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-large
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: cs_mT5-large2_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-large2_0.01_50_v0.1
+
+This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 7.9807
+- Bleu: 0.6899
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| 2.6703        | 1.0   | 6    | 8.3163          | 0.0    | 19.0    |
+| 3.3427        | 2.0   | 12   | 6.5085          | 0.5004 | 19.0    |
+| 2.8652        | 3.0   | 18   | 7.0200          | 0.6899 | 19.0    |
+| 2.9454        | 4.0   | 24   | 7.3333          | 0.2191 | 19.0    |
+| 2.7918        | 5.0   | 30   | 7.5745          | 0.4671 | 12.0    |
+| 3.5645        | 6.0   | 36   | 6.3676          | 0.0    | 19.0    |
+| 3.0885        | 7.0   | 42   | 7.0359          | 0.6908 | 19.0    |
+| 3.5374        | 8.0   | 48   | 6.8709          | 0.1154 | 12.3333 |
+| 3.3746        | 9.0   | 54   | 6.4090          | 0.0    | 19.0    |
+| 2.5927        | 10.0  | 60   | 6.7357          | 0.6381 | 19.0    |
+| 2.581         | 11.0  | 66   | 6.5953          | 0.2635 | 19.0    |
+| 4.1786        | 12.0  | 72   | 7.8617          | 0.2068 | 19.0    |
+| 2.8545        | 13.0  | 78   | 6.2553          | 0.1628 | 19.0    |
+| 2.8925        | 14.0  | 84   | 6.6297          | 0.612  | 19.0    |
+| 3.2424        | 15.0  | 90   | 7.0312          | 0.7377 | 19.0    |
+| 2.379         | 16.0  | 96   | 6.9121          | 0.6562 | 19.0    |
+| 2.2356        | 17.0  | 102  | 6.9446          | 0.2759 | 15.0    |
+| 3.0548        | 18.0  | 108  | 7.5770          | 0.1529 | 19.0    |
+| 2.4637        | 19.0  | 114  | 7.1444          | 0.4497 | 19.0    |
+| 2.96          | 20.0  | 120  | 6.8181          | 0.3779 | 11.0    |
+| 2.2016        | 21.0  | 126  | 6.6893          | 0.6562 | 19.0    |
+| 1.9774        | 22.0  | 132  | 7.3802          | 0.3807 | 19.0    |
+| 1.6734        | 23.0  | 138  | 6.7319          | 0.5405 | 19.0    |
+| 3.1958        | 24.0  | 144  | 7.1645          | 1.2379 | 19.0    |
+| 3.1363        | 25.0  | 150  | 7.7097          | 0.3794 | 19.0    |
+| 2.4353        | 26.0  | 156  | 6.9324          | 0.2522 | 14.0    |
+| 2.8675        | 27.0  | 162  | 6.7989          | 0.1488 | 19.0    |
+| 1.7486        | 28.0  | 168  | 7.1052          | 0.7123 | 19.0    |
+| 2.775         | 29.0  | 174  | 7.0195          | 0.7393 | 19.0    |
+| 1.8752        | 30.0  | 180  | 6.9133          | 0.2119 | 19.0    |
+| 1.7576        | 31.0  | 186  | 7.2143          | 0.2641 | 19.0    |
+| 2.2793        | 32.0  | 192  | 7.0029          | 1.1166 | 19.0    |
+| 1.98          | 33.0  | 198  | 6.9954          | 0.5348 | 19.0    |
+| 1.4242        | 34.0  | 204  | 7.5163          | 0.2088 | 19.0    |
+| 2.413         | 35.0  | 210  | 7.0622          | 0.1433 | 19.0    |
+| 1.2191        | 36.0  | 216  | 7.0088          | 0.5307 | 12.0    |
+| 1.5944        | 37.0  | 222  | 7.7706          | 0.1948 | 19.0    |
+| 1.0044        | 38.0  | 228  | 7.7163          | 0.8485 | 18.4286 |
+| 1.4428        | 39.0  | 234  | 7.4919          | 0.6033 | 19.0    |
+| 3.0175        | 40.0  | 240  | 7.4158          | 0.5109 | 19.0    |
+| 1.3632        | 41.0  | 246  | 6.9819          | 0.4326 | 11.0    |
+| 1.8384        | 42.0  | 252  | 7.0156          | 0.6215 | 18.2381 |
+| 1.3237        | 43.0  | 258  | 7.2082          | 0.4826 | 19.0    |
+| 1.1516        | 44.0  | 264  | 7.5088          | 0.4745 | 18.8571 |
+| 1.3893        | 45.0  | 270  | 7.7298          | 0.4527 | 19.0    |
+| 1.0125        | 46.0  | 276  | 7.8458          | 0.832  | 14.0    |
+| 0.8954        | 47.0  | 282  | 7.9101          | 0.7754 | 17.5714 |
+| 1.8111        | 48.0  | 288  | 7.9713          | 0.6899 | 19.0    |
+| 1.2008        | 49.0  | 294  | 7.9821          | 0.6899 | 19.0    |
+| 1.5131        | 50.0  | 300  | 7.9807          | 0.6899 | 19.0    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 1.13.1+cu117
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/mt5-large",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "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:cd6adf4b6cdf1724dfb4034b3ba6f79ed33c7d942aa4d11896755a0121048ee0
+size 4918393736

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 sha256:5b4bf09eaf556bc5f67a5eea3864678171ca36d6a0d079191aebbcc71795ec0d
+size 4347