Training in progress, epoch 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6139318cf513eafa3224f054690d83317b804a9c28a2577d7370471793ce1b21
+oid sha256:ff4bb58512ee01982f44caed455c7423289727bc15b0fc869b97c0b72a0e9240
 size 1980859973

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0fa9ab0647db949841272150c5f38714cb2e9d7c97e66166b9a8e4985840035
+oid sha256:79dd6cb491bf5c0dc32e975bffbddf3e68f8db6f14f145247bc036a4afc9d96c
 size 990408885

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ddbd433b5599bf8b86b64743d5e39fd3dfe1434235c8a38c9b7bbdd7fa5b81
+oid sha256:36363c17943656effbb47533a23721e90ccabdba74b07267327afecccd9eaedb
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c334c84f22d7de01f067ab9bee69f31e2f916e7efdb35f8cf0f7917bfd43bda
+oid sha256:72b27e4bc84ba5438edd8bff61bb702668a367a4bbc68ac8b35a3ba97d2b72e4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3347413539886475,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-10520",
-  "epoch": 4.0,
+  "best_metric": 2.331069231033325,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-13150",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 10520,
+  "global_step": 13150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -209,13 +209,62 @@
       "eval_steps_per_second": 1.46,
       "eval_translation_length": 45665,
       "step": 10520
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 8.17490494296578e-06,
+      "loss": 2.3618,
+      "step": 11000
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 6.273764258555133e-06,
+      "loss": 2.3667,
+      "step": 11500
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 4.3726235741444865e-06,
+      "loss": 2.377,
+      "step": 12000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.4714828897338406e-06,
+      "loss": 2.346,
+      "step": 12500
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 5.70342205323194e-07,
+      "loss": 2.3494,
+      "step": 13000
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 0.04900460577934908,
+      "eval_brevity_penalty": 0.9780979152370445,
+      "eval_length_ratio": 0.978334301512511,
+      "eval_loss": 2.331069231033325,
+      "eval_precisions": [
+        0.12658339197748064,
+        0.058000714881448825,
+        0.031020853918560506,
+        0.0276665140764477
+      ],
+      "eval_reference_length": 46479,
+      "eval_runtime": 201.3997,
+      "eval_samples_per_second": 17.413,
+      "eval_steps_per_second": 1.455,
+      "eval_translation_length": 45472,
+      "step": 13150
     }
   ],
   "logging_steps": 500,
   "max_steps": 13150,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 8.644376817303552e+16,
+  "total_flos": 1.080547102162944e+17,
   "trial_name": null,
   "trial_params": null
 }