Training in progress, step 5940, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e0ffa6186a8d19a1c6a1af2754af73bbde6f3d4b17d0eaa6d63f56b1dcc237
+oid sha256:608a6b07ab17338bd6282af158218a38aaf660c765e9d6ab6b3901cfdb0f98b7
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9f6b01c389b88e9bf0fa9b136dc9465beaeaf31a2e306aab9eded42fe708a84
+oid sha256:21a7d513c9296103d22d55f32962fde622c0d973a7f373aa4a9c0fe2c3f05177
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:715d2d6b3ea46b462c5a3d4523172f732bb653b4084281a8a43ddfdca55ee170
+oid sha256:e0127f56f128ab49d16717c9bb322e33079e0546dc1e679e0ba07a312af3b19a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79a21920ea4884fef0686ddc829dd24e9c53857b4d31a716734744f6af5ee77
+oid sha256:14f5d4d06571f17a13a7fb5f8c4d4c26d3ffcd4700c7abd904f5f1753c1fd7ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4736,
+  "epoch": 0.4752,
   "eval_steps": 500,
-  "global_step": 5920,
+  "global_step": 5940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2079,6 +2079,13 @@
       "learning_rate": 2.476939810755923e-05,
       "loss": 3.4988,
       "step": 5920
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 27.388093948364258,
+      "learning_rate": 2.4732482149416325e-05,
+      "loss": 3.4577,
+      "step": 5940
     }
   ],
   "logging_steps": 20,
@@ -2086,7 +2093,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.4003597454016512e+16,
+  "total_flos": 1.4047360541392896e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null