Training in progress, step 9300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b773bdf4055e53552cee0ed25da5c686cd04dc17af6b5a2d0bf3dd951e16525
+oid sha256:d3f3a1db5589596622438f3305091bec4d8eac0af6ce2a5fb67fdb2fabd6a46c
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10372dacbd6eaf45478a0c95249dcd88ed2ce0ce6aa512de458d4897ecfc863
+oid sha256:4d2b73126a971289ab203697cf1e1236e8169aa0b895581f652f1cc563a281b4
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20e6dce8f2f1c5a17a180c274638622919bd91b1b4a11df9b9fbd8d8e95cbf84
+oid sha256:bda55b185dc98f3bbacd230aaacff604bd97a164ddf9fc1b48c814e202c2b868
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f59af528e00285e6f0500198bcd9b612dd10ddf7de75e7254a328683370acd
+oid sha256:b7ad8d31b03afdc3955f524b574e208e67f3c465ce1d021ebb4d8b9cc6f6fd1a
 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": 2.6705370101596517,
+  "epoch": 2.699564586357039,
   "eval_steps": 100,
-  "global_step": 9200,
+  "global_step": 9300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1387,6 +1387,21 @@
       "eval_samples_per_second": 213.273,
       "eval_steps_per_second": 3.333,
       "step": 9200
+    },
+    {
+      "epoch": 2.699564586357039,
+      "grad_norm": 1.317325472831726,
+      "learning_rate": 7.300435413642961e-05,
+      "loss": 1.9853,
+      "step": 9300
+    },
+    {
+      "epoch": 2.699564586357039,
+      "eval_loss": 1.04426109790802,
+      "eval_runtime": 212.5953,
+      "eval_samples_per_second": 214.017,
+      "eval_steps_per_second": 3.344,
+      "step": 9300
     }
   ],
   "logging_steps": 100,
@@ -1401,7 +1416,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 4
       }
     },
     "TrainerControl": {
@@ -1415,7 +1430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.203331526714982e+16,
+  "total_flos": 9.30337028749394e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null