Training in progress, step 23500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0266a8a3dca96a0991e0f8227b776b2465d53b4076610920fe55fa400b73d62
+oid sha256:f0c4faa2315e68aa9aea8ea99bb2ce367fbb61bde3da5ac200e2a9601bc7fdcd
 size 5125261

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6098cf86a2c326970b5ec5b98d6cb81beaafbfd692923f7910d181cd4b211c7a
+oid sha256:03c6e120c754988f10077d7886fae6ca428ecc92c6e4f302cac26741ece4630f
 size 2460465086

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313b59c81cd481a9990bc3df1bc6d8537b8c373ab865f11fdeeb77db5cb8489b
+oid sha256:f65df4ff749405790486e5ba9c1d8d7e5606bcfbf44b567be6002269b26a798d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a532235df6adca43705297d05a00b0238294408e024df73149fee8663d9f9c8c
+oid sha256:e1a9a8aa5348c19db1b2ca4d9c95314dfb4a9f0d11c59d3aa91c8287dfe0af6b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.452415108680725,
-  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-22500",
-  "epoch": 5.06719541749284,
+  "best_metric": 1.4470324516296387,
+  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-23500",
+  "epoch": 5.17735183961225,
   "eval_steps": 500,
-  "global_step": 23000,
+  "global_step": 23500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -651,13 +651,27 @@
       "eval_samples_per_second": 202.816,
       "eval_steps_per_second": 12.69,
       "step": 23000
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 1.2169333333333336e-05,
+      "loss": 1.3704,
+      "step": 23500
+    },
+    {
+      "epoch": 5.18,
+      "eval_loss": 1.4470324516296387,
+      "eval_runtime": 45.0353,
+      "eval_samples_per_second": 201.575,
+      "eval_steps_per_second": 12.612,
+      "step": 23500
     }
   ],
   "logging_steps": 500,
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 2.3353667300622336e+16,
+  "total_flos": 2.3852778579296256e+16,
   "trial_name": null,
   "trial_params": null
 }