Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
     "gate_proj",
-    "o_proj",
+    "v_proj",
     "down_proj",
+    "o_proj",
+    "q_proj",
     "up_proj",
-    "q_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:b78d966700171e907bd160b341c5bf7acbd51fc358a4f49eee24c16e2eef0885
+oid sha256:f4dbc8af9279899a6b4ebcdcaf3794013f2ec5f32a3243c79baabbbfba5edc29
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3b73b1d4e694c6ca8816db5955229be047f3039ddf8fee76e61c3a662fd144
+oid sha256:f644799f195f73e766580a1ce39c2b7da8e58c392f7f76f8efaf2c93062b87b6
 size 160172858

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.00023949227637408692,
-      "grad_norm": 5.556643962860107,
+      "grad_norm": 5.223796367645264,
       "learning_rate": 2e-05,
       "loss": 2.4864,
       "step": 1
@@ -18,31 +18,31 @@
     {
       "epoch": 0.00023949227637408692,
       "eval_loss": 3.196671962738037,
-      "eval_runtime": 164.0333,
-      "eval_samples_per_second": 5.365,
-      "eval_steps_per_second": 5.365,
+      "eval_runtime": 163.78,
+      "eval_samples_per_second": 5.373,
+      "eval_steps_per_second": 5.373,
       "step": 1
     },
     {
       "epoch": 0.00047898455274817384,
-      "grad_norm": 4.200049877166748,
+      "grad_norm": 3.92407488822937,
       "learning_rate": 4e-05,
       "loss": 3.3358,
       "step": 2
     },
     {
       "epoch": 0.0007184768291222608,
-      "grad_norm": 3.4988012313842773,
+      "grad_norm": 3.1619839668273926,
       "learning_rate": 6e-05,
-      "loss": 3.3931,
+      "loss": 3.3959,
       "step": 3
     },
     {
       "epoch": 0.0007184768291222608,
-      "eval_loss": 3.08847713470459,
-      "eval_runtime": 164.5024,
-      "eval_samples_per_second": 5.349,
-      "eval_steps_per_second": 5.349,
+      "eval_loss": 3.0963945388793945,
+      "eval_runtime": 163.8871,
+      "eval_samples_per_second": 5.37,
+      "eval_steps_per_second": 5.37,
       "step": 3
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e3eaba4fc887116ba05575a8a64bfbe0629dae4f12cb37cac79d895993962b
+oid sha256:06b93c27182e910c542b1e5fa166e9014b0895cb2f985ab3ed11d7d2d2b13627
 size 6776