Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f5c9015a9bb396b8b84e3211c75e985cae3e3133e42f52fb3193c8c0597f24
+oid sha256:07dd5ee5d0d3a7a4055356a3bf0632801f26003ed8e6bdff2e481f1935cc3500
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5b94cd5e21e232ccd47f8395a753f34eb133080837217316209b5472cf0924
+oid sha256:870ae205076922d4c72c7a49736f88689c8fbf4246001280f789f4cb1e34e626
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f6891a2dad4098258cacbb534eda6cb23344f32c27a937c7da2508a5fd6662
+oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00506482982171799,
+  "epoch": 0.01012965964343598,
   "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": 29.031,
       "eval_steps_per_second": 14.523,
       "step": 25
+    },
+    {
+      "epoch": 0.00526742301458671,
+      "grad_norm": NaN,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.00547001620745543,
+      "grad_norm": NaN,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.005672609400324149,
+      "grad_norm": NaN,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0058752025931928685,
+      "grad_norm": NaN,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.006077795786061589,
+      "grad_norm": NaN,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.006280388978930308,
+      "grad_norm": NaN,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.006482982171799027,
+      "grad_norm": NaN,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.006685575364667747,
+      "grad_norm": NaN,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.006888168557536467,
+      "grad_norm": NaN,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.007090761750405186,
+      "grad_norm": NaN,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.007293354943273906,
+      "grad_norm": NaN,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0074959481361426255,
+      "grad_norm": NaN,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.007698541329011345,
+      "grad_norm": NaN,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.007901134521880064,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.008103727714748784,
+      "grad_norm": NaN,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.008306320907617504,
+      "grad_norm": NaN,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.008508914100486223,
+      "grad_norm": NaN,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.008711507293354943,
+      "grad_norm": NaN,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.008914100486223663,
+      "grad_norm": NaN,
+      "learning_rate": 1.958900965154743e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.009116693679092382,
+      "grad_norm": NaN,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.009319286871961102,
+      "grad_norm": NaN,
+      "learning_rate": 1.7482355012393177e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.009521880064829822,
+      "grad_norm": NaN,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.009724473257698542,
+      "grad_norm": NaN,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.00992706645056726,
+      "grad_norm": NaN,
+      "learning_rate": 1.443454345648252e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.01012965964343598,
+      "grad_norm": NaN,
+      "learning_rate": 1.3456284669124158e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.01012965964343598,
+      "eval_loss": NaN,
+      "eval_runtime": 71.5185,
+      "eval_samples_per_second": 29.069,
+      "eval_steps_per_second": 14.542,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2630470487506944.0,
+  "total_flos": 5234896712761344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null