Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0a9f3bc9bdf3caa203134644c6071b898b9dfc2a9de861858cf75efe3e28ba5
+oid sha256:65240d116995e611ecbc650bcb4778b3401a0509d3aa220307b3c31cf1952f7e
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8d864d40f05ac5ef6ceea3553467eb16ba456c3653872b0dddcfd3d6cf933a
+oid sha256:44ed85d529718b386f8608857370d16fde89dcd3fcc6b15cfa277b30bdbd0ebd
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c3b6d15e752779cee5e9a6942923b5dafa23e30d7576be88fa9256bbf60f50
+oid sha256:8bb3b882e2821464a9e8ecf24229d2761b3972d473187bb0e8987bc38205d855
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c061cc93bc8f89035440fff607b7c18ef87206a55525ba751b807a11abf6d3e
+oid sha256:8325774c5216d42461f4f0d2f46a295a9e74d21ab580cd43104c1ce37b007328
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0027897357940674,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.2185792349726776,
+  "best_metric": 1.9537049531936646,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.29143897996357016,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,13 +49,27 @@
       "eval_samples_per_second": 43.535,
       "eval_steps_per_second": 5.447,
       "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 1.9806,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 1.9537049531936646,
+      "eval_runtime": 144.1171,
+      "eval_samples_per_second": 43.534,
+      "eval_steps_per_second": 5.447,
+      "step": 400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.7869715412615168e+16,
+  "total_flos": 2.3847291608039424e+16,
   "trial_name": null,
   "trial_params": null
 }