Training in progress, step 9140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a26110e7834c1f75bf667cb78a27934275699342535f70d91611de4b759e11f
+oid sha256:66f5cc7dc8a42efe36ea76d8ca34e1a3c950c58533fa878ecad8d052380ac9f8
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9b1ac0cee5529382bf0af2e23e74569e060fdad0a5c8ce28b8a4575e5bbbd4a
+oid sha256:84699a0b76749e08a4088d70c72da5ffb07c2ecf5da72c70b97e96ec7eb934f3
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d92688ab149ae3d2e8540b107e36e29f9346aed504282ef57b5b6880174ef198
+oid sha256:481dc395f467fef8db19044242527752744d919a7271d6ece20ea5b5cd541aa2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8394cc03bc74834b66f0ae2abaadc4e104cc02be3d2024bd053349a26e0c7ddd
+oid sha256:290442ea872222629cafe79f666d304861e371480c9ea6270813c4faff62a31b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7296,
+  "epoch": 0.7312,
   "eval_steps": 500,
-  "global_step": 9120,
+  "global_step": 9140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3199,6 +3199,13 @@
       "learning_rate": 1.7848886898095356e-05,
       "loss": 3.4606,
       "step": 9120
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 31.924890518188477,
+      "learning_rate": 1.7801174965633898e-05,
+      "loss": 3.3977,
+      "step": 9140
     }
   ],
   "logging_steps": 20,
@@ -3206,7 +3213,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.156355597759283e+16,
+  "total_flos": 2.161509406624973e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null