Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f4e51bed17eb56869c2fc2d96a7f8e8b70aa63acaf71803357ce324b1d9b8e
+oid sha256:22a09b86e33681c67569e6c335015aeced3094b21a42dd09edb0e5539274b93b
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbbdcd95cb688f6db2ee6f2752d625eaf67d6d2eaf9d7fea1708f3fc3161077f
+oid sha256:cbc9f0d71a35978caeca0680692936ceede33cc9fa27b44315ff4f67be96e3b8
 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": 458.977,
       "eval_steps_per_second": 57.372,
       "step": 15
+    },
+    {
+      "epoch": 0.012633795402702229,
+      "grad_norm": 0.09788131713867188,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.375,
+      "step": 18
+    },
+    {
+      "epoch": 0.01403755044744692,
+      "eval_loss": 10.371757507324219,
+      "eval_runtime": 5.1826,
+      "eval_samples_per_second": 463.084,
+      "eval_steps_per_second": 57.886,
+      "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