Training in progress, step 738, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff836c102370effe0873d714d18fb4deb97c990377413beb28af0209b7117fd
+oid sha256:8577b4857b879d05e0f8a6cfe7c43b8c8ced9e7dfe63a4280e2e26a0e15e3c94
 size 735396724

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23121584ddfa42bf24d51afe9540f4af170e58a7d92879f2ef5afc774afcf860
+oid sha256:94b0395fd5b76ce19e34d146a8c289af03287be06f938af8e5a3ecf61883d775
 size 1470915147

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09f12437570e9924f51bc4a821db9b068e306d232df0cca1a764d5a6c61a79f
+oid sha256:2438a2027427b3d96e56afa02342e40b518cc5a4732faf79d6925d5d55c577f0
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b886aa3d5bf3a5412d189e2e63abc0e0362d43ead0c1373f953b7ddf9847afb
+oid sha256:b38c30466207633871e8888206bfe5061612dc77969df08738de7f38180f016e
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be74bf3f842bae7677c9d0f21bf8c2bf8bdef7bc5e4729c1e101ce625035e9bd
+oid sha256:500ceadf909eafd207b60a2fffbb122c8876c30e24e54f8c5c803d79507c972c
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb1124a4af024eed9c934cf3ba9d0d996a738e061f5691271c14c7e5100af77b
+oid sha256:67ea961a54ce2c81798cc07b051c3e0a86c346a5b46ed3c52e9ad1a579e735e6
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fc7fdc06cdeb8bb2807eccde88ebb8242a3864a3857fb765782ad7bd05e4c1
+oid sha256:0b516e159fa8c859060ac9216c8c88e777ae6b3be75cd282753aa03e2d8ddd5d
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5836b27184f990ca621738efc9434979e8a956e3ee20e9620b60dc22e0b28dc
+oid sha256:c00c04a0504831ef1b89143e9318053ab8faf9658d240bdb98b2f4c94afaf578
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40658d030b33d76a0abb569872fbae573ee257ce1a678d173300ad883007eb86
+oid sha256:d58dcb0bbaa1efa8f03be4baf87c9eab892f94695cc44466d3b7dcde1769437c
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e84ac527cf9cfef8619fd0f3a76b8211c6167dcc7c225bfa4dafe4104b5fd35
+oid sha256:05560e77f104933fad67bf5dcd7fe3899a199c567c3ae3bd1089287dcba01cbe
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8cacffbc62e563c7b7ee69a67f0fcd9357f9269af92f22b2b3802c932e9df3
+oid sha256:1095ec08fae81706719696411543a90b06fc787d5310b31ba6bec1d086872596
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 492,
-  "best_metric": 0.7237721816258966,
-  "best_model_checkpoint": "model/checkpoint-492",
-  "epoch": 1.2576687116564418,
+  "best_global_step": 738,
+  "best_metric": 0.7250351529639901,
+  "best_model_checkpoint": "model/checkpoint-738",
+  "epoch": 1.50920245398773,
   "eval_steps": 123,
-  "global_step": 615,
+  "global_step": 738,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,31 @@
       "eval_samples_per_second": 1987.855,
       "eval_steps_per_second": 31.064,
       "step": 615
+    },
+    {
+      "epoch": 1.329243353783231,
+      "grad_norm": 0.28684553503990173,
+      "learning_rate": 1.723540054406503e-05,
+      "loss": 0.0963,
+      "step": 650
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.2544998824596405,
+      "learning_rate": 1.6762547661862417e-05,
+      "loss": 0.0946,
+      "step": 700
+    },
+    {
+      "epoch": 1.50920245398773,
+      "eval_entity_f1": 0.7250351529639901,
+      "eval_entity_precision": 0.6421383532568621,
+      "eval_entity_recall": 0.8727158772868242,
+      "eval_loss": 0.09457383304834366,
+      "eval_runtime": 75.1677,
+      "eval_samples_per_second": 1995.539,
+      "eval_steps_per_second": 31.184,
+      "step": 738
     }
   ],
   "logging_steps": 50,
@@ -166,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.797577516843008e+16,
+  "total_flos": 9.35469922690007e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null