Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948c531ff2d79b50333fb8d36ebb91fef37713ba4c194dce7ea6b1f86382396c
+oid sha256:1c4e0ebf76da4865efdca1d9c017eb12953429c6450d8ac7b6d1413f7893ddfd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2abcbc4034ca5424bc8c06094138a66dabe009fe682acc8e01d5bb5093135504
+oid sha256:98269e6cfde63cb38f575aa650ba0cffaf95774142b0cf43b9d50b5c3ffa4e05
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aef72e80bca5ad86c4740cd44eaa6a311a9485d9a446667badbb08fac831b01
+oid sha256:8a72025a75dfde9f6316cf7e78853946a2bfc45ed559fba6d15f16c4440f7ee5
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472d41c9b9333a74c9178e69008f711ff75ebcb1c9882a89e4e8e8fceffd9b44
+oid sha256:99ef6f22d42e935fbf13f0628837cd5d2513a098109335b9474dbc5e57db0c7d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04528384041800468,
+  "epoch": 0.06792576062700702,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 10.985,
       "eval_steps_per_second": 2.746,
       "step": 26
+    },
+    {
+      "epoch": 0.04702552658792794,
+      "grad_norm": 0.3819328546524048,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0898,
+      "step": 27
+    },
+    {
+      "epoch": 0.048767212757851196,
+      "grad_norm": 0.38801172375679016,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0728,
+      "step": 28
+    },
+    {
+      "epoch": 0.05050889892777445,
+      "grad_norm": 0.3896499276161194,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0931,
+      "step": 29
+    },
+    {
+      "epoch": 0.052250585097697706,
+      "grad_norm": 0.44811469316482544,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.104,
+      "step": 30
+    },
+    {
+      "epoch": 0.05399227126762097,
+      "grad_norm": 0.3136563003063202,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.071,
+      "step": 31
+    },
+    {
+      "epoch": 0.055733957437544224,
+      "grad_norm": 0.4052649736404419,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0825,
+      "step": 32
+    },
+    {
+      "epoch": 0.05747564360746748,
+      "grad_norm": 0.3598843216896057,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0904,
+      "step": 33
+    },
+    {
+      "epoch": 0.059217329777390734,
+      "grad_norm": 0.3175484538078308,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0929,
+      "step": 34
+    },
+    {
+      "epoch": 0.060959015947313996,
+      "grad_norm": 0.3411295413970947,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0826,
+      "step": 35
+    },
+    {
+      "epoch": 0.06270070211723724,
+      "grad_norm": 0.4295560419559479,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0854,
+      "step": 36
+    },
+    {
+      "epoch": 0.0644423882871605,
+      "grad_norm": 0.336063414812088,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0659,
+      "step": 37
+    },
+    {
+      "epoch": 0.06618407445708377,
+      "grad_norm": 0.3456127643585205,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0928,
+      "step": 38
+    },
+    {
+      "epoch": 0.06792576062700702,
+      "grad_norm": 0.37239643931388855,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0807,
+      "step": 39
+    },
+    {
+      "epoch": 0.06792576062700702,
+      "eval_loss": 0.07401972264051437,
+      "eval_runtime": 352.2856,
+      "eval_samples_per_second": 10.98,
+      "eval_steps_per_second": 2.745,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.172502199222927e+17,
+  "total_flos": 9.258753298834391e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null