Training in progress, step 500, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/trainer_state.json

@@ -81,9 +81,9 @@
     {
       "epoch": 0.07145409074669525,
       "eval_news_finetune_val_loss": 0.48679304122924805,
-      "eval_news_finetune_val_runtime": 1002.7224,
-      "eval_news_finetune_val_samples_per_second": 1.396,
-      "eval_news_finetune_val_steps_per_second": 1.396,
+      "eval_news_finetune_val_runtime": 1001.9158,
+      "eval_news_finetune_val_samples_per_second": 1.397,
+      "eval_news_finetune_val_steps_per_second": 1.397,
       "step": 100
     },
     {
@@ -159,9 +159,9 @@
     {
       "epoch": 0.1429081814933905,
       "eval_news_finetune_val_loss": 0.4338369369506836,
-      "eval_news_finetune_val_runtime": 1003.2801,
-      "eval_news_finetune_val_samples_per_second": 1.395,
-      "eval_news_finetune_val_steps_per_second": 1.395,
+      "eval_news_finetune_val_runtime": 1002.1695,
+      "eval_news_finetune_val_samples_per_second": 1.397,
+      "eval_news_finetune_val_steps_per_second": 1.397,
       "step": 200
     },
     {
@@ -237,9 +237,9 @@
     {
       "epoch": 0.21436227224008575,
       "eval_news_finetune_val_loss": 0.40391305088996887,
-      "eval_news_finetune_val_runtime": 1003.2872,
-      "eval_news_finetune_val_samples_per_second": 1.395,
-      "eval_news_finetune_val_steps_per_second": 1.395,
+      "eval_news_finetune_val_runtime": 1002.5797,
+      "eval_news_finetune_val_samples_per_second": 1.396,
+      "eval_news_finetune_val_steps_per_second": 1.396,
       "step": 300
     },
     {
@@ -315,9 +315,9 @@
     {
       "epoch": 0.285816362986781,
       "eval_news_finetune_val_loss": 0.39322975277900696,
-      "eval_news_finetune_val_runtime": 1003.4166,
-      "eval_news_finetune_val_samples_per_second": 1.395,
-      "eval_news_finetune_val_steps_per_second": 1.395,
+      "eval_news_finetune_val_runtime": 1002.8865,
+      "eval_news_finetune_val_samples_per_second": 1.396,
+      "eval_news_finetune_val_steps_per_second": 1.396,
       "step": 400
     },
     {
@@ -393,9 +393,9 @@
     {
       "epoch": 0.35727045373347627,
       "eval_news_finetune_val_loss": 0.3787713646888733,
-      "eval_news_finetune_val_runtime": 1003.589,
-      "eval_news_finetune_val_samples_per_second": 1.395,
-      "eval_news_finetune_val_steps_per_second": 1.395,
+      "eval_news_finetune_val_runtime": 1002.8588,
+      "eval_news_finetune_val_samples_per_second": 1.396,
+      "eval_news_finetune_val_steps_per_second": 1.396,
       "step": 500
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2782bf8a609c154eefb42753d138dafcba3aa0ea92b9d87f5184a3cbc4f0f0be
+oid sha256:367406c6dccce148fee91e86e6fa08ac415e3c6a88231b8f42f8d49575bf98f6
 size 5624