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:f685d1b73db37255c28b0937b165cf8eafb0099434ebb5026f9d5f086049f370
+oid sha256:c53254f7ea39fe8f31247ca88cb1caeabdacc9a6e1133aeda2a0e5a64a20f392
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ccbe8f52b64656a2fae23bebc063ec4f55dfced1911be4f5675713b7a3b725
+oid sha256:3cfe9e8e0441d1088dc84ff17fd775ff5fe66a0f007e919d9ba407a9f990ffd0
 size 79968772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6cd3789a603cc9db1f0b416612fba074ab96fe35f4ad309fac449135e2f22d
+oid sha256:8c620901f4f18db9d2766b73b498690238d01bc9e321c63a96cb81351dc958c9
 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": 0.03759398496240601,
+  "epoch": 0.046992481203007516,
   "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": 27.926,
       "eval_steps_per_second": 6.982,
       "step": 20
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 1.2767959833145142,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.724,
+      "step": 21
+    },
+    {
+      "epoch": 0.045112781954887216,
+      "grad_norm": 1.445420265197754,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.7438,
+      "step": 24
+    },
+    {
+      "epoch": 0.046992481203007516,
+      "eval_loss": 1.6554962396621704,
+      "eval_runtime": 16.0491,
+      "eval_samples_per_second": 27.914,
+      "eval_steps_per_second": 6.979,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3973659450408960.0,
+  "total_flos": 4967074313011200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null