Hugging Face's logo

MetaCore-LLM
/
MetaCore-1-Test-Instruct

Text Generation
Transformers
Safetensors
Russian
llama
russian
causal-lm
instruction-tuning
sft
tiny
text-generation-inference
Model card Files
xet
 Community
MetaCore-LLM commited on
Commit
27796c5
·
verified ·
1 Parent(s): 0cd523b

Загрузка SFT модели

Browse files
Files changed (18) hide show
  1. checkpoint-392/config.json +32 -0
  2. checkpoint-392/generation_config.json +7 -0
  3. checkpoint-392/model.safetensors +3 -0
  4. checkpoint-392/optimizer.pt +3 -0
  5. checkpoint-392/rng_state_0.pth +3 -0
  6. checkpoint-392/rng_state_1.pth +3 -0
  7. checkpoint-392/scaler.pt +3 -0
  8. checkpoint-392/scheduler.pt +3 -0
  9. checkpoint-392/tokenizer.json +0 -0
  10. checkpoint-392/tokenizer_config.json +14 -0
  11. checkpoint-392/trainer_state.json +167 -0
  12. checkpoint-392/training_args.bin +3 -0
  13. config.json +32 -0
  14. generation_config.json +7 -0
  15. model.safetensors +3 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +14 -0
  18. training_args.bin +3 -0
checkpoint-392/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": null,
10
+ "head_dim": 32,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 128,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 384,
15
+ "max_position_embeddings": 256,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 4,
19
+ "num_hidden_layers": 4,
20
+ "num_key_value_heads": 4,
21
+ "pad_token_id": null,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_parameters": {
25
+ "rope_theta": 10000,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": true,
29
+ "transformers_version": "5.0.0",
30
+ "use_cache": false,
31
+ "vocab_size": 119547
32
+ }
checkpoint-392/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.0.0",
6
+ "use_cache": true
7
+ }
checkpoint-392/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488ae2bf3724b663a30aacd2afdb1df70b8daf5b241eef22992520e8902f29f7
3
+ size 64624680
checkpoint-392/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18dc158aec1c7c9da10b14e8ae1f2e79ef5576816e55352d58f248b25c3863bf
3
+ size 129274187
checkpoint-392/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7
3
+ size 14917
checkpoint-392/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e
3
+ size 14917
checkpoint-392/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f4fed85ea0917cc2d05bf8af0c7463301adc898027ff20864aac2aa94a9e56b
3
+ size 1383
checkpoint-392/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d49c6dee0f462b8a36d5288eeea109e6138974eca0f28ee56a2cfb29d45d3f0
3
+ size 1465
checkpoint-392/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-392/tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "TokenizersBackend",
13
+ "unk_token": "[UNK]"
14
+ }
checkpoint-392/trainer_state.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 392,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1024,
14
+ "grad_norm": 0.6643874645233154,
15
+ "learning_rate": 3.8000000000000005e-06,
16
+ "loss": 6.914890289306641,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.2048,
21
+ "grad_norm": 0.6963622570037842,
22
+ "learning_rate": 7.800000000000002e-06,
23
+ "loss": 6.9171875,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.3072,
28
+ "grad_norm": 0.6798524260520935,
29
+ "learning_rate": 9.736842105263159e-06,
30
+ "loss": 6.913761901855469,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.4096,
35
+ "grad_norm": 0.5872651934623718,
36
+ "learning_rate": 9.152046783625732e-06,
37
+ "loss": 6.889324188232422,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.512,
42
+ "grad_norm": 0.6345335245132446,
43
+ "learning_rate": 8.567251461988305e-06,
44
+ "loss": 6.8931327819824215,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.6144,
49
+ "grad_norm": 0.672644853591919,
50
+ "learning_rate": 7.982456140350877e-06,
51
+ "loss": 6.873789978027344,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.7168,
56
+ "grad_norm": 0.6409351229667664,
57
