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:f645718eddfa5ff97c8ae8d88ce9f90035f38b4876135d0f746438b833c3a278
+oid sha256:eddf1cea2bd9909955e3b4fcd2a91d57d875b81c4cbd42e678317f10c09312cd
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa56f6c262fabd77fa269c14378d9e41268d61d8ddb4b93d3154fa8c5884f49a
+oid sha256:ad1bb15100dac099b8949e2ebf3d7ce3923eb55c8c3d48b7417c82c6a1dbe614
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb5f1f2063cc0fc9d69930536ad8305cd213d31011d601a76e1f19f1f368b7a
+oid sha256:ce48dec86ac6000671bbcda61602ac669c6643b660b3c79e45fe5bfda138dc71
 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": 0.32432432432432434,
+  "epoch": 0.4864864864864865,
   "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": 67.028,
       "eval_steps_per_second": 33.514,
       "step": 6
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 0.3570092022418976,
+      "learning_rate": 0.00014,
+      "loss": 11.8717,
+      "step": 7
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.5594825744628906,
+      "learning_rate": 0.00016,
+      "loss": 11.9122,
+      "step": 8
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 0.45945826172828674,
+      "learning_rate": 0.00018,
+      "loss": 11.8951,
+      "step": 9
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "eval_loss": 11.869675636291504,
+      "eval_runtime": 0.1191,
+      "eval_samples_per_second": 67.148,
+      "eval_steps_per_second": 33.574,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 750935605248.0,
+  "total_flos": 1188981374976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null