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:d1ff5894c2514a95f86e6b612ebd365a6b9c1d90547cf7a031e294d332ad449e
+oid sha256:682347369938a6b248be485042904639060d57afc95863e315a0254c0fc84d85
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f17ea3cf88576e35dd5c383c52acf6cb249d63db58f1fecedbbb6c780a7a6f
+oid sha256:c029563114eddb6462262929e4ae0c034f88455adf24d731fba7ec07fd7615db
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6425776668305c004e03f9019bc158962fb5b8b75d34b017106a5817399724df
+oid sha256:34ad3b13fe0fb3cf191e6f3eee9378319e3ba008cef668b62e2ba7e986b55ec0
 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": 0.01885902876001886,
+  "epoch": 0.028288543140028287,
   "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": 12.972,
       "eval_steps_per_second": 1.627,
       "step": 10
+    },
+    {
+      "epoch": 0.02263083451202263,
+      "grad_norm": 0.3598170578479767,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 1.4709,
+      "step": 12
+    },
+    {
+      "epoch": 0.028288543140028287,
+      "grad_norm": 0.2836269438266754,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.2911,
+      "step": 15
+    },
+    {
+      "epoch": 0.028288543140028287,
+      "eval_loss": 1.324967384338379,
+      "eval_runtime": 68.8059,
+      "eval_samples_per_second": 12.979,
+      "eval_steps_per_second": 1.628,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.457435902476288e+16,
+  "total_flos": 2.168380245147648e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null