Training in progress, step 475, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35fdc3732366dff9de600a01d5ce5145f7d0e07bceb43814d746a0080a65e66d
+oid sha256:3f91a032091b4d44d60bb0e09eb86f9d305f9365256cbdf069a77d1b7cfcaa95
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3d0361efcd4dd0b0d6b12d05a30f694592f9c4135c2d8f41fb997c555f8c24
+oid sha256:d592ae1b646b7d407d98d03dc5e76455a2198a6440aa75c55be4c11c27328d76
 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": 1.5753,
       "step": 450
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.0967741935483873e-05,
+      "loss": 1.4993,
+      "step": 451
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.056451612903226e-05,
+      "loss": 1.4323,
+      "step": 452
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.0161290322580645e-05,
+      "loss": 1.3859,
+      "step": 453
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.975806451612903e-05,
+      "loss": 1.4642,
+      "step": 454
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 1.5044,
+      "step": 455
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8951612903225807e-05,
+      "loss": 1.6467,
+      "step": 456
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8548387096774193e-05,
+      "loss": 1.7044,
+      "step": 457
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8145161290322583e-05,
+      "loss": 1.6132,
+      "step": 458
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.774193548387097e-05,
+      "loss": 1.5187,
+      "step": 459
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.733870967741936e-05,
+      "loss": 1.4658,
+      "step": 460
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.693548387096774e-05,
+      "loss": 1.6948,
+      "step": 461
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.653225806451613e-05,
+      "loss": 1.6474,
+      "step": 462
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 1.6093,
+      "step": 463
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5725806451612903e-05,
+      "loss": 1.495,
+      "step": 464
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5322580645161292e-05,
+      "loss": 1.7579,
+      "step": 465
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4919354838709679e-05,
+      "loss": 1.5608,
+      "step": 466
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4516129032258066e-05,
+      "loss": 1.3834,
+      "step": 467
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4112903225806454e-05,
+      "loss": 1.683,
+      "step": 468
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3709677419354839e-05,
+      "loss": 1.5524,
+      "step": 469
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3306451612903225e-05,
+      "loss": 1.3225,
+      "step": 470
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 1.5097,
+      "step": 471
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.25e-05,
+      "loss": 1.7213,
+      "step": 472
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2096774193548388e-05,
+      "loss": 1.4272,
+      "step": 473
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.1693548387096775e-05,
+      "loss": 1.884,
+      "step": 474
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.129032258064516e-05,
+      "loss": 1.5357,
+      "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
 }