Training in progress, step 3100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa4fca34cbed28dfbb1cd0b64ab6ad7ea8411ecd57025c2603e8e34d69f96efa
+oid sha256:de28cb71dde45a81a54b3d1a9f98383d32681c7bf4a39d7b2428e9f5088fc3db
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21fd822768be183f3f21935f34b833106ba986b0c6deb53a62db58fb4544ab88
+oid sha256:020cada3aefe0f5ccb9b9447412182f9d5e599454f2c435c87fa80e7951951f1
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c427cc96f82888b4f5f999f54fbddd6ffd6601cc97fca9c2d0bb619f41c0d43
+oid sha256:322bada2f10d53fad14797dc434e75b724f0fe20c8e233700961e2da700249cf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d629f47b012bd4716fbd06c1a801bd8338866570d3f145993b800ebbcd5f242a
+oid sha256:c133ae85aa212487f321d21dc8fe7464e4eae3cf31ce65958f7e8ef1225ee086
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda321a22829d039fcd566a3c7d2c1122d8fd1d3c4a3340add915e3e858c1b45
+oid sha256:15a95978c9b046f47f13ca5883e064bc69b533b0da0b7011a42cab1a820940a8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2170e2709f230c49ff410906179c868ec7a5748fcf6a0bab2da9ce8832e524f2
+oid sha256:44d2fe243abfa65a9c2d195676bf6b1da269aaa99b3ee303ba35d68c65518c46
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266007e2046e89dca879b11f93a11db868f0c26dc5a6e44ba8e9f335c12b6523
+oid sha256:6503614989aa6b5b6c10f43b08431f913566b72043e0d1c0da3f3b5fcba779d3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8169597387313843,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2900",
-  "epoch": 4.016064257028113,
+  "best_metric": 0.8133747577667236,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3100",
+  "epoch": 4.149933065595716,
   "eval_steps": 100,
-  "global_step": 3000,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -457,6 +457,21 @@
       "eval_samples_per_second": 893.337,
       "eval_steps_per_second": 3.61,
       "step": 3000
+    },
+    {
+      "epoch": 4.149933065595716,
+      "grad_norm": 0.19783490896224976,
+      "learning_rate": 0.0005850066934404283,
+      "loss": 0.7826,
+      "step": 3100
+    },
+    {
+      "epoch": 4.149933065595716,
+      "eval_loss": 0.8133747577667236,
+      "eval_runtime": 6.3555,
+      "eval_samples_per_second": 895.607,
+      "eval_steps_per_second": 3.619,
+      "step": 3100
     }
   ],
   "logging_steps": 100,
@@ -471,7 +486,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -485,7 +500,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0893681229824e+17,
+  "total_flos": 1.12568039374848e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null