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

@@ -1,5 +1,120 @@
 ---
-license: other
-license_name: other
-license_link: LICENSE
+license: apache-2.0
+base_model: eslamxm/mt5-base-finetuned-arur
+tags:
+- generated_from_trainer
+model-index:
+- name: T6
+  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. -->
+
+# T6
+
+This model is a fine-tuned version of [eslamxm/mt5-base-finetuned-arur](https://huggingface.co/eslamxm/mt5-base-finetuned-arur) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5941
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 64
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.2591        | 1.0   | 37   | 0.2616          |
+| 0.1639        | 2.0   | 74   | 0.2497          |
+| 0.1771        | 3.0   | 111  | 0.2448          |
+| 0.1465        | 4.0   | 148  | 0.2486          |
+| 0.1294        | 5.0   | 185  | 0.2499          |
+| 0.118         | 6.0   | 222  | 0.2520          |
+| 0.1014        | 7.0   | 259  | 0.2582          |
+| 0.0986        | 8.0   | 296  | 0.2631          |
+| 0.1021        | 9.0   | 333  | 0.2775          |
+| 0.0783        | 10.0  | 370  | 0.2867          |
+| 0.0699        | 11.0  | 407  | 0.2906          |
+| 0.062         | 12.0  | 444  | 0.3010          |
+| 0.059         | 13.0  | 481  | 0.3144          |
+| 0.0592        | 14.0  | 518  | 0.3265          |
+| 0.0513        | 15.0  | 555  | 0.3365          |
+| 0.0404        | 16.0  | 592  | 0.3550          |
+| 0.0417        | 17.0  | 629  | 0.3552          |
+| 0.0385        | 18.0  | 666  | 0.3682          |
+| 0.0303        | 19.0  | 703  | 0.3728          |
+| 0.0355        | 20.0  | 740  | 0.3947          |
+| 0.0232        | 21.0  | 777  | 0.4208          |
+| 0.024         | 22.0  | 814  | 0.4080          |
+| 0.023         | 23.0  | 851  | 0.4265          |
+| 0.0169        | 24.0  | 888  | 0.4233          |
+| 0.0185        | 25.0  | 925  | 0.4450          |
+| 0.0214        | 26.0  | 962  | 0.4528          |
+| 0.0159        | 27.0  | 999  | 0.4486          |
+| 0.0156        | 28.0  | 1036 | 0.4926          |
+| 0.017         | 29.0  | 1073 | 0.4927          |
+| 0.0137        | 30.0  | 1110 | 0.4886          |
+| 0.0139        | 31.0  | 1147 | 0.5205          |
+| 0.0108        | 32.0  | 1184 | 0.4953          |
+| 0.0136        | 33.0  | 1221 | 0.4925          |
+| 0.0129        | 34.0  | 1258 | 0.5081          |
+| 0.0099        | 35.0  | 1295 | 0.5252          |
+| 0.0116        | 36.0  | 1332 | 0.5241          |
+| 0.0134        | 37.0  | 1369 | 0.5352          |
+| 0.0111        | 38.0  | 1406 | 0.5469          |
+| 0.0089        | 39.0  | 1443 | 0.5618          |
+| 0.0103        | 40.0  | 1480 | 0.5781          |
+| 0.0083        | 41.0  | 1517 | 0.5896          |
+| 0.0091        | 42.0  | 1554 | 0.5287          |
+| 0.0115        | 43.0  | 1591 | 0.5556          |
+| 0.0069        | 44.0  | 1628 | 0.5497          |
+| 0.0069        | 45.0  | 1665 | 0.5896          |
+| 0.0089        | 46.0  | 1702 | 0.5799          |
+| 0.0056        | 47.0  | 1739 | 0.5654          |
+| 0.0072        | 48.0  | 1776 | 0.5683          |
+| 0.0097        | 49.0  | 1813 | 0.5642          |
+| 0.0065        | 50.0  | 1850 | 0.5623          |
+| 0.0073        | 51.0  | 1887 | 0.5906          |
+| 0.0078        | 52.0  | 1924 | 0.5932          |
+| 0.0068        | 53.0  | 1961 | 0.5923          |
+| 0.006         | 54.0  | 1998 | 0.5978          |
+| 0.005         | 55.0  | 2035 | 0.5846          |
+| 0.0082        | 56.0  | 2072 | 0.5886          |
+| 0.0081        | 57.0  | 2109 | 0.5844          |
+| 0.0056        | 58.0  | 2146 | 0.5878          |
+| 0.0069        | 59.0  | 2183 | 0.5890          |
+| 0.0075        | 60.0  | 2220 | 0.5946          |
+| 0.0077        | 61.0  | 2257 | 0.5897          |
+| 0.0064        | 62.0  | 2294 | 0.5908          |
+| 0.0049        | 63.0  | 2331 | 0.5934          |
+| 0.005         | 64.0  | 2368 | 0.5941          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "eslamxm/mt5-base-finetuned-arur",
+  "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 +1,7 @@
+{
+  "_from_model_config": true,
+  "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 sha256:3eed2b531a8f58eb02f8c08ac3a11c78a23ac7b136f0b8ec7e6289e209494197
+size 2329638768

runs/Feb08_09-50-40_02a9afb5e7cd/events.out.tfevents.1707385841.02a9afb5e7cd.734.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f264d6af60b69534f400abf1418fd100635bc7a5ac979e4627d4570d8b3f354d
+size 100545

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

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 sha256:589a163f1112fea5f00676c01e130b8e51806479ec7c94f8e0c0e7182053e12b
+size 16315477

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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,
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5715b55d9c2c539d8cf47951ea43c252b83660f019293555a5d8fb31665bf43
+size 4536