Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f922f77057556ba0bcabd0b984085fc186027ffbdf3beefa3e31272d00f7a7
+oid sha256:f7c02aba99973b10a7dfafa7bcd9a75fe12d13ea34fabb70f1aabb457960381e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b7fa13844fc30bb2c5c5bf9d11b0a7264158fed85f36fb2d18ed9bbd8862985
+oid sha256:ac73fcef0178e0b5e417bbb81dec02e8a57efdaf13660a9a79d9a51c0695b055
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb51c4fb3a634956d61a25a3ca8fe7d5dc2947935cdb108666d882979263988
+oid sha256:8a6d0ee99bdd0319882c2fbace1fb60e096d6f8574b0dc2a723a28b6700bceec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016415868673050615,
+  "epoch": 0.024623803009575923,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 24.257,
       "eval_steps_per_second": 12.129,
       "step": 6
+    },
+    {
+      "epoch": 0.019151846785225718,
+      "grad_norm": 2.461836576461792,
+      "learning_rate": 0.00014,
+      "loss": 9.1362,
+      "step": 7
+    },
+    {
+      "epoch": 0.02188782489740082,
+      "grad_norm": 1.9313154220581055,
+      "learning_rate": 0.00016,
+      "loss": 8.3081,
+      "step": 8
+    },
+    {
+      "epoch": 0.024623803009575923,
+      "grad_norm": 2.00248122215271,
+      "learning_rate": 0.00018,
+      "loss": 7.9256,
+      "step": 9
+    },
+    {
+      "epoch": 0.024623803009575923,
+      "eval_loss": 2.111816883087158,
+      "eval_runtime": 6.3508,
+      "eval_samples_per_second": 24.249,
+      "eval_steps_per_second": 12.124,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1099394866741248.0,
+  "total_flos": 1628733135912960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null