Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a09b86e33681c67569e6c335015aeced3094b21a42dd09edb0e5539274b93b
+oid sha256:37d18a82c3d76e317c375e8ce7148bcaadcbf107910ab35f1ce0e6d564ff158a
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc9f0d71a35978caeca0680692936ceede33cc9fa27b44315ff4f67be96e3b8
+oid sha256:47213a62fa9c69f5f69eec1acd34b9c6ae3c097151b14c86c8a3f84ed7fff05f
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232b35a26bef178eec09e66c24898c4e539aa83018f1fe5fb9337bcbf7093c76
+oid sha256:38b203c487a223bbc58ff68bdb5abcc1dc73df8232401ff6f5ebb4ec48efbf8d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01403755044744692,
+  "epoch": 0.01754693805930865,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 463.084,
       "eval_steps_per_second": 57.886,
       "step": 20
+    },
+    {
+      "epoch": 0.014739427969819266,
+      "grad_norm": 0.08976900577545166,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 10.3723,
+      "step": 21
+    },
+    {
+      "epoch": 0.016845060536936303,
+      "grad_norm": 0.10850024223327637,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 10.3716,
+      "step": 24
+    },
+    {
+      "epoch": 0.01754693805930865,
+      "eval_loss": 10.368788719177246,
+      "eval_runtime": 5.2374,
+      "eval_samples_per_second": 458.24,
+      "eval_steps_per_second": 57.28,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2286788542464.0,
+  "total_flos": 2844541845504.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null