Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3450032956484af5b5ff329e1947f3061dba4ae8bcdd637c42361124446edb7f
+oid sha256:5f9d14c52b55896e03b273fc9fe78b2e8373080957a07118b4b990d91ab2bdc0
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d92cfe910fd508325bf3b07371b1c2cc6701ab49b4cc09af7ba4ac8b8d7143e1
+oid sha256:9b1fde7d3efe241e005940c4bd954376adcce1e3cf0eb4d084051b373a553f5a
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb3b882e2821464a9e8ecf24229d2761b3972d473187bb0e8987bc38205d855
+oid sha256:9013865ce1db6c56389ad8c81d9da591edccc22d595720deba33a4baadab4fc1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8325774c5216d42461f4f0d2f46a295a9e74d21ab580cd43104c1ce37b007328
+oid sha256:b3fb62e1a686af03a6294538f23b0512dc4df0d77f62afb535a9f3732c29458d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9539737701416016,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.29143897996357016,
+  "best_metric": 1.911293625831604,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.36429872495446264,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,13 +63,27 @@
       "eval_samples_per_second": 43.695,
       "eval_steps_per_second": 5.467,
       "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 1.9262,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.911293625831604,
+      "eval_runtime": 143.5587,
+      "eval_samples_per_second": 43.703,
+      "eval_steps_per_second": 5.468,
+      "step": 500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3847291608039424e+16,
+  "total_flos": 2.9805494916120576e+16,
   "trial_name": null,
   "trial_params": null
 }