Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:878a35f34cd75f45d403c328a94efa5875841d2b2917a026661461fe9a326377
+oid sha256:067b8a7c716303526670dfb8bc56fae03cdbbf29ed37d4991fe64c928e0bdbd0
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0a69880690b268acd014dbb76f6b9dbeac3ab805b96ce286bbc304abcabbb0
+oid sha256:981f8568e18df91cfeab6eec5f61217695b23396cd15d999934d53fd8ca2d195
 size 3250759392

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19942036ae732bf0600dafcf1c4422b97c2fe83799394bc0c6ff948aabb78ad9
+oid sha256:ca1292d0949d9001f354d7b1957f5d7fb3c5eda5b3075a3cdda1634add393adf
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d09b05bd39538ef18816113a9132fa750a22f57bb959571defdc79d084dac52
+oid sha256:b52c0d5230cbe4dff3dcbc875016ea8649032c17265bd3fa32928b7d60fd030d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c7d20f5d8e2a0e338070c52ebbebc70e1adc04ba4e4f2f006768811444edf6
+oid sha256:a77e0e803bec330fe1d60d35d35c94f06878c2de756c5dca3c6a6f9c076ae62e
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 2000,
-  "best_metric": 50.8,
-  "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-2000",
-  "epoch": 0.8630361612151549,
+  "best_global_step": 3000,
+  "best_metric": 51.14,
+  "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-3000",
+  "epoch": 1.0355570898420643,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -423,6 +423,89 @@
       "eval_samples_per_second": 1.072,
       "eval_steps_per_second": 0.268,
       "step": 2500
+    },
+    {
+      "epoch": 0.880296884439458,
+      "grad_norm": 2.877305746078491,
+      "learning_rate": 2.9004290311047557e-06,
+      "loss": 0.4369,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8975576076637611,
+      "grad_norm": 2.5334177017211914,
+      "learning_rate": 2.8557382910260993e-06,
+      "loss": 0.4371,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9148183308880642,
+      "grad_norm": 2.780935049057007,
+      "learning_rate": 2.811047550947444e-06,
+      "loss": 0.3965,
+      "step": 2650
+    },
+    {
+      "epoch": 0.9320790541123674,
+      "grad_norm": 3.019552707672119,
+      "learning_rate": 2.7663568108687883e-06,
+      "loss": 0.4191,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9493397773366704,
+      "grad_norm": 3.7161452770233154,
+      "learning_rate": 2.7216660707901327e-06,
+      "loss": 0.4164,
+      "step": 2750
+    },
+    {
+      "epoch": 0.9666005005609735,
+      "grad_norm": 2.9958629608154297,
+      "learning_rate": 2.6769753307114764e-06,
+      "loss": 0.4069,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9838612237852766,
+      "grad_norm": 2.9618115425109863,
+      "learning_rate": 2.632284590632821e-06,
+      "loss": 0.4302,
+      "step": 2850
+    },
+    {
+      "epoch": 1.0010356433934582,
+      "grad_norm": 2.9072768688201904,
+      "learning_rate": 2.5875938505541653e-06,
+      "loss": 0.426,
+      "step": 2900
+    },
+    {
+      "epoch": 1.0182963666177614,
+      "grad_norm": 3.2817041873931885,
+      "learning_rate": 2.5429031104755098e-06,
+      "loss": 0.3912,
+      "step": 2950
+    },
+    {
+      "epoch": 1.0355570898420643,
+      "grad_norm": 2.7742252349853516,
+      "learning_rate": 2.498212370396854e-06,
+      "loss": 0.3576,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0355570898420643,
+      "eval_gen_len": 53.4542757417103,
+      "eval_loss": 0.5370803475379944,
+      "eval_rouge1": 51.14,
+      "eval_rouge2": 36.78,
+      "eval_rougeL": 44.59,
+      "eval_rougeLsum": 45.09,
+      "eval_runtime": 5216.1975,
+      "eval_samples_per_second": 1.099,
+      "eval_steps_per_second": 0.275,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -437,7 +520,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -451,7 +534,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.583765884928e+16,
+  "total_flos": 1.029923149703086e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null