Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328078cf723ccaeea844dee1a2b86acb48294c5941287893d0a89027bedcb1b5
+oid sha256:5479e3fb1429f6f1432a3f9cbbf5788e5a6ebdf6b2766bbe5c723ea6589a5ead
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f153f64fc5ddc1092c3e0aa807321bac0897bd1f489ef52bf78c66dcf37447
+oid sha256:d02790c5ffa334edf2879f8bd8513d07be98c168dc224ba8eadd8818b78205bf
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8ae2cb1e582e9310963ad3ed8b41f0acd771a18e5c2e6e9ee8cbbe52fdc3cd
+oid sha256:359d0ddb346e1a051d153b9361e52227f5a93bfd11d7d59f8d34fe81bcaff9e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027472527472527472,
+  "epoch": 0.054945054945054944,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 33.691,
       "eval_steps_per_second": 16.846,
       "step": 5
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 0.02454882673919201,
+      "learning_rate": 6e-05,
+      "loss": 11.932,
+      "step": 6
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 0.02835436351597309,
+      "learning_rate": 7e-05,
+      "loss": 11.9315,
+      "step": 7
+    },
+    {
+      "epoch": 0.04395604395604396,
+      "grad_norm": 0.026226777583360672,
+      "learning_rate": 8e-05,
+      "loss": 11.9322,
+      "step": 8
+    },
+    {
+      "epoch": 0.04945054945054945,
+      "grad_norm": 0.027679918333888054,
+      "learning_rate": 9e-05,
+      "loss": 11.9327,
+      "step": 9
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "grad_norm": 0.025617027655243874,
+      "learning_rate": 0.0001,
+      "loss": 11.9329,
+      "step": 10
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "eval_loss": 11.931732177734375,
+      "eval_runtime": 18.2319,
+      "eval_samples_per_second": 33.677,
+      "eval_steps_per_second": 16.839,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 59957575680.0,
+  "total_flos": 119915151360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null