Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
     "o_proj",
+    "gate_proj",
+    "up_proj",
     "down_proj",
     "q_proj",
-    "k_proj",
-    "up_proj"
+    "v_proj",
+    "k_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:eefa655f5cd147e98ce63dfb0864cd0f92c83e67ee1e29285d374f653484e6c0
+oid sha256:a902795c26876dcee6b17dc58d09dd059ab7b2f55ec48b89c1ff02da8cf9ecb3
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4142c3be2e841af94ef187a11cda09345575cb0c87d999166ace020f8c145c
+oid sha256:e261f1115c62590373aa85e1d643acceebcca1d9aa9ec0a2679bfc6820da89ca
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.014423760585486889,
+      "grad_norm": 0.016470158472657204,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933897018432617,
-      "eval_runtime": 0.057,
-      "eval_samples_per_second": 280.626,
-      "eval_steps_per_second": 70.156,
+      "eval_loss": 11.933887481689453,
+      "eval_runtime": 0.0606,
+      "eval_samples_per_second": 263.811,
+      "eval_steps_per_second": 65.953,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66de82d82c5b0fa059d38c05b8f39349f42fdee7e39cca74a06df079a9b400cf
+oid sha256:63acd19e180ef85d1bc60ddcf89dd22b91f48a47fa65f512d0b68f85d93ba1af
 size 6776