Training in progress, step 4500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4a4f60720b11184986674e7b4a366ad3b9d917f91ec76c2f59fba01fcd1c4ba
+oid sha256:1a21f118c92639e50630bd3304c31d719c9ba254801eb32498f3302882f834e6
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cbb52d27c2843adda090a89873589ae51928d0a9e3b2e66f311e8f9097f3aa3
+oid sha256:7ba57843d972b62a81c6521f5b436e3573412b058bcfea5c7abf95d33bb0315a
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea4fa4d8b63c46011d327d88624348ec23af27ba1a62258b0451a85ac1f2f91
+oid sha256:b82dc9ddea4fba50f844e37ce1f457895028a7fe397f5b2d6de068c83714aa59
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.190580503833516,
+  "epoch": 2.4644030668127055,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,41 @@
       "learning_rate": 6.903478280128721e-05,
       "loss": 0.6712,
       "step": 4000
+    },
+    {
+      "epoch": 2.245345016429354,
+      "grad_norm": 2.228999137878418,
+      "learning_rate": 6.725360685364384e-05,
+      "loss": 0.668,
+      "step": 4100
+    },
+    {
+      "epoch": 2.3001095290251916,
+      "grad_norm": 2.125016450881958,
+      "learning_rate": 6.54472135141977e-05,
+      "loss": 0.6735,
+      "step": 4200
+    },
+    {
+      "epoch": 2.3548740416210294,
+      "grad_norm": 2.3794703483581543,
+      "learning_rate": 6.361824295720199e-05,
+      "loss": 0.6594,
+      "step": 4300
+    },
+    {
+      "epoch": 2.4096385542168672,
+      "grad_norm": 2.231340169906616,
+      "learning_rate": 6.176936835514312e-05,
+      "loss": 0.6691,
+      "step": 4400
+    },
+    {
+      "epoch": 2.4644030668127055,
+      "grad_norm": 2.1866331100463867,
+      "learning_rate": 5.9903291971706e-05,
+      "loss": 0.687,
+      "step": 4500
     }
   ],
   "logging_steps": 100,
@@ -306,7 +341,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9236155642036552e+18,
+  "total_flos": 2.1638170935806853e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null