second model upload
Browse files- README.md +3 -3
- adapter_config.json +279 -279
- adapter_model.safetensors +1 -1
- all_results.json +6 -6
- checkpoint-620/README.md +202 -0
- checkpoint-620/adapter_config.json +335 -0
- checkpoint-620/adapter_model.safetensors +3 -0
- checkpoint-620/added_tokens.json +16 -0
- checkpoint-620/chat_template.json +3 -0
- checkpoint-620/merges.txt +0 -0
- checkpoint-620/optimizer.pt +3 -0
- checkpoint-620/preprocessor_config.json +29 -0
- checkpoint-620/rng_state_0.pth +3 -0
- checkpoint-620/rng_state_1.pth +3 -0
- checkpoint-620/scaler.pt +3 -0
- checkpoint-620/scheduler.pt +3 -0
- checkpoint-620/special_tokens_map.json +31 -0
- checkpoint-620/tokenizer.json +3 -0
- checkpoint-620/tokenizer_config.json +148 -0
- checkpoint-620/trainer_state.json +467 -0
- checkpoint-620/training_args.bin +3 -0
- checkpoint-620/vocab.json +0 -0
- runs/Mar16_11-00-49_ca1aedd8ff14/events.out.tfevents.1742123117.ca1aedd8ff14.153.0 +3 -0
- train_results.json +6 -6
- trainer_log.jsonl +63 -47
- trainer_state.json +308 -196
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
license: other
|
4 |
-
base_model: saim1212/penguin2
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
- lora
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# qwen2vl_lora_16lr_7b
|
18 |
|
19 |
-
This model is a fine-tuned version of [saim1212/penguin2](https://huggingface.co/saim1212/penguin2) on the talk2car dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
|
|
47 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
48 |
- lr_scheduler_type: cosine
|
49 |
- lr_scheduler_warmup_ratio: 0.1
|
50 |
-
- num_epochs:
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
license: other
|
4 |
+
base_model: saim1212/penguin2-checkpoint1
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
- lora
|
|
|
16 |
|
17 |
# qwen2vl_lora_16lr_7b
|
18 |
|
19 |
+
This model is a fine-tuned version of [saim1212/penguin2-checkpoint1](https://huggingface.co/saim1212/penguin2-checkpoint1) on the talk2car dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
47 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
48 |
- lr_scheduler_type: cosine
|
49 |
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 10.0
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "saim1212/penguin2",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -20,314 +20,314 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"model.layers.
|
24 |
-
"model.layers.
|
25 |
-
"model.layers.5.
|
26 |
-
"model.layers.
|
27 |
-
"model.layers.2.self_attn.k_proj",
|
28 |
-
"model.layers.7.self_attn_text.k_proj",
|
29 |
-
"model.layers.6.self_attn.k_proj",
|
30 |
-
"model.layers.20.self_attn.q_proj",
|
31 |
-
"model.layers.25.self_attn.q_proj",
|
32 |
-
"model.layers.1.self_attn.o_proj",
|
33 |
"model.layers.22.self_attn.k_proj",
|
34 |
-
"model.layers.
|
35 |
-
"model.layers.
|
36 |
-
"model.layers.
|
37 |
-
"model.layers.
|
38 |
-
"model.layers.2.self_attn.o_proj",
|
39 |
-
"model.layers.3.self_attn_text.k_proj",
|
40 |
-
"model.layers.0.self_attn_text.v_proj",
|
41 |
"model.layers.16.self_attn.q_proj",
|
42 |
-
"model.layers.
|
43 |
-
"model.layers.
|
44 |
-
"model.layers.12.self_attn.k_proj",
|
45 |
-
"model.layers.17.self_attn_text.v_proj",
|
46 |
-
"model.layers.25.self_attn.k_proj",
|
47 |
-
"model.layers.0.self_attn.k_proj",
|
48 |
-
"model.layers.23.self_attn.v_proj",
|
49 |
-
"model.layers.20.self_attn.k_proj",
|
50 |
-
"model.layers.13.self_attn_text.v_proj",
|
51 |
"model.layers.9.self_attn.o_proj",
|
52 |
-
"model.layers.
|
53 |
-
"model.layers.
|
54 |
-
"model.layers.22.self_attn.q_proj",
|
55 |
-
"model.layers.19.mlp.gate_proj",
|
56 |
-
"model.layers.4.mlp.gate_proj",
|
57 |
-
"model.layers.18.self_attn.k_proj",
|
58 |
-
"model.layers.23.self_attn_text.q_proj",
|
59 |
-
"model.layers.23.self_attn.k_proj",
|
60 |
-
"model.layers.24.self_attn.k_proj",
|
61 |
"model.layers.13.self_attn_text.q_proj",
|
62 |
-
"model.layers.2.self_attn.q_proj",
|
63 |
-
"model.layers.3.self_attn_text.q_proj",
|
64 |
-
"model.layers.0.self_attn_text.k_proj",
|
65 |
-
"model.layers.22.mlp.gate_proj",
|
66 |
-
"model.layers.5.mlp.down_proj",
|
67 |
-
"model.layers.11.self_attn_text.q_proj",
|
68 |
-
"model.layers.2.self_attn_text.k_proj",
|
69 |
-
"model.layers.14.self_attn_text.q_proj",
|
70 |
-
"model.layers.9.mlp.up_proj",
|
71 |
-
"model.layers.19.self_attn_text.o_proj",
|
72 |
-
"model.layers.2.self_attn_text.o_proj",
|
73 |
-
"model.layers.3.self_attn_text.v_proj",
|
74 |
-
"model.layers.27.self_attn.k_proj",
|
75 |
-
"model.layers.27.self_attn_text.v_proj",
|
76 |
-
"model.layers.7.self_attn_text.q_proj",
|
77 |
-
"model.layers.1.mlp.up_proj",
|
78 |
-
"model.layers.11.self_attn.q_proj",
|
79 |
-
"model.layers.8.self_attn_text.v_proj",
|
80 |
-
"model.layers.19.self_attn.k_proj",
|
81 |
-
"model.layers.24.self_attn.q_proj",
|
82 |
-
"model.layers.12.self_attn_text.q_proj",
|
83 |
-
"model.layers.27.mlp.down_proj",
|
84 |
-
"model.layers.12.self_attn_text.k_proj",
|
85 |
-
"model.layers.11.self_attn.v_proj",
|
86 |
-
"model.layers.13.mlp.up_proj",
|
87 |
-
"model.layers.8.self_attn_text.q_proj",
|
88 |
-
"model.layers.22.self_attn.v_proj",
|
89 |
-
"model.layers.14.self_attn.o_proj",
|
90 |
-
"model.layers.23.self_attn.q_proj",
|
91 |
-
"model.layers.23.self_attn.o_proj",
|
92 |
-
"model.layers.14.mlp.down_proj",
|
93 |
-
"model.layers.16.mlp.down_proj",
|
94 |
-
"model.layers.10.self_attn.q_proj",
|
95 |
-
"model.layers.27.mlp.up_proj",
|
96 |
-
"model.layers.17.mlp.up_proj",
|
97 |
-
"model.layers.16.self_attn_text.v_proj",
|
98 |
-
"model.layers.4.mlp.down_proj",
|
99 |
-
"model.layers.22.mlp.down_proj",
|
100 |
-
"model.layers.0.self_attn.q_proj",
|
101 |
-
"model.layers.27.mlp.gate_proj",
|
102 |
-
"model.layers.9.mlp.gate_proj",
|
103 |
-
"model.layers.22.mlp.up_proj",
|
104 |
-
"model.layers.2.self_attn.v_proj",
|
105 |
-
"model.layers.14.self_attn.q_proj",
|
106 |
-
"model.layers.7.mlp.gate_proj",
|
107 |
-
"model.layers.21.self_attn.k_proj",
|
108 |
-
"model.layers.13.self_attn.q_proj",
|
109 |
-
"model.layers.11.mlp.down_proj",
|
110 |
-
"model.layers.6.self_attn_text.k_proj",
|
111 |
-
"model.layers.16.self_attn_text.o_proj",
|
112 |
-
"model.layers.4.self_attn_text.k_proj",
|
113 |
-
"model.layers.24.self_attn_text.v_proj",
|
114 |
-
"model.layers.16.mlp.up_proj",
|
115 |
-
"model.layers.13.self_attn.k_proj",
|
116 |
-
"model.layers.5.self_attn_text.v_proj",
|
117 |
-
"model.layers.22.self_attn_text.k_proj",
|
118 |
-
"model.layers.15.self_attn_text.q_proj",
|
119 |
-
"model.layers.8.self_attn.q_proj",
|
120 |
-
"model.layers.25.self_attn_text.v_proj",
|
121 |
-
"model.layers.8.self_attn.o_proj",
|
122 |
-
"model.layers.27.self_attn_text.k_proj",
|
123 |
-
"model.layers.21.mlp.up_proj",
|
124 |
-
"model.layers.9.self_attn.v_proj",
|
125 |
-
"model.layers.5.mlp.up_proj",
|
126 |
-
"model.layers.11.self_attn_text.k_proj",
|
127 |
-
"model.layers.18.mlp.up_proj",
|
128 |
-
"model.layers.17.self_attn.q_proj",
|
129 |
-
"model.layers.25.mlp.down_proj",
|
130 |
-
"model.layers.16.self_attn.o_proj",
|
131 |
-
"model.layers.15.self_attn.o_proj",
|
132 |
-
"model.layers.1.mlp.down_proj",
|
133 |
-
"model.layers.24.mlp.gate_proj",
|
134 |
-
"model.layers.10.self_attn_text.q_proj",
|
135 |
-
"model.layers.7.self_attn.k_proj",
|
136 |
-
"model.layers.7.mlp.down_proj",
|
137 |
-
"model.layers.17.self_attn_text.k_proj",
|
138 |
-
"model.layers.6.mlp.down_proj",
|
139 |
-
"model.layers.10.self_attn.k_proj",
|
140 |
-
"model.layers.17.self_attn.o_proj",
|
141 |
-
"model.layers.20.self_attn_text.q_proj",
|
142 |
-
"model.layers.26.self_attn_text.o_proj",
|
143 |
-
"model.layers.10.self_attn.v_proj",
|
144 |
-
"model.layers.20.self_attn_text.k_proj",
|
145 |
-
"model.layers.19.self_attn.o_proj",
|
146 |
-
"model.layers.8.mlp.down_proj",
|
147 |
-
"model.layers.0.mlp.down_proj",
|
148 |
-
"model.layers.13.self_attn_text.o_proj",
|
149 |
-
"model.layers.18.self_attn.q_proj",
|
150 |
"model.layers.13.mlp.gate_proj",
|
151 |
-
"model.layers.
|
152 |
-
"model.layers.
|
153 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
154 |
"model.layers.3.mlp.up_proj",
|
|
|
|
|
|
|
|
|
155 |
"model.layers.5.self_attn.v_proj",
|
156 |
-
"model.layers.
|
157 |
-
"model.layers.
|
158 |
-
"model.layers.
|
159 |
-
"model.layers.13.self_attn.o_proj",
|
160 |
-
"model.layers.24.mlp.down_proj",
|
161 |
-
"model.layers.26.mlp.down_proj",
|
162 |
-
"model.layers.19.mlp.up_proj",
|
163 |
-
"model.layers.17.self_attn.v_proj",
|
164 |
-
"model.layers.1.self_attn.q_proj",
|
165 |
-
"model.layers.5.self_attn_text.q_proj",
|
166 |
-
"model.layers.4.self_attn_text.q_proj",
|
167 |
"model.layers.18.mlp.gate_proj",
|
|
|
|
|
|
|
168 |
"model.layers.26.self_attn_text.v_proj",
|
|
|
|
|
|
|
|
|
|
|
169 |
"model.layers.8.mlp.gate_proj",
|
170 |
-
"model.layers.
|
171 |
-
"model.layers.
|
172 |
-
"model.layers.
|
173 |
-
"model.layers.
|
174 |
-
"model.layers.
|
175 |
-
"model.layers.7.self_attn.o_proj",
|
176 |
-
"model.layers.26.self_attn.q_proj",
|
177 |
-
"model.layers.24.self_attn_text.o_proj",
|
178 |
-
"model.layers.17.self_attn.k_proj",
|
179 |
-
"model.layers.7.self_attn_text.o_proj",
|
180 |
-
"model.layers.24.self_attn_text.q_proj",
|
181 |
-
"model.layers.22.self_attn_text.q_proj",
|
182 |
-
"model.layers.7.self_attn.q_proj",
|
183 |
-
"model.layers.20.self_attn.v_proj",
|
184 |
-
"model.layers.10.mlp.up_proj",
|
185 |
-
"model.layers.19.self_attn_text.k_proj",
|
186 |
-
"model.layers.14.self_attn_text.o_proj",
|
187 |
-
"model.layers.22.self_attn_text.v_proj",
|
188 |
-
"model.layers.17.mlp.down_proj",
|
189 |
-
"model.layers.16.mlp.gate_proj",
|
190 |
-
"model.layers.8.self_attn.v_proj",
|
191 |
-
"model.layers.4.self_attn_text.o_proj",
|
192 |
-
"model.layers.26.mlp.gate_proj",
|
193 |
-
"model.layers.1.mlp.gate_proj",
|
194 |
-
"model.layers.18.self_attn_text.v_proj",
|
195 |
-
"model.layers.25.self_attn_text.k_proj",
|
196 |
-
"model.layers.0.mlp.gate_proj",
|
197 |
-
"model.layers.1.self_attn_text.k_proj",
|
198 |
-
"model.layers.18.self_attn_text.o_proj",
|
199 |
-
"model.layers.24.mlp.up_proj",
|
200 |
-
"model.layers.26.mlp.up_proj",
|
201 |
"model.layers.21.self_attn.q_proj",
|
202 |
-
"model.layers.
|
203 |
-
"model.layers.
|
204 |
-
"model.layers.
|
205 |
-
"model.layers.
|
206 |
-
"model.layers.8.mlp.up_proj",
|
207 |
-
"model.layers.10.self_attn.o_proj",
|
208 |
-
"model.layers.21.self_attn_text.k_proj",
|
209 |
-
"model.layers.5.mlp.gate_proj",
|
210 |
-
"model.layers.12.mlp.up_proj",
|
211 |
"model.layers.25.mlp.gate_proj",
|
212 |
-
"model.layers.
|
213 |
-
"model.layers.
|
214 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
215 |
"model.layers.5.self_attn_text.o_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
216 |
"model.layers.12.self_attn.v_proj",
|
|
|
|
|
|
|
|
|
|
|
217 |
"model.layers.1.self_attn.k_proj",
|
218 |
-
"model.layers.
|
219 |
-
"model.layers.25.self_attn.
|
220 |
-
"model.layers.
|
221 |
-
"model.layers.
|
222 |
-
"model.layers.6.
|
|
|
223 |
"model.layers.12.self_attn_text.v_proj",
|
224 |
-
"model.layers.
|
225 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
226 |
"model.layers.9.self_attn_text.v_proj",
|
227 |
-
"model.layers.
|
228 |
-
"model.layers.
|
229 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
230 |
"model.layers.18.self_attn_text.q_proj",
|
231 |
-
"model.layers.
|
232 |
-
"model.layers.
|
233 |
-
"model.layers.
|
234 |
-
"model.layers.
|
235 |
-
"model.layers.
|
236 |
-
"model.layers.
|
237 |
-
"model.layers.
|
238 |
-
"model.layers.
