Training in progress, step 4700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4fdcfcdbc428ac62e3be4844df2a7454e840e8969a5d0c963a4d867d92764b4
+oid sha256:0b2ebc191aabc6518793124df3ec298a1068dca6ea1077091f4ec338c4512e2e
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368b55a584bc772d0b6375dbcd91c7f46be779bdc0ef7190ada74b670b7c8a1b
+oid sha256:da785101c78f6dba8b1d769af93c9e7addd1451bd3280b193c78ec34b8a92a2e
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a11bb7b12b9642bd5d82055be71dcb8d8482abac72121424fe481d88f5de75b
+oid sha256:21f98b38a5644907d645ad97db8abc78adfefa25b7bb27d6365c84f993e3afd0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1818895e958d1cb907d3d67eeeaacce674781a97f1e95a9febb4e6ac8d60460f
+oid sha256:8d438bcc44b8d54150c5792a66e3e5020186af506dfd2594179ec54fbf9e4cae
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a4fe1ceeb1cb8cee5e1e7b373586181b6fea32cd158c5e5eaeeed87798c2ea
+oid sha256:bdcdbf45854e83758fb28548c63ecd326f239ee595c8bfeb7203ec3a5ea5ad7a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45ace3b97e4bece8ab00e978bc4f2ddd7d0408f2682a1d707793492ed9cc9aa3
+oid sha256:3bf80ca3ed0ae8728cae90df90e2694d6facafbe5f1f509a5b1356858eb2c480
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5dc6da207765f4ba830c89b2a2c26098140ff38d2eed9174783bad0060f41de
+oid sha256:85ab8ba4274200fbed9bf770f5d7a8007101aadb14e325d86f417f8df6b6001a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7793735861778259,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4600",
-  "epoch": 6.157965194109773,
+  "epoch": 6.291834002677376,
   "eval_steps": 100,
-  "global_step": 4600,
+  "global_step": 4700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -697,6 +697,21 @@
       "eval_samples_per_second": 894.112,
       "eval_steps_per_second": 3.613,
       "step": 4600
+    },
+    {
+      "epoch": 6.291834002677376,
+      "grad_norm": 0.20140951871871948,
+      "learning_rate": 0.0003708165997322624,
+      "loss": 0.7186,
+      "step": 4700
+    },
+    {
+      "epoch": 6.291834002677376,
+      "eval_loss": 0.7824135422706604,
+      "eval_runtime": 6.379,
+      "eval_samples_per_second": 892.303,
+      "eval_steps_per_second": 3.606,
+      "step": 4700
     }
   ],
   "logging_steps": 100,
@@ -711,7 +726,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -725,7 +740,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.67036445523968e+17,
+  "total_flos": 1.70667672600576e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null