llm/llama38binstruct-summary-100s

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4113
+- Loss: 1.9040
 
 ## Model description
 
@@ -47,17 +47,17 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
-- lr_scheduler_warmup_steps: 10
+- lr_scheduler_warmup_steps: 20
 - training_steps: 100
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6248        | 10.0  | 25   | 1.7454          |
-| 0.0129        | 20.0  | 50   | 2.0997          |
-| 0.0048        | 30.0  | 75   | 2.3748          |
-| 0.0035        | 40.0  | 100  | 2.4113          |
+| 2.2823        | 10.0  | 25   | 1.9040          |
+| 2.2883        | 20.0  | 50   | 1.9040          |
+| 2.2944        | 30.0  | 75   | 1.9040          |
+| 2.2857        | 40.0  | 100  | 1.9040          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9a36074c57992daf0f50184679987c713bb570eef1e0c528792fbd4b6a82d2
-size 167832240
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

runs/Jun19_07-40-29_0113f146e29c/events.out.tfevents.1718782840.0113f146e29c.57332.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a532b72c9097c994946e75c93cd72957de50d65b748d63ddc4a46e6b50186e5e
+size 9237

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6a133b2959b8874953eff0eb1fd4348bc71812a1110398b0cc36cbdf2de4d3
+oid sha256:f52e5fe216009eec8b3e369fae845d481ba7f79d6486b867f01d9e87147cc361
 size 5432