Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be5e064b7165dae266d7e82dfcd4993e33d4d8906e20feca05b36df8decf6d5e
+oid sha256:6404affd48a52bc5082ef3d7b71f630b3b1082bedf7e0a55c31c5f4180552442
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aadd1fe822b829f47f6d387a6bc2066be09991f1153385f8e4d76ce719051ea
+oid sha256:185070f38b21569af6a22a98d0908585219f3241095ec35cf41a17420e5703c3
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4de4373f558eed2f93d1cb972a5487fc8c6ec3f8011620e65273d44292ea9d
+oid sha256:8f955ef1757b7af43a664773656d9c93de93be247e1dc6e1fdf5ebb3680067d1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19726027397260273,
+  "epoch": 0.2958904109589041,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 11.574,
       "eval_steps_per_second": 1.503,
       "step": 18
+    },
+    {
+      "epoch": 0.23013698630136986,
+      "grad_norm": 1.2642624378204346,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 0.4035,
+      "step": 21
+    },
+    {
+      "epoch": 0.26301369863013696,
+      "grad_norm": 0.6770612001419067,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.2893,
+      "step": 24
+    },
+    {
+      "epoch": 0.2958904109589041,
+      "grad_norm": 0.7164978384971619,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.2385,
+      "step": 27
+    },
+    {
+      "epoch": 0.2958904109589041,
+      "eval_loss": 0.2964910566806793,
+      "eval_runtime": 13.3316,
+      "eval_samples_per_second": 11.552,
+      "eval_steps_per_second": 1.5,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7608197015535616e+16,
+  "total_flos": 4.179574270407475e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null