nblinh63 commited on
Commit
92a0ce8
1 Parent(s): 4297b1e

End of training

Browse files
README.md ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: NousResearch/Hermes-2-Pro-Mistral-7B
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 100a0c0b-2d76-4902-8ff6-a4302c454c37
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.4.1`
20
+ ```yaml
21
+ adapter: lora
22
+ base_model: NousResearch/Hermes-2-Pro-Mistral-7B
23
+ bf16: auto
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - 8ebec48b3dec2f52_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/8ebec48b3dec2f52_train_data.json
32
+ type:
33
+ field_input: input
34
+ field_instruction: instruction
35
+ field_output: output
36
+ format: '{instruction} {input}'
37
+ no_input_format: '{instruction}'
38
+ system_format: '{system}'
39
+ system_prompt: ''
40
+ debug: null
41
+ deepspeed: null
42
+ early_stopping_patience: null
43
+ eval_max_new_tokens: 128
44
+ eval_table_size: null
45
+ evals_per_epoch: 1
46
+ flash_attention: true
47
+ fp16: null
48
+ fsdp: null
49
+ fsdp_config: null
50
+ gradient_accumulation_steps: 1
51
+ gradient_checkpointing: true
52
+ group_by_length: false
53
+ hub_model_id: nblinh63/100a0c0b-2d76-4902-8ff6-a4302c454c37
54
+ hub_repo: null
55
+ hub_strategy: end
56
+ hub_token: null
57
+ learning_rate: 0.0003
58
+ load_in_4bit: true
59
+ load_in_8bit: true
60
+ local_rank: null
61
+ logging_steps: 1
62
+ lora_alpha: 32
63
+ lora_dropout: 0.05
64
+ lora_fan_in_fan_out: null
65
+ lora_model_dir: null
66
+ lora_r: 16
67
+ lora_target_linear: true
68
+ lr_scheduler: cosine
69
+ max_steps: 10
70
+ micro_batch_size: 1
71
+ mlflow_experiment_name: /tmp/8ebec48b3dec2f52_train_data.json
72
+ model_type: AutoModelForCausalLM
73
+ num_epochs: 1
74
+ optimizer: adamw_bnb_8bit
75
+ output_dir: miner_id_24
76
+ pad_to_sequence_len: true
77
+ resume_from_checkpoint: null
78
+ s2_attention: null
79
+ sample_packing: false
80
+ saves_per_epoch: 1
81
+ sequence_len: 2048
82
+ strict: false
83
+ tf32: false
84
+ tokenizer_type: AutoTokenizer
85
+ train_on_inputs: false
86
+ trust_remote_code: true
87
+ val_set_size: 0.05
88
+ wandb_entity: null
89
+ wandb_mode: online
90
+ wandb_name: 100a0c0b-2d76-4902-8ff6-a4302c454c37
91
+ wandb_project: Gradients-On-Demand
92
+ wandb_run: your_name
93
+ wandb_runid: 100a0c0b-2d76-4902-8ff6-a4302c454c37
94
+ warmup_steps: 10
95
+ weight_decay: 0.0
96
+ xformers_attention: true
97
+
98
+ ```
99
+
100
+ </details><br>
101
+
102
+ # 100a0c0b-2d76-4902-8ff6-a4302c454c37
103
+
104
+ This model is a fine-tuned version of [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) on the None dataset.
