Training in progress, step 12500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64dbcf237fae8369f55b23d09ee7ff302b4305e95230470792806d4f5beaefce
+oid sha256:7e82e347b2238a2124e52fa6bbcb52a581a8376f642371fa693a2b74ccf64bbc
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471516a79c1d1bce2d7f0221facbc27273c25803ac0ef5c4f6871e9e4d64cf86
+oid sha256:59483524ed5516cde7ebadc084d889b4039cb25a2ec01036cddccb6c62e4b263
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f26f933cd5a30682ad42a3de6cd890f8aaa49723c34ab9ccdf6d24b30e628d
+oid sha256:6f3dfe1e2f7f2fd5854887c0faffeef0e864d418e8da96df789b7b060dfeefbe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f7c983c5137eb206988110c9b1855bdf7c8f7f5f71b7c6884401c6871ab55a9
+oid sha256:581f26c042b017b35232c26ec1300c4f70bffc2cf5f6d147680616274578d17d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.493765586034913,
+  "epoch": 2.597672485453034,
   "eval_steps": 500,
-  "global_step": 12000,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,6 +191,13 @@
       "learning_rate": 3.381823219728457e-06,
       "loss": 0.3168,
       "step": 12000
+    },
+    {
+      "epoch": 2.597672485453034,
+      "grad_norm": 1.3090420961380005,
+      "learning_rate": 2.6891105569409807e-06,
+      "loss": 0.3176,
+      "step": 12500
     }
   ],
   "logging_steps": 500,
@@ -210,7 +217,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.461377145765888e+16,
+  "total_flos": 1.522272934821888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null