Training in progress, epoch 16, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc4723fe9045490ac6bc5296f519d941b154df0caf643e2dce487d167c2b24a
+oid sha256:1febf146cbefa4616cf07697fcadd4ad1993ddac143ecb6e68e00f26f4ebb7f9
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859637f67f49d20bfb67c6536373704259170230074c442155b5764193a5bb4a
+oid sha256:e4b0d3900dba4992406f6ba5ddb840c62e3aa69976e05ddfa4f2db862788cff2
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e870823f3400c37084fa566df496ba6a8dee59e7600040b664dd7a65032280a
+oid sha256:e479a4621da806b031f596bb2ec665f9d626a329d4c48bff43208ddaf5107612
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dcc0ca83739baa01baf2312b341daaad1a3c78ff7ebd453696abe2d7239a53f
+oid sha256:2127cb7f98021af2ecfa1248845f016187bade36565a2ded3aecf156e298bb33
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8705362677574158,
-  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-3855",
-  "epoch": 15.0,
+  "best_metric": 0.8568298816680908,
+  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-4112",
+  "epoch": 16.0,
   "eval_steps": 500,
-  "global_step": 3855,
+  "global_step": 4112,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,21 @@
       "eval_samples_per_second": 46.565,
       "eval_steps_per_second": 5.821,
       "step": 3855
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.5744128227233887,
+      "learning_rate": 7.322916666666667e-05,
+      "loss": 0.5853,
+      "step": 4112
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.8568298816680908,
+      "eval_runtime": 9.2831,
+      "eval_samples_per_second": 46.536,
+      "eval_steps_per_second": 5.817,
+      "step": 4112
     }
   ],
   "logging_steps": 500,
@@ -260,7 +275,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.539929923990323e+17,
+  "total_flos": 5.909258585589678e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null