Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4703734016b9126fc17594fcfa8b023554a6a97fedf5597c02c6083c80bfabf3
+oid sha256:179b8efca90dc9dde7e0a8cc2d12970c5f97a05fd76efd9625c67d28e0f7b5e9
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d4f1bfae77ffc874d5a250e1a852ec6eb483852d9fbaaef0a47fabf0ca6322
+oid sha256:7a4422b3d1f964db21d93a8ffbd30ae226dcced1cd77f55c1377a3731485311e
 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": 0.1182033096926714,
+  "epoch": 0.2364066193853428,
   "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": 0.12293144208037825,
+      "grad_norm": NaN,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "eval_loss": NaN,
+      "eval_runtime": 17.6996,
+      "eval_samples_per_second": 10.057,
+      "eval_steps_per_second": 1.299,
+      "step": 27
+    },
+    {
+      "epoch": 0.13238770685579196,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.13711583924349882,
+      "grad_norm": NaN,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.14657210401891252,
+      "grad_norm": NaN,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.15130023640661938,
+      "grad_norm": NaN,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.15602836879432624,
+      "grad_norm": NaN,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.1607565011820331,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.16548463356973994,
+      "grad_norm": NaN,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "eval_loss": NaN,
+      "eval_runtime": 17.6898,
+      "eval_samples_per_second": 10.062,
+      "eval_steps_per_second": 1.3,
+      "step": 36
+    },
+    {
+      "epoch": 0.17494089834515367,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.17966903073286053,
+      "grad_norm": NaN,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.18439716312056736,
+      "grad_norm": NaN,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.18912529550827423,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.1938534278959811,
+      "grad_norm": NaN,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.19858156028368795,
+      "grad_norm": NaN,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.2033096926713948,
+      "grad_norm": NaN,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.20803782505910165,
+      "grad_norm": NaN,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "eval_loss": NaN,
+      "eval_runtime": 17.6849,
+      "eval_samples_per_second": 10.065,
+      "eval_steps_per_second": 1.301,
+      "step": 45
+    },
+    {
+      "epoch": 0.21749408983451538,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": NaN,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.22695035460992907,
+      "grad_norm": NaN,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.23167848699763594,
+      "grad_norm": NaN,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.2364066193853428,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.63364550475776e+16,
+  "total_flos": 3.26729100951552e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null