End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: gpt2
+license: other
+base_model: facebook/opt-125m
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bertQA
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0127
 
 ## Model description
 
@@ -32,18 +34,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: linear
 - num_epochs: 1
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0128        | 1.0   | 6496 | 0.0127          |
 
 
 ### Framework versions

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.40.2"
 }

runs/May15_18-34-55_35c2d6acf988/events.out.tfevents.1715801650.35c2d6acf988.1694.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ac94eb920f3d0ec8bc1d1823409dbb678439a2c66de98f41dcd175b874fe1b
+size 359