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 sha256:12353d247845b07af7787c9a5ae349514f8015e7b292f18b4b65e6e1a7e9c828
+oid sha256:f6b3c2b30aca0a374d889a79c31eb8d0074551172d9bd83f294e3b6bdfcc4ddc
 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": 0.01012965964343598,
+  "epoch": 0.02025931928687196,
   "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": 0.01053484602917342,
+      "grad_norm": NaN,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.01094003241491086,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.01094003241491086,
+      "eval_loss": NaN,
+      "eval_runtime": 70.4497,
+      "eval_samples_per_second": 29.51,
+      "eval_steps_per_second": 3.691,
+      "step": 27
+    },
+    {
+      "epoch": 0.011345218800648298,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.011750405186385737,
+      "grad_norm": NaN,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.012155591572123177,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.012560777957860616,
+      "grad_norm": NaN,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.012965964343598054,
+      "grad_norm": NaN,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.013371150729335495,
+      "grad_norm": NaN,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.013776337115072933,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.014181523500810372,
+      "grad_norm": NaN,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.014586709886547812,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.014586709886547812,
+      "eval_loss": NaN,
+      "eval_runtime": 70.469,
+      "eval_samples_per_second": 29.502,
+      "eval_steps_per_second": 3.69,
+      "step": 36
+    },
+    {
+      "epoch": 0.014991896272285251,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.01539708265802269,
+      "grad_norm": NaN,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.015802269043760128,
+      "grad_norm": NaN,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.01620745542949757,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.01661264181523501,
+      "grad_norm": NaN,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.017017828200972446,
+      "grad_norm": NaN,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.017423014586709886,
+      "grad_norm": NaN,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.017828200972447326,
+      "grad_norm": NaN,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.018233387358184763,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.018233387358184763,
+      "eval_loss": NaN,
+      "eval_runtime": 70.4502,
+      "eval_samples_per_second": 29.51,
+      "eval_steps_per_second": 3.691,
+      "step": 45
+    },
+    {
+      "epoch": 0.018638573743922204,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.019043760129659644,
+      "grad_norm": NaN,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.019448946515397084,
+      "grad_norm": NaN,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.01985413290113452,
+      "grad_norm": NaN,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.02025931928687196,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3036637877501952.0,
+  "total_flos": 5918870439198720.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null