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:e5e6cc3f5ade40a8e874e995d657e610d46cc8ae5fbd62a777483ca05a6a1f19
+oid sha256:2fdf5ae8a3434d45cfd675959fdf2531e12910656fef66cf41871b32e07f735c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b549c7992556bf7ede8945185f5fd3055a9a22839c885d48347ca92d6cf8193
+oid sha256:b196f3391fcef7d5f7d85def0872a05414eeca6dcde82e64412b9a8e3299327d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf191b7c52ae0f5950e3f1f1dec5b3d92cc3089d5753f800d4b1b7550aa71db3
+oid sha256:e05fe95363144ef3cc38bcd7440fb89fde10bc93ca8cbfa57af8f7736ec5802e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793e67e8ce9008665aa65ff20b6ea7fbcd694d12c7efb6b4719021ac264b7609
+oid sha256:0addd62454d87d49bfedc26e0b85659f0aaed290a84e144284ca9b72f10d6fc8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2691588785046729,
+  "epoch": 0.5383177570093458,
   "eval_steps": 7,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 19.037,
       "eval_steps_per_second": 2.443,
       "step": 7
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 29.873859405517578,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 27.8654,
+      "step": 10
+    },
+    {
+      "epoch": 0.41869158878504675,
+      "eval_loss": 9.885928193398286e-06,
+      "eval_runtime": 11.905,
+      "eval_samples_per_second": 18.984,
+      "eval_steps_per_second": 2.436,
+      "step": 14
     }
   ],
   "logging_steps": 10,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5238444917653504e+16,
+  "total_flos": 5.047688983530701e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null