Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392f91404937b3f8e83dbf5e3238b2e1b55a08eff0537a0bc1faa5a597db2413
+oid sha256:bb4b0fca46c3ded7e0354733843df8d4bf1b9df58dec5886477ec67a8376d162
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7491e60f617fd24e4e62d602f06cd3c59090ea408ce2faf4cff9bcf48eb3cd1
+oid sha256:efe2d4f69eb0fec6e19d2d081594a274f18dd48630014acd73fcf4cd64764f7d
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fee8f786c47ef8800fb245c2ff9962d344cd4084fee9a79e8dec838b113fd1aa
+oid sha256:ff6829903aaa4143f234b90612cf464d1814d88258a1a614f0e155e2ec01b5e7
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35459df988092e3ff9e3c1b91118d006576bed7e1956fe6101d7671fcd8c5396
+oid sha256:472d41c9b9333a74c9178e69008f711ff75ebcb1c9882a89e4e8e8fceffd9b44
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09614051305754565,
+  "epoch": 0.1922810261150913,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 11.193,
       "eval_steps_per_second": 2.801,
       "step": 13
+    },
+    {
+      "epoch": 0.1035359371388953,
+      "grad_norm": 69.56649017333984,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 86.8469,
+      "step": 14
+    },
+    {
+      "epoch": 0.11093136122024497,
+      "grad_norm": 67.40845489501953,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 88.4199,
+      "step": 15
+    },
+    {
+      "epoch": 0.11832678530159464,
+      "grad_norm": 70.2257308959961,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 91.2391,
+      "step": 16
+    },
+    {
+      "epoch": 0.12572220938294432,
+      "grad_norm": 46.68100357055664,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 87.3729,
+      "step": 17
+    },
+    {
+      "epoch": 0.13311763346429398,
+      "grad_norm": 102.54607391357422,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 82.5651,
+      "step": 18
+    },
+    {
+      "epoch": 0.14051305754564364,
+      "grad_norm": 116.23051452636719,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 93.5197,
+      "step": 19
+    },
+    {
+      "epoch": 0.1479084816269933,
+      "grad_norm": 65.93101501464844,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 82.7672,
+      "step": 20
+    },
+    {
+      "epoch": 0.15530390570834296,
+      "grad_norm": 57.98164749145508,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 85.3329,
+      "step": 21
+    },
+    {
+      "epoch": 0.16269932978969262,
+      "grad_norm": 60.674495697021484,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 84.3847,
+      "step": 22
+    },
+    {
+      "epoch": 0.17009475387104228,
+      "grad_norm": 72.81175231933594,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 88.0836,
+      "step": 23
+    },
+    {
+      "epoch": 0.17749017795239197,
+      "grad_norm": 57.464141845703125,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 83.9486,
+      "step": 24
+    },
+    {
+      "epoch": 0.18488560203374163,
+      "grad_norm": 41.056941986083984,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 79.0182,
+      "step": 25
+    },
+    {
+      "epoch": 0.1922810261150913,
+      "grad_norm": 55.79506301879883,
+      "learning_rate": 5e-05,
+      "loss": 85.1922,
+      "step": 26
+    },
+    {
+      "epoch": 0.1922810261150913,
+      "eval_loss": 2.7002317905426025,
+      "eval_runtime": 81.3945,
+      "eval_samples_per_second": 11.192,
+      "eval_steps_per_second": 2.801,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.925022064588882e+17,
+  "total_flos": 5.850044129177764e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null