Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9613c2e7f642985b568f77e8cab863a85be2474126c8195c9c931e0a44fe24e6
+oid sha256:ea40139134d514acc1dc8a61268eace84f2776d3576257935a4fff6313d06774
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b58adb62c9b91cd654d7e0f3cf020d97c1b02664dff12c7d3420ddcf2a641e2
+oid sha256:98506a499e60fd562c2b1007eefb7ab4725a7fda6e3484d9f831ffde04be7fc6
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc0be6ea566a92a47cf4d56217281e386f843e06522023dd8197a948ed9e286
+oid sha256:e86f58829937a8acffca5e531d676885e50856ce418bf57f05c225b8e15b57fa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f54ddca02d239c58855a16c5bc980045aec7545ffdf7cf801ec77e8b86fd1a4
+oid sha256:a2f0d923b20ad4f5784d29616e7b951d8afd156607ca9226a3c91646ee220dcd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b6fea2a10a6e28f7eccb9d6ab3f26a882f21d1933fa3c3091a73a255b353d3
+oid sha256:61c057c39bfc1468df94484bb9e101a8ba79e3653110549b9d464e53d5c5df3f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f480b2a29f7d632bb15594aa0e5d60f53946cf53a367d7d49bd169e384c52566
+oid sha256:2a38d9269b34da0fc830cc909b5ef8244d15504b6c9f4b61d0188676023df1d5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c25a970a50d36e750b7558449ba1adca04e287c48a7a47e03d446fb3d06de1dd
+oid sha256:cc2ca0be91b990ef7bf75634166e7d3683a02c219d760d1d1277edde7a90e21c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7650670409202576,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5400",
-  "epoch": 7.228915662650603,
+  "epoch": 7.362784471218206,
   "eval_steps": 100,
-  "global_step": 5400,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -817,6 +817,21 @@
       "eval_samples_per_second": 887.065,
       "eval_steps_per_second": 3.584,
       "step": 5400
+    },
+    {
+      "epoch": 7.362784471218206,
+      "grad_norm": 0.19670027494430542,
+      "learning_rate": 0.0002637215528781794,
+      "loss": 0.6967,
+      "step": 5500
+    },
+    {
+      "epoch": 7.362784471218206,
+      "eval_loss": 0.7688850164413452,
+      "eval_runtime": 6.3788,
+      "eval_samples_per_second": 892.334,
+      "eval_steps_per_second": 3.606,
+      "step": 5500
     }
   ],
   "logging_steps": 100,
@@ -831,7 +846,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -845,7 +860,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.96086262136832e+17,
+  "total_flos": 1.9971748921344e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null