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:e33924f9cdb98a93251b06b94c0849f3fba614512f1298d1d0a9f9c893679636
+oid sha256:07d30939326e816a189b26f5655c153ee8727420c9c4defc5a455d436c10854d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c8b327c3a50ead211e7dbe60f073fa972e3c33c42e6f0f0f9a7efb0ad88925
+oid sha256:d12b37a3b707886434c9516a68593a7e771e66a2f37aa23582aa82a06ced76d9
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793e49fa41f48955d210aed6c8e1fbdcac43ce6a8f0ab68ba7c6dfbae402f000
+oid sha256:04aa846b05680e03795b2088d18a8b9d01ae35f26e41f6a393a79e7cdb395e61
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001568396804391511,
+  "epoch": 0.0023525952065872667,
   "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": 6.316,
       "eval_steps_per_second": 3.158,
       "step": 6
+    },
+    {
+      "epoch": 0.0018297962717900961,
+      "grad_norm": 0.7309572696685791,
+      "learning_rate": 7e-05,
+      "loss": 0.1376,
+      "step": 7
+    },
+    {
+      "epoch": 0.0020911957391886813,
+      "grad_norm": 1.0636768341064453,
+      "learning_rate": 8e-05,
+      "loss": 0.1193,
+      "step": 8
+    },
+    {
+      "epoch": 0.0023525952065872667,
+      "grad_norm": 0.42810970544815063,
+      "learning_rate": 9e-05,
+      "loss": 0.0449,
+      "step": 9
+    },
+    {
+      "epoch": 0.0023525952065872667,
+      "eval_loss": NaN,
+      "eval_runtime": 1020.1784,
+      "eval_samples_per_second": 6.316,
+      "eval_steps_per_second": 3.158,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.5610589610901504e+16,
+  "total_flos": 5.378682805813248e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null