Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd1135ec428732f59e93730b803cf1bf120879bf1d680108db9597b73cd8203
+oid sha256:1756695100508f384748848f37362c0a92701451378276e043ef7f3c362dfcd4
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c3e5d9fc04a3acdf36b8dd658c508e7866eff7ccfe1a612897704bd1bda6e9c
+oid sha256:8773d9266c62da06bf399f56cb0c16d50f2c1a26ea46e2b85554430db8143450
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0d20d58bd89e713c08b07c8c7060ac9cf564e52b782f77021cead0bd733f4b
+oid sha256:72de1dad8d6233809f2cfc8005c48069a201d59ec0aed6d89a2e0fa5965139f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1630e356c8109125846f0083f0594c5f2b74cf28542e3a04cec04692c98c9d13
+oid sha256:8fd91438459da8cfd11b42ba89bb250b1431fb386cdd7af85c96ff891f5bd392
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4546965918536992,
+  "epoch": 1.6625103906899419,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,13 @@
       "learning_rate": 1.030756442227764e-05,
       "loss": 0.3417,
       "step": 3500
+    },
+    {
+      "epoch": 1.6625103906899419,
+      "grad_norm": 0.7672457098960876,
+      "learning_rate": 8.92213909670269e-06,
+      "loss": 0.3444,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -83,7 +90,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8524801509949440.0,
+  "total_flos": 9742717291069440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null