Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:517bae1cbe8e61855e5c9e682798973e5a5563b882428b519e405b4cdf083fe2
+oid sha256:402a1852fc7cac9700e5ee0d0dce99f73adcfe23aad307515a1ae3e70e3b0f8c
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988765cc0fb5f0ab61abc3bfc4e43f942b8af26c08f9c0dc2de1debf3025f959
+oid sha256:ba3c0a3600c9d6481528afc62e45771c88c6e35d0ca84c0bf2587b0d774162fb
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c69b824253ff1a0f68a35d89ef1937ad58396ad24222443cdfdb55bb024185b
+oid sha256:6697f228e01d9570a9ca8a159a36858b53464b14af2c48a02d573db55895bf97
 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": 0.7627118644067796,
+  "epoch": 0.8389830508474576,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -221,6 +221,21 @@
       "eval_samples_per_second": 18.89,
       "eval_steps_per_second": 2.384,
       "step": 90
+    },
+    {
+      "epoch": 0.8050847457627118,
+      "grad_norm": 0.5288379192352295,
+      "learning_rate": 1.4411039697577175e-06,
+      "loss": 0.7473,
+      "step": 95
+    },
+    {
+      "epoch": 0.8389830508474576,
+      "eval_loss": 0.7672185897827148,
+      "eval_runtime": 22.2757,
+      "eval_samples_per_second": 18.855,
+      "eval_steps_per_second": 2.379,
+      "step": 99
     }
   ],
   "logging_steps": 5,
@@ -240,7 +255,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3953750603399168e+17,
+  "total_flos": 1.5349125663739085e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null