Training in progress, step 63, checkpoint

checkpoint-63/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "dense_h_to_4h",
     "dense_4h_to_h",
     "query_key_value",
-    "dense",
-    "dense_h_to_4h"
+    "dense"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-63/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c04e4a5ee03ad4fdf0d8ba26bcb9a845b52e0ffbd4c951d39c70c454d130bb6
+oid sha256:84870ad2b082f3826b0ed2ce8fa97fce56a8ddda28564330d270419cf4c14948
 size 25192592

checkpoint-63/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e56c92dea78ac4f66ad3020662353b8a735395a7deb986154bc80bca931863c
+oid sha256:0229abefac5f451a6b28b1746d32d13ea09db4f682456b6847c5b44e6ed18c8f
 size 50493050

checkpoint-63/trainer_state.json

@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 0.2016,
-      "eval_logps/chosen": -106.34315490722656,
+      "eval_logps/chosen": -70.4515609741211,
       "eval_logps/ref_chosen": -70.265625,
       "eval_logps/ref_rejected": -63.51186752319336,
-      "eval_logps/rejected": -106.34315490722656,
-      "eval_loss": 0.6557361483573914,
-      "eval_rewards/accuracies": 0.6162024772678456,
-      "eval_rewards/chosen": -1.8038759231567383,
-      "eval_rewards/margins": 0.1433669477701187,
-      "eval_rewards/rejected": -1.9472428560256958,
-      "eval_runtime": 2599.3441,
-      "eval_samples_per_second": 32.24,
-      "eval_steps_per_second": 4.03,
+      "eval_logps/rejected": -70.4515609741211,
+      "eval_loss": 0.700020968914032,
+      "eval_rewards/accuracies": 0.5043316388630343,
+      "eval_rewards/chosen": -0.009296582080423832,
+      "eval_rewards/margins": -0.0003258216893300414,
+      "eval_rewards/rejected": -0.00897076167166233,
+      "eval_runtime": 2598.2788,
+      "eval_samples_per_second": 32.253,
+      "eval_steps_per_second": 4.032,
       "step": 63
     }
   ],

checkpoint-63/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46ff4287a15bff07546a9b59f8721b8272bf4ace050683003790d085d41bfcd5
+oid sha256:c6686dc40b6db461a3b988241b5bc24010b480d0524615f6ccf956bf69c70fdf
 size 5176