Training in progress, step 5600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea40139134d514acc1dc8a61268eace84f2776d3576257935a4fff6313d06774
+oid sha256:385e7d4ca672a7f7d09dc708e15e8eed0bf47ee9d8e72a8351fd66832bc142c5
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98506a499e60fd562c2b1007eefb7ab4725a7fda6e3484d9f831ffde04be7fc6
+oid sha256:b08cd290e6d6011c076277ae65bac68b9ef10b10317411792a9e4a809daa235f
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86f58829937a8acffca5e531d676885e50856ce418bf57f05c225b8e15b57fa
+oid sha256:818ecebd78fc073f436e178a1e926759c63b5f6f336cfeeb849a5306f3a9c3b0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f0d923b20ad4f5784d29616e7b951d8afd156607ca9226a3c91646ee220dcd
+oid sha256:f03dfff0082388c7470059b187e898743736b13cb855ad34c8a10166c9d39bd7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61c057c39bfc1468df94484bb9e101a8ba79e3653110549b9d464e53d5c5df3f
+oid sha256:4898a07531975dfeaa7813cc9aae9a48afa5ce9c9840de7c5e61c67eebf51247
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a38d9269b34da0fc830cc909b5ef8244d15504b6c9f4b61d0188676023df1d5
+oid sha256:90ce73d047925e1d348166841f032e966d1946f5dae4a6562144a3f84977a883
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc2ca0be91b990ef7bf75634166e7d3683a02c219d760d1d1277edde7a90e21c
+oid sha256:1300660f204fef850ce4b9a6bbf864be491ac15c92d8165d61ea8c87a21648e0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7650670409202576,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5400",
-  "epoch": 7.362784471218206,
+  "epoch": 7.49665327978581,
   "eval_steps": 100,
-  "global_step": 5500,
+  "global_step": 5600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -832,6 +832,21 @@
       "eval_samples_per_second": 892.334,
       "eval_steps_per_second": 3.606,
       "step": 5500
+    },
+    {
+      "epoch": 7.49665327978581,
+      "grad_norm": 0.22708941996097565,
+      "learning_rate": 0.00025033467202141904,
+      "loss": 0.6978,
+      "step": 5600
+    },
+    {
+      "epoch": 7.49665327978581,
+      "eval_loss": 0.7693562507629395,
+      "eval_runtime": 6.3747,
+      "eval_samples_per_second": 892.903,
+      "eval_steps_per_second": 3.608,
+      "step": 5600
     }
   ],
   "logging_steps": 100,
@@ -846,7 +861,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -860,7 +875,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9971748921344e+17,
+  "total_flos": 2.03348716290048e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null