|
239 |
-
"model.layers.15.self_attn_text.k_proj",
|
240 |
-
"model.layers.5.self_attn.o_proj",
|
241 |
-
"model.layers.0.self_attn.o_proj",
|
242 |
-
"model.layers.13.self_attn_text.k_proj",
|
243 |
-
"model.layers.21.self_attn_text.o_proj",
|
244 |
-
"model.layers.3.self_attn.v_proj",
|
245 |
-
"model.layers.6.self_attn.o_proj",
|
246 |
"model.layers.4.self_attn.k_proj",
|
247 |
-
"model.layers.
|
248 |
-
"model.layers.
|
249 |
-
"model.layers.
|
250 |
-
"model.layers.
|
|
|
251 |
"model.layers.19.self_attn.v_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
252 |
"model.layers.12.mlp.down_proj",
|
253 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
254 |
"model.layers.10.self_attn_text.v_proj",
|
255 |
-
"model.layers.
|
256 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
257 |
"model.layers.14.self_attn_text.k_proj",
|
258 |
-
"model.layers.
|
259 |
-
"model.layers.
|
260 |
-
"model.layers.
|
261 |
-
"model.layers.
|
|
|
|
|
|
|
262 |
"model.layers.10.self_attn_text.k_proj",
|
263 |
-
"model.layers.
|
|
|
264 |
"model.layers.8.self_attn_text.k_proj",
|
265 |
-
"model.layers.19.self_attn_text.q_proj",
|
266 |
-
"model.layers.15.self_attn_text.o_proj",
|
267 |
-
"model.layers.3.self_attn_text.o_proj",
|
268 |
-
"model.layers.12.self_attn.q_proj",
|
269 |
-
"model.layers.14.self_attn.k_proj",
|
270 |
-
"model.layers.18.self_attn.o_proj",
|
271 |
-
"model.layers.0.mlp.up_proj",
|
272 |
-
"model.layers.4.self_attn.v_proj",
|
273 |
-
"model.layers.10.mlp.down_proj",
|
274 |
-
"model.layers.25.self_attn.v_proj",
|
275 |
-
"model.layers.21.self_attn_text.v_proj",
|
276 |
-
"model.layers.15.self_attn.k_proj",
|
277 |
-
"model.layers.21.mlp.down_proj",
|
278 |
-
"model.layers.27.self_attn_text.q_proj",
|
279 |
-
"model.layers.15.mlp.down_proj",
|
280 |
-
"model.layers.24.self_attn.v_proj",
|
281 |
-
"model.layers.15.mlp.up_proj",
|
282 |
-
"model.layers.9.self_attn.k_proj",
|
283 |
-
"model.layers.2.self_attn_text.v_proj",
|
284 |
-
"model.layers.3.self_attn.q_proj",
|
285 |
-
"model.layers.27.self_attn_text.o_proj",
|
286 |
-
"model.layers.8.self_attn_text.o_proj",
|
287 |
-
"model.layers.11.self_attn_text.v_proj",
|
288 |
-
"model.layers.18.self_attn.v_proj",
|
289 |
-
"model.layers.6.self_attn_text.o_proj",
|
290 |
-
"model.layers.1.self_attn_text.q_proj",
|
291 |
-
"model.layers.14.mlp.gate_proj",
|
292 |
-
"model.layers.6.self_attn_text.v_proj",
|
293 |
-
"model.layers.4.mlp.up_proj",
|
294 |
-
"model.layers.9.self_attn_text.o_proj",
|
295 |
"model.layers.20.self_attn_text.v_proj",
|
296 |
-
"model.layers.
|
297 |
-
"model.layers.
|
298 |
-
"model.layers.
|
299 |
-
"model.layers.
|
300 |
-
"model.layers.
|
301 |
-
"model.layers.
|
302 |
-
"model.layers.9.
|
303 |
-
"model.layers.
|
304 |
-
"model.layers.3.mlp.gate_proj",
|
305 |
-
"model.layers.15.mlp.gate_proj",
|
306 |
-
"model.layers.16.self_attn.k_proj",
|
307 |
-
"model.layers.2.mlp.gate_proj",
|
308 |
"model.layers.2.mlp.up_proj",
|
309 |
-
"model.layers.
|
310 |
-
"model.layers.
|
311 |
-
"model.layers.
|
312 |
-
"model.layers.
|
313 |
-
"model.layers.
|
314 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
315 |
"model.layers.20.mlp.gate_proj",
|
316 |
-
"model.layers.
|
317 |
-
"model.layers.
|
318 |
-
"model.layers.11.self_attn.k_proj",
|
319 |
-
"model.layers.3.self_attn.o_proj",
|
320 |
-
"model.layers.19.self_attn_text.v_proj",
|
321 |
-
"model.layers.1.self_attn_text.v_proj",
|
322 |
"model.layers.11.mlp.gate_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
323 |
"model.layers.11.mlp.up_proj",
|
324 |
-
"model.layers.
|
325 |
-
"model.layers.
|
326 |
-
"model.layers.
|
327 |
-
"model.layers.
|
328 |
-
"model.layers.
|
329 |
-
"model.layers.
|
330 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
331 |
],
|
332 |
"task_type": "CAUSAL_LM",
|
333 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "saim1212/penguin2-checkpoint1",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"model.layers.25.self_attn_text.k_proj",
|
24 |
+
"model.layers.12.mlp.up_proj",
|
25 |
+
"model.layers.5.mlp.gate_proj",
|
26 |
+
"model.layers.22.self_attn_text.v_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"model.layers.22.self_attn.k_proj",
|
28 |
+
"model.layers.16.self_attn.o_proj",
|
29 |
+
"model.layers.6.self_attn.q_proj",
|
30 |
+
"model.layers.19.self_attn.o_proj",
|
31 |
+
"model.layers.2.mlp.gate_proj",
|
|
|
|
|
|
|
32 |
"model.layers.16.self_attn.q_proj",
|
33 |
+
"model.layers.3.self_attn.k_proj",
|
34 |
+
"model.layers.3.mlp.down_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
"model.layers.9.self_attn.o_proj",
|
36 |
+
"model.layers.8.self_attn_text.o_proj",
|
37 |
+
"model.layers.20.mlp.up_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
"model.layers.13.self_attn_text.q_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
"model.layers.13.mlp.gate_proj",
|
40 |
+
"model.layers.21.self_attn.o_proj",
|
41 |
+
"model.layers.19.self_attn.q_proj",
|
42 |
+
"model.layers.6.self_attn_text.q_proj",
|
43 |
+
"model.layers.1.self_attn_text.v_proj",
|
44 |
+
"model.layers.11.mlp.down_proj",
|
45 |
+
"model.layers.0.self_attn.k_proj",
|
46 |
+
"model.layers.14.mlp.up_proj",
|
47 |
+
"model.layers.18.self_attn.k_proj",
|
48 |
"model.layers.3.mlp.up_proj",
|
49 |
+
"model.layers.12.self_attn_text.k_proj",
|
50 |
+
"model.layers.26.mlp.gate_proj",
|
51 |
+
"model.layers.21.self_attn_text.q_proj",
|
52 |
+
"model.layers.10.self_attn_text.q_proj",
|
53 |
"model.layers.5.self_attn.v_proj",
|
54 |
+
"model.layers.19.mlp.gate_proj",
|
55 |
+
"model.layers.7.self_attn_text.o_proj",
|
56 |
+
"model.layers.10.mlp.up_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
"model.layers.18.mlp.gate_proj",
|
58 |
+
"model.layers.17.self_attn_text.v_proj",
|
59 |
+
"model.layers.27.self_attn.v_proj",
|
60 |
+
"model.layers.0.self_attn_text.o_proj",
|
61 |
"model.layers.26.self_attn_text.v_proj",
|
62 |
+
"model.layers.16.self_attn_text.v_proj",
|
63 |
+
"model.layers.21.self_attn_text.o_proj",
|
64 |
+
"model.layers.5.self_attn.k_proj",
|
65 |
+
"model.layers.16.mlp.down_proj",
|
66 |
+
"model.layers.9.self_attn_text.o_proj",
|
67 |
"model.layers.8.mlp.gate_proj",
|
68 |
+
"model.layers.8.self_attn.k_proj",
|
69 |
+
"model.layers.8.self_attn.o_proj",
|
70 |
+
"model.layers.10.self_attn.k_proj",
|
71 |
+
"model.layers.23.mlp.up_proj",
|
72 |
+
"model.layers.25.self_attn_text.q_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
"model.layers.21.self_attn.q_proj",
|
74 |
+
"model.layers.23.mlp.gate_proj",
|
75 |
+
"model.layers.25.self_attn.v_proj",
|
76 |
+
"model.layers.1.mlp.down_proj",
|
77 |
+
"model.layers.27.self_attn_text.k_proj",
|
|
|
|
|
|
|
|
|
|
|
78 |
"model.layers.25.mlp.gate_proj",
|
79 |
+
"model.layers.2.self_attn.o_proj",
|
80 |
+
"model.layers.14.self_attn.q_proj",
|
81 |
+
"model.layers.0.self_attn.o_proj",
|
82 |
+
"model.layers.24.mlp.up_proj",
|
83 |
+
"model.layers.11.self_attn.v_proj",
|
84 |
+
"model.layers.10.mlp.gate_proj",
|
85 |
+
"model.layers.2.self_attn_text.v_proj",
|
86 |
+
"model.layers.19.self_attn_text.o_proj",
|
87 |
+
"model.layers.7.self_attn_text.v_proj",
|
88 |
+
"model.layers.3.self_attn.v_proj",
|
89 |
+
"model.layers.2.self_attn.v_proj",
|
90 |
"model.layers.5.self_attn_text.o_proj",
|
91 |
+
"model.layers.15.self_attn.q_proj",
|
92 |
+
"model.layers.23.self_attn_text.k_proj",
|
93 |
+
"model.layers.15.self_attn_text.v_proj",
|
94 |
+
"model.layers.4.self_attn.v_proj",
|
95 |
+
"model.layers.15.self_attn_text.q_proj",
|
96 |
+
"model.layers.2.self_attn.q_proj",
|
97 |
+
"model.layers.22.self_attn_text.q_proj",
|
98 |
+
"model.layers.6.mlp.gate_proj",
|
99 |
+
"model.layers.13.self_attn_text.o_proj",
|
100 |
+
"model.layers.22.mlp.down_proj",
|
101 |
+
"model.layers.25.self_attn_text.o_proj",
|
102 |
+
"model.layers.12.mlp.gate_proj",
|
103 |
+
"model.layers.2.self_attn_text.q_proj",
|
104 |
+
"model.layers.24.self_attn.v_proj",
|
105 |
+
"model.layers.27.self_attn.q_proj",
|
106 |
+
"model.layers.21.self_attn_text.k_proj",
|
107 |
+
"model.layers.27.mlp.up_proj",
|
108 |
+
"model.layers.17.self_attn.q_proj",
|
109 |
+
"model.layers.27.self_attn_text.q_proj",
|
110 |
+
"model.layers.7.self_attn.k_proj",
|
111 |
+
"model.layers.20.self_attn_text.o_proj",
|
112 |
+
"model.layers.24.self_attn.k_proj",
|
113 |
+
"model.layers.1.self_attn_text.o_proj",
|
114 |
+
"model.layers.4.self_attn_text.q_proj",
|
115 |
+
"model.layers.16.self_attn_text.o_proj",
|
116 |
+
"model.layers.27.mlp.gate_proj",
|
117 |
+
"model.layers.0.mlp.up_proj",
|
118 |
+
"model.layers.26.self_attn.v_proj",
|
119 |
"model.layers.12.self_attn.v_proj",
|
120 |
+
"model.layers.25.self_attn.k_proj",
|
121 |
+
"model.layers.8.self_attn_text.v_proj",
|
122 |
+
"model.layers.4.self_attn_text.v_proj",
|
123 |
+
"model.layers.16.self_attn_text.q_proj",
|
124 |
+
"model.layers.10.self_attn_text.o_proj",
|
125 |
"model.layers.1.self_attn.k_proj",
|
126 |
+
"model.layers.11.self_attn_text.k_proj",
|
127 |
+
"model.layers.25.self_attn.q_proj",
|
128 |
+
"model.layers.19.self_attn_text.k_proj",
|
129 |
+
"model.layers.20.mlp.down_proj",
|
130 |
+
"model.layers.6.self_attn_text.v_proj",
|
131 |
+
"model.layers.14.self_attn_text.v_proj",
|
132 |
"model.layers.12.self_attn_text.v_proj",
|
133 |
+
"model.layers.26.self_attn.o_proj",
|
134 |
+
"model.layers.7.self_attn.v_proj",
|
135 |
+
"model.layers.15.mlp.gate_proj",
|
136 |
+
"model.layers.15.mlp.down_proj",
|
137 |
+
"model.layers.6.self_attn.v_proj",
|
138 |
+
"model.layers.7.mlp.up_proj",
|
139 |
+
"model.layers.23.self_attn_text.v_proj",
|
140 |
+
"model.layers.13.self_attn.q_proj",
|
141 |
+
"model.layers.18.self_attn.v_proj",
|
142 |
+
"model.layers.20.self_attn.q_proj",
|
143 |
+
"model.layers.24.self_attn.o_proj",
|
144 |
+
"model.layers.16.self_attn.k_proj",
|
145 |
+
"model.layers.8.self_attn.v_proj",
|
146 |
+
"model.layers.24.self_attn_text.q_proj",
|
147 |
+
"model.layers.17.mlp.up_proj",
|
148 |
+
"model.layers.0.mlp.gate_proj",
|
149 |
+
"model.layers.23.self_attn.o_proj",
|
150 |
+
"model.layers.7.self_attn_text.q_proj",
|
151 |
+
"model.layers.20.self_attn.o_proj",
|
152 |
+
"model.layers.26.self_attn_text.k_proj",
|
153 |
+
"model.layers.24.self_attn_text.o_proj",
|
154 |
+
"model.layers.17.self_attn_text.k_proj",
|
155 |
+
"model.layers.1.mlp.up_proj",
|
156 |
+
"model.layers.11.self_attn.q_proj",
|
157 |
+
"model.layers.12.self_attn.k_proj",
|
158 |
+
"model.layers.0.mlp.down_proj",
|
159 |
+
"model.layers.15.self_attn.o_proj",
|
160 |
+
"model.layers.14.self_attn_text.q_proj",
|
161 |
+
"model.layers.8.mlp.up_proj",
|
162 |
"model.layers.9.self_attn_text.v_proj",
|
163 |
+
"model.layers.17.self_attn.k_proj",
|
164 |
+
"model.layers.10.self_attn.v_proj",
|
165 |
+
"model.layers.20.self_attn_text.q_proj",
|
166 |
+
"model.layers.18.self_attn.o_proj",
|
167 |
+
"model.layers.27.self_attn.o_proj",
|
168 |
+
"model.layers.22.self_attn_text.o_proj",
|
169 |
+
"model.layers.11.self_attn_text.q_proj",
|
170 |
+
"model.layers.18.self_attn_text.v_proj",
|
171 |
+
"model.layers.23.self_attn_text.q_proj",
|
172 |
+
"model.layers.16.mlp.up_proj",
|
173 |
+
"model.layers.3.self_attn_text.q_proj",
|
174 |
"model.layers.18.self_attn_text.q_proj",
|
175 |
+
"model.layers.0.self_attn_text.k_proj",
|
176 |
+
"model.layers.2.self_attn_text.o_proj",
|
177 |
+
"model.layers.7.self_attn.o_proj",
|
178 |
+
"model.layers.4.self_attn.q_proj",
|
179 |
+
"model.layers.5.self_attn.q_proj",
|
180 |
+
"model.layers.13.mlp.up_proj",
|
181 |
+
"model.layers.22.mlp.gate_proj",
|
182 |
+
"model.layers.10.mlp.down_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
183 |
"model.layers.4.self_attn.k_proj",
|
184 |
+
"model.layers.2.self_attn_text.k_proj",
|
185 |
+
"model.layers.11.self_attn_text.o_proj",
