Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:695a4bb17024694cc3d7a531324d989a2ac335736b5d11b85507560af5b9555c
+oid sha256:4d1eee51dd6becffca4a156978cafca9aee39ca06ccca259bb6ebad16630c82f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f805d548733d065965a5c9a5cd9a6bf8048c3eb986f9c2b1cb58ff438192633e
+oid sha256:91960bf5514333786ed5ca4c1183957decbc3de6d00df2f18d9d611df3be3af9
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e300bddb0d7e7d6e026d32cddc3203212379cd7e7d4945e7775d35a028e0ce1f
+oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
 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": 0.23952095808383234,
+  "epoch": 0.47904191616766467,
   "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": 0.2899,
       "step": 9
+    },
+    {
+      "epoch": 0.2874251497005988,
+      "grad_norm": 0.12527230381965637,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.015,
+      "step": 12
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "grad_norm": 0.023354211822152138,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0011,
+      "step": 15
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "eval_loss": 7.335327245527878e-05,
+      "eval_runtime": 1.9021,
+      "eval_samples_per_second": 9.463,
+      "eval_steps_per_second": 4.732,
+      "step": 16
+    },
+    {
+      "epoch": 0.4311377245508982,
+      "grad_norm": 0.013110329397022724,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0003,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1842091508367360.0,
+  "total_flos": 3684183016734720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null