Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
+    "gate_proj",
     "o_proj",
+    "up_proj",
     "v_proj",
-    "down_proj",
     "k_proj",
-    "gate_proj"
+    "q_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4504c0b30f5656a6c01247b462c6131a74300029e235538a5317d476f20c76cc
+oid sha256:42dbe66bbb1a275a1f530e86f9907b6f7c42eb91f4ff686c9ed12ff24b99c3d7
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc81c97848e338c67fad456c43c4eccf40ccc2d0a14fa097a29b3e9cca0b8fb
+oid sha256:a317b12c2c75facd132edae182aadd32e1a78df2d40edd06f8aa655a8ce2e9e2
 size 45221242

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 8.23011398707872e-05,
-      "grad_norm": 0.7503308057785034,
+      "grad_norm": 0.6557537913322449,
       "learning_rate": 2e-05,
       "loss": 1.5917,
       "step": 1
@@ -18,31 +18,31 @@
     {
       "epoch": 8.23011398707872e-05,
       "eval_loss": 1.959477186203003,
-      "eval_runtime": 133.9988,
-      "eval_samples_per_second": 19.09,
-      "eval_steps_per_second": 19.09,
+      "eval_runtime": 135.3765,
+      "eval_samples_per_second": 18.895,
+      "eval_steps_per_second": 18.895,
       "step": 1
     },
     {
       "epoch": 0.0001646022797415744,
-      "grad_norm": 0.8759475350379944,
+      "grad_norm": 0.7621749639511108,
       "learning_rate": 4e-05,
       "loss": 1.8288,
       "step": 2
     },
     {
       "epoch": 0.00024690341961236165,
-      "grad_norm": 0.6373544931411743,
+      "grad_norm": 0.5589603781700134,
       "learning_rate": 6e-05,
-      "loss": 1.0265,
+      "loss": 1.0263,
       "step": 3
     },
     {
       "epoch": 0.00024690341961236165,
-      "eval_loss": 1.9565452337265015,
-      "eval_runtime": 160.8486,
-      "eval_samples_per_second": 15.903,
-      "eval_steps_per_second": 15.903,
+      "eval_loss": 1.957216739654541,
+      "eval_runtime": 161.0963,
+      "eval_samples_per_second": 15.879,
+      "eval_steps_per_second": 15.879,
       "step": 3
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478a261d562ef7004d0f64e3e27b2ba59d503990d5008804b57fbc37d15611f7
+oid sha256:923ce18a73524fc48b19c36dee905217bafd6d65025d46d8a80d999e0fe09dba
 size 6776