Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:448870c2221be3c02be6cd06bfff331f690dfadcb716a83ebc397701b516e492
+oid sha256:a0e0dd2c7e9b78e1c77e15a56c0f0bc779d5cda976d16754030ac35be04f7eec
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6d78489f0750c668f6f070cb14c4c5dad4f0c82b98b7119ddb3be2aa50f1f9
+oid sha256:942eba0bb8f58d4b7581c989360277a057f5708f98a5a43be495540f714dedbb
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d6aaba191fcba668a6a8829a2dac4730731a3cc4b900d2e8633196091bf4953
+oid sha256:7fcce9de0cc1f71342c751f72457aac3b43dcfc73ff0bfc403ea380246d9d7b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012292562999385371,
+  "epoch": 0.01843884449907806,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 12.709,
       "eval_steps_per_second": 1.594,
       "step": 10
+    },
+    {
+      "epoch": 0.014751075599262446,
+      "grad_norm": 2.486225128173828,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 0.6877,
+      "step": 12
+    },
+    {
+      "epoch": 0.01843884449907806,
+      "grad_norm": 1.9635486602783203,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6047,
+      "step": 15
+    },
+    {
+      "epoch": 0.01843884449907806,
+      "eval_loss": 0.5996317267417908,
+      "eval_runtime": 107.9179,
+      "eval_samples_per_second": 12.704,
+      "eval_steps_per_second": 1.594,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5462264182145024e+16,
+  "total_flos": 2.375908886524723e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null