Hugging Face's logo

quintic
/
finetune_lean_2b

Text Generation
Transformers
PyTorch
Safetensors
codegen
Model card Files
xet
 Community
1
quintic commited on
Commit
234adcf
·
1 Parent(s): 9073631

first commit

Browse files
Files changed (12) hide show
  1. added_tokens.json +40 -0
  2. all_results.json +8 -0
  3. config.json +42 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +5 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +10 -0
  9. train_results.json +8 -0
  10. trainer_state.json +145 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "train_loss": 0.8623725891113281,
4
+ "train_runtime": 17895.3422,
5
+ "train_samples": 7338,
6
+ "train_samples_per_second": 8.201,
7
+ "train_steps_per_second": 0.032
8
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "codegen-2b",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "CodeGenForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "codegen",
15
+ "n_ctx": 2048,
16
+ "n_embd": 2560,
17
+ "n_head": 32,
18
+ "n_inner": null,
19
+ "n_layer": 32,
20
+ "n_positions": 2048,
21
+ "resid_pdrop": 0.0,
22
+ "rotary_dim": 64,
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
+ "temperature": 1.0
34
+ }
35
+ },
36
+ "tie_word_embeddings": false,
37
+ "tokenizer_class": "GPT2Tokenizer",
38
+ "torch_dtype": "float16",
39
+ "transformers_version": "4.26.0.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 50295
42
+ }
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 sha256:5491ba16df5b25ecc315722771ce961d22e94387d5c6219c8860c6a3adb2c761
3
+ size 5683754645
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
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": 2048,
6
+ "name_or_path": "codegen-2b",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "CodeGenTokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "train_loss": 0.8623725891113281,
4
+ "train_runtime": 17895.3422,
5
+ "train_samples": 7338,
6
+ "train_samples_per_second": 8.201,
7
+ "train_steps_per_second": 0.032
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 20.0,
5
+ "global_step": 580,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 3.6559821951932435e-06,
13
+ "loss": 2.0662,
14
+ "step": 29
15
+ },
16
+ {
17
+ "epoch": 2.0,
18
+ "learning_rate": 5.463687482021196e-06,
19
+ "loss": 1.413,
20
+ "step": 58
21
+ },
22
+ {
23
+ "epoch": 3.0,
24
+ "learning_rate": 6.2507068274056945e-06,
25
+ "loss": 1.1678,
26
+ "step": 87
27
+ },
28
+ {
29
+ "epoch": 4.0,
30
+ "learning_rate": 6.760687110038668e-06,
31
+ "loss": 1.0382,
32
+ "step": 116
33
+ },
34
+ {
35
+ "epoch": 5.0,
36
+ "learning_rate": 7.13867309942701e-06,
37
+ "loss": 0.954,
38
+ "step": 145
39
+ },
40
+ {
41
+ "epoch": 6.0,
42
+ "learning_rate": 7.439130415804967e-06,
43
+ "loss": 0.8951,
44
+ "step": 174
45
+ },
46
+ {
47
+ "epoch": 7.0,
48
+ "learning_rate": 7.688512885309291e-06,
49
+ "loss": 0.8487,
50
+ "step": 203
51
+ },
52
+ {
53
+ "epoch": 8.0,
54
+ "learning_rate": 7.901687980648141e-06,
55
+ "loss": 0.8119,
56
+ "step": 232
57
+ },
58
+ {
59
+ "epoch": 9.0,
60
+ "learning_rate": 8.087848755754509e-06,
61
+ "loss": 0.7811,
62
+ "step": 261
63
+ },
64
+ {
65
+ "epoch": 10.0,
66
+ "learning_rate": 8.253078243154342e-06,
67
+ "loss": 0.7546,
68
+ "step": 290
69
+ },
70
+ {
71
+ "epoch": 11.0,
72
+ "learning_rate": 8.401611184973133e-06,
73
+ "loss": 0.7308,
74
+ "step": 319
75
+ },
76
+ {
77
+ "epoch": 12.0,
78
+ "learning_rate": 8.53651443066959e-06,
79
+ "loss": 0.7102,
80
+ "step": 348
81
+ },
82
+ {
83
+ "epoch": 13.0,
84
+ "learning_rate": 8.66008046615066e-06,
85
+ "loss": 0.6909,
86
+ "step": 377
87
+ },
88
+ {
89
+ "epoch": 14.0,
90
+ "learning_rate": 8.774067992353493e-06,
91
+ "loss": 0.6728,
92
+ "step": 406
93
+ },
94
+ {
95
+ "epoch": 15.0,
96
+ "learning_rate": 8.879855771890845e-06,
97
+ "loss": 0.6564,
98
+ "step": 435
99
+ },
100
+ {
101
+ "epoch": 16.0,
102
+ "learning_rate": 8.9785447549646e-06,
103
+ "loss": 0.64,
104
+ "step": 464
105
+ },
106
+ {
107
+ "epoch": 17.0,
108
+ "learning_rate": 9.071028041604564e-06,
109
+ "loss": 0.6247,
110
+ "step": 493
111
+ },
112
+ {
113
+ "epoch": 18.0,
114
+ "learning_rate": 9.15804011885607e-06,
115
+ "loss": 0.611,
116
+ "step": 522
117
+ },
118
+ {
119
+ "epoch": 19.0,
120
+ "learning_rate": 9.240192329946528e-06,
121
+ "loss": 0.5964,
122
+ "step": 551
123
+ },
124
+ {
125
+ "epoch": 20.0,
126
+ "learning_rate": 9.317998951644404e-06,
127
+ "loss": 0.5837,
128
+ "step": 580
129
+ },
130
+ {
131
+ "epoch": 20.0,
132
+ "step": 580,
133
+ "total_flos": 1134007009935360.0,
134
+ "train_loss": 0.8623725891113281,
135
+ "train_runtime": 17895.3422,
136
+ "train_samples_per_second": 8.201,
137
+ "train_steps_per_second": 0.032
138
+ }
139
+ ],
140
+ "max_steps": 580,
141
+ "num_train_epochs": 20,
142
+ "total_flos": 1134007009935360.0,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af1939104c42f2af07f1335fe47d2c0404dc2544f0d711e0c77c51425d77d88f
3
+ size 4603
vocab.json ADDED
The diff for this file is too large to render. See raw diff