Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:509c0d4cedc39a7d5f04e46393cd74eb9d4493e19ce2ac547c4b6af361a3a5ab
+oid sha256:007f6b24edc41404479f5bb854ec2cd4a1978cd2337d057ee563433199c9b77d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00f9475d98a5a69c207f26315cfcf59b80d910ef69f9f66490768be95dffcdcb
+oid sha256:ef162a08746f5b07557989aa92c3ea24954b07ff9ead49acf3c7ae37695c9752
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5518b27092ab6aaacc0cc21ef2c162b93293f363ec7ec1be39604905ad54e10
+oid sha256:3b09a88054123c089ea7a12187c1a69bb1039c54e68994009c312791f99785e8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
+oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0355255603790283,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5681818181818182,
+  "best_metric": 1.0230828523635864,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.7102272727272727,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 12.008,
       "eval_steps_per_second": 1.505,
       "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 1.1733,
+      "step": 500
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.0230828523635864,
+      "eval_runtime": 124.322,
+      "eval_samples_per_second": 12.001,
+      "eval_steps_per_second": 1.504,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.2452348635136e+16,
+  "total_flos": 2.80842883485696e+16,
   "trial_name": null,
   "trial_params": null
 }