End of training

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: mHossain/bangla-para-v3-500000
+license: apache-2.0
+base_model: google/mt5-base
 tags:
 - generated_from_trainer
 metrics:
@@ -14,14 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bangla_idiom_generation_v1
 
-This model is a fine-tuned version of [mHossain/bangla-para-v3-500000](https://huggingface.co/mHossain/bangla-para-v3-500000) on an unknown dataset.
+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: nan
 - Rouge1: 0.0
 - Rouge2: 0.0
 - Rougel: 0.0
 - Rougelsum: 0.0
-- Gen Len: 0.0
+- Gen Len: 6.6947
 
 ## Model description
 
@@ -49,17 +50,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5000
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 0.99  | 56   | nan             | 0.0    | 0.0    | 0.0    | 0.0       | 8.6062  |
-| No log        | 2.0   | 113  | nan             | 0.0    | 0.0    | 0.0    | 0.0       | 8.6018  |
-| No log        | 2.99  | 169  | nan             | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 4.0   | 226  | nan             | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 4.96  | 280  | nan             | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 0.99  | 56   | nan             | 0.0    | 0.0    | 0.0    | 0.0       | 6.6947  |
+| No log        | 2.0   | 113  | nan             | 0.0    | 0.0    | 0.0    | 0.0       | 6.6947  |
+| No log        | 2.97  | 168  | nan             | 0.0    | 0.0    | 0.0    | 0.0       | 6.6947  |
 
 
 ### Framework versions

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "mHossain/bangla-para-v3-500000",
+  "_name_or_path": "google/mt5-base",
   "architectures": [
-    "T5ForConditionalGeneration"
+    "MT5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 2048,
@@ -12,12 +12,11 @@
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
-  "gradient_checkpointing": false,
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
+  "model_type": "mt5",
   "num_decoder_layers": 12,
   "num_heads": 12,
   "num_layers": 12,
@@ -26,8 +25,9 @@
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.33.3",
   "use_cache": true,
-  "vocab_size": 32100
+  "vocab_size": 250112
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1608a9f6e173e6796be86bf339142a11ddd069615599425173a36f97938b1aec
-size 990236853
+oid sha256:e2ca6d2561d7c2deb19e574d655a10408dbe061ceafcc98d3791baf9fd99f2d8
+size 2329702581

special_tokens_map.json

@@ -1,106 +1,4 @@
 {
-  "additional_special_tokens": [
-    "<extra_id_0>",
-    "<extra_id_1>",
-    "<extra_id_2>",
-    "<extra_id_3>",
-    "<extra_id_4>",
-    "<extra_id_5>",
-    "<extra_id_6>",
-    "<extra_id_7>",
-    "<extra_id_8>",
-    "<extra_id_9>",
-    "<extra_id_10>",
-    "<extra_id_11>",
-    "<extra_id_12>",
-    "<extra_id_13>",
-    "<extra_id_14>",
-    "<extra_id_15>",
-    "<extra_id_16>",
-    "<extra_id_17>",
-    "<extra_id_18>",
-    "<extra_id_19>",
-    "<extra_id_20>",
-    "<extra_id_21>",
-    "<extra_id_22>",
-    "<extra_id_23>",
-    "<extra_id_24>",
-    "<extra_id_25>",
-    "<extra_id_26>",
-    "<extra_id_27>",
-    "<extra_id_28>",
-    "<extra_id_29>",
-    "<extra_id_30>",
-    "<extra_id_31>",
-    "<extra_id_32>",
-    "<extra_id_33>",
-    "<extra_id_34>",
-    "<extra_id_35>",
-    "<extra_id_36>",
-    "<extra_id_37>",
-    "<extra_id_38>",
-    "<extra_id_39>",
-    "<extra_id_40>",
-    "<extra_id_41>",
-    "<extra_id_42>",
-    "<extra_id_43>",
-    "<extra_id_44>",
-    "<extra_id_45>",
-    "<extra_id_46>",
-    "<extra_id_47>",
-    "<extra_id_48>",
-    "<extra_id_49>",
-    "<extra_id_50>",
-    "<extra_id_51>",
-    "<extra_id_52>",
-    "<extra_id_53>",
-    "<extra_id_54>",
-    "<extra_id_55>",
-    "<extra_id_56>",
-    "<extra_id_57>",
-    "<extra_id_58>",
-    "<extra_id_59>",
-    "<extra_id_60>",
-    "<extra_id_61>",
-    "<extra_id_62>",
-    "<extra_id_63>",
-    "<extra_id_64>",
-    "<extra_id_65>",
-    "<extra_id_66>",
-    "<extra_id_67>",
-    "<extra_id_68>",
-    "<extra_id_69>",
-    "<extra_id_70>",
-    "<extra_id_71>",
-    "<extra_id_72>",
-    "<extra_id_73>",
-    "<extra_id_74>",
-    "<extra_id_75>",
-    "<extra_id_76>",
-    "<extra_id_77>",
-    "<extra_id_78>",
-    "<extra_id_79>",
-    "<extra_id_80>",
-    "<extra_id_81>",
-    "<extra_id_82>",
-    "<extra_id_83>",
-    "<extra_id_84>",
-    "<extra_id_85>",
-    "<extra_id_86>",
-    "<extra_id_87>",
-    "<extra_id_88>",
-    "<extra_id_89>",
-    "<extra_id_90>",
-    "<extra_id_91>",
-    "<extra_id_92>",
-    "<extra_id_93>",
-    "<extra_id_94>",
-    "<extra_id_95>",
-    "<extra_id_96>",
-    "<extra_id_97>",
-    "<extra_id_98>",
-    "<extra_id_99>"
-  ],
   "eos_token": "</s>",
   "pad_token": "<pad>",
   "unk_token": "<unk>"

