Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:269fa87ffa5e940102f89a3be2aa2217ba999951a2a333183ec5d19f72328cf9
+oid sha256:431fc27e0e6c4e3a5eda619c552f45fd5337e519fb6f24fdfc454b540f19cf16
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba90db7605206492eb48fd325fc84d03e1d2a826c211beb85ae16d83181ef21
+oid sha256:2e83e6a8956a7c6795969a06a5f7ca21ada953f61c2cb1809611b49ca1e1a36a
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe857a15cfad11d521d686079650bc523522af67539d91db4012db6206f54275
+oid sha256:aa382952e0adbb7e7abb917278c0a70d8bfd97851369da627797b4983c8f9cb6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021369804466289132,
+  "epoch": 0.0042739608932578265,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 7.5124,
       "step": 9
+    },
+    {
+      "epoch": 0.002564376535954696,
+      "grad_norm": 5.509289264678955,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 4.9222,
+      "step": 12
+    },
+    {
+      "epoch": 0.00320547066994337,
+      "grad_norm": 4.7509236335754395,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 5.0086,
+      "step": 15
+    },
+    {
+      "epoch": 0.0034191687146062615,
+      "eval_loss": 0.9060437679290771,
+      "eval_runtime": 459.6826,
+      "eval_samples_per_second": 4.288,
+      "eval_steps_per_second": 2.145,
+      "step": 16
+    },
+    {
+      "epoch": 0.003846564803932044,
+      "grad_norm": 3.560378313064575,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.3933,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347829962342400.0,
+  "total_flos": 1.26956599246848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null