Training in progress, epoch 0, checkpoint

checkpoint-10/adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

checkpoint-10/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95edfc15c11e1911bcb46049050cce1c30999ab29e7e0744cf746851ba37a97f
+oid sha256:85a1b99ae008ba7c6da4b5cf364fa6a3ea39c6f7ac50e67932ca0c9df59b633d
 size 27280152

checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:285028a330680fb86ca00f62609251b948eb5f61c74cf62d872a55ea3960a0ff
+oid sha256:6c304e74304a901db0ba964287398edaf92b297d85b03533d30c8685e165a3a5
 size 54602042

checkpoint-10/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6653721928596497,
+  "best_metric": 0.6339428424835205,
   "best_model_checkpoint": "./Zephyr/05-01-24-HuggingFaceH4-zephyr-7b-beta_Treino-QPTQ-2_epochs-1_batch_2/checkpoints/checkpoint-10",
   "epoch": 0.9195402298850575,
   "eval_steps": 500,
@@ -10,10 +10,10 @@
   "log_history": [
     {
       "epoch": 0.92,
-      "eval_loss": 0.6653721928596497,
-      "eval_runtime": 6.1024,
-      "eval_samples_per_second": 3.114,
-      "eval_steps_per_second": 1.639,
+      "eval_loss": 0.6339428424835205,
+      "eval_runtime": 6.0974,
+      "eval_samples_per_second": 3.116,
+      "eval_steps_per_second": 1.64,
       "step": 10
     }
   ],

checkpoint-10/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab5ec99a97a89a5447e5e70abd51e05ade1aa99560d9ffd7b4690ea5b2ac3d1
+oid sha256:d2278489907e63a7c604df2d692712eb54f88e46f0ebac3ac216407e8863bb1a
 size 4792