Training in progress, step 4000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19898aba0a4623dd74d6547da7158f99c65402876b4d2a015e255f33d1d7ff81
+oid sha256:5bdd34706a42a3e0eda9ebf0516f9d594e11f10eaf56294a8eeb53e8afb2cde7
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea60b54f0d66bd07f149cc53197e48b174eb16c9efdb7a225125adbb7ed2c0b
+oid sha256:b82a21175e3cfc48aa09480f709b9176f223ff04bc53bcb5993ed92955e813dd
 size 151032837

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b836b0763d8c8c7392ab9bf480880e0c4fd0fbff6b82477d0ff13a6bddc661
+oid sha256:6135dea6869e11c78000d3b6bc11b1b1ade2c0fc5925996274588326a90a2389
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42424f90eb68391066979b79f87ab18e2fce2a0abc640b46cf1b3f4c12c720a
+oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1041266918182373,
-  "best_model_checkpoint": "./outputs/checkpoint-3900",
-  "epoch": 2.8422586520947175,
+  "best_metric": 1.0935524702072144,
+  "best_model_checkpoint": "./outputs/checkpoint-4000",
+  "epoch": 2.9151183970856103,
   "eval_steps": 100,
-  "global_step": 3900,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,13 +553,27 @@
       "eval_samples_per_second": 18.321,
       "eval_steps_per_second": 2.292,
       "step": 3900
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.0002,
+      "loss": 1.0798,
+      "step": 4000
+    },
+    {
+      "epoch": 2.92,
+      "eval_loss": 1.0935524702072144,
+      "eval_runtime": 342.5842,
+      "eval_samples_per_second": 18.314,
+      "eval_steps_per_second": 2.291,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2644917795692257e+18,
+  "total_flos": 1.2969119672150784e+18,
   "trial_name": null,
   "trial_params": null
 }