End of training

README.md

@@ -9,18 +9,18 @@ base_model: Aravindan/gpt2out
 datasets:
 - generator
 model-index:
-- name: gpt2coder-instruct
+- name: output_dir
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# gpt2coder-instruct
+# output_dir
 
 This model is a fine-tuned version of [Aravindan/gpt2out](https://huggingface.co/Aravindan/gpt2out) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2879
+- Loss: 2.4231
 
 ## Model description
 
@@ -47,16 +47,14 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 80
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
-- training_steps: 100
+- training_steps: 50
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.624         | 0.0147 | 30   | 2.4234          |
-| 2.5018        | 0.0294 | 60   | 2.3461          |
-| 2.4781        | 0.0441 | 90   | 2.2879          |
+| 2.6346        | 0.0147 | 30   | 2.4231          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ce1a3da80fb0ec2881ee2f099c7cc7de7ce5e529b6eb6d882c412dab2c4232
+oid sha256:3c9d94f5357649f82fb50b00753f4dea566bf93d56c116eafef6e0d4bd7d819b
 size 2362376

runs/Jun13_11-30-16_64efe294a367/events.out.tfevents.1718278359.64efe294a367.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30da07901f6b776cbe9693a17874180f77545ed3e8ea3020debb65208a38c02a
+size 6659

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd68b478a4f85dbd16967cf79e92cf4e7be5afb41510aaffa1744ebf3da8149
+oid sha256:545fdcdfa578c78beef917f63c6d03ca8ab1f74ed19ce0cb794697949e4bb254
 size 5368