Model save

README.md

@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mnoukhov/pythia160m-sft-tldr](https://huggingface.co/mnoukhov/pythia160m-sft-tldr) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5486
-- Accuracy: 0.7121
+- Loss: 0.5399
+- Accuracy: 0.7213
 
 ## Model description
 
@@ -45,8 +45,8 @@ The following hyperparameters were used during training:
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 4
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 256
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
 - total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| No log        | 0.2012 | 73   | 0.5667          | 0.6998   |
-| 0.6204        | 0.4025 | 146  | 0.5560          | 0.7120   |
-| 0.5593        | 0.6037 | 219  | 0.5532          | 0.7078   |
-| 0.5593        | 0.8050 | 292  | 0.5486          | 0.7121   |
+| 0.596         | 0.2006 | 291  | 0.5819          | 0.6923   |
+| 0.5382        | 0.4011 | 582  | 0.5513          | 0.7151   |
+| 0.505         | 0.6017 | 873  | 0.5480          | 0.7141   |
+| 0.4836        | 0.8022 | 1164 | 0.5399          | 0.7213   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9c43592c1a56d23791aa6c6dff2372eec63304787d3761f7be097f2f125558
+oid sha256:b287adaea768b5fa7d4fdf1bb33d5fee3e53393b29a3e2868b3ebb29d710a49e
 size 494777904