Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:667c8d93fa26c140ab3745aabe915606d99decca2ef84d3db8d23e02a922dae0
+oid sha256:8ba452b7ef27367bb19b4d8562020c600a8e382628462f7a92d1ebf0654c79b5
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593d635a30b14767a1698960ec78cb8d24b81263ee6295f64194d12ad5f25dd2
+oid sha256:46c602fea721bf047f31a7251e1b4d821409f7ddbfca3af829fa3293552a839f
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0b89d8fa755d9416ca83ad352390b182e71fbf00b8789f333eff5f707340c0
+oid sha256:3041e11cb3df79669236c0aeac387af2479aca689d59e2ab812b65731dd06876
 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": 0.3559322033898305,
+  "epoch": 0.4708097928436911,
   "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": 18.7,
       "eval_steps_per_second": 9.35,
       "step": 189
+    },
+    {
+      "epoch": 0.3578154425612053,
+      "grad_norm": 0.40222638845443726,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 0.3894,
+      "step": 190
+    },
+    {
+      "epoch": 0.3766478342749529,
+      "grad_norm": 0.3540307283401489,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 0.4443,
+      "step": 200
+    },
+    {
+      "epoch": 0.3954802259887006,
+      "grad_norm": 0.4166598320007324,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 0.3663,
+      "step": 210
+    },
+    {
+      "epoch": 0.4143126177024482,
+      "grad_norm": 0.5152053236961365,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 0.3393,
+      "step": 220
+    },
+    {
+      "epoch": 0.4331450094161959,
+      "grad_norm": 0.3762021064758301,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 0.3951,
+      "step": 230
+    },
+    {
+      "epoch": 0.4519774011299435,
+      "grad_norm": 0.39529839158058167,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 0.3999,
+      "step": 240
+    },
+    {
+      "epoch": 0.4708097928436911,
+      "grad_norm": 0.5087373852729797,
+      "learning_rate": 0.0,
+      "loss": 0.4061,
+      "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": 2.900550437830656e+16,
+  "total_flos": 3.8219503632384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null