Training in progress, epoch 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd15c54ce790c7516cb0d030eb8ff51312d9d594cc86699aaab0955c180e0fd
+oid sha256:6139318cf513eafa3224f054690d83317b804a9c28a2577d7370471793ce1b21
 size 1980859973

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3189017799e464e97ffb8a5e4bb37d2d3a4c52cd249802e8c7dcb7ad9a25afa3
+oid sha256:e0fa9ab0647db949841272150c5f38714cb2e9d7c97e66166b9a8e4985840035
 size 990408885

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:969c7a9f9e96e582bdeeaa51020c2fe36c4aa27f31056f54feeaf0a9a8297b2c
+oid sha256:58ddbd433b5599bf8b86b64743d5e39fd3dfe1434235c8a38c9b7bbdd7fa5b81
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d42e8f748d546c35d0a3efca92030df4b30dc0bda4152d70d8cbdd1a281cf40
+oid sha256:9c334c84f22d7de01f067ab9bee69f31e2f916e7efdb35f8cf0f7917bfd43bda
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3411617279052734,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-7890",
-  "epoch": 3.0,
+  "best_metric": 2.3347413539886475,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-10520",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 7890,
+  "global_step": 10520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,13 +154,68 @@
       "eval_steps_per_second": 1.46,
       "eval_translation_length": 45550,
       "step": 7890
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.958174904942966e-05,
+      "loss": 2.4461,
+      "step": 8000
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 1.7680608365019013e-05,
+      "loss": 2.4042,
+      "step": 8500
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 1.5779467680608364e-05,
+      "loss": 2.4027,
+      "step": 9000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 1.387832699619772e-05,
+      "loss": 2.3927,
+      "step": 9500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1.1977186311787073e-05,
+      "loss": 2.3733,
+      "step": 10000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.0076045627376426e-05,
+      "loss": 2.3716,
+      "step": 10500
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 0.04869515928692814,
+      "eval_brevity_penalty": 0.9823324657661657,
+      "eval_length_ratio": 0.9824867144301728,
+      "eval_loss": 2.3347413539886475,
+      "eval_precisions": [
+        0.12663965838169275,
+        0.0574505431946487,
+        0.030477866031926728,
+        0.027230821761893922
+      ],
+      "eval_reference_length": 46479,
+      "eval_runtime": 200.6451,
+      "eval_samples_per_second": 17.479,
+      "eval_steps_per_second": 1.46,
+      "eval_translation_length": 45665,
+      "step": 10520
     }
   ],
   "logging_steps": 500,
   "max_steps": 13150,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 6.483282612977664e+16,
+  "total_flos": 8.644376817303552e+16,
   "trial_name": null,
   "trial_params": null
 }