Training in progress, step 510, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b26d91313aaa896592f91528b4808810b4e31adaf596f7c4791511dfe0cd2bba
+oid sha256:5a44a782ea638c6f7e9dc51e718ea5f60364b15256a8cf012bd12a3e32e577b7
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a28ecb8a00c3df5f8b9b52ab5cf79dda76dbc10564ce05e7b895a08fb67ae152
+oid sha256:3d81439b95ab9fdfc28944c3f45684bab1b89a36ee16c058a71c1fbf8c0e50d5
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4abb51b574d8bd727a9685baa9a35f9e2ae27bf9668470e35b87cf1485a72cc
+oid sha256:cd7132b96ed38ba9b738ad147e8a862f64c2ac7a948dbbba18a7efce0585f901
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fddb3c6495e31ce8a45b6dfb6d508bbfc811e06668b6e6199da2ea35c0410ca7
+oid sha256:a13a5d867c4b3340715fb328361f350e2a0ea77e86afd98eac6d64dcb61c2c63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6535101908767389,
+  "epoch": 0.6599805888062116,
   "eval_steps": 386,
-  "global_step": 505,
+  "global_step": 510,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3558,6 +3558,41 @@
       "learning_rate": 9.652213747295906e-05,
       "loss": 0.8605,
       "step": 505
+    },
+    {
+      "epoch": 0.6548042704626335,
+      "grad_norm": 0.7796474695205688,
+      "learning_rate": 9.650701409094018e-05,
+      "loss": 0.803,
+      "step": 506
+    },
+    {
+      "epoch": 0.656098350048528,
+      "grad_norm": 0.8425498008728027,
+      "learning_rate": 9.649185908845818e-05,
+      "loss": 0.9324,
+      "step": 507
+    },
+    {
+      "epoch": 0.6573924296344226,
+      "grad_norm": 0.6857015490531921,
+      "learning_rate": 9.647667247581703e-05,
+      "loss": 0.8701,
+      "step": 508
+    },
+    {
+      "epoch": 0.658686509220317,
+      "grad_norm": 0.7896414995193481,
+      "learning_rate": 9.646145426334223e-05,
+      "loss": 0.7447,
+      "step": 509
+    },
+    {
+      "epoch": 0.6599805888062116,
+      "grad_norm": 0.7142564058303833,
+      "learning_rate": 9.644620446138077e-05,
+      "loss": 0.9221,
+      "step": 510
     }
   ],
   "logging_steps": 1,
@@ -3577,7 +3612,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.6455827170525184e+17,
+  "total_flos": 5.701479575637197e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null