Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471f6db16d6a5314737a1290d4b70c97c59148efb52847a49159127382c41de9
+oid sha256:8b9f1da02e9d67f73af939be2f4e6c029294540168787c6c1cbd1658a80e5400
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c456faca4348ecc5ab41efa60798beab17c7dbd88dca282ae751ca457374fd50
+oid sha256:25517486c3c1126f87f0d559ba0f40d2e3167bb0e19ede7d430164436ca893f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:559fc41b1666bf9d08bbf36782e6c7ecd5d9cb035c707b8454088fa01b378aaa
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008284231999917158,
+  "epoch": 0.0016568463999834316,
   "eval_steps": 10,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 6.857,
       "eval_steps_per_second": 3.429,
       "step": 10
+    },
+    {
+      "epoch": 0.0009112655199908873,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.000994107839990059,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010769501599892305,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.001159792479988402,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.0012426347999875736,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013254771199867452,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.0014083194399859167,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.0014911617599850883,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.00157400407998426,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0016568463999834316,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0016568463999834316,
+      "eval_loss": NaN,
+      "eval_runtime": 1482.283,
+      "eval_samples_per_second": 6.858,
+      "eval_steps_per_second": 3.429,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -107,12 +185,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4321866512531456e+16,
+  "total_flos": 2.8466919858241536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null