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:de908b5d7d4f1d6d9632458d5d2ce36b0bc2e6d0a3cd92e2c41a59455b99736b
+oid sha256:6f37d4c9fb93dd101d43f3381339e0c9a88fbf8baf396242a7852eb935d8e667
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42605ae7916d94133b356db81262266d10feb2d598db5b733662c9ab9b366647
+oid sha256:00c28e5ebd873c455c98e0419c426388f9dcc9cb06be8991c0a6bde5132021d2
 size 111078

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62799726ec41abcc2bd4f4509df5dc69917063df942179f8740a71402b9944ef
+oid sha256:06f3828ea52b194ed76e01c62f9f5be77b2bd9f9cfe728db3d9d8cc44a4f67a8
 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": 0.030612244897959183,
+  "epoch": 0.04591836734693878,
   "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": 132.644,
       "eval_steps_per_second": 66.322,
       "step": 6
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 0.060700736939907074,
+      "learning_rate": 0.00014,
+      "loss": 10.3771,
+      "step": 7
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 0.07724273949861526,
+      "learning_rate": 0.00016,
+      "loss": 10.3736,
+      "step": 8
+    },
+    {
+      "epoch": 0.04591836734693878,
+      "grad_norm": 0.0864340215921402,
+      "learning_rate": 0.00018,
+      "loss": 10.3787,
+      "step": 9
+    },
+    {
+      "epoch": 0.04591836734693878,
+      "eval_loss": 10.379778861999512,
+      "eval_runtime": 0.3336,
+      "eval_samples_per_second": 125.907,
+      "eval_steps_per_second": 62.953,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 313814679552.0,
+  "total_flos": 470722019328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null