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:afb312d6caa3d1bee581f967dd1431d04681ee66864ae5f4c64f066d18465b55
+oid sha256:ba90c16edf6c24480dcfc422bac0e83e5e3d08e5cf7d1b3ad2d64e1f28d11d0f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a6917cea3eecf51c00c302fca776210c1d6c4cef4537e392cf16c89424500b
+oid sha256:491c2392e762f9449de6712cd45b3bd8fe63e47c02f2b3d59b94f892aa5aaea9
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75b7fe1ed9d1a988cf26f4ac07eea6ab570c3b37f92d1c4968cd69d6c61bd803
+oid sha256:891155de6377a4508f22e954f15f57ef4af67ae2e130e02796b781a8ce5af0a1
 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": 0.022263450834879406,
+  "epoch": 0.03339517625231911,
   "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": 4.223,
       "eval_steps_per_second": 2.112,
       "step": 6
+    },
+    {
+      "epoch": 0.025974025974025976,
+      "grad_norm": 15.347859382629395,
+      "learning_rate": 0.00014,
+      "loss": 3.3472,
+      "step": 7
+    },
+    {
+      "epoch": 0.029684601113172542,
+      "grad_norm": 12.538643836975098,
+      "learning_rate": 0.00016,
+      "loss": 2.6497,
+      "step": 8
+    },
+    {
+      "epoch": 0.03339517625231911,
+      "grad_norm": 10.789239883422852,
+      "learning_rate": 0.00018,
+      "loss": 1.4241,
+      "step": 9
+    },
+    {
+      "epoch": 0.03339517625231911,
+      "eval_loss": 0.3812977075576782,
+      "eval_runtime": 27.2928,
+      "eval_samples_per_second": 4.177,
+      "eval_steps_per_second": 2.088,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8902647402725376.0,
+  "total_flos": 1.3353971104088064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null