Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c585be001e0a1a2354845d9756bcbdb656ad917a8770b41c4c9e5cc3fc1e1a
+oid sha256:e38ae896a63cd8b70ad6d0ff02fafac5a428a586fd8da33bd8a7180ec088ecd3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd853656f029028b75f392d29de411db4f210e2fa884b40fa4dd37d56188f736
+oid sha256:34efd4a6a42cc6f27f534cefff00e6f87140976c2e30581fa2b2e1afe7fa23ff
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf5ca6fa489a6167c2debe00d595ee8d7939f79fc4b59c62a45f43288d1972c
+oid sha256:4bc8d07c95f760114e0463f9ed93d996031729b85e177afff8df0095a228e169
 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": 0.06474820143884892,
+  "epoch": 0.12949640287769784,
   "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": 12.115,
       "eval_steps_per_second": 1.553,
       "step": 9
+    },
+    {
+      "epoch": 0.08633093525179857,
+      "grad_norm": 2.9950151443481445,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 4.8732,
+      "step": 12
+    },
+    {
+      "epoch": 0.1079136690647482,
+      "grad_norm": 3.6927051544189453,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 4.6017,
+      "step": 15
+    },
+    {
+      "epoch": 0.12949640287769784,
+      "grad_norm": 3.0494635105133057,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 4.6042,
+      "step": 18
+    },
+    {
+      "epoch": 0.12949640287769784,
+      "eval_loss": 1.0919393301010132,
+      "eval_runtime": 19.3623,
+      "eval_samples_per_second": 12.085,
+      "eval_steps_per_second": 1.549,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5468848970989568e+16,
+  "total_flos": 3.0937697941979136e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null