Training in progress, step 3700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c94f2cbc0f8cd0538722dcd140f69f48483b184ff166470b000dba0dacc6617
+oid sha256:e18e73ce64e2835b41b3ec3e966871a0f2b4ec3d40a2303935541a739645c9eb
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278f67f0952f63166c3b3f3987b482241a5cc68d620de47d1c103e2da196d1f3
+oid sha256:5622a16620ca0e402e49caf114f93e81fb6f1562816e1eb50f22224c4304a79a
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef0cbe118e41f50f73b72dc69901b2174467b76d419ab6a1e3302e9eaafde12a
+oid sha256:ff244788f228d59f20add1a127912b5b144f70e4c321b25031a681809deb1ae0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
+oid sha256:c157d4508adfa804f177e78fb4986d5f3ffb3ec20ae255fb757aa13c0595fdb4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2685626745224,
-  "best_model_checkpoint": "./outputs/checkpoint-3600",
-  "epoch": 2.6229508196721314,
+  "best_metric": 1.257932186126709,
+  "best_model_checkpoint": "./outputs/checkpoint-3700",
+  "epoch": 2.6958105646630237,
   "eval_steps": 100,
-  "global_step": 3600,
+  "global_step": 3700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -511,13 +511,27 @@
       "eval_samples_per_second": 43.676,
       "eval_steps_per_second": 5.465,
       "step": 3600
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0002,
+      "loss": 1.2361,
+      "step": 3700
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 1.257932186126709,
+      "eval_runtime": 143.6501,
+      "eval_samples_per_second": 43.676,
+      "eval_steps_per_second": 5.465,
+      "step": 3700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.145691983734784e+17,
+  "total_flos": 2.2052180376706253e+17,
   "trial_name": null,
   "trial_params": null
 }