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:fce9930b3ef81cf07c6c211716922123bde2ebe2f244999f5c364b42921c429a
+oid sha256:5cc6c2ed1eb1ec5b321ad5410d2c4185509ffb9cfcfb91c2513387e6f1dc172e
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba6dea2c06ed4c41d0455b04922c1d4f68b51b8e461049fa35b269a3d2cbeb4e
+oid sha256:5f95e0b312634e6aca7a7e49528c17c3928767f6128867838fcca7ab3afe4f28
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b6a158c84ac6a2bb295366e2caae4dfc38a123e092d320dc9f8152b74bc96f
+oid sha256:4789694b0dfbba236adc1e0423cccff54c291754e75185fa5ae6a3664fb3ce4a
 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": 0.20634920634920634,
+  "epoch": 0.4126984126984127,
   "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": 37.805,
       "eval_steps_per_second": 19.602,
       "step": 10
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 4.0556817054748535,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.9843,
+      "step": 15
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 2.6014246940612793,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.1812,
+      "step": 20
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "eval_loss": 3.064946413040161,
+      "eval_runtime": 0.8004,
+      "eval_samples_per_second": 33.732,
+      "eval_steps_per_second": 17.491,
+      "step": 20
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "grad_norm": 2.9831440448760986,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.9105,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 312709170069504.0,
+  "total_flos": 625418340139008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null