Training in progress, epoch 12, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf7f54b64df93ce0f2fcb68fc7e653d2405f54ec2007bc21b1dbbf171b3b035
+oid sha256:ce74b4ea3d361c5c1ecc6ccad52d4d7d3857b396ffea6e6b6c00324281204439
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be947d954b496169e373878044be7308c4f2c478c1251870839f1a7cb47be36
+oid sha256:537bc2d1bbcd4c3dbc85b5398935c759488f1f94d15718533f482e0754ba7a47
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2322f66ff1c6e187e3a28e99424d0d727cfb601d8182c3cf171308f1229edf01
+oid sha256:5db4090529d4135db703428fd5d184e762992f7b5cc78772988d1fb1c76fb83c
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4fd1f16fcb95d9548ef1b42dd4a5a37d5b3e9dd4348574c75fdb00d7912893
+oid sha256:90e4057f36069d27dc95b7bc5bc3711e846f4900ff0fdc62b6ca072336f562a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9429148435592651,
-  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-2827",
-  "epoch": 11.0,
+  "best_metric": 0.9054032564163208,
+  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-3084",
+  "epoch": 12.0,
   "eval_steps": 500,
-  "global_step": 2827,
+  "global_step": 3084,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -172,6 +172,21 @@
       "eval_samples_per_second": 46.459,
       "eval_steps_per_second": 5.807,
       "step": 2827
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.4817085564136505,
+      "learning_rate": 7.9921875e-05,
+      "loss": 0.7099,
+      "step": 3084
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.9054032564163208,
+      "eval_runtime": 9.2846,
+      "eval_samples_per_second": 46.529,
+      "eval_steps_per_second": 5.816,
+      "step": 3084
     }
   ],
   "logging_steps": 500,
@@ -200,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.062615277592904e+17,
+  "total_flos": 4.4319439391922586e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null