Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7d093658435cedba7ec4df3bd95238efc79e9c02844dcd644a6f77c5da0217
+oid sha256:729e79dba611318caa3979644cab0d3734a4d4765da257f7774c4b38e18a031d
 size 628216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365db6611fa226642bef07db7bc38c04744fac4bafd9902f0e02778919233426
+oid sha256:ef9e5c9e12cc8614baa994380d9489bfcc40d3353d7ff7a38a3f01b5ae0a65fe
 size 352122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b073eae0856d95a78bd1210e484de480f18e699d417df6566c139d5389912738
+oid sha256:e2edc0261f7034ce0d71cea4f289a97e7923584b1d4870351bbf4900337528d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015434241149810134,
+  "epoch": 0.020415662896574253,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 359.346,
       "eval_steps_per_second": 179.673,
       "step": 189
+    },
+    {
+      "epoch": 0.015515903801396431,
+      "grad_norm": 0.2047327607870102,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 10.7352,
+      "step": 190
+    },
+    {
+      "epoch": 0.0163325303172594,
+      "grad_norm": 0.20196911692619324,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 10.7285,
+      "step": 200
+    },
+    {
+      "epoch": 0.017149156833122372,
+      "grad_norm": 0.21181835234165192,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 10.7256,
+      "step": 210
+    },
+    {
+      "epoch": 0.017965783348985343,
+      "grad_norm": 0.23975443840026855,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 10.7394,
+      "step": 220
+    },
+    {
+      "epoch": 0.01878240986484831,
+      "grad_norm": 0.21740056574344635,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 10.7338,
+      "step": 230
+    },
+    {
+      "epoch": 0.019599036380711282,
+      "grad_norm": 0.2698234021663666,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 10.7245,
+      "step": 240
+    },
+    {
+      "epoch": 0.020415662896574253,
+      "grad_norm": 0.2873691916465759,
+      "learning_rate": 0.0,
+      "loss": 10.729,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 12061004267520.0,
+  "total_flos": 16031529566208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null