Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:149a09998bf83e31819b4090132c2d9eb7a95f79fbfd79d14ca99701afb2b106
+oid sha256:cb833c87b5112d0139a3072a6b4f95cd4323cfd3d156ef6a8e841ebfac293362
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac0da93c6ac2a9191052ef608e652b77666a46926201a5e53e599744f601fa1
+oid sha256:144c2af10cc322d858a390c1516fd6b81e604b7ee197aa471e1a7706f6ff4a4e
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5fcc107cd0de5799df59f0bf6b3a9f6637359068ab89f890c741b49034e80db
+oid sha256:7376cbf010a9f08e21c74d30e4ee024a7246fb9200b1adb483a435bf9cadb59a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd37581d93a41fc457d899cacb7a67009a6909f6dbf72b467de55158ef91ac94
+oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3995251655578613,
-  "best_model_checkpoint": "./outputs/checkpoint-2500",
-  "epoch": 1.8214936247723132,
+  "best_metric": 1.38627290725708,
+  "best_model_checkpoint": "./outputs/checkpoint-2600",
+  "epoch": 1.8943533697632058,
   "eval_steps": 100,
-  "global_step": 2500,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,13 +357,27 @@
       "eval_samples_per_second": 43.597,
       "eval_steps_per_second": 5.455,
       "step": 2500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 1.3804,
+      "step": 2600
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 1.38627290725708,
+      "eval_runtime": 143.9593,
+      "eval_samples_per_second": 43.582,
+      "eval_steps_per_second": 5.453,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.4900150729136538e+17,
+  "total_flos": 1.549670670211154e+17,
   "trial_name": null,
   "trial_params": null
 }