Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc14169f14d6c16100fb689fe0fe23d2a3c91b774290a588b1d02843182a4d98
+oid sha256:c14efe289e9d6b68e1d5f6f2d468758e34e5fccad14fe98d0aa59c891e015f7a
 size 435773944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f1a2944e1df9ff3494ce8d0ae7c84c913df11d519bdf8a1c9873ace5dc1d4fb
+oid sha256:51ad0dc15dff5be446ba97f3ab39de0804ea19c6708fac1efe95d00110eddd93
 size 222034900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762ec1330e13c4a107fd3c42f49c9235920da537fe3ae2864bb64948b2968312
+oid sha256:fa2c1d5a97dae61d9453fafd03f4c7d8eea28e16ba48efd0c4f825b9e78ee9a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16835016835016836,
+  "epoch": 0.25252525252525254,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 24.577,
       "eval_steps_per_second": 12.387,
       "step": 100
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.0527721315156668e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 9.965347999241203e-06,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.21885521885521886,
+      "grad_norm": 9.623281584936194e-06,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.2356902356902357,
+      "grad_norm": 8.889406672096811e-06,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.25252525252525254,
+      "grad_norm": 8.956275451055262e-06,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.25252525252525254,
+      "eval_loss": 1.7172290256439737e-07,
+      "eval_runtime": 5.0926,
+      "eval_samples_per_second": 24.545,
+      "eval_steps_per_second": 12.371,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.06612949778432e+16,
+  "total_flos": 1.59919424667648e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null