End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: t5-small
+base_model: google/flan-t5-base
 tags:
 - generated_from_trainer
 metrics:
@@ -15,14 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_awesome_billsum_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 [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.4029
-- Rouge1: 0.1183
-- Rouge2: 0.0471
-- Rougel: 0.1193
-- Rougelsum: 0.1192
-- Gen Len: 19.0
+- Loss: nan
+- Rouge1: 0.1332
+- Rouge2: 0.0347
+- Rougel: 0.1064
+- Rougelsum: 0.1064
+- Gen Len: 16.5
 
 ## Model description
 
@@ -42,8 +42,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 1    | 4.4613          | 0.1183 | 0.0471 | 0.1193 | 0.1192    | 19.0    |
-| No log        | 2.0   | 2    | 4.4263          | 0.1183 | 0.0471 | 0.1193 | 0.1192    | 19.0    |
-| No log        | 3.0   | 3    | 4.4168          | 0.1183 | 0.0471 | 0.1193 | 0.1192    | 19.0    |
-| No log        | 4.0   | 4    | 4.4029          | 0.1183 | 0.0471 | 0.1193 | 0.1192    | 19.0    |
+| No log        | 1.0   | 6    | nan             | 0.1332 | 0.0347 | 0.1064 | 0.1064    | 16.5    |
+| No log        | 2.0   | 12   | nan             | 0.1332 | 0.0347 | 0.1064 | 0.1064    | 16.5    |
+| No log        | 3.0   | 18   | nan             | 0.1332 | 0.0347 | 0.1064 | 0.1064    | 16.5    |
+| No log        | 4.0   | 24   | nan             | 0.1332 | 0.0347 | 0.1064 | 0.1064    | 16.5    |
 
 
 ### Framework versions

config.json

@@ -1,26 +1,26 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "google/flan-t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "relu",
+  "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
+  "is_gated_act": true,
   "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,
@@ -54,6 +54,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.34.0",
   "use_cache": true,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8995b71542d59558e543fee5eb12a3cc2b22bda782f882213a0c96912326d404
-size 242071641
+oid sha256:a9c41f877fe0e15973fabd60eebe3564b42af1d4ff106ce50b28fe6c667b6cb6
+size 990408885

tokenizer_config.json

@@ -932,6 +932,7 @@
   "extra_ids": 100,
   "model_max_length": 512,
   "pad_token": "<pad>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f20c1e1ae813ca76269b2d3ca33858eca2c560adedf441300496fc045bb9e0
+oid sha256:4bbd787da759710f604fb694cd57a2f73c2d8c7c8ddea819bf59feb62becc091
 size 4219