Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e7105cce5faa00c060f05ab7c3a7c7fedbc98977a9e99e0a6bcfdfe4dbc0612
+oid sha256:f2049f9097961c9d8b770c2eea468b1eb33ebab484005197d92ea06715b69a0f
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e41d2a69392e1045fa137a2c6632b1226114dbf26ebf2189f314e1baabdbbd4
+oid sha256:a76a659076b209499b420365440eb3feb1f99ac8a0db7534eb74acb7127319fb
 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": 0.12953367875647667,
+  "epoch": 0.19430051813471502,
   "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": 5.869,
       "eval_steps_per_second": 2.943,
       "step": 50
+    },
+    {
+      "epoch": 0.13212435233160622,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.13471502590673576,
+      "grad_norm": NaN,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.13730569948186527,
+      "grad_norm": NaN,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.13989637305699482,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.14248704663212436,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.14507772020725387,
+      "grad_norm": NaN,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.14766839378238342,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.15025906735751296,
+      "grad_norm": NaN,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.15284974093264247,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.15544041450777202,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.15803108808290156,
+      "grad_norm": NaN,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.16062176165803108,
+      "grad_norm": NaN,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.16321243523316062,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.16580310880829016,
+      "grad_norm": NaN,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.16839378238341968,
+      "grad_norm": NaN,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.17098445595854922,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.17357512953367876,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.17616580310880828,
+      "grad_norm": NaN,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.17875647668393782,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.18134715025906736,
+      "grad_norm": NaN,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.18393782383419688,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.18652849740932642,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.18911917098445596,
+      "grad_norm": NaN,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.19170984455958548,
+      "grad_norm": NaN,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.19430051813471502,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.19430051813471502,
+      "eval_loss": NaN,
+      "eval_runtime": 55.389,
+      "eval_samples_per_second": 5.868,
+      "eval_steps_per_second": 2.943,
+      "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": 1.27854515847168e+17,
+  "total_flos": 1.91781773770752e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null