Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81750cf4351c62f467fa31cd7b9d64a5c6b54b220ad076d6d668eb9844803aca
+oid sha256:08f90b36688b91b98709e870def8f894caf61ce415609f43683d608e6fa4e858
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6796a4fe299f2d46b565219a8d5ab5b44e38bb09dfe9c205cdfd25ad869b6fcb
+oid sha256:0d9a3bd27d6c24b34f17fee845d9969b2887828a99e0874adb72c3dd2e8bc7d9
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:921505c38e3140072fcb25b091248df87486cd572d25945bf43989c3adec66d2
+oid sha256:194b8cbcb4fd2b265a5d4d8d52182519dbf27c44b152e543049f035deb419f42
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7caa9fa897837d1407d3cee463cfb4344d4ea9bf72b6aacc7133003f48d23ba
+oid sha256:3360e651dce0e406d8c16d733ad14185a2cf6842077b4e5b5119e92b6cdfb4cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06440071556350627,
+  "epoch": 0.07155635062611806,
   "eval_steps": 500,
-  "global_step": 180,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -151,14 +151,30 @@
       "loss": 0.4525,
       "num_input_tokens_seen": 121416,
       "step": 180
+    },
+    {
+      "epoch": 0.06797853309481217,
+      "grad_norm": 0.5061659216880798,
+      "learning_rate": 0.00018640429338103758,
+      "loss": 0.4439,
+      "num_input_tokens_seen": 128284,
+      "step": 190
+    },
+    {
+      "epoch": 0.07155635062611806,
+      "grad_norm": 0.3323754072189331,
+      "learning_rate": 0.00018568872987477638,
+      "loss": 0.4489,
+      "num_input_tokens_seen": 135571,
+      "step": 200
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 121416,
+  "num_input_tokens_seen": 135571,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2730217072508928.0,
+  "total_flos": 3048513035655168.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null