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:c4c79e9c45d87a2fd69b4e76d17dc407cf2410143881615a05bd21d3d349a6d2
+oid sha256:b43635177605b74a69081652a2317e912b69595c88c8902696ca2035eaaff791
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f18691f48df363e0b501810030ed9f13581c6dad30dacbff46a509fb28b2c9
+oid sha256:46f5841ca7e59d67695536048a15ed85f4762ab51ada73624fc57111798a9f60
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:22cdbc90fe5ab190ddc8c8d596470e7106be9ee2374df85af28061b6a32f91c4
 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": 0.145985401459854,
+  "epoch": 0.21897810218978103,
   "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": 192.195,
       "eval_steps_per_second": 25.069,
       "step": 10
+    },
+    {
+      "epoch": 0.17518248175182483,
+      "grad_norm": 0.22880136966705322,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 11.921,
+      "step": 12
+    },
+    {
+      "epoch": 0.21897810218978103,
+      "grad_norm": 0.2586361765861511,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.9164,
+      "step": 15
+    },
+    {
+      "epoch": 0.21897810218978103,
+      "eval_loss": 11.910693168640137,
+      "eval_runtime": 0.6212,
+      "eval_samples_per_second": 185.133,
+      "eval_steps_per_second": 24.148,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 48208281600.0,
+  "total_flos": 72312422400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null