Aivesa commited on
Commit
ebfce83
·
verified ·
1 Parent(s): 1e7a8a1

Training in progress, step 3

Browse files
README.md ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: unsloth/Qwen2.5-0.5B
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ datasets:
9
+ - Aivesa/dataset_e393b615-2f4d-4521-8903-a1ed65df68c0
10
+ model-index:
11
+ - name: 8d691798-b51f-4c3e-8647-9f219f734984
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ [<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)
19
+ <details><summary>See axolotl config</summary>
20
+
21
+ axolotl version: `0.6.0`
22
+ ```yaml
23
+ adapter: lora
24
+ base_model: unsloth/Qwen2.5-0.5B
25
+ bf16: auto
26
+ chat_template: llama3
27
+ dataset_prepared_path: /workspace/axolotl/data/prepared
28
+ datasets:
29
+ - ds_type: json
30
+ format: custom
31
+ path: Aivesa/dataset_e393b615-2f4d-4521-8903-a1ed65df68c0
32
+ type:
33
+ field_instruction: context
34
+ field_output: question
35
+ system_format: '{system}'
36
+ system_prompt: ''
37
+ debug: null
38
+ deepspeed: null
39
+ early_stopping_patience: null
40
+ eval_max_new_tokens: 128
41
+ eval_table_size: null
42
+ evals_per_epoch: 4
43
+ flash_attention: false
44
+ fp16: null
45
+ fsdp: null
46
+ fsdp_config: null
47
+ gradient_accumulation_steps: 4
48
+ gradient_checkpointing: false
49
+ group_by_length: false
50
+ hub_model_id: Aivesa/8d691798-b51f-4c3e-8647-9f219f734984
51
+ hub_private_repo: true
52
+ hub_repo: null
53
+ hub_strategy: checkpoint
54
+ hub_token: null
55
+ learning_rate: 0.0002
56
+ load_in_4bit: false
57
+ load_in_8bit: false
58
+ local_rank: null
59
+ logging_steps: 1
60
+ lora_alpha: 16
61
+ lora_dropout: 0.05
62
+ lora_fan_in_fan_out: null
63
+ lora_model_dir: null
64
+ lora_r: 8
65
+ lora_target_linear: true
66
+ lr_scheduler: cosine
67
+ max_steps: 10
68
+ micro_batch_size: 2
69
+ model_type: AutoModelForCausalLM
70
+ num_epochs: 1
71
+ optimizer: adamw_bnb_8bit
72
+ output_dir: /workspace/axolotl/outputs
73
+ pad_to_sequence_len: true
74
+ push_to_hub: true
75
+ resume_from_checkpoint: null
76
+ s2_attention: null
77
+ sample_packing: false
78
+ save_safetensors: true
79
+ saves_per_epoch: 4
80
+ sequence_len: 512
81
+ strict: false
82
+ tf32: false
83
+ tokenizer_type: AutoTokenizer
84
+ train_on_inputs: false
85
+ trust_remote_code: true
86
+ use_accelerate: true
87
+ val_set_size: 0.05
88
+ wandb_entity: null
89
+ wandb_mode: online
90
+ wandb_name: e393b615-2f4d-4521-8903-a1ed65df68c0
91
+ wandb_project: Gradients-On-Demand
92
+ wandb_run: your_name
93
+ wandb_runid: e393b615-2f4d-4521-8903-a1ed65df68c0
94
+ warmup_steps: 10
95
+ weight_decay: 0.0
96
+ xformers_attention: null
97
+
98
+ ```
99
+
100
+ </details><br>
101
+
102
+ # 8d691798-b51f-4c3e-8647-9f219f734984
103
+
104
+ This model is a fine-tuned version of [unsloth/Qwen2.5-0.5B](https://huggingface.co/unsloth/Qwen2.5-0.5B) on the Aivesa/dataset_e393b615-2f4d-4521-8903-a1ed65df68c0 dataset.
105
+ It achieves the following results on the evaluation set:
106
+ - Loss: 2.5295
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: 0.0002
126
+ - train_batch_size: 2
127
+ - eval_batch_size: 2
128
+ - seed: 42
129
+ - gradient_accumulation_steps: 4
130
+ - total_train_batch_size: 8
131
+ - optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
132
+ - lr_scheduler_type: cosine
133
+ - lr_scheduler_warmup_steps: 10
134
+ - training_steps: 10
135
+
136
+ ### Training results
137
+
138
+ | Training Loss | Epoch | Step | Validation Loss |
139
+ |:-------------:|:------:|:----:|:---------------:|
140
+ | 2.7718 | 0.0131 | 3 | 3.0769 |
141
+ | 2.9479 | 0.0262 | 6 | 2.8964 |
142
+ | 2.6364 | 0.0393 | 9 | 2.5295 |
143
+
144
+
145
+ ### Framework versions
146
+
147
+ - PEFT 0.14.0
148
+ - Transformers 4.47.1
149
+ - Pytorch 2.5.0a0+e000cf0ad9.nv24.10
150
+ - Datasets 3.1.0
151
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "katuni4ka/tiny-random-olmo-hf",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": null,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "v_proj",
27
+ "down_proj",
28
+ "up_proj",
29
+ "o_proj",
30
+ "k_proj",
31
+ "gate_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7ca7aefc1739a96ebb92a997f270fbc629a26b0b61dc4a9281a1c640301787
3
+ size 81576
added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|PAD_TOKEN|>": 151665,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "katuni4ka/tiny-random-olmo-hf",
4
+ "architectures": [
5
+ "OlmoForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "clip_qkv": null,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 64,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 172,
15
+ "max_position_embeddings": 2048,
16
+ "model_type": "olmo",
17
+ "num_attention_heads": 2,
18
+ "num_hidden_layers": 2,
19
+ "num_key_value_heads": 2,
20
+ "pad_token_id": 1,
21
+ "pretraining_tp": 1,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.47.1",
27
+ "use_cache": false,
28
+ "vocab_size": 50304
29
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
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 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "|||IP_ADDRESS|||",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": false
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "|||EMAIL_ADDRESS|||",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "50278": {
215
+ "content": "|||PHONE_NUMBER|||",
216
+ "lstrip": false,
217
+ "normalized": true,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "50279": {
223
+ "content": "<|endoftext|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "50280": {
231
+ "content": "[PAD]",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ }
238
+ },
239
+ "bos_token": null,
240
+ "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 %}",
241
+ "clean_up_tokenization_spaces": true,
242
+ "eos_token": "<|endoftext|>",
243
+ "extra_special_tokens": {},
244
+ "model_max_length": 1000000000000000019884624838656,
245
+ "pad_token": "[PAD]",
246
+ "tokenizer_class": "GPTNeoXTokenizer",
247
+ "unk_token": null
248
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b5c52ba222bbd5fc191c6251729c68c46911b6c388fc9b39d7497e08dd9fc6
3
+ size 6904
vocab.json ADDED
The diff for this file is too large to render. See raw diff