Training in progress, step 475, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007809edd7af4f540d9ef711501d9600279a89047629f58c6f5b36c1156a331e
+oid sha256:dc3524aa66c0624c20b7ed75f0239732b9a0d674504063ee93ca37e881f117d7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34943ec29084e48b3f49590d338f41865c45622b34f694d06283ca1ce73a16b8
+oid sha256:289f7545377a6902ccc671e39a89e786cef894b58b529dadb726c9ebb9b6db41
 size 42546196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d29c136a058d95ad4140ff9606955f9a05a50a3e532f1b4839b76863188a7c
+oid sha256:7d04fa6ba62e6d2693994357040d1f8b0df1a2292ac61d59108919d588e97608
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e97d6e4a8f37abdf7b71b21660735ad9bd8fbfe143b0732cce58d9053bbb5d
+oid sha256:829afd908950b55f19acd29cd95ce4b7eeb6e3a96dff858cc79db502814ed864
 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": 2.1370967741935487e-05,
       "loss": 1.5823,
       "step": 450
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.0967741935483873e-05,
+      "loss": 1.502,
+      "step": 451
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.056451612903226e-05,
+      "loss": 1.4476,
+      "step": 452
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.0161290322580645e-05,
+      "loss": 1.3888,
+      "step": 453
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.975806451612903e-05,
+      "loss": 1.4592,
+      "step": 454
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 1.489,
+      "step": 455
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8951612903225807e-05,
+      "loss": 1.6278,
+      "step": 456
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8548387096774193e-05,
+      "loss": 1.7016,
+      "step": 457
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8145161290322583e-05,
+      "loss": 1.622,
+      "step": 458
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.774193548387097e-05,
+      "loss": 1.5188,
+      "step": 459
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.733870967741936e-05,
+      "loss": 1.4665,
+      "step": 460
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.693548387096774e-05,
+      "loss": 1.6974,
+      "step": 461
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.653225806451613e-05,
+      "loss": 1.6466,
+      "step": 462
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 1.6057,
+      "step": 463
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5725806451612903e-05,
+      "loss": 1.489,
+      "step": 464
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5322580645161292e-05,
+      "loss": 1.7375,
+      "step": 465
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4919354838709679e-05,
+      "loss": 1.5686,
+      "step": 466
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4516129032258066e-05,
+      "loss": 1.382,
+      "step": 467
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4112903225806454e-05,
+      "loss": 1.7037,
+      "step": 468
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3709677419354839e-05,
+      "loss": 1.5521,
+      "step": 469
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3306451612903225e-05,
+      "loss": 1.3172,
+      "step": 470
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 1.4997,
+      "step": 471
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.25e-05,
+      "loss": 1.7076,
+      "step": 472
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2096774193548388e-05,
+      "loss": 1.432,
+      "step": 473
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.1693548387096775e-05,
+      "loss": 1.8895,
+      "step": 474
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.129032258064516e-05,
+      "loss": 1.536,
+      "step": 475
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2.779017123638477e+16,
+  "total_flos": 2.920625653658419e+16,
   "trial_name": null,
   "trial_params": null
 }