Training in progress, epoch 1
Browse files- config.json +32 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +10 -0
- tokenizer.json +0 -0
- tokenizer_config.json +241 -0
- training.log +188 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"OlmoeForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"clip_qkv": null,
|
8 |
+
"eos_token_id": 50279,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 2048,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 1024,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_type": "olmoe",
|
15 |
+
"norm_topk_prob": false,
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_experts": 64,
|
18 |
+
"num_experts_per_tok": 8,
|
19 |
+
"num_hidden_layers": 16,
|
20 |
+
"num_key_value_heads": 16,
|
21 |
+
"output_router_logits": false,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 10000.0,
|
26 |
+
"router_aux_loss_coef": 0.01,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.51.0",
|
30 |
+
"use_cache": false,
|
31 |
+
"vocab_size": 50304
|
32 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:055a4e8a768089e54832955dbc6b8d773563c6f2636236a4fa9bea1412028e0e
|
3 |
+
size 4997744872
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2844f3243f9625b2fc4c5ae7b66a8ee5c3899a988f4d6b1e37984806336c6b1
|
3 |
+
size 4997235176
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30a2c2804f6033d028897a56e69440f84daf679377b4c71dae41617086d569e1
|
3 |
+
size 3843741912
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": "<|endoftext|>"
|
10 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
231 |
+
"bos_token": null,
|
232 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
233 |
+
"clean_up_tokenization_spaces": true,
|
234 |
+
"eos_token": "<|endoftext|>",
|
235 |
+
"extra_special_tokens": {},
|
236 |
+
"fast_tokenizer": true,
|
237 |
+
"model_max_length": 1000000000000000019884624838656,
|
238 |
+
"pad_token": "<|endoftext|>",
|
239 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
240 |
+
"unk_token": null
|
241 |
+
}
|
training.log
ADDED
@@ -0,0 +1,188 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2025-09-23 13:08:07 - INFO - __main__ - Model parameters AuxFreeModelConfig(model_name_or_path='allenai/OLMoE-1B-7B-0125', model_revision='main', torch_dtype='bfloat16', trust_remote_code=True, attn_implementation='flash_attention_2', use_peft=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, lora_target_modules=None, lora_modules_to_save=None, lora_task_type='CAUSAL_LM', use_rslora=False, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bias_update_speed=0.0001, remove_aux_loss=True, add_aux_free_loss=True, sinkhorn_routing=False, enable_forced_experts=False, num_forced_experts=2, bias_file_path='')
|
2 |
+
2025-09-23 13:08:07 - INFO - __main__ - Script parameters ScriptArguments(dataset_name='fw407/Commonsense-15K', dataset_config=None, dataset_train_split='train', dataset_test_split='test', gradient_checkpointing_use_reentrant=False, ignore_bias_buffers=False)
|
3 |
+
2025-09-23 13:08:07 - INFO - __main__ - Training parameters SFTConfig(
|
4 |
+
_n_gpu=1,
|
5 |
+
accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
|
6 |
+
adafactor=False,
|
7 |
+
adam_beta1=0.9,
|
8 |
+
adam_beta2=0.999,
|
9 |
+
adam_epsilon=1e-08,
|
10 |
+
auto_find_batch_size=False,
|
11 |
+
average_tokens_across_devices=False,
|
12 |
+
batch_eval_metrics=False,
