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:fb18e3203c6596a519a05db5fb6280fa28b0c566962db92cdc3a004895496d0d
+oid sha256:c08c2f07741aed4ca4737a5237a7eeb5b6cb1c2a195d2beb80c893e2b98b5b3a
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d3d2b965eb6ced570f38399325ad36627583ae169f012723595cb950d631c8
+oid sha256:9fcaa4025915407ef308e414819e4078810646d6f6747cab48f19565912f983b
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c1a265e3ce6e49c82bf4680ec1ef7369cd0f139daf195d39d30bd867b6095a3
+oid sha256:2caab57c9738a6223b66a33175b22839bf9437a089ed80e62b0e4247b5a00c6c
 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": 0.00016848844801078326,
+  "epoch": 0.0003369768960215665,
   "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": 9.3501,
       "step": 9
+    },
+    {
+      "epoch": 0.0002021861376129399,
+      "grad_norm": 6.206903457641602,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 8.3669,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002527326720161749,
+      "grad_norm": 5.715407848358154,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 9.2975,
+      "step": 15
+    },
+    {
+      "epoch": 0.00026958151681725324,
+      "eval_loss": 2.2501394748687744,
+      "eval_runtime": 1502.938,
+      "eval_samples_per_second": 16.627,
+      "eval_steps_per_second": 8.314,
+      "step": 16
+    },
+    {
+      "epoch": 0.0003032792064194099,
+      "grad_norm": 3.972928524017334,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.8518,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 600237114654720.0,
+  "total_flos": 1200474229309440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null