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:a1015b6c1e0d5f9c1409c2ce27b7d2e3cd565397419d0743bc232e4e1dc546fc
+oid sha256:cd5cd5cd61f79cf8a7d4cb8fe7bdf1e3a7c05e64f3ab2436903b1de6103d18ee
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9a1d9eff6e5ce3711f501c8013b148ef7ed8086dbed1cbb9cda2d8055ab8dc
+oid sha256:847baf0de346b8d0a11da2569f370445a34103232f9f9ace782d6c694a5b850f
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23685a98ac97c18b140e04fa25373f64d83f75cb833242b433110acfd689d626
+oid sha256:f022be21eadc25c785cc017915debb63eff9607bbd792ce43bb3e27c6b09cee0
 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": 0.0011948026086523623,
+  "epoch": 0.0017922039129785433,
   "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": 4.255,
       "eval_steps_per_second": 4.255,
       "step": 6
+    },
+    {
+      "epoch": 0.0013939363767610893,
+      "grad_norm": 2.7793145179748535,
+      "learning_rate": 0.00014,
+      "loss": 0.4502,
+      "step": 7
+    },
+    {
+      "epoch": 0.0015930701448698163,
+      "grad_norm": 1.5942715406417847,
+      "learning_rate": 0.00016,
+      "loss": 0.3581,
+      "step": 8
+    },
+    {
+      "epoch": 0.0017922039129785433,
+      "grad_norm": 2.2092483043670654,
+      "learning_rate": 0.00018,
+      "loss": 0.3398,
+      "step": 9
+    },
+    {
+      "epoch": 0.0017922039129785433,
+      "eval_loss": 0.41140756011009216,
+      "eval_runtime": 248.3936,
+      "eval_samples_per_second": 4.259,
+      "eval_steps_per_second": 4.259,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4601366169255936.0,
+  "total_flos": 6902049253883904.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null