Hugging Face's logo

kejian
/
debug-pt-conditional

Transformers
PyTorch
English
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
1
kejian commited on
Commit
36ed44f
·
1 Parent(s): 602e7aa

Training in progress, step 10

Browse files
Files changed (23) hide show
  1. added_tokens.json +4 -0
  2. checkpoint-10/added_tokens.json +4 -0
  3. checkpoint-10/config.json +39 -0
  4. checkpoint-10/merges.txt +0 -0
  5. checkpoint-10/optimizer.pt +3 -0
  6. checkpoint-10/pytorch_model.bin +3 -0
  7. checkpoint-10/rng_state.pth +3 -0
  8. checkpoint-10/scaler.pt +3 -0
  9. checkpoint-10/scheduler.pt +3 -0
  10. checkpoint-10/special_tokens_map.json +10 -0
  11. checkpoint-10/tokenizer.json +0 -0
  12. checkpoint-10/tokenizer_config.json +10 -0
  13. checkpoint-10/trainer_state.json +86 -0
  14. checkpoint-10/training_args.bin +3 -0
  15. checkpoint-10/vocab.json +0 -0
  16. config.json +39 -0
  17. merges.txt +0 -0
  18. pytorch_model.bin +3 -0
  19. special_tokens_map.json +10 -0
  20. tokenizer.json +0 -0
  21. tokenizer_config.json +10 -0
  22. training_args.bin +3 -0
  23. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|aligned|>": 32768,
3
+ "<|misaligned|>": 32769
4
+ }
checkpoint-10/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|aligned|>": 32768,
3
+ "<|misaligned|>": 32769
4
+ }
checkpoint-10/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "codeparrot/codeparrot-small",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": true,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": true,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.23.0",
37
+ "use_cache": true,
38
+ "vocab_size": 32770
39
+ }
checkpoint-10/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1c4794fd0d8d0496a3090cf4a475aa399ac5de0d998858f48a3c5121efee025
3
+ size 888164869
checkpoint-10/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd7462249e492f6f210a7658d1c633831d667aa3832213850dbe1172d70118b
3
+ size 456677949
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:161a56127a981ee95a98604b846e7d094c4d36965e080acf468d3b9d780a531c
3
+ size 14511
checkpoint-10/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285e76ebe66a23f043b42182e14294a93d529fdc5c0c08159fd9fc10bbeaad36
3
+ size 557
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c2ddb7902910d2c20a8a5f45dc537e670c0c8e8e1ae57a7480a7a1ff175c04
3
+ size 627
checkpoint-10/special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|aligned|>",
4
+ "<|misaligned|>"
5
+ ],
6
+ "bos_token": "<|endoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "<|endoftext|>",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-10/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "codeparrot/codeparrot-small",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-10/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.00019859395480001588,
5
+ "global_step": 10,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.5873015873015873e-06,
13
+ "loss": 10.5611,
14
+ "theoretical_loss": 20.84128112621979,
15
+ "tokens_seen": 65536
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 3.1746031746031746e-06,
20
+ "loss": 10.5541,
21
+ "theoretical_loss": 17.594664429001284,
22
+ "tokens_seen": 131072
23
+ },
24
+ {
25
+ "epoch": 0.0,
26
+ "learning_rate": 4.7619047619047615e-06,
27
+ "loss": 10.4474,
28
+ "theoretical_loss": 15.967940417509208,
29
+ "tokens_seen": 196608
30
+ },
31
+ {
32
+ "epoch": 0.0,
33
+ "learning_rate": 6.349206349206349e-06,
34
+ "loss": 10.2462,
35
+ "theoretical_loss": 14.92078008066121,
36
+ "tokens_seen": 262144
37
+ },
38
+ {
39
+ "epoch": 0.0,
40
+ "learning_rate": 7.936507936507936e-06,
41
+ "loss": 10.0164,
42
+ "theoretical_loss": 14.164680262435617,
43
+ "tokens_seen": 327680
44
+ },
45
+ {
46
+ "epoch": 0.0,
47
+ "learning_rate": 9.523809523809523e-06,
48
+ "loss": 9.716,
49
+ "theoretical_loss": 13.581024797222863,
50
+ "tokens_seen": 393216
51
+ },
52
+ {
53
+ "epoch": 0.0,
54
+ "learning_rate": 1.1111111111111112e-05,
55
+ "loss": 9.4783,
56
+ "theoretical_loss": 13.11027232607383,
57
+ "tokens_seen": 458752
58
+ },
59
+ {
60
+ "epoch": 0.0,
61
+ "learning_rate": 1.2698412698412699e-05,
62
+ "loss": 9.3542,
63
+ "theoretical_loss": 12.718592950155966,
64
+ "tokens_seen": 524288
65
+ },
66
+ {
67
+ "epoch": 0.0,
68
+ "learning_rate": 1.4285714285714285e-05,
69
+ "loss": 9.1909,
70
+ "theoretical_loss": 12.385055788546264,
71
+ "tokens_seen": 589824
72
+ },
73
+ {
74
+ "epoch": 0.0,
75
+ "learning_rate": 1.5873015873015872e-05,
76
+ "loss": 9.0334,
77
+ "theoretical_loss": 12.09587593170772,
78
+ "tokens_seen": 655360
79
+ }
80
+ ],
81
+ "max_steps": 50354,
82
+ "num_train_epochs": 9223372036854775807,
83
+ "total_flos": 334453800960000.0,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e1de143a346134b48eeb8e53dee538b9629bd2ac1815c9ff4c63785678812b
3
+ size 3387
checkpoint-10/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "codeparrot/codeparrot-small",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": true,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": true,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.23.0",
37
+ "use_cache": true,
38
+ "vocab_size": 32770
39
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd7462249e492f6f210a7658d1c633831d667aa3832213850dbe1172d70118b
3
+ size 456677949
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|aligned|>",
4
+ "<|misaligned|>"
5
+ ],
6
+ "bos_token": "<|endoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "<|endoftext|>",
9
+ "unk_token": "<|endoftext|>"
10
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "codeparrot/codeparrot-small",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e1de143a346134b48eeb8e53dee538b9629bd2ac1815c9ff4c63785678812b
3
+ size 3387
vocab.json ADDED
The diff for this file is too large to render. See raw diff