Training in progress, step 615, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b67c149f93729ff5d99f0579c55f8a26bb90fe36bcc54fa14c0c80571b72bc
+oid sha256:4ff836c102370effe0873d714d18fb4deb97c990377413beb28af0209b7117fd
 size 735396724

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fea94f691bcda836a311e6903ddfbcac11ebb5e781b8a9476dfc2efe58fea1a
+oid sha256:23121584ddfa42bf24d51afe9540f4af170e58a7d92879f2ef5afc774afcf860
 size 1470915147

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e6530759c518c078edc4ae49d672f5f242a93037b0e4dd194c202c72d75543
+oid sha256:d09f12437570e9924f51bc4a821db9b068e306d232df0cca1a764d5a6c61a79f
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366c74d3a7fe533d4fa142e544c066f8f9646b963e7962826461ae512537ca63
+oid sha256:2b886aa3d5bf3a5412d189e2e63abc0e0362d43ead0c1373f953b7ddf9847afb
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb1b72021107976ad5d442650034b28c3c6bc9c3e8de922d645c6277ea8d9eb
+oid sha256:be74bf3f842bae7677c9d0f21bf8c2bf8bdef7bc5e4729c1e101ce625035e9bd
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5bcca44a7f5fab1f8e98dce58817837a3d7095f1ad1c0ef1c858df738b40285
+oid sha256:fb1124a4af024eed9c934cf3ba9d0d996a738e061f5691271c14c7e5100af77b
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea798263f1db0f52960cdcad18f3b680365093036927425971d0f7b83b8cac1
+oid sha256:33fc7fdc06cdeb8bb2807eccde88ebb8242a3864a3857fb765782ad7bd05e4c1
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c94f331ae72a64d5dac40124aeea47d4554af3a199298edfb60ccc8b3d6eb31
+oid sha256:b5836b27184f990ca621738efc9434979e8a956e3ee20e9620b60dc22e0b28dc
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa4dd4ef2abf1151df3ac605c46ea001fb6a28e625e02202e88d37f2af78be6
+oid sha256:40658d030b33d76a0abb569872fbae573ee257ce1a678d173300ad883007eb86
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a89d4c15664b7f5001cf76be5071f4d0e1cffc50ac157651c9bce0d5c37b6ab
+oid sha256:5e84ac527cf9cfef8619fd0f3a76b8211c6167dcc7c225bfa4dafe4104b5fd35
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bba0415825f315ff5d45583b7b1ecd031ea2fde60e522a47be2528cc3a730746
+oid sha256:ff8cacffbc62e563c7b7ee69a67f0fcd9357f9269af92f22b2b3802c932e9df3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 492,
   "best_metric": 0.7237721816258966,
   "best_model_checkpoint": "model/checkpoint-492",
-  "epoch": 1.0061349693251533,
+  "epoch": 1.2576687116564418,
   "eval_steps": 123,
-  "global_step": 492,
+  "global_step": 615,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,38 @@
       "eval_samples_per_second": 1980.667,
       "eval_steps_per_second": 30.951,
       "step": 492
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.2750433385372162,
+      "learning_rate": 1.8455893306060422e-05,
+      "loss": 0.1016,
+      "step": 500
+    },
+    {
+      "epoch": 1.1247443762781186,
+      "grad_norm": 0.29885414242744446,
+      "learning_rate": 1.8083934841122383e-05,
+      "loss": 0.0981,
+      "step": 550
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.23177891969680786,
+      "learning_rate": 1.7676508057876326e-05,
+      "loss": 0.0969,
+      "step": 600
+    },
+    {
+      "epoch": 1.2576687116564418,
+      "eval_entity_f1": 0.7210088680783326,
+      "eval_entity_precision": 0.6396341157410339,
+      "eval_entity_recall": 0.8732237602792275,
+      "eval_loss": 0.09714934974908829,
+      "eval_runtime": 75.4582,
+      "eval_samples_per_second": 1987.855,
+      "eval_steps_per_second": 31.064,
+      "step": 615
     }
   ],
   "logging_steps": 50,
@@ -134,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.235385980413542e+16,
+  "total_flos": 7.797577516843008e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null