Training in progress, step 6340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c64b2afa3075c63c8b9f594cccb3ee92261843651be4ce842e6f492eeda183
+oid sha256:665884f5884803b9a5bbea0709b82dd7fbb647b93fad77b359888693e9cff352
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d07424ebe3809b342981b7f4601654f56d1e92c48e452c0691c294c5cd8fd1e
+oid sha256:f7ce0ad1ff0c9d0b20bcddceaaa44934a70735779e9f943f3d8229f9c73ef187
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec163df978966f1649bfa7de360f9e162803dced01b76f578e0c72ae9cc60d8
+oid sha256:d629e4cc722d8e87bb022ff0d9602b06aa0cd7b201a1717d04fe682ff20396b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c21c5aa08a74ea5fd586db5a5e4a5db803cbdef83255f0ea8bbf1d608282c0
+oid sha256:1fcd4e201825a35fb3ea0cae13bedc3b38b96d5f8699bf82f679e567b3a62a37
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5056,
+  "epoch": 0.5072,
   "eval_steps": 500,
-  "global_step": 6320,
+  "global_step": 6340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2219,6 +2219,13 @@
       "learning_rate": 2.4012129778456556e-05,
       "loss": 3.5062,
       "step": 6320
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 36.066741943359375,
+      "learning_rate": 2.397324701119233e-05,
+      "loss": 3.6017,
+      "step": 6340
     }
   ],
   "logging_steps": 20,
@@ -2226,7 +2233,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.4934662058835968e+16,
+  "total_flos": 1.4971240651358208e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null