Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155d439e73369b0d5d760de677bc7ce14fe41909c724ac4b88fe795a3872ec26
+oid sha256:c281d94d9d7b30299f39d1dcb4c32e229770b673a3f9f6db96ff16878db1d862
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038b5c55e7840ce6802d7753d2c85be5de892c39bcc895b99fa0a8eaa1ef080e
+oid sha256:18013bdbfe059218a3a94f4887aea74c7e206c6e75bd78d65b71c56a1c3699dc
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12beed8359fe142c0bd78cf5e499f7058c2c13c901dc109a35a05e5a60f3c080
+oid sha256:8a787192adbf84242f4b8cb401581e3a7836211ae22a109ec4de70e071b1870b
 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": 0.015050651230101303,
+  "epoch": 0.030101302460202605,
   "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": 15.888,
       "eval_steps_per_second": 7.944,
       "step": 10
+    },
+    {
+      "epoch": 0.017366136034732273,
+      "grad_norm": 1.1096508502960205,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.3631,
+      "step": 15
+    },
+    {
+      "epoch": 0.023154848046309694,
+      "grad_norm": 1.1899404525756836,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.2529,
+      "step": 20
+    },
+    {
+      "epoch": 0.023154848046309694,
+      "eval_loss": 0.21950246393680573,
+      "eval_runtime": 22.9687,
+      "eval_samples_per_second": 15.848,
+      "eval_steps_per_second": 7.924,
+      "step": 20
+    },
+    {
+      "epoch": 0.02894356005788712,
+      "grad_norm": 0.7090124487876892,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1765,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2265426859917312.0,
+  "total_flos": 4574419620986880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null