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:c059316f7641b3327527334eb124fb722ea96436ac4c27732bd4aab3b748076b
+oid sha256:ab451d99f204b710ac87131c42b4729112f9ea3a2241b2e58602309965a25935
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3a546bb0b534c206b9be2bb896ebfa6a626193c1ff28652bbd59d67b17957a
+oid sha256:afd6cf917cd7b543db680d7e184b5c31c94f84ea69b85289b6fbe8a8f94c4aa2
 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": 0.0024519049415314977,
+  "epoch": 0.004903809883062995,
   "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": 15.542,
       "eval_steps_per_second": 7.774,
       "step": 10
+    },
+    {
+      "epoch": 0.002829121086382497,
+      "grad_norm": 10.258428573608398,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.9175,
+      "step": 15
+    },
+    {
+      "epoch": 0.003772161448509996,
+      "grad_norm": 13.949254989624023,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.6865,
+      "step": 20
+    },
+    {
+      "epoch": 0.003772161448509996,
+      "eval_loss": 0.6223310232162476,
+      "eval_runtime": 143.8688,
+      "eval_samples_per_second": 15.521,
+      "eval_steps_per_second": 7.764,
+      "step": 20
+    },
+    {
+      "epoch": 0.004715201810637495,
+      "grad_norm": 14.729504585266113,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.512,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2278473338978304.0,
+  "total_flos": 4556946677956608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null