Training in progress, step 9160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66f5cc7dc8a42efe36ea76d8ca34e1a3c950c58533fa878ecad8d052380ac9f8
+oid sha256:20f1a714eb67c73b6569a5f7e5dedf54237b0ad2716eb3b0475c33a5c2632e6b
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84699a0b76749e08a4088d70c72da5ffb07c2ecf5da72c70b97e96ec7eb934f3
+oid sha256:9730bd1fd19af1573bb86be461d8d2283246a50b424518f179c57f93b8e62ac4
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481dc395f467fef8db19044242527752744d919a7271d6ece20ea5b5cd541aa2
+oid sha256:626b6a087fd94d790b874f54e98174d3e59d634f407178aef84daa0bee2f4f38
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290442ea872222629cafe79f666d304861e371480c9ea6270813c4faff62a31b
+oid sha256:ff87507bf7d087bfecc1378d173f4afe91a57804efc7c9f721f922c781ee2ed5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7312,
+  "epoch": 0.7328,
   "eval_steps": 500,
-  "global_step": 9140,
+  "global_step": 9160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3206,6 +3206,13 @@
       "learning_rate": 1.7801174965633898e-05,
       "loss": 3.3977,
       "step": 9140
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 32.8968620300293,
+      "learning_rate": 1.775343365017254e-05,
+      "loss": 3.5308,
+      "step": 9160
     }
   ],
   "logging_steps": 20,
@@ -3213,7 +3220,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.161509406624973e+16,
+  "total_flos": 2.166026780786688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null