Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e31d7b1c858fa031c87009968672d2dfb8fb635142bd67e0ced27c64ceff9ce
+oid sha256:18d672a1575b1f21621fac1db7adb929e5744de2aabb7381afbc512d8312f215
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:249ef7b8edd3447f694a385ab4371bcb1a4037e241067a3f850540f338450d19
+oid sha256:0b9795985dbbc5d90ddee94d8b261ea5b0d3730d43fe21749ad91acae644263c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17cbebe4a9e2c8ad0c518b56649d7131ed53158aace72f907edc100be5f2ba1a
+oid sha256:b9abf883c2e9c09674e212674962f98f5fa416abc3e528367d43967e85b78711
 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": 0.005399231647803967,
+  "epoch": 0.010798463295607933,
   "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": 17.668,
       "eval_steps_per_second": 8.834,
       "step": 13
+    },
+    {
+      "epoch": 0.008306510227390717,
+      "grad_norm": 0.31124502420425415,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.6846,
+      "step": 20
+    },
+    {
+      "epoch": 0.010798463295607933,
+      "eval_loss": 0.5951049327850342,
+      "eval_runtime": 57.4895,
+      "eval_samples_per_second": 17.638,
+      "eval_steps_per_second": 8.819,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4284339600752640.0,
+  "total_flos": 8568679201505280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null