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:bd487c4ec4a32c02aaf5d86550676b9339c6823a39e3946176d28125323267b2
+oid sha256:e1440d30eca990df72291ae8f85a075251a37bbc5b99b40df6b35f6f4fc4d49b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43eb6e0667c7ea7216f77dcc7c86c566282f69d7d8483866b0a3929724243bf0
+oid sha256:767800bc8524835ec66c7260df84286ab66417c82295e1e78492a8473227744e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87e4caf284f84836b86fbb9d15f85d95c4be4769dd1ae693ef400a82f62b7ca
+oid sha256:1f6c67b9aca20f5df3caeacd4f86d6e96a90915841fe6b6bf98a7b03df3266e5
 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": 0.0005855658029571073,
+  "epoch": 0.0007507253884065479,
   "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": 1.734,
       "step": 35
+    },
+    {
+      "epoch": 0.0006005803107252383,
+      "grad_norm": 1.1226017475128174,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8147,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006005803107252383,
+      "eval_loss": 1.9749507904052734,
+      "eval_runtime": 1996.5098,
+      "eval_samples_per_second": 14.047,
+      "eval_steps_per_second": 7.023,
+      "step": 40
+    },
+    {
+      "epoch": 0.000675652849565893,
+      "grad_norm": 0.8765591382980347,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7135,
+      "step": 45
+    },
+    {
+      "epoch": 0.0007507253884065479,
+      "grad_norm": 0.7855657935142517,
+      "learning_rate": 0.0,
+      "loss": 1.4901,
+      "step": 50
+    },
+    {
+      "epoch": 0.0007507253884065479,
+      "eval_loss": 1.9711557626724243,
+      "eval_runtime": 2012.0558,
+      "eval_samples_per_second": 13.938,
+      "eval_steps_per_second": 6.969,
+      "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": 7398256992583680.0,
+  "total_flos": 9617734090358784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null