|
186 |
+
"model.layers.24.self_attn_text.k_proj",
|
187 |
+
"model.layers.6.mlp.up_proj",
|
188 |
+
"model.layers.4.self_attn.o_proj",
|
189 |
"model.layers.19.self_attn.v_proj",
|
190 |
+
"model.layers.21.mlp.gate_proj",
|
191 |
+
"model.layers.26.self_attn_text.o_proj",
|
192 |
+
"model.layers.4.mlp.up_proj",
|
193 |
+
"model.layers.11.self_attn.k_proj",
|
194 |
+
"model.layers.17.self_attn_text.q_proj",
|
195 |
+
"model.layers.25.self_attn_text.v_proj",
|
196 |
+
"model.layers.26.self_attn.k_proj",
|
197 |
+
"model.layers.2.self_attn.k_proj",
|
198 |
+
"model.layers.1.self_attn.o_proj",
|
199 |
+
"model.layers.3.mlp.gate_proj",
|
200 |
+
"model.layers.18.mlp.down_proj",
|
201 |
+
"model.layers.9.mlp.up_proj",
|
202 |
+
"model.layers.6.self_attn.k_proj",
|
203 |
+
"model.layers.19.mlp.down_proj",
|
204 |
"model.layers.12.mlp.down_proj",
|
205 |
+
"model.layers.6.self_attn_text.k_proj",
|
206 |
+
"model.layers.13.self_attn.k_proj",
|
207 |
+
"model.layers.25.mlp.down_proj",
|
208 |
+
"model.layers.18.mlp.up_proj",
|
209 |
+
"model.layers.17.mlp.down_proj",
|
210 |
+
"model.layers.10.self_attn.q_proj",
|
211 |
+
"model.layers.7.self_attn.q_proj",
|
212 |
+
"model.layers.7.mlp.down_proj",
|
213 |
+
"model.layers.20.self_attn.k_proj",
|
214 |
+
"model.layers.6.self_attn_text.o_proj",
|
215 |
+
"model.layers.22.self_attn_text.k_proj",
|
216 |
+
"model.layers.7.mlp.gate_proj",
|
217 |
+
"model.layers.5.mlp.up_proj",
|
218 |
+
"model.layers.11.self_attn.o_proj",
|
219 |
+
"model.layers.14.self_attn.v_proj",
|
220 |
+
"model.layers.14.self_attn_text.o_proj",
|
221 |
+
"model.layers.17.mlp.gate_proj",
|
222 |
+
"model.layers.24.self_attn_text.v_proj",
|
223 |
+
"model.layers.9.self_attn_text.k_proj",
|
224 |
+
"model.layers.20.self_attn_text.k_proj",
|
225 |
+
"model.layers.1.self_attn.v_proj",
|
226 |
+
"model.layers.9.mlp.gate_proj",
|
227 |
+
"model.layers.4.self_attn_text.k_proj",
|
228 |
"model.layers.10.self_attn_text.v_proj",
|
229 |
+
"model.layers.23.self_attn.v_proj",
|
230 |
+
"model.layers.21.mlp.up_proj",
|
231 |
+
"model.layers.8.self_attn_text.q_proj",
|
232 |
+
"model.layers.24.self_attn.q_proj",
|
233 |
+
"model.layers.26.mlp.down_proj",
|
234 |
+
"model.layers.14.mlp.down_proj",
|
235 |
+
"model.layers.22.self_attn.q_proj",
|
236 |
+
"model.layers.15.self_attn.v_proj",
|
237 |
+
"model.layers.3.self_attn_text.k_proj",
|
238 |
+
"model.layers.18.self_attn_text.o_proj",
|
239 |
+
"model.layers.13.self_attn.o_proj",
|
240 |
+
"model.layers.1.self_attn_text.k_proj",
|
241 |
+
"model.layers.8.self_attn.q_proj",
|
242 |
+
"model.layers.8.mlp.down_proj",
|
243 |
+
"model.layers.19.self_attn.k_proj",
|
244 |
+
"model.layers.9.self_attn_text.q_proj",
|
245 |
+
"model.layers.21.self_attn.v_proj",
|
246 |
+
"model.layers.12.self_attn_text.q_proj",
|
247 |
+
"model.layers.5.self_attn_text.k_proj",
|
248 |
+
"model.layers.16.mlp.gate_proj",
|
249 |
+
"model.layers.22.self_attn.o_proj",
|
250 |
+
"model.layers.27.mlp.down_proj",
|
251 |
+
"model.layers.4.self_attn_text.o_proj",
|
252 |
+
"model.layers.12.self_attn_text.o_proj",
|
253 |
+
"model.layers.26.mlp.up_proj",
|
254 |
+
"model.layers.5.self_attn_text.q_proj",
|
255 |
+
"model.layers.18.self_attn.q_proj",
|
256 |
+
"model.layers.0.self_attn_text.v_proj",
|
257 |
+
"model.layers.19.self_attn_text.v_proj",
|
258 |
+
"model.layers.5.self_attn.o_proj",
|
259 |
+
"model.layers.21.mlp.down_proj",
|
260 |
+
"model.layers.27.self_attn_text.v_proj",
|
261 |
+
"model.layers.1.self_attn.q_proj",
|
262 |
+
"model.layers.25.self_attn.o_proj",
|
263 |
+
"model.layers.3.self_attn_text.o_proj",
|
264 |
+
"model.layers.4.mlp.down_proj",
|
265 |
+
"model.layers.6.mlp.down_proj",
|
266 |
+
"model.layers.0.self_attn_text.q_proj",
|
267 |
+
"model.layers.3.self_attn.o_proj",
|
268 |
+
"model.layers.23.self_attn_text.o_proj",
|
269 |
"model.layers.14.self_attn_text.k_proj",
|
270 |
+
"model.layers.26.self_attn.q_proj",
|
271 |
+
"model.layers.14.self_attn.k_proj",
|
272 |
+
"model.layers.1.mlp.gate_proj",
|
273 |
+
"model.layers.15.self_attn_text.o_proj",
|
274 |
+
"model.layers.19.self_attn_text.q_proj",
|
275 |
+
"model.layers.2.mlp.down_proj",
|
276 |
+
"model.layers.20.self_attn.v_proj",
|
277 |
"model.layers.10.self_attn_text.k_proj",
|
278 |
+
"model.layers.22.mlp.up_proj",
|
279 |
+
"model.layers.0.self_attn.q_proj",
|
280 |
"model.layers.8.self_attn_text.k_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
281 |
"model.layers.20.self_attn_text.v_proj",
|
282 |
+
"model.layers.25.mlp.up_proj",
|
283 |
+
"model.layers.9.self_attn.v_proj",
|
284 |
+
"model.layers.13.mlp.down_proj",
|
285 |
+
"model.layers.16.self_attn_text.k_proj",
|
286 |
+
"model.layers.10.self_attn.o_proj",
|
287 |
+
"model.layers.5.mlp.down_proj",
|
288 |
+
"model.layers.9.self_attn.q_proj",
|
289 |
+
"model.layers.27.self_attn_text.o_proj",
|
|
|
|
|
|
|
|
|
290 |
"model.layers.2.mlp.up_proj",
|
291 |
+
"model.layers.16.self_attn.v_proj",
|
292 |
+
"model.layers.14.self_attn.o_proj",
|
293 |
+
"model.layers.12.self_attn.o_proj",
|
294 |
+
"model.layers.22.self_attn.v_proj",
|
295 |
+
"model.layers.23.self_attn.q_proj",
|
296 |
+
"model.layers.1.self_attn_text.q_proj",
|
297 |
+
"model.layers.3.self_attn_text.v_proj",
|
298 |
+
"model.layers.18.self_attn_text.k_proj",
|
299 |
+
"model.layers.23.self_attn.k_proj",
|
300 |
+
"model.layers.27.self_attn.k_proj",
|
301 |
+
"model.layers.17.self_attn.o_proj",
|
302 |
"model.layers.20.mlp.gate_proj",
|
303 |
+
"model.layers.13.self_attn_text.v_proj",
|
304 |
+
"model.layers.15.self_attn.k_proj",
|
|
|
|
|
|
|
|
|
305 |
"model.layers.11.mlp.gate_proj",
|
306 |
+
"model.layers.9.mlp.down_proj",
|
307 |
+
"model.layers.5.self_attn_text.v_proj",
|
308 |
+
"model.layers.11.self_attn_text.v_proj",
|
309 |
+
"model.layers.24.mlp.down_proj",
|
310 |
+
"model.layers.6.self_attn.o_proj",
|
311 |
+
"model.layers.9.self_attn.k_proj",
|
312 |
+
"model.layers.23.mlp.down_proj",
|
313 |
+
"model.layers.14.mlp.gate_proj",
|
314 |
+
"model.layers.15.self_attn_text.k_proj",
|
315 |
+
"model.layers.13.self_attn.v_proj",
|
316 |
"model.layers.11.mlp.up_proj",
|
317 |
+
"model.layers.17.self_attn_text.o_proj",
|
318 |
+
"model.layers.7.self_attn_text.k_proj",
|
319 |
+
"model.layers.17.self_attn.v_proj",
|
320 |
+
"model.layers.15.mlp.up_proj",
|
321 |
+
"model.layers.4.mlp.gate_proj",
|
322 |
+
"model.layers.21.self_attn.k_proj",
|
323 |
+
"model.layers.24.mlp.gate_proj",
|
324 |
+
"model.layers.0.self_attn.v_proj",
|
325 |
+
"model.layers.26.self_attn_text.q_proj",
|
326 |
+
"model.layers.12.self_attn.q_proj",
|
327 |
+
"model.layers.21.self_attn_text.v_proj",
|
328 |
+
"model.layers.3.self_attn.q_proj",
|
329 |
+
"model.layers.13.self_attn_text.k_proj",
|
330 |
+
"model.layers.19.mlp.up_proj"
|
331 |
],
|
332 |
"task_type": "CAUSAL_LM",
|
333 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 91374880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5aea25041f898230eedf018fc9da3ee20aff4ea8d58da1da68fc1d52a1f313f
|
3 |
size 91374880
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 1.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 0.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 9.848,
|
3 |
+
"total_flos": 2.117785669819433e+17,
|
4 |
+
"train_loss": 1.5235166057463616,
|
5 |
+
"train_runtime": 30234.6635,
|
6 |
+
"train_samples_per_second": 0.661,
|
7 |
+
"train_steps_per_second": 0.021
|
8 |
}
|
checkpoint-620/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: saim1212/penguin2-checkpoint1
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-620/adapter_config.json
ADDED
@@ -0,0 +1,335 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "saim1212/penguin2-checkpoint1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
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": 0.0,
|
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 |
+
"model.layers.25.self_attn_text.k_proj",
|
24 |
+
"model.layers.12.mlp.up_proj",
|
25 |
+
"model.layers.5.mlp.gate_proj",
|
26 |
+
"model.layers.22.self_attn_text.v_proj",
|
27 |
+
"model.layers.22.self_attn.k_proj",
|
28 |
+
"model.layers.16.self_attn.o_proj",
|
29 |
+
"model.layers.6.self_attn.q_proj",
|
30 |
+
"model.layers.19.self_attn.o_proj",
|
31 |
+
"model.layers.2.mlp.gate_proj",
|
32 |
+
"model.layers.16.self_attn.q_proj",
|
33 |
+
"model.layers.3.self_attn.k_proj",
|
34 |
+
"model.layers.3.mlp.down_proj",
|
35 |
+
"model.layers.9.self_attn.o_proj",
|
36 |
+
"model.layers.8.self_attn_text.o_proj",
|
37 |
+
"model.layers.20.mlp.up_proj",
|
38 |
+
"model.layers.13.self_attn_text.q_proj",
|
39 |
+
"model.layers.13.mlp.gate_proj",
|
40 |
+
"model.layers.21.self_attn.o_proj",
|
41 |
+
"model.layers.19.self_attn.q_proj",
|
42 |
+
"model.layers.6.self_attn_text.q_proj",
|
43 |
+
"model.layers.1.self_attn_text.v_proj",
|
44 |
+
"model.layers.11.mlp.down_proj",
|
45 |
+
"model.layers.0.self_attn.k_proj",
|
46 |
+
"model.layers.14.mlp.up_proj",
|
47 |
+
"model.layers.18.self_attn.k_proj",
|
48 |
+
"model.layers.3.mlp.up_proj",
|
49 |
+
"model.layers.12.self_attn_text.k_proj",
|
50 |
+
"model.layers.26.mlp.gate_proj",
|
51 |
+
"model.layers.21.self_attn_text.q_proj",
|
52 |
+
"model.layers.10.self_attn_text.q_proj",
|
53 |
+
"model.layers.5.self_attn.v_proj",
|
54 |
+
"model.layers.19.mlp.gate_proj",
|
55 |
+
"model.layers.7.self_attn_text.o_proj",
|
56 |
+
"model.layers.10.mlp.up_proj",
|
57 |
+
"model.layers.18.mlp.gate_proj",
|
58 |
+
"model.layers.17.self_attn_text.v_proj",
|
59 |
+
"model.layers.27.self_attn.v_proj",
|
60 |
+
"model.layers.0.self_attn_text.o_proj",
|
61 |
+
"model.layers.26.self_attn_text.v_proj",
|
62 |
+
"model.layers.16.self_attn_text.v_proj",
|
63 |
+
"model.layers.21.self_attn_text.o_proj",
|
64 |
+
"model.layers.5.self_attn.k_proj",
|
65 |
+
"model.layers.16.mlp.down_proj",
|
66 |
+
"model.layers.9.self_attn_text.o_proj",
|
67 |
+
"model.layers.8.mlp.gate_proj",
|
68 |
+
"model.layers.8.self_attn.k_proj",
|
69 |
+
"model.layers.8.self_attn.o_proj",
|
70 |
+
"model.layers.10.self_attn.k_proj",
|
71 |
+
"model.layers.23.mlp.up_proj",
|
72 |
+
"model.layers.25.self_attn_text.q_proj",
|
73 |
+
"model.layers.21.self_attn.q_proj",
|
74 |
+
"model.layers.23.mlp.gate_proj",
|
75 |
+
"model.layers.25.self_attn.v_proj",
|
76 |
+
"model.layers.1.mlp.down_proj",
|
77 |
+
"model.layers.27.self_attn_text.k_proj",
|
78 |
+
"model.layers.25.mlp.gate_proj",
|
79 |
+
"model.layers.2.self_attn.o_proj",
|
80 |
+
"model.layers.14.self_attn.q_proj",
|
81 |
+
"model.layers.0.self_attn.o_proj",
|
82 |
+
"model.layers.24.mlp.up_proj",
|
83 |
+
"model.layers.11.self_attn.v_proj",
|
84 |
+
"model.layers.10.mlp.gate_proj",
|
85 |
+
"model.layers.2.self_attn_text.v_proj",
|
86 |
+
"model.layers.19.self_attn_text.o_proj",
|
87 |
+
"model.layers.7.self_attn_text.v_proj",
|
88 |
+
"model.layers.3.self_attn.v_proj",
|
89 |
+
"model.layers.2.self_attn.v_proj",
|
90 |
+
"model.layers.5.self_attn_text.o_proj",
|
91 |
+
"model.layers.15.self_attn.q_proj",
|
92 |
+
"model.layers.23.self_attn_text.k_proj",
|
93 |
+
"model.layers.15.self_attn_text.v_proj",
|
94 |
+
"model.layers.4.self_attn.v_proj",
|
95 |
+
"model.layers.15.self_attn_text.q_proj",
|
96 |
+
"model.layers.2.self_attn.q_proj",
|
97 |
+
"model.layers.22.self_attn_text.q_proj",
|
98 |
+
"model.layers.6.mlp.gate_proj",
|
99 |
+
"model.layers.13.self_attn_text.o_proj",
|
100 |
+
"model.layers.22.mlp.down_proj",
|
101 |
+
"model.layers.25.self_attn_text.o_proj",
|
102 |
+
"model.layers.12.mlp.gate_proj",
|
103 |
+
"model.layers.2.self_attn_text.q_proj",
|
104 |
+
"model.layers.24.self_attn.v_proj",
|
105 |
+
"model.layers.27.self_attn.q_proj",
|
106 |
+
"model.layers.21.self_attn_text.k_proj",
|
107 |
+
"model.layers.27.mlp.up_proj",
|
108 |
+
