Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a504e7087c42efa0abf4ec92b7f2fffe60bc836a276d2d8040eb1e14d8fe701
+oid sha256:d91107f5c242c8df5342db2e311f2309392ecf0548153ba97e37db1ac8814530
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3a1c360125505fbecae7ce8c3717ae80f5d8f194f13bc58ae229409e120928
+oid sha256:24377944ce0dd27b0697f70f0d52d926be551d7d662470a7bb5e641270e05441
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f3d5d54b849ab203f6cdfb3dbb15af8bac4b9cdd7cf70876a104c601b1d220d
+oid sha256:79438b1731d80b13c3e856d3e6ada7b258fe0028bd55a30293421a89363cfff2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef61bc9a6dc6a8e5bc76abe40655ca3cc8891ccb7b6be31278a254ac81104357
+oid sha256:16ad2180f5b27e9af3551807b0da763fbb16c05640f8b967bf27f34341ae1380
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 75.0,
+  "epoch": 100.0,
   "eval_steps": 1000,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -457,13 +457,163 @@
       "learning_rate": 6.105263157894737e-05,
       "loss": 0.0034,
       "step": 75
+    },
+    {
+      "epoch": 76.0,
+      "learning_rate": 5.894736842105263e-05,
+      "loss": 0.0041,
+      "step": 76
+    },
+    {
+      "epoch": 77.0,
+      "learning_rate": 5.68421052631579e-05,
+      "loss": 0.0041,
+      "step": 77
+    },
+    {
+      "epoch": 78.0,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 0.0034,
+      "step": 78
+    },
+    {
+      "epoch": 79.0,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 0.0038,
+      "step": 79
+    },
+    {
+      "epoch": 80.0,
+      "learning_rate": 5.052631578947369e-05,
+      "loss": 0.0037,
+      "step": 80
+    },
+    {
+      "epoch": 81.0,
+      "learning_rate": 4.842105263157895e-05,
+      "loss": 0.0044,
+      "step": 81
+    },
+    {
+      "epoch": 82.0,
+      "learning_rate": 4.6315789473684214e-05,
+      "loss": 0.0044,
+      "step": 82
+    },
+    {
+      "epoch": 83.0,
+      "learning_rate": 4.421052631578947e-05,
+      "loss": 0.0042,
+      "step": 83
+    },
+    {
+      "epoch": 84.0,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 0.0037,
+      "step": 84
+    },
+    {
+      "epoch": 85.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0039,
+      "step": 85
+    },
+    {
+      "epoch": 86.0,
+      "learning_rate": 3.789473684210527e-05,
+      "loss": 0.0029,
+      "step": 86
+    },
+    {
+      "epoch": 87.0,
+      "learning_rate": 3.578947368421053e-05,
+      "loss": 0.0039,
+      "step": 87
+    },
+    {
+      "epoch": 88.0,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 0.004,
+      "step": 88
+    },
+    {
+      "epoch": 89.0,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.0042,
+      "step": 89
+    },
+    {
+      "epoch": 90.0,
+      "learning_rate": 2.9473684210526314e-05,
+      "loss": 0.0038,
+      "step": 90
+    },
+    {
+      "epoch": 91.0,
+      "learning_rate": 2.7368421052631583e-05,
+      "loss": 0.0035,
+      "step": 91
+    },
+    {
+      "epoch": 92.0,
+      "learning_rate": 2.5263157894736845e-05,
+      "loss": 0.0041,
+      "step": 92
+    },
+    {
+      "epoch": 93.0,
+      "learning_rate": 2.3157894736842107e-05,
+      "loss": 0.0039,
+      "step": 93
+    },
+    {
+      "epoch": 94.0,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 0.0034,
+      "step": 94
+    },
+    {
+      "epoch": 95.0,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 0.0044,
+      "step": 95
+    },
+    {
+      "epoch": 96.0,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 0.0041,
+      "step": 96
+    },
+    {
+      "epoch": 97.0,
+      "learning_rate": 1.4736842105263157e-05,
+      "loss": 0.0036,
+      "step": 97
+    },
+    {
+      "epoch": 98.0,
+      "learning_rate": 1.2631578947368422e-05,
+      "loss": 0.0037,
+      "step": 98
+    },
+    {
+      "epoch": 99.0,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.006,
+      "step": 99
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 0.0041,
+      "step": 100
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 100,
   "save_steps": 25,
-  "total_flos": 802308556800000.0,
+  "total_flos": 1069744742400000.0,
   "trial_name": null,
   "trial_params": null
 }