Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efd90182dfa6a81ee47d9232456689b3603b96f32f042109f9b660e92bd1d92
+oid sha256:a5aa386a2c9834888591403fce04fe54adfa1b43b9303a7d60a963d38ab108b0
 size 72673016

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811fb76be471b2d061d804906e97d50c54cb2cf42f67f6d42e24bb576f4155dc
+oid sha256:96d730b214272ab23149f7fdff1c73ce01ac20891661aebf4d80825d10e2e10d
 size 36892564

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c54609d4e8cb89282e95eaa414501a7844ec04587efed4c10cd692e700fa780
+oid sha256:068d082f32e81259395603675356a1debbab51aee10f85787a0679721344dfcf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f40779dea4b6e00c1e20018f59c11c5cbe1ad90972d2ca12df667176352bf8
+oid sha256:6dfbeacc2e776d52cf1b01ae6429ccbc09a726e11618310ffaa3029c92c97a0e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08980054825597883,
+  "epoch": 0.09452689290103035,
   "eval_steps": 1000,
-  "global_step": 475,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2857,13 +2857,163 @@
       "learning_rate": 1.4112903225806454e-05,
       "loss": 1.6849,
       "step": 475
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3709677419354839e-05,
+      "loss": 1.9449,
+      "step": 476
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3306451612903225e-05,
+      "loss": 1.6432,
+      "step": 477
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 1.725,
+      "step": 478
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.25e-05,
+      "loss": 1.7214,
+      "step": 479
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2096774193548388e-05,
+      "loss": 1.9034,
+      "step": 480
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.1693548387096775e-05,
+      "loss": 1.691,
+      "step": 481
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.129032258064516e-05,
+      "loss": 2.1742,
+      "step": 482
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.0887096774193549e-05,
+      "loss": 1.6739,
+      "step": 483
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.0483870967741936e-05,
+      "loss": 1.7993,
+      "step": 484
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.0080645161290323e-05,
+      "loss": 1.544,
+      "step": 485
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 1.8974,
+      "step": 486
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.274193548387097e-06,
+      "loss": 1.774,
+      "step": 487
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.870967741935484e-06,
+      "loss": 1.4694,
+      "step": 488
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.46774193548387e-06,
+      "loss": 1.7621,
+      "step": 489
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 1.7785,
+      "step": 490
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.661290322580646e-06,
+      "loss": 2.0437,
+      "step": 491
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.258064516129033e-06,
+      "loss": 1.7494,
+      "step": 492
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.854838709677419e-06,
+      "loss": 1.7531,
+      "step": 493
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 1.9762,
+      "step": 494
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.048387096774194e-06,
+      "loss": 1.6643,
+      "step": 495
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.64516129032258e-06,
+      "loss": 1.8211,
+      "step": 496
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.241935483870968e-06,
+      "loss": 1.6926,
+      "step": 497
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 1.8867,
+      "step": 498
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.435483870967742e-06,
+      "loss": 1.6068,
+      "step": 499
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.032258064516129e-06,
+      "loss": 1.6741,
+      "step": 500
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2.279886077804544e+16,
+  "total_flos": 2.396005929934848e+16,
   "trial_name": null,
   "trial_params": null
 }