Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b74265b17ca020ad147ba93efef015a8c237e1c34da6d3dd21e759b0aef08a2
+oid sha256:5f63c324370d68f5ae915b6e4591dd20798a4fe695252925fd638287b294cda5
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8417b3f9d5b1359970536bb12f52bc99c995b94763d8ae32f24181d5adae6553
+oid sha256:a08dc001d6523df0b6243b81afd032842523458b62424edf57f8205ce63e4428
 size 40570324

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d8f7f8e1a76d94091cc701a4a00cc6fd2a3c1a746e29e297276a305cc6801f
+oid sha256:d9e48c8790931566a35bec8b98e5a5d357b59c99de92c1d3375876db20a1bad1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1584b1b2cf9ecd956165af14d13e1fadf07b1f7d91e0a62867f52fe0a3a9ac7c
+oid sha256:0c00cc7e13d62adea907af47c9ff36acc6d7a2226f05496beea30760c284641c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0018656716417910447,
+  "epoch": 0.0024875621890547263,
   "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": 5.4736842105263165e-05,
       "loss": 1.5881,
       "step": 75
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 1.2379,
+      "step": 76
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.052631578947369e-05,
+      "loss": 1.5001,
+      "step": 77
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.842105263157895e-05,
+      "loss": 1.6074,
+      "step": 78
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.6315789473684214e-05,
+      "loss": 1.5181,
+      "step": 79
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.421052631578947e-05,
+      "loss": 1.6825,
+      "step": 80
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 1.5768,
+      "step": 81
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4e-05,
+      "loss": 1.6137,
+      "step": 82
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.789473684210527e-05,
+      "loss": 1.6044,
+      "step": 83
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.578947368421053e-05,
+      "loss": 1.534,
+      "step": 84
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 1.524,
+      "step": 85
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 1.5299,
+      "step": 86
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.9473684210526314e-05,
+      "loss": 1.7204,
+      "step": 87
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.7368421052631583e-05,
+      "loss": 1.7303,
+      "step": 88
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.5263157894736845e-05,
+      "loss": 1.3288,
+      "step": 89
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.3157894736842107e-05,
+      "loss": 1.2958,
+      "step": 90
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 1.453,
+      "step": 91
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 1.5348,
+      "step": 92
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 1.3595,
+      "step": 93
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.4736842105263157e-05,
+      "loss": 1.464,
+      "step": 94
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.2631578947368422e-05,
+      "loss": 1.6339,
+      "step": 95
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 1.5956,
+      "step": 96
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 1.5153,
+      "step": 97
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.315789473684211e-06,
+      "loss": 1.2618,
+      "step": 98
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 1.8239,
+      "step": 99
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 1.7529,
+      "step": 100
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 4183967298846720.0,
+  "total_flos": 5407982518321152.0,
   "trial_name": null,
   "trial_params": null
 }