Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
+    "o_proj",
     "down_proj",
     "q_proj",
+    "k_proj",
+    "v_proj",
     "gate_proj",
-    "o_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cb60cfb6a4e3bc1518b920996bb48b00754ed1b17a5ca60daf58b81f3687167
+oid sha256:599547c7872fadb3e881464e4a020f2116fc88c5b3188af8b5411670dd295a7c
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4087e87e5a083938c3ff189682e3694473f025bd1a4bf489a875a45055b975fe
+oid sha256:10d0b4da74aa12381baffc346fe8c94467a7f3cec3ea54671920f25923ab57f0
 size 97487290

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.00018793459875963165,
-      "grad_norm": 0.40805867314338684,
+      "grad_norm": 0.4121508002281189,
       "learning_rate": 2e-05,
       "loss": 2.0097,
       "step": 1
@@ -18,31 +18,31 @@
     {
       "epoch": 0.00018793459875963165,
       "eval_loss": 2.225860595703125,
-      "eval_runtime": 104.7616,
-      "eval_samples_per_second": 10.7,
-      "eval_steps_per_second": 10.7,
+      "eval_runtime": 104.6968,
+      "eval_samples_per_second": 10.707,
+      "eval_steps_per_second": 10.707,
       "step": 1
     },
     {
       "epoch": 0.0003758691975192633,
-      "grad_norm": 0.3363264501094818,
+      "grad_norm": 0.34095901250839233,
       "learning_rate": 4e-05,
       "loss": 2.0424,
       "step": 2
     },
     {
       "epoch": 0.0005638037962788949,
-      "grad_norm": 0.4387308359146118,
+      "grad_norm": 0.4388081431388855,
       "learning_rate": 6e-05,
-      "loss": 2.2437,
+      "loss": 2.2435,
       "step": 3
     },
     {
       "epoch": 0.0005638037962788949,
-      "eval_loss": 2.223356246948242,
-      "eval_runtime": 105.324,
-      "eval_samples_per_second": 10.643,
-      "eval_steps_per_second": 10.643,
+      "eval_loss": 2.2231271266937256,
+      "eval_runtime": 105.4847,
+      "eval_samples_per_second": 10.627,
+      "eval_steps_per_second": 10.627,
       "step": 3
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acaeb28a4fb49aa88292474a6784853956ad77b62156abc6a5e8cbc29594a649
+oid sha256:abb88f4cc1adc89d4050bb1bb8aee4d5e2999228bec3f38fcda07d103361cace
 size 6776