Training in progress, step 2300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b672b5cdfd1f8862685ea34563e2c8e28e69748fe9718cf421bba7dfab2006c
+oid sha256:69d727907d193aef09e2a9d80365acb6f2462a20c6a4bbe793bc592fe7653384
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260d8bec545542491a26819f31102a5e9700298d557614b9b96e6fe9e6ee6451
+oid sha256:14db266b84b7a4fd9c6961d6cbddc96684ca7a5facf6bbc70686999fceb9b40f
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3a8e3d7dc555cfd33954afbf3db56bb6f83c1bb4e5cfd281fce73c4efbf5429
+oid sha256:ee07e8dcd8ba9e44bfd4964110f49118b76a8cef649358084a25ac12aea38df8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef340a6411b8b518408fb09d160dd4f0e5ee5f7993bb698e2f1a2e34fceebc38
+oid sha256:bef8ba89520738b13bda5df191bb09dcdf29a49633395376036fac6c7c910b7e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed0f6b270edd75f8ad03a0a501c63fc180ed748c6bbf472a303f1bd0c278a32e
+oid sha256:982c6813cdea3b949eb3e7af3ec5f20a06ee4f7d374e292b05a8b646d098fd83
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40348d850ac58ccc5115d7000f52e5cadd7b36ee5e2c20f7f67b47d1868058ef
+oid sha256:ba15cb4748b341969934bf30614b73106ba62fd6173231a4135f3d41ad085f55
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0163aa20d0187419bf300d2a367c9e4f82a09b492cfb237f304e3a6bfac7210e
+oid sha256:f0c45ce9ebd2e6f751801c4dc4b8d6cab111bdc01864bb53ac8fcc86dd2f2927
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8368203639984131,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2100",
-  "epoch": 2.9451137884872827,
+  "best_metric": 0.8286001682281494,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2300",
+  "epoch": 3.0789825970548863,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -337,6 +337,21 @@
       "eval_samples_per_second": 886.529,
       "eval_steps_per_second": 3.582,
       "step": 2200
+    },
+    {
+      "epoch": 3.0789825970548863,
+      "grad_norm": 0.2126319259405136,
+      "learning_rate": 0.0006921017402945113,
+      "loss": 0.8298,
+      "step": 2300
+    },
+    {
+      "epoch": 3.0789825970548863,
+      "eval_loss": 0.8286001682281494,
+      "eval_runtime": 6.4466,
+      "eval_samples_per_second": 882.942,
+      "eval_steps_per_second": 3.568,
+      "step": 2300
     }
   ],
   "logging_steps": 100,
@@ -351,7 +366,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -365,7 +380,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.9886995685376e+16,
+  "total_flos": 8.3518222761984e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null