Hugging Face's logo

mkhalifa
/
grace-discrim-multiarith

PyTorch
Model card Files
xet
Community
Muhammad Khalifa commited on
Commit
5194ecc
·
1 Parent(s): cf8b0a5

first commit

Browse files
Files changed (9) hide show
  1. added_tokens.json +6 -0
  2. data_args.json +15 -0
  3. model_args.json +4 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +109 -0
  6. spiece.model +3 -0
  7. tokenizer_config.json +112 -0
  8. train_args.json +121 -0
  9. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<<": 32100,
3
+ ">>": 32101,
4
+ "[CLS]": 32102,
5
+ "[SEP]": 32103
6
+ }
data_args.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_style": "enc",
3
+ "task": "multiarith",
4
+ "trajectory_path": "data/discriminator_data/sampled_trajectories/multiarith-clean/llama-7b/trajectories.jsonl",
5
+ "validation_split_percentage": 5,
6
+ "max_len": 512,
7
+ "n_examples": null,
8
+ "dev_is_train": false,
9
+ "invalid_prefix_prob": 0.0,
10
+ "max_alignment_cost": 2.0,
11
+ "step_aligner_model": "roscoe",
12
+ "step_delimiter": null,
13
+ "break_after_extra_step": false,
14
+ "use_correct_samples": false
15
+ }
model_args.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "model": "google/flan-t5-large",
3
+ "pooling": "max"
4
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85613bfeea255b9b4a36fe6fbc9b97befe2317ec648adbba2f88169440e9e70
3
+ size 3136877397
special_tokens_map.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "cls_token": "[CLS]",
105
+ "eos_token": "</s>",
106
+ "pad_token": "<pad>",
107
+ "sep_token": "[SEP]",
108
+ "unk_token": "<unk>"
109
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
train_args.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "ckpts/discrim/contrastive_models/gen.llama-7b/flan_t5_large_multiarith-clean_100K/",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": true,
6
+ "do_predict": false,
7
+ "evaluation_strategy": "steps",
8
+ "prediction_loss_only": true,
9
+ "per_device_train_batch_size": 8,
10
+ "per_device_eval_batch_size": 8,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "learning_rate": 6e-05,
17
+ "weight_decay": 0.01,
18
+ "adam_beta1": 0.9,
19
+ "adam_beta2": 0.999,
20
+ "adam_epsilon": 1e-08,
21
+ "max_grad_norm": 1.0,
22
+ "num_train_epochs": 5.0,
23
+ "max_steps": -1,
24
+ "lr_scheduler_type": "cosine_with_restarts",
25
+ "warmup_ratio": 0.06,
26
+ "warmup_steps": 0,
27
+ "log_level": "passive",
28
+ "log_level_replica": "warning",
29
+ "log_on_each_node": true,
30
+ "logging_dir": "ckpts/discrim/contrastive_models/gen.llama-7b/flan_t5_large_multiarith-clean_100K/runs/May20_03-24-27_leibniz",
31
+ "logging_strategy": "steps",
32
+ "logging_first_step": false,
33
+ "logging_steps": 50,
34
+ "logging_nan_inf_filter": true,
35
+ "save_strategy": "steps",
36
+ "save_steps": 1000,
37
+ "save_total_limit": 2,
38
+ "save_safetensors": false,
39
+ "save_on_each_node": false,
40
+ "no_cuda": false,
41
+ "use_mps_device": false,
42
+ "seed": 7,
43
+ "data_seed": null,
44
+ "jit_mode_eval": false,
45
+ "use_ipex": false,
46
+ "bf16": true,
47
+ "fp16": false,
48
+ "fp16_opt_level": "O1",
49
+ "half_precision_backend": "cuda_amp",
50
+ "bf16_full_eval": false,
51
+ "fp16_full_eval": false,
52
+ "tf32": null,
53
+ "local_rank": 0,
54
+ "xpu_backend": null,
55
+ "tpu_num_cores": null,
56
+ "tpu_metrics_debug": false,
57
+ "debug": [],
58
+ "dataloader_drop_last": false,
59
+ "eval_steps": 1000,
60
+ "dataloader_num_workers": 0,
61
+ "past_index": -1,
62
+ "run_name": "ckpts/discrim/contrastive_models/gen.llama-7b/flan_t5_large_multiarith-clean_100K/",
63
+ "disable_tqdm": false,
64
+ "remove_unused_columns": true,
65
+ "label_names": null,
66
+ "load_best_model_at_end": true,
67
+ "metric_for_best_model": "loss",
68
+ "greater_is_better": false,
69
+ "ignore_data_skip": false,
70
+ "sharded_ddp": [],
71
+ "fsdp": [],
72
+ "fsdp_min_num_params": 0,
73
+ "fsdp_config": {
74
+ "fsdp_min_num_params": 0,
75
+ "xla": false,
76
+ "xla_fsdp_grad_ckpt": false
77
+ },
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "deepspeed": null,
80
+ "label_smoothing_factor": 0.0,
81
+ "optim": "adamw_hf",
82
+ "optim_args": null,
83
+ "adafactor": false,
84
+ "group_by_length": false,
85
+ "length_column_name": "length",
86
+ "report_to": [
87
+ "wandb"
88
+ ],
89
+ "ddp_find_unused_parameters": null,
90
+ "ddp_bucket_cap_mb": null,
91
+ "dataloader_pin_memory": true,
92
+ "skip_memory_metrics": true,
93
+ "use_legacy_prediction_loop": false,
94
+ "push_to_hub": false,
95
+ "resume_from_checkpoint": null,
96
+ "hub_model_id": null,
97
+ "hub_strategy": "every_save",
98
+ "hub_token": null,
99
+ "hub_private_repo": false,
100
+ "gradient_checkpointing": false,
101
+ "include_inputs_for_metrics": false,
102
+ "fp16_backend": "auto",
103
+ "push_to_hub_model_id": null,
104
+ "push_to_hub_organization": null,
105
+ "push_to_hub_token": null,
106
+ "_n_gpu": 1,
107
+ "mp_parameters": "",
108
+ "auto_find_batch_size": false,
109
+ "full_determinism": false,
110
+ "torchdynamo": null,
111
+ "ray_scope": "last",
112
+ "ddp_timeout": 1800,
113
+ "torch_compile": false,
114
+ "torch_compile_backend": null,
115
+ "torch_compile_mode": null,
116
+ "margin": 1.0,
117
+ "ckpt_dir": null,
118
+ "loss_type": "maxmargin",
119
+ "fix_tokenizer": false,
120
+ "dev_metric": "loss"
121
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c4852fc2e1d52afb34e43ff6e4a8de9233aac1b180bdae5a6a12162246233b
3
+ size 3835