Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcdc0f35846bc754577cd10e20f7cd208a8c3b9782dd1734562927f12aa9ff4
+oid sha256:642fa6ea93c5328a689db3c12119bd05458197b5485e216e3956041034addce5
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c222ad7729e8edc625af49bfa2accf203ab4ff265dd02ca19ee4431b28a163f1
+oid sha256:8378598f65d8748972165126ccc549178508d4ee275fc11095ac033bbfcd0d94
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670f2e3ed201a39b7134ca5f6503aca666cb99ac973528bcdb06393401ddc686
+oid sha256:5a11114094a1bb5fd000ee0ef08e018069d40428a8429f7375de3021f2c81601
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a770cb4ae613cc009292941b2afefaa83fcb03984ba92a4fe9b157b556d9e215
+oid sha256:7fdd00fe5e4ffe28b2f553058edb3aaca4dc6f249363b91632307b35ded3965d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13595706618962433,
+  "epoch": 0.14311270125223613,
   "eval_steps": 500,
-  "global_step": 380,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -311,14 +311,30 @@
       "loss": 0.4354,
       "num_input_tokens_seen": 252526,
       "step": 380
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "grad_norm": 0.500701904296875,
+      "learning_rate": 0.00017209302325581395,
+      "loss": 0.4421,
+      "num_input_tokens_seen": 258974,
+      "step": 390
+    },
+    {
+      "epoch": 0.14311270125223613,
+      "grad_norm": 0.2604714035987854,
+      "learning_rate": 0.00017137745974955278,
+      "loss": 0.4338,
+      "num_input_tokens_seen": 265411,
+      "step": 400
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 252526,
+  "num_input_tokens_seen": 265411,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 5678417971703808.0,
+  "total_flos": 5968156119717888.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null