Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17354674ebfd7ee39e27d2d7c18efe07ba47500bf6960899f0eafdf72eead626
+oid sha256:cc8084e5d2f40c117fb67d150045799cf2c3cae6229373318b8bd37a0a605209
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ffd1ca3853498761f71027ee26ab56f29b18b7339583b6e4060a60d4b7e6d35
+oid sha256:a4575ef57c4ebf8ade03a543a393b32ae16e5578f529ef3653494f07df3f0f2d
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88a294175177dc754ff5113f4db5f5889ecf637e68dfb3e98c14246dd8d3714
+oid sha256:4f21d552e0b8edeac4b814e68abd63ad5a2fa0f0f0b7c2bf9dd3d572dde4cd39
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70db09ddd19e86007f322d281cc5c5f94909d942e37598ec3ceaa08be20aecba
+oid sha256:2b4f9a397f8fb58627464d50119035e3cc721b6c9f0cc18f4836a495d9182e5f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:598c58dd54a328d92dfc9ab91d559118e55f09ef3e6d1a542d0d2ba34a4f7769
+oid sha256:736c0a3c5e9cad8a63099122bc81fcfe6c1a1da1f52783fd5ab9a0a79f0525e7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1529a258db9857087589ba7d21800b6cb787f5ab31dae6d6c97ea8d5a4171643
+oid sha256:182d0fd1f95f38608a11f6b6579d63e24538540d9ce9b05d123e02020b4a25cf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ae85bf7a65e337693025f4ceb61bc3ab49ed353192027ce2cc225b05fa7ea5
+oid sha256:c6a126727af8bb09352afcee26a5ce13ba782b7b555b31ebe9b3deaff7994ff9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.78049236536026,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4200",
-  "epoch": 5.890227576974565,
+  "epoch": 6.024096385542169,
   "eval_steps": 100,
-  "global_step": 4400,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -667,6 +667,21 @@
       "eval_samples_per_second": 886.234,
       "eval_steps_per_second": 3.581,
       "step": 4400
+    },
+    {
+      "epoch": 6.024096385542169,
+      "grad_norm": 0.19529978930950165,
+      "learning_rate": 0.00039759036144578315,
+      "loss": 0.7329,
+      "step": 4500
+    },
+    {
+      "epoch": 6.024096385542169,
+      "eval_loss": 0.7827839851379395,
+      "eval_runtime": 6.3652,
+      "eval_samples_per_second": 894.234,
+      "eval_steps_per_second": 3.613,
+      "step": 4500
     }
   ],
   "logging_steps": 100,
@@ -681,7 +696,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -695,7 +710,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.59773991370752e+17,
+  "total_flos": 1.6340521844736e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null