Training in progress, epoch 13, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce74b4ea3d361c5c1ecc6ccad52d4d7d3857b396ffea6e6b6c00324281204439
+oid sha256:61296ef3abdaf20c3b3026b34347ec0e6031a2bd0ff0e6dbef79bcd3d5ec458e
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537bc2d1bbcd4c3dbc85b5398935c759488f1f94d15718533f482e0754ba7a47
+oid sha256:917b4f9f47ec17a9437bfeb1cd7168cae9f6e91f5c365a8cddc94cd551b235c4
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db4090529d4135db703428fd5d184e762992f7b5cc78772988d1fb1c76fb83c
+oid sha256:841ff7483af4dea0e042045ede94c69b12193ccb48c09783725211409c900279
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e4057f36069d27dc95b7bc5bc3711e846f4900ff0fdc62b6ca072336f562a3
+oid sha256:4731002895dbb11ec91ffad1da0438c29128b79f50ca3a29b1c7b62c41a21da5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9054032564163208,
-  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-3084",
-  "epoch": 12.0,
+  "best_metric": 0.8854942917823792,
+  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-3341",
+  "epoch": 13.0,
   "eval_steps": 500,
-  "global_step": 3084,
+  "global_step": 3341,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,21 @@
       "eval_samples_per_second": 46.529,
       "eval_steps_per_second": 5.816,
       "step": 3084
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.4569827914237976,
+      "learning_rate": 7.824869791666667e-05,
+      "loss": 0.6726,
+      "step": 3341
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.8854942917823792,
+      "eval_runtime": 9.2942,
+      "eval_samples_per_second": 46.481,
+      "eval_steps_per_second": 5.81,
+      "step": 3341
     }
   ],
   "logging_steps": 500,
@@ -215,7 +230,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.4319439391922586e+17,
+  "total_flos": 4.8012726007916134e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null