Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3efa631529d19460ca850d512f923d0e99ff972c7aa0e6be6e5f8f92152ed1d7
+oid sha256:0772a7cfd0d34f5da2d93801ccb44b56d99ae9a3f085f1e42c9525e6e3ff03c0
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641530905aae4fb6676aec0aab6bd85d867c1aa05431bf2ebab956bc1b441635
+oid sha256:fc64165e6fccd4185ea355786d288060836f77e481a685747b22754c94a184fa
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:109840deab3769bfe3711ab7fc3d0717cd3af7fb8722bdab6748ba80b0be6d2f
+oid sha256:d4cfbf6b6f407e64e4f262c6135c7c52e93982a6f99286470ecffa7d28c17c2f
 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": 0.921540379524231,
-  "best_model_checkpoint": "./outputs/checkpoint-2500",
-  "epoch": 3.3333333333333335,
+  "best_metric": 0.9189460277557373,
+  "best_model_checkpoint": "./outputs/checkpoint-2600",
+  "epoch": 3.466666666666667,
   "eval_steps": 100,
-  "global_step": 2500,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,6 +357,20 @@
       "eval_samples_per_second": 2.493,
       "eval_steps_per_second": 0.313,
       "step": 2500
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 0.0002,
+      "loss": 0.7242,
+      "step": 2600
+    },
+    {
+      "epoch": 3.47,
+      "eval_loss": 0.9189460277557373,
+      "eval_runtime": 777.6576,
+      "eval_samples_per_second": 2.482,
+      "eval_steps_per_second": 0.311,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
@@ -364,7 +378,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 6.474662583520973e+17,
+  "total_flos": 6.734630518750925e+17,
   "trial_name": null,
   "trial_params": null
 }