Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98905e7d37a8aa0d6df45ba681f3a2a4359e4336604bee4ffc227150b9806c95
+oid sha256:6c87775b5edcb585b28c4eddf54d4dce8265909ac975ae4e8fc2a1c79dad687a
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49deef8f299a331a25efff71e9b859f94ea84d718be78b8227128ff95c29df0d
+oid sha256:5c1c3428353a34d0c5b140915486f3aa259f22376c50e64b89b91fa5ea52e74f
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c509aaa365c9873a5507cd533df3abf62268c415e299cebaee5bfc9f5cea8a
+oid sha256:9bd09ace895178fe2265702e7f4382b90709d73d1ef6b0e69e6c37a98d08dcfd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
+oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06747891283973759,
+  "epoch": 0.10121836925960637,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 34.878,
       "eval_steps_per_second": 4.418,
       "step": 18
+    },
+    {
+      "epoch": 0.07872539831302718,
+      "grad_norm": 0.15399610996246338,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 1.9246,
+      "step": 21
+    },
+    {
+      "epoch": 0.08997188378631678,
+      "grad_norm": 0.18686576187610626,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 1.9773,
+      "step": 24
+    },
+    {
+      "epoch": 0.10121836925960637,
+      "grad_norm": 0.1838475912809372,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 2.0225,
+      "step": 27
+    },
+    {
+      "epoch": 0.10121836925960637,
+      "eval_loss": 1.988869071006775,
+      "eval_runtime": 12.9477,
+      "eval_samples_per_second": 34.755,
+      "eval_steps_per_second": 4.402,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5844294439010304.0,
+  "total_flos": 8726412244549632.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null