Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a59db3b7bc5149d973c96c280777f3990754bdcec9f299521098f77e1035f5
+oid sha256:07d0001978f7f34de62fbd900eb8a172a4417b9414b4e0c28c67ae6bffb9ea5d
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:340a393736658cad87778098f4afe112dfe90b7d219b2fe060ae50044f1ce98b
+oid sha256:5f2acc403df79cfaf7d1beba6586075c055971d4dc30c4d9e1bc6fac257de195
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d063b22e3f0d47453d510e6d69d6b5c7549b2f69d04acdb0050a8e9f517c0aac
+oid sha256:2833948efdf50a46433c6293d8c3846881e32eddfd503abe75bb0fae1ed0507f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d99dc7a150ff6ed818c8735e9e9061e757b4b841b8d74bde2c9d7a2195ff136
+oid sha256:fab1f30942a5e2bb9a9e5cc3477ef48cdcd39a7b78f8a45a46db0926bdbf2b4f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028425452856479332,
+  "epoch": 0.03158383650719926,
   "eval_steps": 17,
-  "global_step": 153,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -444,6 +444,49 @@
       "eval_samples_per_second": 32.557,
       "eval_steps_per_second": 4.072,
       "step": 153
+    },
+    {
+      "epoch": 0.028982814677194612,
+      "grad_norm": 0.7660591006278992,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.6667,
+      "step": 156
+    },
+    {
+      "epoch": 0.02954017649790989,
+      "grad_norm": 0.6604006290435791,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 0.6237,
+      "step": 159
+    },
+    {
+      "epoch": 0.030097538318625175,
+      "grad_norm": 0.8076897263526917,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6899,
+      "step": 162
+    },
+    {
+      "epoch": 0.030654900139340455,
+      "grad_norm": 0.8138939738273621,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.606,
+      "step": 165
+    },
+    {
+      "epoch": 0.031212261960055738,
+      "grad_norm": 0.7922996878623962,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 0.7121,
+      "step": 168
+    },
+    {
+      "epoch": 0.03158383650719926,
+      "eval_loss": 0.6988500356674194,
+      "eval_runtime": 278.3236,
+      "eval_samples_per_second": 32.574,
+      "eval_steps_per_second": 4.074,
+      "step": 170
     }
   ],
   "logging_steps": 3,
@@ -463,7 +506,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.40418605318144e+16,
+  "total_flos": 5.965192033940275e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null