Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2862b9f6c633e3e8980c074f36bb19a26cd0e9887b38fc84454dd296aeeb3fb3
+oid sha256:75b3a7e45a2f2d0f74741d3114794f9491a4465357a2790f09d7ecbd422ff779
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456c196c460f48367dabef4a556d2ba994723262e929b958928874735dbdf78d
+oid sha256:23487211eb545ddd1166e963919451590a064d99697f02994e88c818d85cce7e
 size 21318842

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cdaf8c69858d18dc44a05637dae968a115d8603c38f7640f3a45a768dfa5dec
+oid sha256:fcb4e038ee1d3ef202856ea5ca68261dc5b38a8fd4b0dd9d507f5456bce31974
 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": 0.049049662783568364,
+  "epoch": 0.07357449417535254,
   "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": 11.7029,
       "step": 18
+    },
+    {
+      "epoch": 0.05150214592274678,
+      "grad_norm": 3.9225502014160156,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.6225,
+      "step": 21
+    },
+    {
+      "epoch": 0.05885959534028203,
+      "grad_norm": 3.59427547454834,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 12.0697,
+      "step": 24
+    },
+    {
+      "epoch": 0.05885959534028203,
+      "eval_loss": 2.8084943294525146,
+      "eval_runtime": 2.614,
+      "eval_samples_per_second": 65.8,
+      "eval_steps_per_second": 32.9,
+      "step": 24
+    },
+    {
+      "epoch": 0.06621704475781728,
+      "grad_norm": 3.1728599071502686,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.7113,
+      "step": 27
+    },
+    {
+      "epoch": 0.07357449417535254,
+      "grad_norm": 3.4855759143829346,
+      "learning_rate": 0.0,
+      "loss": 11.3748,
+      "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": 120711700021248.0,
+  "total_flos": 175678634852352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null