Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f27336794f76d308ce9c9d9b430a151168841c2efa2d4648b2820d2ebb1f4415
+oid sha256:608e4adb16671b13d0d92c3024754eb47d06a13e14a2f00539e8e3180cf5fc54
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90bc8c9cdddb40956375b8bf8cecbe53f327a110a851dd5d6714152ec98678d9
+oid sha256:f08779c51122cff9fc724f36fd3d6b016f56700d308ee07e024f11dab3cc0228
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22eb049858741d0446f5141132cbaa4a21e005113ef62d567590227c7e5fb963
+oid sha256:b48b39a0e824b1a3c18c1be18c454fa0b89a07e7ba413d8629bdab8b716f86c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003070763379965631,
+  "epoch": 0.0006141526759931262,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 16.141,
       "eval_steps_per_second": 8.07,
       "step": 10
+    },
+    {
+      "epoch": 0.0003543188515344959,
+      "grad_norm": 1.313326358795166,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.451,
+      "step": 15
+    },
+    {
+      "epoch": 0.00047242513537932787,
+      "grad_norm": 1.3732658624649048,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.1585,
+      "step": 20
+    },
+    {
+      "epoch": 0.00047242513537932787,
+      "eval_loss": 2.032883882522583,
+      "eval_runtime": 1099.1405,
+      "eval_samples_per_second": 16.218,
+      "eval_steps_per_second": 8.109,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005905314192241598,
+      "grad_norm": 1.797598958015442,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.0492,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1988618012590080.0,
+  "total_flos": 4059240891678720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null