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 +1,79 @@
+---
+language:
+- bn
+license: apache-2.0
+base_model: bigscience/mt0-small
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: Tahmid37/Tahmid37/mt0-small-text-to-ipa-v-final-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. -->
+
+# Tahmid37/Tahmid37/mt0-small-text-to-ipa-v-final-1
+
+This model is a fine-tuned version of [bigscience/mt0-small](https://huggingface.co/bigscience/mt0-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0536
+- Wer: 0.0358
+
+## 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: 0.001
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2000
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.1705        | 0.17  | 4000  | 0.0798          | 0.0763 |
+| 0.1399        | 0.34  | 8000  | 0.0799          | 0.0728 |
+| 0.1359        | 0.51  | 12000 | 0.0818          | 0.0778 |
+| 0.1323        | 0.67  | 16000 | 0.0818          | 0.0750 |
+| 0.1248        | 0.84  | 20000 | 0.0777          | 0.0683 |
+| 0.1217        | 1.01  | 24000 | 0.0768          | 0.0675 |
+| 0.0984        | 1.18  | 28000 | 0.0767          | 0.0691 |
+| 0.0937        | 1.35  | 32000 | 0.0734          | 0.0617 |
+| 0.0951        | 1.52  | 36000 | 0.0720          | 0.0590 |
+| 0.0884        | 1.69  | 40000 | 0.0676          | 0.0513 |
+| 0.0854        | 1.86  | 44000 | 0.0639          | 0.0491 |
+| 0.0836        | 2.02  | 48000 | 0.0629          | 0.0453 |
+| 0.0625        | 2.19  | 52000 | 0.0611          | 0.0443 |
+| 0.0606        | 2.36  | 56000 | 0.0598          | 0.0418 |
+| 0.0568        | 2.53  | 60000 | 0.0555          | 0.0383 |
+| 0.0521        | 2.7   | 64000 | 0.0553          | 0.0375 |
+| 0.0537        | 2.87  | 68000 | 0.0536          | 0.0358 |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Tahmid37/mt0-small-text-to-ipa-v2",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.2,
+  "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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.34.1",
+  "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": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da90be4e04d548d78673e37b36252d887de3cb45ce99c60d38050f5d8eb687eb
+size 1200772613

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:d842e6af904403ce6bf8ee58faffd9abad1682513c28c27454d81dc67eaf296c
+size 16315149

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "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,
+  "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 sha256:96af243ee0e9c2c156952282d0a95037c5316c3b3a3e4c81eec7afe2f5879259
+size 4283