Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:763a2e6211692a29489c663be78e38405ddeebee7123cf422bef0897660522b5
+oid sha256:1c004f34c54fd1f3daf8e261d84a7a1757591cd731ccc03e414920ea5c14307b
 size 1852600

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e89a0b2817e3604c09bf67f0d4eb755faa1736d27ad6237f97d28a1b19ceb5
+oid sha256:851725364a78e2688d08b65ac507b37eb1cd1824bb79778d93a924c368ade572
 size 1108346

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f2397b349c3d7d219331d0f9f17be72806daa1aedfdb0787087c6d5818527b
+oid sha256:471500541aec9e4570286570c42981a081703fc6b0eca9480f56cf2521c795bd
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c26800e6aad79542c71a265990c35470e0f0c258d88e99aef73f16b83c77e16
+oid sha256:69c5572f1342b41c6a930522d275b4fa95be59a8658b646079d52144a96dd33c
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 146.4307504575961,
+  "epoch": 148.87126296522268,
   "eval_steps": 500,
-  "global_step": 30000,
+  "global_step": 30500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10507,6 +10507,181 @@
       "learning_rate": 3.934426229508197e-06,
       "loss": 0.1866,
       "step": 30000
+    },
+    {
+      "epoch": 146.52837095790116,
+      "grad_norm": 2.8058741092681885,
+      "learning_rate": 3.8032786885245906e-06,
+      "loss": 0.1751,
+      "step": 30020
+    },
+    {
+      "epoch": 146.62599145820622,
+      "grad_norm": 2.752978563308716,
+      "learning_rate": 3.672131147540984e-06,
+      "loss": 0.1826,
+      "step": 30040
+    },
+    {
+      "epoch": 146.7236119585113,
+      "grad_norm": 3.0315961837768555,
+      "learning_rate": 3.540983606557377e-06,
+      "loss": 0.1623,
+      "step": 30060
+    },
+    {
+      "epoch": 146.82123245881635,
+      "grad_norm": 3.3782765865325928,
+      "learning_rate": 3.409836065573771e-06,
+      "loss": 0.1784,
+      "step": 30080
+    },
+    {
+      "epoch": 146.9188529591214,
+      "grad_norm": 2.961002826690674,
+      "learning_rate": 3.278688524590164e-06,
+      "loss": 0.1764,
+      "step": 30100
+    },
+    {
+      "epoch": 147.0164734594265,
+      "grad_norm": 3.775484561920166,
+      "learning_rate": 3.1475409836065574e-06,
+      "loss": 0.1595,
+      "step": 30120
+    },
+    {
+      "epoch": 147.11409395973155,
+      "grad_norm": 4.18531608581543,
+      "learning_rate": 3.016393442622951e-06,
+      "loss": 0.1599,
+      "step": 30140
+    },
+    {
+      "epoch": 147.2117144600366,
+      "grad_norm": 2.9723432064056396,
+      "learning_rate": 2.8852459016393446e-06,
+      "loss": 0.159,
+      "step": 30160
+    },
+    {
+      "epoch": 147.30933496034166,
+      "grad_norm": 3.2833070755004883,
+      "learning_rate": 2.754098360655738e-06,
+      "loss": 0.1657,
+      "step": 30180
+    },
+    {
+      "epoch": 147.40695546064674,
+      "grad_norm": 3.4174959659576416,
+      "learning_rate": 2.6229508196721314e-06,
+      "loss": 0.175,
+      "step": 30200
+    },
+    {
+      "epoch": 147.5045759609518,
+      "grad_norm": 3.3127195835113525,
+      "learning_rate": 2.491803278688525e-06,
+      "loss": 0.1815,
+      "step": 30220
+    },
+    {
+      "epoch": 147.60219646125685,
+      "grad_norm": 3.7137949466705322,
+      "learning_rate": 2.360655737704918e-06,
+      "loss": 0.198,
+      "step": 30240
+    },
+    {
+      "epoch": 147.69981696156194,
+      "grad_norm": 2.630924701690674,
+      "learning_rate": 2.2295081967213117e-06,
+      "loss": 0.1687,
+      "step": 30260
+    },
+    {
+      "epoch": 147.797437461867,
+      "grad_norm": 3.330245018005371,
+      "learning_rate": 2.098360655737705e-06,
+      "loss": 0.1581,
+      "step": 30280
+    },
+    {
+      "epoch": 147.89505796217205,
+      "grad_norm": 3.237410068511963,
+      "learning_rate": 1.9672131147540985e-06,
+      "loss": 0.2022,
+      "step": 30300
+    },
+    {
+      "epoch": 147.99267846247713,
+      "grad_norm": 2.633331537246704,
+      "learning_rate": 1.836065573770492e-06,
+      "loss": 0.1613,
+      "step": 30320
+    },
+    {
+      "epoch": 148.09029896278219,
+      "grad_norm": 2.527902603149414,
+      "learning_rate": 1.7049180327868855e-06,
+      "loss": 0.1749,
+      "step": 30340
+    },
+    {
+      "epoch": 148.18791946308724,
+      "grad_norm": 2.9230234622955322,
+      "learning_rate": 1.5737704918032787e-06,
+      "loss": 0.1464,
+      "step": 30360
+    },
+    {
+      "epoch": 148.28553996339232,
+      "grad_norm": 2.591038703918457,
+      "learning_rate": 1.4426229508196723e-06,
+      "loss": 0.1819,
+      "step": 30380
+    },
+    {
+      "epoch": 148.38316046369738,
+      "grad_norm": 3.6826913356781006,
+      "learning_rate": 1.3114754098360657e-06,
+      "loss": 0.1909,
+      "step": 30400
+    },
+    {
+      "epoch": 148.48078096400243,
+      "grad_norm": 3.1828205585479736,
+      "learning_rate": 1.180327868852459e-06,
+      "loss": 0.1727,
+      "step": 30420
+    },
+    {
+      "epoch": 148.57840146430752,
+      "grad_norm": 3.3356974124908447,
+      "learning_rate": 1.0491803278688525e-06,
+      "loss": 0.1624,
+      "step": 30440
+    },
+    {
+      "epoch": 148.67602196461257,
+      "grad_norm": 3.1692721843719482,
+      "learning_rate": 9.18032786885246e-07,
+      "loss": 0.1769,
+      "step": 30460
+    },
+    {
+      "epoch": 148.77364246491763,
+      "grad_norm": 2.968018054962158,
+      "learning_rate": 7.868852459016393e-07,
+      "loss": 0.1594,
+      "step": 30480
+    },
+    {
+      "epoch": 148.87126296522268,
+      "grad_norm": 3.693136692047119,
+      "learning_rate": 6.557377049180328e-07,
+      "loss": 0.1927,
+      "step": 30500
     }
   ],
   "logging_steps": 20,
@@ -10526,7 +10701,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.859765296186163e+17,
+  "total_flos": 3.924112697660375e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null