"model.layers.17.self_attn.q_proj",
|
109 |
+
"model.layers.27.self_attn_text.q_proj",
|
110 |
+
"model.layers.7.self_attn.k_proj",
|
111 |
+
"model.layers.20.self_attn_text.o_proj",
|
112 |
+
"model.layers.24.self_attn.k_proj",
|
113 |
+
"model.layers.1.self_attn_text.o_proj",
|
114 |
+
"model.layers.4.self_attn_text.q_proj",
|
115 |
+
"model.layers.16.self_attn_text.o_proj",
|
116 |
+
"model.layers.27.mlp.gate_proj",
|
117 |
+
"model.layers.0.mlp.up_proj",
|
118 |
+
"model.layers.26.self_attn.v_proj",
|
119 |
+
"model.layers.12.self_attn.v_proj",
|
120 |
+
"model.layers.25.self_attn.k_proj",
|
121 |
+
"model.layers.8.self_attn_text.v_proj",
|
122 |
+
"model.layers.4.self_attn_text.v_proj",
|
123 |
+
"model.layers.16.self_attn_text.q_proj",
|
124 |
+
"model.layers.10.self_attn_text.o_proj",
|
125 |
+
"model.layers.1.self_attn.k_proj",
|
126 |
+
"model.layers.11.self_attn_text.k_proj",
|
127 |
+
"model.layers.25.self_attn.q_proj",
|
128 |
+
"model.layers.19.self_attn_text.k_proj",
|
129 |
+
"model.layers.20.mlp.down_proj",
|
130 |
+
"model.layers.6.self_attn_text.v_proj",
|
131 |
+
"model.layers.14.self_attn_text.v_proj",
|
132 |
+
"model.layers.12.self_attn_text.v_proj",
|
133 |
+
"model.layers.26.self_attn.o_proj",
|
134 |
+
"model.layers.7.self_attn.v_proj",
|
135 |
+
"model.layers.15.mlp.gate_proj",
|
136 |
+
"model.layers.15.mlp.down_proj",
|
137 |
+
"model.layers.6.self_attn.v_proj",
|
138 |
+
"model.layers.7.mlp.up_proj",
|
139 |
+
"model.layers.23.self_attn_text.v_proj",
|
140 |
+
"model.layers.13.self_attn.q_proj",
|
141 |
+
"model.layers.18.self_attn.v_proj",
|
142 |
+
"model.layers.20.self_attn.q_proj",
|
143 |
+
"model.layers.24.self_attn.o_proj",
|
144 |
+
"model.layers.16.self_attn.k_proj",
|
145 |
+
"model.layers.8.self_attn.v_proj",
|
146 |
+
"model.layers.24.self_attn_text.q_proj",
|
147 |
+
"model.layers.17.mlp.up_proj",
|
148 |
+
"model.layers.0.mlp.gate_proj",
|
149 |
+
"model.layers.23.self_attn.o_proj",
|
150 |
+
"model.layers.7.self_attn_text.q_proj",
|
151 |
+
"model.layers.20.self_attn.o_proj",
|
152 |
+
"model.layers.26.self_attn_text.k_proj",
|
153 |
+
"model.layers.24.self_attn_text.o_proj",
|
154 |
+
"model.layers.17.self_attn_text.k_proj",
|
155 |
+
"model.layers.1.mlp.up_proj",
|
156 |
+
"model.layers.11.self_attn.q_proj",
|
157 |
+
"model.layers.12.self_attn.k_proj",
|
158 |
+
"model.layers.0.mlp.down_proj",
|
159 |
+
"model.layers.15.self_attn.o_proj",
|
160 |
+
"model.layers.14.self_attn_text.q_proj",
|
161 |
+
"model.layers.8.mlp.up_proj",
|
162 |
+
"model.layers.9.self_attn_text.v_proj",
|
163 |
+
"model.layers.17.self_attn.k_proj",
|
164 |
+
"model.layers.10.self_attn.v_proj",
|
165 |
+
"model.layers.20.self_attn_text.q_proj",
|
166 |
+
"model.layers.18.self_attn.o_proj",
|
167 |
+
"model.layers.27.self_attn.o_proj",
|
168 |
+
"model.layers.22.self_attn_text.o_proj",
|
169 |
+
"model.layers.11.self_attn_text.q_proj",
|
170 |
+
"model.layers.18.self_attn_text.v_proj",
|
171 |
+
"model.layers.23.self_attn_text.q_proj",
|
172 |
+
"model.layers.16.mlp.up_proj",
|
173 |
+
"model.layers.3.self_attn_text.q_proj",
|
174 |
+
"model.layers.18.self_attn_text.q_proj",
|
175 |
+
"model.layers.0.self_attn_text.k_proj",
|
176 |
+
"model.layers.2.self_attn_text.o_proj",
|
177 |
+
"model.layers.7.self_attn.o_proj",
|
178 |
+
"model.layers.4.self_attn.q_proj",
|
179 |
+
"model.layers.5.self_attn.q_proj",
|
180 |
+
"model.layers.13.mlp.up_proj",
|
181 |
+
"model.layers.22.mlp.gate_proj",
|
182 |
+
"model.layers.10.mlp.down_proj",
|
183 |
+
"model.layers.4.self_attn.k_proj",
|
184 |
+
"model.layers.2.self_attn_text.k_proj",
|
185 |
+
"model.layers.11.self_attn_text.o_proj",
|
186 |
+
"model.layers.24.self_attn_text.k_proj",
|
187 |
+
"model.layers.6.mlp.up_proj",
|
188 |
+
"model.layers.4.self_attn.o_proj",
|
189 |
+
"model.layers.19.self_attn.v_proj",
|
190 |
+
"model.layers.21.mlp.gate_proj",
|
191 |
+
"model.layers.26.self_attn_text.o_proj",
|
192 |
+
"model.layers.4.mlp.up_proj",
|
193 |
+
"model.layers.11.self_attn.k_proj",
|
194 |
+
"model.layers.17.self_attn_text.q_proj",
|
195 |
+
"model.layers.25.self_attn_text.v_proj",
|
196 |
+
"model.layers.26.self_attn.k_proj",
|
197 |
+
"model.layers.2.self_attn.k_proj",
|
198 |
+
"model.layers.1.self_attn.o_proj",
|
199 |
+
"model.layers.3.mlp.gate_proj",
|
200 |
+
"model.layers.18.mlp.down_proj",
|
201 |
+
"model.layers.9.mlp.up_proj",
|
202 |
+
"model.layers.6.self_attn.k_proj",
|
203 |
+
"model.layers.19.mlp.down_proj",
|
204 |
+
"model.layers.12.mlp.down_proj",
|
205 |
+
"model.layers.6.self_attn_text.k_proj",
|
206 |
+
"model.layers.13.self_attn.k_proj",
|
207 |
+
"model.layers.25.mlp.down_proj",
|
208 |
+
"model.layers.18.mlp.up_proj",
|
209 |
+
"model.layers.17.mlp.down_proj",
|
210 |
+
"model.layers.10.self_attn.q_proj",
|
211 |
+
"model.layers.7.self_attn.q_proj",
|
212 |
+
"model.layers.7.mlp.down_proj",
|
213 |
+
"model.layers.20.self_attn.k_proj",
|
214 |
+
"model.layers.6.self_attn_text.o_proj",
|
215 |
+
"model.layers.22.self_attn_text.k_proj",
|
216 |
+
"model.layers.7.mlp.gate_proj",
|
217 |
+
"model.layers.5.mlp.up_proj",
|
218 |
+
"model.layers.11.self_attn.o_proj",
|
219 |
+
"model.layers.14.self_attn.v_proj",
|
220 |
+
"model.layers.14.self_attn_text.o_proj",
|
221 |
+
"model.layers.17.mlp.gate_proj",
|
222 |
+
"model.layers.24.self_attn_text.v_proj",
|
223 |
+
"model.layers.9.self_attn_text.k_proj",
|
224 |
+
"model.layers.20.self_attn_text.k_proj",
|
225 |
+
"model.layers.1.self_attn.v_proj",
|
226 |
+
"model.layers.9.mlp.gate_proj",
|
227 |
+
"model.layers.4.self_attn_text.k_proj",
|
228 |
+
"model.layers.10.self_attn_text.v_proj",
|
229 |
+
"model.layers.23.self_attn.v_proj",
|
230 |
+
"model.layers.21.mlp.up_proj",
|
231 |
+
"model.layers.8.self_attn_text.q_proj",
|
232 |
+
"model.layers.24.self_attn.q_proj",
|
233 |
+
"model.layers.26.mlp.down_proj",
|
234 |
+
"model.layers.14.mlp.down_proj",
|
235 |
+
"model.layers.22.self_attn.q_proj",
|
236 |
+
"model.layers.15.self_attn.v_proj",
|
237 |
+
"model.layers.3.self_attn_text.k_proj",
|
238 |
+
"model.layers.18.self_attn_text.o_proj",
|
239 |
+
"model.layers.13.self_attn.o_proj",
|
240 |
+
"model.layers.1.self_attn_text.k_proj",
|
241 |
+
"model.layers.8.self_attn.q_proj",
|
242 |
+
"model.layers.8.mlp.down_proj",
|
243 |
+
"model.layers.19.self_attn.k_proj",
|
244 |
+
"model.layers.9.self_attn_text.q_proj",
|
245 |
+
"model.layers.21.self_attn.v_proj",
|
246 |
+
"model.layers.12.self_attn_text.q_proj",
|
247 |
+
"model.layers.5.self_attn_text.k_proj",
|
248 |
+
"model.layers.16.mlp.gate_proj",
|
249 |
+
"model.layers.22.self_attn.o_proj",
|
250 |
+
"model.layers.27.mlp.down_proj",
|
251 |
+
"model.layers.4.self_attn_text.o_proj",
|
252 |
+
"model.layers.12.self_attn_text.o_proj",
|
253 |
+
"model.layers.26.mlp.up_proj",
|
254 |
+
"model.layers.5.self_attn_text.q_proj",
|
255 |
+
"model.layers.18.self_attn.q_proj",
|
256 |
+
"model.layers.0.self_attn_text.v_proj",
|
257 |
+
"model.layers.19.self_attn_text.v_proj",
|
258 |
+
"model.layers.5.self_attn.o_proj",
|
259 |
+
"model.layers.21.mlp.down_proj",
|
260 |
+
"model.layers.27.self_attn_text.v_proj",
|
261 |
+
"model.layers.1.self_attn.q_proj",
|
262 |
+
"model.layers.25.self_attn.o_proj",
|
263 |
+
"model.layers.3.self_attn_text.o_proj",
|
264 |
+
"model.layers.4.mlp.down_proj",
|
265 |
+
"model.layers.6.mlp.down_proj",
|
266 |
+
"model.layers.0.self_attn_text.q_proj",
|
267 |
+
"model.layers.3.self_attn.o_proj",
|
268 |
+
"model.layers.23.self_attn_text.o_proj",
|
269 |
+
"model.layers.14.self_attn_text.k_proj",
|
270 |
+
"model.layers.26.self_attn.q_proj",
|
271 |
+
"model.layers.14.self_attn.k_proj",
|
272 |
+
"model.layers.1.mlp.gate_proj",
|
273 |
+
"model.layers.15.self_attn_text.o_proj",
|
274 |
+
"model.layers.19.self_attn_text.q_proj",
|
275 |
+
"model.layers.2.mlp.down_proj",
|
276 |
+
"model.layers.20.self_attn.v_proj",
|
277 |
+
"model.layers.10.self_attn_text.k_proj",
|
278 |
+
"model.layers.22.mlp.up_proj",
|
279 |
+
"model.layers.0.self_attn.q_proj",
|
280 |
+
"model.layers.8.self_attn_text.k_proj",
|
281 |
+
"model.layers.20.self_attn_text.v_proj",
|
282 |
+
"model.layers.25.mlp.up_proj",
|
283 |
+
"model.layers.9.self_attn.v_proj",
|
284 |
+
"model.layers.13.mlp.down_proj",
|
285 |
+
"model.layers.16.self_attn_text.k_proj",
|
286 |
+
"model.layers.10.self_attn.o_proj",
|
287 |
+
"model.layers.5.mlp.down_proj",
|
288 |
+
"model.layers.9.self_attn.q_proj",
|
289 |
+
"model.layers.27.self_attn_text.o_proj",
|
290 |
+
"model.layers.2.mlp.up_proj",
|
291 |
+
"model.layers.16.self_attn.v_proj",
|
292 |
+
"model.layers.14.self_attn.o_proj",
|
293 |
+
"model.layers.12.self_attn.o_proj",
|
294 |
+
"model.layers.22.self_attn.v_proj",
|
295 |
+
"model.layers.23.self_attn.q_proj",
|
296 |
+
"model.layers.1.self_attn_text.q_proj",
|
297 |
+
"model.layers.3.self_attn_text.v_proj",
|
298 |
+
"model.layers.18.self_attn_text.k_proj",
|
299 |
+
"model.layers.23.self_attn.k_proj",
|
300 |
+
"model.layers.27.self_attn.k_proj",
|
301 |
+
"model.layers.17.self_attn.o_proj",
|
302 |
+
"model.layers.20.mlp.gate_proj",
|
303 |
+
"model.layers.13.self_attn_text.v_proj",
|
304 |
+
"model.layers.15.self_attn.k_proj",
|
305 |
+
"model.layers.11.mlp.gate_proj",
|
306 |
+
"model.layers.9.mlp.down_proj",
|
307 |
+
"model.layers.5.self_attn_text.v_proj",
|
308 |
+
"model.layers.11.self_attn_text.v_proj",
|
309 |
+
"model.layers.24.mlp.down_proj",
|
310 |
+
"model.layers.6.self_attn.o_proj",
|
311 |
+
"model.layers.9.self_attn.k_proj",
|
312 |
+
"model.layers.23.mlp.down_proj",
|
313 |
+
"model.layers.14.mlp.gate_proj",
|
314 |
+
"model.layers.15.self_attn_text.k_proj",
|
315 |
+
"model.layers.13.self_attn.v_proj",
|
316 |
+
"model.layers.11.mlp.up_proj",
|
317 |
+
"model.layers.17.self_attn_text.o_proj",
|
318 |
+
"model.layers.7.self_attn_text.k_proj",
|
319 |
+
"model.layers.17.self_attn.v_proj",
|
320 |
+
"model.layers.15.mlp.up_proj",
|
321 |
+
"model.layers.4.mlp.gate_proj",
|
322 |
+
"model.layers.21.self_attn.k_proj",
|
323 |
+
"model.layers.24.mlp.gate_proj",
|
324 |
+
"model.layers.0.self_attn.v_proj",
|
325 |
+
"model.layers.26.self_attn_text.q_proj",
|
326 |
+
"model.layers.12.self_attn.q_proj",
|
327 |
+
"model.layers.21.self_attn_text.v_proj",
|
328 |
+
"model.layers.3.self_attn.q_proj",
|
329 |
+
"model.layers.13.self_attn_text.k_proj",
|
330 |
+
"model.layers.19.mlp.up_proj"
|
331 |
+
],
|
332 |
+
"task_type": "CAUSAL_LM",
|
333 |
+
"use_dora": false,
|
334 |
+
"use_rslora": false
|
335 |
+
}
|
checkpoint-620/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5aea25041f898230eedf018fc9da3ee20aff4ea8d58da1da68fc1d52a1f313f
|
3 |
+
size 91374880
|
checkpoint-620/added_tokens.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|box_end|>": 151649,
|
3 |
+
"<|box_start|>": 151648,
|
4 |
+
"<|endoftext|>": 151643,
|
5 |
+
"<|im_end|>": 151645,
|
6 |
+
"<|im_start|>": 151644,
|
7 |
+
"<|image_pad|>": 151655,
|
8 |
+
"<|object_ref_end|>": 151647,
|
9 |
+
"<|object_ref_start|>": 151646,
|
10 |
+
"<|quad_end|>": 151651,
|
11 |
+
"<|quad_start|>": 151650,
|
12 |
+
"<|video_pad|>": 151656,
|
13 |
+
"<|vision_end|>": 151653,
|
14 |
+
"<|vision_pad|>": 151654,
|
15 |
+
"<|vision_start|>": 151652
|
16 |
+
}
|
checkpoint-620/chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
3 |
+
}
|
checkpoint-620/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-620/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83601b26aeedfa6d673c7eb4e30b1259d6f41697c58f66ab82fbd02be9331752
|
3 |
+
size 183102410
|
checkpoint-620/preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": true,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.48145466,
|
8 |
+
0.4578275,
|
9 |
+
0.40821073
|
10 |
+
],
|
11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.26862954,
