Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5094ffec2321f19e18bcc19af50d0426df4d49111221a1a228bbd0c7b98136
+oid sha256:6d59b9e1a92f7305939d2f0c45593d4fc76b32fb9de6ec1dcb7077fadb1b75aa
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c43bd7d752560faa3652929d9424a50a5320578193f838e75b54f8f3cc111f2
+oid sha256:171cf63a1306630d3e2d026d59e582e605a24b135907a360761e948dadc54eaa
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8448d25449f472557b0939c1cf359c33ece66f8152b147429bbab35b50b33bf2
+oid sha256:f4d5a61f54fc87372e46a202a94df31ed2db3cd5d6d0426b43d1ce44b91621bb
 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": 0.0005847953216374269,
+  "epoch": 0.0008771929824561404,
   "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": 317.994,
       "eval_steps_per_second": 158.997,
       "step": 6
+    },
+    {
+      "epoch": 0.0006822612085769981,
+      "grad_norm": 0.19658085703849792,
+      "learning_rate": 7e-05,
+      "loss": 11.7631,
+      "step": 7
+    },
+    {
+      "epoch": 0.0007797270955165692,
+      "grad_norm": 0.24124307930469513,
+      "learning_rate": 8e-05,
+      "loss": 11.7583,
+      "step": 8
+    },
+    {
+      "epoch": 0.0008771929824561404,
+      "grad_norm": 0.15978692471981049,
+      "learning_rate": 9e-05,
+      "loss": 11.7894,
+      "step": 9
+    },
+    {
+      "epoch": 0.0008771929824561404,
+      "eval_loss": 11.758536338806152,
+      "eval_runtime": 20.4001,
+      "eval_samples_per_second": 317.645,
+      "eval_steps_per_second": 158.822,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 458325098496.0,
+  "total_flos": 687487647744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null