Training in progress, step 6900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05b232be1d19b91bb70b3a606a05d5795d8d41e89f0c87a53cc256a7214a179
+oid sha256:15b4a4c2155d4aa5d9ba3242e977b2dba6c5db7e9966a368227fd5382033a9d2
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68649c807bddeb5467b7a1df64a47ae962680a20f380aa278b302de7ab04e60a
+oid sha256:99733c997fc7435948570b4de5efe8122bb8d127b7a18fef6a258586e08c0aef
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d953c7618f3e712d410b5cb05c321f0bf9de8c3fb1d37c2044c067ce184beec4
+oid sha256:39f04f6fd7c65d03db1dadb8f38687e3b2d58ce7526cb15c9a8c8b748a722949
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c07b26723a4e3cf85e98545bf0b9bb5063492d19219987cfb46330b8d5860042
+oid sha256:0edea2ed5e3ece25dc521aa3671e1ca478b0465607eea7f15adda71ddd55af89
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b829a9470d15d55e871b4c3cf43a7d43be6cbfeae1631930a480d4470a8c8a7
+oid sha256:8b9057f14bf3373d9e1f241ad9da2d6855725376530c8d981ecc5264012c16e5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276789ea518bb4b590d51ebdb65398f085bef04975b01d315246991bc35103c3
+oid sha256:60c89da50d878de65c791945958d2ad63fbb056fd379f71d2ad048791404f48f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8989f2ab2a5ce31c6a7733c32b9323b3737aaff053ae8efe7b9a1117361e4d7
+oid sha256:fefc6f5e9bfe1c9e70e43ba61c03a371abcf2583878488a0cf8b57511098aefb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7487396597862244,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6500",
-  "epoch": 9.103078982597054,
+  "epoch": 9.236947791164658,
   "eval_steps": 100,
-  "global_step": 6800,
+  "global_step": 6900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1027,6 +1027,21 @@
       "eval_samples_per_second": 893.433,
       "eval_steps_per_second": 3.61,
       "step": 6800
+    },
+    {
+      "epoch": 9.236947791164658,
+      "grad_norm": 0.21241113543510437,
+      "learning_rate": 7.630522088353414e-05,
+      "loss": 0.6629,
+      "step": 6900
+    },
+    {
+      "epoch": 9.236947791164658,
+      "eval_loss": 0.7512398958206177,
+      "eval_runtime": 6.3681,
+      "eval_samples_per_second": 893.836,
+      "eval_steps_per_second": 3.612,
+      "step": 6900
     }
   ],
   "logging_steps": 100,
@@ -1041,7 +1056,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 4
       }
     },
     "TrainerControl": {
@@ -1055,7 +1070,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.46923441209344e+17,
+  "total_flos": 2.50554668285952e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null