Training in progress, step 6320, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d9867527ada8f06b3d5b4a3b1a084c5587bf5d24b8f6abb3243ac9e5ecc1bb
+oid sha256:58c64b2afa3075c63c8b9f594cccb3ee92261843651be4ce842e6f492eeda183
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:664614e14cc5551b8f4f79a692c8c7ab8b97cdcef757ae57c283fec6b60fca8b
+oid sha256:9d07424ebe3809b342981b7f4601654f56d1e92c48e452c0691c294c5cd8fd1e
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe631caac525a44feb552772252434ef5806653f82e9cba96375efa0ad983cd3
+oid sha256:8ec163df978966f1649bfa7de360f9e162803dced01b76f578e0c72ae9cc60d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8ab3807f200a849a139d1332c1073c145c9a442b57cd4342cee505d555158f
+oid sha256:27c21c5aa08a74ea5fd586db5a5e4a5db803cbdef83255f0ea8bbf1d608282c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.504,
+  "epoch": 0.5056,
   "eval_steps": 500,
-  "global_step": 6300,
+  "global_step": 6320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2212,6 +2212,13 @@
       "learning_rate": 2.405091801274387e-05,
       "loss": 3.4403,
       "step": 6300
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 67.38970184326172,
+      "learning_rate": 2.4012129778456556e-05,
+      "loss": 3.5062,
+      "step": 6320
     }
   ],
   "logging_steps": 20,
@@ -2219,7 +2226,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.4891030195109888e+16,
+  "total_flos": 1.4934662058835968e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null