Training in progress, step 4100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60abf88d896a194144af4d46953b60449e1221e1a95206d3184cc6888468f1b3
+oid sha256:58904a09d2c64b3af1fe77f00887cba4248f9483bd0ac2677c899654f1df66ed
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c31c122da48d6c9c0f2cdde3c7ef9521f0fd07780cbea9911eef7d5f74b3986
+oid sha256:d399b620d3b044063e90c4a82c58a56992e901eda2495728359da6520d58da88
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:433c43bb530b3efe8cd31ff9a32e89904e5dd3b0867a45122f34dbefd5725c76
+oid sha256:01228c358c1c5bd7e8d1e30fd7170ee7e7e01eaa5037c80171296afcca88fdbd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:964c69f61d0bbf0c796f0c2c9c9e1115ff56f13e1e7564a1b7a147cbb95abc2a
+oid sha256:dd593900009094dac4848a91bffea810cd27abb68e41341848d2730ca4540832
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1086384f9480def9ef326fcb17e1858cd985a99bbe88fa0719775b0cfbe77694
+oid sha256:e4e118c022d36fb38d58d0d7f0e3edb67b05d2a137df1ba7684c820d27509268
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35ff45b850b10b88d179a4b292143f4790bf179db89196535716df70aaf3df49
+oid sha256:c0c260699388e534a54ab049ec860d4b3bec4fc81bbf3db000ead4ea6f2487ca
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c21aa8c015b0555648fb033821c3da85b80cf68da16ae0f0aa43c78eed3bb59a
+oid sha256:09ac653d13867a7357fb216c15368c33da04027e0687353248f2f6a7723c2089
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7911626696586609,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3900",
-  "epoch": 5.35475234270415,
+  "best_metric": 0.7832607626914978,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4100",
+  "epoch": 5.4886211512717535,
   "eval_steps": 100,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -607,6 +607,21 @@
       "eval_samples_per_second": 893.27,
       "eval_steps_per_second": 3.609,
       "step": 4000
+    },
+    {
+      "epoch": 5.4886211512717535,
+      "grad_norm": 0.22185169160366058,
+      "learning_rate": 0.00045113788487282465,
+      "loss": 0.7461,
+      "step": 4100
+    },
+    {
+      "epoch": 5.4886211512717535,
+      "eval_loss": 0.7832607626914978,
+      "eval_runtime": 6.3959,
+      "eval_samples_per_second": 889.94,
+      "eval_steps_per_second": 3.596,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
@@ -621,7 +636,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -635,7 +650,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4524908306432e+17,
+  "total_flos": 1.48880310140928e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null