Training in progress, step 2960, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae4eed7cd394c61aa3c6ecdd8052158a478064360315d029f17e32256eeee681
+oid sha256:38f3ea2e710f0123cd317966daf5b272ed615e4c14e337828c2d49a95e7b8e06
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55110cd9ffb93b3104fa143dc8570104252d530b5877a1e1f6fcf5027bc6942a
+oid sha256:17331faf06503e7a590d855b1e16fe6253841ce13f64d11a95d99f09a89b197b
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd1bd04e105a77373055d2926a8c85b9996ff31aefddd05f3540ecf3ddcf98d
+oid sha256:ea602ef2e312790e8849d1db4637c3556e36e10604ffe460922bf490e4a189ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5833769099940ec8d804fcc38926afe248b7045a909e8f61b7a28f1965f42d1c
+oid sha256:f1976d584552c3d9a749942a954e8edac0eb73a5bcb3e8631cd101d6b353e1f8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2352,
+  "epoch": 0.2368,
   "eval_steps": 500,
-  "global_step": 2940,
+  "global_step": 2960,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1036,6 +1036,13 @@
       "learning_rate": 2.8935890574033325e-05,
       "loss": 3.6372,
       "step": 2940
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 24.437808990478516,
+      "learning_rate": 2.8917845792248085e-05,
+      "loss": 3.5737,
+      "step": 2960
     }
   ],
   "logging_steps": 20,
@@ -1043,7 +1050,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6949309266886656.0,
+  "total_flos": 6996976257859584.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null