Training in progress, step 3800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e18e73ce64e2835b41b3ec3e966871a0f2b4ec3d40a2303935541a739645c9eb
+oid sha256:53d904cb6fee366037ac5fdbda41679702f12a97f970942d2e9cd2685bb3fff4
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5622a16620ca0e402e49caf114f93e81fb6f1562816e1eb50f22224c4304a79a
+oid sha256:4e55638d968d67a53b0a6c5982ed9e8b389f3667f4c10e371f8c0f75be2f3ce7
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff244788f228d59f20add1a127912b5b144f70e4c321b25031a681809deb1ae0
+oid sha256:0625d44593f9a35a65bd6a0c353b2ee783deaa835a908009e34809ad32c4166a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c157d4508adfa804f177e78fb4986d5f3ffb3ec20ae255fb757aa13c0595fdb4
+oid sha256:3961d2f201ce99426ee113655da78d8214f6ef72fc082855daa3c565989888c2
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.257932186126709,
-  "best_model_checkpoint": "./outputs/checkpoint-3700",
-  "epoch": 2.6958105646630237,
+  "best_metric": 1.2482833862304688,
+  "best_model_checkpoint": "./outputs/checkpoint-3800",
+  "epoch": 2.768670309653916,
   "eval_steps": 100,
-  "global_step": 3700,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -525,13 +525,27 @@
       "eval_samples_per_second": 43.676,
       "eval_steps_per_second": 5.465,
       "step": 3700
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 3800
+    },
+    {
+      "epoch": 2.77,
+      "eval_loss": 1.2482833862304688,
+      "eval_runtime": 143.6429,
+      "eval_samples_per_second": 43.678,
+      "eval_steps_per_second": 5.465,
+      "step": 3800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.2052180376706253e+17,
+  "total_flos": 2.2648457919379046e+17,
   "trial_name": null,
   "trial_params": null
 }