Training in progress, step 620, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc4a41d5d22b7d0d85455aa32db9e7c97b9166ea007173ae0f8b60ba7996b322
+oid sha256:c92ea041d259fd0f1f97d3d99cc8dcb4a35f0729c4f9cfe1e03af37c28316782
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a60897eab1d7588d260a33b2f1fa0c1b58f193663e391249437e08e9459931
+oid sha256:78a98df909e786b9af2ba1de67522448ec74261759633c6997092bdf4beaab7f
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ab3296562ebe49bf8535f9527f415326e1c9c49a2be5613326da9318c84575
+oid sha256:9c65cd55e2fff96c97e67ca068ed8c714e7c66984dea1333f2e03593c396075d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b87b8c463789ee95efb85f337d13d204d6d893266f8733a46591a2aa7fddc131
+oid sha256:e1ce72457ecdb61a4ff660064d82592f9b16269351060cb691068fea59fdedc2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.048,
+  "epoch": 0.0496,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,13 @@
       "learning_rate": 3e-05,
       "loss": 3.726,
       "step": 600
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 49.25693893432617,
+      "learning_rate": 2.999992132854894e-05,
+      "loss": 3.8692,
+      "step": 620
     }
   ],
   "logging_steps": 20,
@@ -224,7 +231,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1434832198336512.0,
+  "total_flos": 1478300032499712.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null