Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d197d13e95ecedd3c92b1e419c3fa639e69b2ecef35f4f8d11c8ec3bb217933
+oid sha256:8df2cd5c49743fadd7dc34f36f53d9ce155a42dba452dee5d3d75bf957d83ced
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2af8bdd562181e23a67fb1ef60be680f5a27f3597b4e6c92be7550df3e56b3a
+oid sha256:6caed337f6df5bb80de4f3889d5ed66febc6a148b541c5cc6ae41ac48b1d6562
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44a40a272b348c4ca9b50ab67314e7f3e02ed0a63f0e65a984b9a85dda18fc1
+oid sha256:f36200f14a40952b0bdb6a1d8eb87a6a36477e7fb53bdd6a8937f3fddc9dcca4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2a7616f99506ce2115c2b51a0c8d6af99dd5ac2b72ef98b701eba7ab661118
+oid sha256:da625bdbaba1e1b9a41c85e65d17da2b21a48f48126a4ef7c6978303b33ffaa8
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5464540719985962,
-  "best_model_checkpoint": "./outputs/checkpoint-2200",
-  "epoch": 1.6029143897996359,
+  "best_metric": 1.5316085815429688,
+  "best_model_checkpoint": "./outputs/checkpoint-2300",
+  "epoch": 1.6757741347905282,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,13 +315,27 @@
       "eval_samples_per_second": 43.708,
       "eval_steps_per_second": 5.469,
       "step": 2200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 1.5286,
+      "step": 2300
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 1.5316085815429688,
+      "eval_runtime": 143.5896,
+      "eval_samples_per_second": 43.694,
+      "eval_steps_per_second": 5.467,
+      "step": 2300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.3101343701897216e+17,
+  "total_flos": 1.369615582192681e+17,
   "trial_name": null,
   "trial_params": null
 }