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:b4d0b7a3615f51bb3ec47a546ebef6713eaa54f62eb92cda757cc80797941650
+oid sha256:9dfa27dc57d9bdc19a8a62a9911e4706be0e650beff1c843278bd3c65f146ba4
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa5d05b8c75fe847c91caf3536a4eb6ef6fc4ebddeaa36b9998f4b80a0642a65
+oid sha256:46cab93585c5eda908ca63eb0d162fccc66e229658058f0bf91cd21d8fcc853c
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759e77ccf458a889b7b5189552587bc5a6060b4a877912775f82bf425e75e65c
+oid sha256:2976c6db6ebcdf9dabf12702a779e061718bd1c4ef8e49e51b66e2a5fcb97d74
 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": 2.1099581718444824,
-  "best_model_checkpoint": "./outputs/checkpoint-2600",
-  "epoch": 1.8943533697632058,
+  "best_metric": 2.09414005279541,
+  "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": 29.53,
       "eval_steps_per_second": 3.695,
       "step": 2600
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0002,
+      "loss": 2.0887,
+      "step": 2700
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 2.09414005279541,
+      "eval_runtime": 205.8822,
+      "eval_samples_per_second": 30.474,
+      "eval_steps_per_second": 3.813,
+      "step": 2700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.639893171800064e+16,
+  "total_flos": 7.934011037632512e+16,
   "trial_name": null,
   "trial_params": null
 }