Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2944cf54ed544d1176a4e30b9ed7399ec23f6ab42fb847c01bd83e717832f376
+oid sha256:9889b903d1a84241f6de9a4633a5a74580871e06fcf56c7242ee68563b54e1f0
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2673ae1fc9e1717a7293559e63bdcc598a1ce77a628ce2a1a7ca8dcd4f96417f
+oid sha256:6b9e97f68af56ded89a7904b7fde8cb57af9f3ba0b07a55980472ce040e65407
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd93ad71d1e4da2e65f4e2c9390e9d7b7bc2ea6079b0f1bd60a10893bb8881fb
+oid sha256:323eed6e808e7833f72c9c158993f7f51694aa2d568e26d624f9902a8b7f9ab0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025078369905956112,
+  "epoch": 0.03761755485893417,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 13.507,
       "eval_steps_per_second": 1.688,
       "step": 10
+    },
+    {
+      "epoch": 0.030094043887147336,
+      "grad_norm": 0.6223757266998291,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 1.7599,
+      "step": 12
+    },
+    {
+      "epoch": 0.03761755485893417,
+      "grad_norm": 0.5316658020019531,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.7352,
+      "step": 15
+    },
+    {
+      "epoch": 0.03761755485893417,
+      "eval_loss": 1.6541856527328491,
+      "eval_runtime": 49.8208,
+      "eval_samples_per_second": 13.488,
+      "eval_steps_per_second": 1.686,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.345767604224e+16,
+  "total_flos": 2.0522955964416e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null