Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63c8c7cf6d28cbf03173b0548ac97b1b2ca0f09db3bd878b01b17bb8208402f4
+oid sha256:d4fac1b6593ddd4513d1418d7e0760c590a008d52314f1bed58690e264aef8cc
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d0ea35b358a1b3652b1fd55e55b154a2fa5ad31c41b9fecab7c4fb0845186c
+oid sha256:5e724a854b6606076d82d2e6fd0712a3634b9f0198df210ce4087ab607527eca
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4153372e5441b0ea2e6a8c0a0ff12401521178273f30862f0b9f4725190679f0
+oid sha256:b1fbac2690de67edd93baf8d76b7485f0d1b64a83524d673302021c491150379
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003322896031695316,
+  "epoch": 0.004260123117558097,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.2086,
       "step": 35
+    },
+    {
+      "epoch": 0.003408098494046478,
+      "grad_norm": 3.0704267024993896,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2071,
+      "step": 40
+    },
+    {
+      "epoch": 0.003408098494046478,
+      "eval_loss": 0.25280508399009705,
+      "eval_runtime": 158.765,
+      "eval_samples_per_second": 31.128,
+      "eval_steps_per_second": 15.564,
+      "step": 40
+    },
+    {
+      "epoch": 0.0038341108058022877,
+      "grad_norm": 1.9233769178390503,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1697,
+      "step": 45
+    },
+    {
+      "epoch": 0.004260123117558097,
+      "grad_norm": 5.35168981552124,
+      "learning_rate": 0.0,
+      "loss": 0.2624,
+      "step": 50
+    },
+    {
+      "epoch": 0.004260123117558097,
+      "eval_loss": 0.2518482506275177,
+      "eval_runtime": 158.7971,
+      "eval_samples_per_second": 31.121,
+      "eval_steps_per_second": 15.561,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 347248838836224.0,
+  "total_flos": 445190819020800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null