Training in progress, epoch 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bef42164b2a51e4051a44517ba752324c8de85f5419cfc846dd91c7d95c4cb4
+oid sha256:0726fa530c6ac77f8f3c68ffe7f1ba01db45a098cc51f636a7c1ba8b59d3586d
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:920b1b664dfff0e47d3c0852b3fc85d0b4f592e6c894b312f72b5a089a6596a9
+oid sha256:b34dbfea05eb5422e006a144b5f954b538f4359044e7e416f9e704e152a7989b
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6321fbaddd43eddcbca683c61cefc7d2d7729864e6691f1cec4a47a1cdd357d
+oid sha256:987189384bf09d11dec2af9c70406cd2efd3483f1c3cd71dce5b9fd6c31868a2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640ac802dd40cc795df7389c02195fc11e6f3f215f805047340eb365622bc3f8
+oid sha256:14143acff0ead4485046a1fe7314fe8dc180e8a9f26db4244c2b5510c7a3c384
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.9787917137145996,
   "best_model_checkpoint": "dq158/morbius/checkpoint-790",
-  "epoch": 5.99936768890294,
+  "epoch": 6.9984192222573505,
   "eval_steps": 500,
-  "global_step": 2372,
+  "global_step": 2767,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -145,13 +145,38 @@
       "eval_steps_per_second": 0.63,
       "eval_translation_length": 51951,
       "step": 2372
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 5.812361531865285e-06,
+      "loss": 2.1567,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 1.9794704914093018,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 51995,
+      "eval_runtime": 560.6932,
+      "eval_samples_per_second": 5.015,
+      "eval_steps_per_second": 0.628,
+      "eval_translation_length": 51995,
+      "step": 2767
     }
   ],
   "logging_steps": 500,
   "max_steps": 7900,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.0395849173395046e+17,
+  "total_flos": 1.212849070229422e+17,
   "trial_name": null,
   "trial_params": null
 }