Training in progress, step 3200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de28cb71dde45a81a54b3d1a9f98383d32681c7bf4a39d7b2428e9f5088fc3db
+oid sha256:4bc348b2f67ae50ac338e43ec78d914361843cbf1e3b704f81a788fbe94e835a
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020cada3aefe0f5ccb9b9447412182f9d5e599454f2c435c87fa80e7951951f1
+oid sha256:67032d3cbdea034fb916679f8d1d0bd1f24d9c39f3b6c36ff3c41d6a02107d1a
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322bada2f10d53fad14797dc434e75b724f0fe20c8e233700961e2da700249cf
+oid sha256:db91dd5e9083ef8e2bd49e1ee4ec3ac01f536d0772b293168dd335f34eb14ebe
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c133ae85aa212487f321d21dc8fe7464e4eae3cf31ce65958f7e8ef1225ee086
+oid sha256:dabdcb1d64ee62b3d44e9be0fda637a6eeefd3ba1adf1f4af2033d80e8af9a96
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a95978c9b046f47f13ca5883e064bc69b533b0da0b7011a42cab1a820940a8
+oid sha256:ddc87dd35064d2bd252c124860330c1c252335e10cb120fb9c4bb983480c26ac
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d2fe243abfa65a9c2d195676bf6b1da269aaa99b3ee303ba35d68c65518c46
+oid sha256:83866576b1071745a157c9879af6dffd8ac9b144d23bab164f4910105ec261e2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6503614989aa6b5b6c10f43b08431f913566b72043e0d1c0da3f3b5fcba779d3
+oid sha256:675ec9db3b9601b5c3a7ab2fca2c541e6b66bed8f3f8436e760187306c91cbc1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8133747577667236,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3100",
-  "epoch": 4.149933065595716,
+  "best_metric": 0.805473268032074,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3200",
+  "epoch": 4.28380187416332,
   "eval_steps": 100,
-  "global_step": 3100,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -472,6 +472,21 @@
       "eval_samples_per_second": 895.607,
       "eval_steps_per_second": 3.619,
       "step": 3100
+    },
+    {
+      "epoch": 4.28380187416332,
+      "grad_norm": 0.19236040115356445,
+      "learning_rate": 0.000571619812583668,
+      "loss": 0.7805,
+      "step": 3200
+    },
+    {
+      "epoch": 4.28380187416332,
+      "eval_loss": 0.805473268032074,
+      "eval_runtime": 6.4107,
+      "eval_samples_per_second": 887.894,
+      "eval_steps_per_second": 3.588,
+      "step": 3200
     }
   ],
   "logging_steps": 100,
@@ -500,7 +515,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.12568039374848e+17,
+  "total_flos": 1.16199266451456e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null