Training in progress, step 9400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f3a1db5589596622438f3305091bec4d8eac0af6ce2a5fb67fdb2fabd6a46c
+oid sha256:182ee968b6fdeec8216ae2242608aac4cf00a82309a22f2bc546f245f6a30f5b
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d2b73126a971289ab203697cf1e1236e8169aa0b895581f652f1cc563a281b4
+oid sha256:dfc3984044cbf3ce86e00b28e3e8d7a9ea91edc27a0b44779f188f12efd55185
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda55b185dc98f3bbacd230aaacff604bd97a164ddf9fc1b48c814e202c2b868
+oid sha256:56f87b775049fb0adab4e0d540aff9b9f075c23a8d207a780cdfad0536093ab3
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7ad8d31b03afdc3955f524b574e208e67f3c465ce1d021ebb4d8b9cc6f6fd1a
+oid sha256:a16798b06a013ad4b7ec3ca11219408d900e5c425fe7c3d917c437397043544f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0438764095306396,
   "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-8900",
-  "epoch": 2.699564586357039,
+  "epoch": 2.7285921625544267,
   "eval_steps": 100,
-  "global_step": 9300,
+  "global_step": 9400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1402,6 +1402,21 @@
       "eval_samples_per_second": 214.017,
       "eval_steps_per_second": 3.344,
       "step": 9300
+    },
+    {
+      "epoch": 2.7285921625544267,
+      "grad_norm": 1.2580476999282837,
+      "learning_rate": 7.271407837445574e-05,
+      "loss": 1.9873,
+      "step": 9400
+    },
+    {
+      "epoch": 2.7285921625544267,
+      "eval_loss": 1.0441796779632568,
+      "eval_runtime": 213.1744,
+      "eval_samples_per_second": 213.436,
+      "eval_steps_per_second": 3.335,
+      "step": 9400
     }
   ],
   "logging_steps": 100,
@@ -1416,7 +1431,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 4
+        "early_stopping_patience_counter": 5
       }
     },
     "TrainerControl": {
@@ -1425,12 +1440,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.30337028749394e+16,
+  "total_flos": 9.403409048272896e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null