Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37c5abec758a6a1d60531ea9ab1e9f895f3a845d976ec6afa20d636107215337
+oid sha256:91bb03afe31ff738bd0eace4501a9dc88586f3b6a8717cd5301ea09d46c11152
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:885339dafe08f64bbc3eb820fa3f6df3505881ed13b2ac07fe16f35afadf0598
+oid sha256:3dc9234cb05ae2135b2fc67bb3771616fcba4bc172d1a6cb905f4a40e22391cc
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0154a27a40600d0a754c771567ba022a68f11c88e563865cb34b236853a15a9c
+oid sha256:5142478ccedbfc68fb5a8ce2ba3458c7b6a5ae64269d4450a1c5a497edd79236
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a32869ab546757070fb9f1228e165e54f415c129174bc47db03ac5a199f7222
+oid sha256:f190edae933ae376a7b265d8d0dc37867b70f47e329e822be82903912064f125
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.225291589932474,
+  "epoch": 2.3020257826887662,
   "eval_steps": 500,
-  "global_step": 14500,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -201,13 +201,19 @@
       "learning_rate": 0.0005550951503990178,
       "loss": 0.5353,
       "step": 14500
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.0005397483118477594,
+      "loss": 0.5289,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 7686247000571904.0,
+  "total_flos": 7952726548807680.0,
   "trial_name": null,
   "trial_params": null
 }