Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84053879b7577cb26994e1ec713b37c6bd8eb4ea6814243b75a2aff8a3f654ba
+oid sha256:f0aad5ea861ca95f02e164a636e7f4f55b3c9542806c936c4a02a81a9b76203c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76d704d9bedc21f92ad5f3623857c6424d88c040469fae87764b9129aac10f7
+oid sha256:420d46b1d517ea00cf021c320254bab4ecd2c4399be72dd1c32ca6a13b70c1bb
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0372018a4be5540bc5abe6dc6460517fafa00663177aa4622b9d278e34d5efdc
+oid sha256:6c7cbbb04512bd9b58eb37215dd24c52eccba02c770c21d16b116ae65aab2177
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0044511973292816025,
+  "epoch": 0.008902394658563205,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 19.857,
       "eval_steps_per_second": 2.483,
       "step": 10
+    },
+    {
+      "epoch": 0.006847995891202465,
+      "grad_norm": 0.8173860311508179,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1707,
+      "step": 20
+    },
+    {
+      "epoch": 0.006847995891202465,
+      "eval_loss": 0.07577058672904968,
+      "eval_runtime": 991.4538,
+      "eval_samples_per_second": 19.846,
+      "eval_steps_per_second": 2.481,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.443949909835776e+16,
+  "total_flos": 6.871421590437888e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null