End of training

README.md

@@ -1,60 +1,60 @@
----
-library_name: transformers
-license: apache-2.0
-base_model: google/mt5-small
-tags:
-- generated_from_trainer
-model-index:
-- name: mt5-small-spelling_aws
-  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. -->
-
-# mt5-small-spelling_aws
-
-This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 8.1457
-
-## 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: 5
-- eval_batch_size: 5
-- seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- num_epochs: 3
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 23.7553       | 1.0   | 16   | 12.6564         |
-| 16.551        | 2.0   | 32   | 8.1747          |
-| 16.9482       | 3.0   | 48   | 8.1457          |
-
-
-### Framework versions
-
-- Transformers 4.48.1
-- Pytorch 2.5.1+cu124
-- Datasets 3.2.0
-- Tokenizers 0.21.0
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/mt5-small
+tags:
+- generated_from_trainer
+model-index:
+- name: mt5-small-spelling_aws
+  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. -->
+
+# mt5-small-spelling_aws
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.4578
+
+## 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: 5
+- eval_batch_size: 5
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 18.9688       | 1.0   | 16   | 11.7121         |
+| 17.0706       | 2.0   | 32   | 10.7868         |
+| 15.6808       | 3.0   | 48   | 10.4578         |
+
+
+### Framework versions
+
+- Transformers 4.48.1
+- Pytorch 2.0.1+cu118
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -1,32 +1,32 @@
-{
-  "_name_or_path": "google/mt5-small",
-  "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": 0.1,
-  "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": 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": "4.48.1",
-  "use_cache": true,
-  "vocab_size": 250112
-}
+{
+  "_name_or_path": "google/mt5-small",
+  "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": 0.1,
+  "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": 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": "4.48.1",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -1,7 +1,7 @@
-{
-  "_from_model_config": true,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
-  "transformers_version": "4.48.1"
-}
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.48.1"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6201a10282ac113df1d3aa1d0b8fac74c4d011f3929749bb68a7178b09ad13
+oid sha256:4b448fd2e05c3d5ad828d2d613e4822c7ea34afb1b34b3f3bc0092a5c2804823
 size 1200729512

special_tokens_map.json

@@ -1,23 +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
-  }
-}
+{
+  "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
+  }
+}

tokenizer_config.json

@@ -1,40 +1,40 @@
-{
-  "add_prefix_space": true,
-  "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": false,
-  "eos_token": "</s>",
-  "extra_ids": 0,
-  "extra_special_tokens": {},
-  "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "MT5Tokenizer",
-  "unk_token": "<unk>"
-}
+{
+  "add_prefix_space": true,
+  "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": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "MT5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c7d37a616372bd7b4c6e16738ca1db6c0ad226bd0f579c4f94e6e822445670d
-size 5368
+oid sha256:574bb98b56ed106f9c8ef97d170a94a28e19af29ecb95390557b5a017ec2c5a8
+size 4923