Training in progress, epoch 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff7f9757e809d561c115e2938e4b1e054f12512e4faa14683175bf1da61b830
+oid sha256:d654805ed9234ae2d8fdbc075cce837e33725c04237f9038125b36d9d62dae99
 size 1980859973

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298ba19a4609d7dd947bbb269dd9f6739bce5396313593cc5c633140fa54700e
+oid sha256:9863c9e4a421b4c8a5dd0c97c81ae647ff18a8e1c42001a147142a64b1334be5
 size 990408885

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71cc14f2f2a99ed544f7de8010d2c41e8d37087bf31674d350dddb637d0ba4aa
+oid sha256:ca9e3700e39325a3e1dc8b4b73fc256108f4cb106e4b099a5b0ae926f40e91ad
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3fb20f868db7426ac2664add45589679b3c5c8958de4e6a4cecd76b00023e37
+oid sha256:855eca6957908186c8cb9f482cb515942df4091ad40eb4895f55eafc501ea74c
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.574343204498291,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-12168",
-  "epoch": 4.0,
+  "best_metric": 2.5664496421813965,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-15210",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 12168,
+  "global_step": 15210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -227,13 +227,68 @@
       "eval_steps_per_second": 1.613,
       "eval_translation_length": 25887,
       "step": 12168
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 8.908612754766601e-06,
+      "loss": 2.5331,
+      "step": 12500
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 7.264957264957266e-06,
+      "loss": 2.4913,
+      "step": 13000
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 5.621301775147929e-06,
+      "loss": 2.512,
+      "step": 13500
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 3.977646285338593e-06,
+      "loss": 2.5832,
+      "step": 14000
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 2.3339907955292573e-06,
+      "loss": 2.5606,
+      "step": 14500
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 6.903353057199211e-07,
+      "loss": 2.5644,
+      "step": 15000
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 0.02983644416340299,
+      "eval_brevity_penalty": 0.37064217148618556,
+      "eval_length_ratio": 0.5018774786937811,
+      "eval_loss": 2.5664496421813965,
+      "eval_precisions": [
+        0.19133285696271699,
+        0.1052951608816823,
+        0.04713310797882518,
+        0.044222661963348536
+      ],
+      "eval_reference_length": 47404,
+      "eval_runtime": 201.0635,
+      "eval_samples_per_second": 20.173,
+      "eval_steps_per_second": 1.681,
+      "eval_translation_length": 23791,
+      "step": 15210
     }
   ],
   "logging_steps": 500,
   "max_steps": 15210,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 9.996087831035904e+16,
+  "total_flos": 1.249510978879488e+17,
   "trial_name": null,
   "trial_params": null
 }