Training in progress, step 5130, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b20934b18063c0d43e1cc111f116b29f304cb00e94181ca32a4c16745b5b1342
+oid sha256:33542d657951fc711393135a39b0e0684ed25d61cf98113bff1a12483ddbcf73
 size 498640508

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b51ffda4d0fb6ec6a4a2ef086771cd878ed8342d3c2742ab9e09b3b62cacffd
+oid sha256:3882725d43e32cb60155e6a5f4f7fbab15ce55e2a98db50dfce7295987b1fed0
 size 997404043

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d444c8e76002d9beea566dae4d76956376b864c8fcc79608f7ea6b8aab646646
+oid sha256:e0de456d23c0279ef9b1c7230b21886478e650deea6d6127db316ca690bfdb7b
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2dd05f393cb43123ffd5143047d0b810bf6f7b9b04a6b494bd7518c9f570e8
+oid sha256:aa2fde459a6873aa856f595805d2e643164ffe89b4eb834e69a2660e2b76f5aa
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4400,
   "best_metric": 0.8001271963887049,
   "best_model_checkpoint": "roberta_en_med_merged_classes/checkpoint-4400",
-  "epoch": 5.614394382679929,
+  "epoch": 6.0,
   "eval_steps": 400,
-  "global_step": 4800,
+  "global_step": 5130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -476,6 +476,27 @@
       "eval_samples_per_second": 102.041,
       "eval_steps_per_second": 1.597,
       "step": 4800
+    },
+    {
+      "epoch": 5.731421884142773,
+      "grad_norm": 667246.875,
+      "learning_rate": 1.0006497725795972e-06,
+      "loss": 0.2232,
+      "step": 4900
+    },
+    {
+      "epoch": 5.848449385605617,
+      "grad_norm": 597527.5,
+      "learning_rate": 5.674680528481699e-07,
+      "loss": 0.2195,
+      "step": 5000
+    },
+    {
+      "epoch": 5.965476887068461,
+      "grad_norm": 716894.25,
+      "learning_rate": 1.3428633311674248e-07,
+      "loss": 0.21,
+      "step": 5100
     }
   ],
   "logging_steps": 100,
@@ -490,12 +511,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.075267666347008e+16,
+  "total_flos": 8.629371698794906e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null