Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa13a44cb5fa7398efc25d14ec161697f4e0b32e1b13354e91c11726cc55da1
+oid sha256:d05b2c2c9b2d581d92485eba6a860e07b6da956c48a009e5a6f791785845071e
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc895517579eb4120987a61426713077595205131abd90d9a379a2acc037f011
+oid sha256:4e950a510fa6a75d273af5a873d09436db017fab6e710e9e506f6ff12b291b94
 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": 2.1183180809020996,
-  "best_model_checkpoint": "./outputs/checkpoint-2500",
-  "epoch": 1.8214936247723132,
+  "best_metric": 2.107461929321289,
+  "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": 30.412,
       "eval_steps_per_second": 3.805,
       "step": 2500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 2.1031,
+      "step": 2600
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 2.107461929321289,
+      "eval_runtime": 206.4059,
+      "eval_samples_per_second": 30.396,
+      "eval_steps_per_second": 3.803,
+      "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
 }