Training complete!

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: t5-small
+base_model: t5-base
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # receipt-core-model
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4566
+- Loss: 8.6191
 
 ## Model description
 
@@ -35,33 +35,31 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.001
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
 - 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: 100
+- num_epochs: 200
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.6391        | 1.0   | 8    | 1.9149          |
-| 1.1508        | 2.0   | 16   | 1.4115          |
-| 0.5832        | 3.0   | 24   | 1.3418          |
-| 0.3521        | 4.0   | 32   | 1.3398          |
-| 0.262         | 5.0   | 40   | 1.3215          |
-| 0.2127        | 6.0   | 48   | 1.3763          |
-| 0.1671        | 7.0   | 56   | 1.4019          |
-| 0.1425        | 8.0   | 64   | 1.4218          |
-| 0.1332        | 9.0   | 72   | 1.4471          |
-| 0.1183        | 10.0  | 80   | 1.4566          |
+| No log        | 0     | 0    | 8.6191          |
+| No log        | 0     | 0    | 8.6191          |
+| No log        | 0     | 0    | 8.6191          |
+| No log        | 0     | 0    | 8.6191          |
+| No log        | 0     | 0    | 8.6191          |
+| No log        | 0     | 0    | 8.6191          |
 
 
 ### Framework versions
 
 - Transformers 4.48.1
-- Pytorch 2.5.1+cu124
+- Pytorch 2.6.0+cu124
 - Datasets 3.2.0
 - Tokenizers 0.21.0

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34218b4fe92e3965b4b2c788b88b493c1d924485617d9f2bc695a46ba0bea540
-size 242041896
+oid sha256:cc2e7c858126b4fca7136693c76d392df0e8da05f58f3f06edee52f20dcadd96
+size 891644712

special_tokens_map.json

@@ -101,25 +101,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "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": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -928,11 +928,11 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_ids": 100,
   "extra_special_tokens": {},
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed87c7836f9d14cd0f9067ce05ebe69c735622017e7f91dd4deeb7fef1b3460
-size 5432
+oid sha256:50b395219fe48af3debdf0965de7246070b7a1aa85e4b029897567e13fd5f236
+size 5496