Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f3452ba584f0e87a5a3c1479c28e324dc55930fc9c60f8382066f5961d7a344
+oid sha256:646309dd6c5cad0e9f726271aa3acca2b4cdf147724b908a1ad050fcf1650080
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ac2425658954e629478d9bf6f08126dcff73a5f3d86b57067c32868f6edb68
+oid sha256:c319f0fb5c7148585c2398f30f930de8607e47e769f4bee68bbda539f1945cd1
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56b73ba5f2d662c92296e87599e4454df3aa952447ac02ee3c950d1f55780e2
+oid sha256:37a2b5c509866b11bed647f66c687065b510bff5b458b83c626fe64e91b5e8bf
 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": 0.01117006422786931,
+  "epoch": 0.016755096341803964,
   "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": 1.6812,
       "step": 18
+    },
+    {
+      "epoch": 0.011728567439262776,
+      "grad_norm": 0.3746090233325958,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.5182,
+      "step": 21
+    },
+    {
+      "epoch": 0.013404077073443172,
+      "grad_norm": 0.35193824768066406,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.6265,
+      "step": 24
+    },
+    {
+      "epoch": 0.013404077073443172,
+      "eval_loss": 1.5419925451278687,
+      "eval_runtime": 73.8676,
+      "eval_samples_per_second": 10.207,
+      "eval_steps_per_second": 5.104,
+      "step": 24
+    },
+    {
+      "epoch": 0.015079586707623568,
+      "grad_norm": 0.34421786665916443,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.4906,
+      "step": 27
+    },
+    {
+      "epoch": 0.016755096341803964,
+      "grad_norm": 0.3292273283004761,
+      "learning_rate": 0.0,
+      "loss": 1.6185,
+      "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": 1.364775325925376e+16,
+  "total_flos": 2.094771430490112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null