Hugging Face's logo

Mattimax
/
microDAC

Text Generation
Transformers
Safetensors
Italian
gpt2
DAC
data-ai
DATA-AI
transformer
experimental
text-generation-inference
Model card Files
xet
Community
Mattimax commited on
Commit
3de0efc
·
verified ·
1 Parent(s): d4d2daf

Upload 18 files

Browse files
Files changed (18) hide show
  1. checkpoint-1308/config.json +40 -0
  2. checkpoint-1308/generation_config.json +11 -0
  3. checkpoint-1308/model.safetensors +3 -0
  4. checkpoint-1308/optimizer.pt +3 -0
  5. checkpoint-1308/rng_state.pth +3 -0
  6. checkpoint-1308/scheduler.pt +3 -0
  7. checkpoint-1308/special_tokens_map.json +46 -0
  8. checkpoint-1308/tokenizer.json +0 -0
  9. checkpoint-1308/tokenizer_config.json +72 -0
  10. checkpoint-1308/trainer_state.json +125 -0
  11. checkpoint-1308/training_args.bin +3 -0
  12. config.json +40 -0
  13. generation_config.json +11 -0
  14. model.safetensors +3 -0
  15. special_tokens_map.json +46 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +72 -0
  18. training_args.bin +3 -0
checkpoint-1308/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "loss_type": "ForCausalLMLoss",
14
+ "model_type": "gpt2",
15
+ "n_ctx": 2048,
16
+ "n_embd": 512,
17
+ "n_head": 8,
18
+ "n_inner": null,
19
+ "n_layer": 16,
20
+ "n_positions": 2048,
21
+ "pad_token_id": 0,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "transformers_version": "4.57.0",
38
+ "use_cache": false,
39
+ "vocab_size": 32000
40
+ }
checkpoint-1308/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2,
6
+ 50256
7
+ ],
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.57.0",
10
+ "use_cache": false
11
+ }
checkpoint-1308/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4aed0e1f6a1e0bd50bba422386415fac2a4f7cdd505421c5cac2f5e74609e35
3
+ size 271506784
checkpoint-1308/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b1993e5ba37c1901e791e688885a36c988f01cd3bfde6e9568c7b262f8d1ac
3
+ size 543138251
checkpoint-1308/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e1043c41d11e6f9bba2d0674f3040754cb5d411d0905059da81f776f7dbeb3
3
+ size 14645
checkpoint-1308/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35590a0a987e27afaf7567a841b202929085c72fcb3866c8d4bec7cf07d6e3d8
3
+ size 1465
checkpoint-1308/special_tokens_map.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|user|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|assistant|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|sep|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "<|bos|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "<|eos|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<|pad|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ }
46
+ }
checkpoint-1308/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1308/tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|pad|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|bos|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|eos|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|user|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<|assistant|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<|sep|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<|unk|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<|user|>",
62
+ "<|assistant|>",
63
+ "<|sep|>"
64
+ ],
65
+ "bos_token": "<|bos|>",
66
+ "clean_up_tokenization_spaces": false,
67
+ "eos_token": "<|eos|>",
68
+ "extra_special_tokens": {},
69
+ "model_max_length": 1000000000000000019884624838656,
70
+ "pad_token": "<|pad|>",
71
+ "tokenizer_class": "PreTrainedTokenizerFast"
72
+ }
checkpoint-1308/trainer_state.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 2000,
7
+ "global_step": 1308,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1530221882172915,
14
+ "grad_norm": 0.8040502667427063,
15
+ "learning_rate": 0.0002994777318812451,
16
+ "loss": 7.6443,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.306044376434583,
21
+ "grad_norm": 0.835146427154541,
22
+ "learning_rate": 0.0002915914482556251,
23
+ "loss": 6.0577,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.4590665646518745,
28
+ "grad_norm": 0.8971789479255676,
29
+ "learning_rate": 0.0002746940863458308,
30
+ "loss": 5.6654,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.612088752869166,
35
+ "grad_norm": 0.7257961630821228,
36
+ "learning_rate": 0.0002498610179546161,
37
