Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8763ea45a0e1a1162037fde4da7db00a7ec966607e7c171e825f82e5480edb
+oid sha256:d680bf864856f9bfa584eb3208b4e38f5e9cb6cd1f58cceb049b31b9b2acfd73
 size 1625426996

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf6cc4c9a5c84cd78894459997f1185829c62926ab482b300712416712c557e
+oid sha256:3f2cfa1bc4665664041205554f346f8cb1719a2a51264588c21beb85644ae889
 size 3250759951

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0d34626275b21013e64e56b387386f6077114f4f50caa3f397c767638b70bc
-size 14308
+oid sha256:f73c7f3308641c8e2c15d99e5247e6be2d37417c7acb4a7ad64cb68b6d5fa4d2
+size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ac1b6df18ca358b9dc89245c201dff2865173edc344e5d1c93abdea6f4beaa
+oid sha256:3b776a4dee12abf784324330625ce24646d6dfd2b7e10e3f7907e7112d9954c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -107,13 +107,19 @@
       "learning_rate": 1.335113484646195e-06,
       "loss": 0.0613,
       "step": 7000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0713,
+      "step": 7500
     }
   ],
   "logging_steps": 500,
   "max_steps": 7500,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1.18505067675648e+16,
+  "total_flos": 1.26966087401472e+16,
   "trial_name": null,
   "trial_params": null
 }