Training in progress, step 30, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 0.0030075187969924814,
       "eval_loss": NaN,
-      "eval_runtime": 26.6856,
-      "eval_samples_per_second": 5.246,
-      "eval_steps_per_second": 2.623,
+      "eval_runtime": 27.481,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 2.547,
       "step": 1
     },
     {
@@ -26,9 +26,9 @@
     {
       "epoch": 0.015037593984962405,
       "eval_loss": NaN,
-      "eval_runtime": 27.5034,
-      "eval_samples_per_second": 5.09,
-      "eval_steps_per_second": 2.545,
+      "eval_runtime": 27.5842,
+      "eval_samples_per_second": 5.075,
+      "eval_steps_per_second": 2.538,
       "step": 5
     },
     {
@@ -48,9 +48,9 @@
     {
       "epoch": 0.03007518796992481,
       "eval_loss": NaN,
-      "eval_runtime": 27.5491,
-      "eval_samples_per_second": 5.082,
-      "eval_steps_per_second": 2.541,
+      "eval_runtime": 27.6578,
+      "eval_samples_per_second": 5.062,
+      "eval_steps_per_second": 2.531,
       "step": 10
     },
     {
@@ -70,9 +70,9 @@
     {
       "epoch": 0.045112781954887216,
       "eval_loss": NaN,
-      "eval_runtime": 27.6227,
-      "eval_samples_per_second": 5.068,
-      "eval_steps_per_second": 2.534,
+      "eval_runtime": 26.6388,
+      "eval_samples_per_second": 5.255,
+      "eval_steps_per_second": 2.628,
       "step": 15
     },
     {
@@ -85,9 +85,9 @@
     {
       "epoch": 0.06015037593984962,
       "eval_loss": NaN,
-      "eval_runtime": 27.5039,
-      "eval_samples_per_second": 5.09,
-      "eval_steps_per_second": 2.545,
+      "eval_runtime": 27.7237,
+      "eval_samples_per_second": 5.05,
+      "eval_steps_per_second": 2.525,
       "step": 20
     },
     {
@@ -107,9 +107,9 @@
     {
       "epoch": 0.07518796992481203,
       "eval_loss": NaN,
-      "eval_runtime": 27.5947,
-      "eval_samples_per_second": 5.073,
-      "eval_steps_per_second": 2.537,
+      "eval_runtime": 27.6693,
+      "eval_samples_per_second": 5.06,
+      "eval_steps_per_second": 2.53,
       "step": 25
     },
     {
@@ -129,9 +129,9 @@
     {
       "epoch": 0.09022556390977443,
       "eval_loss": NaN,
-      "eval_runtime": 27.6176,
-      "eval_samples_per_second": 5.069,
-      "eval_steps_per_second": 2.535,
+      "eval_runtime": 24.5914,
+      "eval_samples_per_second": 5.693,
+      "eval_steps_per_second": 2.847,
       "step": 30
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadbb2cc0e6d20d3373ebcf4dbeb7b0874555a2254d75c2babdcd1a27f59d922
+oid sha256:20186f755d00f92880a9ff8e59a22ed00993d2306608766329a7eb9705257573
 size 6776