Training in progress, step 2, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f4bd8173a488493bfc135b0b00d218b60f7ca3127442bac3ee332b279de308
+oid sha256:e7aadff02eb8558c9740beadd5a8515e6a692bec62185c57715dc74eb516e3e8
 size 1770585648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6e45df8c72375b9124c1cf915cc824a784b313fcc071cd79625c91d75d52e7a
+oid sha256:6f22fda284fe8c75934d03ac77ff1560b4a2fcc4bc20b3580a6483453cc4bcdf
 size 99235764

last-checkpoint/trainer_state.json

@@ -10,32 +10,32 @@
   "log_history": [
     {
       "epoch": 0.8,
-      "grad_norm": 4.495707988739014,
+      "grad_norm": 11.588508605957031,
       "learning_rate": 2e-05,
-      "loss": 5.4988,
+      "loss": 13.3042,
       "step": 1
     },
     {
       "epoch": 0.8,
-      "eval_loss": 5.075080871582031,
-      "eval_runtime": 0.3898,
-      "eval_samples_per_second": 2.566,
-      "eval_steps_per_second": 2.566,
+      "eval_loss": 11.52426815032959,
+      "eval_runtime": 0.39,
+      "eval_samples_per_second": 2.564,
+      "eval_steps_per_second": 2.564,
       "step": 1
     },
     {
       "epoch": 1.6,
-      "grad_norm": 4.435665607452393,
+      "grad_norm": 11.549392700195312,
       "learning_rate": 4e-05,
-      "loss": 5.2725,
+      "loss": 13.1934,
       "step": 2
     },
     {
       "epoch": 1.6,
-      "eval_loss": 5.068875789642334,
-      "eval_runtime": 0.3873,
-      "eval_samples_per_second": 2.582,
-      "eval_steps_per_second": 2.582,
+      "eval_loss": 11.268893241882324,
+      "eval_runtime": 0.3904,
+      "eval_samples_per_second": 2.562,
+      "eval_steps_per_second": 2.562,
       "step": 2
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44748d1dcddc20382d94692c82fe6f19df00bbe11e18d390697f5a775b282d62
+oid sha256:af853a67b3854fa26b67dfae731715dfd1e79725227c471b95b403f47394d08e
 size 6136