Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f6eebfa927dd597f5b2467576d1b4e5a74f50d01f39872c16db123c54f82a8c
+oid sha256:37a61330fb4b126c3c4eb0f63d931d154002ec983225023c4deb546519f8cffc
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e73b5e3c013bcae7afbd24e1fe85edb611862c66c9afeb07e64296806e4d87
+oid sha256:6bd4ef7a92a49436a0788cb4927a590434998ae173d0eaef8326c2aa609d3dbf
 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": 0.049782202862476664,
+  "epoch": 0.07467330429371499,
   "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": 39.691,
       "eval_steps_per_second": 19.845,
       "step": 20
+    },
+    {
+      "epoch": 0.0522713130056005,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.059738643434972,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.06222775357809583,
+      "eval_loss": NaN,
+      "eval_runtime": 4.3392,
+      "eval_samples_per_second": 39.178,
+      "eval_steps_per_second": 19.589,
+      "step": 25
+    },
+    {
+      "epoch": 0.0672059738643435,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.07467330429371499,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07467330429371499,
+      "eval_loss": NaN,
+      "eval_runtime": 4.2884,
+      "eval_samples_per_second": 39.642,
+      "eval_steps_per_second": 19.821,
+      "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": 1535246629601280.0,
+  "total_flos": 2302869944401920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null