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:d0adc26f05f6db82cb37b3d3148814ffa5dbfbdc39ff75b6bebf3f81ebcf3c5f
+oid sha256:0c529450b6b38e0cee15e5c16a9477919e1146327431559a7f6cb617dccee247
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b34b596e90492ba446476a753a663db3d24c7eecc1dac6f4b2d90b03d67acd5c
+oid sha256:d10898a608cfaffa1bf58cc291da1b1c008a419413621b20950e0448d0ffcef6
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a473e259f90059ec4ed9a7947684705738b607e85a68248a0b3ecc7557ae37
+oid sha256:4e5490d94bb03531bf8be5cc1bbbbb8917faf84a2ab32417656d21a48c1d381f
 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": 0.005145458143677024,
+  "epoch": 0.010290916287354047,
   "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": 12.036,
       "eval_steps_per_second": 6.018,
       "step": 10
+    },
+    {
+      "epoch": 0.005937067088858104,
+      "grad_norm": 0.6631811261177063,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.1461,
+      "step": 15
+    },
+    {
+      "epoch": 0.007916089451810805,
+      "grad_norm": 0.6872115135192871,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.0504,
+      "step": 20
+    },
+    {
+      "epoch": 0.007916089451810805,
+      "eval_loss": 0.9962456226348877,
+      "eval_runtime": 88.4825,
+      "eval_samples_per_second": 12.025,
+      "eval_steps_per_second": 6.012,
+      "step": 20
+    },
+    {
+      "epoch": 0.009895111814763506,
+      "grad_norm": 0.5847287774085999,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.017,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3204170240753664.0,
+  "total_flos": 6613736009760768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null