Training in progress, step 1500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9689b9f0527ef69eaf40c04582a46896dec254a13f9e6543c57ecbe26f9784c
+oid sha256:078d8071521ede112852e855f8810ba95c3f181a89a694ada8beb7269d3fb0ad
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24ebb60a3a9c5fe279068d726787f339228db50963f678eaced9e177c149c9fb
+oid sha256:84a29e30a075284b9ca0004c0fbc0946bc886a09ebab5725f1a735c2e5c00f6b
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4558773c2541a5a022e4ec2e47d3339b64f91f90908327276dc2eb4fefc1ab74
+oid sha256:29c2aa74deb31db2b12469b47a7fce16317bcec2c98e85828fe8c23d20d8ef5a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5bbff6876531d3e6111ff71974a9625b415ff732fa62571778e1d69f33c1ffc
+oid sha256:29da31604d6d4c40d5fac4d688da87a17172e648b9960b502678a992f7f9b1f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.2064383029937744,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-1000",
-  "epoch": 0.2203128442388191,
+  "best_metric": 2.8919074535369873,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-1500",
+  "epoch": 0.3304692663582287,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,13 +35,27 @@
       "eval_samples_per_second": 210.76,
       "eval_steps_per_second": 13.187,
       "step": 1000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.95e-05,
+      "loss": 3.1484,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 2.8919074535369873,
+      "eval_runtime": 42.8255,
+      "eval_samples_per_second": 211.977,
+      "eval_steps_per_second": 13.263,
+      "step": 1500
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 1033641173188608.0,
+  "total_flos": 1527571717423104.0,
   "trial_name": null,
   "trial_params": null
 }