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_v0.2
+  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_v0.2
+
+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: 6.5103
+- Bleu: 0.6102
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| 7.711         | 1.0   | 6    | 12.1049         | 0.1934 | 17.0952 |
+| 9.9285        | 2.0   | 12   | 7.2425          | 0.1897 | 19.0    |
+| 6.1686        | 3.0   | 18   | 6.5311          | 0.3794 | 19.0    |
+| 6.0527        | 4.0   | 24   | 6.4394          | 0.6102 | 19.0    |
+| 6.0341        | 5.0   | 30   | 6.3821          | 0.6102 | 19.0    |
+| 4.9353        | 6.0   | 36   | 6.2037          | 0.704  | 19.0    |
+| 5.3025        | 7.0   | 42   | 6.2245          | 0.2318 | 19.0    |
+| 5.4882        | 8.0   | 48   | 6.4244          | 0.0    | 19.0    |
+| 4.3601        | 9.0   | 54   | 6.4695          | 0.0    | 19.0    |
+| 4.8256        | 10.0  | 60   | 6.1939          | 0.6102 | 19.0    |
+| 6.2603        | 11.0  | 66   | 7.2294          | 0.6102 | 19.0    |
+| 5.5046        | 12.0  | 72   | 7.1054          | 0.704  | 19.0    |
+| 5.6536        | 13.0  | 78   | 6.2424          | 0.6102 | 19.0    |
+| 5.2092        | 14.0  | 84   | 6.2343          | 0.2016 | 19.0    |
+| 4.5288        | 15.0  | 90   | 6.1996          | 0.6102 | 19.0    |
+| 5.3447        | 16.0  | 96   | 6.4456          | 0.0    | 3.0     |
+| 4.7282        | 17.0  | 102  | 6.0271          | 0.2172 | 19.0    |
+| 5.3814        | 18.0  | 108  | 6.2591          | 0.6102 | 19.0    |
+| 3.8156        | 19.0  | 114  | 6.2314          | 0.6102 | 19.0    |
+| 4.9031        | 20.0  | 120  | 6.3173          | 0.1986 | 19.0    |
+| 4.4266        | 21.0  | 126  | 6.5376          | 0.6102 | 19.0    |
+| 4.1837        | 22.0  | 132  | 6.1329          | 0.6405 | 19.0    |
+| 4.2994        | 23.0  | 138  | 6.1589          | 0.6102 | 19.0    |
+| 4.3625        | 24.0  | 144  | 6.0873          | 0.6218 | 19.0    |
+| 4.8956        | 25.0  | 150  | 6.2374          | 0.2318 | 19.0    |
+| 4.3551        | 26.0  | 156  | 6.2230          | 0.6102 | 19.0    |
+| 4.025         | 27.0  | 162  | 6.2925          | 0.6929 | 19.0    |
+| 3.9071        | 28.0  | 168  | 6.2040          | 0.6102 | 19.0    |
+| 4.1388        | 29.0  | 174  | 6.3024          | 0.6218 | 19.0    |
+| 3.942         | 30.0  | 180  | 6.4055          | 0.2176 | 19.0    |
+| 4.0977        | 31.0  | 186  | 6.3005          | 0.2874 | 19.0    |
+| 4.6125        | 32.0  | 192  | 6.2886          | 0.6102 | 19.0    |
+| 4.4031        | 33.0  | 198  | 6.2948          | 0.704  | 19.0    |
+| 3.8115        | 34.0  | 204  | 6.2838          | 0.6102 | 19.0    |
+| 4.8767        | 35.0  | 210  | 6.2233          | 0.6102 | 19.0    |
+| 3.6557        | 36.0  | 216  | 6.2860          | 0.6102 | 19.0    |
+| 3.9009        | 37.0  | 222  | 6.3841          | 0.6102 | 19.0    |
+| 4.4334        | 38.0  | 228  | 6.3916          | 0.6102 | 19.0    |
+| 3.3359        | 39.0  | 234  | 6.3696          | 0.6102 | 19.0    |
+| 4.2239        | 40.0  | 240  | 6.4627          | 0.6102 | 19.0    |
+| 3.7335        | 41.0  | 246  | 6.5189          | 0.6102 | 19.0    |
+| 3.544         | 42.0  | 252  | 6.4958          | 0.6102 | 19.0    |
+| 3.77          | 43.0  | 258  | 6.5922          | 0.6102 | 19.0    |
+| 3.4661        | 44.0  | 264  | 6.6700          | 0.6218 | 19.0    |
+| 4.0715        | 45.0  | 270  | 6.6247          | 0.6102 | 19.0    |
+| 3.8948        | 46.0  | 276  | 6.5279          | 0.6102 | 19.0    |
+| 3.8278        | 47.0  | 282  | 6.4594          | 0.6102 | 19.0    |
+| 4.1446        | 48.0  | 288  | 6.4570          | 0.6102 | 19.0    |
+| 3.7627        | 49.0  | 294  | 6.4923          | 0.6102 | 19.0    |
+| 3.5996        | 50.0  | 300  | 6.5103          | 0.6102 | 19.0    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 1.13.1+cu117
+- Datasets 2.17.0
+- Tokenizers 0.15.1

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 sha256:6f415b3e37274ca2bee1bcbc15b0de2fa1587dfd74460d81b933db1180d06234
+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:d1f1dcad77bea447578105d7cbeb377397f6f6fdc8290f24e12874a5218046d5
+size 4283