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:f113c46aa4441d78fd36c9c46e118a4312ea639719c42196fa5b9bb418b58016
+oid sha256:74da47094c96896426639c4a8fb962a8e70b5fc806b7d7bd426fd1c9de360e4b
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09552d256120afaf8806266e6bb3cdf15cabd766a52f27f4a46655e1b1049a3f
+oid sha256:9bf1beb84d2af9790cc09a1220fbd623c94e74c5572595f9d6f0c745dfb35987
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8561716d95541b53b652b5115466c42cbcb262907d8a19f267e61cdb694347c
+oid sha256:42a3fe4a57e29c75b53b9129d2ed4ef5a4612694ca662c69f8eb13c941fb9762
 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": 0.00427715996578272,
+  "epoch": 0.00855431993156544,
   "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": 2.2736,
       "step": 9
+    },
+    {
+      "epoch": 0.0051325919589392645,
+      "grad_norm": 1.7971843481063843,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.9401,
+      "step": 12
+    },
+    {
+      "epoch": 0.00641573994867408,
+      "grad_norm": 1.240454077720642,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.5096,
+      "step": 15
+    },
+    {
+      "epoch": 0.006843455945252352,
+      "eval_loss": 2.646683692932129,
+      "eval_runtime": 13.4282,
+      "eval_samples_per_second": 73.353,
+      "eval_steps_per_second": 36.714,
+      "step": 16
+    },
+    {
+      "epoch": 0.007698887938408896,
+      "grad_norm": 1.0643540620803833,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.3632,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 83302551650304.0,
+  "total_flos": 166605103300608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null