Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fcbe9bdda2410d6e7bac72d128922f0a6f97341a6b1df2aad6c0655e442004e
+oid sha256:a11bf616cf38061efc4c2fe034d530f67a4d048476d40df64098f1629800331c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef44c4d032640d06a9129c2dde08f2d53538b984c5b30dd2f2ac61a370327c9e
+oid sha256:504d5c2d40f49676e5ced3c024b84ccc87717fb9d5a352043364732f9fac0a55
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6691656f59836e679b0b16a9e5fb6259737616134b8601994c32a922f156d9a2
+oid sha256:7d66b1a8c16da8ebf7970425c7c306a82ffa223990ce4f0cb56084c069e08e81
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.507997512817383,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.5828779599271403,
+  "best_metric": 2.485630512237549,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 0.6557377049180327,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,13 +119,27 @@
       "eval_samples_per_second": 30.654,
       "eval_steps_per_second": 3.835,
       "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 2.478,
+      "step": 900
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 2.485630512237549,
+      "eval_runtime": 204.5609,
+      "eval_samples_per_second": 30.671,
+      "eval_steps_per_second": 3.837,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.277701378039808e+16,
+  "total_flos": 2.562316410028032e+16,
   "trial_name": null,
   "trial_params": null
 }