Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85047b9c04df0e7ce9646fb4cd71e1d85ef08416eb74483964847677944e717d
+oid sha256:8661537ad86d1fa8b5c100fec1ddcec28dbb78f6e2ba5ee266df6453f7af548e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7206e688cbce421e2453eb16cf1bbe6967d5d6abf8cd8c0385c8331d8cdff73e
+oid sha256:c355f395f4622f63dd83b1c886bd24c91568d5ce988970a748548a88f7a4f5dc
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6d2b73783f687c5f81e1f4c81dd570fc4ab1ebafa6563658b87e6a7f9990bbf
+oid sha256:2aff1a6c4cc7a958d2f4e8ae002b51812321a670105c72ba191a30258605048d
 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": 0.0009655915176498988,
+  "epoch": 0.0019311830352997975,
   "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": 12.099,
       "eval_steps_per_second": 6.051,
       "step": 10
+    },
+    {
+      "epoch": 0.0011141440588268063,
+      "grad_norm": 10.058262825012207,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 6.0454,
+      "step": 15
+    },
+    {
+      "epoch": 0.0014855254117690751,
+      "grad_norm": 13.010249137878418,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 5.9304,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014855254117690751,
+      "eval_loss": 1.4773796796798706,
+      "eval_runtime": 467.8787,
+      "eval_samples_per_second": 12.116,
+      "eval_steps_per_second": 6.059,
+      "step": 20
+    },
+    {
+      "epoch": 0.001856906764711344,
+      "grad_norm": 8.150615692138672,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 6.0852,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2935725263683584.0,
+  "total_flos": 6265801682190336.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null