Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "down_proj",
-    "q_proj",
+    "gate_proj",
     "v_proj",
+    "q_proj",
+    "down_proj",
     "up_proj",
-    "gate_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4eed70775f49b71047399b80c753ba0da06fdc3275ab67f6f412953df0e78d4
+oid sha256:2697665b676227dfe9222aa6a3aaa25a1a8fffed3dd11180a2c464abf0288d49
 size 80013120

last-checkpoint/trainer_state.json

@@ -18,9 +18,9 @@
     {
       "epoch": 1.396028995522237e-05,
       "eval_loss": 1.870382308959961,
-      "eval_runtime": 1842.0549,
-      "eval_samples_per_second": 8.187,
-      "eval_steps_per_second": 8.187,
+      "eval_runtime": 1878.2928,
+      "eval_samples_per_second": 8.029,
+      "eval_steps_per_second": 8.029,
       "step": 1
     },
     {
@@ -40,9 +40,9 @@
     {
       "epoch": 4.188086986566711e-05,
       "eval_loss": 1.870382308959961,
-      "eval_runtime": 1823.007,
-      "eval_samples_per_second": 8.273,
-      "eval_steps_per_second": 8.273,
+      "eval_runtime": 1814.1651,
+      "eval_samples_per_second": 8.313,
+      "eval_steps_per_second": 8.313,
       "step": 3
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e2120fce261a3f11caf9498f0f2c7c47b2d4840984af1e8cfb44d3982cfeb2
+oid sha256:8592505319a0e1bd652dbec69d0ae190ac2673d977246a6c07d54713cd9bce43
 size 6776