Training in progress, epoch 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78de1845d42de8e97166e8d03c88d7280317088266d512255171d83e18a8a1e5
+oid sha256:2e182cf7af55a4587a0ca3ba6416b1aa45eafc79633351a41e5d59811f7a451c
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5f0238759a93a9592fd56d938808164b244ac6e6bb3e90c17087d301135f128
+oid sha256:cec0c19e5d8676c555d959ec2b293902f093b7ead0acaa05a8a02126e66971d0
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e723f49fe760d012e95cecfb34027c4fde3be5d77172e6153faab81be88006
+oid sha256:729abbd3ef67de81491d0ba432cad08d03530a09134bacfb682480f442a1aec0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e51bf061e0cdfb069f5bf54e7d5368500d8ffe6cdb788eb18b7c3b43df1234
+oid sha256:e79d3f19a5bd9c30d954331796aa7283483a96c6d7e33353c55c9ee00b681646
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.446006178855896,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-4425",
-  "epoch": 3.0,
+  "best_metric": 1.4407896995544434,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-5900",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 4425,
+  "global_step": 5900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,13 +112,50 @@
       "eval_steps_per_second": 0.563,
       "eval_translation_length": 36005,
       "step": 4425
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 1.9491525423728814e-05,
+      "loss": 1.6183,
+      "step": 4500
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 1.6101694915254237e-05,
+      "loss": 1.6291,
+      "step": 5000
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.2711864406779661e-05,
+      "loss": 1.6058,
+      "step": 5500
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 1.4407896995544434,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 36007,
+      "eval_runtime": 291.6745,
+      "eval_samples_per_second": 6.74,
+      "eval_steps_per_second": 0.562,
+      "eval_translation_length": 36007,
+      "step": 5900
     }
   ],
   "logging_steps": 500,
   "max_steps": 7375,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 3.634828978264474e+16,
+  "total_flos": 4.846438637685965e+16,
   "trial_name": null,
   "trial_params": null
 }