Training in progress, step 3300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc348b2f67ae50ac338e43ec78d914361843cbf1e3b704f81a788fbe94e835a
+oid sha256:a6fcc6b68ed6c8fcec7935714d880896ac1f50e26c53db7f0662d98ab1a15414
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67032d3cbdea034fb916679f8d1d0bd1f24d9c39f3b6c36ff3c41d6a02107d1a
+oid sha256:6146b500d61dcfd9fb8f6f470d354ea82c8673e39cf6c885f67eebe284bdc832
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db91dd5e9083ef8e2bd49e1ee4ec3ac01f536d0772b293168dd335f34eb14ebe
+oid sha256:c9c9bcd7d5c7db6d39407cf0f484e960bc685e2e96251815b42ccafca7685683
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dabdcb1d64ee62b3d44e9be0fda637a6eeefd3ba1adf1f4af2033d80e8af9a96
+oid sha256:be59fda547433051d1e3429d31d948c03fb4fc94f4aa092a8ba1a6c18f620262
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc87dd35064d2bd252c124860330c1c252335e10cb120fb9c4bb983480c26ac
+oid sha256:e3d90284b24f335c55911eb7de6e1b04f64d7916ffd27324cbd36e8c39ff5f39
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83866576b1071745a157c9879af6dffd8ac9b144d23bab164f4910105ec261e2
+oid sha256:793dfcb846de77f43d414bbe711491e2af32eca9823a49b468c31c54598cb459
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675ec9db3b9601b5c3a7ab2fca2c541e6b66bed8f3f8436e760187306c91cbc1
+oid sha256:c7623b48a4372484f57d0d82402f5c3c0b0e58b745867e2e8f7526e0f0890c47
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.805473268032074,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3200",
-  "epoch": 4.28380187416332,
+  "epoch": 4.417670682730924,
   "eval_steps": 100,
-  "global_step": 3200,
+  "global_step": 3300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,6 +487,21 @@
       "eval_samples_per_second": 887.894,
       "eval_steps_per_second": 3.588,
       "step": 3200
+    },
+    {
+      "epoch": 4.417670682730924,
+      "grad_norm": 0.20242071151733398,
+      "learning_rate": 0.0005582329317269076,
+      "loss": 0.775,
+      "step": 3300
+    },
+    {
+      "epoch": 4.417670682730924,
+      "eval_loss": 0.8090841174125671,
+      "eval_runtime": 6.3804,
+      "eval_samples_per_second": 892.112,
+      "eval_steps_per_second": 3.605,
+      "step": 3300
     }
   ],
   "logging_steps": 100,
@@ -501,7 +516,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -515,7 +530,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.16199266451456e+17,
+  "total_flos": 1.19830493528064e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null