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:a60d7b0515cd56e5a94c39867a78ab42512b41704e1ed69bb29dca7f90121d64
+oid sha256:53c1f47619c20dc7f21c6e24d15419289847495bfc992fd961db41853e9b4312
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c28a68fdf807ec9c1f32ca5c75fa695a66e2a2ecd837ee87ff4e4fd4abaa63
+oid sha256:6ee91a657ee619e0fd33bfa35f8d28008e6db64424f30745334c9715eed5e8d9
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f7017296cc3da84fdfa03b39bd71e63a684a78aa62b84295cc2387ce598c36
+oid sha256:0446c283f3d13924158b53fab172b648ee5a8318605e10f8c682e330fe303df8
 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": 0.00037007910440856734,
+  "epoch": 0.000555118656612851,
   "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": 123.998,
       "eval_steps_per_second": 62.008,
       "step": 6
+    },
+    {
+      "epoch": 0.00043175895514332855,
+      "grad_norm": 163.31253051757812,
+      "learning_rate": 0.00014,
+      "loss": 11.0275,
+      "step": 7
+    },
+    {
+      "epoch": 0.0004934388058780898,
+      "grad_norm": 163.90606689453125,
+      "learning_rate": 0.00016,
+      "loss": 9.5341,
+      "step": 8
+    },
+    {
+      "epoch": 0.000555118656612851,
+      "grad_norm": 163.04898071289062,
+      "learning_rate": 0.00018,
+      "loss": 8.9825,
+      "step": 9
+    },
+    {
+      "epoch": 0.000555118656612851,
+      "eval_loss": 2.6047780513763428,
+      "eval_runtime": 55.0856,
+      "eval_samples_per_second": 123.934,
+      "eval_steps_per_second": 61.976,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 32989422551040.0,
+  "total_flos": 49867731763200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null