Training in progress, step 2700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb723f1eb8653b71e1a06676986ed9bdbbf6c6da6d4f3191cffc299dc3f436a
+oid sha256:b55253205b265429c4329d889be58663da122889fae1be1af323faa4cdd2a55b
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:659f1651c8d502fd5b6ad4356bdb6dd6d9ea1bcad20dd05519c192fe009ba4a2
+oid sha256:a90c559550d2478dede85e57d6af776ad0c7c350ac3363096a03cdc0c718e0a0
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec8a6a85c74c84b1931c98dfb99024e5154ce0f3a099bd81af66da693b03813f
+oid sha256:22c037384a9cbc8581bd2019de705fcab8ab427ff19cd49f03b529c50a205a6a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
+oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3768706321716309,
-  "best_model_checkpoint": "./outputs/checkpoint-2600",
-  "epoch": 1.8943533697632058,
+  "best_metric": 1.3619952201843262,
+  "best_model_checkpoint": "./outputs/checkpoint-2700",
+  "epoch": 1.9672131147540983,
   "eval_steps": 100,
-  "global_step": 2600,
+  "global_step": 2700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -371,13 +371,27 @@
       "eval_samples_per_second": 43.62,
       "eval_steps_per_second": 5.458,
       "step": 2600
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0002,
+      "loss": 1.3603,
+      "step": 2700
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 1.3619952201843262,
+      "eval_runtime": 143.7532,
+      "eval_samples_per_second": 43.644,
+      "eval_steps_per_second": 5.461,
+      "step": 2700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.5498375085790822e+17,
+  "total_flos": 1.60955611905024e+17,
   "trial_name": null,
   "trial_params": null
 }