Training complete!

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/flan-t5-small
+base_model: google/flan-t5-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # t5_samsum
 
-This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.6740
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
 
 ## Model description
 
@@ -35,21 +33,17 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 128
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 5
+- num_epochs: 7
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.7622        | 4.3431 | 500  | 1.6740          |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google/flan-t5-small",
+  "_name_or_path": "google/flan-t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 1024,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 8,
-  "num_heads": 6,
-  "num_layers": 8,
+  "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 sha256:7a81f701959e64809aa8097357af610a1b1c8e0fb8080de3b3f15097f38ef8cd
-size 307867048
+oid sha256:2abe1fe1207202a4099c23c0c42fa1c03a203f069397ca1a747100a67cb950c2
+size 990345064

runs/Apr28_05-00-55_1a8962b2312d/events.out.tfevents.1714280460.1a8962b2312d.198.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe05a7100c1f515dc68aaf71e5bc765317795e65864222ae533504540d12714d
+size 5540

runs/Apr28_05-01-27_1a8962b2312d/events.out.tfevents.1714280490.1a8962b2312d.198.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54fa2fe2fe9fce1b0323623308c11d4338404e929717cab4804cb1a1c5caf0d2
+size 10992

runs/Apr28_05-18-06_1a8962b2312d/events.out.tfevents.1714281489.1a8962b2312d.198.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f981ce99b2440b18249d80f89bac6f9d6a05d1b6e3caf3ebd163466a1a7921
+size 16441

runs/Apr28_05-18-06_1a8962b2312d/events.out.tfevents.1714281620.1a8962b2312d.198.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba821bd1083214ffb3b141d6f99f3c33ec846de418c7d792596ce7ad0cd601f
+size 5893

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8736c5e7d9454fbfaa0e7970cbda73c4ec93c51f0da1049c0ae582ffdf9b88
+oid sha256:40019762bd963d141d7d0426ec01ebcf753e9935dd6e0fc2e1f62b6daf71044d
 size 4984