Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
+    "dense_h_to_4h",
     "query_key_value",
-    "dense_4h_to_h",
-    "dense_h_to_4h"
+    "dense",
+    "dense_4h_to_h"
   ],
   "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 sha256:57d10411134e4e8b7edda32ed065076e3056c883ffa784c0858322790cbad7b6
+oid sha256:d45b8f2e0055ebb30f1397db12b068ac241a6c0352338292f386717953cc3b0d
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeab8927a565136c9f73997876730b368ec0c248749f7d2e08d63b4928c2539b
+oid sha256:849a792038c1a3e942f39d68c654e6a4d5d783afcaa1b9ad21de0f5556b1227a
 size 17190970

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0021727322107550242,
-      "grad_norm": 37.16297912597656,
+      "grad_norm": 38.3082275390625,
       "learning_rate": 2e-05,
       "loss": 26.2925,
       "step": 1
@@ -18,96 +18,96 @@
     {
       "epoch": 0.0021727322107550242,
       "eval_loss": 6.362123489379883,
-      "eval_runtime": 69.8308,
-      "eval_samples_per_second": 2.778,
-      "eval_steps_per_second": 1.389,
+      "eval_runtime": 69.9182,
+      "eval_samples_per_second": 2.775,
+      "eval_steps_per_second": 1.387,
       "step": 1
     },
     {
       "epoch": 0.0043454644215100485,
-      "grad_norm": 32.820220947265625,
+      "grad_norm": 34.35226821899414,
       "learning_rate": 4e-05,
       "loss": 23.3629,
       "step": 2
     },
     {
       "epoch": 0.006518196632265073,
-      "grad_norm": 45.58674621582031,
+      "grad_norm": 46.58251953125,
       "learning_rate": 6e-05,
-      "loss": 31.4505,
+      "loss": 31.458,
       "step": 3
     },
     {
       "epoch": 0.006518196632265073,
-      "eval_loss": 6.055120944976807,
-      "eval_runtime": 68.8054,
-      "eval_samples_per_second": 2.82,
-      "eval_steps_per_second": 1.41,
+      "eval_loss": 6.052692413330078,
+      "eval_runtime": 69.8071,
+      "eval_samples_per_second": 2.779,
+      "eval_steps_per_second": 1.39,
       "step": 3
     },
     {
       "epoch": 0.008690928843020097,
-      "grad_norm": 33.71705627441406,
+      "grad_norm": 34.892906188964844,
       "learning_rate": 8e-05,
-      "loss": 22.7458,
+      "loss": 22.7088,
       "step": 4
     },
     {
       "epoch": 0.010863661053775122,
-      "grad_norm": 26.417665481567383,
+      "grad_norm": 27.14177703857422,
       "learning_rate": 0.0001,
-      "loss": 19.5417,
+      "loss": 19.6406,
       "step": 5
     },
     {
       "epoch": 0.013036393264530146,
-      "grad_norm": 31.988718032836914,
+      "grad_norm": 33.119747161865234,
       "learning_rate": 0.00012,
-      "loss": 24.3794,
+      "loss": 24.4518,
       "step": 6
     },
     {
       "epoch": 0.013036393264530146,
-      "eval_loss": 4.7808332443237305,
-      "eval_runtime": 67.3901,
-      "eval_samples_per_second": 2.879,
-      "eval_steps_per_second": 1.439,
+      "eval_loss": 4.772887706756592,
+      "eval_runtime": 70.422,
+      "eval_samples_per_second": 2.755,
+      "eval_steps_per_second": 1.377,
       "step": 6
     },
     {
       "epoch": 0.015209125475285171,
-      "grad_norm": 29.322267532348633,
+      "grad_norm": 29.63689422607422,
       "learning_rate": 0.00014,
-      "loss": 19.7093,
+      "loss": 19.6883,
       "step": 7
     },
     {
       "epoch": 0.017381857686040194,
-      "grad_norm": 27.37926483154297,
+      "grad_norm": 27.822065353393555,
       "learning_rate": 0.00016,
-      "loss": 18.7525,
+      "loss": 18.6915,
       "step": 8
     },
     {
       "epoch": 0.01955458989679522,
-      "grad_norm": 28.797134399414062,
+      "grad_norm": 29.270885467529297,
       "learning_rate": 0.00018,
-      "loss": 17.7134,
+      "loss": 17.4177,
       "step": 9
     },
     {
       "epoch": 0.01955458989679522,
-      "eval_loss": 3.6513190269470215,
-      "eval_runtime": 68.1618,
-      "eval_samples_per_second": 2.846,
-      "eval_steps_per_second": 1.423,
+      "eval_loss": 3.6328675746917725,
+      "eval_runtime": 69.2865,
+      "eval_samples_per_second": 2.8,
+      "eval_steps_per_second": 1.4,
       "step": 9
     },
     {
       "epoch": 0.021727322107550243,
-      "grad_norm": 34.8036003112793,
+      "grad_norm": 35.51152038574219,
       "learning_rate": 0.0002,
-      "loss": 16.0472,
+      "loss": 15.9869,
       "step": 10
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7039ee5e93e39ae75f53f38b044442799d1e30cd7ff9a83e519c275615c657cc
+oid sha256:b5626cd2613597d38b016ac503b35d867aeed1b5b31a1151465dc38b87f3fc7b
 size 6776