cs_mT5_0.01_50_v0.1
+
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 7.3188
+- Bleu: 1.2029
+- Gen Len: 19.0
+
+## 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: 0.01
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| 3.6406        | 1.0   | 6    | 6.1758          | 0.1903 | 19.0    |
+| 4.2513        | 2.0   | 12   | 6.4360          | 0.4971 | 19.0    |
+| 3.1515        | 3.0   | 18   | 6.2761          | 0.1689 | 19.0    |
+| 3.4713        | 4.0   | 24   | 6.4576          | 0.4973 | 19.0    |
+| 3.2069        | 5.0   | 30   | 6.6858          | 0.176  | 10.0    |
+| 3.5913        | 6.0   | 36   | 6.2785          | 0.7212 | 19.0    |
+| 3.7814        | 7.0   | 42   | 6.1120          | 0.7212 | 19.0    |
+| 3.2429        | 8.0   | 48   | 6.3660          | 0.3725 | 19.0    |
+| 3.2716        | 9.0   | 54   | 6.6523          | 0.4214 | 19.0    |
+| 3.3443        | 10.0  | 60   | 6.4341          | 0.3793 | 19.0    |
+| 2.4705        | 11.0  | 66   | 6.8433          | 0.7412 | 19.0    |
+| 3.0869        | 12.0  | 72   | 6.9583          | 0.0    | 19.0    |
+| 2.5187        | 13.0  | 78   | 6.3333          | 1.1569 | 19.0    |
+| 3.1211        | 14.0  | 84   | 6.4031          | 0.2813 | 19.0    |
+| 2.7326        | 15.0  | 90   | 6.4055          | 0.7962 | 19.0    |
+| 2.5142        | 16.0  | 96   | 6.5799          | 0.1843 | 19.0    |
+| 3.0964        | 17.0  | 102  | 6.8379          | 0.9395 | 19.0    |
+| 2.5998        | 18.0  | 108  | 6.4570          | 0.0    | 19.0    |
+| 3.2495        | 19.0  | 114  | 6.6350          | 0.2045 | 19.0    |
+| 3.2509        | 20.0  | 120  | 6.3533          | 0.7212 | 19.0    |
+| 3.2998        | 21.0  | 126  | 6.3142          | 0.6756 | 19.0    |
+| 2.7829        | 22.0  | 132  | 6.5953          | 0.6646 | 19.0    |
+| 3.0842        | 23.0  | 138  | 6.6276          | 0.7056 | 19.0    |
+| 1.8502        | 24.0  | 144  | 6.6472          | 0.2386 | 19.0    |
+| 1.945         | 25.0  | 150  | 6.6534          | 0.6966 | 19.0    |
+| 2.7704        | 26.0  | 156  | 7.1955          | 0.7611 | 13.0    |
+| 3.1289        | 27.0  | 162  | 6.6522          | 0.7286 | 17.0    |
+| 3.0663        | 28.0  | 168  | 6.3873          | 0.8029 | 19.0    |
+| 3.4269        | 29.0  | 174  | 6.4310          | 0.204  | 19.0    |
+| 2.7845        | 30.0  | 180  | 6.7221          | 0.3228 | 19.0    |
+| 2.0443        | 31.0  | 186  | 6.8353          | 0.3228 | 19.0    |
+| 3.1621        | 32.0  | 192  | 7.1400          | 0.1346 | 19.0    |
+| 2.4147        | 33.0  | 198  | 6.8844          | 1.2029 | 19.0    |
+| 2.5869        | 34.0  | 204  | 6.7074          | 0.7475 | 19.0    |
+| 2.1119        | 35.0  | 210  | 6.5778          | 0.7212 | 19.0    |
+| 1.7629        | 36.0  | 216  | 6.5553          | 0.7867 | 19.0    |
+| 2.3745        | 37.0  | 222  | 6.7126          | 0.7663 | 19.0    |
+| 2.368         | 38.0  | 228  | 6.8008          | 0.4815 | 19.0    |
+| 2.17          | 39.0  | 234  | 6.6388          | 0.7892 | 19.0    |
+| 2.4311        | 40.0  | 240  | 6.6423          | 0.3228 | 19.0    |
+| 2.8392        | 41.0  | 246  | 6.7127          | 0.3226 | 19.0    |
+| 2.386         | 42.0  | 252  | 6.8011          | 0.31   | 19.0    |
+| 2.7473        | 43.0  | 258  | 6.8704          | 0.31   | 19.0    |
+| 1.9796        | 44.0  | 264  | 6.9846          | 1.2029 | 19.0    |
+| 1.4857        | 45.0  | 270  | 7.1239          | 1.2029 | 19.0    |
+| 1.8413        | 46.0  | 276  | 7.2177          | 1.194  | 19.0    |
+| 2.171         | 47.0  | 282  | 7.2605          | 1.2029 | 19.0    |
+| 1.9659        | 48.0  | 288  | 7.3048          | 1.2029 | 19.0    |
+| 1.3681        | 49.0  | 294  | 7.3093          | 1.2029 | 19.0    |
+| 2.086         | 50.0  | 300  | 7.3188          | 1.2029 | 19.0    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 1.13.1+cu117
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "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": "4.35.2",
+  "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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c411eeaa530077a0ffc6dc17e9195bbe126e96a3568bf71ee5cb5baae768386e
+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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c816e64ca5739a75c4a484bbff22b624131f1b667f423dbeaeaa053b501fdafe
+size 16330559

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:df4fe0590dd007dcf660026dc8eabcd6708b12523fea1804bfddae3f2fd24df1
+size 4283