Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e646f56ae7f3f1f4ba01bf89e59dc30ea3889a0c9aacdf56ef6a025c1c072063
+oid sha256:7692bb221a467f68a14536696bbb00924c02a8473bd124e9431708b66c7a9524
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c762e745e6b10819fd8afb33b4a1b715c756c7b22945b0044c81ebcb593a7d
+oid sha256:8cbc589a06e2970f3d1e1f484146819e64848b461fbefd953e917f429a552096
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08333333333333333,
+  "epoch": 0.10416666666666667,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,48 @@
       "eval_samples_per_second": 24.339,
       "eval_steps_per_second": 12.194,
       "step": 24
+    },
+    {
+      "epoch": 0.08680555555555555,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.09027777777777778,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.09722222222222222,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.10069444444444445,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.10416666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6102436502568960.0,
+  "total_flos": 7628045628211200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null