Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8294bd123b3ad0eb343e1ba6d2f6b317f6c388ded3edd507dd6db8545bba0198
+oid sha256:3e63e20f89ae5ce2c794e796da20de8967ea722380ac22f94b092fb268836076
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b897d24d021cf6f86d5df39094acde3a8a6841d829a346f0952f1599ccee23a8
+oid sha256:eb054cf418115fefb2aaddab1d0d7a94d4017501f620b24ced8b59d481995c06
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6358da13f324834878bd2b4485e5667664a0d92ed16a7f6a761dd9dea8cc65
+oid sha256:4cf66005e5e6a4f3553669f4e9894b69e1bc5f9207c5bf2c3d2ce3aab9394607
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
+oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.449354410171509,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 2.4278199672698975,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 0.5828779599271403,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,13 +105,27 @@
       "eval_samples_per_second": 30.677,
       "eval_steps_per_second": 3.838,
       "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 2.4278,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 2.4278199672698975,
+      "eval_runtime": 204.6341,
+      "eval_samples_per_second": 30.66,
+      "eval_steps_per_second": 3.836,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.042513200078848e+16,
+  "total_flos": 2.333865205776384e+16,
   "trial_name": null,
   "trial_params": null
 }