Training in progress, epoch 1

adapter_config.json

@@ -25,8 +25,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52af2eba14357a8295689f041a36970347582ae25a07ec15f22b392c70a32ac0
+oid sha256:5ad7cbf60dd99c739ae3769da5ab6dec2e4deefdf61e7ddea03b005f20466e20
 size 10108960

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 14,
-  "best_metric": 7.769174098968506,
+  "best_metric": 7.774374485015869,
   "best_model_checkpoint": "qwen2.5-7b-instruct-sft/checkpoint-14",
   "epoch": 2.0,
   "eval_steps": 8,
@@ -11,36 +11,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.011311172668513388,
-      "eval_entropy": 1.995360060742027,
-      "eval_loss": 8.486817359924316,
-      "eval_mean_token_accuracy": 0.3320777494656412,
-      "eval_num_tokens": 10173.0,
-      "eval_runtime": 5.7445,
-      "eval_samples_per_second": 3.308,
-      "eval_steps_per_second": 3.308,
+      "eval_accuracy": 0.009382151029748284,
+      "eval_entropy": 1.9991131769983392,
+      "eval_loss": 8.462516784667969,
+      "eval_mean_token_accuracy": 0.3313447864432084,
+      "eval_num_tokens": 10200.0,
+      "eval_runtime": 5.9276,
+      "eval_samples_per_second": 3.205,
+      "eval_steps_per_second": 3.205,
       "step": 7
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.012003693444136657,
-      "eval_entropy": 2.3059515451130115,
-      "eval_loss": 7.769174098968506,
-      "eval_mean_token_accuracy": 0.3835462488626179,
-      "eval_num_tokens": 20346.0,
-      "eval_runtime": 5.4565,
-      "eval_samples_per_second": 3.482,
-      "eval_steps_per_second": 3.482,
+      "eval_accuracy": 0.009382151029748282,
+      "eval_entropy": 2.2881032667661967,
+      "eval_loss": 7.774374485015869,
+      "eval_mean_token_accuracy": 0.38798953043787104,
+      "eval_num_tokens": 20400.0,
+      "eval_runtime": 5.6575,
+      "eval_samples_per_second": 3.358,
+      "eval_steps_per_second": 3.358,
       "step": 14
     },
     {
       "epoch": 2.0,
       "step": 14,
-      "total_flos": 946051451375616.0,
-      "train_loss": 9.178882053920201,
-      "train_runtime": 64.9953,
-      "train_samples_per_second": 1.539,
-      "train_steps_per_second": 0.215
+      "total_flos": 948562351718400.0,
+      "train_loss": 9.186460222516741,
+      "train_runtime": 63.5624,
+      "train_samples_per_second": 1.573,
+      "train_steps_per_second": 0.22
     }
   ],
   "logging_steps": 20,
@@ -60,7 +60,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 946051451375616.0,
+  "total_flos": 948562351718400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d8482c3d536c482f9ff6dc3cc5cf37c97b34842af3ea1abd2e8a6ce1ad5ccc
+oid sha256:17d8fae980fd538a4af1f30218f3a02c9953cd57289afafef173d0fa6bca5dfc
 size 5752