Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f8f8e345274e45a85c3bc5026d2fe6967934002f7734016d32e26e55e21b2db
+oid sha256:f19d2cd403377d1dc8981fa1c0c75e29808aad785d00d0e77f897e124b2f9e42
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be2bae0d31c378999c612f6c4a5cc02833ef752f416ed66d5de6a8cc8e13d03e
+oid sha256:9ebb8c923ef85df4478921677a6d25b1ab23f84632db8b4c86765dc20c46532a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040b95482c646935022d148ebc91f462fbf2195cfa3365adbbe3bd6ca1f35a74
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02761922297919352,
+  "epoch": 0.05523844595838704,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 12.886,
       "eval_steps_per_second": 3.222,
       "step": 25
+    },
+    {
+      "epoch": 0.028723991898361258,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.029828760817529,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.03093352973669674,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.03203829865586448,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.03314306757503222,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03314306757503222,
+      "eval_loss": NaN,
+      "eval_runtime": 88.7745,
+      "eval_samples_per_second": 12.887,
+      "eval_steps_per_second": 3.222,
+      "step": 30
+    },
+    {
+      "epoch": 0.03424783649419996,
+      "grad_norm": NaN,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.0353526054133677,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.036457374332535444,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.037562143251703185,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.038666912170870926,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.038666912170870926,
+      "eval_loss": NaN,
+      "eval_runtime": 88.7833,
+      "eval_samples_per_second": 12.885,
+      "eval_steps_per_second": 3.221,
+      "step": 35
+    },
+    {
+      "epoch": 0.03977168109003867,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.04087645000920641,
+      "grad_norm": NaN,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.04198121892837415,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.04308598784754189,
+      "grad_norm": NaN,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.04419075676670963,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04419075676670963,
+      "eval_loss": NaN,
+      "eval_runtime": 88.7845,
+      "eval_samples_per_second": 12.885,
+      "eval_steps_per_second": 3.221,
+      "step": 40
+    },
+    {
+      "epoch": 0.04529552568587737,
+      "grad_norm": NaN,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.04640029460504511,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.047505063524212854,
+      "grad_norm": NaN,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.048609832443380595,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.049714601362548336,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.049714601362548336,
+      "eval_loss": NaN,
+      "eval_runtime": 88.803,
+      "eval_samples_per_second": 12.882,
+      "eval_steps_per_second": 3.221,
+      "step": 45
+    },
+    {
+      "epoch": 0.05081937028171608,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.05192413920088382,
+      "grad_norm": NaN,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.05302890812005156,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.0541336770392193,
+      "grad_norm": NaN,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.05523844595838704,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05523844595838704,
+      "eval_loss": NaN,
+      "eval_runtime": 88.787,
+      "eval_samples_per_second": 12.885,
+      "eval_steps_per_second": 3.221,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9797016276172800.0,
+  "total_flos": 1.95940325523456e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null