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:b6fdea5eb4709962716e2f6f51911aecdbd042b385cc7338f78f04e4ed53590f
+oid sha256:accc1d39d426e757618983ac9121c0083a5375257be7b9f22c2cf69f0f144f24
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90a166b4e6f704cd055238b1c5849bb5b177589f34d0a299f7269ade66462766
+oid sha256:b3126f1b97ee2c2e2f26e720510f2cee0092ace840d159584189a7b4878a05ea
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
+oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
 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": 0.00025353362489700194,
+  "epoch": 0.0005070672497940039,
   "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": 15.886,
       "eval_steps_per_second": 7.943,
       "step": 10
+    },
+    {
+      "epoch": 0.0002925387979580792,
+      "grad_norm": 18.491188049316406,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 10.0615,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003900517306107723,
+      "grad_norm": 20.197280883789062,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 8.5525,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003900517306107723,
+      "eval_loss": 2.060377597808838,
+      "eval_runtime": 1351.5612,
+      "eval_samples_per_second": 15.974,
+      "eval_steps_per_second": 7.987,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004875646632634653,
+      "grad_norm": 21.58411979675293,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 8.0305,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2278470721732608.0,
+  "total_flos": 4556941443465216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null