Training in progress, step 794, checkpoint

checkpoint-794/adapter_config.json

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

checkpoint-794/trainer_state.json

@@ -362,9 +362,9 @@
     {
       "epoch": 0.12610340479192939,
       "eval_loss": 1.8593257665634155,
-      "eval_runtime": 19.2003,
-      "eval_samples_per_second": 36.718,
-      "eval_steps_per_second": 18.385,
+      "eval_runtime": 18.8102,
+      "eval_samples_per_second": 37.48,
+      "eval_steps_per_second": 18.766,
       "step": 50
     },
     {
@@ -720,9 +720,9 @@
     {
       "epoch": 0.25220680958385877,
       "eval_loss": 1.821334719657898,
-      "eval_runtime": 19.6836,
-      "eval_samples_per_second": 35.817,
-      "eval_steps_per_second": 17.934,
+      "eval_runtime": 18.8896,
+      "eval_samples_per_second": 37.322,
+      "eval_steps_per_second": 18.688,
       "step": 100
     },
     {
@@ -1078,9 +1078,9 @@
     {
       "epoch": 0.37831021437578816,
       "eval_loss": 1.8017936944961548,
-      "eval_runtime": 19.647,
-      "eval_samples_per_second": 35.883,
-      "eval_steps_per_second": 17.967,
+      "eval_runtime": 18.8835,
+      "eval_samples_per_second": 37.334,
+      "eval_steps_per_second": 18.694,
       "step": 150
     },
     {
@@ -1436,9 +1436,9 @@
     {
       "epoch": 0.5044136191677175,
       "eval_loss": 1.7910906076431274,
-      "eval_runtime": 19.1164,
-      "eval_samples_per_second": 36.879,
-      "eval_steps_per_second": 18.466,
+      "eval_runtime": 18.8348,
+      "eval_samples_per_second": 37.431,
+      "eval_steps_per_second": 18.742,
       "step": 200
     },
     {
@@ -1794,9 +1794,9 @@
     {
       "epoch": 0.6305170239596469,
       "eval_loss": 1.7830545902252197,
-      "eval_runtime": 19.1394,
-      "eval_samples_per_second": 36.835,
-      "eval_steps_per_second": 18.444,
+      "eval_runtime": 18.8692,
+      "eval_samples_per_second": 37.362,
+      "eval_steps_per_second": 18.708,
       "step": 250
     },
     {
@@ -2152,9 +2152,9 @@
     {
       "epoch": 0.7566204287515763,
       "eval_loss": 1.7733962535858154,
-      "eval_runtime": 19.163,
-      "eval_samples_per_second": 36.79,
-      "eval_steps_per_second": 18.421,
+      "eval_runtime": 18.9029,
+      "eval_samples_per_second": 37.296,
+      "eval_steps_per_second": 18.674,
       "step": 300
     },
     {
@@ -2510,9 +2510,9 @@
     {
       "epoch": 0.8827238335435057,
       "eval_loss": 1.7664289474487305,
-      "eval_runtime": 19.1662,
-      "eval_samples_per_second": 36.783,
-      "eval_steps_per_second": 18.418,
+      "eval_runtime": 19.1441,
+      "eval_samples_per_second": 36.826,
+      "eval_steps_per_second": 18.439,
       "step": 350
     },
     {
@@ -2868,9 +2868,9 @@
     {
       "epoch": 1.0075662042875158,
       "eval_loss": 1.7607698440551758,
-      "eval_runtime": 19.1575,
-      "eval_samples_per_second": 36.8,
-      "eval_steps_per_second": 18.426,
+      "eval_runtime": 18.8004,
+      "eval_samples_per_second": 37.499,
+      "eval_steps_per_second": 18.776,
       "step": 400
     },
     {
@@ -3226,9 +3226,9 @@
     {
       "epoch": 1.1336696090794451,
       "eval_loss": 1.7592146396636963,
-      "eval_runtime": 19.6481,
-      "eval_samples_per_second": 35.881,
-      "eval_steps_per_second": 17.966,
+      "eval_runtime": 18.8668,
+      "eval_samples_per_second": 37.367,
+      "eval_steps_per_second": 18.71,
       "step": 450
     },
     {
@@ -3584,9 +3584,9 @@
     {
       "epoch": 1.2597730138713745,
       "eval_loss": 1.7565970420837402,
-      "eval_runtime": 19.188,
-      "eval_samples_per_second": 36.742,
-      "eval_steps_per_second": 18.397,
+      "eval_runtime": 19.2415,
+      "eval_samples_per_second": 36.64,
+      "eval_steps_per_second": 18.346,
       "step": 500
     },
     {
@@ -3942,9 +3942,9 @@
     {
       "epoch": 1.385876418663304,
       "eval_loss": 1.7535345554351807,
-      "eval_runtime": 19.0961,
-      "eval_samples_per_second": 36.918,
-      "eval_steps_per_second": 18.485,
+      "eval_runtime": 18.9427,
+      "eval_samples_per_second": 37.218,
+      "eval_steps_per_second": 18.635,
       "step": 550
     },
     {
@@ -4300,9 +4300,9 @@
     {
       "epoch": 1.5119798234552333,
       "eval_loss": 1.7527234554290771,
-      "eval_runtime": 19.1093,
-      "eval_samples_per_second": 36.893,
-      "eval_steps_per_second": 18.473,
+      "eval_runtime": 18.7311,
+      "eval_samples_per_second": 37.638,
+      "eval_steps_per_second": 18.846,
       "step": 600
     },
     {
@@ -4658,9 +4658,9 @@
     {
       "epoch": 1.6380832282471627,
       "eval_loss": 1.749564528465271,
-      "eval_runtime": 19.1442,
-      "eval_samples_per_second": 36.826,
-      "eval_steps_per_second": 18.439,
+      "eval_runtime": 18.8736,
+      "eval_samples_per_second": 37.354,
+      "eval_steps_per_second": 18.703,
       "step": 650
     },
     {
@@ -5016,9 +5016,9 @@
     {
       "epoch": 1.764186633039092,
       "eval_loss": 1.7481378316879272,
-      "eval_runtime": 19.1022,
-      "eval_samples_per_second": 36.907,
-      "eval_steps_per_second": 18.48,
+      "eval_runtime": 18.8397,
+      "eval_samples_per_second": 37.421,
+      "eval_steps_per_second": 18.737,
       "step": 700
     },
     {
@@ -5374,9 +5374,9 @@
     {
       "epoch": 1.8902900378310215,
       "eval_loss": 1.7464284896850586,
-      "eval_runtime": 19.0761,
-      "eval_samples_per_second": 36.957,
-      "eval_steps_per_second": 18.505,
+      "eval_runtime": 18.6784,
+      "eval_samples_per_second": 37.744,
+      "eval_steps_per_second": 18.899,
       "step": 750
     },
     {
@@ -5692,7 +5692,7 @@
   "max_steps": 794,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
-  "save_steps": 200,
+  "save_steps": 50,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {

checkpoint-794/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908ac25afcecebd00cf3e224398e924723fc17436e832bf290d1f7c335a5a4b7
+oid sha256:ec3d8df95ba642eec10e761db819efa4c74dbd8edeed27cfd2cb36ccafa00305
 size 6161