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:a566e55c359d95bc6a6ba380e62d5e37bb186741188a98a0c592a3677f751be5
+oid sha256:03e922a81ef4007bf62d030e9883f89a16964c20c008143d39832e01bef59f54
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48db7f5d8c869518b63dd7fce527a584257a7e3cc22e8172fd10a7da8d95babd
+oid sha256:4a594db4126fabb1f9d3fba04874ee097557d5e0877b255a36496ef43edb3e3f
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dcf0a1d550e1486617643b9462f1d9eebdf9ddec6eafb10d0a8a79a9850919a
+oid sha256:05cf802ece851e37f7a2e8e09140678d93619f6c1e72127ae6bb12317798901b
 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": 2.174529552459717,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 1.530054644808743,
+  "best_metric": 2.1577847003936768,
+  "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": 30.46,
       "eval_steps_per_second": 3.811,
       "step": 2100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 2.1386,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 2.1577847003936768,
+      "eval_runtime": 206.4236,
+      "eval_samples_per_second": 30.394,
+      "eval_steps_per_second": 3.803,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.174508048386048e+16,
+  "total_flos": 6.469323520149504e+16,
   "trial_name": null,
   "trial_params": null
 }