End of training

README.md

@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.7924
-- Rouge1: 19.257
-- Rouge2: 16.2211
-- Rougel: 19.1608
-- Rougelsum: 19.0681
+- Loss: 0.8955
+- Rouge1: 16.29
+- Rouge2: 13.1077
+- Rougel: 16.322
+- Rougelsum: 16.301
 - Gen Len: 19.0
 
 ## Model description
@@ -42,24 +42,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 35   | 0.8425          | 18.4127 | 15.0168 | 18.2095 | 18.2336   | 19.0    |
-| No log        | 2.0   | 70   | 0.7924          | 19.257  | 16.2211 | 19.1608 | 19.0681   | 19.0    |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2  | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:------:|:---------:|:-------:|
+| No log        | 1.0   | 70   | 0.8955          | 16.29  | 13.1077 | 16.322 | 16.301    | 19.0    |
 
 
 ### Framework versions
 
-- Transformers 4.36.1
+- Transformers 4.36.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.15.0
 - Tokenizers 0.15.0

config.json

@@ -56,7 +56,7 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.36.1",
+  "transformers_version": "4.36.2",
   "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": "4.36.1"
+  "transformers_version": "4.36.2"
 }

logs/events.out.tfevents.1703027245.5556ec9213c3.9756.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aece2ba2c239f153002ec37a11067f494a1a54150027084932a01bd980ee38a6
+size 10796

logs/events.out.tfevents.1703027499.5556ec9213c3.9756.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691f0c9bccec200efc1eed415faccca94c4635857e5d15212336cca33474dc8c
+size 5962

logs/events.out.tfevents.1703030521.5556ec9213c3.9756.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674f1e6eb79213afccfca4474d3a2e45206ec84a188c0e924a05ceadb02d1937
+size 6333

logs/events.out.tfevents.1703033346.5556ec9213c3.9756.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a6f748aeca38d2e2edfe6d8f6fceec67116ddcc0b4b83249bd9055384fa0b68
+size 603

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d2f791c9586d50f222b24573f377e4668037c94728412d086920d9a595f085
+oid sha256:caef9b8bcc2881402f068cf91c31bac5783f2ea5eb84a09f5f15c40599c40a08
 size 990345064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05c1fadac25e8d5bb19eb7f417dd2ba99cbf65f7aaa9c0c050993715b31fe81
+oid sha256:df93c35e33d4e77fbfabecd3dc4a30221465cd21776b288b530cdad359530a1e
 size 4920