Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee445f42259eb708388e06a716c810a7efa682c6cbf2ba3e4b2a76cf3094c49
+oid sha256:9abefb5dbb7d74f27a49f3f66f13eb8932e56fedf94d48588dc96813b81668c5
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6450889938176d33a2c2905f2f7a13aef03aa0222e78e5871f21fe99bda36c83
+oid sha256:ff1a814809399bc31e3f44ea4a76d78c848700ab640abae1c3ec4538f4f8da77
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eac30a54a346eb77c88df167a4adbf13ea272bd1dd65fd9f0292631c36fab66
+oid sha256:b671a8eca01cb9b6f4736829516f37a248a3b5268cb765ba18a2dd729fd3c17b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
+oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4419173002243042,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 1.530054644808743,
+  "best_metric": 1.429054617881775,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 1.6029143897996359,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,13 +301,27 @@
       "eval_samples_per_second": 43.629,
       "eval_steps_per_second": 5.459,
       "step": 2100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.4105,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.429054617881775,
+      "eval_runtime": 143.9668,
+      "eval_samples_per_second": 43.579,
+      "eval_steps_per_second": 5.453,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2520111653502157e+17,
+  "total_flos": 1.3116148866861466e+17,
   "trial_name": null,
   "trial_params": null
 }