End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: google-t5/t5-small
+base_model: google-t5/t5-base
 tags:
 - generated_from_trainer
 metrics:
@@ -16,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # billsum-model
 
-This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
+This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4378
-- Rouge1: 0.1774
-- Rouge2: 0.077
-- Rougel: 0.147
-- Rougelsum: 0.1469
+- Loss: 1.8421
+- Rouge1: 0.1961
+- Rouge2: 0.1049
+- Rougel: 0.1705
+- Rougelsum: 0.1707
 - Gen Len: 19.0
 
 ## Model description
@@ -43,27 +43,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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: 4
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 124  | 2.6318          | 0.1377 | 0.0468 | 0.1119 | 0.1117    | 19.0    |
-| No log        | 2.0   | 248  | 2.4967          | 0.1492 | 0.0559 | 0.1209 | 0.1208    | 19.0    |
-| No log        | 3.0   | 372  | 2.4503          | 0.1735 | 0.075  | 0.1434 | 0.1431    | 19.0    |
-| No log        | 4.0   | 496  | 2.4378          | 0.1774 | 0.077  | 0.147  | 0.1469    | 19.0    |
+| 2.395         | 1.0   | 989  | 1.8823          | 0.193  | 0.1042 | 0.1686 | 0.1688    | 19.0    |
+| 1.9058        | 2.0   | 1978 | 1.8421          | 0.1961 | 0.1049 | 0.1705 | 0.1707    | 19.0    |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.5.0+cu121
-- Datasets 3.0.2
-- Tokenizers 0.19.1
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google-t5/t5-small",
+  "_name_or_path": "google-t5/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,
@@ -55,7 +55,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.46.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b2cc6b1e584d75a20619f7ad4d2aec7d339532ca775fe5f41c0fbeed2a13a3
-size 242041896
+oid sha256:bc6ccfe186305df271191b4c6de49b8e07f67791ec3709806b5cf3def68be8f5
+size 891644712

runs/Nov18_06-25-56_65c9a8d1c9df/events.out.tfevents.1731911158.65c9a8d1c9df.1129.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2dc84ba8f326753bbc6673fa4567680b34589f2958b8831e611fc9e4a020ee8
+size 8192

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

@@ -927,10 +927,10 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "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 sha256:6a8455c3306d3cb790680585116a0bc0daed75a202aead4dbfb84b8519e5932d
-size 5432
+oid sha256:d36a8f82de6a42739757fdc9f5ba2f9a17557791de7167c7689d01d92baca55f
+size 5496