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:da90fa0e16e41fdfe764b4234dbea16e19ff591391333eb9adcdc7f6278266c7
+oid sha256:12643d73306d913bb59b9fef8ebce83ff830057d2ff5d47969f3e4d61fdebd0c
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe28944b0e69e5f100787ef18ce315e0ecd9f75ff6d8c81f53c778898769765
+oid sha256:2e3f5b4eec3e66d80a2fd8c3c6b19d5807558d664d02d881def3beb6b46979ab
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6653bc060345fb346135d580a2bf3cff0c36f2c54b348b5459115515481320b6
+oid sha256:c5c166beb56023c475d0a1e4488772a1479f599ca29e77e7106a93caafb4ed00
 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": 0.006460730870179689,
+  "epoch": 0.007537519348542971,
   "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": 8.377,
       "eval_steps_per_second": 4.191,
       "step": 24
+    },
+    {
+      "epoch": 0.00672992798977051,
+      "grad_norm": 2.6795260906219482,
+      "learning_rate": 0.000138268343236509,
+      "loss": 3.646,
+      "step": 25
+    },
+    {
+      "epoch": 0.00699912510936133,
+      "grad_norm": 2.925718307495117,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.1437,
+      "step": 26
+    },
+    {
+      "epoch": 0.0072683222289521504,
+      "grad_norm": 2.81306529045105,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 3.9201,
+      "step": 27
+    },
+    {
+      "epoch": 0.007537519348542971,
+      "grad_norm": 2.4982492923736572,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 3.8325,
+      "step": 28
+    },
+    {
+      "epoch": 0.007537519348542971,
+      "eval_loss": 3.943394660949707,
+      "eval_runtime": 187.1247,
+      "eval_samples_per_second": 8.363,
+      "eval_steps_per_second": 4.184,
+      "step": 28
     }
   ],
   "logging_steps": 1,
@@ -250,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8405464677023744e+16,
+  "total_flos": 2.147304212319437e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null