Training in progress, step 12000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42041a41037e15a396adf59b761131c6df3212890520ea4b8a81b5e87859bfb
+oid sha256:734ee4c9e61c206c074d233f74a60b28716eecd6eb7198faec82abee52bbec07
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6d9b5f6ace7846f66e54325a83eb4bb1b638fe3304783cceae5d11cc4a2c03
+oid sha256:6ba8301662b7791577a9d1f94fe22dd1ce397d26ecb26dbb9429da528f60b33d
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67afb9ca5ff5dc93d08fbb37308311c5d902249bbda09b3b3f0b514883261a65
+oid sha256:4d1b3417c3dc98ae65d30b31041cbae54929c75379bb3a67c06a4eac3c50dfb9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73ab92407ca5c93876d0a7e59f0176b1954d3d7aa094d297bce73f64e8e4dfa
+oid sha256:a483dedbbda3c5a2d928d5d5361397fb3bbf3b4cab6b12408d8f5a19d03a3d9e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6881217956542969,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-11500",
-  "epoch": 2.53359770874642,
+  "best_metric": 1.6784749031066895,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-12000",
+  "epoch": 2.6437541308658297,
   "eval_steps": 500,
-  "global_step": 11500,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,13 +329,27 @@
       "eval_samples_per_second": 210.252,
       "eval_steps_per_second": 13.155,
       "step": 11500
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.600166666666667e-05,
+      "loss": 1.6854,
+      "step": 12000
+    },
+    {
+      "epoch": 2.64,
+      "eval_loss": 1.6784749031066895,
+      "eval_runtime": 42.7581,
+      "eval_samples_per_second": 212.311,
+      "eval_steps_per_second": 13.284,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 1.1677239982424064e+16,
+  "total_flos": 1.2185798482722816e+16,
   "trial_name": null,
   "trial_params": null
 }