Training in progress, epoch 3, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2896b0e460b13c2fcb39e49f7ec060b7d02a1b79070d233b61c37b5e93e48b1
+oid sha256:3185710f9ed48293a778de595fcd38098844825122d64b9829b1b93f6412f403
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd01c67e5e0fe606bcdfc36e0a412aebf6cbd94293880ad793ae83f99af331a7
+oid sha256:e6d9360daf7120c5d39d8ef5625d204b3b6837a8189e798928f762e83a610468
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0e56207d1824629ca039d98adaf43ba52dfd5027a5104848867cc2184fbaab7
+oid sha256:bbddb6a0f6f63e14b35b515dcd6478e86f1cce79a693afe0ccaec7cdbe6f4fcc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a5465fff9c19a1cb7746395473101a537f837442799282a6bd4b367fce7e095
+oid sha256:727027b6d6031aa8f34a43940937c6f906ae36c7156fab65320547a0006b7c81
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.835176944732666,
   "best_model_checkpoint": "dq158/morbius/checkpoint-9568",
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 19136,
+  "global_step": 28704,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,13 +273,146 @@
       "eval_steps_per_second": 1.314,
       "eval_translation_length": 104272,
       "step": 19136
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 2.9619565217391305e-05,
+      "loss": 1.9566,
+      "step": 19500
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 2.9096989966555184e-05,
+      "loss": 1.9582,
+      "step": 20000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 2.8574414715719066e-05,
+      "loss": 1.9681,
+      "step": 20500
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 2.8051839464882945e-05,
+      "loss": 1.9374,
+      "step": 21000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.7529264214046824e-05,
+      "loss": 1.9412,
+      "step": 21500
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.7006688963210703e-05,
+      "loss": 1.9557,
+      "step": 22000
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.6484113712374582e-05,
+      "loss": 1.9684,
+      "step": 22500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.5961538461538464e-05,
+      "loss": 1.9307,
+      "step": 23000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.5438963210702343e-05,
+      "loss": 1.9237,
+      "step": 23500
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 2.491638795986622e-05,
+      "loss": 1.9608,
+      "step": 24000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 2.43938127090301e-05,
+      "loss": 1.9549,
+      "step": 24500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 2.3871237458193983e-05,
+      "loss": 1.9211,
+      "step": 25000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.334866220735786e-05,
+      "loss": 1.9698,
+      "step": 25500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.282608695652174e-05,
+      "loss": 1.9413,
+      "step": 26000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.230351170568562e-05,
+      "loss": 1.9943,
+      "step": 26500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.1780936454849498e-05,
+      "loss": 1.938,
+      "step": 27000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.125836120401338e-05,
+      "loss": 1.987,
+      "step": 27500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.073578595317726e-05,
+      "loss": 1.9455,
+      "step": 28000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.0213210702341138e-05,
+      "loss": 1.9788,
+      "step": 28500
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 0.08712036412034174,
+      "eval_brevity_penalty": 0.7810596870491452,
+      "eval_length_ratio": 0.8018579316519923,
+      "eval_loss": 1.8364616632461548,
+      "eval_precisions": [
+        0.1853626762201647,
+        0.1156396502935338,
+        0.08657517535834096,
+        0.08341024457775727
+      ],
+      "eval_reference_length": 134020,
+      "eval_runtime": 809.3386,
+      "eval_samples_per_second": 15.762,
+      "eval_steps_per_second": 1.315,
+      "eval_translation_length": 107465,
+      "step": 28704
     }
   ],
   "logging_steps": 500,
   "max_steps": 47840,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.5722850521029018e+17,
+  "total_flos": 2.3584275781543526e+17,
   "trial_name": null,
   "trial_params": null
 }