Training in progress, epoch 14, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61296ef3abdaf20c3b3026b34347ec0e6031a2bd0ff0e6dbef79bcd3d5ec458e
+oid sha256:ed725d9d2506469d1164aec4f81769d1c9e8856bbeb7c943c0a98de5d6737ec1
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917b4f9f47ec17a9437bfeb1cd7168cae9f6e91f5c365a8cddc94cd551b235c4
+oid sha256:b05270c73f97bd25b934d8b74c562ffeb6ce543f62195b399f5201e5d590088c
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:841ff7483af4dea0e042045ede94c69b12193ccb48c09783725211409c900279
+oid sha256:6799f5713e360b18bd49bdd40d277a79cff0753fb1327fffa08665ffe174400c
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4731002895dbb11ec91ffad1da0438c29128b79f50ca3a29b1c7b62c41a21da5
+oid sha256:cf4f8eb4eac6f82f900daa0f2c66883ed858058792a4319784f342865fc75551
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8854942917823792,
-  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-3341",
-  "epoch": 13.0,
+  "best_metric": 0.8803820013999939,
+  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-3598",
+  "epoch": 14.0,
   "eval_steps": 500,
-  "global_step": 3341,
+  "global_step": 3598,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -202,6 +202,21 @@
       "eval_samples_per_second": 46.481,
       "eval_steps_per_second": 5.81,
       "step": 3341
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.5499886274337769,
+      "learning_rate": 7.657552083333333e-05,
+      "loss": 0.6395,
+      "step": 3598
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.8803820013999939,
+      "eval_runtime": 9.2888,
+      "eval_samples_per_second": 46.508,
+      "eval_steps_per_second": 5.813,
+      "step": 3598
     }
   ],
   "logging_steps": 500,
@@ -230,7 +245,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.8012726007916134e+17,
+  "total_flos": 5.170601262390968e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null