Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c866b681847079f3b9029f07492db9880da802a14740ef308276cbc48af7029
+oid sha256:e1143902ff3564e4c1002e08abff0e3901f7b2864ff1561402b11204e5362411
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b0feae9377bfd2ee4adc15c04b256d703f0f8cfe89d645ffa2f876e8acdd71
+oid sha256:db52ebf37465555ffb2a88505ae648a96569156a76709768fa9d1a22d929c602
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5818eed0ee5844cae7078ebbf0cd36b392212601ec7951f21f30f58ec6711de0
+oid sha256:8c1160b60ff5f8d1ce07bd99cf7c1f641950e24f450dc82b69252f6b166db4c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10bc8edf4e1fadab9976453bf48d4affbe0fded7ba378b722041dd8223dc111e
+oid sha256:86f012eba30607df0ae053cd324d767650b13de6ae604fa48d8a90e45bcf2f90
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00014008545212579673,
+  "epoch": 0.00015565050236199636,
   "eval_steps": 500,
-  "global_step": 180,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -70,6 +70,13 @@
       "learning_rate": 2.9833333333333335e-05,
       "loss": 3.2489,
       "step": 180
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.890682220458984,
+      "learning_rate": 3.316666666666667e-05,
+      "loss": 3.0499,
+      "step": 200
     }
   ],
   "logging_steps": 20,
@@ -77,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 901465913585664.0,
+  "total_flos": 985164675969024.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null