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:e14e61af4559d46962375519214b4d74a3ba5ddeefce1e504fa36d37abf679c5
+oid sha256:948c531ff2d79b50333fb8d36ebb91fef37713ba4c194dce7ea6b1f86382396c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3116a34039b7f4d73e522f8cc99970daf015e9c62025b70d68e2b3bcad1340ab
+oid sha256:2abcbc4034ca5424bc8c06094138a66dabe009fe682acc8e01d5bb5093135504
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5e3c19f7b2892f9204c2db9ed620b572aab049411a4232f39c90287c803cca
+oid sha256:5aef72e80bca5ad86c4740cd44eaa6a311a9485d9a446667badbb08fac831b01
 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": 0.02264192020900234,
+  "epoch": 0.04528384041800468,
   "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": 10.985,
       "eval_steps_per_second": 2.746,
       "step": 13
+    },
+    {
+      "epoch": 0.024383606378925598,
+      "grad_norm": 0.8086413145065308,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.147,
+      "step": 14
+    },
+    {
+      "epoch": 0.026125292548848853,
+      "grad_norm": 0.9576364755630493,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 0.1463,
+      "step": 15
+    },
+    {
+      "epoch": 0.027866978718772112,
+      "grad_norm": 0.5651424527168274,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 0.1489,
+      "step": 16
+    },
+    {
+      "epoch": 0.029608664888695367,
+      "grad_norm": 0.7270596623420715,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 0.1385,
+      "step": 17
+    },
+    {
+      "epoch": 0.03135035105861862,
+      "grad_norm": 0.7695695161819458,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1344,
+      "step": 18
+    },
+    {
+      "epoch": 0.033092037228541885,
+      "grad_norm": 0.5415513515472412,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 0.1271,
+      "step": 19
+    },
+    {
+      "epoch": 0.03483372339846514,
+      "grad_norm": 0.5811421871185303,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1157,
+      "step": 20
+    },
+    {
+      "epoch": 0.036575409568388395,
+      "grad_norm": 0.5054365992546082,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 0.1075,
+      "step": 21
+    },
+    {
+      "epoch": 0.03831709573831165,
+      "grad_norm": 0.43094682693481445,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0977,
+      "step": 22
+    },
+    {
+      "epoch": 0.04005878190823491,
+      "grad_norm": 0.35248297452926636,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.0912,
+      "step": 23
+    },
+    {
+      "epoch": 0.04180046807815817,
+      "grad_norm": 0.46628761291503906,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.1272,
+      "step": 24
+    },
+    {
+      "epoch": 0.04354215424808142,
+      "grad_norm": 0.37774521112442017,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 0.0911,
+      "step": 25
+    },
+    {
+      "epoch": 0.04528384041800468,
+      "grad_norm": 0.318975567817688,
+      "learning_rate": 5e-05,
+      "loss": 0.0788,
+      "step": 26
+    },
+    {
+      "epoch": 0.04528384041800468,
+      "eval_loss": 0.08614670485258102,
+      "eval_runtime": 352.1165,
+      "eval_samples_per_second": 10.985,
+      "eval_steps_per_second": 2.746,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.086251099611464e+17,
+  "total_flos": 6.172502199222927e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null