Training in progress, step 12900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45996c7c3827c42035ef33857663cf97d8646274efc340c1e59d70cfce3d1ed1
+oid sha256:92e4d3a24989c058dce810550324b446956002a1ec0e09b420026db209c2a60d
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffaecc7a53d1917059c82b5b68051f3c876eb201667f8145114f7c13f94cb226
+oid sha256:77f480cfa7730662ffb401034694baab29b3ee65573dcc560af58e3076c7480e
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fae1937abf0cbdf02cd5b4cc941b1d11472fe3757a52930fe7db4f99719b1057
+oid sha256:0a19cb26834bb300d311ca96e9ab4523f1b9af1aed5b729363ab485dcce03194
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1830c26a382ee66a79a69484e18414a1ce714a42276dbbc3828145602902947a
+oid sha256:05e77d45b7360e6234dfa016d82b5c92a87cf281877240b4c2896988de54ea06
 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": 3.7155297532656024,
+  "epoch": 3.7445573294629897,
   "eval_steps": 100,
-  "global_step": 12800,
+  "global_step": 12900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1927,6 +1927,21 @@
       "eval_samples_per_second": 211.786,
       "eval_steps_per_second": 3.31,
       "step": 12800
+    },
+    {
+      "epoch": 3.7445573294629897,
+      "grad_norm": 1.2558367252349854,
+      "learning_rate": 6.25544267053701e-05,
+      "loss": 1.9083,
+      "step": 12900
+    },
+    {
+      "epoch": 3.7445573294629897,
+      "eval_loss": 1.0279453992843628,
+      "eval_runtime": 214.5403,
+      "eval_samples_per_second": 212.053,
+      "eval_steps_per_second": 3.314,
+      "step": 12900
     }
   ],
   "logging_steps": 100,
@@ -1941,7 +1956,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 4
       }
     },
     "TrainerControl": {
@@ -1955,7 +1970,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2803554590012211e+17,
+  "total_flos": 1.2903593350791168e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null