Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b4a5a9bcb8a417e61ad120189aa54a93d426b04e4470199acd09afa16dbf320
+oid sha256:663925bed6ba8b3bbe59020859f97e284fe0325138795e5e62dec3c8bd7cc460
 size 3029024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dacbb0ebde2add8e836c94c6e55cea16c6da5c43ac59cb4cf1681073c6df1904
+oid sha256:132ec7d2df7ed8c349fcdd109e275f05514c669d68cb903adf4de832cea72ccb
 size 1663290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da16db7f175cbeb8ab1c1defb517314066de6eb4ba36824780a8372e0d8b72d
+oid sha256:8ae7ea429f3e44d20701513020b1a327873eaf55a7493d83e01ce4ef5a7f7732
 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": 0.11396011396011396,
+  "epoch": 0.17094017094017094,
   "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": 117.406,
       "eval_steps_per_second": 15.072,
       "step": 10
+    },
+    {
+      "epoch": 0.13675213675213677,
+      "grad_norm": 18.148941040039062,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 7.354,
+      "step": 12
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 17.978164672851562,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 5.8882,
+      "step": 15
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "eval_loss": 5.262752056121826,
+      "eval_runtime": 1.2623,
+      "eval_samples_per_second": 117.251,
+      "eval_steps_per_second": 15.052,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8503594844160.0,
+  "total_flos": 12101269585920.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null