Training in progress, step 492, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00617d127e52142db152f51035e6d793d67b79698553c806fb0c755de24a4944
+oid sha256:d1b67c149f93729ff5d99f0579c55f8a26bb90fe36bcc54fa14c0c80571b72bc
 size 735396724

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aec0adc0e2b4b305e7a1da493a55e418ee0ee5d560c8ff61b106568d5b0bac5
+oid sha256:2fea94f691bcda836a311e6903ddfbcac11ebb5e781b8a9476dfc2efe58fea1a
 size 1470915147

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5daafd01e11a8e378bee423bfc78dc889b9595f52486fe44309d6cfdb1e8f39e
+oid sha256:07e6530759c518c078edc4ae49d672f5f242a93037b0e4dd194c202c72d75543
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd946779b63f36a745f76b3dea5b82fdda34f69f71b29d30bc33c6469ec6efc7
+oid sha256:366c74d3a7fe533d4fa142e544c066f8f9646b963e7962826461ae512537ca63
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb52d3d9719c3a23780cb0726fd105f13eb3795bef452c37de45847245f48c4
+oid sha256:6fb1b72021107976ad5d442650034b28c3c6bc9c3e8de922d645c6277ea8d9eb
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ea23a163b521be4be62f809b70e9314364da460e9093ec7e246193690284e2
+oid sha256:a5bcca44a7f5fab1f8e98dce58817837a3d7095f1ad1c0ef1c858df738b40285
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3aa0ea2b718d2e995605d91b46b0095c0770bb817cc0b7bb955f992dbfd3445
+oid sha256:aea798263f1db0f52960cdcad18f3b680365093036927425971d0f7b83b8cac1
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:274b05ab7fd4442bba200371ded2027858747aed543ac8bcea81c8efc8330216
+oid sha256:5c94f331ae72a64d5dac40124aeea47d4554af3a199298edfb60ccc8b3d6eb31
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70ecf73265273c79012c58e718f348331144177d9b2caba269cbcb34dabd37a
+oid sha256:8aa4dd4ef2abf1151df3ac605c46ea001fb6a28e625e02202e88d37f2af78be6
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c8994ebdec0308f7fb2f8c656db7abc240ad44611736b9d1866dfbb4e908d2
+oid sha256:8a89d4c15664b7f5001cf76be5071f4d0e1cffc50ac157651c9bce0d5c37b6ab
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b81c99c7d092f3e4d54713b045255676277930acb48938b544aa14bde54b79
+oid sha256:bba0415825f315ff5d45583b7b1ecd031ea2fde60e522a47be2528cc3a730746
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 369,
-  "best_metric": 0.7108936942946532,
-  "best_model_checkpoint": "model/checkpoint-369",
-  "epoch": 0.754601226993865,
+  "best_global_step": 492,
+  "best_metric": 0.7237721816258966,
+  "best_model_checkpoint": "model/checkpoint-492",
+  "epoch": 1.0061349693251533,
   "eval_steps": 123,
-  "global_step": 369,
+  "global_step": 492,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -90,6 +90,31 @@
       "eval_samples_per_second": 1978.617,
       "eval_steps_per_second": 30.919,
       "step": 369
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.29296356439590454,
+      "learning_rate": 1.9087040177743547e-05,
+      "loss": 0.1051,
+      "step": 400
+    },
+    {
+      "epoch": 0.9202453987730062,
+      "grad_norm": 0.2886279821395874,
+      "learning_rate": 1.8790751482432022e-05,
+      "loss": 0.1032,
+      "step": 450
+    },
+    {
+      "epoch": 1.0061349693251533,
+      "eval_entity_f1": 0.7237721816258966,
+      "eval_entity_precision": 0.645184879014441,
+      "eval_entity_recall": 0.868750067537632,
+      "eval_loss": 0.09940221905708313,
+      "eval_runtime": 75.7321,
+      "eval_samples_per_second": 1980.667,
+      "eval_steps_per_second": 30.951,
+      "step": 492
     }
   ],
   "logging_steps": 50,
@@ -109,7 +134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.673116000432947e+16,
+  "total_flos": 6.235385980413542e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null