Training in progress, step 8500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01861254ab771cffc2b386bf15a24f0dce4108809ac0a3b9e448682a0173df89
+oid sha256:2f94e35755520a0f7e5cb3e04c51948616dd93f8faed15240eae4cd76ff5701a
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e44646ea0b75089d534d04daec8cb14ccd9715c0e028c529dc9eb895f70bdf6
+oid sha256:22bc33c1b08185780070fb9de3c0e3544d6f1e9ea83ecbe2c1adc475a6cf633b
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb8331a0cb2cb307b39b0da0b470a58555001c978787ebd90623aba530a8dc8
+oid sha256:a131a175c5566e57b28eaa6e2f8992dce40add13d847e57f6cdc32ef74ccde8a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d64a3855d0240351ac941927f8c9f47d17fad44609c69b42750ebc5d867d2437
+oid sha256:87aa9497739f6faf83c415d8ea20f74ba8b21a289f3e19579e4ca76487913fba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.845486044883728,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-8000",
-  "epoch": 1.762502753910553,
+  "best_metric": 1.8124595880508423,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-8500",
+  "epoch": 1.8726591760299627,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,13 +231,27 @@
       "eval_samples_per_second": 205.084,
       "eval_steps_per_second": 12.832,
       "step": 8000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.7167333333333334e-05,
+      "loss": 1.9305,
+      "step": 8500
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.8124595880508423,
+      "eval_runtime": 43.561,
+      "eval_samples_per_second": 208.398,
+      "eval_steps_per_second": 13.039,
+      "step": 8500
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 8137037587808256.0,
+  "total_flos": 8633541568757760.0,
   "trial_name": null,
   "trial_params": null
 }