Training in progress, step 2640, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102a934b9c2b16bd152b8fb45fb756ed8a39ee8f7db8b00ff347bd79c86fbef6
+oid sha256:54c37478ba6579cff2d0646434ea7d1892cb48a4219f90126afbdf7bde329abb
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:352473e3f8f3dae7afcda846881ada181c756f061e5a3d9beb1d4a3e068eeb5d
+oid sha256:8b0e5872ff2188ce6710b4b1015cc3fcaf69768dd90c4fa6ab9ac4aecfb9a52a
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc2667f22c446f99eb24a0261709aeedb26c632fa56415781522ee28f079a36
+oid sha256:27177ac056c4d9dbf19f5cb10b2bae9ee9392da9370d73a04aa8b3b9bc1e770d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b7e6b2fa8982dc42ac672b8fc6e736397d0e1ef6af55fabc97bdaa24968e490
+oid sha256:ea196c4dba55ede2883451624fdfc54856529c0e1f9c30be6a7f36bcba4e1179
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2096,
+  "epoch": 0.2112,
   "eval_steps": 500,
-  "global_step": 2620,
+  "global_step": 2640,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -924,6 +924,13 @@
       "learning_rate": 2.920460247795056e-05,
       "loss": 3.621,
       "step": 2620
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 29.75731086730957,
+      "learning_rate": 2.918891825699857e-05,
+      "loss": 3.6067,
+      "step": 2640
     }
   ],
   "logging_steps": 20,
@@ -931,7 +938,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6207501971718144.0,
+  "total_flos": 6257137317445632.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null