Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b9bf232e4a6ef968ad1b4c1b1bfe7342e021a163790c978f046772d83bac7b
+oid sha256:9bf219203169155f0ba49692dda7b173b05527cc5ec37b5523af619e2b9d80d6
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3fa868721523b792982e7220748b07f4179f95e86f5dda8a43091793398074
+oid sha256:c92b9494e768f997d81f97a3ed397494cf92bafe4962d0b95e00b8c007da5a8d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:448bbc553540594d633ec30ae1c253e733828d3dc87d75d93d24f77b036cc560
+oid sha256:f76a55d3b6d411688470e6cf3013a12bdc47afb74e2a72b6e1364af79077d04b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc4901b159f74fdbb5a3fb1d67edf3f42447515a8bebc49be5a5ca3c03d052b
+oid sha256:d579e10fc5d75a0cf8184362888fbbb8f7711e4113fea00d39ea00e90b75ff21
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c756a24eb4b8a136f869c0788960b4ee1d45f7dec2c29901b7bdd6f9d512e95d
+oid sha256:2b197f4a916c4103304657f40e4a3e6d93f55520536e672cd3271cc8b5bd7771
 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": 0.22259321090706732,
+  "epoch": 0.44518642181413465,
   "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": 16.807,
       "eval_steps_per_second": 4.37,
       "step": 25
+    },
+    {
+      "epoch": 0.23149693934335003,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.24040066777963273,
+      "grad_norm": NaN,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.2493043962159154,
+      "grad_norm": NaN,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.2582081246521981,
+      "grad_norm": NaN,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.2671118530884808,
+      "grad_norm": NaN,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.2760155815247635,
+      "grad_norm": NaN,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.2849193099610462,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.2938230383973289,
+      "grad_norm": NaN,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.30272676683361155,
+      "grad_norm": NaN,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.3116304952698943,
+      "grad_norm": NaN,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.32053422370617696,
+      "grad_norm": NaN,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.32943795214245963,
+      "grad_norm": NaN,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.33834168057874237,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.34724540901502504,
+      "grad_norm": NaN,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.3561491374513077,
+      "grad_norm": NaN,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.36505286588759045,
+      "grad_norm": NaN,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.3739565943238731,
+      "grad_norm": NaN,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.3828603227601558,
+      "grad_norm": NaN,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.39176405119643853,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.4006677796327212,
+      "grad_norm": NaN,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.4095715080690039,
+      "grad_norm": NaN,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.41847523650528656,
+      "grad_norm": NaN,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.4273789649415693,
+      "grad_norm": NaN,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.43628269337785197,
+      "grad_norm": NaN,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.44518642181413465,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.44518642181413465,
+      "eval_loss": NaN,
+      "eval_runtime": 2.9713,
+      "eval_samples_per_second": 16.828,
+      "eval_steps_per_second": 4.375,
+      "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": 2.817301471601623e+17,
+  "total_flos": 5.6319666600647066e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null