Sarathbabu-Karunanithi/GK_10000

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
 metrics:
@@ -15,13 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # GK_10000
 
-This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9931
-- Rouge1: 0.4006
-- Rouge2: 0.2788
-- Rougel: 0.3740
-- Rougelsum: 0.3800
+- Loss: 1.6340
+- Rouge1: 0.4195
+- Rouge2: 0.3016
+- Rougel: 0.3924
+- Rougelsum: 0.3995
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 2.554         | 1.0   | 875  | 2.0791          | 0.3957 | 0.2732 | 0.3694 | 0.3759    |
-| 2.2115        | 2.0   | 1750 | 2.0134          | 0.3943 | 0.2722 | 0.3670 | 0.3738    |
-| 2.0677        | 3.0   | 2625 | 1.9931          | 0.4006 | 0.2788 | 0.3740 | 0.3800    |
+| 2.1243        | 1.0   | 875  | 1.7023          | 0.4106 | 0.2880 | 0.3827 | 0.3899    |
+| 1.6975        | 2.0   | 1750 | 1.6422          | 0.4231 | 0.3026 | 0.3957 | 0.4025    |
+| 1.495         | 3.0   | 2625 | 1.6340          | 0.4195 | 0.3016 | 0.3924 | 0.3995    |
 
 
 ### 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 sha256:24cac9a1351815e0cfb4c76d37df902788683ba4f9f8d87cda7e1e8b8e5984a7
-size 307867048
+oid sha256:10773ab683b60f1acea55140ba105aa71cccca966a9fafe85a6a36aa555a4b70
+size 990345064

runs/Aug01_16-53-31_1e8d57a22581/events.out.tfevents.1722531220.1e8d57a22581.214.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94266fbacddd4f23bc5b1d43d9f5e5c515d2036b233d1f66766e8570bde77e0d
+size 8681

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9425ce4dab8d315f4de08dccfdcad0e3903e134abcb035548c8fff0121c9aaa7
+oid sha256:9dcb21fd2d9f448ebefa8e68e21fa6b6883588bc1370260e56685f433ff2cbf6
 size 5240