Training in progress, step 19000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b26486e1fe864aaa707e43908b590aa8e0a293d7408341c680542008907156f
+oid sha256:139b762c258c9eb5cc544fedb22991559230c273e6b61d624ac96e111319c69f
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1732e4a933c930f68d86d2d498f090ac77021f39be32c92ad6a6c9f09fa1ed95
+oid sha256:2382b216c6169368827bf00947023a9e337a5851fc9d5518f5344300bd0fe1fe
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feece917c56bf36ba9e3ec6c050ec644c0ec5b7bd37756014773b0f22a42b7cd
+oid sha256:1932f6e219883f4a3f24819081a49b0aebfec1abfca44525a259e77652bf11c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eee77549b9fb54e6a74b8fda0ad4da0d65d300dde02f9ba94785b9401f1af9b
+oid sha256:8ccfc3f38f2e307720e2cbe200293361cc2776fbe89851498ed91ff727b05ff5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8391651319828117,
+  "epoch": 2.9158993247391036,
   "eval_steps": 500,
-  "global_step": 18500,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,13 +249,19 @@
       "learning_rate": 0.00043238182934315537,
       "loss": 0.5236,
       "step": 18500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.00041703499079189687,
+      "loss": 0.5266,
+      "step": 19000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 9806634315939840.0,
+  "total_flos": 1.0071282520424448e+16,
   "trial_name": null,
   "trial_params": null
 }