Training in progress, step 187, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d0001978f7f34de62fbd900eb8a172a4417b9414b4e0c28c67ae6bffb9ea5d
+oid sha256:8915e517418e97b5c0dfb3779664d2c40b45665f64d48eb60d1382ec12d8cde9
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f2acc403df79cfaf7d1beba6586075c055971d4dc30c4d9e1bc6fac257de195
+oid sha256:85624fa52d7ffe7f93b2576f3a9ef9539986c75b102284f236abe1a7e157ae84
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2833948efdf50a46433c6293d8c3846881e32eddfd503abe75bb0fae1ed0507f
+oid sha256:33d1775f05b594bce7d5b393be72148726e66c23321342a55f0e172135811102
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab1f30942a5e2bb9a9e5cc3477ef48cdcd39a7b78f8a45a46db0926bdbf2b4f
+oid sha256:43427779b8e6e83ef9780afcdea7472d2419de40e6f85cfedb90b60f89a2ff0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03158383650719926,
+  "epoch": 0.03474222015791918,
   "eval_steps": 17,
-  "global_step": 170,
+  "global_step": 187,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,6 +487,56 @@
       "eval_samples_per_second": 32.574,
       "eval_steps_per_second": 4.074,
       "step": 170
+    },
+    {
+      "epoch": 0.031769623780771014,
+      "grad_norm": 0.8445965051651001,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 0.6391,
+      "step": 171
+    },
+    {
+      "epoch": 0.0323269856014863,
+      "grad_norm": 0.7874613404273987,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 0.7674,
+      "step": 174
+    },
+    {
+      "epoch": 0.03288434742220158,
+      "grad_norm": 0.8437705636024475,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 0.6699,
+      "step": 177
+    },
+    {
+      "epoch": 0.03344170924291686,
+      "grad_norm": 0.7565687298774719,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.7346,
+      "step": 180
+    },
+    {
+      "epoch": 0.03399907106363214,
+      "grad_norm": 0.7713425159454346,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 0.6421,
+      "step": 183
+    },
+    {
+      "epoch": 0.03455643288434742,
+      "grad_norm": 0.755294144153595,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 0.6981,
+      "step": 186
+    },
+    {
+      "epoch": 0.03474222015791918,
+      "eval_loss": 0.6977519392967224,
+      "eval_runtime": 278.5744,
+      "eval_samples_per_second": 32.544,
+      "eval_steps_per_second": 4.071,
+      "step": 187
     }
   ],
   "logging_steps": 3,
@@ -506,7 +556,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.965192033940275e+16,
+  "total_flos": 6.567372765580493e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null