Training in progress, step 14000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86cfbda9500d9fa815610ac526e15ac59017c011ab852a8d213fe369e2c87264
+oid sha256:08e62e1d907de6e13703c06269ae211079a067af431e84171420afebacc1db1e
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797b0c667f1da4b858bbb1ee44c67e059568d00802694b682626ab1637074e27
+oid sha256:6f06f09e6735c2c42525ec8cdb3cc7f28944ed4e48bee00a36ef6bd2ec390875
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e94687f2321daa5ab010d3ad0f01731437e5893f8fb090bda50165155ecfbd
+oid sha256:7d6b752ded1d95c4c9060fd0d8e2103d4197782abf53ce90c1e09961db418400
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bad3162e73fe33bc16c82c735842e363e840b493e85ecb0197fcc604f79f916
+oid sha256:fe789f43fc2c6f3714ad5234e7fa28d162538759dd048ff1df0690fb4b7c5e82
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6240772008895874,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-13500",
-  "epoch": 2.9742233972240584,
+  "best_metric": 1.6128900051116943,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-14000",
+  "epoch": 3.084379819343468,
   "eval_steps": 500,
-  "global_step": 13500,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -385,13 +385,27 @@
       "eval_samples_per_second": 209.98,
       "eval_steps_per_second": 13.138,
       "step": 13500
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.5335e-05,
+      "loss": 1.5917,
+      "step": 14000
+    },
+    {
+      "epoch": 3.08,
+      "eval_loss": 1.6128900051116943,
+      "eval_runtime": 42.9712,
+      "eval_samples_per_second": 211.258,
+      "eval_steps_per_second": 13.218,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 1.3701383402815488e+16,
+  "total_flos": 1.4186984138735616e+16,
   "trial_name": null,
   "trial_params": null
 }