Training in progress, step 475, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0240065ca1b5ed67384fd5aaf0b8316e661300a63f84ad84cbbf3755931d6749
+oid sha256:1efd90182dfa6a81ee47d9232456689b3603b96f32f042109f9b660e92bd1d92
 size 72673016

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78478f107d623e983c32299c6998f1d12bc2f1b52b0affbbae8200ea5787c998
+oid sha256:811fb76be471b2d061d804906e97d50c54cb2cf42f67f6d42e24bb576f4155dc
 size 36892564

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d39aec35151764d808003fba5886e79decf24837f16631ca32bcf663661b5fa
+oid sha256:7c54609d4e8cb89282e95eaa414501a7844ec04587efed4c10cd692e700fa780
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3caecce00506e02ee5b8d54b798aaba8f7686aa7732466b92b01f7b66819e6f
+oid sha256:c7f40779dea4b6e00c1e20018f59c11c5cbe1ad90972d2ca12df667176352bf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08507420361092731,
+  "epoch": 0.08980054825597883,
   "eval_steps": 1000,
-  "global_step": 450,
+  "global_step": 475,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2707,13 +2707,163 @@
       "learning_rate": 2.4193548387096777e-05,
       "loss": 1.7733,
       "step": 450
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.3790322580645163e-05,
+      "loss": 1.6785,
+      "step": 451
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.338709677419355e-05,
+      "loss": 1.6109,
+      "step": 452
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.2983870967741935e-05,
+      "loss": 1.5554,
+      "step": 453
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.258064516129032e-05,
+      "loss": 1.5901,
+      "step": 454
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.217741935483871e-05,
+      "loss": 1.687,
+      "step": 455
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.1774193548387097e-05,
+      "loss": 1.7672,
+      "step": 456
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.1370967741935487e-05,
+      "loss": 1.9025,
+      "step": 457
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.0967741935483873e-05,
+      "loss": 1.804,
+      "step": 458
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.056451612903226e-05,
+      "loss": 1.725,
+      "step": 459
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.0161290322580645e-05,
+      "loss": 1.6565,
+      "step": 460
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.975806451612903e-05,
+      "loss": 1.8996,
+      "step": 461
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 1.7974,
+      "step": 462
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8951612903225807e-05,
+      "loss": 1.8168,
+      "step": 463
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8548387096774193e-05,
+      "loss": 1.7012,
+      "step": 464
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8145161290322583e-05,
+      "loss": 1.9804,
+      "step": 465
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.774193548387097e-05,
+      "loss": 1.7656,
+      "step": 466
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.733870967741936e-05,
+      "loss": 1.5495,
+      "step": 467
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.693548387096774e-05,
+      "loss": 1.8389,
+      "step": 468
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.653225806451613e-05,
+      "loss": 1.7781,
+      "step": 469
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 1.6191,
+      "step": 470
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5725806451612903e-05,
+      "loss": 1.6805,
+      "step": 471
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5322580645161292e-05,
+      "loss": 1.9133,
+      "step": 472
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4919354838709679e-05,
+      "loss": 1.5507,
+      "step": 473
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4516129032258066e-05,
+      "loss": 2.0498,
+      "step": 474
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4112903225806454e-05,
+      "loss": 1.6849,
+      "step": 475
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2.1692039993327616e+16,
+  "total_flos": 2.279886077804544e+16,
   "trial_name": null,
   "trial_params": null
 }