Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "up_proj",
-    "down_proj",
     "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
     "k_proj",
-    "gate_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 sha256:68f487aa222d26357d3b760e9a17f69a08eedbd42c11631c61da3f7ab345eaa8
+oid sha256:1d62c59a22d074ea25f4d3cf45ad91c2015d68ff6a3b1fe187695cf818751fdd
 size 80792096

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f8bc6fa9761b34169cf09009a689be0421c610ccd837675a87112c385c8cad5
+oid sha256:bc11c4d9110d0efae4ad28cb780bd33ef9c2fa2e335cfab103e7f12f542300fa
 size 14244

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 8.618275052248293e-05,
       "eval_loss": NaN,
-      "eval_runtime": 336.0585,
-      "eval_samples_per_second": 14.539,
-      "eval_steps_per_second": 7.27,
+      "eval_runtime": 331.7922,
+      "eval_samples_per_second": 14.726,
+      "eval_steps_per_second": 7.363,
       "step": 1
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.0008618275052248292,
       "eval_loss": NaN,
-      "eval_runtime": 335.5914,
-      "eval_samples_per_second": 14.559,
-      "eval_steps_per_second": 7.28,
+      "eval_runtime": 331.9842,
+      "eval_samples_per_second": 14.718,
+      "eval_steps_per_second": 7.359,
       "step": 10
     },
     {
@@ -55,9 +55,9 @@
     {
       "epoch": 0.0017236550104496584,
       "eval_loss": NaN,
-      "eval_runtime": 335.6421,
-      "eval_samples_per_second": 14.557,
-      "eval_steps_per_second": 7.279,
+      "eval_runtime": 331.1945,
+      "eval_samples_per_second": 14.753,
+      "eval_steps_per_second": 7.376,
       "step": 20
     },
     {
@@ -77,9 +77,9 @@
     {
       "epoch": 0.0025854825156744875,
       "eval_loss": NaN,
-      "eval_runtime": 335.398,
-      "eval_samples_per_second": 14.568,
-      "eval_steps_per_second": 7.284,
+      "eval_runtime": 330.4337,
+      "eval_samples_per_second": 14.787,
+      "eval_steps_per_second": 7.393,
       "step": 30
     },
     {
@@ -99,9 +99,9 @@
     {
       "epoch": 0.003447310020899317,
       "eval_loss": NaN,
-      "eval_runtime": 335.6166,
-      "eval_samples_per_second": 14.558,
-      "eval_steps_per_second": 7.279,
+      "eval_runtime": 330.5903,
+      "eval_samples_per_second": 14.78,
+      "eval_steps_per_second": 7.39,
       "step": 40
     },
     {
@@ -121,9 +121,9 @@
     {
       "epoch": 0.004309137526124146,
       "eval_loss": NaN,
-      "eval_runtime": 335.7403,
-      "eval_samples_per_second": 14.553,
-      "eval_steps_per_second": 7.276,
+      "eval_runtime": 330.0357,
+      "eval_samples_per_second": 14.804,
+      "eval_steps_per_second": 7.402,
       "step": 50
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25fd71fe8415b64b1f441eb970a98b37a04133c8317c80879bf54aa07922811c
+oid sha256:fa1d37cf89fbf818b70abdb7b8d6f4e2e14ae744a7c9847899987fedf464b73f
 size 6776