Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe2c1413d067ed3e914a3c6865f247815b864a395acb9e59792a4bb2c3f0167
+oid sha256:52b09e92d5bb81698a317471c9da9378d7cadfda3fde4e696dae3506dbe441aa
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97abf77192149eca21940f3cf9c567711e8675d3200265c15eef3d535c2ce37d
+oid sha256:e5316e2ea56fe084fdfdddb5ab7f1c0996281f4bb372da6965767b4e682d8249
 size 101107578

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b54133148dbee2f9976dbcc37f669cadd4f360094c47c9373fa7ada39d9d95c1
+oid sha256:7c04d044dd1828bae4a7219763c171f8e3b92a1b129b7f62c011e4811f5c690b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003745283283864383,
+  "epoch": 0.0007490566567728766,
   "eval_steps": 8,
-  "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": 9e-05,
       "loss": 1.9006,
       "step": 9
+    },
+    {
+      "epoch": 0.000449433994063726,
+      "grad_norm": 0.22203008830547333,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.5323,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005617924925796575,
+      "grad_norm": 0.24594427645206451,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.684,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005992453254183013,
+      "eval_loss": 1.6712545156478882,
+      "eval_runtime": 475.179,
+      "eval_samples_per_second": 23.661,
+      "eval_steps_per_second": 11.831,
+      "step": 16
+    },
+    {
+      "epoch": 0.0006741509910955889,
+      "grad_norm": 0.277011901140213,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.7029,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 579019934269440.0,
+  "total_flos": 1119438539587584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null