Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4792b6295769671ef028bc072477a4dc6b2cdad04d8241af13a27bd5bc283018
+oid sha256:a5e631321de4a7f0edb9e4df608fffc1169a28c054004bb84d9c90bde1efd3eb
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0809bfda509f79842fa22ff4a74001a45f4de3e95e2aa0f32fada66c76f6bf1
+oid sha256:5d6bfa10fd72fa4552abbd126a8f73bf03087ddbbf0f406afd69187f481374aa
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e29647aaac7584d5c979f85f161bf7892d8e311714c56e2e611ee2a08b9475e5
+oid sha256:bf48ab9fa8bab1e3ff4f0f626fd9093b03562bae08edaf3a3a13235fa6b1ce3b
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5603f8c0ec715faa1d0b7e7b75e57ca14609131762cc7b196cf6563d0272d241
+oid sha256:52f67e79141a1e8ab27edc1a44643202c30fbb22e5b9c3ef6241c285d6911e39
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0438764095306396,
   "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-8900",
-  "epoch": 2.583454281567489,
+  "epoch": 2.6124818577648767,
   "eval_steps": 100,
-  "global_step": 8900,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1342,6 +1342,21 @@
       "eval_samples_per_second": 213.365,
       "eval_steps_per_second": 3.334,
       "step": 8900
+    },
+    {
+      "epoch": 2.6124818577648767,
+      "grad_norm": 1.307707667350769,
+      "learning_rate": 7.387518142235124e-05,
+      "loss": 1.9753,
+      "step": 9000
+    },
+    {
+      "epoch": 2.6124818577648767,
+      "eval_loss": 1.0445740222930908,
+      "eval_runtime": 212.5813,
+      "eval_samples_per_second": 214.031,
+      "eval_steps_per_second": 3.345,
+      "step": 9000
     }
   ],
   "logging_steps": 100,
@@ -1356,7 +1371,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -1370,7 +1385,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.903215244378112e+16,
+  "total_flos": 9.003254005157069e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null