Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e4d3a24989c058dce810550324b446956002a1ec0e09b420026db209c2a60d
+oid sha256:f9ca3bdde2a61ba667a72d8eaf0bf5f81ab499a354226b51a4333e12abbc7ce3
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f480cfa7730662ffb401034694baab29b3ee65573dcc560af58e3076c7480e
+oid sha256:7becabf93fc0c5dc3517b5d4509f6b85181312fd7caf2139e8743d6d6bd57379
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a19cb26834bb300d311ca96e9ab4523f1b9af1aed5b729363ab485dcce03194
+oid sha256:f9d2d17fcb4f3a6b40a17c5ccf26f3e9f1dfd80a4b480d1429f00089f6f9f636
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e77d45b7360e6234dfa016d82b5c92a87cf281877240b4c2896988de54ea06
+oid sha256:94be6c288bea87cefdacbf3a9a3ab65a00906b955f2a23f5957dfac4af499c86
 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": 3.7445573294629897,
+  "epoch": 3.7735849056603774,
   "eval_steps": 100,
-  "global_step": 12900,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1942,6 +1942,21 @@
       "eval_samples_per_second": 212.053,
       "eval_steps_per_second": 3.314,
       "step": 12900
+    },
+    {
+      "epoch": 3.7735849056603774,
+      "grad_norm": 1.3605984449386597,
+      "learning_rate": 6.226415094339622e-05,
+      "loss": 1.8947,
+      "step": 13000
+    },
+    {
+      "epoch": 3.7735849056603774,
+      "eval_loss": 1.0254005193710327,
+      "eval_runtime": 214.5443,
+      "eval_samples_per_second": 212.049,
+      "eval_steps_per_second": 3.314,
+      "step": 13000
     }
   ],
   "logging_steps": 100,
@@ -1956,7 +1971,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 4
+        "early_stopping_patience_counter": 5
       }
     },
     "TrainerControl": {
@@ -1965,12 +1980,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2903593350791168e+17,
+  "total_flos": 1.3003632111570125e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null