Training in progress, step 4100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da238eef5fe48061c46f8db062b03e964ca3f2afbc19978a6a0624516625913
+oid sha256:665743a09bf79dcd69946448918fb0c16aa79bd6616b8cfb311dda0ec4b4bdf5
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:432e51cd9ccf38fca38ad8784e132487dfdf2626caccc7dc87ff5987b616c1bf
+oid sha256:c545798a80cf3e21310f966375ea19a1ece615f35be28021957920f347dae719
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba10e0017806276ad36c9962a8d3fa89bfabe64354bedff59216e48a02da40c
+oid sha256:be9cef20fcb5836bc994b3161e3caaa39c6412b1a8cf4e470a339da81589749a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
+oid sha256:1ef51ed05818f33aebca9592cb64baf0df006aad2a34a7cf944f4a48b70afce3
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2177170515060425,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9143897996357016,
+  "best_metric": 1.205187439918518,
+  "best_model_checkpoint": "./outputs/checkpoint-4100",
+  "epoch": 2.987249544626594,
   "eval_steps": 100,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,13 +567,27 @@
       "eval_samples_per_second": 43.704,
       "eval_steps_per_second": 5.468,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.205187439918518,
+      "eval_runtime": 143.4816,
+      "eval_samples_per_second": 43.727,
+      "eval_steps_per_second": 5.471,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3843183295659213e+17,
+  "total_flos": 2.444085005899776e+17,
   "trial_name": null,
   "trial_params": null
 }