Training in progress, step 3840, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175377434e91570ba0503cb65b60e3da93186545522c2fe8072ad4cc8b11275e
+oid sha256:284042f1664a5796615aa283febe817ed9e49a8af41551fb6e661f390d511bb2
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768b6f828e5f45d19ac1fea1d9cc18f4468112696b9a0b5239c51d6f4ee1b726
+oid sha256:36269b05883f5a51c6e5f370a57e8ab0a53a3683048108ce6371f0858331fb8e
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bcda82f0545371c86a78ab3eaa83186230c2a6cfed788aa4c35cfa1861b4374
+oid sha256:64281a3ad73d5aa5ef7c55a19c53eff35be3d66177b7da19a80778210370534c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af880d0b17024d5002dcef5b391f000f9d2ae4a7c243ef221f8d5830189586bf
+oid sha256:e0ccc7acb86aed79d55cdf455a4f5517a63d1b5c4b0d0db16d89e38b3a587e58
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3056,
+  "epoch": 0.3072,
   "eval_steps": 500,
-  "global_step": 3820,
+  "global_step": 3840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1344,6 +1344,13 @@
       "learning_rate": 2.8006544540078535e-05,
       "loss": 3.5414,
       "step": 3820
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 33.06633758544922,
+      "learning_rate": 2.798227659988717e-05,
+      "loss": 3.5586,
+      "step": 3840
     }
   ],
   "logging_steps": 20,
@@ -1351,7 +1358,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 9011193678200832.0,
+  "total_flos": 9053775752724480.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null