Training in progress, epoch 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8e033f8dea1d357ffe6629c15f19815f5e32cd70953d97be45fc17aa0912ae
+oid sha256:bd19122e1b6607cdb79a7016978319f5233648dfa21d17f64f4c5ed9ebfab2b1
 size 2371770

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d868b832fd968e13a3ef455165a190aba8506b04ef6b945c6e766f7ee84d1f
+oid sha256:20f9eff7f8c80652672f33d591daec33e74fa91afea6f63662fcce0b413fc45e
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525e460409507e49b218a1b42d06d85873c630a5ed78eb21f16030edb00fde0c
+oid sha256:b21196dd7454f3b651b63e42d3595da46748179b2ded600b1b8e0ecb74a09883
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d507458213a337e4449ea78916d032601a9ab5585183fda8bd21d6d89f7d231
+oid sha256:429bbb7d8273481822c70b354c32cf6b2c09f778063e5299935515e96827f77b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.8215827941894531,
   "best_model_checkpoint": "dq158/pingusPongus/checkpoint-3162",
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 25296,
+  "global_step": 28458,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -459,13 +459,68 @@
       "eval_steps_per_second": 0.605,
       "eval_translation_length": 52579,
       "step": 25296
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 3.283962902837673e-05,
+      "loss": 1.8288,
+      "step": 25500
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 3.22428902702372e-05,
+      "loss": 1.7989,
+      "step": 26000
+    },
+    {
+      "epoch": 8.38,
+      "learning_rate": 3.164161167838985e-05,
+      "loss": 1.795,
+      "step": 26500
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 3.103617013343307e-05,
+      "loss": 1.7786,
+      "step": 27000
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 3.0426945125298563e-05,
+      "loss": 1.7924,
+      "step": 27500
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 2.9814318515387547e-05,
+      "loss": 1.8087,
+      "step": 28000
+    },
+    {
+      "epoch": 9.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 1.8519303798675537,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 52432,
+      "eval_runtime": 580.9392,
+      "eval_samples_per_second": 4.839,
+      "eval_steps_per_second": 0.606,
+      "eval_translation_length": 52432,
+      "step": 28458
     }
   ],
   "logging_steps": 500,
   "max_steps": 63240,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.3854558560609894e+17,
+  "total_flos": 1.558637838068613e+17,
   "trial_name": null,
   "trial_params": null
 }