Training in progress, step 189, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51588d5886ef3b767841df9146b5c76d98518b6f622e12003a4221539dcfbf82
+oid sha256:9d7d093658435cedba7ec4df3bd95238efc79e9c02844dcd644a6f77c5da0217
 size 628216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13be2dfdfef9a31db0a3f35725cbcb18029fd5569348871c46c0288f5cca1c4c
+oid sha256:365db6611fa226642bef07db7bc38c04744fac4bafd9902f0e02778919233426
 size 352122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a1229e947f829fb64e83f81ccba01f4ad40a299cc6fb64b3b927bbcfd42e1c
+oid sha256:b073eae0856d95a78bd1210e484de480f18e699d417df6566c139d5389912738
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
+oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010289494099873423,
+  "epoch": 0.015434241149810134,
   "eval_steps": 63,
-  "global_step": 126,
+  "global_step": 189,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,56 @@
       "eval_samples_per_second": 359.091,
       "eval_steps_per_second": 179.545,
       "step": 126
+    },
+    {
+      "epoch": 0.01061614470621861,
+      "grad_norm": 0.310713529586792,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 10.7422,
+      "step": 130
+    },
+    {
+      "epoch": 0.011432771222081582,
+      "grad_norm": 0.2092239260673523,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 10.7337,
+      "step": 140
+    },
+    {
+      "epoch": 0.012249397737944551,
+      "grad_norm": 0.19805459678173065,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 10.7418,
+      "step": 150
+    },
+    {
+      "epoch": 0.013066024253807521,
+      "grad_norm": 0.179554283618927,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 10.7348,
+      "step": 160
+    },
+    {
+      "epoch": 0.01388265076967049,
+      "grad_norm": 0.22178767621517181,
+      "learning_rate": 4.8160743168947496e-05,
+      "loss": 10.7329,
+      "step": 170
+    },
+    {
+      "epoch": 0.014699277285533462,
+      "grad_norm": 0.23290759325027466,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 10.7324,
+      "step": 180
+    },
+    {
+      "epoch": 0.015434241149810134,
+      "eval_loss": 10.731443405151367,
+      "eval_runtime": 7.1741,
+      "eval_samples_per_second": 359.346,
+      "eval_steps_per_second": 179.673,
+      "step": 189
     }
   ],
   "logging_steps": 10,
@@ -134,7 +184,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8069132058624.0,
+  "total_flos": 12061004267520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null