Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bdbcce4c51cc30592eb0e6da2ce93adb0554d95dbdd5ccca6d42982fe451ee7
+oid sha256:155b9086a463a09abb92e23c5a777b377255eaaf766868cace9702e5185a7ea7
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd62d838d30c008345f9ae8cd506ac0da1b5fe45e33486e8d1274073e6cd5788
+oid sha256:58114a34c6c3e1055c7caf68d5fba071eeec92cded273ec6b1641b24cbd27a44
 size 7086458

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc4ed8003cee3857b883d2882928713db796eb24640eb9f44e903a7f5259703
+oid sha256:bd0214bbe109dca9c79f696d3784ba0601ee4dda3eb56b95625502e9d6ad1cc2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02004008016032064,
+  "epoch": 0.03006012024048096,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 25.19,
       "eval_steps_per_second": 12.603,
       "step": 10
+    },
+    {
+      "epoch": 0.022044088176352707,
+      "grad_norm": 1.0535022020339966,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.4243,
+      "step": 11
+    },
+    {
+      "epoch": 0.02404809619238477,
+      "grad_norm": 1.0760126113891602,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.4287,
+      "step": 12
+    },
+    {
+      "epoch": 0.026052104208416832,
+      "grad_norm": 1.047857403755188,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 3.4245,
+      "step": 13
+    },
+    {
+      "epoch": 0.028056112224448898,
+      "grad_norm": 0.9840763807296753,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.2842,
+      "step": 14
+    },
+    {
+      "epoch": 0.03006012024048096,
+      "grad_norm": 0.9731857180595398,
+      "learning_rate": 5e-05,
+      "loss": 3.2958,
+      "step": 15
+    },
+    {
+      "epoch": 0.03006012024048096,
+      "eval_loss": 3.302708148956299,
+      "eval_runtime": 66.7476,
+      "eval_samples_per_second": 25.184,
+      "eval_steps_per_second": 12.6,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2221401377341440.0,
+  "total_flos": 3332102066012160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null