Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e165344101c56e0d4f69e07a00b1e7b199b2c31ab5321aff14cafd3c3406e1e
+oid sha256:42b2a11b8b55b026d35ddc25ecebc46ffde10621a77a35b0ecf78734cbbc342a
 size 90310010

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb38976bcbed505d46f9b893c84210b8a368bf22d7b477ebf8ae33dd43739138
+oid sha256:207532cf427baf179d1f23bd7c10f00bbac6712e13727094e91baec620fb5d7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004013270547945205,
+  "epoch": 0.0005351027397260274,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 22.093,
       "eval_steps_per_second": 11.047,
       "step": 15
+    },
+    {
+      "epoch": 0.0004280821917808219,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.00045483732876712326,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.00048159246575342463,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.000508347602739726,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0005351027397260274,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005351027397260274,
+      "eval_loss": NaN,
+      "eval_runtime": 712.7294,
+      "eval_samples_per_second": 22.081,
+      "eval_steps_per_second": 11.041,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1838672882171904.0,
+  "total_flos": 2516078680866816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null