Training in progress, step 28, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e64cd9429c3e3e5761c51f818f35c75ecd1232057c81228740dea4aa744c7d
+oid sha256:7215f9f15c094cf3cdeb1e5537709a89bef70adc369dc292e35882f21cc46725
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cb57304bbdb393557583e9ea391f4cfe629785a56d8b7f467320faeb6a4decb
+oid sha256:8ed5fd588ee748ab7c105ed8409ef61fdb4fcfc08394d7fd879127026767aac6
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63c8755f60283d61d8f5e9b05b9fc3d8c48b7abe96f514359bc54f46be9cceb
+oid sha256:6e18c671f1c508102bc524438e5e499b73e4276946e8f3dfc5062547fd2a74b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:470670603e8fdc5330cdb9a9152c4fd9c3d8c5a74dd26bffbbb0d869d097eafa
+oid sha256:ff994fffd2fb6fe21545e6fbc55baa2a1474438a89b2d40605678f7de701427c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06460296096904442,
+  "epoch": 0.07537012113055182,
   "eval_steps": 4,
-  "global_step": 24,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,42 @@
       "eval_samples_per_second": 7.812,
       "eval_steps_per_second": 7.812,
       "step": 24
+    },
+    {
+      "epoch": 0.06729475100942127,
+      "grad_norm": 9.104133605957031,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.6002,
+      "step": 25
+    },
+    {
+      "epoch": 0.06998654104979811,
+      "grad_norm": 1.2012132406234741,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.2677,
+      "step": 26
+    },
+    {
+      "epoch": 0.07267833109017496,
+      "grad_norm": 0.8289370536804199,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.1694,
+      "step": 27
+    },
+    {
+      "epoch": 0.07537012113055182,
+      "grad_norm": 1.3279316425323486,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.2077,
+      "step": 28
+    },
+    {
+      "epoch": 0.07537012113055182,
+      "eval_loss": 0.2843972444534302,
+      "eval_runtime": 10.1018,
+      "eval_samples_per_second": 7.82,
+      "eval_steps_per_second": 7.82,
+      "step": 28
     }
   ],
   "logging_steps": 1,
@@ -250,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9830006507175936.0,
+  "total_flos": 1.1591988805632e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null