Training in progress, epoch 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb2b0764d46cdc39d3cfc8da65f2e33f421f936ed0b43591a344d624a0e8cc6
+oid sha256:2bef42164b2a51e4051a44517ba752324c8de85f5419cfc846dd91c7d95c4cb4
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:603b8ba831d7729fbeede1b810117812b38ca1ab4a88a54b002aab7aa79fa0c9
+oid sha256:920b1b664dfff0e47d3c0852b3fc85d0b4f592e6c894b312f72b5a089a6596a9
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307278cafa2e7fc7cf12212db9810637e1fbf444b426a62ee30019fd8d31fcc1
+oid sha256:f6321fbaddd43eddcbca683c61cefc7d2d7729864e6691f1cec4a47a1cdd357d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d34bc3c0e5ede37587b8d9461e9b651c2612ca91d13122ea1ae5e59e474a04
+oid sha256:640ac802dd40cc795df7389c02195fc11e6f3f215f805047340eb365622bc3f8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.9787917137145996,
   "best_model_checkpoint": "dq158/morbius/checkpoint-790",
-  "epoch": 4.997786911160291,
+  "epoch": 5.99936768890294,
   "eval_steps": 500,
-  "global_step": 1976,
+  "global_step": 2372,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,13 +120,38 @@
       "eval_steps_per_second": 0.629,
       "eval_translation_length": 52050,
       "step": 1976
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 6.313989956284292e-06,
+      "loss": 2.1554,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 1.9794400930404663,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 51951,
+      "eval_runtime": 559.0901,
+      "eval_samples_per_second": 5.03,
+      "eval_steps_per_second": 0.63,
+      "eval_translation_length": 51951,
+      "step": 2372
     }
   ],
   "logging_steps": 500,
   "max_steps": 7900,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 8.663207644495872e+16,
+  "total_flos": 1.0395849173395046e+17,
   "trial_name": null,
   "trial_params": null
 }