Training in progress, epoch 3, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6393b8f0ca5e88756c2083d1f2a1907a0f9a6dbb6883be0a4876e58b8454d9e5
+oid sha256:78de1845d42de8e97166e8d03c88d7280317088266d512255171d83e18a8a1e5
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c614a827b995ce3eaf6b4ca43b101bd027894d4a25801ccc43d2a50633f617fc
+oid sha256:b5f0238759a93a9592fd56d938808164b244ac6e6bb3e90c17087d301135f128
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86155979fa4274be782ec567e9a698db195e65592845142c9f3ce5d5d0bead1a
+oid sha256:c1e723f49fe760d012e95cecfb34027c4fde3be5d77172e6153faab81be88006
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d9908d10066d14a0312f52aee3b01a644d08d03fb490399a3d67eceed366c84
+oid sha256:58e51bf061e0cdfb069f5bf54e7d5368500d8ffe6cdb788eb18b7c3b43df1234
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4565129280090332,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-2950",
-  "epoch": 2.0,
+  "best_metric": 1.446006178855896,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-4425",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 2950,
+  "global_step": 4425,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,13 +75,50 @@
       "eval_steps_per_second": 0.563,
       "eval_translation_length": 35935,
       "step": 2950
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 2.9661016949152544e-05,
+      "loss": 1.6543,
+      "step": 3000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.627118644067797e-05,
+      "loss": 1.6515,
+      "step": 3500
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.2881355932203392e-05,
+      "loss": 1.6408,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 1.446006178855896,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 36005,
+      "eval_runtime": 291.2917,
+      "eval_samples_per_second": 6.749,
+      "eval_steps_per_second": 0.563,
+      "eval_translation_length": 36005,
+      "step": 4425
     }
   ],
   "logging_steps": 500,
   "max_steps": 7375,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 2.4232193188429824e+16,
+  "total_flos": 3.634828978264474e+16,
   "trial_name": null,
   "trial_params": null
 }