Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51fcc77370a81475a4e046ac74ee8c5b43143ed3ca2d8c240ed48958d5bb70fd
+oid sha256:a9ed3b51d66d26c723150fc2a10b1c368924915ab99fdf8336411955ef0f1aeb
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc676310077c6da2beaf9c25bcf03c30557c7f75ed95360d5142b49d60b5600
+oid sha256:fb861ca27f0024365dd6cea6b1a66b168bf2c408b4219548aca3aae4833d519e
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce50dea9e3a4b8bb086ca309a8601c6e377b6b761711e9e5f2dfb23d927271d8
+oid sha256:0cf90e15b7e58f0f1e8a0f70b80c5bad13506c9c5e1615ee2a4bbd31c4048c8e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23684210526315788,
+  "epoch": 0.47368421052631576,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 14.102,
       "eval_steps_per_second": 1.763,
       "step": 9
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 11.629775047302246,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 4.0086,
+      "step": 12
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 10.649725914001465,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 3.8607,
+      "step": 15
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 9.19792366027832,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 3.954,
+      "step": 18
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "eval_loss": 0.8341699838638306,
+      "eval_runtime": 4.56,
+      "eval_samples_per_second": 14.035,
+      "eval_steps_per_second": 1.754,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2656345471778816e+16,
+  "total_flos": 2.531269094355763e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null