Training in progress, step 2600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf111968ecfd2182c79cddf389aace292b624f4a12fdb0bf19c9d0af2659062c
+oid sha256:16838d94768edad04519e160a50d26b25a308f1bef6f73c75c73a4e953a33dad
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3804765c23fc480a9bc5293bd84544675f9d46fa8eb789519d64c12c10c72487
+oid sha256:cf04c22e7bd4aeb40474b8c876e857ed0703db651f039235905d29ac261cff39
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552f53b4bfd8ff78acb22151277476df50231d55d234625cfa40edaa0bf9d3a3
+oid sha256:c9fd353e5dfefc6101a83a5d98caf9c9a5705a14c0ab8ade5223b2ce5b3f0460
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f943f1eeef7f7e5f3f5e29d148df316e616bd2fd831bac81ced32f2548fecd
+oid sha256:223fcd89486c49e6df65821113f3a4b9aa86800e9ee923c785f21124af5e08fc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf49525bf634d756188799e8cd0d7b30d96b1892be840b29e954ce7ba14f5594
+oid sha256:fa85081c50e299ccc1c9c3813903596abe8f8c8fba7b16270e601163512ed80a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d607d560bac1029ae756b5a3cdb456902c25b1aaa01de4add5870301e06f0d06
+oid sha256:ebbb62282efa748ff5d8a9552b46ba05c50b2d92255f80816616d6608479a3d2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6beb8fe2c3ec1351bc7066a891a1abcb74c93ada85504874b2e06ac13e8f908
+oid sha256:3649421385e1a24ace04961edc12c9bf862a555cae6bc8873a6c17202a59515f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8264986872673035,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2400",
-  "epoch": 3.3467202141900936,
+  "best_metric": 0.8202800750732422,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2600",
+  "epoch": 3.480589022757697,
   "eval_steps": 100,
-  "global_step": 2500,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -382,6 +382,21 @@
       "eval_samples_per_second": 890.924,
       "eval_steps_per_second": 3.6,
       "step": 2500
+    },
+    {
+      "epoch": 3.480589022757697,
+      "grad_norm": 0.1842898279428482,
+      "learning_rate": 0.0006519410977242302,
+      "loss": 0.8072,
+      "step": 2600
+    },
+    {
+      "epoch": 3.480589022757697,
+      "eval_loss": 0.8202800750732422,
+      "eval_runtime": 6.3504,
+      "eval_samples_per_second": 896.32,
+      "eval_steps_per_second": 3.622,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
@@ -396,7 +411,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -410,7 +425,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.07806769152e+16,
+  "total_flos": 9.4411903991808e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null