Training in progress, step 155, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6297606052a4277aa0a1e4619bd299b3833e32268284b14aa730349c00e330a7
+oid sha256:c71d237e710a962dcb9e6ba5ccc36a842b75de6c36ff2691b85a6e48f49d4991
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2366e26bc61fe9363daef1823fa6a4707c5d0477f89a365a7728b80458335ff1
+oid sha256:b0df129bdd4dadcc2e2c280e7cf459a2eb420cd37dd7d896ef8cfbf82a4c45fd
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d95327014bf0e992837899fdc63d1e3049ea8baca978228506724df9c716834
+oid sha256:d1849ad9db14ff92103b9d227ede45e09b064472ac17db6af688392748c6c18b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a946cb282348d3fba8c242cd51f3b90b3dccbd24720ee6b6397a7e493e7b92c
+oid sha256:382ece00c385c691790a218c7659825f5fdd28b4e63aa1032e7b069dd2944457
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07335411699981662,
+  "epoch": 0.07579925423314383,
   "eval_steps": 34,
-  "global_step": 150,
+  "global_step": 155,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1097,6 +1097,41 @@
       "learning_rate": 3.973653636207437e-05,
       "loss": 1.0273,
       "step": 150
+    },
+    {
+      "epoch": 0.07384314444648206,
+      "grad_norm": 0.3300507664680481,
+      "learning_rate": 3.8272177871020723e-05,
+      "loss": 1.0187,
+      "step": 151
+    },
+    {
+      "epoch": 0.0743321718931475,
+      "grad_norm": 0.4003622531890869,
+      "learning_rate": 3.682889937467493e-05,
+      "loss": 0.9066,
+      "step": 152
+    },
+    {
+      "epoch": 0.07482119933981295,
+      "grad_norm": 0.3900095522403717,
+      "learning_rate": 3.540719375132129e-05,
+      "loss": 0.866,
+      "step": 153
+    },
+    {
+      "epoch": 0.07531022678647839,
+      "grad_norm": 0.54018634557724,
+      "learning_rate": 3.400754651212776e-05,
+      "loss": 0.981,
+      "step": 154
+    },
+    {
+      "epoch": 0.07579925423314383,
+      "grad_norm": 0.3802890479564667,
+      "learning_rate": 3.263043563534428e-05,
+      "loss": 1.0331,
+      "step": 155
     }
   ],
   "logging_steps": 1,
@@ -1116,7 +1151,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.658431293325312e+17,
+  "total_flos": 6.880379003102822e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null