Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6582285e6ceefad293dc43c7b1e46f720b002966ac196d7c0ed75850fa58072f
+oid sha256:5a278fb208cf82d5c5728afb7c555b5b65b6f6a012bb67285a69e4eb073254f6
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1289f0f9e4695a91c66438eb371e115fd2cf13c51b9b60f4d079bcea0df3f1
+oid sha256:709293e8f8d89d46e62d8dcffb82aec4b6a3854c0c787c3905239ef720804708
 size 3250759392

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f64d1914206b27bc308756481002e046d709339f305bb5f119a7f2db9832e2a
+oid sha256:5420c023313a95f831e40048e5f377d6fb45506c03fe462bce53dbc170b39da5
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fe95f5f8339fd092746c4e1f9ecbd1df3cf41b30fe774157fac457b1083509
+oid sha256:016a72d1342888aeb454c6fd7e33114f8fe7d8d6d4c795719a5831d14388e2ea
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5955ff7ae3c292679cb2d15dfab21a83841dbd226cd7e259de6ef2a4c905fc
+oid sha256:7b44fb2a9542e90532b93ebac4a5e8666f98d6d7698a2bf80999186ee0ee3983
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1000,
   "best_metric": 50.66,
   "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-1000",
-  "epoch": 0.34521446448606197,
+  "epoch": 0.517821696729093,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -174,6 +174,89 @@
       "eval_samples_per_second": 1.092,
       "eval_steps_per_second": 0.273,
       "step": 1000
+    },
+    {
+      "epoch": 0.3624751877103651,
+      "grad_norm": 4.5150227546691895,
+      "learning_rate": 4.241151233464427e-06,
+      "loss": 0.4227,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3797359109346682,
+      "grad_norm": 2.6075778007507324,
+      "learning_rate": 4.19646049338577e-06,
+      "loss": 0.4255,
+      "step": 1100
+    },
+    {
+      "epoch": 0.39699663415897124,
+      "grad_norm": 3.93216609954834,
+      "learning_rate": 4.151769753307115e-06,
+      "loss": 0.4192,
+      "step": 1150
+    },
+    {
+      "epoch": 0.41425735738327435,
+      "grad_norm": 3.318143606185913,
+      "learning_rate": 4.107079013228459e-06,
+      "loss": 0.3984,
+      "step": 1200
+    },
+    {
+      "epoch": 0.43151808060757746,
+      "grad_norm": 3.0835282802581787,
+      "learning_rate": 4.062388273149804e-06,
+      "loss": 0.4086,
+      "step": 1250
+    },
+    {
+      "epoch": 0.44877880383188057,
+      "grad_norm": 2.782550811767578,
+      "learning_rate": 4.017697533071148e-06,
+      "loss": 0.4114,
+      "step": 1300
+    },
+    {
+      "epoch": 0.4660395270561837,
+      "grad_norm": 3.2588839530944824,
+      "learning_rate": 3.973006792992492e-06,
+      "loss": 0.4304,
+      "step": 1350
+    },
+    {
+      "epoch": 0.48330025028048673,
+      "grad_norm": 3.4788544178009033,
+      "learning_rate": 3.928316052913836e-06,
+      "loss": 0.4047,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5005609735047899,
+      "grad_norm": 3.0864784717559814,
+      "learning_rate": 3.883625312835181e-06,
+      "loss": 0.4185,
+      "step": 1450
+    },
+    {
+      "epoch": 0.517821696729093,
+      "grad_norm": 2.8312442302703857,
+      "learning_rate": 3.838934572756525e-06,
+      "loss": 0.4325,
+      "step": 1500
+    },
+    {
+      "epoch": 0.517821696729093,
+      "eval_gen_len": 54.41937172774869,
+      "eval_loss": 0.5411620736122131,
+      "eval_rouge1": 50.59,
+      "eval_rouge2": 36.52,
+      "eval_rougeL": 44.19,
+      "eval_rougeLsum": 44.63,
+      "eval_runtime": 5226.6165,
+      "eval_samples_per_second": 1.096,
+      "eval_steps_per_second": 0.274,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -188,7 +271,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -202,7 +285,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4335063539712e+16,
+  "total_flos": 5.1502595309568e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null