Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15babcd422e2d7014b98d92fa208ab00cf5b2d1cf8f403071c762301a6049101
+oid sha256:03070b525a254ba9d8d848bb2fa3ec3497b48d666b5267b6736e9ada158a2753
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f910c58152ae63ac02d7ba9702a12921ecf32c0f223e02b7d5f3a7ab65be786b
+oid sha256:abc4f9ac653138edab9687b9ae9f54721d9c890e93c0fe5bca5131da11e6558f
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
+oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
 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": 0.004545971133083305,
+  "epoch": 0.00909194226616661,
   "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": 11.7831,
       "step": 9
+    },
+    {
+      "epoch": 0.005455165359699966,
+      "grad_norm": 56.49053192138672,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 8.7552,
+      "step": 12
+    },
+    {
+      "epoch": 0.006818956699624957,
+      "grad_norm": 72.0090103149414,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 7.7473,
+      "step": 15
+    },
+    {
+      "epoch": 0.007273553812933288,
+      "eval_loss": 1.5220115184783936,
+      "eval_runtime": 12.9876,
+      "eval_samples_per_second": 71.376,
+      "eval_steps_per_second": 35.726,
+      "step": 16
+    },
+    {
+      "epoch": 0.008182748039549948,
+      "grad_norm": 106.22815704345703,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.378,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 177003319787520.0,
+  "total_flos": 354006639575040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null