Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e311d145c06083110e04f40ff9bf5933c15e26025fd1ab59f4892dd5cd0e3a7
+oid sha256:1b1ec4423671a6f225577326f04fd9d64b6e0928ca423d82d1739f5a61d39c9b
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68baf4bbe632db79f66fea9b467b3a76d6bdfa40df4447bce1ca066a5ffc04a8
+oid sha256:5678a642de0f846174b19dcdcb3798db37d89f29a029963f4eadec103d7ac7a9
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc6dab0f4dc4a00c15974f378193661a0a163003730e8304a27e1c7de229ff4
+oid sha256:232b35a26bef178eec09e66c24898c4e539aa83018f1fe5fb9337bcbf7093c76
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01052816283558519,
+  "epoch": 0.01403755044744692,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 452.642,
       "eval_steps_per_second": 56.58,
       "step": 15
+    },
+    {
+      "epoch": 0.012633795402702229,
+      "grad_norm": 0.11386722326278687,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3747,
+      "step": 18
+    },
+    {
+      "epoch": 0.01403755044744692,
+      "eval_loss": 10.371191024780273,
+      "eval_runtime": 5.2459,
+      "eval_samples_per_second": 457.498,
+      "eval_steps_per_second": 57.187,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1729035239424.0,
+  "total_flos": 2286788542464.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null