Training in progress, step 12800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b27a14383dd8f5e32b60ef49bc481293813140736526a4d806cb4d5c5b3268e
+oid sha256:45996c7c3827c42035ef33857663cf97d8646274efc340c1e59d70cfce3d1ed1
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb14ca0c2f5ae383677929856e1fecb6cd12be007d2e5ee2ab6922194db8185
+oid sha256:ffaecc7a53d1917059c82b5b68051f3c876eb201667f8145114f7c13f94cb226
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28e5cd297de6a1b12da23dedd476015f955db015600bb1926647d7c00b1169d
+oid sha256:fae1937abf0cbdf02cd5b4cc941b1d11472fe3757a52930fe7db4f99719b1057
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce4913c29db9ab1a6055951072608d3b069c9e334243739e18506537cb2d1ef
+oid sha256:1830c26a382ee66a79a69484e18414a1ce714a42276dbbc3828145602902947a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0211207866668701,
   "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-12500",
-  "epoch": 3.6865021770682147,
+  "epoch": 3.7155297532656024,
   "eval_steps": 100,
-  "global_step": 12700,
+  "global_step": 12800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1912,6 +1912,21 @@
       "eval_samples_per_second": 212.336,
       "eval_steps_per_second": 3.318,
       "step": 12700
+    },
+    {
+      "epoch": 3.7155297532656024,
+      "grad_norm": 1.230591893196106,
+      "learning_rate": 6.284470246734397e-05,
+      "loss": 1.8998,
+      "step": 12800
+    },
+    {
+      "epoch": 3.7155297532656024,
+      "eval_loss": 1.0226044654846191,
+      "eval_runtime": 214.8109,
+      "eval_samples_per_second": 211.786,
+      "eval_steps_per_second": 3.31,
+      "step": 12800
     }
   ],
   "logging_steps": 100,
@@ -1926,7 +1941,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1940,7 +1955,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2703515829233254e+17,
+  "total_flos": 1.2803554590012211e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null