End of training

README.md

@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0826
-- Eval/rewards/chosen: 2.6488
-- Eval/logps/chosen: -184.1138
-- Eval/rewards/rejected: 1.0242
-- Eval/logps/rejected: -223.6231
-- Eval/rewards/margins: 1.6246
-- Eval/kl: 17.0687
+- Loss: 1.2449
+- Eval/rewards/chosen: -0.1725
+- Eval/logps/chosen: -212.3262
+- Eval/rewards/rejected: -0.2031
+- Eval/logps/rejected: -235.8965
+- Eval/rewards/margins: 0.0307
+- Eval/kl: 0.0010
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 1e-05
 - train_batch_size: 1
 - eval_batch_size: 2
 - seed: 9012
@@ -56,11 +56,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |         |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.7159        | 0.9412 | 12   | 0.9105          | 0.0     |
-| 0.4236        | 1.9608 | 25   | 1.0808          | 11.7436 |
-| 0.2641        | 2.9804 | 38   | 1.0826          | 17.0687 |
+| Training Loss | Epoch  | Step | Validation Loss |        |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.7665        | 0.9412 | 12   | 1.3091          | 0.0694 |
+| 0.7349        | 1.9608 | 25   | 1.2881          | 0.0051 |
+| 0.7221        | 2.9804 | 38   | 1.2705          | 0.0002 |
+| 0.6999        | 4.0    | 51   | 1.2533          | 0.0050 |
+| 0.7169        | 4.9412 | 63   | 1.2452          | 0.0    |
+| 0.5263        | 5.6471 | 72   | 1.2449          | 0.0010 |
 
 
 ### Framework versions

adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
     "o_proj",
-    "v_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802d3ab785de55b415eecb965d580c0145fbef3efc693f23754db6d874ef2679
+oid sha256:0ebf779ff29a3749dc8532acb085240b8a785cd4c50e35b41abf092dc92e1725
 size 27297544

metrics.jsonl

@@ -37,3 +37,9 @@
 {"epoch": 0.9411764705882353, "precision": 0.4499999994375, "recall": 0.89999999775, "fold": 0}
 {"epoch": 1.9607843137254903, "precision": 0.5666666657222222, "recall": 0.849999997875, "fold": 0}
 {"epoch": 2.980392156862745, "precision": 0.6734693863806747, "recall": 0.8249999979375, "fold": 0}
+{"epoch": 0.9411764705882353, "precision": 0.41935483825875824, "recall": 0.9749999975625, "fold": 0}
+{"epoch": 1.9607843137254903, "precision": 0.43010752641923927, "recall": 0.9999999975, "fold": 0}
+{"epoch": 2.980392156862745, "precision": 0.4090909086260331, "recall": 0.89999999775, "fold": 0}
+{"epoch": 4.0, "precision": 0.41935483825875824, "recall": 0.9749999975625, "fold": 0}
+{"epoch": 4.9411764705882355, "precision": 0.4252873558330031, "recall": 0.9249999976875, "fold": 0}
+{"epoch": 5.647058823529412, "precision": 0.47499999940625004, "recall": 0.949999997625, "fold": 0}

metrics_epoch_0.9411764705882353_fold_0_lr_1e-05_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 0.9411764705882353, "precision": 0.41935483825875824, "recall": 0.9749999975625, "fold": 0}

metrics_epoch_1.9607843137254903_fold_0_lr_1e-05_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 1.9607843137254903, "precision": 0.43010752641923927, "recall": 0.9999999975, "fold": 0}

metrics_epoch_2.980392156862745_fold_0_lr_1e-05_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 2.980392156862745, "precision": 0.4090909086260331, "recall": 0.89999999775, "fold": 0}

metrics_epoch_4.0_fold_0_lr_1e-05_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 4.0, "precision": 0.41935483825875824, "recall": 0.9749999975625, "fold": 0}

metrics_epoch_4.9411764705882355_fold_0_lr_1e-05_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 4.9411764705882355, "precision": 0.4252873558330031, "recall": 0.9249999976875, "fold": 0}

metrics_epoch_5.647058823529412_fold_0_lr_1e-05_seed_9012_weight_5.0.json

@@ -0,0 +1 @@
+{"epoch": 5.647058823529412, "precision": 0.47499999940625004, "recall": 0.949999997625, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f06a1323ffd1510d415d4befbfce97ba66294e80697d95446a5775786b2e64ea
+oid sha256:91aa9a6d72dce545c31255d8325616915b6df239c9aa35f123473542dbecadad
 size 5688