Training in progress, step 5920, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fed6828ec7857824732422a9380f523d4a261f731255e8724086c998809eb12f
+oid sha256:70e0ffa6186a8d19a1c6a1af2754af73bbde6f3d4b17d0eaa6d63f56b1dcc237
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96485bcca91d9681dbf1765c2fec995608bba06ceae1c7ce1c615957959eb6d1
+oid sha256:b9f6b01c389b88e9bf0fa9b136dc9465beaeaf31a2e306aab9eded42fe708a84
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b24286519e547cddecce5ee08c5603972e0f911b2926a8070867f658fece3cf4
+oid sha256:715d2d6b3ea46b462c5a3d4523172f732bb653b4084281a8a43ddfdca55ee170
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49478f629a8da642b92bfa489a04fa161c3d21da278e9c615a916a5a252b90a0
+oid sha256:a79a21920ea4884fef0686ddc829dd24e9c53857b4d31a716734744f6af5ee77
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.472,
+  "epoch": 0.4736,
   "eval_steps": 500,
-  "global_step": 5900,
+  "global_step": 5920,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2072,6 +2072,13 @@
       "learning_rate": 2.480621158933879e-05,
       "loss": 3.5146,
       "step": 5900
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 34.47429656982422,
+      "learning_rate": 2.476939810755923e-05,
+      "loss": 3.4988,
+      "step": 5920
     }
   ],
   "logging_steps": 20,
@@ -2079,7 +2086,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3958882995175424e+16,
+  "total_flos": 1.4003597454016512e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null