Training in progress, step 220, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f90b36688b91b98709e870def8f894caf61ce415609f43683d608e6fa4e858
+oid sha256:6f96b7c71372582451a8856d4292de48642291473692ec963deff5ab833b885c
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d9a3bd27d6c24b34f17fee845d9969b2887828a99e0874adb72c3dd2e8bc7d9
+oid sha256:5d3cd83379ee9a0b75766a6d2fa05de4b0412e196e40c20ae17db8468a2a4f74
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194b8cbcb4fd2b265a5d4d8d52182519dbf27c44b152e543049f035deb419f42
+oid sha256:982ef721154bc6d11d2c93bcbf72ab00515e1bf0940ca62b8577a5bfc9ad31eb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3360e651dce0e406d8c16d733ad14185a2cf6842077b4e5b5119e92b6cdfb4cd
+oid sha256:d1b11a25e8c3f6d77fc413c8d381545b6c097ced995430c3981be2b0781bd184
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07155635062611806,
+  "epoch": 0.07871198568872988,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -167,14 +167,30 @@
       "loss": 0.4489,
       "num_input_tokens_seen": 135571,
       "step": 200
+    },
+    {
+      "epoch": 0.07513416815742398,
+      "grad_norm": 0.5354058742523193,
+      "learning_rate": 0.00018497316636851522,
+      "loss": 0.4634,
+      "num_input_tokens_seen": 141479,
+      "step": 210
+    },
+    {
+      "epoch": 0.07871198568872988,
+      "grad_norm": 0.4328760504722595,
+      "learning_rate": 0.00018425760286225405,
+      "loss": 0.4545,
+      "num_input_tokens_seen": 147677,
+      "step": 220
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 135571,
+  "num_input_tokens_seen": 147677,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3048513035655168.0,
+  "total_flos": 3320734224623616.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null