Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf431d7f67931c158b0efa78e56576c2847d8af86ba03f041a310818f633526c
+oid sha256:e322a61214d73b2fa1a4c9300cd22a8c5a5d3308d26c9b109eb6c872420f8e98
 size 4545930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8478b9fc3cfec869ad2e04e6be46f673edccc202d68bdca1ca8b4ceddbdb1c14
+oid sha256:2d3906298152c2aa935afa150978546950e9e94274ba523d5b541c68e95a166e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000296081363158596,
+  "epoch": 0.000444122044737894,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 150.441,
       "eval_steps_per_second": 37.613,
       "step": 20
+    },
+    {
+      "epoch": 0.0003108854313165258,
+      "grad_norm": NaN,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0003256894994744556,
+      "grad_norm": NaN,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.00034049356763238536,
+      "grad_norm": NaN,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.00035529763579031517,
+      "grad_norm": NaN,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.00035529763579031517,
+      "eval_loss": NaN,
+      "eval_runtime": 188.8151,
+      "eval_samples_per_second": 150.634,
+      "eval_steps_per_second": 37.661,
+      "step": 24
+    },
+    {
+      "epoch": 0.000370101703948245,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.0003849057721061748,
+      "grad_norm": NaN,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0003997098402641046,
+      "grad_norm": NaN,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.00041451390842203435,
+      "grad_norm": NaN,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.00041451390842203435,
+      "eval_loss": NaN,
+      "eval_runtime": 189.0757,
+      "eval_samples_per_second": 150.427,
+      "eval_steps_per_second": 37.609,
+      "step": 28
+    },
+    {
+      "epoch": 0.00042931797657996416,
+      "grad_norm": NaN,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.000444122044737894,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 43272886026240.0,
+  "total_flos": 64909329039360.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null