Training in progress, step 8000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f0f789a8a65f555cbac381aabdb698cee92b2fe07ebc108095baa2a90d444ef
+oid sha256:01861254ab771cffc2b386bf15a24f0dce4108809ac0a3b9e448682a0173df89
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d1c12de2fbb75ae05e3ff6b9fa7b781b5f9f5474ae72073b04c32c555e4508
+oid sha256:1e44646ea0b75089d534d04daec8cb14ccd9715c0e028c529dc9eb895f70bdf6
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c21aaa67f2aaaaed026273975ece0dc213e3ca36aa91a26d2b9fb91e6ab6af
+oid sha256:abb8331a0cb2cb307b39b0da0b470a58555001c978787ebd90623aba530a8dc8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0f66a037624002af5608b72e074eb3a270272f3e059f861a92a97c993094e9
+oid sha256:d64a3855d0240351ac941927f8c9f47d17fad44609c69b42750ebc5d867d2437
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8790709972381592,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-7500",
-  "epoch": 1.6523463317911435,
+  "best_metric": 1.845486044883728,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-8000",
+  "epoch": 1.762502753910553,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,13 +217,27 @@
       "eval_samples_per_second": 205.698,
       "eval_steps_per_second": 12.87,
       "step": 7500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.7334e-05,
+      "loss": 1.9278,
+      "step": 8000
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 1.845486044883728,
+      "eval_runtime": 44.2649,
+      "eval_samples_per_second": 205.084,
+      "eval_steps_per_second": 12.832,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 7620555611308032.0,
+  "total_flos": 8137037587808256.0,
   "trial_name": null,
   "trial_params": null
 }