Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ee22ed7847f28e04de1ce133795d3f6deb7e665519f56a2f7e4943ff0fcf147
+oid sha256:6e7fe8fc6b18a8ae029a58877e0ec1b980b40e6327e2db876a322aaa311f0171
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c9a0e1e5566485c456ce5fa659fe2f0e342d45dee06a17dcb9daa2708cb4879
+oid sha256:5d9908e8a4ed7d7fd67864fbc5f17ef3982c3a78797b866a7fc3dca564534e02
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03160a1210bc43604b1b84c7fab5c0a795fb73aed78bdafbff90abcff05d831a
+oid sha256:0d0da3873d0775bf81b7bdee3955da665b473c4317959da28b057b61212854f6
 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": 1.351224596143825,
+  "epoch": 1.501302761855133,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 120.139,
       "eval_steps_per_second": 60.365,
       "step": 81
+    },
+    {
+      "epoch": 1.4012506513809275,
+      "grad_norm": 0.053699202835559845,
+      "learning_rate": 1.4323725421878949e-05,
+      "loss": 11.5982,
+      "step": 84
+    },
+    {
+      "epoch": 1.4512767066180303,
+      "grad_norm": 0.07235908508300781,
+      "learning_rate": 9.56279946954021e-06,
+      "loss": 11.8316,
+      "step": 87
+    },
+    {
+      "epoch": 1.501302761855133,
+      "grad_norm": 0.05552632361650467,
+      "learning_rate": 5.709035061653494e-06,
+      "loss": 11.6771,
+      "step": 90
+    },
+    {
+      "epoch": 1.501302761855133,
+      "eval_loss": 11.735032081604004,
+      "eval_runtime": 1.6936,
+      "eval_samples_per_second": 119.863,
+      "eval_steps_per_second": 60.227,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 151338604953600.0,
+  "total_flos": 168136934031360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null