Training in progress, step 480, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a88f4bf7a1b6dddff39e8af97c009fd73b38526759b2a26f6ec08d9b4d183f
+oid sha256:afc3626697f9b8b21110b8ca8aa05f989017e7e572a2ad1c791d8f8de7672958
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c1621a369dc7e4bdf318b29e9869c1af3b08eee35502e0d46b34b86f42bdd0c
+oid sha256:aceadab4673de599001bacd0931786bce2dbbe16d8d14e7b7a5e857b3b4c7b63
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38b8c0c37b77f3baeb6ec8974f233500a56911027cd6d2217e87b0f9c9028ed
+oid sha256:e53efd56a8066289cd7aca225d88c44b543c66b52f0755a9972f2ffab46cccc5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5641c2652ebf9c036c42249768cbb64151dbdde17367e15dd5a080285743b021
+oid sha256:a125a87639fe4cd06b007808fbdba612724f438a0ebfc69a057f80762c8382d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0368,
+  "epoch": 0.0384,
   "eval_steps": 500,
-  "global_step": 460,
+  "global_step": 480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -168,6 +168,13 @@
       "learning_rate": 2.3000000000000003e-05,
       "loss": 3.8172,
       "step": 460
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 26.000978469848633,
+      "learning_rate": 2.4e-05,
+      "loss": 3.8934,
+      "step": 480
     }
   ],
   "logging_steps": 20,
@@ -175,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1091157458190336.0,
+  "total_flos": 1144237424738304.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null