Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0582b7116b5dba8d072bc5a61e35f410c2d7581197fe547f51eeb608d04e84a7
+oid sha256:7243e6d9f92f57ccc92a5e5a11449b180d0953cdfd694387bf9b423db4407d88
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5b80eeab7ab8804236514250b8ad4dbc3e815e14b8bc74007712b5c14a67cd2
+oid sha256:eaa02ae495268d33be2ba170ba7def7840b3b8fec78e9b5a576ee37a5d4540b0
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:227351a4a0f5e17a782ad32abba803fb205cd2e0e28f1f58c0fc8312b290de5f
+oid sha256:bc38aba70c31a73a7fef153a0ca565ccbffcd60ca74b3f258e9cb2b75e2b81f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0020242914979757085,
+  "epoch": 0.004048582995951417,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 7.684,
       "eval_steps_per_second": 0.96,
       "step": 9
+    },
+    {
+      "epoch": 0.002699055330634278,
+      "grad_norm": 3.335261821746826,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 3.6606,
+      "step": 12
+    },
+    {
+      "epoch": 0.0033738191632928477,
+      "grad_norm": 3.0242624282836914,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 3.377,
+      "step": 15
+    },
+    {
+      "epoch": 0.004048582995951417,
+      "grad_norm": 2.4873292446136475,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 3.1263,
+      "step": 18
+    },
+    {
+      "epoch": 0.004048582995951417,
+      "eval_loss": 0.7899854779243469,
+      "eval_runtime": 873.2265,
+      "eval_samples_per_second": 8.575,
+      "eval_steps_per_second": 1.072,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2656330976264192e+16,
+  "total_flos": 2.5312661952528384e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null