Training in progress, step 2, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6015c8163f1df8e22c794a249e6c00712349603742ea89cab4bca412edf7f67
+oid sha256:dd3281f036d04d9f5f470e3ae181a36a2a8d62bd14263758ff7b2f7275a8fefd
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b434b9fffdf083fb79bb4c69340230d1cc690041651fbf48e304454dee1ec24
+oid sha256:bb2aefcd8a898c389afd5016fecc88116ad90317cf7b34a872246179f50b5304
 size 341314196

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0002717883674578728,
-      "grad_norm": 4.489199161529541,
+      "grad_norm": 4.251254558563232,
       "learning_rate": 2e-05,
       "loss": 5.3201,
       "step": 1
@@ -18,14 +18,14 @@
     {
       "epoch": 0.0002717883674578728,
       "eval_loss": 5.817660331726074,
-      "eval_runtime": 742.2088,
-      "eval_samples_per_second": 6.262,
-      "eval_steps_per_second": 1.566,
+      "eval_runtime": 740.7465,
+      "eval_samples_per_second": 6.275,
+      "eval_steps_per_second": 1.569,
       "step": 1
     },
     {
       "epoch": 0.0005435767349157456,
-      "grad_norm": 7.107272624969482,
+      "grad_norm": 6.6031174659729,
       "learning_rate": 4e-05,
       "loss": 5.8911,
       "step": 2

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248ce35ff18e493983381177f2ebda25f083ce99a178fa16cbf1b7fc2bec948d
+oid sha256:749d32b49d3872f7f415b6b04cd14255dda2b9c5197a883623274fec8966023e
 size 6776