|
13 |
+
benchmarks=[],
|
14 |
+
bf16=True,
|
15 |
+
bf16_full_eval=False,
|
16 |
+
callbacks=[],
|
17 |
+
chars_per_token=<CHARS_PER_TOKEN>,
|
18 |
+
chat_template=None,
|
19 |
+
data_seed=None,
|
20 |
+
dataloader_drop_last=False,
|
21 |
+
dataloader_num_workers=0,
|
22 |
+
dataloader_persistent_workers=False,
|
23 |
+
dataloader_pin_memory=True,
|
24 |
+
dataloader_prefetch_factor=None,
|
25 |
+
dataset_batch_size=None,
|
26 |
+
dataset_kwargs=None,
|
27 |
+
dataset_num_proc=None,
|
28 |
+
dataset_text_field=text,
|
29 |
+
ddp_backend=None,
|
30 |
+
ddp_broadcast_buffers=None,
|
31 |
+
ddp_bucket_cap_mb=None,
|
32 |
+
ddp_find_unused_parameters=None,
|
33 |
+
ddp_timeout=1800000000,
|
34 |
+
debug=[],
|
35 |
+
deepspeed=None,
|
36 |
+
disable_tqdm=False,
|
37 |
+
do_eval=True,
|
38 |
+
do_predict=False,
|
39 |
+
do_train=False,
|
40 |
+
eval_accumulation_steps=None,
|
41 |
+
eval_delay=0,
|
42 |
+
eval_do_concat_batches=True,
|
43 |
+
eval_on_start=False,
|
44 |
+
eval_packing=None,
|
45 |
+
eval_steps=None,
|
46 |
+
eval_strategy=IntervalStrategy.NO,
|
47 |
+
eval_use_gather_object=False,
|
48 |
+
fp16=False,
|
49 |
+
fp16_backend=auto,
|
50 |
+
fp16_full_eval=False,
|
51 |
+
fp16_opt_level=O1,
|
52 |
+
fsdp=[],
|
53 |
+
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
|
54 |
+
fsdp_min_num_params=0,
|
55 |
+
fsdp_transformer_layer_cls_to_wrap=None,
|
56 |
+
full_determinism=False,
|
57 |
+
gradient_accumulation_steps=1,
|
58 |
+
gradient_checkpointing=True,
|
59 |
+
gradient_checkpointing_kwargs={'use_reentrant': False},
|
60 |
+
greater_is_better=None,
|
61 |
+
group_by_length=False,
|
62 |
+
half_precision_backend=auto,
|
63 |
+
hub_always_push=False,
|
64 |
+
hub_model_id=OLMoE-1B-7B-0125-aux-free-sft-commonsense15k,
|
65 |
+
hub_model_revision=main,
|
66 |
+
hub_private_repo=None,
|
67 |
+
hub_strategy=HubStrategy.EVERY_SAVE,
|
68 |
+
hub_token=<HUB_TOKEN>,
|
69 |
+
ignore_data_skip=False,
|
70 |
+
include_for_metrics=[],
|
71 |
+
include_inputs_for_metrics=False,
|
72 |
+
include_num_input_tokens_seen=False,
|
73 |
+
include_tokens_per_second=False,
|
74 |
+
jit_mode_eval=False,
|
75 |
+
label_names=None,
|
76 |
+
label_smoothing_factor=0.0,
|
77 |
+
learning_rate=1e-05,
|
78 |
+
length_column_name=length,
|
79 |
+
load_best_model_at_end=False,
|
80 |
+
local_rank=0,
|
81 |
+
log_level=info,
|
82 |
+
log_level_replica=warning,
|
83 |
+
log_on_each_node=True,
|
84 |
+
logging_dir=/tmp/data/OLMoE-1B-7B-0125/aux_free_sft/commonsense15k/runs/Sep23_13-08-06_orchard-flame-5,
|
85 |
+
logging_first_step=False,
|
86 |
+
logging_nan_inf_filter=True,
|
87 |
+
logging_steps=1,
|
88 |
+
logging_strategy=IntervalStrategy.STEPS,
|
89 |
+
lr_scheduler_kwargs={'min_lr_rate': 0.1},
|
90 |
+
lr_scheduler_type=SchedulerType.COSINE_WITH_MIN_LR,
|
91 |
+
max_grad_norm=1.0,
|
92 |
+
max_length=2048,
|
93 |
+
max_seq_length=None,
|
94 |
+
max_steps=-1,
|
95 |
+
metric_for_best_model=None,
|
96 |
+
model_init_kwargs=None,
|
97 |
+
mp_parameters=,
|
98 |
+
neftune_noise_alpha=None,
|
99 |
+
no_cuda=False,
|
100 |
+
num_of_sequences=None,
|
101 |
+
num_train_epochs=1,
|
102 |
+
optim=OptimizerNames.ADAMW_TORCH,
|
103 |
+
optim_args=None,
|
104 |
+
optim_target_modules=None,
|
105 |
+
output_dir=/tmp/data/OLMoE-1B-7B-0125/aux_free_sft/commonsense15k,
|
106 |
+
overwrite_hub_revision=False,
|
107 |
+
overwrite_output_dir=True,
