Training in progress, step 984, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0e470e1eacd956bee52a20508ccdb7f508b31c3c5f624b811daf5cfa3c7cf3
+oid sha256:aa5e5bab35b86229d70f26a2e49c75942780efa3cda825d2a871d062c2c1fa59
 size 735396724

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333e703f3783d34a6d44079c09bfb829d5cf3ee625752b283ca8731d7c2d4193
+oid sha256:54a21b2959809d775978591eaa5277b13773ad436946ab0b94483cc38ea2aa94
 size 1470915147

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386936f571a3bb73993bb57c8096f93a00e47a91407b87b14eafaf523d8d4243
+oid sha256:6f41654f1fbe07595fa1ef489738bf38fa708202f0afe40690db87e9b0629178
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc802edde1abd3269a9fb5bd5728b077d66511bd1040cd61d61bfd756d8edf82
+oid sha256:9c8940da0c0d2aff70d088e0e43c2da7d47cc4c9fd5d64b4c88286396e295d78
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5669e1a3fa934bf58fc578de28d959d51d71136e896799b0f88f3a63a39c20ae
+oid sha256:07cba0ab316dbee8063956335afa01a626d8a9d9c20a70c7df4e27b944868af2
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1e0244fee1d7a41af4c1e6bb36d9c21f1092f569f8c69a338a0d753130e2f1
+oid sha256:2271fc5bfce1d00dd4f4b095bddc827ee5c884ad371a41ca4aba342067afe1e9
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d38a5b73c21e3fdc1d3880bc420afefb2bcaee15f4859f00a2dedf626d423293
+oid sha256:0f0c19859249292f7cb952de238a8509b5021fc9359333b97db72de39a27a246
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6428c4cb1b09dbf4c49c45d7c925fedb46fbf7d14d24a337331ceb01c537fd7e
+oid sha256:939d683092bf98a1f01f7a2e1512a2973eac747b42e6cd23f366912c3be9ff02
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962516c0946264663175debb272171a6aeeef3bcbf3a51bb37623d3e002784bc
+oid sha256:dca7103d76fa5e933f5a9516817d10ef779cc4a3066f71b104cb070da48746ae
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58076390752eb289cf58b117a31dac67edb3ce8024e8cda265f0e1778fdf0150
+oid sha256:0019118f7593961c31004c27d12288aafc234fdfe4a6fb56f223003de8731a48
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b33311c9d1ac1e2e9a207a403ad11f68a52ddbcc7079e83ceb4058a94228f8
+oid sha256:3c914ee4007cd925a03aea76e323b787c53b2b8d9d857569c32b642586a697c6
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 861,
   "best_metric": 0.728103938603657,
   "best_model_checkpoint": "model/checkpoint-861",
-  "epoch": 1.7607361963190185,
+  "epoch": 2.0122699386503067,
   "eval_steps": 123,
-  "global_step": 861,
+  "global_step": 984,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -204,6 +204,31 @@
       "eval_samples_per_second": 1992.087,
       "eval_steps_per_second": 31.13,
       "step": 861
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.2772167921066284,
+      "learning_rate": 1.4597069489554533e-05,
+      "loss": 0.0949,
+      "step": 900
+    },
+    {
+      "epoch": 1.9427402862985685,
+      "grad_norm": 0.24074728786945343,
+      "learning_rate": 1.3999064820296745e-05,
+      "loss": 0.0941,
+      "step": 950
+    },
+    {
+      "epoch": 2.0122699386503067,
+      "eval_entity_f1": 0.7237753555050341,
+      "eval_entity_precision": 0.636850502055661,
+      "eval_entity_recall": 0.8719000226926443,
+      "eval_loss": 0.09294217079877853,
+      "eval_runtime": 75.6133,
+      "eval_samples_per_second": 1983.778,
+      "eval_steps_per_second": 31.0,
+      "step": 984
     }
   ],
   "logging_steps": 50,
@@ -223,7 +248,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.091555797457961e+17,
+  "total_flos": 1.2473698826688922e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null