Training in progress, step 600, checkpoint

checkpoint-600/adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
     "gate_proj",
+    "q_proj",
     "v_proj",
     "down_proj",
+    "o_proj",
     "up_proj",
-    "q_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

checkpoint-600/trainer_state.json

@@ -362,9 +362,9 @@
     {
       "epoch": 0.12610340479192939,
       "eval_loss": 1.8593257665634155,
-      "eval_runtime": 18.8102,
-      "eval_samples_per_second": 37.48,
-      "eval_steps_per_second": 18.766,
+      "eval_runtime": 19.3972,
+      "eval_samples_per_second": 36.345,
+      "eval_steps_per_second": 18.198,
       "step": 50
     },
     {
@@ -720,9 +720,9 @@
     {
       "epoch": 0.25220680958385877,
       "eval_loss": 1.821334719657898,
-      "eval_runtime": 18.8896,
-      "eval_samples_per_second": 37.322,
-      "eval_steps_per_second": 18.688,
+      "eval_runtime": 19.3187,
+      "eval_samples_per_second": 36.493,
+      "eval_steps_per_second": 18.272,
       "step": 100
     },
     {
@@ -1078,9 +1078,9 @@
     {
       "epoch": 0.37831021437578816,
       "eval_loss": 1.8017936944961548,
-      "eval_runtime": 18.8835,
-      "eval_samples_per_second": 37.334,
-      "eval_steps_per_second": 18.694,
+      "eval_runtime": 19.5165,
+      "eval_samples_per_second": 36.123,
+      "eval_steps_per_second": 18.087,
       "step": 150
     },
     {
@@ -1436,9 +1436,9 @@
     {
       "epoch": 0.5044136191677175,
       "eval_loss": 1.7910906076431274,
-      "eval_runtime": 18.8348,
-      "eval_samples_per_second": 37.431,
-      "eval_steps_per_second": 18.742,
+      "eval_runtime": 19.0069,
+      "eval_samples_per_second": 37.092,
+      "eval_steps_per_second": 18.572,
       "step": 200
     },
     {
@@ -1794,9 +1794,9 @@
     {
       "epoch": 0.6305170239596469,
       "eval_loss": 1.7830545902252197,
-      "eval_runtime": 18.8692,
-      "eval_samples_per_second": 37.362,
-      "eval_steps_per_second": 18.708,
+      "eval_runtime": 19.0502,
+      "eval_samples_per_second": 37.008,
+      "eval_steps_per_second": 18.53,
       "step": 250
     },
     {
@@ -2152,9 +2152,9 @@
     {
       "epoch": 0.7566204287515763,
       "eval_loss": 1.7733962535858154,
-      "eval_runtime": 18.9029,
-      "eval_samples_per_second": 37.296,
-      "eval_steps_per_second": 18.674,
+      "eval_runtime": 19.1336,
+      "eval_samples_per_second": 36.846,
+      "eval_steps_per_second": 18.449,
       "step": 300
     },
     {
@@ -2510,9 +2510,9 @@
     {
       "epoch": 0.8827238335435057,
       "eval_loss": 1.7664289474487305,
-      "eval_runtime": 19.1441,
-      "eval_samples_per_second": 36.826,
-      "eval_steps_per_second": 18.439,
+      "eval_runtime": 19.2628,
+      "eval_samples_per_second": 36.599,
+      "eval_steps_per_second": 18.326,
       "step": 350
     },
     {
@@ -2868,9 +2868,9 @@
     {
       "epoch": 1.0075662042875158,
       "eval_loss": 1.7607698440551758,
-      "eval_runtime": 18.8004,
-      "eval_samples_per_second": 37.499,
-      "eval_steps_per_second": 18.776,
+      "eval_runtime": 19.095,
+      "eval_samples_per_second": 36.921,
+      "eval_steps_per_second": 18.487,
       "step": 400
     },
     {
@@ -3226,9 +3226,9 @@
     {
       "epoch": 1.1336696090794451,
       "eval_loss": 1.7592146396636963,
-      "eval_runtime": 18.8668,
-      "eval_samples_per_second": 37.367,
-      "eval_steps_per_second": 18.71,
+      "eval_runtime": 18.9658,
+      "eval_samples_per_second": 37.172,
+      "eval_steps_per_second": 18.612,
       "step": 450
     },
     {
@@ -3584,9 +3584,9 @@
     {
       "epoch": 1.2597730138713745,
       "eval_loss": 1.7565970420837402,
-      "eval_runtime": 19.2415,
-      "eval_samples_per_second": 36.64,
-      "eval_steps_per_second": 18.346,
+      "eval_runtime": 19.3997,
+      "eval_samples_per_second": 36.341,
+      "eval_steps_per_second": 18.196,
       "step": 500
     },
     {
@@ -3942,9 +3942,9 @@
     {
       "epoch": 1.385876418663304,
       "eval_loss": 1.7535345554351807,
-      "eval_runtime": 18.9427,
-      "eval_samples_per_second": 37.218,
-      "eval_steps_per_second": 18.635,
+      "eval_runtime": 19.0004,
+      "eval_samples_per_second": 37.104,
+      "eval_steps_per_second": 18.579,
       "step": 550
     },
     {
@@ -4300,9 +4300,9 @@
     {
       "epoch": 1.5119798234552333,
       "eval_loss": 1.7527234554290771,
-      "eval_runtime": 18.7311,
-      "eval_samples_per_second": 37.638,
-      "eval_steps_per_second": 18.846,
+      "eval_runtime": 19.2415,
+      "eval_samples_per_second": 36.64,
+      "eval_steps_per_second": 18.346,
       "step": 600
     }
   ],

checkpoint-600/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3d8df95ba642eec10e761db819efa4c74dbd8edeed27cfd2cb36ccafa00305
+oid sha256:98acfaad9c3466225d741aedf6691d0b64ec22dd7a298e7a5cde0e7f6a0d3d55
 size 6161