|
14 |
+
0.26130258,
|
15 |
+
0.27577711
|
16 |
+
],
|
17 |
+
"max_pixels": 12845056,
|
18 |
+
"merge_size": 2,
|
19 |
+
"min_pixels": 3136,
|
20 |
+
"patch_size": 14,
|
21 |
+
"processor_class": "Qwen2VLProcessor",
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"longest_edge": 12845056,
|
26 |
+
"shortest_edge": 3136
|
27 |
+
},
|
28 |
+
"temporal_patch_size": 2
|
29 |
+
}
|
checkpoint-620/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b074bf97f241c2662caa5ce956b03d1249c3cc0713b6aef7796673362754f98
|
3 |
+
size 14512
|
checkpoint-620/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58aed9e8d78903cb12015375021c729c3f6c5fd1a1e19e7aee6ddde57c3310b9
|
3 |
+
size 14512
|
checkpoint-620/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74f8fea0ffcabf1857136136180f4c3a564886877d5b601d4022376094a58beb
|
3 |
+
size 988
|
checkpoint-620/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08317d4141be052ac5dc8d082d875b2c2419b963cc5e34daaba5b65ef0dd9f81
|
3 |
+
size 1064
|
checkpoint-620/special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
checkpoint-620/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
|
3 |
+
size 11420371
|
checkpoint-620/tokenizer_config.json
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"151646": {
|
29 |
+
"content": "<|object_ref_start|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"151647": {
|
37 |
+
"content": "<|object_ref_end|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"151648": {
|
45 |
+
"content": "<|box_start|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"151649": {
|
53 |
+
"content": "<|box_end|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"151650": {
|
61 |
+
"content": "<|quad_start|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"151651": {
|
69 |
+
"content": "<|quad_end|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"151652": {
|
77 |
+
"content": "<|vision_start|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"151653": {
|
85 |
+
"content": "<|vision_end|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"151654": {
|
93 |
+
"content": "<|vision_pad|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"151655": {
|
101 |
+
"content": "<|image_pad|>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"151656": {
|
109 |
+
"content": "<|video_pad|>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
}
|
116 |
+
},
|
117 |
+
"additional_special_tokens": [
|
118 |
+
"<|im_start|>",
|
119 |
+
"<|im_end|>",
|
120 |
+
"<|object_ref_start|>",
|
121 |
+
"<|object_ref_end|>",
|
122 |
+
"<|box_start|>",
|
123 |
+
"<|box_end|>",
|
124 |
+
"<|quad_start|>",
|
125 |
+
"<|quad_end|>",
|
126 |
+
"<|vision_start|>",
|
127 |
+
"<|vision_end|>",
|
128 |
+
"<|vision_pad|>",
|
129 |
+
"<|image_pad|>",
|
130 |
+
"<|video_pad|>"
|
131 |
+
],
|
132 |
+
"bos_token": null,
|
133 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
134 |
+
"clean_up_tokenization_spaces": false,
|
135 |
+
"eos_token": "<|im_end|>",
|
136 |
+
"errors": "replace",
|
137 |
+
"extra_special_tokens": {},
|
138 |
+
"max_length": null,
|
139 |
+
"model_max_length": 32768,
|
140 |
+
"pad_to_multiple_of": null,
|
141 |
+
"pad_token": "<|endoftext|>",
|
142 |
+
"pad_token_type_id": 0,
|
143 |
+
"padding_side": "right",
|
144 |
+
"processor_class": "Qwen2VLProcessor",
|
145 |
+
"split_special_tokens": false,
|
146 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
147 |
+
"unk_token": null
|
148 |
+
}
|
checkpoint-620/trainer_state.json
ADDED
@@ -0,0 +1,467 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.848,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 620,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.16,
|
13 |
+
"grad_norm": 53.243560791015625,
|
14 |
+
"learning_rate": 2.580645161290323e-06,
|
15 |
+
"loss": 14.2026,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.32,
|
20 |
+
"grad_norm": 18.361902236938477,
|
21 |
+
"learning_rate": 5.806451612903226e-06,
|
22 |
+
"loss": 6.1329,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.48,
|
27 |
+
"grad_norm": 19.430877685546875,
|
28 |
+
"learning_rate": 9.03225806451613e-06,
|
29 |
+
"loss": 4.058,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.64,
|
34 |
+
"grad_norm": 15.267464637756348,
|
35 |
+
"learning_rate": 1.2258064516129034e-05,
|
36 |
+
"loss": 3.097,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.8,
|
41 |
+
"grad_norm": 9.403186798095703,
|
42 |
+
"learning_rate": 1.5483870967741936e-05,
|
43 |
+
"loss": 2.8274,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.96,
|
48 |
+
"grad_norm": 6.261369228363037,
|
49 |
+
"learning_rate": 1.870967741935484e-05,
|
50 |
+
"loss": 2.4626,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.112,
|
55 |
+
"grad_norm": 5.149415493011475,
|
56 |
+
"learning_rate": 1.999429490929718e-05,
|
57 |
+
"loss": 2.1131,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.272,
|
62 |
+
"grad_norm": 4.141679286956787,
|
63 |
+
"learning_rate": 1.9959454037227215e-05,
|
64 |
+
"loss": 2.0099,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.432,
|
69 |
+
"grad_norm": 4.4521870613098145,
|
70 |
+
"learning_rate": 1.989305206325792e-05,
|
71 |
+
"loss": 1.8846,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.592,
|
76 |
+
"grad_norm": 6.675071716308594,
|
77 |
+
"learning_rate": 1.9795299412524948e-05,
|
78 |
+
"loss": 1.8903,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.752,
|
83 |
+
"grad_norm": 4.7035231590271,
|
84 |
+
"learning_rate": 1.9666505859174462e-05,
|
85 |
+
"loss": 1.7584,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.912,
|
90 |
+
"grad_norm": 6.597540855407715,
|
91 |
+
"learning_rate": 1.9507079544701583e-05,
|
92 |
+
"loss": 1.7185,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.064,
|
97 |
+
"grad_norm": 4.8695759773254395,
|
98 |
+
"learning_rate": 1.9317525684566686e-05,
|
99 |
+
"loss": 1.5598,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.224,
|
104 |
+
"grad_norm": 3.69114351272583,
|
105 |
+
"learning_rate": 1.9098444967188308e-05,
|
106 |
+
"loss": 1.6693,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 2.384,
|
111 |
+
"grad_norm": 3.190814733505249,
|
112 |
+
"learning_rate": 1.8850531650386154e-05,
|
113 |
+
"loss": 1.5646,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 2.544,
|
118 |
+
"grad_norm": 3.4081127643585205,
|
119 |
+
"learning_rate": 1.857457136130651e-05,
|
120 |
+
"loss": 1.4366,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 2.7039999999999997,
|
125 |
+
"grad_norm": 2.457369327545166,
|
126 |
+
"learning_rate": 1.827143860680199e-05,
|
127 |
+
"loss": 1.4132,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.864,
|
132 |
+
"grad_norm": 2.4000205993652344,
|
133 |
+
"learning_rate": 1.7942094002155122e-05,
|
134 |
+
"loss": 1.3689,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.016,
|
139 |
+
"grad_norm": 2.56905198097229,
|
140 |
+
"learning_rate": 1.758758122692791e-05,
|
141 |
+
"loss": 1.2682,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 3.176,
|
146 |
+
"grad_norm": 2.089385986328125,
|
147 |
+
"learning_rate": 1.7209023717584013e-05,
|
148 |
+
"loss": 1.2686,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 3.336,
|
153 |
+
"grad_norm": 2.0517237186431885,
|
154 |
+
"learning_rate": 1.6807621107364613e-05,
|
155 |
+
"loss": 1.2347,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 3.496,
|
160 |
+
"grad_norm": 2.282109260559082,
|
161 |
+
"learning_rate": 1.6384645424699835e-05,
|
162 |
+
"loss": 1.2462,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 3.656,
|
167 |
+
"grad_norm": 2.201382637023926,
|
168 |
+
"learning_rate": 1.594143706220273e-05,
|
169 |
+
"loss": 1.2536,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 3.816,
|
174 |
+
"grad_norm": 1.6903492212295532,
|
175 |
+
"learning_rate": 1.5479400529019987e-05,
|
176 |
+
"loss": 1.2723,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 3.976,
|
181 |
+
"grad_norm": 2.2920656204223633,
|
182 |
+
"learning_rate": 1.5000000000000002e-05,
|
183 |
+
"loss": 1.2036,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 4.128,
|
188 |
+
"grad_norm": 2.610243320465088,
|
189 |
+
"learning_rate": 1.4504754675782731e-05,
|
190 |
+
"loss": 1.0922,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 4.288,
|
195 |
+
"grad_norm": 2.494142770767212,
|
196 |
+
"learning_rate": 1.3995233968515105e-05,
|
197 |
+
"loss": 1.0985,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 4.448,
|
202 |
+
"grad_norm": 1.8717281818389893,
|
203 |
+
"learning_rate": 1.3473052528448203e-05,
|
204 |
+
"loss": 1.1152,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 4.608,
|
209 |
+
"grad_norm": 2.3531064987182617,
|
210 |
+
"learning_rate": 1.2939865127176771e-05,
|
211 |
+
"loss": 1.1175,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 4.768,
|
216 |
+
"grad_norm": 2.1707255840301514,
|
217 |
+
"learning_rate": 1.2397361413735785e-05,
|
218 |
+
"loss": 1.119,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 4.928,
|
223 |
+
"grad_norm": 2.2494473457336426,
|
224 |
+
"learning_rate": 1.1847260560171895e-05,
|
225 |
+
"loss": 1.1175,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 5.08,
|
230 |
+
"grad_norm": 2.7846431732177734,
|
231 |
+
"learning_rate": 1.1291305813557616e-05,
|
232 |
+
"loss": 1.0205,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 5.24,
|
237 |
+
"grad_norm": 2.8679280281066895,
|
238 |
+
"learning_rate": 1.0731258971712762e-05,
|
239 |
+
"loss": 1.0235,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 5.4,
|
244 |
+
"grad_norm": 2.4637234210968018,
|
245 |
+
"learning_rate": 1.0168894800139311e-05,
|
246 |
+
"loss": 1.0103,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 5.5600000000000005,
|
251 |
+
"grad_norm": 2.420814275741577,
|
252 |
+
"learning_rate": 9.605995407862248e-06,
|
253 |
+
"loss": 0.999,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 5.72,
|
258 |
+
"grad_norm": 2.7816896438598633,
|
259 |
+
"learning_rate": 9.04434459999902e-06,
|
260 |
+
"loss": 0.9866,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 5.88,
|
265 |
+
"grad_norm": 3.1777126789093018,
|
266 |
+
"learning_rate": 8.485722224954237e-06,
|
267 |
+
"loss": 1.0309,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 6.032,
|
272 |
+
"grad_norm": 2.992114782333374,
|
273 |
+
"learning_rate": 7.93189853415293e-06,
|
274 |
+
"loss": 0.9126,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 6.192,
|
279 |
+
"grad_norm": 2.742065906524658,
|
280 |
+
"learning_rate": 7.384628572186334e-06,
|
281 |
+
"loss": 0.9194,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 6.352,
|
286 |
+
"grad_norm": 2.3192052841186523,
|
287 |
+
"learning_rate": 6.845646615147445e-06,
|
288 |
+
"loss": 0.907,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 6.5120000000000005,
|
293 |
+
"grad_norm": 3.0966978073120117,
|
294 |
+
"learning_rate": 6.31666067478113e-06,
|
295 |
+
"loss": 0.9,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 6.672,
|
300 |
+
"grad_norm": 2.693567991256714,
|
301 |
+
"learning_rate": 5.799347085864851e-06,
|
302 |
+
"loss": 0.8984,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 6.832,
|
307 |
+
"grad_norm": 2.535724639892578,
|
308 |
+
"learning_rate": 5.295345193972445e-06,
|
309 |
+
"loss": 0.8658,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 6.992,
|
314 |
+
"grad_norm": 2.9776270389556885,
|
315 |
+
"learning_rate": 4.8062521604551245e-06,
|
316 |
+
"loss": 0.9213,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 7.144,
|
321 |
+
"grad_norm": 2.5464305877685547,
|
322 |
+
"learning_rate": 4.333617901102592e-06,
|
323 |
+
"loss": 0.7661,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 7.304,
|
328 |
+
"grad_norm": 2.318953037261963,
|
329 |
+
