pdelobelle
commited on
Commit
•
7f86623
1
Parent(s):
8674e21
Training in progress, step 200
Browse files- config.json +33 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +322 -0
- trainer_state.json +65 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pdelobelle/gemma-2-2b-de",
|
3 |
+
"architectures": [
|
4 |
+
"Gemma2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attn_logit_softcapping": 50.0,
|
9 |
+
"bos_token_id": 2,
|
10 |
+
"cache_implementation": "hybrid",
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"final_logit_softcapping": 30.0,
|
13 |
+
"head_dim": 256,
|
14 |
+
"hidden_act": "gelu_pytorch_tanh",
|
15 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
16 |
+
"hidden_size": 2304,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 9216,
|
19 |
+
"max_position_embeddings": 8192,
|
20 |
+
"model_type": "gemma2",
|
21 |
+
"num_attention_heads": 8,
|
22 |
+
"num_hidden_layers": 26,
|
23 |
+
"num_key_value_heads": 4,
|
24 |
+
"pad_token_id": 3,
|
25 |
+
"query_pre_attn_scalar": 256,
|
26 |
+
"rms_norm_eps": 1e-06,
|
27 |
+
"rope_theta": 10000.0,
|
28 |
+
"sliding_window": 4096,
|
29 |
+
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.44.1",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 20000
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcbc40d14021aebac5404b2954a6b6a4ff0beb27f330b50a87f13b48abc33844
|
3 |
+
size 4141229384
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16e8773affbd03448ffb79173feed1884514012160d3074641ee402dcad4f481
|
3 |
+
size 579378
|
tokenizer_config.json
ADDED
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
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 |
+
"3": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"4": {
|
39 |
+
"content": "▁▁",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"5": {
|
47 |
+
"content": "▁▁▁",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"6": {
|
55 |
+
"content": "▁▁▁▁",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"7": {
|
63 |
+
"content": "▁▁▁▁▁▁▁▁",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"8": {
|
71 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"9": {
|
79 |
+
"content": "--",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"10": {
|
87 |
+
"content": "----",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"11": {
|
95 |
+
"content": "-----",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"12": {
|
103 |
+
"content": "--------",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"13": {
|
111 |
+
"content": "----------------",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"14": {
|
119 |
+
"content": "++",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"15": {
|
127 |
+
"content": "/**",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"16": {
|
135 |
+
"content": "***",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"17": {
|
143 |
+
"content": "****",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"18": {
|
151 |
+
"content": "******",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"19": {
|
159 |
+
"content": "********",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"20": {
|
167 |
+
"content": "**/",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"21": {
|
175 |
+
"content": "##",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"22": {
|
183 |
+
"content": "###",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"23": {
|
191 |
+
"content": "<|im_start|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"24": {
|
199 |
+
"content": "<|im_end|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"25": {
|
207 |
+
"content": "<|system|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": false
|
213 |
+
},
|
214 |
+
"26": {
|
215 |
+
"content": "<|user|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"27": {
|
223 |
+
"content": "<|assistant|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": false
|
229 |
+
},
|
230 |
+
"28": {
|
231 |
+
"content": "▁—",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": false
|
237 |
+
},
|
238 |
+
"29": {
|
239 |
+
"content": "▁“",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": false
|
245 |
+
},
|
246 |
+
"30": {
|
247 |
+
"content": "“",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": false
|
253 |
+
},
|
254 |
+
"31": {
|
255 |
+
"content": "”",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": false
|
261 |
+
},
|
262 |
+
"32": {
|
263 |
+
"content": "’",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": false
|
269 |
+
},
|
270 |
+
"33": {
|
271 |
+
"content": "—",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": false
|
277 |
+
},
|
278 |
+
"34": {
|
279 |
+
"content": "{",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": false
|
285 |
+
},
|
286 |
+
"35": {
|
287 |
+
"content": "}\"",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": false
|
293 |
+
},
|
294 |
+
"36": {
|
295 |
+
"content": "{\"",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": false
|
301 |
+
},
|
302 |
+
"37": {
|
303 |
+
"content": "}",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": false
|
309 |
+
}
|
310 |
+
},
|
311 |
+
"bos_token": "<s>",
|
312 |
+
"clean_up_tokenization_spaces": false,
|
313 |
+
"eos_token": "</s>",
|
314 |
+
"legacy": true,
|
315 |
+
"model_max_length": 1000000000000000019884624838656,
|
316 |
+
"pad_token": "</s>",
|
317 |
+
"sp_model_kwargs": {},
|
318 |
+
"spaces_between_special_tokens": false,
|
319 |
+
"tokenizer_class": "LlamaTokenizer",
|
320 |
+
"unk_token": "<unk>",
|
321 |
+
"use_default_system_prompt": false
|
322 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00041946308724832214,
|
5 |
+
"eval_steps": 200,
|
6 |
+
"global_step": 4,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.00010486577181208053,
|
13 |
+
"grad_norm": 96.5,
|
14 |
+
"learning_rate": 1.680672268907563e-07,
|
15 |
+
"loss": 7.9808,
|
16 |
+
"num_input_tokens_seen": 1048576,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.00020973154362416107,
|
21 |
+
"grad_norm": 99.0,
|
22 |
+
"learning_rate": 3.361344537815126e-07,
|
23 |
+
"loss": 8.0248,
|
24 |
+
"num_input_tokens_seen": 2097152,
|
25 |
+
"step": 2
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.0003145973154362416,
|
29 |
+
"grad_norm": 98.5,
|
30 |
+
"learning_rate": 5.042016806722689e-07,
|
31 |
+
"loss": 7.9878,
|
32 |
+
"num_input_tokens_seen": 3145728,
|
33 |
+
"step": 3
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.00041946308724832214,
|
37 |
+
"grad_norm": 95.5,
|
38 |
+
"learning_rate": 6.722689075630252e-07,
|
39 |
+
"loss": 7.9434,
|
40 |
+
"num_input_tokens_seen": 4194304,
|
41 |
+
"step": 4
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"logging_steps": 1,
|
45 |
+
"max_steps": 9536,
|
46 |
+
"num_input_tokens_seen": 4816896,
|
47 |
+
"num_train_epochs": 9223372036854775807,
|
48 |
+
"save_steps": 200,
|
49 |
+
"stateful_callbacks": {
|
50 |
+
"TrainerControl": {
|
51 |
+
"args": {
|
52 |
+
"should_epoch_stop": false,
|
53 |
+
"should_evaluate": false,
|
54 |
+
"should_log": false,
|
55 |
+
"should_save": false,
|
56 |
+
"should_training_stop": false
|
57 |
+
},
|
58 |
+
"attributes": {}
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"total_flos": 5.094866300174336e+16,
|
62 |
+
"train_batch_size": 1,
|
63 |
+
"trial_name": null,
|
64 |
+
"trial_params": null
|
65 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17ddf3fb8fdb9baa07c29ebd5a499cb1523c190e3c7c6707752f236dce6f27d2
|
3 |
+
size 5304
|