Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a084acb73a004210da15e84a6cd2ec7fba74e2d13a903e45fa8c1511f9b1294e
+oid sha256:169ae74b9cbbb546aa98235ced157dc324be24e1a5c85dbccd156786b8784c52
 size 120213058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44003fb89097099f6c31f476c0fd68f2fee246795b3c141bcadf87b5bbdcb9f8
+oid sha256:c9849cad4042435b87a24ebd2e4195c57e68def312519ab201a41c649649a52d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008815232722143865,
+  "epoch": 0.001763046544428773,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.0009167842031029619,
+      "grad_norm": NaN,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0009520451339915374,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009520451339915374,
+      "eval_loss": NaN,
+      "eval_runtime": 1505.3768,
+      "eval_samples_per_second": 15.864,
+      "eval_steps_per_second": 1.984,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009873060648801129,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0010225669957686884,
+      "grad_norm": NaN,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.0010578279266572638,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010930888575458391,
+      "grad_norm": NaN,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.0011283497884344146,
+      "grad_norm": NaN,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.00116361071932299,
+      "grad_norm": NaN,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0011988716502115656,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.001234132581100141,
+      "grad_norm": NaN,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.0012693935119887166,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0012693935119887166,
+      "eval_loss": NaN,
+      "eval_runtime": 1504.5043,
+      "eval_samples_per_second": 15.874,
+      "eval_steps_per_second": 1.985,
+      "step": 36
+    },
+    {
+      "epoch": 0.001304654442877292,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.0013399153737658673,
+      "grad_norm": NaN,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.0013751763046544428,
+      "grad_norm": NaN,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0014104372355430183,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0014456981664315938,
+      "grad_norm": NaN,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.0014809590973201693,
+      "grad_norm": NaN,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.0015162200282087448,
+      "grad_norm": NaN,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.0015514809590973203,
+      "grad_norm": NaN,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.0015867418899858955,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015867418899858955,
+      "eval_loss": NaN,
+      "eval_runtime": 1504.6339,
+      "eval_samples_per_second": 15.872,
+      "eval_steps_per_second": 1.985,
+      "step": 45
+    },
+    {
+      "epoch": 0.001622002820874471,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.0016572637517630465,
+      "grad_norm": NaN,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.001692524682651622,
+      "grad_norm": NaN,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.0017277856135401975,
+      "grad_norm": NaN,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.001763046544428773,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6364587884544000.0,
+  "total_flos": 1.2729175769088e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null