Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76166dd110f948403481a165ffeebc91d567372862f2190fa405fdccf5b75ac8
+oid sha256:f1f1b5e82db627635867817c1d7fa2a2a829c358bbcaf6447eb82fbe5d2151ed
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe2a73336e970b01cddbe4a75cec8fbc38f1a771c15ecd6bb8a9c4d423c3af4
+oid sha256:d8c50c496b458770b350b396b279b029e80529909de4041e6e5beea9a41f2db9
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a54b2066ddb168e0e8a2c8b49e5058dff33453160b388ac489494504a9cf08e
+oid sha256:f446cf6d695051ccc3995900b4c0f78ea22057a8ce933a58c4c6b7d2168f6297
 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": 0.8441379310344828,
+  "epoch": 0.9379310344827586,
   "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": 69.174,
       "eval_steps_per_second": 8.845,
       "step": 153
+    },
+    {
+      "epoch": 0.8606896551724138,
+      "grad_norm": 0.4854514002799988,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 1.8567,
+      "step": 156
+    },
+    {
+      "epoch": 0.8772413793103448,
+      "grad_norm": 0.4650457203388214,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 2.0116,
+      "step": 159
+    },
+    {
+      "epoch": 0.8937931034482759,
+      "grad_norm": 0.4151840806007385,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.0101,
+      "step": 162
+    },
+    {
+      "epoch": 0.9103448275862069,
+      "grad_norm": 0.49467867612838745,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 2.0835,
+      "step": 165
+    },
+    {
+      "epoch": 0.926896551724138,
+      "grad_norm": 0.622384786605835,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 2.2758,
+      "step": 168
+    },
+    {
+      "epoch": 0.9379310344827586,
+      "eval_loss": 2.102418899536133,
+      "eval_runtime": 4.4651,
+      "eval_samples_per_second": 68.308,
+      "eval_steps_per_second": 8.734,
+      "step": 170
     }
   ],
   "logging_steps": 3,
@@ -463,7 +506,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9725758175969280.0,
+  "total_flos": 1.08063979732992e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null