Training in progress, step 5400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48512a617ecc29150b3fcffc3bac9271f2eda18eca4cee93e9e28f3c59f3c029
+oid sha256:9613c2e7f642985b568f77e8cab863a85be2474126c8195c9c931e0a44fe24e6
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743feb1efb1570c9ec8c4ef71f43c7975a5fe72147038b7cf83ee6fe0eedf3aa
+oid sha256:6b58adb62c9b91cd654d7e0f3cf020d97c1b02664dff12c7d3420ddcf2a641e2
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8226358c0f700bb53afaf3faa43d9a6777fe792182c7a0d8c41428742fabc93e
+oid sha256:ecc0be6ea566a92a47cf4d56217281e386f843e06522023dd8197a948ed9e286
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ea7dbc1c07cc0ee1e9a988b533591fbe9d67d89330e265a709f3e1f3bdef37
+oid sha256:6f54ddca02d239c58855a16c5bc980045aec7545ffdf7cf801ec77e8b86fd1a4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fd91a40094f0ed12960b9a22012adeee1744512dd947ed5b7be5481bdd5925
+oid sha256:40b6fea2a10a6e28f7eccb9d6ab3f26a882f21d1933fa3c3091a73a255b353d3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585c063c64e11f9c35800000b730bf431ff5b1b49d2de618e99ffd81b58444ba
+oid sha256:f480b2a29f7d632bb15594aa0e5d60f53946cf53a367d7d49bd169e384c52566
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e58b1bb199274c073865174a1d6bddf72f0586f5c109844e3442547260217dd
+oid sha256:c25a970a50d36e750b7558449ba1adca04e287c48a7a47e03d446fb3d06de1dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7706419825553894,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5100",
-  "epoch": 7.095046854082999,
+  "best_metric": 0.7650670409202576,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5400",
+  "epoch": 7.228915662650603,
   "eval_steps": 100,
-  "global_step": 5300,
+  "global_step": 5400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -802,6 +802,21 @@
       "eval_samples_per_second": 893.153,
       "eval_steps_per_second": 3.609,
       "step": 5300
+    },
+    {
+      "epoch": 7.228915662650603,
+      "grad_norm": 0.2070448100566864,
+      "learning_rate": 0.00027710843373493976,
+      "loss": 0.6983,
+      "step": 5400
+    },
+    {
+      "epoch": 7.228915662650603,
+      "eval_loss": 0.7650670409202576,
+      "eval_runtime": 6.4167,
+      "eval_samples_per_second": 887.065,
+      "eval_steps_per_second": 3.584,
+      "step": 5400
     }
   ],
   "logging_steps": 100,
@@ -816,7 +831,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -830,7 +845,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.92455035060224e+17,
+  "total_flos": 1.96086262136832e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null