Training in progress, step 24000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c4faa2315e68aa9aea8ea99bb2ce367fbb61bde3da5ac200e2a9601bc7fdcd
+oid sha256:75521d5c95e544b58efe27cae1b05613913aedb7fb3fd2587b30541c6ea79d39
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c6e120c754988f10077d7886fae6ca428ecc92c6e4f302cac26741ece4630f
+oid sha256:f19a935d1c6fe49a12b4c8670f0d53c68e7416233abaeeeaddb7185cdbbbef01
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65df4ff749405790486e5ba9c1d8d7e5606bcfbf44b567be6002269b26a798d
+oid sha256:f138f3ad6bdd935027bc7a15fa8f66489c34e9ca83573106addf32330e6c5fd4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a9a8aa5348c19db1b2ca4d9c95314dfb4a9f0d11c59d3aa91c8287dfe0af6b
+oid sha256:e7089430075c4f4f179c1dba9dd54566fc41d7a7f96f6a8b86e296aa305360f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4470324516296387,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-23500",
-  "epoch": 5.17735183961225,
+  "best_metric": 1.4429727792739868,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-24000",
+  "epoch": 5.287508261731659,
   "eval_steps": 500,
-  "global_step": 23500,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -665,13 +665,27 @@
       "eval_samples_per_second": 201.575,
       "eval_steps_per_second": 12.612,
       "step": 23500
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 1.2003e-05,
+      "loss": 1.3672,
+      "step": 24000
+    },
+    {
+      "epoch": 5.29,
+      "eval_loss": 1.4429727792739868,
+      "eval_runtime": 48.0671,
+      "eval_samples_per_second": 188.861,
+      "eval_steps_per_second": 11.817,
+      "step": 24000
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 2.3852778579296256e+16,
+  "total_flos": 2.4362217465839616e+16,
   "trial_name": null,
   "trial_params": null
 }