Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063630da7714c28e7445fad7963e733bae608521175f5588d669746696d76a8f
+oid sha256:35fdc3732366dff9de600a01d5ce5145f7d0e07bceb43814d746a0080a65e66d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daaf0e6df41de52fae1f6bc78c5532c415025e5608502f45ced7bc3e0802c598
+oid sha256:2c3d0361efcd4dd0b0d6b12d05a30f694592f9c4135c2d8f41fb997c555f8c24
 size 42546196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87113e4cb84c061b6cfa020723b20af9795b52023187a5bcaf6406cd9d955f48
+oid sha256:c0d29c136a058d95ad4140ff9606955f9a05a50a3e532f1b4839b76863188a7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa8d596f677db656253aa29e7d5c21bde227ca39a0071d240ec6415eee1bd74
+oid sha256:d4e97d6e4a8f37abdf7b71b21660735ad9bd8fbfe143b0732cce58d9053bbb5d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08034785896587579,
+  "epoch": 0.08507420361092731,
   "eval_steps": 1000,
-  "global_step": 425,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2557,13 +2557,163 @@
       "learning_rate": 3.1451612903225806e-05,
       "loss": 1.6903,
       "step": 425
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.1048387096774195e-05,
+      "loss": 1.6982,
+      "step": 426
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.0645161290322585e-05,
+      "loss": 1.6198,
+      "step": 427
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.024193548387097e-05,
+      "loss": 1.4291,
+      "step": 428
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9838709677419357e-05,
+      "loss": 1.5107,
+      "step": 429
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9435483870967743e-05,
+      "loss": 1.5258,
+      "step": 430
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 1.6765,
+      "step": 431
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.862903225806452e-05,
+      "loss": 1.6493,
+      "step": 432
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.822580645161291e-05,
+      "loss": 1.69,
+      "step": 433
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.7822580645161288e-05,
+      "loss": 1.5759,
+      "step": 434
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.7419354838709678e-05,
+      "loss": 1.6756,
+      "step": 435
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.7016129032258064e-05,
+      "loss": 1.6169,
+      "step": 436
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.661290322580645e-05,
+      "loss": 1.6075,
+      "step": 437
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.620967741935484e-05,
+      "loss": 1.8312,
+      "step": 438
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.5806451612903226e-05,
+      "loss": 1.7522,
+      "step": 439
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.5403225806451615e-05,
+      "loss": 1.719,
+      "step": 440
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.5e-05,
+      "loss": 1.4561,
+      "step": 441
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.4596774193548387e-05,
+      "loss": 1.7276,
+      "step": 442
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.4193548387096777e-05,
+      "loss": 1.7586,
+      "step": 443
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.3790322580645163e-05,
+      "loss": 1.7074,
+      "step": 444
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.338709677419355e-05,
+      "loss": 1.6946,
+      "step": 445
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.2983870967741935e-05,
+      "loss": 1.641,
+      "step": 446
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.258064516129032e-05,
+      "loss": 1.6791,
+      "step": 447
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.217741935483871e-05,
+      "loss": 1.5758,
+      "step": 448
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.1774193548387097e-05,
+      "loss": 1.752,
+      "step": 449
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.1370967741935487e-05,
+      "loss": 1.5753,
+      "step": 450
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2.627969166011597e+16,
+  "total_flos": 2.779017123638477e+16,
   "trial_name": null,
   "trial_params": null
 }