Training in progress, step 36500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0823af30b457b21d03622b0e5ec607830ad3eb4931531ef4e66fdd7b5d848945
+oid sha256:2e283bac3045331af2f920163391dc8270c8abff22512ef1f29e31862dd04a9a
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e560e12102cb30c8844e9201276e5e4411a817ddf7088c208b2d192b75a8786e
+oid sha256:483348c116ccaa7174bd8084c6da2b6cc18ed069290d5dd0d0544d9cf2fd71fb
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c038200f4f8a74c11a8785b8e167d9df1bbab710a7e672e0abeafc1b98201d
+oid sha256:05f5bce689ca8154dc4a1c1b9f0723925cb97784a667d3c397ef5145b037402d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b506a29889e6812ebf3d570fcad99df58085bc924b25685203b74a2b743ec3a
+oid sha256:a00c29dc4dd3aeb804a939b7c86e93b9e46353a7563608b7d4c84d97515cc47e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.357163429260254,
   "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-36000",
-  "epoch": 7.931262392597488,
+  "epoch": 8.041418814716899,
   "eval_steps": 500,
-  "global_step": 36000,
+  "global_step": 36500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1015,13 +1015,27 @@
       "eval_samples_per_second": 199.813,
       "eval_steps_per_second": 12.502,
       "step": 36000
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 7.837666666666666e-06,
+      "loss": 1.218,
+      "step": 36500
+    },
+    {
+      "epoch": 8.04,
+      "eval_loss": 1.3611406087875366,
+      "eval_runtime": 44.5114,
+      "eval_samples_per_second": 203.948,
+      "eval_steps_per_second": 12.761,
+      "step": 36500
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 3.650436910743552e+16,
+  "total_flos": 3.700439463336346e+16,
   "trial_name": null,
   "trial_params": null
 }