Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7499a74cb1079d0328d83e18964b429e0d5dcccaace438c7254894b264ab1473
+oid sha256:8162e9c74b1ff4b420a55be899652f0216be8f2fa87cd7290c8db840b3495050
 size 912734242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4d6638b80e1dd848fb3de892b8292a10e1ed935082bdd531bc08562767e9e97
+oid sha256:80ae8992277f9c532dd18ce00928c4a76272d2658ddb439402bce0b4ad7de099
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0029663028001898433,
+  "epoch": 0.004449454200284765,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 6.841,
       "eval_steps_per_second": 0.856,
       "step": 50
+    },
+    {
+      "epoch": 0.00302562885619364,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.003084954912197437,
+      "grad_norm": NaN,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.003144280968201234,
+      "grad_norm": NaN,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.003203607024205031,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.003262933080208828,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.0033222591362126247,
+      "grad_norm": NaN,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.0033815851922164215,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.0034409112482202183,
+      "grad_norm": NaN,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.003500237304224015,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.003559563360227812,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.0036188894162316088,
+      "grad_norm": NaN,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.0036782154722354056,
+      "grad_norm": NaN,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.003737541528239203,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.0037968675842429997,
+      "grad_norm": NaN,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.0038561936402467965,
+      "grad_norm": NaN,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.003915519696250593,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.00397484575225439,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.004034171808258187,
+      "grad_norm": NaN,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.004093497864261984,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.004152823920265781,
+      "grad_norm": NaN,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.0042121499762695774,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.004271476032273375,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.004330802088277171,
+      "grad_norm": NaN,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.004390128144280968,
+      "grad_norm": NaN,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.004449454200284765,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.004449454200284765,
+      "eval_loss": NaN,
+      "eval_runtime": 1037.6276,
+      "eval_samples_per_second": 6.841,
+      "eval_steps_per_second": 0.856,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.746225840128e+16,
+  "total_flos": 8.619338760192e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null