Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a95e373cb592a44db7858f3fb1b76af06f848c8b9b8d8fa180a1fcca3d1584
+oid sha256:cb1a87bf1d9b088fc0b8a1225a257a0bcf29fd066f5efeb430aafda9f7257dea
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e635c548ef4505eed39c8665751bd37eebf0f7bcafe1b38fa151d6af4af0e6
+oid sha256:a8f65dcd49ae8ab84935771910d3039e7f87354e1b0bf11e71aa8402fc0bffb2
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe857a15cfad11d521d686079650bc523522af67539d91db4012db6206f54275
+oid sha256:aa382952e0adbb7e7abb917278c0a70d8bfd97851369da627797b4983c8f9cb6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016842105263157894,
+  "epoch": 0.03368421052631579,
   "eval_steps": 7,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 3.2529,
       "step": 9
+    },
+    {
+      "epoch": 0.020210526315789474,
+      "grad_norm": 2.081219434738159,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.5259,
+      "step": 12
+    },
+    {
+      "epoch": 0.023578947368421053,
+      "eval_loss": 1.79923677444458,
+      "eval_runtime": 50.5853,
+      "eval_samples_per_second": 4.942,
+      "eval_steps_per_second": 2.471,
+      "step": 14
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 2.057396411895752,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9331,
+      "step": 15
+    },
+    {
+      "epoch": 0.03031578947368421,
+      "grad_norm": 1.3836475610733032,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.2657,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347792213606400.0,
+  "total_flos": 1.26955844272128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null