Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:611eb546c4213a33a191de2af6f0e9be0eb59bbc9b57f2d2a3596c176b932d95
+oid sha256:19ae7125d034ff264f330bc6f03491eb2bfd9b7f45c35a196594d643a3fa6207
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a19512af0d064526955708988a05200050292d802901635ddabf7d444826a1e
+oid sha256:eb73d85b76527f291eae9fef4fc14669ca986ff9a757fd5c5536cbed915ff4a7
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1daf813549d6191a658ca47468b077c3487cd48e02216803f471e9a5adc4df2b
+oid sha256:518e568369e71743f4b5da12a73c75b71f6b05b27911c3002446d907fd717c19
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25120772946859904,
+  "epoch": 0.37681159420289856,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 239.423,
       "eval_steps_per_second": 30.185,
       "step": 20
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 9.983260154724121,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 7.8034,
+      "step": 30
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "eval_loss": 7.373321056365967,
+      "eval_runtime": 2.9407,
+      "eval_samples_per_second": 237.36,
+      "eval_steps_per_second": 29.925,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 47464386134016.0,
+  "total_flos": 71458813378560.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null