Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a278fb208cf82d5c5728afb7c555b5b65b6f6a012bb67285a69e4eb073254f6
+oid sha256:6af466bfad7b84d3f92fdc82d61cd05694f71ff9eecc943c6b5592bb1d3e564d
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709293e8f8d89d46e62d8dcffb82aec4b6a3854c0c787c3905239ef720804708
+oid sha256:7ff6601686031b7765f34ea912c7bbc2327ba935664b6facb5fb29fd2b6e467a
 size 3250759392

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5420c023313a95f831e40048e5f377d6fb45506c03fe462bce53dbc170b39da5
+oid sha256:d8de8b3ca8b0346edfe159c193ca900a7ac29bd3f6c2ea3b1718b858590ac10e
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016a72d1342888aeb454c6fd7e33114f8fe7d8d6d4c795719a5831d14388e2ea
+oid sha256:f70a28f809f2e99aba9c326954681b23221caf6b22c57b9fb6e81d614c34b1f9
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b44fb2a9542e90532b93ebac4a5e8666f98d6d7698a2bf80999186ee0ee3983
+oid sha256:d51a482c6985f87480f189bb302d591d56fe7879c8ecc114a67e898aa53b82ca
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1000,
-  "best_metric": 50.66,
-  "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-1000",
-  "epoch": 0.517821696729093,
+  "best_global_step": 2000,
+  "best_metric": 50.8,
+  "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-2000",
+  "epoch": 0.6904289289721239,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -257,6 +257,89 @@
       "eval_samples_per_second": 1.096,
       "eval_steps_per_second": 0.274,
       "step": 1500
+    },
+    {
+      "epoch": 0.535082419953396,
+      "grad_norm": 3.31876540184021,
+      "learning_rate": 3.7942438326778697e-06,
+      "loss": 0.4191,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5523431431776992,
+      "grad_norm": 3.1453733444213867,
+      "learning_rate": 3.7495530925992137e-06,
+      "loss": 0.4591,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5696038664020022,
+      "grad_norm": 3.1156108379364014,
+      "learning_rate": 3.7048623525205578e-06,
+      "loss": 0.4243,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5868645896263054,
+      "grad_norm": 3.0627033710479736,
+      "learning_rate": 3.6601716124419022e-06,
+      "loss": 0.4518,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6041253128506084,
+      "grad_norm": 3.0280168056488037,
+      "learning_rate": 3.6154808723632467e-06,
+      "loss": 0.4467,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6213860360749115,
+      "grad_norm": 3.178391456604004,
+      "learning_rate": 3.570790132284591e-06,
+      "loss": 0.4411,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6386467592992147,
+      "grad_norm": 3.445444345474243,
+      "learning_rate": 3.526099392205935e-06,
+      "loss": 0.425,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6559074825235177,
+      "grad_norm": 2.4380524158477783,
+      "learning_rate": 3.4814086521272793e-06,
+      "loss": 0.4237,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6731682057478209,
+      "grad_norm": 3.591120958328247,
+      "learning_rate": 3.4367179120486237e-06,
+      "loss": 0.4465,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6904289289721239,
+      "grad_norm": 2.699303388595581,
+      "learning_rate": 3.3920271719699682e-06,
+      "loss": 0.4328,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6904289289721239,
+      "eval_gen_len": 54.16980802792321,
+      "eval_loss": 0.5556456446647644,
+      "eval_rouge1": 50.8,
+      "eval_rouge2": 36.6,
+      "eval_rougeL": 44.19,
+      "eval_rougeLsum": 44.7,
+      "eval_runtime": 5233.7113,
+      "eval_samples_per_second": 1.095,
+      "eval_steps_per_second": 0.274,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -271,7 +354,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -285,7 +368,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.1502595309568e+16,
+  "total_flos": 6.8670127079424e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null