Training in progress, step 10000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e37398efecfa3a31fa90b80a74744bf27a7183ee5d4b65c685a5acdc3be7f0c
+oid sha256:cea00316da1c8f63aaa2de1ceaf91821f3db54f71f78e8220f3e1265f6201ad7
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b7c4a518cf111b1c1ae82d83f0790046a80ecb9f506077dde0b8959de1497a
+oid sha256:477ec5f93f0ad72365d6b35782bc367a2fca572cd844f6b7fa2610751aa2cee2
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a681cb81ca789c9210dcd3266ce27b1c3b6bb899f13d0d4066b3e586a60fbf
+oid sha256:1ac9d511320285bef7302e4056eb37000e8aeae756cc08f22e2178e60ff35dfb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997004fc2025eb75b5ff10923663d4eaa8001c2bf3733fe3f3d04ebec9bd4bc6
+oid sha256:6f92250a16f6988661c4190515cb8f66eef5cd0a0b7750f2f308074764b56b87
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7763384580612183,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-9500",
-  "epoch": 2.092972020268782,
+  "best_metric": 1.7431403398513794,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-10000",
+  "epoch": 2.2031284423881914,
   "eval_steps": 500,
-  "global_step": 9500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,13 +273,27 @@
       "eval_samples_per_second": 208.534,
       "eval_steps_per_second": 13.048,
       "step": 9500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.6668e-05,
+      "loss": 1.808,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2,
+      "eval_loss": 1.7431403398513794,
+      "eval_runtime": 43.6327,
+      "eval_samples_per_second": 208.055,
+      "eval_steps_per_second": 13.018,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 9638739494043648.0,
+  "total_flos": 1.0154137918242816e+16,
   "trial_name": null,
   "trial_params": null
 }