Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc55ec36e7b40b236fa29b3a07ef4bbfc22651c465bb8c5aa65a46e475ba31ab
+oid sha256:80faec03b0e0c181fad254b0cc333ede8130d1bc49141bd5899accf348f4b54b
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe30e3a36d3aadc8a6fce11ee0ba29ea56602fc131e1f101109207efd76c5c6
+oid sha256:5c94ac2fea3ac7717cf2ed90055bb3064594d25883bfcfed71fa39d991e93398
 size 501028338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b52214f9bd9fd90e146416d19db727ff822d3ff4dfe457467cf1dd46cfde3948
+oid sha256:5da98638b5afea10e0de2f4fc87452ede8bc4b95ee5e48c3293a3388722f1e2e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009103322712790168,
+  "epoch": 0.013654984069185253,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 0.9718,
       "step": 18
+    },
+    {
+      "epoch": 0.009558488848429678,
+      "grad_norm": 0.5597707629203796,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.9183,
+      "step": 21
+    },
+    {
+      "epoch": 0.010923987255348202,
+      "grad_norm": 0.5114228129386902,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.8586,
+      "step": 24
+    },
+    {
+      "epoch": 0.010923987255348202,
+      "eval_loss": 0.848564624786377,
+      "eval_runtime": 86.1377,
+      "eval_samples_per_second": 10.739,
+      "eval_steps_per_second": 5.375,
+      "step": 24
+    },
+    {
+      "epoch": 0.012289485662266727,
+      "grad_norm": 0.4467601776123047,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.8333,
+      "step": 27
+    },
+    {
+      "epoch": 0.013654984069185253,
+      "grad_norm": 0.4542919099330902,
+      "learning_rate": 0.0,
+      "loss": 0.8337,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.26955844272128e+16,
+  "total_flos": 1.90433766408192e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null