Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8338d0371a035aa1a6e38b77dff221fcf9ba83d3e29f4789534a13eabc6e82f8
+oid sha256:c582e34b740c2ab84777b72c509a0e97c269aac69112da8e8698713a54feeae8
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6264c706641e81281ccc8cdc92c1bd7506e0ccf8ae3a5ca2071df4683ad54811
+oid sha256:e5ccefb6bcb213e033c6d906dfab3f18aaf2958fcc017bb013b20f4d401e0fe3
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad7d53f2bd686d5b08e71c45b51b2fc986926916fcd4884c9b343639657183c
+oid sha256:d5134bfc96a8a009684ec48127ff4fc03b2f2e61a0fbe126a34bef4ab7025231
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
+oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.74310692669805,
+  "epoch": 1.936785474108944,
   "eval_steps": 50,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -590,6 +590,69 @@
       "learning_rate": 1.99258117923236e-05,
       "loss": 15.7491,
       "step": 81
+    },
+    {
+      "epoch": 1.7646267652992602,
+      "grad_norm": 18.65260887145996,
+      "learning_rate": 1.796955257999768e-05,
+      "loss": 18.4079,
+      "step": 82
+    },
+    {
+      "epoch": 1.7861466039004708,
+      "grad_norm": 20.124731063842773,
+      "learning_rate": 1.6101230183944144e-05,
+      "loss": 21.8745,
+      "step": 83
+    },
+    {
+      "epoch": 1.8076664425016813,
+      "grad_norm": 15.53337287902832,
+      "learning_rate": 1.4323725421878949e-05,
+      "loss": 14.7667,
+      "step": 84
+    },
+    {
+      "epoch": 1.8291862811028916,
+      "grad_norm": 24.60688018798828,
+      "learning_rate": 1.2639779077309098e-05,
+      "loss": 23.2765,
+      "step": 85
+    },
+    {
+      "epoch": 1.8507061197041024,
+      "grad_norm": 18.01706886291504,
+      "learning_rate": 1.1051987673443085e-05,
+      "loss": 19.2231,
+      "step": 86
+    },
+    {
+      "epoch": 1.8722259583053127,
+      "grad_norm": 17.668659210205078,
+      "learning_rate": 9.56279946954021e-06,
+      "loss": 23.5257,
+      "step": 87
+    },
+    {
+      "epoch": 1.8937457969065232,
+      "grad_norm": 20.853605270385742,
+      "learning_rate": 8.174510685872415e-06,
+      "loss": 22.4145,
+      "step": 88
+    },
+    {
+      "epoch": 1.9152656355077338,
+      "grad_norm": 20.111770629882812,
+      "learning_rate": 6.889261963118898e-06,
+      "loss": 18.1747,
+      "step": 89
+    },
+    {
+      "epoch": 1.936785474108944,
+      "grad_norm": 19.906658172607422,
+      "learning_rate": 5.709035061653494e-06,
+      "loss": 23.4895,
+      "step": 90
     }
   ],
   "logging_steps": 1,
@@ -609,7 +672,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.259916615505674e+17,
+  "total_flos": 4.7332406838951936e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null