Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "query_key_value",
     "dense_4h_to_h",
-    "dense_h_to_4h"
+    "dense_h_to_4h",
+    "query_key_value",
+    "dense"
   ],
   "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 sha256:2cdd41b8034aebed5f4cfddad21d3fd7abe661ba76b481044ea408ec6239fa06
+oid sha256:cb61b34b9e1f46eb4e705e7a0c6abfb38ed940698dceb52d57da6ed10f837632
 size 792912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d09cd9892b864faba5161963a64528f6fc1f5a662ed0c8448f4e47d0c3795f9
+oid sha256:5d1c45c3d4ee56fda3305eaf57bea7795eb21ecb91a887fa6fff461f83d7cd7d
 size 807226

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0013214403700033035,
-      "grad_norm": 36784.828125,
+      "grad_norm": 35878.53515625,
       "learning_rate": 2e-05,
       "loss": 42.0391,
       "step": 1
@@ -18,96 +18,96 @@
     {
       "epoch": 0.0013214403700033035,
       "eval_loss": 10.801332473754883,
-      "eval_runtime": 36.8803,
-      "eval_samples_per_second": 8.65,
-      "eval_steps_per_second": 4.338,
+      "eval_runtime": 37.0602,
+      "eval_samples_per_second": 8.608,
+      "eval_steps_per_second": 4.317,
       "step": 1
     },
     {
       "epoch": 0.002642880740006607,
-      "grad_norm": 44555.4453125,
+      "grad_norm": 40164.90625,
       "learning_rate": 4e-05,
       "loss": 41.0703,
       "step": 2
     },
     {
       "epoch": 0.003964321110009911,
-      "grad_norm": 54956.5703125,
+      "grad_norm": 22879.40234375,
       "learning_rate": 6e-05,
-      "loss": 40.9297,
+      "loss": 42.3828,
       "step": 3
     },
     {
       "epoch": 0.003964321110009911,
-      "eval_loss": 10.430495262145996,
-      "eval_runtime": 36.668,
-      "eval_samples_per_second": 8.7,
-      "eval_steps_per_second": 4.363,
+      "eval_loss": 10.28499698638916,
+      "eval_runtime": 36.8196,
+      "eval_samples_per_second": 8.664,
+      "eval_steps_per_second": 4.346,
       "step": 3
     },
     {
       "epoch": 0.005285761480013214,
-      "grad_norm": 35561.53515625,
+      "grad_norm": 26312.224609375,
       "learning_rate": 8e-05,
-      "loss": 37.1484,
+      "loss": 39.375,
       "step": 4
     },
     {
       "epoch": 0.006607201850016518,
-      "grad_norm": 10920.60546875,
+      "grad_norm": 30341.833984375,
       "learning_rate": 0.0001,
-      "loss": 39.7656,
+      "loss": 42.0781,
       "step": 5
     },
     {
       "epoch": 0.007928642220019821,
-      "grad_norm": 28439.447265625,
+      "grad_norm": 72681.9140625,
       "learning_rate": 0.00012,
-      "loss": 39.2031,
+      "loss": 42.0234,
       "step": 6
     },
     {
       "epoch": 0.007928642220019821,
-      "eval_loss": 8.984987258911133,
-      "eval_runtime": 36.6163,
-      "eval_samples_per_second": 8.712,
-      "eval_steps_per_second": 4.37,
+      "eval_loss": 9.394837379455566,
+      "eval_runtime": 36.7072,
+      "eval_samples_per_second": 8.69,
+      "eval_steps_per_second": 4.359,
       "step": 6
     },
     {
       "epoch": 0.009250082590023126,
-      "grad_norm": 11823.828125,
+      "grad_norm": 22986.171875,
       "learning_rate": 0.00014,
-      "loss": 31.6719,
+      "loss": 30.3867,
       "step": 7
     },
     {
       "epoch": 0.010571522960026428,
-      "grad_norm": 66411.34375,
+      "grad_norm": 9130.1826171875,
       "learning_rate": 0.00016,
-      "loss": 30.0234,
+      "loss": 33.0547,
       "step": 8
     },
     {
       "epoch": 0.011892963330029732,
-      "grad_norm": 18029.048828125,
+      "grad_norm": 27018.677734375,
       "learning_rate": 0.00018,
-      "loss": 30.0859,
+      "loss": 28.6055,
       "step": 9
     },
     {
       "epoch": 0.011892963330029732,
-      "eval_loss": 7.419425964355469,
-      "eval_runtime": 34.0691,
-      "eval_samples_per_second": 9.363,
-      "eval_steps_per_second": 4.696,
+      "eval_loss": 7.373456954956055,
+      "eval_runtime": 32.2691,
+      "eval_samples_per_second": 9.886,
+      "eval_steps_per_second": 4.958,
       "step": 9
     },
     {
       "epoch": 0.013214403700033036,
-      "grad_norm": 23422.70703125,
+      "grad_norm": 43709.67578125,
       "learning_rate": 0.0002,
-      "loss": 28.3867,
+      "loss": 25.9141,
       "step": 10
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097bd66dc3d47f5850103823e5f488e05d11aad4916f7f9c6e0b797fc472f3b8
+oid sha256:2a9bb157562b990b6006ae6ee2dc7d90066e04ec9df07e3b9c02378d3f068f6d
 size 6776