Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b03ac46273a655e872d981dc7cb2e41d5c98dcb8e4d5e562e240322d0d2888
+oid sha256:b07c4d4c298d67a03418122862fdcc86b54210e9a055d3ff0e2f424107515339
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2693224ef432af484735087f6b42679d2660062e58f3451304215967025ab570
+oid sha256:6bf9f021ca867a726e9eb269fca993e70b83c75bb499e438dd8eb7d6a826169b
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:579360aedf9e1e6d78ecaf690eee9abae295d9f1032a5ecb7ca3cda426db0d8f
+oid sha256:2aaa6d8a69d8299a907823adc599422c15491312a4bfb634b6631045d063f404
 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": 0.08048289738430583,
+  "epoch": 0.12072434607645875,
   "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": 6.333,
       "eval_steps_per_second": 0.818,
       "step": 10
+    },
+    {
+      "epoch": 0.096579476861167,
+      "grad_norm": 0.2077365219593048,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 0.0431,
+      "step": 12
+    },
+    {
+      "epoch": 0.12072434607645875,
+      "grad_norm": 0.2362423539161682,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0303,
+      "step": 15
+    },
+    {
+      "epoch": 0.12072434607645875,
+      "eval_loss": 0.022640502080321312,
+      "eval_runtime": 32.9869,
+      "eval_samples_per_second": 6.336,
+      "eval_steps_per_second": 0.819,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.017027157491712e+16,
+  "total_flos": 4.525540736237568e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null