Training in progress, step 540, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a5bbafb92274fe73c656e68ae815c74026d14d6c752004391586ec62c0617ca
+oid sha256:7042f9ed08ad702b4807e2082f62b7c77edad4356283c5cfef4c2ac8b3b06034
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a7f4e516bbee85e2efd4ebaf8cbcad8f26f7ac5fd68acc0e1b8d6076617c481
+oid sha256:ea2f7979011099fe7dff43f9cdaa7c8c71ecebd10fcfa3e69aea88e5fe4630df
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f841c8c705374da539163e3f8b292003c9f867c36cc43bc718b2a7996192a2c0
+oid sha256:cad5804f88e56590ede594cde634ed7edf004b94b62834acab77d105f3c4294b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddb11d96a8b6173e10af5190423ae3f7ff04e92efd4a5a946800f7520b5b8483
+oid sha256:8954cfae79acdcb584a4c2168efc0e60ef154434502bd57627e490c360dd8a90
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0416,
+  "epoch": 0.0432,
   "eval_steps": 500,
-  "global_step": 520,
+  "global_step": 540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,13 @@
       "learning_rate": 2.6000000000000002e-05,
       "loss": 3.8144,
       "step": 520
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 24.934555053710938,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 3.9166,
+      "step": 540
     }
   ],
   "logging_steps": 20,
@@ -196,7 +203,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1248724256292864.0,
+  "total_flos": 1299081332097024.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null