Hugging Face's logo

golaxy
/
gogpt2-7b-pretrain

Text Generation
Transformers
PyTorch
TensorBoard
Chinese
llama
llama2
chinese-llama2
gogpt2-7b
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Chriskuei commited on
Commit
6a3a040
·
1 Parent(s): 67eb539

nit

Browse files
Files changed (36) hide show
  1. all_results.json +15 -0
  2. checkpoint-4000/config.json +26 -0
  3. checkpoint-4000/global_step4000/mp_rank_00_model_states.pt +3 -0
  4. checkpoint-4000/global_step4000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  5. checkpoint-4000/pytorch_model-00001-of-00002.bin +3 -0
  6. checkpoint-4000/rng_state_1.pth +3 -0
  7. checkpoint-4000/rng_state_2.pth +3 -0
  8. checkpoint-4000/rng_state_3.pth +3 -0
  9. checkpoint-4000/rng_state_4.pth +3 -0
  10. checkpoint-4000/rng_state_5.pth +3 -0
  11. checkpoint-4000/rng_state_6.pth +3 -0
  12. checkpoint-4000/rng_state_7.pth +3 -0
  13. checkpoint-4000/trainer_state.json +3142 -0
  14. checkpoint-4000/training_args.bin +3 -0
  15. checkpoint-4000/zero_to_fp32.py +578 -0
  16. config.json +26 -0
  17. eval_results.json +10 -0
  18. generation_config.json +9 -0
  19. pytorch_model-00001-of-00002.bin +3 -0
  20. pytorch_model-00002-of-00002.bin +3 -0
  21. pytorch_model.bin.index.json +330 -0
  22. runs/Jul19_14-52-29_715436/1689749887.7189374/events.out.tfevents.1689749887.715436.72469.1 +3 -0
  23. runs/Jul19_14-52-29_715436/events.out.tfevents.1689749887.715436.72469.0 +3 -0
  24. runs/Jul19_14-59-01_715436/1689750342.6405456/events.out.tfevents.1689750342.715436.75291.1 +3 -0
  25. runs/Jul19_14-59-01_715436/events.out.tfevents.1689750342.715436.75291.0 +3 -0
  26. runs/Jul19_15-22-48_715436/1689751771.9245906/events.out.tfevents.1689751771.715436.80001.1 +3 -0
  27. runs/Jul19_15-22-48_715436/events.out.tfevents.1689751771.715436.80001.0 +3 -0
  28. runs/Jul20_03-05-51_715436/1689793875.322509/events.out.tfevents.1689793875.715436.71505.1 +3 -0
  29. runs/Jul20_03-05-51_715436/events.out.tfevents.1689793875.715436.71505.0 +3 -0
  30. runs/Jul20_03-05-51_715436/events.out.tfevents.1689902211.715436.71505.2 +3 -0
  31. special_tokens_map.json +23 -0
  32. tokenizer.model +3 -0
  33. tokenizer_config.json +35 -0
  34. train_results.json +8 -0
  35. trainer_state.json +3820 -0
  36. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.3399546485260771,
4
+ "eval_loss": 4.18359375,
5
+ "eval_runtime": 6.4986,
6
+ "eval_samples": 35,
7
+ "eval_samples_per_second": 5.386,
8
+ "eval_steps_per_second": 0.308,
9
+ "perplexity": 65.60118435636834,
10
+ "train_loss": 3.7094925158997714,
11
+ "train_runtime": 108243.5499,
12
+ "train_samples": 311198,
13
+ "train_samples_per_second": 2.875,
14
+ "train_steps_per_second": 0.045
15
+ }
checkpoint-4000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/searchgpt/yq/GoGPT/outputs-pt-v1-7b-llama2/ckpt",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.29.1",
24
+ "use_cache": false,
25
+ "vocab_size": 68419
26
+ }
checkpoint-4000/global_step4000/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:814e8129fe526c42fdbd6fe4ff2c9b21f0c161f6982e3883c3e5fea1260a4cb1
3
+ size 2607759360
checkpoint-4000/global_step4000/zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aabd69e33896e791496a8b91b6325d7e6dafe50483e2ed374bf68f6bbc025924
3
+ size 840736473
checkpoint-4000/pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb73d2c6cc7cec148b9ea0157637718f3414f3a18d493daf4255e47befedae9
3
+ size 10531361877
checkpoint-4000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f1e51f8b260af2143aa0e342ab171171f7d983fbaaf95e9400d872b4d8c542
3
+ size 21687
checkpoint-4000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057591ad3bc33c9f75b1e6556c3c29b4328e0785d67a420f2a5a8bb25e58812e
3
+ size 21687
checkpoint-4000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b595d89f2fe53ca5dccc290b880b858a60eb07a5f694175f05519f2257fafbf
3
+ size 21687
checkpoint-4000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dae996da909b80faa4e9fef9f945126f53fa3c7c6da06367a3f71ae24b0f138
3
+ size 21687
checkpoint-4000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de190b28a07218f4d05a1c7ccfccc4e53d6033af244fe3bd9fe3e20275d59de
3
+ size 21687
checkpoint-4000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4cccb61a1758c3ec09da0ddc7ef0957d32362d5baa800f340839c1fa72376e2
3
+ size 21687
checkpoint-4000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed085eb5cf063033df209f9c7714e3c87ee78a57b9ee629a7258a15bd8cde7ac
3
+ size 21687
checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,3142 @@