|
108 |
+
packing=False,
|
109 |
+
past_index=-1,
|
110 |
+
per_device_eval_batch_size=16,
|
111 |
+
per_device_train_batch_size=16,
|
112 |
+
prediction_loss_only=False,
|
113 |
+
push_to_hub=True,
|
114 |
+
push_to_hub_model_id=None,
|
115 |
+
push_to_hub_organization=None,
|
116 |
+
push_to_hub_revision=False,
|
117 |
+
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
|
118 |
+
ray_scope=last,
|
119 |
+
remove_unused_columns=True,
|
120 |
+
report_to=['wandb'],
|
121 |
+
restore_callback_states_from_checkpoint=False,
|
122 |
+
resume_from_checkpoint=None,
|
123 |
+
run_name=/tmp/data/OLMoE-1B-7B-0125/aux_free_sft/commonsense15k,
|
124 |
+
save_on_each_node=False,
|
125 |
+
save_only_model=False,
|
126 |
+
save_safetensors=True,
|
127 |
+
save_steps=500,
|
128 |
+
save_strategy=SaveStrategy.EPOCH,
|
129 |
+
save_total_limit=3,
|
130 |
+
seed=1234,
|
131 |
+
skip_memory_metrics=True,
|
132 |
+
system_prompt=None,
|
133 |
+
tf32=None,
|
134 |
+
torch_compile=False,
|
135 |
+
torch_compile_backend=None,
|
136 |
+
torch_compile_mode=None,
|
137 |
+
torch_empty_cache_steps=None,
|
138 |
+
torchdynamo=None,
|
139 |
+
tp_size=0,
|
140 |
+
tpu_metrics_debug=False,
|
141 |
+
tpu_num_cores=None,
|
142 |
+
use_cpu=False,
|
143 |
+
use_ipex=False,
|
144 |
+
use_legacy_prediction_loop=False,
|
145 |
+
use_liger=False,
|
146 |
+
use_liger_kernel=False,
|
147 |
+
use_mps_device=False,
|
148 |
+
wandb_entity=None,
|
149 |
+
wandb_project=None,
|
150 |
+
warmup_ratio=0.1,
|
151 |
+
warmup_steps=0,
|
152 |
+
weight_decay=0.0,
|
153 |
+
)
|
154 |
+
2025-09-23 13:08:08 - INFO - __main__ - *** Initializing model kwargs ***
|
155 |
+
2025-09-23 13:08:48 - INFO - __main__ - *** Train ***
|
156 |
+
2025-09-23 13:08:48 - INFO - __main__ - OlmoeForCausalLM(
|
157 |
+
(model): OlmoeModel(
|
158 |
+
(embed_tokens): Embedding(50304, 2048, padding_idx=1)
|
159 |
+
(layers): ModuleList(
|
160 |
+
(0-15): 16 x OlmoeDecoderLayer(
|
161 |
+
(self_attn): OlmoeFlashAttention2(
|
162 |
+
(q_proj): Linear(in_features=2048, out_features=2048, bias=False)
|
163 |
+
(k_proj): Linear(in_features=2048, out_features=2048, bias=False)
|
164 |
+
(v_proj): Linear(in_features=2048, out_features=2048, bias=False)
|
165 |
+
(o_proj): Linear(in_features=2048, out_features=2048, bias=False)
|
166 |
+
(q_norm): OlmoeRMSNorm((0,), eps=1e-05)
|
167 |
+
(k_norm): OlmoeRMSNorm((0,), eps=1e-05)
|
168 |
+
)
|
169 |
+
(mlp): OlmoeSparseMoeBlock(
|
170 |
+
(gate): Linear(in_features=2048, out_features=64, bias=False)
|
171 |
+
(experts): ModuleList(
|
172 |
+
(0-63): 64 x OlmoeMLP(
|
173 |
+
(gate_proj): Linear(in_features=2048, out_features=1024, bias=False)
|
174 |
+
(up_proj): Linear(in_features=2048, out_features=1024, bias=False)
|
175 |
+
(down_proj): Linear(in_features=1024, out_features=2048, bias=False)
|
176 |
+
(act_fn): SiLU()
|
177 |
+
)
|
178 |
+
)
|
179 |
+
)
|
180 |
+
(input_layernorm): OlmoeRMSNorm((0,), eps=1e-05)
|
181 |
+
(post_attention_layernorm): OlmoeRMSNorm((0,), eps=1e-05)
|
182 |
+
)
|
183 |
+
)
|
184 |
+
(norm): OlmoeRMSNorm((0,), eps=1e-05)
|
185 |
+
(rotary_emb): OlmoeRotaryEmbedding()
|
186 |
+
)
|
187 |
+
(lm_head): Linear(in_features=2048, out_features=50304, bias=False)
|
188 |
+
)
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86184dc5c6a2dc7bcccb57412ab59744f46e2560393a006b5142b99bfab4a260
|
3 |
+
size 7544
|