Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e42f9052541b5a6ff50585d6bbb15b0f5d92e9761510525ee71a8da3d8a992c
+oid sha256:13a4ac9824595bc25b640c6a0279117b5879341d3cc6fc7d8068eb8ff70678b4
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d467b76ac5edc13c5aaff8b1c3309a2c25979af7f7e08d200d802e2070f281e1
+oid sha256:b643239f63b91418912467e7b57439ead608317aca4b279d3a5880247a00e825
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f214f133cdb51d7d62d59c0aba5528527483d65746e5cf626a78f7260402d1c
+oid sha256:f9d4b92577f6c63dd867e1b2d19083fb1b244002b84c898307cf76402ee38c71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba99001c27a6a50d67f8b708e01f78e672e19cc9bf25e10cf6fac601ed8b1777
+oid sha256:a6e5673f68204a8410dd9102d1cd36a60e27feb63c2db400cfa86d2756b65e70
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4579496623695518,
+  "epoch": 1.5346838551258442,
   "eval_steps": 500,
-  "global_step": 9500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,13 +131,19 @@
       "learning_rate": 0.0007085328422344997,
       "loss": 0.5722,
       "step": 9500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0006931860036832413,
+      "loss": 0.5749,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 5036690159173632.0,
+  "total_flos": 5302569128165376.0,
   "trial_name": null,
   "trial_params": null
 }