Training in progress, step 6800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6762279db85ead5cf0c6da767ffe64e16e81e816f58491fe7c777dc1ead33a
+oid sha256:e05b232be1d19b91bb70b3a606a05d5795d8d41e89f0c87a53cc256a7214a179
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc752128555513abefc446b72ad6b0aa9469c905bbbb7c2e3136df583a575c8
+oid sha256:68649c807bddeb5467b7a1df64a47ae962680a20f380aa278b302de7ab04e60a
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83515a963ffe748284cb7536add2fbd90c539360e91ceb8e556462b00a26d582
+oid sha256:d953c7618f3e712d410b5cb05c321f0bf9de8c3fb1d37c2044c067ce184beec4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e9a3f506b160e41a560ad4a0f4661f2ff551ff0d5f3778c6e9d28bb4926fa5
+oid sha256:c07b26723a4e3cf85e98545bf0b9bb5063492d19219987cfb46330b8d5860042
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c89a9a5568cb9122ac949790318556e01f125989f5e76cdce9decb537524c2b
+oid sha256:0b829a9470d15d55e871b4c3cf43a7d43be6cbfeae1631930a480d4470a8c8a7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:982216749c9008cf7c1aab3fe7f415f72659f731379938ec1b128fa2576aa356
+oid sha256:276789ea518bb4b590d51ebdb65398f085bef04975b01d315246991bc35103c3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68127705cb92049d865675eaafd5923a6658b3e538c69053f2fc03f98477aef1
+oid sha256:b8989f2ab2a5ce31c6a7733c32b9323b3737aaff053ae8efe7b9a1117361e4d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7487396597862244,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6500",
-  "epoch": 8.96921017402945,
+  "epoch": 9.103078982597054,
   "eval_steps": 100,
-  "global_step": 6700,
+  "global_step": 6800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1012,6 +1012,21 @@
       "eval_samples_per_second": 893.061,
       "eval_steps_per_second": 3.609,
       "step": 6700
+    },
+    {
+      "epoch": 9.103078982597054,
+      "grad_norm": 0.2049485594034195,
+      "learning_rate": 8.969210174029451e-05,
+      "loss": 0.6629,
+      "step": 6800
+    },
+    {
+      "epoch": 9.103078982597054,
+      "eval_loss": 0.7550941705703735,
+      "eval_runtime": 6.3709,
+      "eval_samples_per_second": 893.433,
+      "eval_steps_per_second": 3.61,
+      "step": 6800
     }
   ],
   "logging_steps": 100,
@@ -1026,7 +1041,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1040,7 +1055,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.43292214132736e+17,
+  "total_flos": 2.46923441209344e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null