Training in progress, step 4100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bdd34706a42a3e0eda9ebf0516f9d594e11f10eaf56294a8eeb53e8afb2cde7
+oid sha256:1e8bf3267b20ce466b9f9d051d42464c5ef6335acec95e89263d7d20ea836672
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b82a21175e3cfc48aa09480f709b9176f223ff04bc53bcb5993ed92955e813dd
+oid sha256:395d193b2f31d3beb43beea752f16e535424e14bfebd2ab6ad77be68af1e5fb6
 size 151032837

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6135dea6869e11c78000d3b6bc11b1b1ade2c0fc5925996274588326a90a2389
+oid sha256:f464edcf4d7dbfc76ed7a7f5bc57357aae01042f47f660bbd2fdc1fc35daadc9
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
+oid sha256:f55ebe991e4838deda9ff3044672335e03697b65b3fe0753cca61998e974ee51
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0935524702072144,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9151183970856103,
+  "best_metric": 1.0850836038589478,
+  "best_model_checkpoint": "./outputs/checkpoint-4100",
+  "epoch": 2.9879781420765026,
   "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": 18.314,
       "eval_steps_per_second": 2.291,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.0688,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.0850836038589478,
+      "eval_runtime": 396.9254,
+      "eval_samples_per_second": 15.806,
+      "eval_steps_per_second": 1.978,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2969119672150784e+18,
+  "total_flos": 1.3292919651387863e+18,
   "trial_name": null,
   "trial_params": null
 }