Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
     "v_proj",
-    "o_proj",
     "k_proj",
-    "q_proj",
-    "up_proj"
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_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 sha256:787efbd74eef37f370806a03f8001a6e532fc5e0610c35dba24a90fc1c51e77a
+oid sha256:eee58fcfc933c5b893ee33209f23fea23abe21f45cc727ed46f6d1d27c0edfd5
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d73ff117959389698c8a86b089721d57be52e50ff3cce34de14a77a7d3016d1
+oid sha256:22bb10b2203471ee873276c170300c86ad2207d7e13dfdfea31f49ea77924698
 size 160172858

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.00023949227637408692,
-      "grad_norm": 5.190128803253174,
+      "grad_norm": 5.556643962860107,
       "learning_rate": 2e-05,
       "loss": 2.4864,
       "step": 1
@@ -18,96 +18,96 @@
     {
       "epoch": 0.00023949227637408692,
       "eval_loss": 3.196671962738037,
-      "eval_runtime": 163.6418,
-      "eval_samples_per_second": 5.378,
-      "eval_steps_per_second": 5.378,
+      "eval_runtime": 164.0333,
+      "eval_samples_per_second": 5.365,
+      "eval_steps_per_second": 5.365,
       "step": 1
     },
     {
       "epoch": 0.00047898455274817384,
-      "grad_norm": 3.8827998638153076,
+      "grad_norm": 4.200049877166748,
       "learning_rate": 4e-05,
       "loss": 3.3358,
       "step": 2
     },
     {
       "epoch": 0.0007184768291222608,
-      "grad_norm": 3.203981876373291,
+      "grad_norm": 3.4988012313842773,
       "learning_rate": 6e-05,
-      "loss": 3.3946,
+      "loss": 3.3931,
       "step": 3
     },
     {
       "epoch": 0.0007184768291222608,
-      "eval_loss": 3.0946106910705566,
-      "eval_runtime": 162.7901,
-      "eval_samples_per_second": 5.406,
-      "eval_steps_per_second": 5.406,
+      "eval_loss": 3.08847713470459,
+      "eval_runtime": 164.5024,
+      "eval_samples_per_second": 5.349,
+      "eval_steps_per_second": 5.349,
       "step": 3
     },
     {
       "epoch": 0.0009579691054963477,
-      "grad_norm": 3.0879592895507812,
+      "grad_norm": 3.2402377128601074,
       "learning_rate": 8e-05,
-      "loss": 2.7666,
+      "loss": 2.761,
       "step": 4
     },
     {
       "epoch": 0.0011974613818704347,
-      "grad_norm": 3.3717029094696045,
+      "grad_norm": 3.507751703262329,
       "learning_rate": 0.0001,
-      "loss": 2.7991,
+      "loss": 2.7889,
       "step": 5
     },
     {
       "epoch": 0.0014369536582445215,
-      "grad_norm": 2.83575439453125,
+      "grad_norm": 2.906939744949341,
       "learning_rate": 0.00012,
-      "loss": 1.8184,
+      "loss": 1.8125,
       "step": 6
     },
     {
       "epoch": 0.0014369536582445215,
-      "eval_loss": 2.6198861598968506,
-      "eval_runtime": 162.8545,
-      "eval_samples_per_second": 5.404,
-      "eval_steps_per_second": 5.404,
+      "eval_loss": 2.6185643672943115,
+      "eval_runtime": 165.0188,
+      "eval_samples_per_second": 5.333,
+      "eval_steps_per_second": 5.333,
       "step": 6
     },
     {
       "epoch": 0.0016764459346186086,
-      "grad_norm": 2.426558256149292,
+      "grad_norm": 2.618673324584961,
       "learning_rate": 0.00014,
-      "loss": 2.6655,
+      "loss": 2.6648,
       "step": 7
     },
     {
       "epoch": 0.0019159382109926954,
-      "grad_norm": 1.7445547580718994,
+      "grad_norm": 1.8121130466461182,
       "learning_rate": 0.00016,
-      "loss": 1.9561,
+      "loss": 1.9557,
       "step": 8
     },
     {
       "epoch": 0.0021554304873667826,
-      "grad_norm": 1.1460472345352173,
+      "grad_norm": 1.2346168756484985,
       "learning_rate": 0.00018,
-      "loss": 1.7204,
+      "loss": 1.7235,
       "step": 9
     },
     {
       "epoch": 0.0021554304873667826,
-      "eval_loss": 2.171725034713745,
-      "eval_runtime": 163.204,
-      "eval_samples_per_second": 5.392,
-      "eval_steps_per_second": 5.392,
+      "eval_loss": 2.1706855297088623,
+      "eval_runtime": 163.8793,
+      "eval_samples_per_second": 5.37,
+      "eval_steps_per_second": 5.37,
       "step": 9
     },
     {
       "epoch": 0.0023949227637408694,
-      "grad_norm": 1.9641551971435547,
+      "grad_norm": 1.9918853044509888,
       "learning_rate": 0.0002,
-      "loss": 1.5788,
+      "loss": 1.5796,
       "step": 10
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c99d0e2f5b8cc5e216c0a981ae420dfd0fdc085832d4176287c753653f2960
+oid sha256:c8e3eaba4fc887116ba05575a8a64bfbe0629dae4f12cb37cac79d895993962b
 size 6776