Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75562e3246a15d26b7654f8abe42110e9bb645beea72e7da02ed584dd6d51aa0
+oid sha256:5cf92819c598c0f176d87f4df9c4e0c28e10ceafdf2b928e48456d66e8c369ee
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3831b807d987bf641f98512bd1f01e5a738462982b4ce70c68802a2a1981405
+oid sha256:fd0014b616e0e69195fb3213de14d310d1331b26d1ec41171027f935c0a78012
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a21fc8c497409ddc9b996f4582f3a16f6ecb40ae66ee3963e67f3053990ae79
+oid sha256:4d72018e1b083309a146941f9e4b3ad04e76fe2c1f2ad75aec66f569b6d8e871
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aad843443308a13769ba14bc4c69277d1867d41ed29fe98fd53fe751fd3eb52d
+oid sha256:c40dcc1e6b56cd9dcb25d526bbdd1c4f67ba7944c167804456acec9fe00d0a5e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea00c9ebd83f5f58d4b35d81a8606702e0a02050943c66692b2b4de4d5dd422f
+oid sha256:6bb95e3a24e9974009fc61a7c47a202841ba6876158f5a64de2139efb1228e9a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3896736483195324,
+  "epoch": 0.7793472966390648,
   "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": 15.682,
       "eval_steps_per_second": 4.077,
       "step": 25
+    },
+    {
+      "epoch": 0.4052605942523137,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.42084754018509496,
+      "grad_norm": NaN,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.4364344861178763,
+      "grad_norm": NaN,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.4520214320506576,
+      "grad_norm": NaN,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.46760837798343885,
+      "grad_norm": NaN,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.48319532391622017,
+      "grad_norm": NaN,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.4987822698490015,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.5143692157817827,
+      "grad_norm": NaN,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.5299561617145641,
+      "grad_norm": NaN,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.5455431076473454,
+      "grad_norm": NaN,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.5611300535801267,
+      "grad_norm": NaN,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.5767169995129079,
+      "grad_norm": NaN,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.5923039454456892,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.6078908913784705,
+      "grad_norm": NaN,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.6234778373112518,
+      "grad_norm": NaN,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.6390647832440332,
+      "grad_norm": NaN,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.6546517291768145,
+      "grad_norm": NaN,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.6702386751095957,
+      "grad_norm": NaN,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.685825621042377,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.7014125669751583,
+      "grad_norm": NaN,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.7169995129079396,
+      "grad_norm": NaN,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.7325864588407209,
+      "grad_norm": NaN,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.7481734047735021,
+      "grad_norm": NaN,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.7637603507062835,
+      "grad_norm": NaN,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.7793472966390648,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.7793472966390648,
+      "eval_loss": NaN,
+      "eval_runtime": 3.2112,
+      "eval_samples_per_second": 15.57,
+      "eval_steps_per_second": 4.048,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.8298963450855424e+17,
+  "total_flos": 5.659792690171085e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null