Hugging Face's logo

nmthien
/
vietnamese-gpt2

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
nmthien commited on
Commit
c93aa31
·
verified ·
1 Parent(s): 0537eff

Training in progress, step 6500, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +81 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9e0275bab1a6a9782df65a6f8abfba7e17a82295a2cbdb95725d3f45b1e28a0
3
  size 441688704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e5337b3e0214b4729f349032988a9b03806846f7f4bd6d268aef041b459c52
3
  size 441688704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:412e90b7208921d172da8d70bcf2d9eb483f1ba3bacdde12388ae0f1699757ba
3
  size 883473803
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59fe147cb04454b19d7862577b716d215f62ea0d638e3a53e231ac5e1783553f
3
  size 883473803
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c4bb3232333245cce0402989a808fbb8a3484f7c8d0a74db5b1f083ad707d43
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb312d65febc64758e9d1fe191e5c3c93cd8ec224be66347404eb3503c7f723
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6af98c8a00430bf78cf7a33095a269f67cf12c82df483a872be441460ebbbf74
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd42e357d6b98cb9bff543c6a4f4b9f46ab579a827a6b5d2df5dd5d499424c0
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e49e65fc711539cf4a80289687bb7ae73d6c8503caf26e61f786d781a7e51b3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bfe8ee0b406625e2e6930efb21c3d4599f197be5d04a29012b92920efae4631
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.7058823529411765,
6
  "eval_steps": 500,
7
- "global_step": 6000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -944,6 +944,84 @@
944
  "eval_samples_per_second": 48.821,
945
  "eval_steps_per_second": 1.528,
946
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
947
  }
948
  ],
949
  "logging_steps": 50,
@@ -963,7 +1041,7 @@
963
  "attributes": {}
964
  }
965
  },
966
- "total_flos": 1.00336140288e+17,
967
  "train_batch_size": 32,
968
  "trial_name": null,
969
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7647058823529411,
6
  "eval_steps": 500,
7
+ "global_step": 6500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
944
  "eval_samples_per_second": 48.821,
945
  "eval_steps_per_second": 1.528,
946
  "step": 6000
947
+ },
948
+ {
949
+ "epoch": 0.711764705882353,
950
+ "grad_norm": 0.3450179696083069,
951
+ "learning_rate": 0.0001441764705882353,
952
+ "loss": 3.5081927490234377,
953
+ "step": 6050
954
+ },
955
+ {
956
+ "epoch": 0.7176470588235294,
957
+ "grad_norm": 0.3508113920688629,
958
+ "learning_rate": 0.00014123529411764707,
959
+ "loss": 3.5310910034179686,
960
+ "step": 6100
961
+ },
962
+ {
963
+ "epoch": 0.7235294117647059,
964
+ "grad_norm": 0.35503652691841125,
965
+ "learning_rate": 0.00013829411764705883,
966
+ "loss": 3.542174072265625,
967
+ "step": 6150
968
+ },
969
+ {
970
+ "epoch": 0.7294117647058823,
971
+ "grad_norm": 0.3807806074619293,
972
+ "learning_rate": 0.0001353529411764706,
973
+ "loss": 3.5378152465820314,
974
+ "step": 6200
975
+ },
976
+ {
977
+ "epoch": 0.7352941176470589,
978
+ "grad_norm": 0.3575717508792877,
979
+ "learning_rate": 0.00013241176470588233,
980
+ "loss": 3.327708740234375,
981
+ "step": 6250
982
+ },
983
+ {
984
+ "epoch": 0.7411764705882353,
985
+ "grad_norm": 0.34574732184410095,
986
+ "learning_rate": 0.00012947058823529413,
987
+ "loss": 3.2896099853515626,
988
+ "step": 6300
989
+ },
990
+ {
991
+ "epoch": 0.7470588235294118,
992
+ "grad_norm": 0.3618618845939636,
993
+ "learning_rate": 0.0001265294117647059,
994
+ "loss": 3.4104681396484375,
995
+ "step": 6350
996
+ },
997
+ {
998
+ "epoch": 0.7529411764705882,
999
+ "grad_norm": 0.39512887597084045,
1000
+ "learning_rate": 0.00012358823529411766,
1001
+ "loss": 3.5210690307617187,
1002
+ "step": 6400
1003
+ },
1004
+ {
1005
+ "epoch": 0.7588235294117647,
1006
+ "grad_norm": 0.36507633328437805,
1007
+ "learning_rate": 0.00012064705882352942,
1008
+ "loss": 3.5360977172851564,
1009
+ "step": 6450
1010
+ },
1011
+ {
1012
+ "epoch": 0.7647058823529411,
1013
+ "grad_norm": 0.3706028461456299,
1014
+ "learning_rate": 0.00011770588235294117,
1015
+ "loss": 3.5502828979492187,
1016
+ "step": 6500
1017
+ },
1018
+ {
1019
+ "epoch": 0.7647058823529411,
1020
+ "eval_loss": 3.3835549354553223,
1021
+ "eval_runtime": 175.4441,
1022
+ "eval_samples_per_second": 49.549,
1023
+ "eval_steps_per_second": 1.55,
1024
+ "step": 6500
1025
  }
1026
  ],
1027
  "logging_steps": 50,
 
1041
  "attributes": {}
1042
  }
1043
  },
1044
+ "total_flos": 1.08697485312e+17,
1045
  "train_batch_size": 32,
1046
  "trial_name": null,
1047
  "trial_params": null