Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e46b41b65f6a46e901b45ec03d9a2cbb00b450a015c6575b41e48bd80427cc1
+oid sha256:423f9b882745e0a9ec74bbdbf9fb25a7268257af03310895a21f0ebeae44dcc3
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa358ceb32337b9337d51b4ccdc70a58b53644d4301dc2c6bda3f4a97bec1da3
+oid sha256:711e5edd124de36d9cf7b6c8e5eacb0cac6a31d9356f01a159cc9b68fd287bb1
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2388403cc9a223a5303b8d029c440c6329c884a92917023e5b1b367f23fa7bde
+oid sha256:175fdf30b8c703f05d00042db9939bec57bbba272d0f4b5d546a8649ed6d732e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00414871549385671,
+  "epoch": 0.00829743098771342,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 30.118,
       "eval_steps_per_second": 15.059,
       "step": 10
+    },
+    {
+      "epoch": 0.004786979415988511,
+      "grad_norm": 0.13882894814014435,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.603,
+      "step": 15
+    },
+    {
+      "epoch": 0.006382639221318015,
+      "grad_norm": 0.1524791419506073,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.6305,
+      "step": 20
+    },
+    {
+      "epoch": 0.006382639221318015,
+      "eval_loss": 0.6011084318161011,
+      "eval_runtime": 43.967,
+      "eval_samples_per_second": 30.023,
+      "eval_steps_per_second": 15.011,
+      "step": 20
+    },
+    {
+      "epoch": 0.007978299026647519,
+      "grad_norm": 0.13234758377075195,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.5891,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 658664343994368.0,
+  "total_flos": 1310933888532480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null