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:a43af787d66cafe47166b2d91b45514d82e4278044fa2fbae7f0473a8aab0575
+oid sha256:ad07adb276a8e9b4dcb4f0d92035573b16dc7272a6fc8621d0b8551f3a3317b1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47cab627beb4219809625c833f1f3b7d89047ce16bef0f6834367986a3a2d615
+oid sha256:68cb5565f724a13e4984bc66eda84755bcdfd566ae44de65e77f502e24dce74c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d07536b63a31f2c979a9b82bde7091c4a53609c4df276d525fe712871c250a
+oid sha256:3fbfb2ebc436a787250427a55096ccac8da31c15076b6ad72f8489e64c6ccbd5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e92785679980f3fcd23b14ce1acaffcae115e3e9164492d0e4b31775d32447
+oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01951951951951952,
+  "epoch": 0.03903903903903904,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 35.188,
       "eval_steps_per_second": 17.657,
       "step": 13
+    },
+    {
+      "epoch": 0.03003003003003003,
+      "grad_norm": 1.4663447141647339,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.904,
+      "step": 20
+    },
+    {
+      "epoch": 0.03903903903903904,
+      "eval_loss": 0.6685091853141785,
+      "eval_runtime": 8.0321,
+      "eval_samples_per_second": 34.985,
+      "eval_steps_per_second": 17.555,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2117353076686848.0,
+  "total_flos": 4234706153373696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null