Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df2cd5c49743fadd7dc34f36f53d9ce155a42dba452dee5d3d75bf957d83ced
+oid sha256:1205743dbc4c301da388f39f4cbd22836e759477b2c2f3e7128292d73d548c8d
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6caed337f6df5bb80de4f3889d5ed66febc6a148b541c5cc6ae41ac48b1d6562
+oid sha256:3016165f0c6c461ebe01e702e7db990f9f0b6e031dfc0aba79ee968b250f34fc
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36200f14a40952b0bdb6a1d8eb87a6a36477e7fb53bdd6a8937f3fddc9dcca4
+oid sha256:b68fd37a48e3e687292158fa1099cf9a3e8146a4388e28bdd88071f71b6022fb
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da625bdbaba1e1b9a41c85e65d17da2b21a48f48126a4ef7c6978303b33ffaa8
+oid sha256:f3993f1ade40b7ccc43179ee60d2b84e50c356bed8c82f5c7e7b3dedcbb9221a
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5316085815429688,
-  "best_model_checkpoint": "./outputs/checkpoint-2300",
-  "epoch": 1.6757741347905282,
+  "best_metric": 1.5180491209030151,
+  "best_model_checkpoint": "./outputs/checkpoint-2400",
+  "epoch": 1.748633879781421,
   "eval_steps": 100,
-  "global_step": 2300,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,13 +329,27 @@
       "eval_samples_per_second": 43.694,
       "eval_steps_per_second": 5.467,
       "step": 2300
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002,
+      "loss": 1.5271,
+      "step": 2400
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 1.5180491209030151,
+      "eval_runtime": 143.4857,
+      "eval_samples_per_second": 43.726,
+      "eval_steps_per_second": 5.471,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.369615582192681e+17,
+  "total_flos": 1.4291504286643814e+17,
   "trial_name": null,
   "trial_params": null
 }