Training in progress, step 6700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:513d6e3a9274aa9d665a27ec2cd5eea1f9eeb294b2aa4534afbfbbe9f202c174
+oid sha256:1c6762279db85ead5cf0c6da767ffe64e16e81e816f58491fe7c777dc1ead33a
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4782a026b4ebee629a3e481661e7d0ac84988b54142604726015f5e3dc46e3b1
+oid sha256:7bc752128555513abefc446b72ad6b0aa9469c905bbbb7c2e3136df583a575c8
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c36b177c7367f01ea222a33c719df6f1ce597a7eb2acf9b169079f72996b1fc
+oid sha256:83515a963ffe748284cb7536add2fbd90c539360e91ceb8e556462b00a26d582
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906102055779a426735fbb73ff7cf27eabe2a903bd39663352e83c1ee36fb3ef
+oid sha256:b8e9a3f506b160e41a560ad4a0f4661f2ff551ff0d5f3778c6e9d28bb4926fa5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07aef77f9f4e06e24a9b032a1a4b14d34e4981bdde66403a4a3d727b8a90c60e
+oid sha256:4c89a9a5568cb9122ac949790318556e01f125989f5e76cdce9decb537524c2b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edcca2cde2d5aed24e699c740a68be927d4fe8cde5ac4727d32a3e7cfe8ea9d6
+oid sha256:982216749c9008cf7c1aab3fe7f415f72659f731379938ec1b128fa2576aa356
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec5a5fc9c8cd09094621c06e1e96f6821f77d645fe71ee03811a04ba6b5e2cd6
+oid sha256:68127705cb92049d865675eaafd5923a6658b3e538c69053f2fc03f98477aef1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7487396597862244,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6500",
-  "epoch": 8.835341365461847,
+  "epoch": 8.96921017402945,
   "eval_steps": 100,
-  "global_step": 6600,
+  "global_step": 6700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -997,6 +997,21 @@
       "eval_samples_per_second": 894.526,
       "eval_steps_per_second": 3.615,
       "step": 6600
+    },
+    {
+      "epoch": 8.96921017402945,
+      "grad_norm": 0.20792551338672638,
+      "learning_rate": 0.00010307898259705489,
+      "loss": 0.6629,
+      "step": 6700
+    },
+    {
+      "epoch": 8.96921017402945,
+      "eval_loss": 0.7500482201576233,
+      "eval_runtime": 6.3736,
+      "eval_samples_per_second": 893.061,
+      "eval_steps_per_second": 3.609,
+      "step": 6700
     }
   ],
   "logging_steps": 100,
@@ -1011,7 +1026,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -1025,7 +1040,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.39660987056128e+17,
+  "total_flos": 2.43292214132736e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null