Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7da7067d676c26c384ce8d312ac4aa2d15de13e65fa66abbd4ca630d9fa75b
+oid sha256:84f4cb54b5b1135e2555dca18782fce6b5aa14e114889d097b9c5d443226389a
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff61d269ce9a51a7f5e6bcdddbd7eeca933aa357cc74c6496f2cb5180e1da7b3
+oid sha256:9f559f296c831731a888211c612be85a8e463875d640ef803615b1d20c7d00b1
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:421fdcb93fcfd3e1c808f00ff826181eb7b32091d13b1ec59f6470708c0a25b2
+oid sha256:dff403a6b75e6d5e88136345c5d0ea63489b1e9230afeb0c0198abe8b5cb7750
 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": 0.000565493991626339,
+  "epoch": 0.001130987983252678,
   "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": 4.505,
       "eval_steps_per_second": 2.253,
       "step": 10
+    },
+    {
+      "epoch": 0.0006524930672611604,
+      "grad_norm": 0.7909639477729797,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6981,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008699907563482138,
+      "grad_norm": 0.7223533391952515,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.7726,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008699907563482138,
+      "eval_loss": 0.7328978776931763,
+      "eval_runtime": 2379.4552,
+      "eval_samples_per_second": 4.068,
+      "eval_steps_per_second": 2.034,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010874884454352672,
+      "grad_norm": 0.6274079084396362,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.7298,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1012697094684672.0,
+  "total_flos": 2037896622637056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null