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:f0e06338a9ec76de4fc5afb08f9b768d2cf2dad79525ec86fd278fb4e4a42d13
+oid sha256:e33b9c4d5b8234cc5f2bcab386d301080621fe4aa628b2481451f9774ec21779
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48d4d9a940e9c66359179e40ec27ddae86e962cb8934b93fa0f846398b1df10
+oid sha256:689f85e95b656860e4f35fdae01fbf0e0ae2a5ddca7501fa6b17d0fb08d15985
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbad8ba2c5033686167702b52f4d733e73fc51970594ffd4d36a57cb85a15e30
+oid sha256:57a81cc94bb9784a99b66a3847a12e5edc941dafcbd050831d68c21b46d0ac7a
 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": 0.016216216216216217,
+  "epoch": 0.024324324324324326,
   "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": 9.209,
       "eval_steps_per_second": 9.209,
       "step": 6
+    },
+    {
+      "epoch": 0.01891891891891892,
+      "grad_norm": 0.23834799230098724,
+      "learning_rate": 0.00014,
+      "loss": 2.0365,
+      "step": 7
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 0.34777796268463135,
+      "learning_rate": 0.00016,
+      "loss": 2.0777,
+      "step": 8
+    },
+    {
+      "epoch": 0.024324324324324326,
+      "grad_norm": 0.2863074839115143,
+      "learning_rate": 0.00018,
+      "loss": 2.3295,
+      "step": 9
+    },
+    {
+      "epoch": 0.024324324324324326,
+      "eval_loss": 2.1840600967407227,
+      "eval_runtime": 8.339,
+      "eval_samples_per_second": 9.354,
+      "eval_steps_per_second": 9.354,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2034520672960512.0,
+  "total_flos": 3098020115644416.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null