Training in progress, step 1107, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa5e5bab35b86229d70f26a2e49c75942780efa3cda825d2a871d062c2c1fa59
+oid sha256:7c7480c98395387d81f4898bbe803b1b09cd78cf6c4083fd032db515634fae0f
 size 735396724

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a21b2959809d775978591eaa5277b13773ad436946ab0b94483cc38ea2aa94
+oid sha256:9734dac75452a3ec5e8c3f0edcb468474c8ee763d672155f14b9e1257b9a1c37
 size 1470915147

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f41654f1fbe07595fa1ef489738bf38fa708202f0afe40690db87e9b0629178
+oid sha256:5d74a91b2b37f55b3a2d5720e74d3262af0e24471efcd6d170ceb0325b485f0a
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8940da0c0d2aff70d088e0e43c2da7d47cc4c9fd5d64b4c88286396e295d78
+oid sha256:faca9e1fe8518a31ec7fa0aae254931d46829c88d81457c0e89461fd4624fb92
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07cba0ab316dbee8063956335afa01a626d8a9d9c20a70c7df4e27b944868af2
+oid sha256:a4fceef76ebed486b7332993691809fa690411f45e6e6ba2dbec928c7d3e31ed
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2271fc5bfce1d00dd4f4b095bddc827ee5c884ad371a41ca4aba342067afe1e9
+oid sha256:46de38763030bd3661bb86fab5ab0bd55a426cace1f3f5287d2cb74aa8691e88
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0c19859249292f7cb952de238a8509b5021fc9359333b97db72de39a27a246
+oid sha256:8a57aa32fa04ea97ae973812591785d6853db431a6e93c7922a2b09f024c1034
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:939d683092bf98a1f01f7a2e1512a2973eac747b42e6cd23f366912c3be9ff02
+oid sha256:50a488f25d1de2aa3399cc835cc220ad8a953a89a67f3eb8cd51c1a14ab196a9
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca7103d76fa5e933f5a9516817d10ef779cc4a3066f71b104cb070da48746ae
+oid sha256:23c9f3f079d90926eb849142b33bd40944e255042998f9c16ac29c25e9afb3ed
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0019118f7593961c31004c27d12288aafc234fdfe4a6fb56f223003de8731a48
+oid sha256:1a187ed1b9b8d65ac0cdda2ec586655ed6f5cd209ff20fd3c560ca9ab5f61110
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c914ee4007cd925a03aea76e323b787c53b2b8d9d857569c32b642586a697c6
+oid sha256:961fb5d131246985b80718cdf29d24db75cc15fd723a3e9a9995fbe14bc2f6e9
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 861,
-  "best_metric": 0.728103938603657,
-  "best_model_checkpoint": "model/checkpoint-861",
-  "epoch": 2.0122699386503067,
+  "best_global_step": 1107,
+  "best_metric": 0.7315732624029576,
+  "best_model_checkpoint": "model/checkpoint-1107",
+  "epoch": 2.263803680981595,
   "eval_steps": 123,
-  "global_step": 984,
+  "global_step": 1107,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -229,6 +229,38 @@
       "eval_samples_per_second": 1983.778,
       "eval_steps_per_second": 31.0,
       "step": 984
+    },
+    {
+      "epoch": 2.044989775051125,
+      "grad_norm": 0.21148434281349182,
+      "learning_rate": 1.3383514227331213e-05,
+      "loss": 0.0923,
+      "step": 1000
+    },
+    {
+      "epoch": 2.147239263803681,
+      "grad_norm": 0.2723678648471832,
+      "learning_rate": 1.275311844301107e-05,
+      "loss": 0.0878,
+      "step": 1050
+    },
+    {
+      "epoch": 2.2494887525562373,
+      "grad_norm": 0.29290780425071716,
+      "learning_rate": 1.2110643333066026e-05,
+      "loss": 0.0902,
+      "step": 1100
+    },
+    {
+      "epoch": 2.263803680981595,
+      "eval_entity_f1": 0.7315732624029576,
+      "eval_entity_precision": 0.6525847419133266,
+      "eval_entity_recall": 0.8688473217276667,
+      "eval_loss": 0.09130457043647766,
+      "eval_runtime": 75.4966,
+      "eval_samples_per_second": 1986.846,
+      "eval_steps_per_second": 31.048,
+      "step": 1107
     }
   ],
   "logging_steps": 50,
@@ -248,7 +280,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2473698826688922e+17,
+  "total_flos": 1.4029788281621709e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null