Training in progress, step 9180, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f1a714eb67c73b6569a5f7e5dedf54237b0ad2716eb3b0475c33a5c2632e6b
+oid sha256:02c9055a738b9a9de575613a1a5580636f05db397ca77f53fdf338e8870afd3d
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9730bd1fd19af1573bb86be461d8d2283246a50b424518f179c57f93b8e62ac4
+oid sha256:147d3fa875f4ec20c612e78f064b3f808bdb35a6690922445f61b72afc32af1d
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:626b6a087fd94d790b874f54e98174d3e59d634f407178aef84daa0bee2f4f38
+oid sha256:39bf8edf039f594951035ab5637656bd85129b21b01c61e9ca4cb4fb949b5b72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff87507bf7d087bfecc1378d173f4afe91a57804efc7c9f721f922c781ee2ed5
+oid sha256:ffeb4e9a55740f59ac2f34810ad1181abbaa2cb8f6beeff3a39a90a1c460800d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7328,
+  "epoch": 0.7344,
   "eval_steps": 500,
-  "global_step": 9160,
+  "global_step": 9180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3213,6 +3213,13 @@
       "learning_rate": 1.775343365017254e-05,
       "loss": 3.5308,
       "step": 9160
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 23.338972091674805,
+      "learning_rate": 1.77056634524951e-05,
+      "loss": 3.5206,
+      "step": 9180
     }
   ],
   "logging_steps": 20,
@@ -3220,7 +3227,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.166026780786688e+16,
+  "total_flos": 2.1709115811692544e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null