Training in progress, epoch 3, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46abff71e7026647c05fbaf7f699e8ee421c0a2e584b794f2fb0c530d4b1f4b4
+oid sha256:6050f38120b0e933aecb28cd28fb9c7925ebc96441d3fad1965b4adf303d89fd
 size 1980859973

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95635d8117e24e5efeb681934dc5313da771c7b857de60f1ac43e8245d9484ab
+oid sha256:3a7994a97f599475aa5874b645c4945821ebf2eb2b2f90ad0971c97bb6cef71b
 size 990408885

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4844a5d656111932c3ceada711e9cbb272e49c0cfedd858f395737c72b4c6992
+oid sha256:1d79d8043ba95baf61ac1e0e9419f144c2c0f76428640c86753d23d96ba746f8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5371d45631fd7dd6529335dfaa6166f363409fc22e7123a04a9a24603e02dcb6
+oid sha256:d9508142e5058d0d70d25ee8e25948935ec2c9917db374dac6856edde91f4a56
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.6461355686187744,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-6084",
-  "epoch": 2.0,
+  "best_metric": 2.596039056777954,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-9126",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 6084,
+  "global_step": 9126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -117,13 +117,68 @@
       "eval_steps_per_second": 1.822,
       "eval_translation_length": 22165,
       "step": 6084
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 2.863247863247863e-05,
+      "loss": 2.6801,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.69888231426693e-05,
+      "loss": 2.6995,
+      "step": 7000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 2.5345167652859964e-05,
+      "loss": 2.6345,
+      "step": 7500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 2.3701512163050626e-05,
+      "loss": 2.6573,
+      "step": 8000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.205785667324129e-05,
+      "loss": 2.629,
+      "step": 8500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 2.0414201183431952e-05,
+      "loss": 2.6619,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 0.02507600348121833,
+      "eval_brevity_penalty": 0.3107319508436834,
+      "eval_length_ratio": 0.4610792338199308,
+      "eval_loss": 2.596039056777954,
+      "eval_precisions": [
+        0.19751109484375715,
+        0.10842087523172855,
+        0.04568934157875591,
+        0.043348126741665806
+      ],
+      "eval_reference_length": 47404,
+      "eval_runtime": 182.5266,
+      "eval_samples_per_second": 22.221,
+      "eval_steps_per_second": 1.852,
+      "eval_translation_length": 21857,
+      "step": 9126
     }
   ],
   "logging_steps": 500,
   "max_steps": 15210,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 4.998043915517952e+16,
+  "total_flos": 7.497065873276928e+16,
   "trial_name": null,
   "trial_params": null
 }