Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b519dc441504087869e3a2bf834c4cd4f3c4fe9eba03c3b9f76b81430739c5b
+oid sha256:8df007564bf69fb64b17d6eff840b7b1b9f6860105575a31a2cc8e81e72a3f25
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c03552cae0021c9b952444359e74f49151aa468af63259236bac489aa2de985
+oid sha256:82884e0d17be94807da5d1c7e6b4e9510a7ae5c884add7079f5f122c7b044ccf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1784121320249777,
+  "epoch": 0.3568242640499554,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 4.483,
       "eval_steps_per_second": 2.241,
       "step": 25
+    },
+    {
+      "epoch": 0.1855486173059768,
+      "grad_norm": NaN,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.1926851025869759,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.19982158786797502,
+      "grad_norm": NaN,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.20695807314897413,
+      "grad_norm": NaN,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.21409455842997324,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.22123104371097235,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.22836752899197146,
+      "grad_norm": NaN,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.23550401427297057,
+      "grad_norm": NaN,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.24264049955396966,
+      "grad_norm": NaN,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.24977698483496877,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.2569134701159679,
+      "grad_norm": NaN,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.264049955396967,
+      "grad_norm": NaN,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": NaN,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.2783229259589652,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.2854594112399643,
+      "grad_norm": NaN,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.2925958965209634,
+      "grad_norm": NaN,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.29973238180196254,
+      "grad_norm": NaN,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.3068688670829616,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.31400535236396077,
+      "grad_norm": NaN,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.32114183764495985,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.328278322925959,
+      "grad_norm": NaN,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.33541480820695807,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.34255129348795715,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.3496877787689563,
+      "grad_norm": NaN,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.3568242640499554,
+      "grad_norm": NaN,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3568242640499554,
+      "eval_loss": NaN,
+      "eval_runtime": 26.3154,
+      "eval_samples_per_second": 4.484,
+      "eval_steps_per_second": 2.242,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.53626333642752e+16,
+  "total_flos": 7.07252667285504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null