Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "gate_proj",
     "v_proj",
-    "down_proj",
     "o_proj",
+    "k_proj",
     "q_proj",
-    "up_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:f4dbc8af9279899a6b4ebcdcaf3794013f2ec5f32a3243c79baabbbfba5edc29
+oid sha256:b3e868b930f02b4fa547a12fe1eb3c6b45f2144772990bb5891352cf5115c54d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f644799f195f73e766580a1ce39c2b7da8e58c392f7f76f8efaf2c93062b87b6
+oid sha256:c00dd59a9b7b6ff1575563c6a0fa2f9ae3e14f5cb4b7ad9756e53a0cd0f79f6f
 size 160172858

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.00023949227637408692,
-      "grad_norm": 5.223796367645264,
+      "grad_norm": 5.190128803253174,
       "learning_rate": 2e-05,
       "loss": 2.4864,
       "step": 1
@@ -18,31 +18,31 @@
     {
       "epoch": 0.00023949227637408692,
       "eval_loss": 3.196671962738037,
-      "eval_runtime": 163.78,
-      "eval_samples_per_second": 5.373,
-      "eval_steps_per_second": 5.373,
+      "eval_runtime": 163.6418,
+      "eval_samples_per_second": 5.378,
+      "eval_steps_per_second": 5.378,
       "step": 1
     },
     {
       "epoch": 0.00047898455274817384,
-      "grad_norm": 3.92407488822937,
+      "grad_norm": 3.8827998638153076,
       "learning_rate": 4e-05,
       "loss": 3.3358,
       "step": 2
     },
     {
       "epoch": 0.0007184768291222608,
-      "grad_norm": 3.1619839668273926,
+      "grad_norm": 3.203981876373291,
       "learning_rate": 6e-05,
-      "loss": 3.3959,
+      "loss": 3.3946,
       "step": 3
     },
     {
       "epoch": 0.0007184768291222608,
-      "eval_loss": 3.0963945388793945,
-      "eval_runtime": 163.8871,
-      "eval_samples_per_second": 5.37,
-      "eval_steps_per_second": 5.37,
+      "eval_loss": 3.0946106910705566,
+      "eval_runtime": 162.7901,
+      "eval_samples_per_second": 5.406,
+      "eval_steps_per_second": 5.406,
       "step": 3
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b93c27182e910c542b1e5fa166e9014b0895cb2f985ab3ed11d7d2d2b13627
+oid sha256:d9c99d0e2f5b8cc5e216c0a981ae420dfd0fdc085832d4176287c753653f2960
 size 6776