Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e588816b59ca0e2530bf96f6e2fa633db5c75921618178b966c63bedb2843e
+oid sha256:fb6fd523932a9fa60052a7b49db18507715dc2dcd12e2962e8dcde92d9f9bdee
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d035373b9a4860742ee51393c2f73ddfeaedaade1d564bd05e7e1b9e1687ddbe
+oid sha256:23aa35d28feddbfc4c38e244a0a174d9e45006f8a6757a6ae1b7efdd0c4b6d63
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fffc3385b4215ddc4b17b7cac3c79bd90653eb5a98a35e4bb807b66290d1fb8e
+oid sha256:562f684b1f296e89a1c35e1ddeb17a41dd7b79379be83f57533740e866b7bd31
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
+oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.705709384954668,
+  "epoch": 0.7762803234501348,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 29.493,
       "eval_steps_per_second": 14.747,
       "step": 90
+    },
+    {
+      "epoch": 0.7292330311198236,
+      "grad_norm": 0.31848374009132385,
+      "learning_rate": 2.815857265976462e-06,
+      "loss": 0.5111,
+      "step": 93
+    },
+    {
+      "epoch": 0.7527566772849792,
+      "grad_norm": 0.3071320354938507,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 0.512,
+      "step": 96
+    },
+    {
+      "epoch": 0.7762803234501348,
+      "grad_norm": 0.2910892963409424,
+      "learning_rate": 5.7822281945782424e-08,
+      "loss": 0.5128,
+      "step": 99
+    },
+    {
+      "epoch": 0.7762803234501348,
+      "eval_loss": 0.521817147731781,
+      "eval_runtime": 14.6393,
+      "eval_samples_per_second": 29.373,
+      "eval_steps_per_second": 14.686,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.500747528732672e+16,
+  "total_flos": 8.25082228160594e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null