Training in progress, step 3500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d806657a3fcb11e861c5e0e2449f115aa999822a821ad28b8314f5dcb5b05f0
+oid sha256:cc2fa15a5e9fc5174a2f2db460995507bf10f8bbf53cd1a2df5dc209c5ea3b39
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a36ff9352357969b0caead584a1f16d63786d1175c0792e23b1a8f7e50981d
+oid sha256:6b5ac68c94586e230c3959acb54f6801fdcc53cbf82147c8780a12f19b5068e1
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c481b4d8439a487e25df91b61940cbb7a1cf50f4dd7c1f0db2cc8fe8f2f6aab1
+oid sha256:a287a7b84031c05a48ea7c5333d8eebf366f57167dc20774be9b71117c6df912
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e1b950837b9d2a345ea077700263f207e496e38d5422ab64b4e4d5b308c780
+oid sha256:cc99e244e20972590fe93655e8af347e514b6b879b75566c51444528a67c5dee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.394014835357666,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-3000",
-  "epoch": 0.6609385327164574,
+  "best_metric": 2.30385422706604,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-3500",
+  "epoch": 0.771094954835867,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,13 +91,27 @@
       "eval_samples_per_second": 212.092,
       "eval_steps_per_second": 13.27,
       "step": 3000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.883366666666667e-05,
+      "loss": 2.5068,
+      "step": 3500
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 2.30385422706604,
+      "eval_runtime": 44.6981,
+      "eval_samples_per_second": 203.096,
+      "eval_steps_per_second": 12.707,
+      "step": 3500
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 3028697986498560.0,
+  "total_flos": 3540439421681664.0,
   "trial_name": null,
   "trial_params": null
 }