"learning_rate": 3.878940174523371e-06,
|
330 |
+
"loss": 0.791,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 7.464,
|
335 |
+
"grad_norm": 3.2819600105285645,
|
336 |
+
"learning_rate": 3.4436598358091577e-06,
|
337 |
+
"loss": 0.8174,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 7.624,
|
342 |
+
"grad_norm": 2.2935101985931396,
|
343 |
+
"learning_rate": 3.0291562705240107e-06,
|
344 |
+
"loss": 0.8107,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 7.784,
|
349 |
+
"grad_norm": 3.059847354888916,
|
350 |
+
"learning_rate": 2.6367430234880286e-06,
|
351 |
+
"loss": 0.8199,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 7.944,
|
356 |
+
"grad_norm": 2.7650320529937744,
|
357 |
+
"learning_rate": 2.2676636362076075e-06,
|
358 |
+
"loss": 0.819,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 8.096,
|
363 |
+
"grad_norm": 3.0527632236480713,
|
364 |
+
"learning_rate": 1.9230877061433505e-06,
|
365 |
+
"loss": 0.7425,
|
366 |
+
"step": 510
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 8.256,
|
370 |
+
"grad_norm": 2.6537036895751953,
|
371 |
+
"learning_rate": 1.60410718030361e-06,
|
372 |
+
"loss": 0.731,
|
373 |
+
"step": 520
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 8.416,
|
377 |
+
"grad_norm": 2.6983063220977783,
|
378 |
+
"learning_rate": 1.3117328949091634e-06,
|
379 |
+
"loss": 0.7354,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 8.576,
|
384 |
+
"grad_norm": 2.4979090690612793,
|
385 |
+
"learning_rate": 1.0468913720946084e-06,
|
386 |
+
"loss": 0.7442,
|
387 |
+
"step": 540
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 8.736,
|
391 |
+
"grad_norm": 2.457855463027954,
|
392 |
+
"learning_rate": 8.10421883797694e-07,
|
393 |
+
"loss": 0.7333,
|
394 |
+
"step": 550
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 8.896,
|
398 |
+
"grad_norm": 2.766944646835327,
|
399 |
+
"learning_rate": 6.030737921409169e-07,
|
400 |
+
"loss": 0.7399,
|
401 |
+
"step": 560
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 9.048,
|
405 |
+
"grad_norm": 2.2459168434143066,
|
406 |
+
"learning_rate": 4.2550417473364524e-07,
|
407 |
+
"loss": 0.6996,
|
408 |
+
"step": 570
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 9.208,
|
412 |
+
"grad_norm": 2.7171614170074463,
|
413 |
+
"learning_rate": 2.7827574242009434e-07,
|
414 |
+
"loss": 0.7126,
|
415 |
+
"step": 580
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 9.368,
|
419 |
+
"grad_norm": 2.6220312118530273,
|
420 |
+
"learning_rate": 1.6185505607171027e-07,
|
421 |
+
"loss": 0.6958,
|
422 |
+
"step": 590
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 9.528,
|
426 |
+
"grad_norm": 2.0688819885253906,
|
427 |
+
"learning_rate": 7.661104807487607e-08,
|
428 |
+
"loss": 0.7154,
|
429 |
+
"step": 600
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 9.688,
|
433 |
+
"grad_norm": 2.2390174865722656,
|
434 |
+
"learning_rate": 2.2813853199292745e-08,
|
435 |
+
"loss": 0.7047,
|
436 |
+
"step": 610
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 9.848,
|
440 |
+
"grad_norm": 2.2094919681549072,
|
441 |
+
"learning_rate": 6.339525519594159e-10,
|
442 |
+
"loss": 0.7091,
|
443 |
+
"step": 620
|
444 |
+
}
|
445 |
+
],
|
446 |
+
"logging_steps": 10,
|
447 |
+
"max_steps": 620,
|
448 |
+
"num_input_tokens_seen": 0,
|
449 |
+
"num_train_epochs": 10,
|
450 |
+
"save_steps": 1000,
|
451 |
+
"stateful_callbacks": {
|
452 |
+
"TrainerControl": {
|
453 |
+
"args": {
|
454 |
+
"should_epoch_stop": false,
|
455 |
+
"should_evaluate": false,
|
456 |
+
"should_log": false,
|
457 |
+
"should_save": true,
|
458 |
+
"should_training_stop": true
|
459 |
+
},
|
460 |
+
"attributes": {}
|
461 |
+
}
|
462 |
+
},
|
463 |
+
"total_flos": 2.117785669819433e+17,
|
464 |
+
"train_batch_size": 4,
|
465 |
+
"trial_name": null,
|
466 |
+
"trial_params": null
|
467 |
+
}
|
checkpoint-620/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc68d428446e7b26c93265364a77e73cf5e5fd379067282b28ea225efb2cb018
|
3 |
+
size 5688
|
checkpoint-620/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar16_11-00-49_ca1aedd8ff14/events.out.tfevents.1742123117.ca1aedd8ff14.153.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1157d83dd3801b0dd34503ce6098d087c95397b7c7cdefcfa64acaa0629349c3
|
3 |
+
size 19782
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 1.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 0.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 9.848,
|
3 |
+
"total_flos": 2.117785669819433e+17,
|
4 |
+
"train_loss": 1.5235166057463616,
|
5 |
+
"train_runtime": 30234.6635,
|
6 |
+
"train_samples_per_second": 0.661,
|
7 |
+
"train_steps_per_second": 0.021
|
8 |
}
|
trainer_log.jsonl
CHANGED
@@ -1,47 +1,63 @@
|
|
1 |
-
{"current_steps": 10, "total_steps":
|
2 |
-
{"current_steps": 20, "total_steps":
|
3 |
-
{"current_steps": 30, "total_steps":
|
4 |
-
{"current_steps": 40, "total_steps":
|
5 |
-
{"current_steps": 50, "total_steps":
|
6 |
-
{"current_steps": 60, "total_steps":
|
7 |
-
{"current_steps": 70, "total_steps":
|
8 |
-
{"current_steps": 80, "total_steps":
|
9 |
-
{"current_steps": 90, "total_steps":
|
10 |
-
{"current_steps": 100, "total_steps":
|
11 |
-
{"current_steps": 110, "total_steps":
|
12 |
-
{"current_steps": 120, "total_steps":
|
13 |
-
{"current_steps": 130, "total_steps":
|
14 |
-
{"current_steps": 140, "total_steps":
|
15 |
-
{"current_steps": 150, "total_steps":
|
16 |
-
{"current_steps": 160, "total_steps":
|
17 |
-
{"current_steps": 170, "total_steps":
|
18 |
-
{"current_steps": 180, "total_steps":
|
19 |
-
{"current_steps": 190, "total_steps":
|
20 |
-
{"current_steps": 200, "total_steps":
|
21 |
-
{"current_steps": 210, "total_steps":
|
22 |
-
{"current_steps": 220, "total_steps":
|
23 |
-
{"current_steps": 230, "total_steps":
|
24 |
-
{"current_steps": 240, "total_steps":
|
25 |
-
{"current_steps": 250, "total_steps":
|
26 |
-
{"current_steps": 260, "total_steps":
|
27 |
-
{"current_steps": 270, "total_steps":
|
28 |
-
{"current_steps": 280, "total_steps":
|
29 |
-
{"current_steps": 290, "total_steps":
|
30 |
-
{"current_steps": 300, "total_steps":
|
31 |
-
{"current_steps": 310, "total_steps":
|
32 |
-
{"current_steps": 320, "total_steps":
|
33 |
-
{"current_steps": 330, "total_steps":
|
34 |
-
{"current_steps": 340, "total_steps":
|
35 |
-
{"current_steps": 350, "total_steps":
|
36 |
-
{"current_steps": 360, "total_steps":
|
37 |
-
{"current_steps": 370, "total_steps":
|
38 |
-
{"current_steps": 380, "total_steps":
|
39 |
-
{"current_steps": 390, "total_steps":
|
40 |
-
{"current_steps": 400, "total_steps":
|
41 |
-
{"current_steps": 410, "total_steps":
|
42 |
-
{"current_steps": 420, "total_steps":
|
43 |
-
{"current_steps": 430, "total_steps":
|
44 |
-
{"current_steps": 440, "total_steps":
|
45 |
-
{"current_steps": 450, "total_steps":
|
46 |
-
{"current_steps": 460, "total_steps":
|
47 |
-
{"current_steps":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 10, "total_steps": 620, "loss": 14.2026, "lr": 2.580645161290323e-06, "epoch": 0.16, "percentage": 1.61, "elapsed_time": "0:08:09", "remaining_time": "8:18:05"}
|
2 |
+
{"current_steps": 20, "total_steps": 620, "loss": 6.1329, "lr": 5.806451612903226e-06, "epoch": 0.32, "percentage": 3.23, "elapsed_time": "0:16:20", "remaining_time": "8:10:05"}
|
3 |
+
{"current_steps": 30, "total_steps": 620, "loss": 4.058, "lr": 9.03225806451613e-06, "epoch": 0.48, "percentage": 4.84, "elapsed_time": "0:24:30", "remaining_time": "8:02:04"}
|
4 |
+
{"current_steps": 40, "total_steps": 620, "loss": 3.097, "lr": 1.2258064516129034e-05, "epoch": 0.64, "percentage": 6.45, "elapsed_time": "0:32:41", "remaining_time": "7:54:02"}
|
5 |
+
{"current_steps": 50, "total_steps": 620, "loss": 2.8274, "lr": 1.5483870967741936e-05, "epoch": 0.8, "percentage": 8.06, "elapsed_time": "0:40:51", "remaining_time": "7:45:49"}
|
6 |
+
{"current_steps": 60, "total_steps": 620, "loss": 2.4626, "lr": 1.870967741935484e-05, "epoch": 0.96, "percentage": 9.68, "elapsed_time": "0:49:02", "remaining_time": "7:37:42"}
|
7 |
+
{"current_steps": 70, "total_steps": 620, "loss": 2.1131, "lr": 1.999429490929718e-05, "epoch": 1.112, "percentage": 11.29, "elapsed_time": "0:56:48", "remaining_time": "7:26:22"}
|
8 |
+
{"current_steps": 80, "total_steps": 620, "loss": 2.0099, "lr": 1.9959454037227215e-05, "epoch": 1.272, "percentage": 12.9, "elapsed_time": "1:04:59", "remaining_time": "7:18:38"}
|
9 |
+
{"current_steps": 90, "total_steps": 620, "loss": 1.8846, "lr": 1.989305206325792e-05, "epoch": 1.432, "percentage": 14.52, "elapsed_time": "1:13:08", "remaining_time": "7:10:44"}
|
10 |
+
{"current_steps": 100, "total_steps": 620, "loss": 1.8903, "lr": 1.9795299412524948e-05, "epoch": 1.592, "percentage": 16.13, "elapsed_time": "1:21:19", "remaining_time": "7:02:52"}
|
11 |
+
{"current_steps": 110, "total_steps": 620, "loss": 1.7584, "lr": 1.9666505859174462e-05, "epoch": 1.752, "percentage": 17.74, "elapsed_time": "1:29:30", "remaining_time": "6:54:58"}
|
12 |
+
{"current_steps": 120, "total_steps": 620, "loss": 1.7185, "lr": 1.9507079544701583e-05, "epoch": 1.912, "percentage": 19.35, "elapsed_time": "1:37:41", "remaining_time": "6:47:04"}
|
13 |
+
{"current_steps": 130, "total_steps": 620, "loss": 1.5598, "lr": 1.9317525684566686e-05, "epoch": 2.064, "percentage": 20.97, "elapsed_time": "1:45:28", "remaining_time": "6:37:33"}
|
14 |
+
{"current_steps": 140, "total_steps": 620, "loss": 1.6693, "lr": 1.9098444967188308e-05, "epoch": 2.224, "percentage": 22.58, "elapsed_time": "1:53:40", "remaining_time": "6:29:43"}
|
15 |
+
{"current_steps": 150, "total_steps": 620, "loss": 1.5646, "lr": 1.8850531650386154e-05, "epoch": 2.384, "percentage": 24.19, "elapsed_time": "2:01:51", "remaining_time": "6:21:50"}
|
16 |
+
{"current_steps": 160, "total_steps": 620, "loss": 1.4366, "lr": 1.857457136130651e-05, "epoch": 2.544, "percentage": 25.81, "elapsed_time": "2:10:02", "remaining_time": "6:13:51"}
|
17 |
+
{"current_steps": 170, "total_steps": 620, "loss": 1.4132, "lr": 1.827143860680199e-05, "epoch": 2.7039999999999997, "percentage": 27.42, "elapsed_time": "2:18:13", "remaining_time": "6:05:53"}
|
18 |
+
{"current_steps": 180, "total_steps": 620, "loss": 1.3689, "lr": 1.7942094002155122e-05, "epoch": 2.864, "percentage": 29.03, "elapsed_time": "2:26:24", "remaining_time": "5:57:52"}
|
19 |
+
{"current_steps": 190, "total_steps": 620, "loss": 1.2682, "lr": 1.758758122692791e-05, "epoch": 3.016, "percentage": 30.65, "elapsed_time": "2:34:11", "remaining_time": "5:48:57"}
|
20 |
+
{"current_steps": 200, "total_steps": 620, "loss": 1.2686, "lr": 1.7209023717584013e-05, "epoch": 3.176, "percentage": 32.26, "elapsed_time": "2:42:22", "remaining_time": "5:40:59"}
|
21 |
+
{"current_steps": 210, "total_steps": 620, "loss": 1.2347, "lr": 1.6807621107364613e-05, "epoch": 3.336, "percentage": 33.87, "elapsed_time": "2:50:34", "remaining_time": "5:33:00"}
|
22 |
+
{"current_steps": 220, "total_steps": 620, "loss": 1.2462, "lr": 1.6384645424699835e-05, "epoch": 3.496, "percentage": 35.48, "elapsed_time": "2:58:44", "remaining_time": "5:24:59"}
|
23 |
+
{"current_steps": 230, "total_steps": 620, "loss": 1.2536, "lr": 1.594143706220273e-05, "epoch": 3.656, "percentage": 37.1, "elapsed_time": "3:06:56", "remaining_time": "5:16:58"}
|
24 |
+
{"current_steps": 240, "total_steps": 620, "loss": 1.2723, "lr": 1.5479400529019987e-05, "epoch": 3.816, "percentage": 38.71, "elapsed_time": "3:15:08", "remaining_time": "5:08:57"}
|
25 |
+
{"current_steps": 250, "total_steps": 620, "loss": 1.2036, "lr": 1.5000000000000002e-05, "epoch": 3.976, "percentage": 40.32, "elapsed_time": "3:23:18", "remaining_time": "5:00:53"}
|
26 |
+
