Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e970ebd5a85878e24d4e82408f1544b44510ad867e6e14413abc73b59a6e2b87
+oid sha256:99c7c6345d23e47ec7b9dbf26d333608e6fe8626b67a5e372a70651b48e75310
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9015c6e097a9d0d0b930f42989c855220716dbcdd318d26faaab572c32352885
+oid sha256:374e81646506ec785e96925a53b43bcde0358a1c71b2b55faf65745451ec9335
 size 3250759392

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29088cd044384ff39ead7e6da89a896d2c14ec65f5b780b791b52bf8b2923887
+oid sha256:25d54536c46c6f3683b9b736e1a9111acd8762892f281e07dc7a35213344cfda
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917c700dc3c784b68d992933d13de0aadf8e6b69ea6214efe3a71da31083190f
+oid sha256:2fbf1b07c041b197423e5d1ffb8c16c75724e39b14f67ac144d57b7027705d1c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf9a735ef029846b4b68a529e8290b963a10b9c42b981859787d6acbeb3970d
+oid sha256:6b154e3fa863cb05233141214936047bed984525ee21ed80525aafdbf0e2d33a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 3000,
   "best_metric": 51.14,
   "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-3000",
-  "epoch": 1.2081643220850953,
+  "epoch": 1.3807715543281263,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -589,6 +589,89 @@
       "eval_samples_per_second": 1.069,
       "eval_steps_per_second": 0.267,
       "step": 3500
+    },
+    {
+      "epoch": 1.2254250453093984,
+      "grad_norm": 2.9530227184295654,
+      "learning_rate": 2.0066142295316413e-06,
+      "loss": 0.4127,
+      "step": 3550
+    },
+    {
+      "epoch": 1.2426857685337016,
+      "grad_norm": 2.9822258949279785,
+      "learning_rate": 1.9619234894529854e-06,
+      "loss": 0.3785,
+      "step": 3600
+    },
+    {
+      "epoch": 1.2599464917580048,
+      "grad_norm": 3.8967037200927734,
+      "learning_rate": 1.91723274937433e-06,
+      "loss": 0.4015,
+      "step": 3650
+    },
+    {
+      "epoch": 1.2772072149823077,
+      "grad_norm": 2.652034044265747,
+      "learning_rate": 1.872542009295674e-06,
+      "loss": 0.3962,
+      "step": 3700
+    },
+    {
+      "epoch": 1.2944679382066109,
+      "grad_norm": 2.3683066368103027,
+      "learning_rate": 1.8278512692170184e-06,
+      "loss": 0.3942,
+      "step": 3750
+    },
+    {
+      "epoch": 1.311728661430914,
+      "grad_norm": 2.787900447845459,
+      "learning_rate": 1.7831605291383628e-06,
+      "loss": 0.3902,
+      "step": 3800
+    },
+    {
+      "epoch": 1.328989384655217,
+      "grad_norm": 2.8084681034088135,
+      "learning_rate": 1.7384697890597069e-06,
+      "loss": 0.3971,
+      "step": 3850
+    },
+    {
+      "epoch": 1.3462501078795202,
+      "grad_norm": 3.2413413524627686,
+      "learning_rate": 1.6937790489810514e-06,
+      "loss": 0.396,
+      "step": 3900
+    },
+    {
+      "epoch": 1.3635108311038233,
+      "grad_norm": 2.3999781608581543,
+      "learning_rate": 1.6490883089023956e-06,
+      "loss": 0.3836,
+      "step": 3950
+    },
+    {
+      "epoch": 1.3807715543281263,
+      "grad_norm": 3.1420865058898926,
+      "learning_rate": 1.6043975688237399e-06,
+      "loss": 0.3757,
+      "step": 4000
+    },
+    {
+      "epoch": 1.3807715543281263,
+      "eval_gen_len": 54.231239092495635,
+      "eval_loss": 0.5294080376625061,
+      "eval_rouge1": 50.76,
+      "eval_rouge2": 36.73,
+      "eval_rougeL": 44.34,
+      "eval_rougeLsum": 44.9,
+      "eval_runtime": 5340.6521,
+      "eval_samples_per_second": 1.073,
+      "eval_steps_per_second": 0.268,
+      "step": 4000
     }
   ],
   "logging_steps": 50,
@@ -603,7 +686,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -612,12 +695,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.201598467401646e+17,
+  "total_flos": 1.373273785100206e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null