Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c917a896d8592aa077741197e903c625bb83663b3808bd0750cf65aab8c949
+oid sha256:de09785324d59d86d5724b439f4833d7397cb5621afb99c4c54608af51d332db
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ecf4f2d11640f3e8fdb7343df142575ae709db76d625148dd1cd286f46dedd2
+oid sha256:4eddf1a425b78bfa7077983949d0b2d5fdab07f3a6ece24f3112a43e2275765f
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68265a1c59544d7bf18c305ca95baaaca0646bd73f98f83bb470adae096938bb
+oid sha256:0b774cb850c8af04a764818f29624485353fb4e797d73dd76f4613c78e2d1fd0
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f4d188f937da7056a814d8d9ea51fb336e7ff0650952782195eb25e01fc00b
+oid sha256:df53bccd42a0542adafd2539bffb5b941c8e39796128cde2e246f10242bb5d9f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1470884084701538,
-  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-1285",
-  "epoch": 5.0,
+  "best_metric": 1.097914695739746,
+  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-1542",
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 1285,
+  "global_step": 1542,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,21 @@
       "eval_samples_per_second": 46.528,
       "eval_steps_per_second": 5.816,
       "step": 1285
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5049512386322021,
+      "learning_rate": 8.996093750000001e-05,
+      "loss": 1.0031,
+      "step": 1542
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.097914695739746,
+      "eval_runtime": 9.2778,
+      "eval_samples_per_second": 46.563,
+      "eval_steps_per_second": 5.82,
+      "step": 1542
     }
   ],
   "logging_steps": 500,
@@ -110,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8466433079967744e+17,
+  "total_flos": 2.2159719695961293e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null