End of training

README.md

@@ -78,7 +78,7 @@ resume_from_checkpoint: null
 s2_attention: null
 sample_packing: false
 saves_per_epoch: 1
-sequence_len: 2048
+sequence_len: 3072
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -103,7 +103,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [migtissera/Tess-v2.5-Phi-3-medium-128k-14B](https://huggingface.co/migtissera/Tess-v2.5-Phi-3-medium-128k-14B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9605
+- Loss: 0.9849
 
 ## Model description
 
@@ -135,7 +135,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.6037        | 0.0001 | 10   | 0.9605          |
+| 0.6232        | 0.0001 | 10   | 0.9849          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_up_proj",
     "o_proj",
-    "qkv_proj"
+    "qkv_proj",
+    "down_proj",
+    "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c22a8e3355c58e313a250838168aef40a6f2cd1d4993dccc693c90f9b44e027
+oid sha256:007ce58dbafc471d3589fc7cf59213bc4df296e525bf2b12b13418ed5669059e
 size 222938570

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080266c775bcabbe53fe7ca8e5027836b5df61877e45ced7b9a233b0ff0f45d5
+oid sha256:7fa3d21ebbdca5a713d5e1b070ed05604762d25f849cdda41bb04e8591a1aa13
 size 222865880

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58eb57f3917b507923ea755e030c1beca7a855fad468c4aad6fe3913785ca85
+oid sha256:c2c64a0499951c50351a09e07571b6e2d6b303197421e5759275754f342fd5b8
 size 6776