Training in progress, step 460, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1674414802f9fbe588c0e7c80e41a4aee0fa4811a147cf95f3e7209fcf5f367a
+oid sha256:73a88f4bf7a1b6dddff39e8af97c009fd73b38526759b2a26f6ec08d9b4d183f
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3dd7299a79572c367ec3a7034816a83882a521d87f261d46d93c99d9d2ed3e
+oid sha256:3c1621a369dc7e4bdf318b29e9869c1af3b08eee35502e0d46b34b86f42bdd0c
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9711e3d87545bdf48821f9fd5761e262ef9bd1ddc4068a680e4e83b9dc83ad25
+oid sha256:a38b8c0c37b77f3baeb6ec8974f233500a56911027cd6d2217e87b0f9c9028ed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94ba7cf77106ef0a466e3de51efaacf64578702f2e35c780d3a38c5b2f51bb42
+oid sha256:5641c2652ebf9c036c42249768cbb64151dbdde17367e15dd5a080285743b021
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0352,
+  "epoch": 0.0368,
   "eval_steps": 500,
-  "global_step": 440,
+  "global_step": 460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,13 @@
       "learning_rate": 2.2e-05,
       "loss": 3.9554,
       "step": 440
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 33.225223541259766,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 3.8172,
+      "step": 460
     }
   ],
   "logging_steps": 20,
@@ -168,7 +175,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1050707767984128.0,
+  "total_flos": 1091157458190336.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null