Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:444c6d560c0d38a5080111004c8d99ed76d977a489280e415b949784ea109269
+oid sha256:65b76113cc66a54ae0d51cf94af5be1af9504b6a1f06b6ce681d5b3db4a8093d
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c21da93ee61a8c22ed74648b0bd8ceda5b80faae3eca81fde0e420acbf0b4f29
+oid sha256:8354ed4f7a4bea4421fcded7ce83c9bab4384af9af552b5d65672b4ee4f1ac4f
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d8fa6eebf2c491c1f6cfdeebbb5e5a1aa69ec1df13d364c2f3573f8f1b33221
+oid sha256:cc64d5d13a3120771ece3c4a2eb4de07fed7796fc4d888af303e82089a1664f1
 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": 0.03167062549485352,
+  "epoch": 0.06334125098970704,
   "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": 4.5532,
       "step": 9
+    },
+    {
+      "epoch": 0.03800475059382423,
+      "grad_norm": 3.0310347080230713,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 3.9767,
+      "step": 12
+    },
+    {
+      "epoch": 0.047505938242280284,
+      "grad_norm": 3.2726292610168457,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.4547,
+      "step": 15
+    },
+    {
+      "epoch": 0.050673000791765635,
+      "eval_loss": 3.1997406482696533,
+      "eval_runtime": 15.8576,
+      "eval_samples_per_second": 8.387,
+      "eval_steps_per_second": 4.225,
+      "step": 16
+    },
+    {
+      "epoch": 0.057007125890736345,
+      "grad_norm": 3.1917810440063477,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.3664,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3495193466634240.0,
+  "total_flos": 6990386933268480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null