{"current_steps": 260, "total_steps": 620, "loss": 1.0922, "lr": 1.4504754675782731e-05, "epoch": 4.128, "percentage": 41.94, "elapsed_time": "3:31:04", "remaining_time": "4:52:15"}
|
27 |
+
{"current_steps": 270, "total_steps": 620, "loss": 1.0985, "lr": 1.3995233968515105e-05, "epoch": 4.288, "percentage": 43.55, "elapsed_time": "3:39:15", "remaining_time": "4:44:13"}
|
28 |
+
{"current_steps": 280, "total_steps": 620, "loss": 1.1152, "lr": 1.3473052528448203e-05, "epoch": 4.448, "percentage": 45.16, "elapsed_time": "3:47:27", "remaining_time": "4:36:11"}
|
29 |
+
{"current_steps": 290, "total_steps": 620, "loss": 1.1175, "lr": 1.2939865127176771e-05, "epoch": 4.608, "percentage": 46.77, "elapsed_time": "3:55:38", "remaining_time": "4:28:08"}
|
30 |
+
{"current_steps": 300, "total_steps": 620, "loss": 1.119, "lr": 1.2397361413735785e-05, "epoch": 4.768, "percentage": 48.39, "elapsed_time": "4:03:50", "remaining_time": "4:20:05"}
|
31 |
+
{"current_steps": 310, "total_steps": 620, "loss": 1.1175, "lr": 1.1847260560171895e-05, "epoch": 4.928, "percentage": 50.0, "elapsed_time": "4:12:01", "remaining_time": "4:12:01"}
|
32 |
+
{"current_steps": 320, "total_steps": 620, "loss": 1.0205, "lr": 1.1291305813557616e-05, "epoch": 5.08, "percentage": 51.61, "elapsed_time": "4:19:49", "remaining_time": "4:03:34"}
|
33 |
+
{"current_steps": 330, "total_steps": 620, "loss": 1.0235, "lr": 1.0731258971712762e-05, "epoch": 5.24, "percentage": 53.23, "elapsed_time": "4:28:00", "remaining_time": "3:55:31"}
|
34 |
+
{"current_steps": 340, "total_steps": 620, "loss": 1.0103, "lr": 1.0168894800139311e-05, "epoch": 5.4, "percentage": 54.84, "elapsed_time": "4:36:11", "remaining_time": "3:47:27"}
|
35 |
+
{"current_steps": 350, "total_steps": 620, "loss": 0.999, "lr": 9.605995407862248e-06, "epoch": 5.5600000000000005, "percentage": 56.45, "elapsed_time": "4:44:22", "remaining_time": "3:39:22"}
|
36 |
+
{"current_steps": 360, "total_steps": 620, "loss": 0.9866, "lr": 9.04434459999902e-06, "epoch": 5.72, "percentage": 58.06, "elapsed_time": "4:52:33", "remaining_time": "3:31:17"}
|
37 |
+
{"current_steps": 370, "total_steps": 620, "loss": 1.0309, "lr": 8.485722224954237e-06, "epoch": 5.88, "percentage": 59.68, "elapsed_time": "5:00:45", "remaining_time": "3:23:12"}
|
38 |
+
{"current_steps": 380, "total_steps": 620, "loss": 0.9126, "lr": 7.93189853415293e-06, "epoch": 6.032, "percentage": 61.29, "elapsed_time": "5:08:32", "remaining_time": "3:14:52"}
|
39 |
+
{"current_steps": 390, "total_steps": 620, "loss": 0.9194, "lr": 7.384628572186334e-06, "epoch": 6.192, "percentage": 62.9, "elapsed_time": "5:16:43", "remaining_time": "3:06:47"}
|
40 |
+
{"current_steps": 400, "total_steps": 620, "loss": 0.907, "lr": 6.845646615147445e-06, "epoch": 6.352, "percentage": 64.52, "elapsed_time": "5:24:54", "remaining_time": "2:58:42"}
|
41 |
+
{"current_steps": 410, "total_steps": 620, "loss": 0.9, "lr": 6.31666067478113e-06, "epoch": 6.5120000000000005, "percentage": 66.13, "elapsed_time": "5:33:05", "remaining_time": "2:50:36"}
|
42 |
+
{"current_steps": 420, "total_steps": 620, "loss": 0.8984, "lr": 5.799347085864851e-06, "epoch": 6.672, "percentage": 67.74, "elapsed_time": "5:41:16", "remaining_time": "2:42:30"}
|
43 |
+
{"current_steps": 430, "total_steps": 620, "loss": 0.8658, "lr": 5.295345193972445e-06, "epoch": 6.832, "percentage": 69.35, "elapsed_time": "5:49:27", "remaining_time": "2:34:24"}
|
44 |
+
{"current_steps": 440, "total_steps": 620, "loss": 0.9213, "lr": 4.8062521604551245e-06, "epoch": 6.992, "percentage": 70.97, "elapsed_time": "5:57:39", "remaining_time": "2:26:18"}
|
45 |
+
{"current_steps": 450, "total_steps": 620, "loss": 0.7661, "lr": 4.333617901102592e-06, "epoch": 7.144, "percentage": 72.58, "elapsed_time": "6:05:26", "remaining_time": "2:18:03"}
|
46 |
+
{"current_steps": 460, "total_steps": 620, "loss": 0.791, "lr": 3.878940174523371e-06, "epoch": 7.304, "percentage": 74.19, "elapsed_time": "6:13:37", "remaining_time": "2:09:57"}
|
47 |
+
{"current_steps": 470, "total_steps": 620, "loss": 0.8174, "lr": 3.4436598358091577e-06, "epoch": 7.464, "percentage": 75.81, "elapsed_time": "6:21:49", "remaining_time": "2:01:51"}
|
48 |
+
{"current_steps": 480, "total_steps": 620, "loss": 0.8107, "lr": 3.0291562705240107e-06, "epoch": 7.624, "percentage": 77.42, "elapsed_time": "6:30:00", "remaining_time": "1:53:45"}
|
49 |
+
{"current_steps": 490, "total_steps": 620, "loss": 0.8199, "lr": 2.6367430234880286e-06, "epoch": 7.784, "percentage": 79.03, "elapsed_time": "6:38:11", "remaining_time": "1:45:38"}
|
50 |
+
{"current_steps": 500, "total_steps": 620, "loss": 0.819, "lr": 2.2676636362076075e-06, "epoch": 7.944, "percentage": 80.65, "elapsed_time": "6:46:23", "remaining_time": "1:37:31"}
|
51 |
+
{"current_steps": 510, "total_steps": 620, "loss": 0.7425, "lr": 1.9230877061433505e-06, "epoch": 8.096, "percentage": 82.26, "elapsed_time": "6:54:10", "remaining_time": "1:29:19"}
|
52 |
+
{"current_steps": 520, "total_steps": 620, "loss": 0.731, "lr": 1.60410718030361e-06, "epoch": 8.256, "percentage": 83.87, "elapsed_time": "7:02:22", "remaining_time": "1:21:13"}
|
53 |
+
{"current_steps": 530, "total_steps": 620, "loss": 0.7354, "lr": 1.3117328949091634e-06, "epoch": 8.416, "percentage": 85.48, "elapsed_time": "7:10:33", "remaining_time": "1:13:06"}
|
54 |
+
{"current_steps": 540, "total_steps": 620, "loss": 0.7442, "lr": 1.0468913720946084e-06, "epoch": 8.576, "percentage": 87.1, "elapsed_time": "7:18:45", "remaining_time": "1:05:00"}
|
55 |
+
{"current_steps": 550, "total_steps": 620, "loss": 0.7333, "lr": 8.10421883797694e-07, "epoch": 8.736, "percentage": 88.71, "elapsed_time": "7:26:56", "remaining_time": "0:56:53"}
|
56 |
+
{"current_steps": 560, "total_steps": 620, "loss": 0.7399, "lr": 6.030737921409169e-07, "epoch": 8.896, "percentage": 90.32, "elapsed_time": "7:35:08", "remaining_time": "0:48:45"}
|
57 |
+
{"current_steps": 570, "total_steps": 620, "loss": 0.6996, "lr": 4.2550417473364524e-07, "epoch": 9.048, "percentage": 91.94, "elapsed_time": "7:42:54", "remaining_time": "0:40:36"}
|
58 |
+
{"current_steps": 580, "total_steps": 620, "loss": 0.7126, "lr": 2.7827574242009434e-07, "epoch": 9.208, "percentage": 93.55, "elapsed_time": "7:51:05", "remaining_time": "0:32:29"}
|
59 |
+
{"current_steps": 590, "total_steps": 620, "loss": 0.6958, "lr": 1.6185505607171027e-07, "epoch": 9.368, "percentage": 95.16, "elapsed_time": "7:59:17", "remaining_time": "0:24:22"}
|
60 |
+
{"current_steps": 600, "total_steps": 620, "loss": 0.7154, "lr": 7.661104807487607e-08, "epoch": 9.528, "percentage": 96.77, "elapsed_time": "8:07:28", "remaining_time": "0:16:14"}
|
61 |
+
{"current_steps": 610, "total_steps": 620, "loss": 0.7047, "lr": 2.2813853199292745e-08, "epoch": 9.688, "percentage": 98.39, "elapsed_time": "8:15:40", "remaining_time": "0:08:07"}
|
62 |
+
{"current_steps": 620, "total_steps": 620, "loss": 0.7091, "lr": 6.339525519594159e-10, "epoch": 9.848, "percentage": 100.0, "elapsed_time": "8:23:51", "remaining_time": "0:00:00"}
|
63 |
+
{"current_steps": 620, "total_steps": 620, "epoch": 9.848, "percentage": 100.0, "elapsed_time": "8:23:53", "remaining_time": "0:00:00"}
|
trainer_state.json
CHANGED
@@ -1,349 +1,461 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
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.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss":
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate":
|
22 |
-
"loss":
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm":
|
28 |
-
"learning_rate":
|
29 |
-
"loss":
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
-
"epoch":
|
34 |
-
"grad_norm":
|
35 |
-
"learning_rate": 1.
|
36 |
-
"loss":
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
-
"epoch":
|
41 |
-
"grad_norm":
|
42 |
-
"learning_rate": 1.
|
43 |
-
"loss": 2.
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
-
"epoch":
|
48 |
-
"grad_norm":
|
49 |
-
"learning_rate": 1.
|
50 |
-
"loss": 2.
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
-
"epoch":
|
55 |
-
"grad_norm":
|
56 |
-
"learning_rate": 1.
|
57 |
-
"loss":
|
58 |
"step": 70
|
59 |
},
|
60 |
{
|
61 |
-
"epoch":
|
62 |
-
"grad_norm":
|
63 |
-
"learning_rate": 1.
|
64 |
-
"loss":
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
-
"epoch":
|
69 |
-
"grad_norm":
|
70 |
-
"learning_rate": 1.
|
71 |
-
"loss": 1.
|
72 |
"step": 90
|
73 |
},
|
74 |
{
|
75 |
-
"epoch":
|
76 |
-
"grad_norm":
|
77 |
-
"learning_rate": 1.
|
78 |
-
"loss": 1.
|
79 |
"step": 100
|
80 |
},
|
81 |
{
|
82 |
-
"epoch":
|
83 |
-
"grad_norm":
|
84 |
-
"learning_rate": 1.
|
85 |
-
"loss": 1.
|
86 |
"step": 110
|
87 |
},
|
88 |
{
|
89 |
-
"epoch":
|
90 |
-
"grad_norm":
|
91 |
-
"learning_rate": 1.
|
92 |
-
"loss": 1.
|
93 |
"step": 120
|
94 |
},
|
95 |
{
|
96 |
-
"epoch":
|
97 |
-
"grad_norm":
|
98 |
-
"learning_rate": 1.
|
99 |
-
"loss": 1.
|
100 |
"step": 130
|
101 |
},
|
102 |
{
|
103 |
-
"epoch":
|
104 |
-
"grad_norm":
|
105 |
-
"learning_rate": 1.
|
106 |
-
"loss": 1.
|
107 |
"step": 140
|
108 |
},
|
109 |
{
|
110 |
-
"epoch":
|
111 |
-
"grad_norm":
|
112 |
-
"learning_rate": 1.
|
113 |
-
"loss": 1.
|
114 |
"step": 150
|
115 |
},
|
116 |
{
|
117 |
-
"epoch":
|
118 |
-
"grad_norm":
|
119 |
-
"learning_rate": 1.
|
120 |
-
"loss": 1.
|
121 |
"step": 160
|
122 |
},
|
123 |
{
|
124 |
-
"epoch":
|
125 |
-
"grad_norm": 2.
|
126 |
-
"learning_rate": 1.
|
127 |
-
"loss": 1.
|
128 |
"step": 170
|
129 |
},
|
130 |
{
|
131 |
-
"epoch":
|
132 |
-
"grad_norm": 2.
|
133 |
-
"learning_rate": 1.
|
134 |
-
"loss": 1.
|
135 |
"step": 180
|
136 |
},
|
137 |
{
|
138 |
-
"epoch":
|
139 |
-
"grad_norm": 2.
|
140 |
-
"learning_rate": 1.
|
141 |
-
"loss": 1.
|
142 |
"step": 190
|
143 |
},
|
144 |
{
|
145 |
-
"epoch":
|
146 |
-
"grad_norm": 2.
|
147 |
-
"learning_rate": 1.
|
148 |
-
"loss": 1.
|
149 |
"step": 200
|
150 |
},
|
151 |
{
|
152 |
-
"epoch":
|
153 |
-
"grad_norm": 2.
|
154 |
-
"learning_rate": 1.
|
155 |
-
"loss": 1.
|
156 |
"step": 210
|
157 |
},
|
158 |
{
|
159 |
-
"epoch":
|
160 |
-
"grad_norm": 2.
|
161 |
-
"learning_rate": 1.
|
162 |
-
"loss": 1.
|
163 |
"step": 220
|
164 |
},
|
165 |
{
|
166 |
-
"epoch":
|
167 |
-
"grad_norm": 2.
|
168 |
-
"learning_rate": 1.
|
169 |
-
"loss": 1.
|
170 |
"step": 230
|
171 |
},
|
172 |
{
|
173 |
-
"epoch":
|
174 |
-
"grad_norm":
|
175 |
-
"learning_rate": 1.
|
176 |
-
"loss": 1.
|
177 |
"step": 240
|
178 |
},
|
179 |
{
|
180 |
-
"epoch":
|
181 |
-
"grad_norm":
|
182 |
-
"learning_rate": 1.
|
183 |
-
"loss": 1.
|
184 |
"step": 250
|
185 |
},
|
186 |
{
|
187 |
-
"epoch":
|
188 |
-
"grad_norm": 2.
|
189 |
-
"learning_rate":
|
190 |
-
"loss":
|
191 |
"step": 260
|
192 |
},
|
193 |
{
|
194 |
-
"epoch":
|
195 |
-
"grad_norm":
|
196 |
-
"learning_rate":
|
197 |
-
"loss":
|
198 |
"step": 270
|
199 |
},
|
200 |
{
|
201 |
-
"epoch":
|
202 |
-
"grad_norm":
|
203 |
-
"learning_rate":
|
204 |
-
"loss":
|
205 |
"step": 280
|
206 |
},
|
207 |
{
|
208 |
-
"epoch":
|
209 |
-
"grad_norm":
|
210 |
-
"learning_rate":
|
211 |
-
"loss":
|
212 |
"step": 290
|
213 |
},
|
214 |
{
|
215 |
-
"epoch":
|
216 |
-
"grad_norm": 2.
|
217 |
-
"learning_rate":
|
218 |
-
"loss":
|
219 |
"step": 300
|
220 |
},
|
221 |
{
|
222 |
-
"epoch":
|
223 |
-
"grad_norm":
|
224 |
-
"learning_rate":
|
225 |
-
"loss":
|
226 |
"step": 310
|
227 |
},
|
228 |
{
|
229 |
-
"epoch":
|
230 |
-
"grad_norm":
|
231 |
-
"learning_rate":
|
232 |
-
"loss":
|
233 |
"step": 320
|
234 |
},
|
235 |
{
|
236 |
-
"epoch":
|
237 |
-
"grad_norm":
|
238 |
-
"learning_rate":
|
239 |
-
"loss":
|
240 |
"step": 330
|
241 |
},
|
242 |
{
|
243 |
-
"epoch":
|
244 |
-
"grad_norm": 2.
|
245 |
-
"learning_rate":
|
246 |
-
"loss":
|
247 |
"step": 340
|
248 |
},
|
249 |
{
|
250 |
-
"epoch":
|
251 |
-
"grad_norm": 2.
|
252 |
-
"learning_rate":
|
253 |
-
"loss": 0.
