Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:449480b0af4585cc48035ea644e8ac88cd60438e200cf1af6c7fd1f5f2d12a01
+oid sha256:a649346b5209af3a897dde1f4295d5593aa3e3bdf403031643b07de6834dea52
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1b8dcbc071ebbde1307fb39a55a173ba26438df938c35520f665d32966fe01
+oid sha256:8d5427e86568051e6577a296e8bea7d48b398f766600b90e733fb87cee1f7b4f
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0bb62c383dd93bb7277f2f4f3ecc51f45d7c7b1a6c0012d26a10c5589360f2
+oid sha256:6122816c42780a868d77d7c48cf66d125e516c03075f49e683bda8693a41f3d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020930232558139535,
+  "epoch": 0.04186046511627907,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 36.494,
       "eval_steps_per_second": 4.587,
       "step": 9
+    },
+    {
+      "epoch": 0.027906976744186046,
+      "grad_norm": 4.38749361038208,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 5.632,
+      "step": 12
+    },
+    {
+      "epoch": 0.03488372093023256,
+      "grad_norm": 4.592843055725098,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 4.9077,
+      "step": 15
+    },
+    {
+      "epoch": 0.04186046511627907,
+      "grad_norm": 4.174410820007324,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 4.5093,
+      "step": 18
+    },
+    {
+      "epoch": 0.04186046511627907,
+      "eval_loss": 4.481910705566406,
+      "eval_runtime": 19.8608,
+      "eval_samples_per_second": 36.454,
+      "eval_steps_per_second": 4.582,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2351283906281472.0,
+  "total_flos": 4702567812562944.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null