Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6942323f82441adbcfa39c8217185f88c593201d11323a965ce53ee7fb47894
+oid sha256:e20fd9da2a9395c63cd62d10f5ce096f654f33f280e4520a61372816e60fa59d
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f08b5e52b0fa4353f52e15f0ed12a3218a82410f3a186af6d5309b9f733aa130
+oid sha256:11514b197853b462348465f3dc339beef02f4f254b0c41ac5a64915cdbed9ea0
 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": 0.009187798603454611,
+  "epoch": 0.018375597206909223,
   "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": 0.009555310547592797,
+      "grad_norm": NaN,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.009922822491730982,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.009922822491730982,
+      "eval_loss": NaN,
+      "eval_runtime": 66.0896,
+      "eval_samples_per_second": 34.665,
+      "eval_steps_per_second": 4.343,
+      "step": 27
+    },
+    {
+      "epoch": 0.010290334435869165,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.01065784638000735,
+      "grad_norm": NaN,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.011025358324145534,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.01139287026828372,
+      "grad_norm": NaN,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.011760382212421904,
+      "grad_norm": NaN,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.012127894156560088,
+      "grad_norm": NaN,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.012495406100698273,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.012862918044836457,
+      "grad_norm": NaN,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.013230429988974642,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.013230429988974642,
+      "eval_loss": NaN,
+      "eval_runtime": 66.0752,
+      "eval_samples_per_second": 34.673,
+      "eval_steps_per_second": 4.344,
+      "step": 36
+    },
+    {
+      "epoch": 0.013597941933112825,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.01396545387725101,
+      "grad_norm": NaN,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.014332965821389196,
+      "grad_norm": NaN,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.01470047776552738,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.015067989709665565,
+      "grad_norm": NaN,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.015435501653803748,
+      "grad_norm": NaN,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.015803013597941933,
+      "grad_norm": NaN,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.01617052554208012,
+      "grad_norm": NaN,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.016538037486218304,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.016538037486218304,
+      "eval_loss": NaN,
+      "eval_runtime": 66.0779,
+      "eval_samples_per_second": 34.671,
+      "eval_steps_per_second": 4.343,
+      "step": 45
+    },
+    {
+      "epoch": 0.016905549430356485,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.01727306137449467,
+      "grad_norm": NaN,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.017640573318632856,
+      "grad_norm": NaN,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.01800808526277104,
+      "grad_norm": NaN,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.018375597206909223,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2573421930086400.0,
+  "total_flos": 5146843860172800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null