Training in progress, step 1230, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c7480c98395387d81f4898bbe803b1b09cd78cf6c4083fd032db515634fae0f
+oid sha256:b1f6116bb7a97e516a85807c01c35774b985662017b47f98cd24a9124b88166a
 size 735396724

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9734dac75452a3ec5e8c3f0edcb468474c8ee763d672155f14b9e1257b9a1c37
+oid sha256:0413b1e90d649193233154ddf1573518252faaa0645b4753701b0ad69a2662fa
 size 1470915147

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d74a91b2b37f55b3a2d5720e74d3262af0e24471efcd6d170ceb0325b485f0a
+oid sha256:97d11c64ec27315995435b80f4545c5910f08414b5bac8bb540db7076705201c
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faca9e1fe8518a31ec7fa0aae254931d46829c88d81457c0e89461fd4624fb92
+oid sha256:5c8c28c749c2be23b634b4742fc98de354c3cd37e7ad8cd74cfb8729d066ce95
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4fceef76ebed486b7332993691809fa690411f45e6e6ba2dbec928c7d3e31ed
+oid sha256:fc4be99adb9c7eb949a3a51cbbd3ad1786ec86cefbfc0040ef4875b1d486d7fe
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46de38763030bd3661bb86fab5ab0bd55a426cace1f3f5287d2cb74aa8691e88
+oid sha256:ab4b3956a1d2361a5100b2263cffdffbf5a993a1d605e5b7bd4c13e55b2da1ab
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a57aa32fa04ea97ae973812591785d6853db431a6e93c7922a2b09f024c1034
+oid sha256:d15b8e9d63004ab2e9a102455ed0705f23a9d84a48e9a05c181c490b8bb69fbc
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a488f25d1de2aa3399cc835cc220ad8a953a89a67f3eb8cd51c1a14ab196a9
+oid sha256:78bbaf2f1a9c83f97314da925e0f195cc11caadcd7c81afa2a26d8a6f510e2e5
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c9f3f079d90926eb849142b33bd40944e255042998f9c16ac29c25e9afb3ed
+oid sha256:d5622f52c3ef0398b9232619c67583a87f2851661d2f4b4ea0150e23d9d0ebac
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a187ed1b9b8d65ac0cdda2ec586655ed6f5cd209ff20fd3c560ca9ab5f61110
+oid sha256:1065cf0d8778cb459b707725555f8b8dc180e9ecd75d0dcfc31b1719446e7ab0
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961fb5d131246985b80718cdf29d24db75cc15fd723a3e9a9995fbe14bc2f6e9
+oid sha256:89b85ec18beccdd1c56640cd4f658fcf914985c347d546090420a5cd3bc1fcda
 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": 2.263803680981595,
+  "epoch": 2.5153374233128836,
   "eval_steps": 123,
-  "global_step": 1107,
+  "global_step": 1230,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -261,6 +261,31 @@
       "eval_samples_per_second": 1986.846,
       "eval_steps_per_second": 31.048,
       "step": 1107
+    },
+    {
+      "epoch": 2.3517382413087935,
+      "grad_norm": 0.2427435666322708,
+      "learning_rate": 1.1458907761347955e-05,
+      "loss": 0.0891,
+      "step": 1150
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 0.28246018290519714,
+      "learning_rate": 1.0800771222046833e-05,
+      "loss": 0.0894,
+      "step": 1200
+    },
+    {
+      "epoch": 2.5153374233128836,
+      "eval_entity_f1": 0.7291324410312804,
+      "eval_entity_precision": 0.6472937354982619,
+      "eval_entity_recall": 0.8735209258598892,
+      "eval_loss": 0.0904151201248169,
+      "eval_runtime": 75.3828,
+      "eval_samples_per_second": 1989.845,
+      "eval_steps_per_second": 31.095,
+      "step": 1230
     }
   ],
   "logging_steps": 50,
@@ -280,7 +305,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4029788281621709e+17,
+  "total_flos": 1.5594436331307008e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null