Training in progress, step 9200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72fe9633b02a51a49a2cfeadca1ee666fcf1b3fd25d1edaee5806d94baa42146
+oid sha256:9b773bdf4055e53552cee0ed25da5c686cd04dc17af6b5a2d0bf3dd951e16525
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a87453f5493e54965bd9c6b74c8cccaf89bc199afc196a39a1776694b5725e8
+oid sha256:e10372dacbd6eaf45478a0c95249dcd88ed2ce0ce6aa512de458d4897ecfc863
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03dc33a206b870bac827b0d4553fe1f31612e46dc1d6df4c89c4f928ac98827
+oid sha256:20e6dce8f2f1c5a17a180c274638622919bd91b1b4a11df9b9fbd8d8e95cbf84
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297c2ad1be70bae81e3d823568324b3db1a2bdb9ff27011986573fdf4003489a
+oid sha256:54f59af528e00285e6f0500198bcd9b612dd10ddf7de75e7254a328683370acd
 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": 2.641509433962264,
+  "epoch": 2.6705370101596517,
   "eval_steps": 100,
-  "global_step": 9100,
+  "global_step": 9200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1372,6 +1372,21 @@
       "eval_samples_per_second": 213.408,
       "eval_steps_per_second": 3.335,
       "step": 9100
+    },
+    {
+      "epoch": 2.6705370101596517,
+      "grad_norm": 1.25364351272583,
+      "learning_rate": 7.329462989840349e-05,
+      "loss": 1.966,
+      "step": 9200
+    },
+    {
+      "epoch": 2.6705370101596517,
+      "eval_loss": 1.0489540100097656,
+      "eval_runtime": 213.3373,
+      "eval_samples_per_second": 213.273,
+      "eval_steps_per_second": 3.333,
+      "step": 9200
     }
   ],
   "logging_steps": 100,
@@ -1386,7 +1401,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1400,7 +1415,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.103292765936026e+16,
+  "total_flos": 9.203331526714982e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null