Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3e004f33bcb4b20f6924424a7bd4b3c2232c2cf102f316a310917c59bf41f6
+oid sha256:d568dd0fd1698532f40f40ea3e476b481107222384132036a5b5af0a3414c69d
 size 647614116

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5560059478b267921d76a899f71a125eb1e4ec8b685bcb1a7d4a096e4cd0fd65
+oid sha256:b117249a0405fc13119ae5a4e130424b1ac60501fb58fa3d9966fafbeda16582
 size 1295003019

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4ab93550d3f9dfc6f76f03e70886ac01b80969be8e3a31c462f631cd3ea276c
+oid sha256:491fc6f0bef61ce8ec944277c4910499777b4d7ea5798a9e38131138edc3080f
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf451ff600a5ce12ef50b2a8254f31f0e920eae89a966335b89742fc3f30ada9
+oid sha256:af53f9862296eee58ffa07badc825fa23a385ee52489fa52f55a3b350f725c23
 size 1465

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 15.451761251904164,
-  "best_model_checkpoint": "./led_doc_nmt/checkpoint-394",
-  "epoch": 2.0,
+  "best_metric": 17.1792773529393,
+  "best_model_checkpoint": "./led_doc_nmt/checkpoint-591",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 394,
+  "global_step": 591,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,6 +50,31 @@
       "eval_samples_per_second": 3.589,
       "eval_steps_per_second": 0.113,
       "step": 394
+    },
+    {
+      "epoch": 2.030456852791878,
+      "grad_norm": 0.970484733581543,
+      "learning_rate": 9.796954314720813e-06,
+      "loss": 1.8858,
+      "step": 400
+    },
+    {
+      "epoch": 2.5380710659898478,
+      "grad_norm": 0.880925714969635,
+      "learning_rate": 4.720812182741117e-06,
+      "loss": 1.7954,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 17.1792773529393,
+      "eval_comet": 0.41916558686883665,
+      "eval_loss": 1.6308850049972534,
+      "eval_meteor": 0.3591326074542552,
+      "eval_runtime": 391.4856,
+      "eval_samples_per_second": 3.571,
+      "eval_steps_per_second": 0.112,
+      "step": 591
     }
   ],
   "logging_steps": 100,
@@ -73,12 +98,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.6986988615827456e+16,
+  "total_flos": 2.5480482923741184e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null