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:f7db274a39aa8417e9376cd9f9d2ebfa2a73f69f7c1d31485a0849ac339b9e35
+oid sha256:ffe048d9da4be7cfcb90b6f25a800972c9a86174e094b32d97b12d1276fec09d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b1f242a510452e3c22aeadc9a7508029d89a752f5152c99ee75c5ba34cb6923
+oid sha256:ca6e82442ff7d45969661477a0e236a4efb00976f9e356ded0ea3400f38f9876
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ae99abe9570aceb4a5664541501a2c53d7b9f7e4d2be29d10330490d710d77
+oid sha256:4028c612b9c070d4e6df2c0d8ead423b9c3d72e14f7d4b52808d5af3fb645790
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cb9069cac0762cbe9eda0682450e4a822dfd10b17c5f7335626649d1825624d
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017265193370165747,
+  "epoch": 0.02302025782688766,
   "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": 5.2631578947368424e-05,
       "loss": 1.647,
       "step": 75
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.052631578947369e-05,
+      "loss": 1.6026,
+      "step": 76
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.842105263157895e-05,
+      "loss": 1.4526,
+      "step": 77
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.6315789473684214e-05,
+      "loss": 1.5979,
+      "step": 78
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.421052631578947e-05,
+      "loss": 1.4417,
+      "step": 79
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 1.619,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 1.1932,
+      "step": 81
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.789473684210527e-05,
+      "loss": 1.563,
+      "step": 82
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.578947368421053e-05,
+      "loss": 1.4538,
+      "step": 83
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 1.226,
+      "step": 84
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 1.3118,
+      "step": 85
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.9473684210526314e-05,
+      "loss": 1.4562,
+      "step": 86
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.7368421052631583e-05,
+      "loss": 1.2999,
+      "step": 87
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.5263157894736845e-05,
+      "loss": 1.6079,
+      "step": 88
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3157894736842107e-05,
+      "loss": 1.3978,
+      "step": 89
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 1.334,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 1.8286,
+      "step": 91
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 1.2721,
+      "step": 92
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.4736842105263157e-05,
+      "loss": 1.6883,
+      "step": 93
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.2631578947368422e-05,
+      "loss": 1.9406,
+      "step": 94
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 1.4372,
+      "step": 95
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 1.4428,
+      "step": 96
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.315789473684211e-06,
+      "loss": 1.696,
+      "step": 97
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 1.1901,
+      "step": 98
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 1.574,
+      "step": 99
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0,
+      "loss": 1.4564,
+      "step": 100
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1524771366027264.0,
+  "total_flos": 2031145737289728.0,
   "trial_name": null,
   "trial_params": null
 }