Training in progress, step 12500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd435d4c565278ca4fe642f0569217eae31db204692f8170a78cc060584eb864
+oid sha256:4ba4172139359a1d497324e8e22e9a06ebeca96155aa0037a8e9fe2bd0bb1861
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f1632c64d76783d8907c3e92a7713d23c2df60b1e1a3079d9b3c7be3413a9f
+oid sha256:669022ae6cb17619adcdc439fe592ba5a330da40a4b03a681212031e9d3c7b25
 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:a5d59de19a41db12fa634f2104bc781b1687cd88f74eced8badd275d850b3566
+oid sha256:5db0dbd26a91dafa09171d3a40d283c5443302ab9d18cc5d9752c39b01fbce28
 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": 3.3832086450540318e-06,
       "loss": 0.317,
       "step": 12000
+    },
+    {
+      "epoch": 2.597672485453034,
+      "grad_norm": 1.4168757200241089,
+      "learning_rate": 2.690495982266556e-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