Training in progress, epoch 13, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41341b31785ed0a2fbc8630488a4926f852161ef06ea08cc89540c9c37dc6630
+oid sha256:904b02e1e6c26215ea888d3f8f6d7aafb77206ed1937def3937a940637da0f1c
 size 2372346

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7137ffdadd3d98f6eb4df58e0d93207f78d2d3a226609b6aa51f825be2c62570
+oid sha256:cb5663454a11041d207ecbb686a7490a34d8683fe674b45b29b48acdb58fa931
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81575766e0f892673e3292549b8eae61ee2367f845a1b2b10898b9e83a3ef05f
+oid sha256:07f9db347331ffb79c2e2cf5b87f5ee3885eb3ce501d58242d83ec8e3cae758d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fc3d9b89093dc44b3f8ae65848b5c79017341da78ff50d3adcc276738c797e7
+oid sha256:ae3274533ddd7159e50e851656ea6e92a09b25d95e547026de312a25757234d5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5654487609863281,
   "best_model_checkpoint": "dq158/pingusPongus/checkpoint-6323",
-  "epoch": 12.0,
+  "epoch": 13.0,
   "eval_steps": 500,
-  "global_step": 75876,
+  "global_step": 82199,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1141,13 +1141,110 @@
       "eval_steps_per_second": 1.038,
       "eval_translation_length": 52457,
       "step": 75876
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 1.7319657912101309e-06,
+      "loss": 1.7871,
+      "step": 76000
+    },
+    {
+      "epoch": 12.1,
+      "learning_rate": 1.7023574667538268e-06,
+      "loss": 1.7728,
+      "step": 76500
+    },
+    {
+      "epoch": 12.18,
+      "learning_rate": 1.6728731866869999e-06,
+      "loss": 1.792,
+      "step": 77000
+    },
+    {
+      "epoch": 12.26,
+      "learning_rate": 1.6435175362209033e-06,
+      "loss": 1.8009,
+      "step": 77500
+    },
+    {
+      "epoch": 12.34,
+      "learning_rate": 1.6142950805631178e-06,
+      "loss": 1.751,
+      "step": 78000
+    },
+    {
+      "epoch": 12.41,
+      "learning_rate": 1.5852103642075995e-06,
+      "loss": 1.7877,
+      "step": 78500
+    },
+    {
+      "epoch": 12.49,
+      "learning_rate": 1.5562679102279453e-06,
+      "loss": 1.7936,
+      "step": 79000
+    },
+    {
+      "epoch": 12.57,
+      "learning_rate": 1.5274722195740005e-06,
+      "loss": 1.7884,
+      "step": 79500
+    },
+    {
+      "epoch": 12.65,
+      "learning_rate": 1.4988277703718882e-06,
+      "loss": 1.7617,
+      "step": 80000
+    },
+    {
+      "epoch": 12.73,
+      "learning_rate": 1.4703390172276072e-06,
+      "loss": 1.7916,
+      "step": 80500
+    },
+    {
+      "epoch": 12.81,
+      "learning_rate": 1.4420103905342767e-06,
+      "loss": 1.7773,
+      "step": 81000
+    },
+    {
+      "epoch": 12.89,
+      "learning_rate": 1.4138462957831472e-06,
+      "loss": 1.7798,
+      "step": 81500
+    },
+    {
+      "epoch": 12.97,
+      "learning_rate": 1.3858511128784937e-06,
+      "loss": 1.7658,
+      "step": 82000
+    },
+    {
+      "epoch": 13.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 1.5740926265716553,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 52468,
+      "eval_runtime": 677.6429,
+      "eval_samples_per_second": 4.148,
+      "eval_steps_per_second": 1.037,
+      "eval_translation_length": 52468,
+      "step": 82199
     }
   ],
   "logging_steps": 500,
   "max_steps": 126460,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 2.078183784091484e+17,
+  "total_flos": 2.251365766099108e+17,
   "trial_name": null,
   "trial_params": null
 }