Model save

README.md

@@ -1,13 +1,10 @@
 ---
 library_name: peft
 tags:
-- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
 base_model: NorLLM-AI/NorMistral-7B
-datasets:
-- hugodk-sch/aftonposten_title_prefs
 model-index:
 - name: norllm-ai-normistral-7b-align-scan
   results: []
@@ -18,17 +15,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # norllm-ai-normistral-7b-align-scan
 
-This model is a fine-tuned version of [data/norllm-ai-normistral-7b-sft-qlora](https://huggingface.co/data/norllm-ai-normistral-7b-sft-qlora) on the hugodk-sch/aftonposten_title_prefs dataset.
+This model is a fine-tuned version of [NorLLM-AI/NorMistral-7B](https://huggingface.co/NorLLM-AI/NorMistral-7B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4787
-- Rewards/chosen: -0.2528
-- Rewards/rejected: -0.4471
-- Rewards/accuracies: 0.5602
-- Rewards/margins: 0.1943
-- Logps/rejected: -35.4433
-- Logps/chosen: -31.7037
-- Logits/rejected: -2.8306
-- Logits/chosen: -2.8338
+- Loss: 0.6756
+- Rewards/chosen: -0.0773
+- Rewards/rejected: -0.1729
+- Rewards/accuracies: 0.5569
+- Rewards/margins: 0.0956
+- Logps/rejected: -34.9863
+- Logps/chosen: -31.4113
+- Logits/rejected: -2.8175
+- Logits/chosen: -2.8199
 
 ## Model description
 
@@ -57,27 +54,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 4
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.4852        | 0.26  | 100  | 0.4894          | 0.0835         | 0.0380           | 0.5689             | 0.0456          | -34.6349       | -31.1432     | -2.8023         | -2.8050       |
-| 0.4094        | 0.52  | 200  | 0.4824          | 0.1068         | 0.0177           | 0.5432             | 0.0891          | -34.6687       | -31.1045     | -2.8122         | -2.8150       |
-| 0.3408        | 0.78  | 300  | 0.4827          | 0.0196         | -0.0908          | 0.5694             | 0.1105          | -34.8496       | -31.2497     | -2.8188         | -2.8212       |
-| 0.1572        | 1.04  | 400  | 0.4798          | -0.0175        | -0.1496          | 0.5839             | 0.1321          | -34.9475       | -31.3117     | -2.8156         | -2.8172       |
-| 0.1463        | 1.3   | 500  | 0.4816          | -0.0382        | -0.1668          | 0.5843             | 0.1285          | -34.9761       | -31.3462     | -2.8282         | -2.8294       |
-| 0.1315        | 1.56  | 600  | 0.4786          | -0.0124        | -0.1617          | 0.5511             | 0.1493          | -34.9677       | -31.3031     | -2.8038         | -2.8065       |
-| 0.1119        | 1.82  | 700  | 0.4778          | -0.0846        | -0.2536          | 0.5893             | 0.1691          | -35.1209       | -31.4234     | -2.8174         | -2.8202       |
-| 0.0639        | 2.08  | 800  | 0.4746          | -0.1169        | -0.3129          | 0.5689             | 0.1961          | -35.2197       | -31.4772     | -2.8306         | -2.8335       |
-| 0.0635        | 2.34  | 900  | 0.4768          | -0.1886        | -0.3820          | 0.5777             | 0.1934          | -35.3348       | -31.5967     | -2.8313         | -2.8346       |
-| 0.0517        | 2.6   | 1000 | 0.4804          | -0.2063        | -0.3767          | 0.5544             | 0.1704          | -35.3260       | -31.6262     | -2.8305         | -2.8336       |
-| 0.0446        | 2.86  | 1100 | 0.4794          | -0.2379        | -0.4230          | 0.5689             | 0.1851          | -35.4032       | -31.6790     | -2.8298         | -2.8332       |
-| 0.0511        | 3.12  | 1200 | 0.4783          | -0.2347        | -0.4328          | 0.5806             | 0.1982          | -35.4196       | -31.6736     | -2.8297         | -2.8330       |
-| 0.0414        | 3.38  | 1300 | 0.4778          | -0.2496        | -0.4539          | 0.5660             | 0.2043          | -35.4547       | -31.6984     | -2.8309         | -2.8340       |
-| 0.0334        | 3.64  | 1400 | 0.4783          | -0.2495        | -0.4524          | 0.5777             | 0.2028          | -35.4521       | -31.6984     | -2.8308         | -2.8338       |
-| 0.0416        | 3.9   | 1500 | 0.4785          | -0.2460        | -0.4418          | 0.5631             | 0.1958          | -35.4345       | -31.6925     | -2.8303         | -2.8337       |
+| 0.6371        | 0.26  | 100  | 0.6738          | 0.0094         | -0.0765          | 0.6013             | 0.0860          | -34.8257       | -31.2667     | -2.8093         | -2.8120       |
+| 0.5701        | 0.52  | 200  | 0.6704          | -0.0753        | -0.1790          | 0.5777             | 0.1037          | -34.9964       | -31.4080     | -2.8197         | -2.8224       |
+| 0.5462        | 0.78  | 300  | 0.6756          | -0.0773        | -0.1729          | 0.5569             | 0.0956          | -34.9863       | -31.4113     | -2.8175         | -2.8199       |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6442dd659aa9777f2cbf26375980612115d3f4127a6e07013f07d61d34d90456
+oid sha256:43813f75c66ccd2464fcf5bf5cc65f759d1e14b2cf4a16986aa05db48b86060f
 size 671150064

all_results.json

@@ -1,21 +1,8 @@
 {
-    "epoch": 4.0,
-    "eval_logits/chosen": -2.8337740898132324,
-    "eval_logits/rejected": -2.830592393875122,
-    "eval_logps/chosen": -31.703718185424805,
-    "eval_logps/rejected": -35.44328689575195,
-    "eval_loss": 0.4786534011363983,
-    "eval_rewards/accuracies": 0.560215950012207,
-    "eval_rewards/chosen": -0.2527596652507782,
-    "eval_rewards/margins": 0.1943179965019226,
-    "eval_rewards/rejected": -0.4470776319503784,
-    "eval_runtime": 112.8079,
-    "eval_samples": 343,
-    "eval_samples_per_second": 3.041,
-    "eval_steps_per_second": 0.381,
-    "train_loss": 0.15808662716057392,
-    "train_runtime": 11226.5517,
+    "epoch": 1.0,
+    "train_loss": 0.5523774078914098,
+    "train_runtime": 2722.392,
     "train_samples": 3079,
-    "train_samples_per_second": 1.097,
-    "train_steps_per_second": 0.137
+    "train_samples_per_second": 1.131,
+    "train_steps_per_second": 0.141
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.0,
-    "train_loss": 0.15808662716057392,
-    "train_runtime": 11226.5517,
+    "epoch": 1.0,
+    "train_loss": 0.5523774078914098,
+    "train_runtime": 2722.392,
     "train_samples": 3079,
-    "train_samples_per_second": 1.097,
-    "train_steps_per_second": 0.137
+    "train_samples_per_second": 1.131,
+    "train_steps_per_second": 0.141
 }