Training in progress, step 520, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313aba40d65f377c286df07926609c388e7a57dab3c6547cc67866d2fa6580e7
+oid sha256:5a5bbafb92274fe73c656e68ae815c74026d14d6c752004391586ec62c0617ca
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf2e4db48d199e348f95d4a0546bf60cade1749a871623b7819d7780f9cbf26
+oid sha256:2a7f4e516bbee85e2efd4ebaf8cbcad8f26f7ac5fd68acc0e1b8d6076617c481
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97adf2d219717b72b639009fa1340825517d95c4424c6ddd24efbfb53c1ae67
+oid sha256:f841c8c705374da539163e3f8b292003c9f867c36cc43bc718b2a7996192a2c0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46969ffbcb8cc5047d9170dfd926cf7206d745881d80bf65b9ce06c9c4e5194d
+oid sha256:ddb11d96a8b6173e10af5190423ae3f7ff04e92efd4a5a946800f7520b5b8483
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04,
+  "epoch": 0.0416,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,13 @@
       "learning_rate": 2.5e-05,
       "loss": 3.9194,
       "step": 500
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 28.721248626708984,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 3.8144,
+      "step": 520
     }
   ],
   "logging_steps": 20,
@@ -189,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1194824141930496.0,
+  "total_flos": 1248724256292864.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null