Training in progress, step 3600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49956faf6d374c68968a5ce7b6cad75ae6ecaaf9b6c1e44fa3b0c3e7ff27ed82
+oid sha256:2e1f4e4f1159439c73731fbbcb0e06967c84f07e96451c22c6b27cdafffe2cbf
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df6d00900b1e88654bd4ca60efe24abd89010ca1df7cdfd0f2ad54e52ea5cef
+oid sha256:5e384f532f76a074a5d3d8163f8b6586a7dc2684f22aa895121b259381225417
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbea88259d6e3921591759b6b112787854d664c6450349ec06e7cb329889ce0e
+oid sha256:2834e2a42f01beac16b7a64446d928671eb4ab1aa75df5c16b29088d84acc228
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b347a3fa18d78b1079ab69a462b88204415d2ec7a10bf5022f8a257be3147eb4
+oid sha256:5ba6f2560e9e50bf4c07ae51f4b861fc614845908d2b6da36028caeeadf50053
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.377625584602356,
-  "best_model_checkpoint": "./outputs/checkpoint-3500",
-  "epoch": 2.5500910746812386,
+  "best_metric": 1.3661019802093506,
+  "best_model_checkpoint": "./outputs/checkpoint-3600",
+  "epoch": 2.6229508196721314,
   "eval_steps": 100,
-  "global_step": 3500,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,13 +497,27 @@
       "eval_samples_per_second": 43.709,
       "eval_steps_per_second": 5.469,
       "step": 3500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.0002,
+      "loss": 1.3491,
+      "step": 3600
+    },
+    {
+      "epoch": 2.62,
+      "eval_loss": 1.3661019802093506,
+      "eval_runtime": 143.5994,
+      "eval_samples_per_second": 43.691,
+      "eval_steps_per_second": 5.467,
+      "step": 3600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.0839987895230464e+17,
+  "total_flos": 2.1434093681546035e+17,
   "trial_name": null,
   "trial_params": null
 }