Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d7dfd01f9f4b15c9b4e3334a2f577b9eb974b34c06e9eafdb6b2bbb4668d3be
+oid sha256:8ae7109242cad5b517fbc68f69af9be79baceb0f9d918bf30c6a456aab36f73d
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a098dffa38fa9c01aae74eebd50d55d442f41711e114eb99ba341d13be3779bf
+oid sha256:a6150013c5a55351ef3c08536ad845f39a1b502b4c12c8f5e7721ae4addf788a
 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": 0.01288936627282492,
+  "epoch": 0.017185821697099892,
   "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": 9.439,
       "eval_steps_per_second": 4.719,
       "step": 15
+    },
+    {
+      "epoch": 0.013748657357679914,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.014607948442534909,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0163265306122449,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "eval_loss": NaN,
+      "eval_runtime": 51.9397,
+      "eval_samples_per_second": 9.434,
+      "eval_steps_per_second": 4.717,
+      "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": 9888459569233920.0,
+  "total_flos": 1.318461275897856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null