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:d9925894a7478ae1f5e0f546ca599d8cf28610b7a70327dbd4818fba88916e8e
+oid sha256:846054661f24fbb81486c4cf0e46d11187a943057afae445c5ffb1897331b742
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f16329ff260fe84893e73ad99d77a039caee234ffc4e823e6c891dbcbca9a3
+oid sha256:812b57076dde62f09302f1c040bf821fdd66d0fbb0bd75378f9504c8b4d41ae9
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a559162ac019dca5b48b2dec6a4ffc4044c4a17ccd1ca4a1e187238cfc063507
+oid sha256:f1595c0116ee06b19e53460cb22f13e1a02a50c33cec69225408017397f51058
 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": 1.4683642387390137,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 1.4501450061798096,
+  "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": 15.02,
       "eval_steps_per_second": 1.879,
       "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 1.4622,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 1.4501450061798096,
+      "eval_runtime": 417.7046,
+      "eval_samples_per_second": 15.02,
+      "eval_steps_per_second": 1.879,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.2700191707023462e+17,
+  "total_flos": 2.594648461666222e+17,
   "trial_name": null,
   "trial_params": null
 }