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:e5feeac3a993bb2cfe38a6250a8d10866105c66d3d977132c1a9894e34e106d8
+oid sha256:d936aabb480ca5fae6364ac3b8de7e33e7b5e462e6630ded248ae307272054df
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f3a57b1291846abfa3d7d631b056597599bdc1774f48874dd004658cd7058c
+oid sha256:e8b4cc7873d49a2eef7aea09a9b9138b280454806981b41df8f0f582ed1cc963
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab2246ce35e7ce64ce2698ec11dc721f4e76519fed8973ce582374173611c92f
+oid sha256:29c625f59cb26ae54f3255d3f96c9d2e8bbd7bc83d61ca39633ead16a4166ad1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aace979ae288576d45efab9c01d24ab3a2bc32cb3c3d3a7532104464ea843e4a
+oid sha256:50cb0692cbb0a385da2143c88809ac8287c250f7a8df41706cdd6a6f26fb3e6a
 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": 0.02736726874657909,
+  "epoch": 0.05473453749315818,
   "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": 11.451,
       "eval_steps_per_second": 2.977,
       "step": 25
+    },
+    {
+      "epoch": 0.028461959496442254,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.029556650246305417,
+      "grad_norm": NaN,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "grad_norm": NaN,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": NaN,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.03284072249589491,
+      "grad_norm": NaN,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03393541324575807,
+      "grad_norm": NaN,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.03503010399562124,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.0361247947454844,
+      "grad_norm": NaN,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.037219485495347565,
+      "grad_norm": NaN,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.038314176245210725,
+      "grad_norm": NaN,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.03940886699507389,
+      "grad_norm": NaN,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.04050355774493705,
+      "grad_norm": NaN,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.04159824849480022,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.042692939244663386,
+      "grad_norm": NaN,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.043787629994526546,
+      "grad_norm": NaN,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04488232074438971,
+      "grad_norm": NaN,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": NaN,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.04707170224411604,
+      "grad_norm": NaN,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.0481663929939792,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.04926108374384237,
+      "grad_norm": NaN,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.05035577449370553,
+      "grad_norm": NaN,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.051450465243568694,
+      "grad_norm": NaN,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.052545155993431854,
+      "grad_norm": NaN,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.05363984674329502,
+      "grad_norm": NaN,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.05473453749315818,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05473453749315818,
+      "eval_loss": NaN,
+      "eval_runtime": 4.3506,
+      "eval_samples_per_second": 11.493,
+      "eval_steps_per_second": 2.988,
+      "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": 3.57516628583252e+17,
+  "total_flos": 7.155636985124618e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null