Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f68a02d7c84ce57e607aa8da51a84c9a017fd335da2ea608038023646346b0
+oid sha256:05e52ff35b8f983bc0adadb3e1b36f73ed713e0af8d60542ccadd4fcb6bab407
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915b171270da7d787d7eecebf6d9b2d0195106a2c9361cf693bf0a4358206682
+oid sha256:5b8ce8033ba5aa87e61aba3b57d82d3847af3b6bbb5ea46b84ef8b5073572add
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a11a1375777d57e625fdc32e2f9f547ac59706c1926af9227df8f015961b0a4b
+oid sha256:a2a69c88986204bfebabc28ab92e780dfb7d500556cf7bb3d17b453833c3b7fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024980917354798418,
+  "epoch": 0.02747900909027826,
   "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": 9.19,
       "eval_steps_per_second": 1.149,
       "step": 90
+    },
+    {
+      "epoch": 0.025813614599958366,
+      "grad_norm": 0.20059961080551147,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.3737,
+      "step": 93
+    },
+    {
+      "epoch": 0.02664631184511831,
+      "grad_norm": 0.18491944670677185,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.3247,
+      "step": 96
+    },
+    {
+      "epoch": 0.02747900909027826,
+      "grad_norm": 0.17610909044742584,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.3463,
+      "step": 99
+    },
+    {
+      "epoch": 0.02747900909027826,
+      "eval_loss": 0.352405309677124,
+      "eval_runtime": 660.4405,
+      "eval_samples_per_second": 9.188,
+      "eval_steps_per_second": 1.149,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9712891151817114e+17,
+  "total_flos": 2.170515142779863e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null