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:f269de2521f0d1e002ee3d77fa3b033214ec5f9b431159cdf52b7fdea1f0cf3d
+oid sha256:7bc7a3dcaa0936d88e3c4e6301833d8df12db7c199911f4fe07ffeec9b60201f
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd64aba07e8746adb3af4fc58842f2353f1d75f2d93bdf728981a87ab557058a
+oid sha256:9169737eff5da66f3d68a19bab412e4b34d0490c48a12f738affef168e29ae99
 size 39398

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab5744ac991c6a51cb31bf1cd57abcd6eb671ae5b35688f9556c3a2db19ad7be
+oid sha256:a8931450438ae8b2419522305b04898208d1e1d8a63833a5b129ef7578886f1d
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8846f3ddcbef0127b3a41ab63d4857dec886e87dd5c82dc9ff49a951919ee7aa
+oid sha256:ea7a5d7f6a3e29c541f8194ea05fcd850e8a829cfe8d61c1d58566b8e5a092cf
 size 14512

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": 0.006730229949523275,
+  "epoch": 0.010095344924284913,
   "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": 458.556,
       "eval_steps_per_second": 114.792,
       "step": 6
+    },
+    {
+      "epoch": 0.007851934941110488,
+      "grad_norm": 0.016139866784214973,
+      "learning_rate": 0.00014,
+      "loss": 11.927,
+      "step": 7
+    },
+    {
+      "epoch": 0.0089736399326977,
+      "grad_norm": 0.016835955902934074,
+      "learning_rate": 0.00016,
+      "loss": 11.9367,
+      "step": 8
+    },
+    {
+      "epoch": 0.010095344924284913,
+      "grad_norm": 0.01244762446731329,
+      "learning_rate": 0.00018,
+      "loss": 11.9306,
+      "step": 9
+    },
+    {
+      "epoch": 0.010095344924284913,
+      "eval_loss": 11.931243896484375,
+      "eval_runtime": 1.6456,
+      "eval_samples_per_second": 456.359,
+      "eval_steps_per_second": 114.242,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1447477248.0,
+  "total_flos": 2156445696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null