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:afaaf7d622de379fa6d3c6e7f88155ffdfdebb482c3fb7b9660674000f3aac41
+oid sha256:2648f74c43a7439490823efa218360917fc343c43b09aa696b75aad082f60aa9
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62effaee8a16094ed7b4794237761c448591f5f9688a32bcb2f50c0553bee613
+oid sha256:8533ef11c9cac4f52e5b3f9e6ccaa5b31cc23aeb7f0bf899ec653f324af4bca2
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f56528b2b76cb96fdbaeedcd2bc1a7c80bcd9d88cbac90fd5655ce599b9d75
+oid sha256:1a608beb21ca290f1f1a46eb926ba60cee938b7bd70879e0f0bbd7f5e8fe5fe2
 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": 0.0022456770716370988,
+  "epoch": 0.0033685156074556477,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 156.0,
       "eval_steps_per_second": 78.0,
       "step": 20
+    },
+    {
+      "epoch": 0.0023579609252189536,
+      "grad_norm": 1.6708543626009487e-05,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 46.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.002694812485964518,
+      "grad_norm": 1.7559348634677008e-05,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 46.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.002807096339546373,
+      "eval_loss": 11.5,
+      "eval_runtime": 24.4035,
+      "eval_samples_per_second": 153.667,
+      "eval_steps_per_second": 76.833,
+      "step": 25
+    },
+    {
+      "epoch": 0.003031664046710083,
+      "grad_norm": 2.3784989025443792e-05,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 46.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0033685156074556477,
+      "grad_norm": 1.8421775166643783e-05,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0033685156074556477,
+      "eval_loss": 11.5,
+      "eval_runtime": 24.2838,
+      "eval_samples_per_second": 154.424,
+      "eval_steps_per_second": 77.212,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 807895793664.0,
+  "total_flos": 1206856679424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null