Training in progress, step 200, checkpoint

checkpoint-200/adapter_config.json

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

checkpoint-200/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:913950e4971737031da511cdd1b410daae4566f62eb845b3975bca5a102323d8
+size 11421995

checkpoint-200/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": 18.9014,
+      "eval_samples_per_second": 37.299,
+      "eval_steps_per_second": 18.676,
       "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": 19.2199,
+      "eval_samples_per_second": 36.681,
+      "eval_steps_per_second": 18.366,
       "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": 18.9235,
+      "eval_samples_per_second": 37.255,
+      "eval_steps_per_second": 18.654,
       "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": 18.9166,
+      "eval_samples_per_second": 37.269,
+      "eval_steps_per_second": 18.661,
       "step": 200
     }
   ],
@@ -1446,7 +1446,7 @@
   "max_steps": 794,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
-  "save_steps": 200,
+  "save_steps": 50,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {

checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908ac25afcecebd00cf3e224398e924723fc17436e832bf290d1f7c335a5a4b7
+oid sha256:c5837a9ab69dc67dc3394365dc023f22756863ff5c486b65993199054047c5ed
 size 6161