+ "loss": 5.4399,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.7651109410864575,
42
+ "grad_norm": 0.7543347477912903,
43
+ "learning_rate": 0.00021867265437140772,
44
+ "loss": 5.26,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.918133129303749,
49
+ "grad_norm": 1.0183438062667847,
50
+ "learning_rate": 0.00018311386678204316,
51
+ "loss": 5.1171,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 1.0703902065799542,
56
+ "grad_norm": 0.5284886956214905,
57
+ "learning_rate": 0.00014544766628363064,
58
+ "loss": 4.9976,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 1.2234123947972455,
63
+ "grad_norm": 0.5938099026679993,
64
+ "learning_rate": 0.00010807118268549186,
65
+ "loss": 4.8596,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 1.376434583014537,
70
+ "grad_norm": 0.6171284317970276,
71
+ "learning_rate": 7.336310780721984e-05,
72
+ "loss": 4.766,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 1.5294567712318288,
77
+ "grad_norm": 0.6369397640228271,
78
+ "learning_rate": 4.353231219625363e-05,
79
+ "loss": 4.7103,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 1.68247895944912,
84
+ "grad_norm": 0.5873697996139526,
85
+ "learning_rate": 2.047726950930969e-05,
86
+ "loss": 4.661,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 1.8355011476664116,
91
+ "grad_norm": 0.5919450521469116,
92
+ "learning_rate": 5.665234987127964e-06,
93
+ "loss": 4.6367,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 1.9885233358837031,
98
+ "grad_norm": 0.6478385925292969,
99
+ "learning_rate": 3.8867273797626995e-08,
100
+ "loss": 4.6238,
101
+ "step": 1300
102
+ }
103
+ ],
104
+ "logging_steps": 100,
105
+ "max_steps": 1308,
106
+ "num_input_tokens_seen": 0,
107
+ "num_train_epochs": 2,
108
+ "save_steps": 2000,
109
+ "stateful_callbacks": {
110
+ "TrainerControl": {
111
+ "args": {
112
+ "should_epoch_stop": false,
113
+ "should_evaluate": false,
114
+ "should_log": false,
115
+ "should_save": true,
116
+ "should_training_stop": true
117
+ },
118
+ "attributes": {}
119
+ }
120
+ },
121
+ "total_flos": 1.4801529605750784e+16,
122
+ "train_batch_size": 8,
123
+ "trial_name": null,
124
+ "trial_params": null
125
+ }
checkpoint-1308/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e5188905589df532b6978cc933ceb5436429b23d99d961990079d9c7ba03c2
3
+ size 5777
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "loss_type": "ForCausalLMLoss",
14
+ "model_type": "gpt2",
15
+ "n_ctx": 2048,
16
+ "n_embd": 512,
17
+ "n_head": 8,
18
+ "n_inner": null,
19
+ "n_layer": 16,
20
+ "n_positions": 2048,
21
+ "pad_token_id": 0,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "transformers_version": "4.57.0",
38
+ "use_cache": false,
39
+ "vocab_size": 32000
40
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2,
6
+ 50256
7
+ ],
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.57.0",
10
+ "use_cache": false
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4aed0e1f6a1e0bd50bba422386415fac2a4f7cdd505421c5cac2f5e74609e35
3
+ size 271506784
special_tokens_map.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|user|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|assistant|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|sep|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "<|bos|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "<|eos|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<|pad|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ }
46
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|pad|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|bos|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|eos|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|user|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<|assistant|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<|sep|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<|unk|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<|user|>",
62
+ "<|assistant|>",
63
+ "<|sep|>"
64
+ ],
65
+ "bos_token": "<|bos|>",
66
+ "clean_up_tokenization_spaces": false,
67
+ "eos_token": "<|eos|>",
68
+ "extra_special_tokens": {},
69
+ "model_max_length": 1000000000000000019884624838656,
70
+ "pad_token": "<|pad|>",
71
+ "tokenizer_class": "PreTrainedTokenizerFast"
72
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e5188905589df532b6978cc933ceb5436429b23d99d961990079d9c7ba03c2
3
+ size 5777