Training in progress, epoch 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1f3b82e6184cf3fa1f97e3633ed652219d243ea18fef27a35a38877c4c498c
+oid sha256:5b97ff2c46e83b02c5dac9aef9f59c66bb654fc31cf4601ff87ff73224691566
 size 2371770

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63200bebd3227b384c5ba52c132d7b8ab92410896734805be9e58058c777ae71
+oid sha256:538c6afe3af4e0e1ffd7998f1e019f18fbd60f4e2b15c398e1ec3b1435f65d6e
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce000429344a01e02536fd43d4c586bca70568f5e5b5ee181c3030c0d0aae5bd
+oid sha256:b54ac781bcf42bd5774e68cd27f8b47ba97a92bc3e5e5b5762ae0f9660c2d4e6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:845ca0614dd5d49345c95c404b37a30ec6d95611e0a635ec0ac26e0a4196186d
+oid sha256:b57d4c861df932544616bc97fdff1b5095cad53562dd214e165dfc55a56cc480
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.257721424102783,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-6324",
-  "epoch": 4.0,
+  "best_metric": 2.240872383117676,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-7905",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 6324,
+  "global_step": 7905,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -155,13 +155,50 @@
       "eval_steps_per_second": 0.607,
       "eval_translation_length": 53121,
       "step": 6324
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 9.110503086981956e-05,
+      "loss": 2.2444,
+      "step": 6500
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 8.961639836966304e-05,
+      "loss": 2.2152,
+      "step": 7000
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 8.802685374286608e-05,
+      "loss": 2.2,
+      "step": 7500
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.240872383117676,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 52857,
+      "eval_runtime": 579.7989,
+      "eval_samples_per_second": 4.848,
+      "eval_steps_per_second": 0.607,
+      "eval_translation_length": 52857,
+      "step": 7905
     }
   ],
   "logging_steps": 500,
   "max_steps": 31620,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 6.927279280304947e+16,
+  "total_flos": 8.659099100381184e+16,
   "trial_name": null,
   "trial_params": null
 }