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dcab96935a2a51b1461c84e44c952ea8a3640c8bc3e2c6ae7a21d855454ae27
-size 1111492
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae9c57270a3595d4f2d117d70394f1a32d6788aa4fa1d50505064c5f1df2acc
-size 2741559
+oid sha256:db89e268649033b2f206501b13ff4b4edb14f23e84934fb956db725fcacdead8
+size 16330467

tokenizer_config.json

@@ -1,116 +1,12 @@
 {
-  "additional_special_tokens": [
-    "<extra_id_0>",
-    "<extra_id_1>",
-    "<extra_id_2>",
-    "<extra_id_3>",
-    "<extra_id_4>",
-    "<extra_id_5>",
-    "<extra_id_6>",
-    "<extra_id_7>",
-    "<extra_id_8>",
-    "<extra_id_9>",
-    "<extra_id_10>",
-    "<extra_id_11>",
-    "<extra_id_12>",
-    "<extra_id_13>",
-    "<extra_id_14>",
-    "<extra_id_15>",
-    "<extra_id_16>",
-    "<extra_id_17>",
-    "<extra_id_18>",
-    "<extra_id_19>",
-    "<extra_id_20>",
-    "<extra_id_21>",
-    "<extra_id_22>",
-    "<extra_id_23>",
-    "<extra_id_24>",
-    "<extra_id_25>",
-    "<extra_id_26>",
-    "<extra_id_27>",
-    "<extra_id_28>",
-    "<extra_id_29>",
-    "<extra_id_30>",
-    "<extra_id_31>",
-    "<extra_id_32>",
-    "<extra_id_33>",
-    "<extra_id_34>",
-    "<extra_id_35>",
-    "<extra_id_36>",
-    "<extra_id_37>",
-    "<extra_id_38>",
-    "<extra_id_39>",
-    "<extra_id_40>",
-    "<extra_id_41>",
-    "<extra_id_42>",
-    "<extra_id_43>",
-    "<extra_id_44>",
-    "<extra_id_45>",
-    "<extra_id_46>",
-    "<extra_id_47>",
-    "<extra_id_48>",
-    "<extra_id_49>",
-    "<extra_id_50>",
-    "<extra_id_51>",
-    "<extra_id_52>",
-    "<extra_id_53>",
-    "<extra_id_54>",
-    "<extra_id_55>",
-    "<extra_id_56>",
-    "<extra_id_57>",
-    "<extra_id_58>",
-    "<extra_id_59>",
-    "<extra_id_60>",
-    "<extra_id_61>",
-    "<extra_id_62>",
-    "<extra_id_63>",
-    "<extra_id_64>",
-    "<extra_id_65>",
-    "<extra_id_66>",
-    "<extra_id_67>",
-    "<extra_id_68>",
-    "<extra_id_69>",
-    "<extra_id_70>",
-    "<extra_id_71>",
-    "<extra_id_72>",
-    "<extra_id_73>",
-    "<extra_id_74>",
-    "<extra_id_75>",
-    "<extra_id_76>",
-    "<extra_id_77>",
-    "<extra_id_78>",
-    "<extra_id_79>",
-    "<extra_id_80>",
-    "<extra_id_81>",
-    "<extra_id_82>",
-    "<extra_id_83>",
-    "<extra_id_84>",
-    "<extra_id_85>",
-    "<extra_id_86>",
-    "<extra_id_87>",
-    "<extra_id_88>",
-    "<extra_id_89>",
-    "<extra_id_90>",
-    "<extra_id_91>",
-    "<extra_id_92>",
-    "<extra_id_93>",
-    "<extra_id_94>",
-    "<extra_id_95>",
-    "<extra_id_96>",
-    "<extra_id_97>",
-    "<extra_id_98>",
-    "<extra_id_99>"
-  ],
+  "additional_special_tokens": null,
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
-  "extra_ids": 100,
-  "max_length": 256,
-  "model_max_length": 512,
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d7efdc37520569424fe4eed96c8c208978aaede0c5bf31ae1df34d4cf312ac8
+oid sha256:fc1271bc9048d835a02ebb57f946bd307f8e92d53eb49033d4bf383964f1dea1
 size 4219