105
+ It achieves the following results on the evaluation set:
106
+ - Loss: 1.3008
107
+
108
+ ## Model description
109
+
110
+ More information needed
111
+
112
+ ## Intended uses & limitations
113
+
114
+ More information needed
115
+
116
+ ## Training and evaluation data
117
+
118
+ More information needed
119
+
120
+ ## Training procedure
121
+
122
+ ### Training hyperparameters
123
+
124
+ The following hyperparameters were used during training:
125
+ - learning_rate: 0.0003
126
+ - train_batch_size: 1
127
+ - eval_batch_size: 1
128
+ - seed: 42
129
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
130
+ - lr_scheduler_type: cosine
131
+ - lr_scheduler_warmup_steps: 10
132
+ - training_steps: 10
133
+
134
+ ### Training results
135
+
136
+ | Training Loss | Epoch | Step | Validation Loss |
137
+ |:-------------:|:------:|:----:|:---------------:|
138
+ | 2.0655 | 0.0002 | 10 | 1.3008 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - PEFT 0.13.2
144
+ - Transformers 4.46.0
145
+ - Pytorch 2.5.0+cu124
146
+ - Datasets 3.0.1
147
+ - Tokenizers 0.20.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Hermes-2-Pro-Mistral-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "o_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0998454fb96b99db6c59c3ea8ca6fa91e10494a0df344bd9dccec125265e8dd8
3
+ size 167934026
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02eb4687853619a607eee9b2aa942f7f2302f60c6089ea10f12c4a0f3a7abf1
3
+ size 167832240
added_tokens.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad10>": 32010,
3
+ "<pad11>": 32011,
4
+ "<pad12>": 32012,
5
+ "<pad13>": 32013,
6
+ "<pad14>": 32014,
7
+ "<pad15>": 32015,
8
+ "<pad16>": 32016,
9
+ "<pad17>": 32017,
10
+ "<pad18>": 32018,
11
+ "<pad19>": 32019,
12
+ "<pad20>": 32020,
13
+ "<pad21>": 32021,
14
+ "<pad22>": 32022,
15
+ "<pad23>": 32023,
16
+ "<pad24>": 32024,
17
+ "<pad25>": 32025,
18
+ "<pad26>": 32026,
19
+ "<pad27>": 32027,
20
+ "<pad28>": 32028,
21
+ "<pad29>": 32029,
22
+ "<pad2>": 32002,
23
+ "<pad30>": 32030,
24
+ "<pad31>": 32031,
25
+ "<pad3>": 32003,
26
+ "<pad4>": 32004,
27
+ "<pad5>": 32005,
28
+ "<pad6>": 32006,
29
+ "<pad7>": 32007,
30
+ "<pad8>": 32008,
31
+ "<pad9>": 32009,
32
+ "<|im_end|>": 32000,
33
+ "<|im_start|>": 32001
34
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "NousResearch/Hermes-2-Pro-Mistral-7B",
4
+ "architectures": [
5
+ "MistralForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 32000,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 32768,
16
+ "model_type": "mistral",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "quantization_config": {
21
+ "_load_in_4bit": false,
22
+ "_load_in_8bit": true,
23
+ "bnb_4bit_compute_dtype": "float32",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "fp4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": false,
32
+ "load_in_8bit": true,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_theta": 10000.0,
37
+ "sliding_window": 4096,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.46.0",
41
+ "use_cache": false,
42
+ "vocab_size": 32032
43
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,301 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "32002": {
47
+ "content": "<pad2>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "32003": {
55
+ "content": "<pad3>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "32004": {
63
+ "content": "<pad4>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "32005": {
71
+ "content": "<pad5>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "32006": {
79
+ "content": "<pad6>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "32007": {
87
+ "content": "<pad7>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "32008": {
95
+ "content": "<pad8>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "32009": {
103
+ "content": "<pad9>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "32010": {
111
+ "content": "<pad10>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "32011": {
119
+ "content": "<pad11>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "32012": {
127
+ "content": "<pad12>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "32013": {
135
+ "content": "<pad13>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "32014": {
143
+ "content": "<pad14>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "32015": {
151
+ "content": "<pad15>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "32016": {
159
+ "content": "<pad16>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "32017": {
167
+ "content": "<pad17>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "32018": {
175
+ "content": "<pad18>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "32019": {
183
+ "content": "<pad19>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "32020": {
191
+ "content": "<pad20>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "32021": {
199
+ "content": "<pad21>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "32022": {
207
+ "content": "<pad22>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "32023": {
215
+ "content": "<pad23>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "32024": {
223
+ "content": "<pad24>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ },
230
+ "32025": {
231
+ "content": "<pad25>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false
237
+ },
238
+ "32026": {
239
+ "content": "<pad26>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": false
245
+ },
246
+ "32027": {
247
+ "content": "<pad27>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": false
253
+ },
254
+ "32028": {
255
+ "content": "<pad28>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": false
261
+ },
262
+ "32029": {
263
+ "content": "<pad29>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "32030": {
271
+ "content": "<pad30>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "32031": {
279
+ "content": "<pad31>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ }
286
+ },
287
+ "additional_special_tokens": [],
288
+ "bos_token": "<s>",
289
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
290
+ "clean_up_tokenization_spaces": true,
291
+ "eos_token": "<|im_end|>",
292
+ "legacy": true,
293
+ "model_max_length": 1000000000000000019884624838656,
294
+ "pad_token": "</s>",
295
+ "sp_model_kwargs": {},
296
+ "spaces_between_special_tokens": false,
297
+ "tokenizer_class": "LlamaTokenizer",
298
+ "unk_token": "<unk>",
299
+ "use_default_system_prompt": false,
300
+ "use_fast": true
301
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:676f89be7f97b5c1579b09cdbb486dd9d6b39e42a4c4f1ccc72afaf496dd711e
3
+ size 6776