Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4e49830ca4084ef96f5c95d7ee075a79d349858c85e07cc39702093eaa3455
+oid sha256:49746f42e10d14a022ce382d0b0f149a2cab0eb4aa73d58370661e1ee25ce37c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2671111e7f8b7b54f65ad73c945053eefc3d6789e802b6ccdc864b5ab113e011
+oid sha256:b31d967effc0ea305c9e8a5260be0e8e95ca32237e42ccccff7da79ba25713b5
 size 160172858

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0008097165991902834,
-      "grad_norm": 5.536149024963379,
+      "grad_norm": 5.4282379150390625,
       "learning_rate": 2e-05,
       "loss": 14.12,
       "step": 1
@@ -18,14 +18,14 @@
     {
       "epoch": 0.0008097165991902834,
       "eval_loss": 16.039548873901367,
-      "eval_runtime": 46.298,
-      "eval_samples_per_second": 5.637,
-      "eval_steps_per_second": 5.637,
+      "eval_runtime": 47.0534,
+      "eval_samples_per_second": 5.547,
+      "eval_steps_per_second": 5.547,
       "step": 1
     },
     {
       "epoch": 0.0016194331983805667,
-      "grad_norm": 5.57291841506958,
+      "grad_norm": 5.544086456298828,
       "learning_rate": 4e-05,
       "loss": 14.9434,
       "step": 2
@@ -34,15 +34,15 @@
       "epoch": 0.0024291497975708503,
       "grad_norm": NaN,
       "learning_rate": 4e-05,
-      "loss": 17.5653,
+      "loss": 17.5639,
       "step": 3
     },
     {
       "epoch": 0.0024291497975708503,
-      "eval_loss": 16.010469436645508,
-      "eval_runtime": 48.2421,
-      "eval_samples_per_second": 5.41,
-      "eval_steps_per_second": 5.41,
+      "eval_loss": 16.009519577026367,
+      "eval_runtime": 47.55,
+      "eval_samples_per_second": 5.489,
+      "eval_steps_per_second": 5.489,
       "step": 3
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7eb56965fd55276c944caeebbd855891392f90553ede8609b47d5de737c680
+oid sha256:ba57699bba9b310c57bde7376897c4b366951d205389ca4384cb9831382eab5b
 size 6776