Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: akrishnan1/arxiv_summarization_model
+base_model: google-t5/t5-small
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,16 +13,16 @@ probably proofread and complete it, then remove this comment. -->
 
 # akrishnan1/arxiv_summarization_model
 
-This model is a fine-tuned version of [akrishnan1/arxiv_summarization_model](https://huggingface.co/akrishnan1/arxiv_summarization_model) on an unknown dataset.
+This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.7649
-- Validation Loss: 2.7152
-- Train Rouge1: 17.4143
-- Train Rouge2: 6.1880
-- Train Rougel: 13.5825
-- Train Rougelsum: 15.6683
+- Train Loss: 2.6862
+- Validation Loss: 2.4424
+- Train Rouge1: 17.9778
+- Train Rouge2: 6.7295
+- Train Rougel: 14.3327
+- Train Rougelsum: 16.3045
 - Train Gen Len: 19.0
-- Epoch: 2
+- Epoch: 0
 
 ## Model description
 
@@ -48,9 +48,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
 |:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
-| 2.8019     | 2.7361          | 17.1985      | 6.1226       | 13.4386      | 15.8710         | 19.0          | 0     |
-| 2.7832     | 2.7251          | 17.3981      | 6.0631       | 13.4450      | 15.8012         | 19.0          | 1     |
-| 2.7649     | 2.7152          | 17.4143      | 6.1880       | 13.5825      | 15.6683         | 19.0          | 2     |
+| 2.6862     | 2.4424          | 17.9778      | 6.7295       | 14.3327      | 16.3045         | 19.0          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "akrishnan1/arxiv_summarization_model",
+  "_name_or_path": "google-t5/t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

logs/train/events.out.tfevents.1714514322.cf05c62b2ebf.1206.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde5968255b4f83c7437e727901af32deb4be2e8b39e6cbbaf1ec97fcd2f544e
+size 78

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f51da9715ce106dcd2e5f15567f1f1c302a983ad04d7f675a8a1f43d91ac65b6
+oid sha256:1ce6f767e3f4fee49c37a5065fb8570f04ff6447c2187c321dc7632943c534c6
 size 373902664

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -930,12 +930,8 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "max_length": 128,
   "model_max_length": 512,
   "pad_token": "<pad>",
-  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }