Training in progress, step 8500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b332b6e8afc923724f84413e33299c5790f4ee8cf15f65d6144ba400e36d6c3
+oid sha256:0278328958930d3beaacbe8bed27397e998fbcabe1fca7fa0eae8eafd80ecf51
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8644418b35ffaf32d8aff1eed51b7d29638fabcb22b0cccef0d136903c9d9bb8
+oid sha256:4e59834f34401a93fcb0300abb81ffe29f6ae8d1c35b22ab4a0642dde9c40b2e
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d694e0d8a3c8e350e985b3c92970945d2995494a99fcf921d95897d24d690561
+oid sha256:f4a81dafce04c7537f75efee5aacdd30a9f6039bc0738e6674b85fdce84b597c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.381161007667032,
+  "epoch": 4.6549835706462215,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,6 +567,41 @@
       "learning_rate": 4.594141928707629e-06,
       "loss": 0.1685,
       "step": 8000
+    },
+    {
+      "epoch": 4.435925520262869,
+      "grad_norm": 0.9013499021530151,
+      "learning_rate": 3.8270834474090466e-06,
+      "loss": 0.1684,
+      "step": 8100
+    },
+    {
+      "epoch": 4.490690032858708,
+      "grad_norm": 0.8273316621780396,
+      "learning_rate": 3.1275100164689543e-06,
+      "loss": 0.1666,
+      "step": 8200
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.8490225076675415,
+      "learning_rate": 2.496444112952734e-06,
+      "loss": 0.1709,
+      "step": 8300
+    },
+    {
+      "epoch": 4.600219058050383,
+      "grad_norm": 0.9616093635559082,
+      "learning_rate": 1.9348080852294783e-06,
+      "loss": 0.1676,
+      "step": 8400
+    },
+    {
+      "epoch": 4.6549835706462215,
+      "grad_norm": 0.6257395148277283,
+      "learning_rate": 1.4434228048932796e-06,
+      "loss": 0.1657,
+      "step": 8500
     }
   ],
   "logging_steps": 100,
@@ -586,7 +621,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.843744149453193e+18,
+  "total_flos": 4.086908592883286e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null