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:e8b94780c3cf245dfe157c3d068aebe0a7932b167db5d2b62e1f9f8286b4bb86
+oid sha256:07efcb239bf95861e2c3de9937de52f1cc63d97c2f77276ae04c2db6554c8a6d
 size 124756544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc49742d8acd25b9f3a0970d5d5a0d215cb72234b70cae74ff91cc7a742c82c
+oid sha256:bc666f53956dd14fd9275bd9c4991c19c98d6436f3348a3ccf170757a88bf73b
 size 63958740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b2a9a72f7f393abae05660f3d7d4956b52c8fcebe7e36b9bdf343e5a5d898f4
+oid sha256:d559250c31842a46cac390738afd0fa9c8572aef1ec90ad52af762fd9a38e34e
 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": 0.006120527306967985,
+  "epoch": 0.01224105461393597,
   "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": 9.388,
       "eval_steps_per_second": 4.699,
       "step": 10
+    },
+    {
+      "epoch": 0.007062146892655367,
+      "grad_norm": 0.8888987302780151,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.6859,
+      "step": 15
+    },
+    {
+      "epoch": 0.009416195856873822,
+      "grad_norm": 1.3303650617599487,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.9099,
+      "step": 20
+    },
+    {
+      "epoch": 0.009416195856873822,
+      "eval_loss": 3.8060638904571533,
+      "eval_runtime": 95.3447,
+      "eval_samples_per_second": 9.387,
+      "eval_steps_per_second": 4.699,
+      "step": 20
+    },
+    {
+      "epoch": 0.011770244821092278,
+      "grad_norm": 1.7675096988677979,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.6147,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4287495017594880.0,
+  "total_flos": 8574990035189760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null