Training in progress, step 3800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d563b1be4f7c8dbed3c5f1dde599542b1c98b2b9bfc8b06330c4aaf249e3330
+oid sha256:fe62918a4dffa4665f1d9717eddd64f5e60ba45038bb6ff732fdd8a3063355ac
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dce1638358698bed2c4e927c03ed0a9635536a7637672c5aa2fcbe27fb7e76d
+oid sha256:b63d8161ac2d59af0624fc5badc426f9233200135f1f2bea08b9fc3528678795
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c5dbd422cf501975116692792c2de3c2f4469824fcbf1bfd413b8a70806cc3
+oid sha256:966abaeea490518d524411c6c93b2cb01cabbd7b354c975c231fa3c86331e17e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b67e8639c4ce4300a4880c7bcd2541c91c7cc8bb6e15dbd9373ac35ed3175a20
+oid sha256:cb592c268b6f8eab99358b5a12e18084bc178639195f5911973b566c7c32da81
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3542754650115967,
-  "best_model_checkpoint": "./outputs/checkpoint-3700",
-  "epoch": 2.6958105646630237,
+  "best_metric": 1.343408226966858,
+  "best_model_checkpoint": "./outputs/checkpoint-3800",
+  "epoch": 2.768670309653916,
   "eval_steps": 100,
-  "global_step": 3700,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -525,13 +525,27 @@
       "eval_samples_per_second": 43.665,
       "eval_steps_per_second": 5.463,
       "step": 3700
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.0002,
+      "loss": 1.3058,
+      "step": 3800
+    },
+    {
+      "epoch": 2.77,
+      "eval_loss": 1.343408226966858,
+      "eval_runtime": 143.6047,
+      "eval_samples_per_second": 43.689,
+      "eval_steps_per_second": 5.466,
+      "step": 3800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.2028662541416858e+17,
+  "total_flos": 2.2624424255319245e+17,
   "trial_name": null,
   "trial_params": null
 }