Training in progress, step 5700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385e7d4ca672a7f7d09dc708e15e8eed0bf47ee9d8e72a8351fd66832bc142c5
+oid sha256:b963713c26e6a540837d4509d70d66f81e9e24308ec16d71b5d6662c7fd051d2
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b08cd290e6d6011c076277ae65bac68b9ef10b10317411792a9e4a809daa235f
+oid sha256:6595bd2248d4977ded600f62f6d7d6763fcba678d81254c117049811d1bca329
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818ecebd78fc073f436e178a1e926759c63b5f6f336cfeeb849a5306f3a9c3b0
+oid sha256:2b683fe93e06659e14c07a27acf9c77daa9ccce6805dc6d4934912532d8ca893
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03dfff0082388c7470059b187e898743736b13cb855ad34c8a10166c9d39bd7
+oid sha256:5b650c99e52f3a7d345f923602342fc636939e6770108043213e468229236c75
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4898a07531975dfeaa7813cc9aae9a48afa5ce9c9840de7c5e61c67eebf51247
+oid sha256:8c506d6c56df8eae6736b3c371165ebaccb53c63ee03a6afd543d841179e8486
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ce73d047925e1d348166841f032e966d1946f5dae4a6562144a3f84977a883
+oid sha256:ad36219e25c788c02e9e91298b0c2723c0887b37c75e14504ad38b22827719b0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1300660f204fef850ce4b9a6bbf864be491ac15c92d8165d61ea8c87a21648e0
+oid sha256:acda5f631277da28f3059fbed5212e54672b69d0acc256aa668e57f8df64b8d5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7650670409202576,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5400",
-  "epoch": 7.49665327978581,
+  "best_metric": 0.7648805975914001,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5700",
+  "epoch": 7.6305220883534135,
   "eval_steps": 100,
-  "global_step": 5600,
+  "global_step": 5700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -847,6 +847,21 @@
       "eval_samples_per_second": 892.903,
       "eval_steps_per_second": 3.608,
       "step": 5600
+    },
+    {
+      "epoch": 7.6305220883534135,
+      "grad_norm": 0.2055513709783554,
+      "learning_rate": 0.00023694779116465866,
+      "loss": 0.69,
+      "step": 5700
+    },
+    {
+      "epoch": 7.6305220883534135,
+      "eval_loss": 0.7648805975914001,
+      "eval_runtime": 6.3649,
+      "eval_samples_per_second": 894.277,
+      "eval_steps_per_second": 3.614,
+      "step": 5700
     }
   ],
   "logging_steps": 100,
@@ -861,7 +876,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -875,7 +890,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.03348716290048e+17,
+  "total_flos": 2.06979943366656e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null