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:ea39b1b2b34e1d00188d2181fbb823fefbc8a809ae5e527271e42ff80438cf62
+oid sha256:ca2dbbca216bd5c077aa9db307ca1927b738ca10c8b9b5b35255f5abb97d766f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8ce41d2957cca3ea4af22e6dbdc580e2d74c5411609ca1ae1206f670fa0425
+oid sha256:ec5a1672a6eeb0dbea27aed50fd871b5171f990b68323b1959f3a54208f6cfda
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b9445452b0f4ec2e34ecc2a5014eb62a4d39167a4355d4fcd661626ad65a5d
+oid sha256:759e77ccf458a889b7b5189552587bc5a6060b4a877912775f82bf425e75e65c
 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": 2.1192965507507324,
-  "best_model_checkpoint": "./outputs/checkpoint-2500",
-  "epoch": 1.8214936247723132,
+  "best_metric": 2.107308864593506,
+  "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": 11.138,
       "eval_steps_per_second": 1.394,
       "step": 2500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 2.1027,
+      "step": 2600
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 2.107308864593506,
+      "eval_runtime": 353.5605,
+      "eval_samples_per_second": 17.745,
+      "eval_steps_per_second": 2.22,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.346343543662592e+16,
+  "total_flos": 7.639893171800064e+16,
   "trial_name": null,
   "trial_params": null
 }