Training in progress, epoch 15, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed725d9d2506469d1164aec4f81769d1c9e8856bbeb7c943c0a98de5d6737ec1
+oid sha256:bbc4723fe9045490ac6bc5296f519d941b154df0caf643e2dce487d167c2b24a
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05270c73f97bd25b934d8b74c562ffeb6ce543f62195b399f5201e5d590088c
+oid sha256:859637f67f49d20bfb67c6536373704259170230074c442155b5764193a5bb4a
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6799f5713e360b18bd49bdd40d277a79cff0753fb1327fffa08665ffe174400c
+oid sha256:6e870823f3400c37084fa566df496ba6a8dee59e7600040b664dd7a65032280a
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf4f8eb4eac6f82f900daa0f2c66883ed858058792a4319784f342865fc75551
+oid sha256:0dcc0ca83739baa01baf2312b341daaad1a3c78ff7ebd453696abe2d7239a53f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8803820013999939,
-  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-3598",
-  "epoch": 14.0,
+  "best_metric": 0.8705362677574158,
+  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-3855",
+  "epoch": 15.0,
   "eval_steps": 500,
-  "global_step": 3598,
+  "global_step": 3855,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,21 @@
       "eval_samples_per_second": 46.508,
       "eval_steps_per_second": 5.813,
       "step": 3598
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.5064253211021423,
+      "learning_rate": 7.490234375e-05,
+      "loss": 0.6111,
+      "step": 3855
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.8705362677574158,
+      "eval_runtime": 9.2774,
+      "eval_samples_per_second": 46.565,
+      "eval_steps_per_second": 5.821,
+      "step": 3855
     }
   ],
   "logging_steps": 500,
@@ -245,7 +260,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.170601262390968e+17,
+  "total_flos": 5.539929923990323e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null