Training in progress, step 14200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e9cbaceb5831adbecae784c9a136002a89e2a397f162dc5d34feccdcfc1987
+oid sha256:c223a46d77a0541dcf420db07f84a2df91cb6efadc0cbaf5a4f31fc8b2d4bda2
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676264a97b567a751b525fb63caaff00c5c1b3e0b1e4124f1f621f8307e1e6f4
+oid sha256:e22222c7e481af1bfbb43f8dbffa1dee9047bc0752a761bb5f0ff95b2a33adbb
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6698b95ba39be6900dd16f234973145e2e775d4d9ac937bc19752bc4332316f3
+oid sha256:766c0d79e698c319904b5a6e85f8ea9f97dc14779ac45e924ad2fddbd9283585
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd98cac66890d1740350aad97da31e64db12386e28d7f78c3f4d6ac75af4216
+oid sha256:2c6bde81151072c66a172cffde1bbb8230ce11a6a939cceab6c676f6ad133502
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20067078952209785,
+  "epoch": 0.20095382307572562,
   "eval_steps": 500,
-  "global_step": 14180,
+  "global_step": 14200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4970,6 +4970,13 @@
       "learning_rate": 1.0305368692688174e-05,
       "loss": 3.4774,
       "step": 14180
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 23.29683494567871,
+      "learning_rate": 1.0239940674851941e-05,
+      "loss": 3.5437,
+      "step": 14200
     }
   ],
   "logging_steps": 20,
@@ -4977,7 +4984,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.080950876618752e+16,
+  "total_flos": 3.084582491140915e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null