dmcooller/neural-schevchenko-ft

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5362
+- Loss: 2.8946
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -44,19 +44,23 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 6
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.2884        | 0.93  | 7    | 2.8684          |
-| 2.5646        | 2.0   | 15   | 2.6798          |
-| 2.7782        | 2.93  | 22   | 2.6071          |
-| 2.3583        | 4.0   | 30   | 2.5528          |
-| 2.6542        | 4.93  | 37   | 2.5394          |
-| 2.2268        | 5.6   | 42   | 2.5362          |
+| 3.4598        | 0.93  | 7    | 3.2557          |
+| 2.9593        | 2.0   | 15   | 3.1634          |
+| 3.2911        | 2.93  | 22   | 3.0877          |
+| 2.8107        | 4.0   | 30   | 3.0155          |
+| 3.1487        | 4.93  | 37   | 2.9706          |
+| 2.7215        | 6.0   | 45   | 2.9352          |
+| 3.0814        | 6.93  | 52   | 2.9147          |
+| 2.6827        | 8.0   | 60   | 2.9008          |
+| 3.0544        | 8.93  | 67   | 2.8953          |
+| 2.3489        | 9.33  | 70   | 2.8946          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6ce7c477223d096b826f49d9c4e3bbb70f69a1efa10b0f61474476f38b0b7b
-size 11542872
+oid sha256:88764e2de12e5ca0e53a87554e507d5b9766f380cf6daa8adaeac59392161157
+size 11543960

runs/Apr08_14-06-27_52ebaf0dfa60/events.out.tfevents.1712585228.52ebaf0dfa60.35.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a46f82bda064354a92bb5870ec904b306b21ad4a9fdc5f073329995d7f0734
+size 5235

runs/Apr08_14-07-49_52ebaf0dfa60/events.out.tfevents.1712585273.52ebaf0dfa60.35.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eacfc1fbbc90f68bfd52eb5d7f1af49f9a2bffda5af725cd5e9befc490e973b7
+size 10313

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa77db5615744e4e59540a3862059b59e4eeaa792e3ae2d2dacea2bbee5afb2
+oid sha256:4ea4b49bc49491b225f433f8404338586ccbce8d3877222bbb263af2b8cef166
 size 4920