Training in progress, step 1353, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f6116bb7a97e516a85807c01c35774b985662017b47f98cd24a9124b88166a
+oid sha256:4a3b8dae878391ccdde5efef65aac68f898765585be40fdedb1763b5c32d3572
 size 735396724

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0413b1e90d649193233154ddf1573518252faaa0645b4753701b0ad69a2662fa
+oid sha256:bd47712bd98321074a343390bc24e5d74bdfe0e54b79a2fb374b6c8370fe9155
 size 1470915147

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d11c64ec27315995435b80f4545c5910f08414b5bac8bb540db7076705201c
+oid sha256:3fe140131aade8de244a1f9906c0ea077cbc86618e1ec76642211d944eabdc9e
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8c28c749c2be23b634b4742fc98de354c3cd37e7ad8cd74cfb8729d066ce95
+oid sha256:692b76aced1495252a289c9275f5bfacc17dbd8baed1fc23a89e2669bd6a6ee6
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4be99adb9c7eb949a3a51cbbd3ad1786ec86cefbfc0040ef4875b1d486d7fe
+oid sha256:6d64529358832803e0826e10a5306180840848f0d71ee25b721a5947710297c9
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4b3956a1d2361a5100b2263cffdffbf5a993a1d605e5b7bd4c13e55b2da1ab
+oid sha256:14bbf33bb5acf93fd7470dc8fd65bac5bb46efac5fccaef5be2ca4f3df4df544
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d15b8e9d63004ab2e9a102455ed0705f23a9d84a48e9a05c181c490b8bb69fbc
+oid sha256:cf55bbcce84afd6678660c3daaf444f06b34e64692fc3c5dc1f70cc20cbf3356
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78bbaf2f1a9c83f97314da925e0f195cc11caadcd7c81afa2a26d8a6f510e2e5
+oid sha256:8ad6f352ce2f4372e730c435e79ff404e511e04b4848728adb550294d444318c
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5622f52c3ef0398b9232619c67583a87f2851661d2f4b4ea0150e23d9d0ebac
+oid sha256:253ac58e55fb568050459353a65b6484e3db6a1e8efc73dff58aa0168523c749
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1065cf0d8778cb459b707725555f8b8dc180e9ecd75d0dcfc31b1719446e7ab0
+oid sha256:0430e7d456ad88d276ee666d3bba222029b41da9e47292339f857192e8367cdd
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89b85ec18beccdd1c56640cd4f658fcf914985c347d546090420a5cd3bc1fcda
+oid sha256:5a2b98aadf3dee607faf6695c52919e41f78eab249593a5656849f6f096106f2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1107,
   "best_metric": 0.7315732624029576,
   "best_model_checkpoint": "model/checkpoint-1107",
-  "epoch": 2.5153374233128836,
+  "epoch": 2.766871165644172,
   "eval_steps": 123,
-  "global_step": 1230,
+  "global_step": 1353,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -286,6 +286,38 @@
       "eval_samples_per_second": 1989.845,
       "eval_steps_per_second": 31.095,
       "step": 1230
+    },
+    {
+      "epoch": 2.556237218813906,
+      "grad_norm": 0.23193299770355225,
+      "learning_rate": 1.0139121293640819e-05,
+      "loss": 0.0883,
+      "step": 1250
+    },
+    {
+      "epoch": 2.658486707566462,
+      "grad_norm": 0.22019708156585693,
+      "learning_rate": 9.476860969626324e-06,
+      "loss": 0.0892,
+      "step": 1300
+    },
+    {
+      "epoch": 2.7607361963190185,
+      "grad_norm": 0.21104931831359863,
+      "learning_rate": 8.816895921614581e-06,
+      "loss": 0.0867,
+      "step": 1350
+    },
+    {
+      "epoch": 2.766871165644172,
+      "eval_entity_f1": 0.7256578908461596,
+      "eval_entity_precision": 0.6445169298121908,
+      "eval_entity_recall": 0.8729698187830259,
+      "eval_loss": 0.0912156030535698,
+      "eval_runtime": 75.6029,
+      "eval_samples_per_second": 1984.052,
+      "eval_steps_per_second": 31.004,
+      "step": 1353
     }
   ],
   "logging_steps": 50,
@@ -300,12 +332,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.5594436331307008e+17,
+  "total_flos": 1.7151309741922714e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null