Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af70f7222c9cdf2e69819047e2aa13d72c772bd26f08a078d0fba3393893db62
+oid sha256:f3c549460f2352b0840c34e8087ed1a56d55058822c4640a721a9b46d68b93c4
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f592bfc075e83062ff92534db96d79b8185858049c8afbd40bd85c2d07d9aea
+oid sha256:446166174bae7855c669f468907c1ca21f637d9edeacae5364adbae3a691634a
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288a16e6d9d8c06d39eaaf028ab7ce6ab9c130eeb62c3121161c9ecb57cfd771
+oid sha256:0202e01efe8f13fd7b2c8ee3c96f603708af0ebe0527513b8b210324c785c8c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12931034482758622,
+  "epoch": 0.1724137931034483,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 10.843,
       "eval_steps_per_second": 1.39,
       "step": 15
+    },
+    {
+      "epoch": 0.15517241379310345,
+      "grad_norm": 12.68582534790039,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.2727,
+      "step": 18
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "eval_loss": 0.6887093782424927,
+      "eval_runtime": 17.9522,
+      "eval_samples_per_second": 10.862,
+      "eval_steps_per_second": 1.393,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.146497013481472e+16,
+  "total_flos": 2.861996017975296e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null