Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d56e96d448484b3a5ff460b50a564fdcb1a524608b85aeeaed512553bb1e75b5
+oid sha256:6980d9cb6578d5a45c451abfa4b28749e0e69ddada4527c1d325b81416221f68
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:360852f0a3cd6c3521066a822f380c3bd32121e03a019d99fe4eee24af2b334a
+oid sha256:c67d0c2b0ec893fb4cdb2a72036fd20fadca00f782e395d7dbfc5c60269fa4d7
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ee9996d7e390a7bc351c99a8f5ef4c8f78fb4be6dc54143fb3bec2131dce68b
+oid sha256:57be20421170f25d7026a038ec19d4695b917e87817a59b2840e1f4390ced113
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07964601769911504,
+  "epoch": 0.1592920353982301,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 7.813,
       "eval_steps_per_second": 1.974,
       "step": 9
+    },
+    {
+      "epoch": 0.10619469026548672,
+      "grad_norm": 16.30251693725586,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 4.4943,
+      "step": 12
+    },
+    {
+      "epoch": 0.13274336283185842,
+      "grad_norm": 2.594444513320923,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 1.7033,
+      "step": 15
+    },
+    {
+      "epoch": 0.1592920353982301,
+      "grad_norm": 0.005044514779001474,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0137,
+      "step": 18
+    },
+    {
+      "epoch": 0.1592920353982301,
+      "eval_loss": 0.0003469553776085377,
+      "eval_runtime": 12.2289,
+      "eval_samples_per_second": 7.769,
+      "eval_steps_per_second": 1.963,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.255823024062464e+16,
+  "total_flos": 2.479445457764352e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null