End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/bigbird-pegasus-large-pubmed
+base_model: sharmadhruv/my_awesome_qa_model
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_awesome_qa_model
 
-This model is a fine-tuned version of [google/bigbird-pegasus-large-pubmed](https://huggingface.co/google/bigbird-pegasus-large-pubmed) on an unknown dataset.
+This model is a fine-tuned version of [sharmadhruv/my_awesome_qa_model](https://huggingface.co/sharmadhruv/my_awesome_qa_model) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.9818
+- Loss: 4.2362
 
 ## Model description
 
@@ -40,13 +40,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.9967        | 1.0   | 1000 | 4.9818          |
+| 4.6597        | 1.0   | 1000 | 4.5738          |
+| 4.4218        | 2.0   | 2000 | 4.3305          |
+| 4.2711        | 3.0   | 3000 | 4.2362          |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/bigbird-pegasus-large-pubmed",
+  "_name_or_path": "sharmadhruv/my_awesome_qa_model",
   "activation_dropout": 0.0,
   "activation_function": "gelu_new",
   "architectures": [

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7ed193bb74e6c8bcc91a0192476909e0429fbb77da6a1d6ebfd018df0e73206
+oid sha256:901e75d1b23924d722789b981a20af561a8db9e53025a03fa1e8b25ccfac46ed
 size 2307633752

tokenizer_config.json

@@ -64,10 +64,17 @@
   "eos_token": "</s>",
   "mask_token": "[MASK]",
   "mask_token_sent": null,
+  "max_length": 384,
   "model_max_length": 4096,
   "offset": 0,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "tokenizer_class": "PegasusTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f30372cc0156aa8c95ac4e76aa3db410490a4e31eacda6fe1f0efc0e29255ca8
+oid sha256:55e55e7db5b922b038a9d340b566a1fc89b687e43de16971047fc6dc593092bb
 size 5112