Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5082e216d918cb155f07a0ee9dcc74d8b33063c623f68526dbbb0c4660ac101d
+oid sha256:57df0ec4640354d1ed908854c4cfa27cdd775f978430f8f06a519a77d74ad5b0
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10ac7c4afa049112e9bccd4709339863be1042a9c1356e65f0a6d33f943eb68
+oid sha256:a9c901e6f5d9e9111a0422001e1c1305463de4caba2a354b6efc7a96d567ca21
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c455b0fa8104f640543b248b2fbe706d034e1d6aeb5559e591ec277167811d01
+oid sha256:20677e5e2e60410329c087c893abef46418602f333d1dc730af126965461fbab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe3b760b122c9a956a1bee0ed9d65cd87b93bd52b73b0ebef3ebe29b040300a
+oid sha256:eea7f623cd481ba36c9dac2e99157b3024c8f34f519d9ea8f089678f3424e388
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6405693950177936,
+  "epoch": 0.6470397929472662,
   "eval_steps": 386,
-  "global_step": 495,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3488,6 +3488,41 @@
       "learning_rate": 9.667162991617633e-05,
       "loss": 0.897,
       "step": 495
+    },
+    {
+      "epoch": 0.6418634746036881,
+      "grad_norm": 0.7679833173751831,
+      "learning_rate": 9.665682330077551e-05,
+      "loss": 0.84,
+      "step": 496
+    },
+    {
+      "epoch": 0.6431575541895826,
+      "grad_norm": 0.9792498350143433,
+      "learning_rate": 9.664198496305517e-05,
+      "loss": 0.9597,
+      "step": 497
+    },
+    {
+      "epoch": 0.6444516337754772,
+      "grad_norm": 0.9134929180145264,
+      "learning_rate": 9.662711491310398e-05,
+      "loss": 1.0342,
+      "step": 498
+    },
+    {
+      "epoch": 0.6457457133613718,
+      "grad_norm": 0.7805169224739075,
+      "learning_rate": 9.661221316103224e-05,
+      "loss": 0.8463,
+      "step": 499
+    },
+    {
+      "epoch": 0.6470397929472662,
+      "grad_norm": 0.8533938527107239,
+      "learning_rate": 9.659727971697174e-05,
+      "loss": 0.8315,
+      "step": 500
     }
   ],
   "logging_steps": 1,
@@ -3507,7 +3542,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.5337889998831616e+17,
+  "total_flos": 5.58968585846784e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null