Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7619d6d9b7b1f98142754e0ee7aaa2fa78d7f616728b0937255be260419e6c6
+oid sha256:e4c3d15bccae4e542a64e97b70184cda16a6436092ca41515a713a5ea1df3e73
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18fc6e3d69aefbf4310e5826e56b6e16d74b7498b13c46c2f777cf72f5709bb3
+oid sha256:7c5d13f1671e91671aa221b98032c0f40fff0248e5b08941d0c0315d3b4da3d3
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfcfb7e12de9afeed6967cff0aeffa633fecf1b0469c1a40f3315ec78a50cc27
+oid sha256:296cf5594ce08d90ca2b2f149a2c461f378a809be111d5bafa2262d9e15c09d6
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5626935958862305,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 1.5464439392089844,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 1.092896174863388,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,13 +203,27 @@
       "eval_samples_per_second": 43.583,
       "eval_steps_per_second": 5.453,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 1.5362,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 1.5464439392089844,
+      "eval_runtime": 143.8789,
+      "eval_samples_per_second": 43.606,
+      "eval_steps_per_second": 5.456,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.34624139321344e+16,
+  "total_flos": 8.942208266285875e+16,
   "trial_name": null,
   "trial_params": null
 }