Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb078275f5fa91778de46581f3f5dad176d10df12ee7923c2f1c1ff15c003d4c
+oid sha256:7cb723f1eb8653b71e1a06676986ed9bdbbf6c6da6d4f3191cffc299dc3f436a
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d18349d213872df6b0ef49f521349d64dfb6bc666a9ff93f11aa0b79376c868
+oid sha256:659f1651c8d502fd5b6ad4356bdb6dd6d9ea1bcad20dd05519c192fe009ba4a2
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b2c53f529a62a0884f6998e7f192527c1a4b1a76b45c95aa4b317f0f9f4397
+oid sha256:ec8a6a85c74c84b1931c98dfb99024e5154ce0f3a099bd81af66da693b03813f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd37581d93a41fc457d899cacb7a67009a6909f6dbf72b467de55158ef91ac94
+oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3896080255508423,
-  "best_model_checkpoint": "./outputs/checkpoint-2500",
-  "epoch": 1.8214936247723132,
+  "best_metric": 1.3768706321716309,
+  "best_model_checkpoint": "./outputs/checkpoint-2600",
+  "epoch": 1.8943533697632058,
   "eval_steps": 100,
-  "global_step": 2500,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,13 +357,27 @@
       "eval_samples_per_second": 43.616,
       "eval_steps_per_second": 5.457,
       "step": 2500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 1.3709,
+      "step": 2600
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 1.3768706321716309,
+      "eval_runtime": 143.8343,
+      "eval_samples_per_second": 43.62,
+      "eval_steps_per_second": 5.458,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.4901757565064806e+17,
+  "total_flos": 1.5498375085790822e+17,
   "trial_name": null,
   "trial_params": null
 }