Training in progress, step 12500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:734ee4c9e61c206c074d233f74a60b28716eecd6eb7198faec82abee52bbec07
+oid sha256:78d6f18043997ba6c5f72b35d08e7d9d57cff6dfa6353fa46313d842ab92f74b
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba8301662b7791577a9d1f94fe22dd1ce397d26ecb26dbb9429da528f60b33d
+oid sha256:c0edd5c4bcf31ae78ac35f08ba69a78253a15627cb942b130989c2f3625a36c7
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1b3417c3dc98ae65d30b31041cbae54929c75379bb3a67c06a4eac3c50dfb9
+oid sha256:7ca1555f29260587b9e25d9a2345c989e19c723ac7e9da97a1c81769d1a479f0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a483dedbbda3c5a2d928d5d5361397fb3bbf3b4cab6b12408d8f5a19d03a3d9e
+oid sha256:9e18a5aa14a087ff69df53418c23cd916d7aa2a72db184ecee6ea1072f8f7dde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6784749031066895,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-12000",
-  "epoch": 2.6437541308658297,
+  "best_metric": 1.6570212841033936,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-12500",
+  "epoch": 2.7539105529852392,
   "eval_steps": 500,
-  "global_step": 12000,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,13 +343,27 @@
       "eval_samples_per_second": 212.311,
       "eval_steps_per_second": 13.284,
       "step": 12000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.5835e-05,
+      "loss": 1.6603,
+      "step": 12500
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 1.6570212841033936,
+      "eval_runtime": 42.6669,
+      "eval_samples_per_second": 212.765,
+      "eval_steps_per_second": 13.312,
+      "step": 12500
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 1.2185798482722816e+16,
+  "total_flos": 1.269127563116544e+16,
   "trial_name": null,
   "trial_params": null
 }