ninagroot/Llama-360Mtest

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 7.2089
+- Loss: 6.0825
 
 ## Model description
 
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 100
+- lr_scheduler_warmup_steps: 10
 - num_epochs: 20
 - mixed_precision_training: Native AMP
 
@@ -48,18 +48,18 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.57  | 1    | 9.6356          |
-| No log        | 1.71  | 3    | 9.5387          |
-| No log        | 2.86  | 5    | 9.3202          |
-| No log        | 4.0   | 7    | 8.9818          |
-| No log        | 4.57  | 8    | 8.7723          |
-| No log        | 5.71  | 10   | 8.3589          |
-| No log        | 6.86  | 12   | 8.0324          |
-| No log        | 8.0   | 14   | 7.7929          |
-| No log        | 8.57  | 15   | 7.7018          |
-| No log        | 9.71  | 17   | 7.5004          |
-| No log        | 10.86 | 19   | 7.3090          |
-| 7.7857        | 11.43 | 20   | 7.2089          |
+| No log        | 0.57  | 1    | 9.5914          |
+| No log        | 1.71  | 3    | 8.7234          |
+| No log        | 2.86  | 5    | 7.9484          |
+| No log        | 4.0   | 7    | 7.4874          |
+| No log        | 4.57  | 8    | 7.2589          |
+| No log        | 5.71  | 10   | 6.8699          |
+| No log        | 6.86  | 12   | 6.4984          |
+| No log        | 8.0   | 14   | 6.3137          |
+| No log        | 8.57  | 15   | 6.2260          |
+| No log        | 9.71  | 17   | 6.1466          |
+| No log        | 10.86 | 19   | 6.0892          |
+| 6.4287        | 11.43 | 20   | 6.0825          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6290bb0785659e04767fe8cdf8c82d1f91f177a264ace29bedf516884d83c4de
+oid sha256:11de8bed84be5a7eac7c265fa9935089fcc5dae14da45b80251f7bb5ee62255c
 size 1408774432

runs/Apr16_13-22-53_gcn20.local.snellius.surf.nl/events.out.tfevents.1713266583.gcn20.local.snellius.surf.nl.2628227.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a965513ebcd50284db2f3832f02c8a078cd84e6dfa61e19860e93b10e2bc4f5
+size 8310

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9642187a459ad7b52158c5702400b6f550ccbc6bfeaae638de778b52a4535a12
+oid sha256:31af086df66532a581d10e9852435b342a8ceebc0a3efd9d4199899841747cd7
 size 4984