Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15534d3755a6a4e5e30be58ff2c4a2167b06163faa57b68008187ad1d7497fd7
+oid sha256:3aa99e7cf2c3076f5ba88203146caeafb7c3c3e471219a98518a8ae34ea3bac0
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6489f32e9d976acd503d0b7c43cb423d90e76a6dcb755e2bf8df2eb2ca94cc0c
+oid sha256:f808c01192174f4f98f7f0269a5c6044231c9e8c5247c1824b0f10192f14b6fd
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:842160c84da2f20ba4769075d37abcad1cd79e1e28006529f9f33b1c2157a9d4
+oid sha256:9e6d5121af4ad8437561e7d254c21798ee487271bfae0bf79a1a5a2f43ee4420
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0018657369077742926,
+  "epoch": 0.0023321711347178654,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 16.013,
       "eval_steps_per_second": 4.003,
       "step": 20
+    },
+    {
+      "epoch": 0.001959023753163007,
+      "grad_norm": 3.2567591667175293,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.0721,
+      "step": 21
+    },
+    {
+      "epoch": 0.002238884289329151,
+      "grad_norm": 2.1846158504486084,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.9161,
+      "step": 24
+    },
+    {
+      "epoch": 0.0023321711347178654,
+      "eval_loss": 0.9646629691123962,
+      "eval_runtime": 1127.0671,
+      "eval_samples_per_second": 16.019,
+      "eval_steps_per_second": 4.005,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4438711779328e+16,
+  "total_flos": 3.048173869203456e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null