Training in progress, step 6, checkpoint

checkpoint-6/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
-    "up_proj",
     "k_proj",
-    "gate_proj",
     "o_proj",
-    "v_proj"
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-6/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b042d84330c9e80a700a76ba670dc37749d83b8f3610f3e63c743c682b68432a
+oid sha256:23d63df04d2a4e7e10203dd44638deabd34dd427a0104e8267e2d3ac1bceb2d4
 size 83945296

checkpoint-6/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f7a078e0f6ba68ce9e7f734f032938611a1199f15263ec13894f7c8a4f4dcf
+oid sha256:ab9e42b5dea46f6b8b149f46780e73dcc0e0ad9fd7082d4541219418bec3f96f
 size 168149074

checkpoint-6/trainer_state.json

@@ -10,60 +10,60 @@
   "log_history": [
     {
       "epoch": 0.0006200589055960316,
-      "grad_norm": 0.7733756303787231,
+      "grad_norm": 0.7731499075889587,
       "learning_rate": 4.000000000000001e-06,
       "loss": 1.166,
       "step": 1
     },
     {
       "epoch": 0.0012401178111920632,
-      "grad_norm": 0.34648507833480835,
+      "grad_norm": 0.346652090549469,
       "learning_rate": 8.000000000000001e-06,
       "loss": 0.9594,
       "step": 2
     },
     {
       "epoch": 0.0018601767167880949,
-      "grad_norm": 0.3973380923271179,
+      "grad_norm": 0.39937612414360046,
       "learning_rate": 1.2e-05,
-      "loss": 0.8281,
+      "loss": 0.828,
       "step": 3
     },
     {
       "epoch": 0.0018601767167880949,
-      "eval_loss": 1.0490500926971436,
-      "eval_runtime": 28.8129,
-      "eval_samples_per_second": 3.471,
-      "eval_steps_per_second": 3.471,
+      "eval_loss": 1.0491173267364502,
+      "eval_runtime": 26.0459,
+      "eval_samples_per_second": 3.839,
+      "eval_steps_per_second": 3.839,
       "step": 3
     },
     {
       "epoch": 0.0024802356223841263,
-      "grad_norm": 0.342887282371521,
+      "grad_norm": 0.3457990288734436,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.9881,
+      "loss": 0.988,
       "step": 4
     },
     {
       "epoch": 0.0031002945279801583,
-      "grad_norm": 0.46208909153938293,
+      "grad_norm": 0.513918399810791,
       "learning_rate": 2e-05,
       "loss": 0.8319,
       "step": 5
     },
     {
       "epoch": 0.0037203534335761897,
-      "grad_norm": 0.4722931981086731,
+      "grad_norm": 0.47683727741241455,
       "learning_rate": 1.9200000000000003e-05,
-      "loss": 0.9364,
+      "loss": 0.9366,
       "step": 6
     },
     {
       "epoch": 0.0037203534335761897,
-      "eval_loss": 1.0428661108016968,
-      "eval_runtime": 26.3402,
-      "eval_samples_per_second": 3.796,
-      "eval_steps_per_second": 3.796,
+      "eval_loss": 1.0431987047195435,
+      "eval_runtime": 26.2352,
+      "eval_samples_per_second": 3.812,
+      "eval_steps_per_second": 3.812,
       "step": 6
     }
   ],

checkpoint-6/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c433cc5009675ccadca19513c8ae659f957c78885071da55c2a8d32a98d517a
+oid sha256:cbe2fb31cf4c04f893e5299faa77267af76b8447f922d82c2d6c0200e1fe225f
 size 5688