+ "learning_rate": 7.397660818713451e-06,
58
+ "loss": 6.862256622314453,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.8192,
63
+ "grad_norm": 0.7224740982055664,
64
+ "learning_rate": 6.812865497076025e-06,
65
+ "loss": 6.871943664550781,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.9216,
70
+ "grad_norm": 0.8125230669975281,
71
+ "learning_rate": 6.2280701754385975e-06,
72
+ "loss": 6.865367889404297,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 1.02048,
77
+ "grad_norm": 0.7702969908714294,
78
+ "learning_rate": 5.64327485380117e-06,
79
+ "loss": 6.855899810791016,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 1.12288,
84
+ "grad_norm": 0.591278076171875,
85
+ "learning_rate": 5.058479532163744e-06,
86
+ "loss": 6.86078109741211,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 1.22528,
91
+ "grad_norm": 0.5725053548812866,
92
+ "learning_rate": 4.473684210526316e-06,
93
+ "loss": 6.845599365234375,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 1.32768,
98
+ "grad_norm": 0.5741755962371826,
99
+ "learning_rate": 3.88888888888889e-06,
100
+ "loss": 6.850102233886719,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 1.43008,
105
+ "grad_norm": 0.5692065358161926,
106
+ "learning_rate": 3.3040935672514624e-06,
107
+ "loss": 6.841368865966797,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 1.53248,
112
+ "grad_norm": 0.7679271697998047,
113
+ "learning_rate": 2.7192982456140356e-06,
114
+ "loss": 6.853921508789062,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 1.6348799999999999,
119
+ "grad_norm": 0.5517163872718811,
120
+ "learning_rate": 2.1345029239766084e-06,
121
+ "loss": 6.8445579528808596,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 1.7372800000000002,
126
+ "grad_norm": 0.5690770745277405,
127
+ "learning_rate": 1.5497076023391812e-06,
128
+ "loss": 6.840210723876953,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 1.83968,
133
+ "grad_norm": 0.5253134965896606,
134
+ "learning_rate": 9.649122807017545e-07,
135
+ "loss": 6.8394020080566404,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 1.94208,
140
+ "grad_norm": 0.5329280495643616,
141
+ "learning_rate": 3.801169590643275e-07,
142
+ "loss": 6.830560302734375,
143
+ "step": 380
144
+ }
145
+ ],
146
+ "logging_steps": 20,
147
+ "max_steps": 392,
148
+ "num_input_tokens_seen": 0,
149
+ "num_train_epochs": 2,
150
+ "save_steps": 500,
151
+ "stateful_callbacks": {
152
+ "TrainerControl": {
153
+ "args": {
154
+ "should_epoch_stop": false,
155
+ "should_evaluate": false,
156
+ "should_log": false,
157
+ "should_save": true,
158
+ "should_training_stop": true
159
+ },
160
+ "attributes": {}
161
+ }
162
+ },
163
+ "total_flos": 174622256922624.0,
164
+ "train_batch_size": 2,
165
+ "trial_name": null,
166
+ "trial_params": null
167
+ }
checkpoint-392/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2a8f045f176447f577db324b81169038d35d913229d2b4e8663ab8c549983c
3
+ size 5201
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": null,
10
+ "head_dim": 32,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 128,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 384,
15
+ "max_position_embeddings": 256,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 4,
19
+ "num_hidden_layers": 4,
20
+ "num_key_value_heads": 4,
21
+ "pad_token_id": null,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_parameters": {
25
+ "rope_theta": 10000,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": true,
29
+ "transformers_version": "5.0.0",
30
+ "use_cache": false,
31
+ "vocab_size": 119547
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.0.0",
6
+ "use_cache": true
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488ae2bf3724b663a30aacd2afdb1df70b8daf5b241eef22992520e8902f29f7
3
+ size 64624680
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "TokenizersBackend",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2a8f045f176447f577db324b81169038d35d913229d2b4e8663ab8c549983c
3
+ size 5201