Training in progress, step 4600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8084e5d2f40c117fb67d150045799cf2c3cae6229373318b8bd37a0a605209
+oid sha256:d4fdcfcdbc428ac62e3be4844df2a7454e840e8969a5d0c963a4d867d92764b4
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4575ef57c4ebf8ade03a543a393b32ae16e5578f529ef3653494f07df3f0f2d
+oid sha256:368b55a584bc772d0b6375dbcd91c7f46be779bdc0ef7190ada74b670b7c8a1b
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f21d552e0b8edeac4b814e68abd63ad5a2fa0f0f0b7c2bf9dd3d572dde4cd39
+oid sha256:2a11bb7b12b9642bd5d82055be71dcb8d8482abac72121424fe481d88f5de75b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4f9a397f8fb58627464d50119035e3cc721b6c9f0cc18f4836a495d9182e5f
+oid sha256:1818895e958d1cb907d3d67eeeaacce674781a97f1e95a9febb4e6ac8d60460f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736c0a3c5e9cad8a63099122bc81fcfe6c1a1da1f52783fd5ab9a0a79f0525e7
+oid sha256:51a4fe1ceeb1cb8cee5e1e7b373586181b6fea32cd158c5e5eaeeed87798c2ea
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:182d0fd1f95f38608a11f6b6579d63e24538540d9ce9b05d123e02020b4a25cf
+oid sha256:45ace3b97e4bece8ab00e978bc4f2ddd7d0408f2682a1d707793492ed9cc9aa3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a126727af8bb09352afcee26a5ce13ba782b7b555b31ebe9b3deaff7994ff9
+oid sha256:b5dc6da207765f4ba830c89b2a2c26098140ff38d2eed9174783bad0060f41de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.78049236536026,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4200",
-  "epoch": 6.024096385542169,
+  "best_metric": 0.7793735861778259,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4600",
+  "epoch": 6.157965194109773,
   "eval_steps": 100,
-  "global_step": 4500,
+  "global_step": 4600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -682,6 +682,21 @@
       "eval_samples_per_second": 894.234,
       "eval_steps_per_second": 3.613,
       "step": 4500
+    },
+    {
+      "epoch": 6.157965194109773,
+      "grad_norm": 0.18886443972587585,
+      "learning_rate": 0.0003842034805890228,
+      "loss": 0.7246,
+      "step": 4600
+    },
+    {
+      "epoch": 6.157965194109773,
+      "eval_loss": 0.7793735861778259,
+      "eval_runtime": 6.3661,
+      "eval_samples_per_second": 894.112,
+      "eval_steps_per_second": 3.613,
+      "step": 4600
     }
   ],
   "logging_steps": 100,
@@ -696,7 +711,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -710,7 +725,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6340521844736e+17,
+  "total_flos": 1.67036445523968e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null