Training in progress, step 6600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:607db0aaa8aec5e0c77d2ae44dc9557d7f988e24abbaafafb4f1cac3b2f705c1
+oid sha256:513d6e3a9274aa9d665a27ec2cd5eea1f9eeb294b2aa4534afbfbbe9f202c174
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec9a254aabc26c9ecaf2cca002ad97ad758900e1f80c8fe6c553cb0486cd0cbe
+oid sha256:4782a026b4ebee629a3e481661e7d0ac84988b54142604726015f5e3dc46e3b1
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f76838f8e3a157a00d912b4db2e3d23619e7a0258f470c79764f0201444368
+oid sha256:0c36b177c7367f01ea222a33c719df6f1ce597a7eb2acf9b169079f72996b1fc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:531bda37c4200f52a8cc18f945f8530ba4b8f333e7e166099701e69c6e3dab0f
+oid sha256:906102055779a426735fbb73ff7cf27eabe2a903bd39663352e83c1ee36fb3ef
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e10dda7822ada68460df36e65fcda5e475c2ef0ad7968e70f7057f87ffe1360
+oid sha256:07aef77f9f4e06e24a9b032a1a4b14d34e4981bdde66403a4a3d727b8a90c60e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870b1b4c249a2b7e5c44fcd3356decbda105298b8a1839f4d0cfae2d944ee375
+oid sha256:edcca2cde2d5aed24e699c740a68be927d4fe8cde5ac4727d32a3e7cfe8ea9d6
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d317150b0d3412b691ca8098a37f80eb1b7190219c8c4e550a8598f46571a60c
+oid sha256:ec5a5fc9c8cd09094621c06e1e96f6821f77d645fe71ee03811a04ba6b5e2cd6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7487396597862244,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6500",
-  "epoch": 8.701472556894243,
+  "epoch": 8.835341365461847,
   "eval_steps": 100,
-  "global_step": 6500,
+  "global_step": 6600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -982,6 +982,21 @@
       "eval_samples_per_second": 891.523,
       "eval_steps_per_second": 3.602,
       "step": 6500
+    },
+    {
+      "epoch": 8.835341365461847,
+      "grad_norm": 0.20785841345787048,
+      "learning_rate": 0.00011646586345381527,
+      "loss": 0.6697,
+      "step": 6600
+    },
+    {
+      "epoch": 8.835341365461847,
+      "eval_loss": 0.755291223526001,
+      "eval_runtime": 6.3631,
+      "eval_samples_per_second": 894.526,
+      "eval_steps_per_second": 3.615,
+      "step": 6600
     }
   ],
   "logging_steps": 100,
@@ -996,7 +1011,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -1010,7 +1025,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3602975997952e+17,
+  "total_flos": 2.39660987056128e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null