Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
-    "up_proj",
-    "q_proj",
     "o_proj",
+    "up_proj",
     "k_proj",
-    "v_proj"
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "gate_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 sha256:5344747694a61708e96c8a4e00e2799e1905bcadbdb1d01506a862ce2f444f53
+oid sha256:5ef4c6f7cc54411cdede7e80b8136e4bfdbec1de581df71f9ed00577c8a6e094
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ebce503da8b58137d2bff47b5cc743155774fb06bace205e1ffc048190703ce
+oid sha256:1658ba55bc06c88083b78c019c8e5d9b95b6e5ee29a094564902d13db9e4e9da
 size 160172858

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0008097165991902834,
-      "grad_norm": 5.4282379150390625,
+      "grad_norm": 5.243322849273682,
       "learning_rate": 2e-05,
       "loss": 14.12,
       "step": 1
@@ -18,14 +18,14 @@
     {
       "epoch": 0.0008097165991902834,
       "eval_loss": 16.039548873901367,
-      "eval_runtime": 47.0534,
-      "eval_samples_per_second": 5.547,
-      "eval_steps_per_second": 5.547,
+      "eval_runtime": 48.3021,
+      "eval_samples_per_second": 5.403,
+      "eval_steps_per_second": 5.403,
       "step": 1
     },
     {
       "epoch": 0.0016194331983805667,
-      "grad_norm": 5.544086456298828,
+      "grad_norm": 5.311802387237549,
       "learning_rate": 4e-05,
       "loss": 14.9434,
       "step": 2
@@ -34,73 +34,73 @@
       "epoch": 0.0024291497975708503,
       "grad_norm": NaN,
       "learning_rate": 4e-05,
-      "loss": 17.5639,
+      "loss": 17.5635,
       "step": 3
     },
     {
       "epoch": 0.0024291497975708503,
-      "eval_loss": 16.009519577026367,
-      "eval_runtime": 47.55,
-      "eval_samples_per_second": 5.489,
-      "eval_steps_per_second": 5.489,
+      "eval_loss": 16.010040283203125,
+      "eval_runtime": 47.6629,
+      "eval_samples_per_second": 5.476,
+      "eval_steps_per_second": 5.476,
       "step": 3
     },
     {
       "epoch": 0.0032388663967611335,
-      "grad_norm": 5.151875972747803,
+      "grad_norm": 4.934993267059326,
       "learning_rate": 6e-05,
-      "loss": 15.4592,
+      "loss": 15.4629,
       "step": 4
     },
     {
       "epoch": 0.004048582995951417,
-      "grad_norm": 7.000217914581299,
+      "grad_norm": 6.582982063293457,
       "learning_rate": 8e-05,
-      "loss": 14.515,
+      "loss": 14.5189,
       "step": 5
     },
     {
       "epoch": 0.004858299595141701,
-      "grad_norm": 7.624449253082275,
+      "grad_norm": 7.352993011474609,
       "learning_rate": 0.0001,
-      "loss": 14.5286,
+      "loss": 14.5364,
       "step": 6
     },
     {
       "epoch": 0.004858299595141701,
-      "eval_loss": 15.218199729919434,
-      "eval_runtime": 47.6689,
-      "eval_samples_per_second": 5.475,
-      "eval_steps_per_second": 5.475,
+      "eval_loss": 15.222670555114746,
+      "eval_runtime": 47.7487,
+      "eval_samples_per_second": 5.466,
+      "eval_steps_per_second": 5.466,
       "step": 6
     },
     {
       "epoch": 0.005668016194331984,
-      "grad_norm": 7.740715980529785,
+      "grad_norm": 7.531305313110352,
       "learning_rate": 0.00012,
-      "loss": 16.2921,
+      "loss": 16.2939,
       "step": 7
     },
     {
       "epoch": 0.006477732793522267,
-      "grad_norm": 8.621045112609863,
+      "grad_norm": 8.360276222229004,
       "learning_rate": 0.00014,
-      "loss": 13.8891,
+      "loss": 13.913,
       "step": 8
     },
     {
       "epoch": 0.0072874493927125505,
-      "grad_norm": 11.440580368041992,
+      "grad_norm": 11.318435668945312,
       "learning_rate": 0.00016,
-      "loss": 13.0894,
+      "loss": 13.087,
       "step": 9
     },
     {
       "epoch": 0.0072874493927125505,
-      "eval_loss": 12.089701652526855,
-      "eval_runtime": 47.7959,
-      "eval_samples_per_second": 5.461,
-      "eval_steps_per_second": 5.461,
+      "eval_loss": 12.104350090026855,
+      "eval_runtime": 45.0844,
+      "eval_samples_per_second": 5.789,
+      "eval_steps_per_second": 5.789,
       "step": 9
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba57699bba9b310c57bde7376897c4b366951d205389ca4384cb9831382eab5b
+oid sha256:a6e1305fc8f281ddb72b2abbc2f99245c4a414545702847872a68fca4d715eef
 size 6776