Training in progress, step 6540, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab44c0650fc35117528c103709aeefeda1ba5a0c1b201a042c443fced883ac06
+oid sha256:d30cf0270ab7eb3471153a28d31eec5ab87afc18c35880c0689d7b33e9ccec01
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f8827e725054a7d3aa47b66a00e417f27bf58195e5d53d80134e98a97b930d
+oid sha256:15270cb1bec565741ee825e92d321439b45a02901ba1581ae9722a89f84ea419
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:966b1d0c91c0efe2171d6c761e8fb3dd8dd23b43cb7c345758210f8c5726e8a5
+oid sha256:3334f41707da2f1f3b6ff0afd38e2f3ea20e604b3409a23e240e2d1711a472d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9c2686d4c99776f5194741a1ee501ae1a6b12f42eb0cf041ec1c8a8c483c5a
+oid sha256:5d3da2849decc3d12a1c67a143710f26acee85daa0e821364144220b5cf57d3c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5216,
+  "epoch": 0.5232,
   "eval_steps": 500,
-  "global_step": 6520,
+  "global_step": 6540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2289,6 +2289,13 @@
       "learning_rate": 2.361911574288736e-05,
       "loss": 3.5952,
       "step": 6520
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 41.03891372680664,
+      "learning_rate": 2.3579310239743776e-05,
+      "loss": 3.5194,
+      "step": 6540
     }
   ],
   "logging_steps": 20,
@@ -2296,7 +2303,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.539204209197056e+16,
+  "total_flos": 1.5443350539239424e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null