sjpritchard/gemma3-cpt

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # cpt
 
 This model is a fine-tuned version of [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0570
 
 ## Model description
 
@@ -34,10 +36,10 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 16
 - total_train_batch_size: 16
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
@@ -46,6 +48,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.2493        | 2.7160 | 100  | 1.0570          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70fb454e1be752517fd3934bac841cdd2105ed2acab8c2f6e96d054660eb0d78
+oid sha256:7f7654b2b3f52e7b847fb0dc5eae2eb78bebcf24770ce6a6afa6cbbbd4393f76
 size 1999811208

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091e3cf7f0e56c10d7383f000a34ef2824e95368e43def66837540b0550b6f83
-size 33384832
+oid sha256:9973f4bca203c8d837008e3f9c0629e3306414802214fe017994420cf9391c4f
+size 33384836

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c5dd3ea81aeebcaf0942e5647eae70c5fe9b66eb071cdf02603a9b0b895526
+oid sha256:66af19fe38f80bb1031cdc6c00c1a4577307f0e74af65cf63db505b08e23270b
 size 5649