Training in progress, epoch 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce9ee458806a62ae72a1e4d5a5acc18de5a23f594846dc936e964bf32d34ebae
+oid sha256:a439bb31358d05c083aec181dc04c10dbb5fcc668174b9ab393917d19d7ebaa3
 size 2371770

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94598a1ea1df407591b98594fea9e8dcf2043b9124d78c0764a36b0a04886f57
+oid sha256:0363553bd2c0b6be1229b2249a2e03d68d4405453c01a0107dc6d001f6d736c9
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21196dd7454f3b651b63e42d3595da46748179b2ded600b1b8e0ecb74a09883
+oid sha256:37187fd0c8eed32cbc388563b490eb72c0ff986800302ec0ab6c19bdf8d63a37
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686749d972d4e90f466b72f5a04d569779ab107826b090f5c435d2ae6efde530
+oid sha256:fde980dad26ff75414ed06027ec8ba5e7d484abbe46896b9304dc37a9238984f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.215216636657715,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-14229",
-  "epoch": 9.0,
+  "best_metric": 2.214895725250244,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-15810",
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 14229,
+  "global_step": 15810,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -346,13 +346,50 @@
       "eval_steps_per_second": 0.605,
       "eval_translation_length": 52546,
       "step": 14229
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 5.784166422325311e-05,
+      "loss": 2.0341,
+      "step": 14500
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 5.534019366928e-05,
+      "loss": 2.0094,
+      "step": 15000
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 5.282512040728659e-05,
+      "loss": 2.0032,
+      "step": 15500
+    },
+    {
+      "epoch": 10.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.214895725250244,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 52363,
+      "eval_runtime": 584.3355,
+      "eval_samples_per_second": 4.811,
+      "eval_steps_per_second": 0.602,
+      "eval_translation_length": 52363,
+      "step": 15810
     }
   ],
   "logging_steps": 500,
   "max_steps": 31620,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.558637838068613e+17,
+  "total_flos": 1.7318198200762368e+17,
   "trial_name": null,
   "trial_params": null
 }