Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b12232e99d92a7db1ff704b8556f829bd7f364212012ab8b335eb2e76fb7b60
+oid sha256:39007a35c09aa20531bb24768dfdecf28a8f3d5e9a441e552ac4f8f6f7f61736
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:febf9d687607ada403e99af3459e40e0fe59ed18cce572bcf837c5382d71f8eb
+oid sha256:f0c59790f2e3ba0a4714a087914c6124ed7398fe25ca94de6ab9e0301a8e585f
 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": 0.14519056261343014,
+  "epoch": 0.29038112522686027,
   "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": 29.957,
       "eval_steps_per_second": 14.979,
       "step": 25
+    },
+    {
+      "epoch": 0.15099818511796734,
+      "grad_norm": NaN,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.15680580762250454,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 5.59,
+      "step": 27
+    },
+    {
+      "epoch": 0.16261343012704174,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1611.2329,
+      "step": 28
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": NaN,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 135.0654,
+      "step": 29
+    },
+    {
+      "epoch": 0.17422867513611615,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 165.8565,
+      "step": 30
+    },
+    {
+      "epoch": 0.18003629764065335,
+      "grad_norm": NaN,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.18584392014519055,
+      "grad_norm": NaN,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 81.9507,
+      "step": 32
+    },
+    {
+      "epoch": 0.19165154264972778,
+      "grad_norm": NaN,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.19745916515426498,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 6.6547,
+      "step": 34
+    },
+    {
+      "epoch": 0.20326678765880218,
+      "grad_norm": NaN,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.20907441016333939,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 7.5238,
+      "step": 36
+    },
+    {
+      "epoch": 0.2148820326678766,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.2206896551724138,
+      "grad_norm": NaN,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 68.1653,
+      "step": 38
+    },
+    {
+      "epoch": 0.226497277676951,
+      "grad_norm": NaN,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.2323049001814882,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.2381125226860254,
+      "grad_norm": NaN,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.24392014519056263,
+      "grad_norm": NaN,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.24972776769509983,
+      "grad_norm": NaN,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 707.1777,
+      "step": 43
+    },
+    {
+      "epoch": 0.255535390199637,
+      "grad_norm": NaN,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 195.0476,
+      "step": 44
+    },
+    {
+      "epoch": 0.2613430127041742,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.9188,
+      "step": 45
+    },
+    {
+      "epoch": 0.2671506352087114,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.27295825771324866,
+      "grad_norm": NaN,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.7395,
+      "step": 47
+    },
+    {
+      "epoch": 0.27876588021778587,
+      "grad_norm": NaN,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 8.7959,
+      "step": 48
+    },
+    {
+      "epoch": 0.28457350272232307,
+      "grad_norm": NaN,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.29038112522686027,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.29038112522686027,
+      "eval_loss": NaN,
+      "eval_runtime": 9.683,
+      "eval_samples_per_second": 29.949,
+      "eval_steps_per_second": 14.975,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9620119382523904e+16,
+  "total_flos": 5.985367319012966e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null