|
254 |
"step": 350
|
255 |
},
|
256 |
{
|
257 |
-
"epoch":
|
258 |
-
"grad_norm": 2.
|
259 |
-
"learning_rate":
|
260 |
-
"loss": 0.
|
261 |
"step": 360
|
262 |
},
|
263 |
{
|
264 |
-
"epoch":
|
265 |
-
"grad_norm": 3.
|
266 |
-
"learning_rate":
|
267 |
-
"loss":
|
268 |
"step": 370
|
269 |
},
|
270 |
{
|
271 |
-
"epoch":
|
272 |
-
"grad_norm": 2.
|
273 |
-
"learning_rate":
|
274 |
-
"loss": 0.
|
275 |
"step": 380
|
276 |
},
|
277 |
{
|
278 |
-
"epoch":
|
279 |
-
"grad_norm": 2.
|
280 |
-
"learning_rate":
|
281 |
-
"loss": 0.
|
282 |
"step": 390
|
283 |
},
|
284 |
{
|
285 |
-
"epoch":
|
286 |
-
"grad_norm": 2.
|
287 |
-
"learning_rate":
|
288 |
-
"loss": 0.
|
289 |
"step": 400
|
290 |
},
|
291 |
{
|
292 |
-
"epoch":
|
293 |
-
"grad_norm":
|
294 |
-
"learning_rate":
|
295 |
-
"loss": 0.
|
296 |
"step": 410
|
297 |
},
|
298 |
{
|
299 |
-
"epoch":
|
300 |
-
"grad_norm": 2.
|
301 |
-
"learning_rate": 5.
|
302 |
-
"loss": 0.
|
303 |
"step": 420
|
304 |
},
|
305 |
{
|
306 |
-
"epoch":
|
307 |
-
"grad_norm": 2.
|
308 |
-
"learning_rate":
|
309 |
-
"loss": 0.
|
310 |
"step": 430
|
311 |
},
|
312 |
{
|
313 |
-
"epoch":
|
314 |
-
"grad_norm": 2.
|
315 |
-
"learning_rate":
|
316 |
-
"loss": 0.
|
317 |
"step": 440
|
318 |
},
|
319 |
{
|
320 |
-
"epoch":
|
321 |
-
"grad_norm": 2.
|
322 |
-
"learning_rate":
|
323 |
-
"loss": 0.
|
324 |
"step": 450
|
325 |
},
|
326 |
{
|
327 |
-
"epoch":
|
328 |
-
"grad_norm": 2.
|
329 |
-
"learning_rate":
|
330 |
-
"loss": 0.
|
331 |
"step": 460
|
332 |
},
|
333 |
{
|
334 |
-
"epoch":
|
335 |
-
"
|
336 |
-
"
|
337 |
-
"
|
338 |
-
"
|
339 |
-
|
340 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
341 |
}
|
342 |
],
|
343 |
"logging_steps": 10,
|
344 |
-
"max_steps":
|
345 |
"num_input_tokens_seen": 0,
|
346 |
-
"num_train_epochs":
|
347 |
"save_steps": 1000,
|
348 |
"stateful_callbacks": {
|
349 |
"TrainerControl": {
|
@@ -357,7 +469,7 @@
|
|
357 |
"attributes": {}
|
358 |
}
|
359 |
},
|
360 |
-
"total_flos":
|
361 |
"train_batch_size": 4,
|
362 |
"trial_name": null,
|
363 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.848,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 620,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.16,
|
13 |
+
"grad_norm": 53.243560791015625,
|
14 |
+
"learning_rate": 2.580645161290323e-06,
|
15 |
+
"loss": 14.2026,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.32,
|
20 |
+
"grad_norm": 18.361902236938477,
|
21 |
+
"learning_rate": 5.806451612903226e-06,
|
22 |
+
"loss": 6.1329,
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.48,
|
27 |
+
"grad_norm": 19.430877685546875,
|
28 |
+
"learning_rate": 9.03225806451613e-06,
|
29 |
+
"loss": 4.058,
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.64,
|
34 |
+
"grad_norm": 15.267464637756348,
|
35 |
+
"learning_rate": 1.2258064516129034e-05,
|
36 |
+
"loss": 3.097,
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 0.8,
|
41 |
+
"grad_norm": 9.403186798095703,
|
42 |
+
"learning_rate": 1.5483870967741936e-05,
|
43 |
+
"loss": 2.8274,
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.96,
|
48 |
+
"grad_norm": 6.261369228363037,
|
49 |
+
"learning_rate": 1.870967741935484e-05,
|
50 |
+
"loss": 2.4626,
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 1.112,
|
55 |
+
"grad_norm": 5.149415493011475,
|
56 |
+
"learning_rate": 1.999429490929718e-05,
|
57 |
+
"loss": 2.1131,
|
58 |
"step": 70
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 1.272,
|
62 |
+
"grad_norm": 4.141679286956787,
|
63 |
+
"learning_rate": 1.9959454037227215e-05,
|
64 |
+
"loss": 2.0099,
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 1.432,
|
69 |
+
"grad_norm": 4.4521870613098145,
|
70 |
+
"learning_rate": 1.989305206325792e-05,
|
71 |
+
"loss": 1.8846,
|
72 |
"step": 90
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 1.592,
|
76 |
+
"grad_norm": 6.675071716308594,
|
77 |
+
"learning_rate": 1.9795299412524948e-05,
|
78 |
+
"loss": 1.8903,
|
79 |
"step": 100
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 1.752,
|
83 |
+
"grad_norm": 4.7035231590271,
|
84 |
+
"learning_rate": 1.9666505859174462e-05,
|
85 |
+
"loss": 1.7584,
|
86 |
"step": 110
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 1.912,
|
90 |
+
"grad_norm": 6.597540855407715,
|
91 |
+
"learning_rate": 1.9507079544701583e-05,
|
92 |
+
"loss": 1.7185,
|
93 |
"step": 120
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 2.064,
|
97 |
+
"grad_norm": 4.8695759773254395,
|
98 |
+
"learning_rate": 1.9317525684566686e-05,
|
99 |
+
"loss": 1.5598,
|
100 |
"step": 130
|
101 |
},
|
102 |
{
|
103 |
+
"epoch": 2.224,
|
104 |
+
"grad_norm": 3.69114351272583,
|
105 |
+
"learning_rate": 1.9098444967188308e-05,
|
106 |
+
"loss": 1.6693,
|
107 |
"step": 140
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 2.384,
|
111 |
+
"grad_norm": 3.190814733505249,
|
112 |
+
"learning_rate": 1.8850531650386154e-05,
|
113 |
+
"loss": 1.5646,
|
114 |
"step": 150
|
115 |
},
|
116 |
{
|
117 |
+
"epoch": 2.544,
|
118 |
+
"grad_norm": 3.4081127643585205,
|
119 |
+
"learning_rate": 1.857457136130651e-05,
|
120 |
+
"loss": 1.4366,
|
121 |
"step": 160
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 2.7039999999999997,
|
125 |
+
"grad_norm": 2.457369327545166,
|
126 |
+
"learning_rate": 1.827143860680199e-05,
|
127 |
+
"loss": 1.4132,
|
128 |
"step": 170
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 2.864,
|
132 |
+
"grad_norm": 2.4000205993652344,
|
133 |
+
"learning_rate": 1.7942094002155122e-05,
|
134 |
+
"loss": 1.3689,
|
135 |
"step": 180
|
136 |
},
|
137 |
{
|
138 |
+
"epoch": 3.016,
|
139 |
+
"grad_norm": 2.56905198097229,
|
140 |
+
"learning_rate": 1.758758122692791e-05,
|
141 |
+
"loss": 1.2682,
|
142 |
"step": 190
|
143 |
},
|
144 |
{
|
145 |
+
"epoch": 3.176,
|
146 |
+
"grad_norm": 2.089385986328125,
|
147 |
+
"learning_rate": 1.7209023717584013e-05,
|
148 |
+
"loss": 1.2686,
|
149 |
"step": 200
|
150 |
},
|
151 |
{
|
152 |
+
"epoch": 3.336,
|
153 |
+
"grad_norm": 2.0517237186431885,
|
154 |
+
"learning_rate": 1.6807621107364613e-05,
|
155 |
+
"loss": 1.2347,
|
156 |
"step": 210
|
157 |
},
|
158 |
{
|
159 |
+
"epoch": 3.496,
|
160 |
+
"grad_norm": 2.282109260559082,
|
161 |
+
"learning_rate": 1.6384645424699835e-05,
|
162 |
+
"loss": 1.2462,
|
163 |
"step": 220
|
164 |
},
|
165 |
{
|
166 |
+
"epoch": 3.656,
|
167 |
+
"grad_norm": 2.201382637023926,
|
168 |
+
"learning_rate": 1.594143706220273e-05,
|
169 |
+
"loss": 1.2536,
|
170 |
"step": 230
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 3.816,
|
174 |
+
"grad_norm": 1.6903492212295532,
|
175 |
+
"learning_rate": 1.5479400529019987e-05,
|
176 |
+
"loss": 1.2723,
|
177 |
"step": 240
|
178 |
},
|
179 |
{
|
180 |
+
"epoch": 3.976,
|
181 |
+
"grad_norm": 2.2920656204223633,
|
182 |
+
"learning_rate": 1.5000000000000002e-05,
|
183 |
+
"loss": 1.2036,
|
184 |
"step": 250
|
185 |
},
|
186 |
{
|
187 |
+
"epoch": 4.128,
|
188 |
+
"grad_norm": 2.610243320465088,
|
189 |
+
"learning_rate": 1.4504754675782731e-05,
|
190 |
+
"loss": 1.0922,
|
191 |
"step": 260
|
192 |
},
|
193 |
{
|
194 |
+
"epoch": 4.288,
|
195 |
+
"grad_norm": 2.494142770767212,
|
196 |
+
"learning_rate": 1.3995233968515105e-05,
|
197 |
+
"loss": 1.0985,
|
198 |
"step": 270
|
199 |
},
|
200 |
{
|
201 |
+
"epoch": 4.448,
|
202 |
+
"grad_norm": 1.8717281818389893,
|
203 |
+
"learning_rate": 1.3473052528448203e-05,
|
204 |
+
"loss": 1.1152,
|
205 |
"step": 280
|
206 |
},
|
207 |
{
|
208 |
+
"epoch": 4.608,
|
209 |
+
"grad_norm": 2.3531064987182617,
|
210 |
+
"learning_rate": 1.2939865127176771e-05,
|
211 |
+
"loss": 1.1175,
|
212 |
"step": 290
|
213 |
},
|
214 |
{
|
215 |
+
"epoch": 4.768,
|
216 |
+
"grad_norm": 2.1707255840301514,
|
217 |
+
"learning_rate": 1.2397361413735785e-05,
|
218 |
+
"loss": 1.119,
|
219 |
"step": 300
|
220 |
},
|
221 |
{
|
222 |
+
"epoch": 4.928,
|
223 |
+
"grad_norm": 2.2494473457336426,
|
224 |
+
"learning_rate": 1.1847260560171895e-05,
|
225 |
+
"loss": 1.1175,
|
226 |
"step": 310
|
227 |
},
|
228 |
{
|
229 |
+
"epoch": 5.08,
|
230 |
+
"grad_norm": 2.7846431732177734,
|
231 |
+
"learning_rate": 1.1291305813557616e-05,
|
232 |
+
"loss": 1.0205,
|
233 |
"step": 320
|
234 |
},
|
235 |
{
|
236 |
+
"epoch": 5.24,
|
237 |
+
"grad_norm": 2.8679280281066895,
|
238 |
+
"learning_rate": 1.0731258971712762e-05,
|
239 |
+
"loss": 1.0235,
|
240 |
"step": 330
|
241 |
},
|
242 |
{
|
243 |
+
"epoch": 5.4,
|
244 |
+
"grad_norm": 2.4637234210968018,
|
245 |
+
"learning_rate": 1.0168894800139311e-05,
|
246 |
+
"loss": 1.0103,
|
247 |
"step": 340
|
248 |
},
|
249 |
{
|
250 |
+
"epoch": 5.5600000000000005,
|
251 |
+
"grad_norm": 2.420814275741577,
|
252 |
+
"learning_rate": 9.605995407862248e-06,
|
253 |
+
"loss": 0.999,
|
254 |
"step": 350
|
255 |
},
|
256 |
{
|
257 |
+
"epoch": 5.72,
|
258 |
+
"grad_norm": 2.7816896438598633,
|
259 |
+
"learning_rate": 9.04434459999902e-06,
|
260 |
+
"loss": 0.9866,
|
261 |
"step": 360
|
262 |
},
|
263 |
{
|
264 |
+
"epoch": 5.88,
|
265 |
+
"grad_norm": 3.1777126789093018,
|
266 |
+
"learning_rate": 8.485722224954237e-06,
|
267 |
+
"loss": 1.0309,
|
268 |
"step": 370
|
269 |
},
|
270 |
{
|
271 |
+
"epoch": 6.032,
|
272 |
+
"grad_norm": 2.992114782333374,
|
273 |
+
"learning_rate": 7.93189853415293e-06,
|
274 |
+
"loss": 0.9126,
|
275 |
"step": 380
|
276 |
},
|
277 |
{
|
278 |
+
"epoch": 6.192,
|
279 |
+
"grad_norm": 2.742065906524658,
|
280 |
+
"learning_rate": 7.384628572186334e-06,
|
281 |
+
"loss": 0.9194,
|
282 |
"step": 390
|
283 |
},
|
284 |
{
|
285 |
+
"epoch": 6.352,
|
286 |
+
"grad_norm": 2.3192052841186523,
|
287 |
+
"learning_rate": 6.845646615147445e-06,
|
288 |
+
"loss": 0.907,
|
289 |
"step": 400
|
290 |
},
|
291 |
{
|
292 |
+
"epoch": 6.5120000000000005,
|
293 |
+
"grad_norm": 3.0966978073120117,
|
294 |
+
"learning_rate": 6.31666067478113e-06,
|
295 |
+
"loss": 0.9,
|
296 |
"step": 410
|
297 |
},
|
298 |
{
|
299 |
+
"epoch": 6.672,
|
300 |
+
"grad_norm": 2.693567991256714,
|
301 |
+
"learning_rate": 5.799347085864851e-06,
|
302 |
+
"loss": 0.8984,
|
303 |
"step": 420
|
304 |
},
|
305 |
{
|
306 |
+
"epoch": 6.832,
|
307 |
+
"grad_norm": 2.535724639892578,
|
308 |
+
"learning_rate": 5.295345193972445e-06,
|
309 |
+
"loss": 0.8658,
|
310 |
"step": 430
|
311 |
},
|
312 |
{
|
313 |
+
"epoch": 6.992,
|
314 |
+
"grad_norm": 2.9776270389556885,
|
315 |
+
"learning_rate": 4.8062521604551245e-06,
|
316 |
+
"loss": 0.9213,
|
317 |
"step": 440
|
318 |
},
|
319 |
{
|
320 |
+
"epoch": 7.144,
|
321 |
+
"grad_norm": 2.5464305877685547,
|
322 |
+
"learning_rate": 4.333617901102592e-06,
|
323 |
+
"loss": 0.7661,
|
324 |
"step": 450
|
325 |
},
|
326 |
{
|
327 |
+
"epoch": 7.304,
|
328 |
+
"grad_norm": 2.318953037261963,
|
329 |
+
"learning_rate": 3.878940174523371e-06,
|
330 |
+
"loss": 0.791,
|
331 |
"step": 460
|
332 |
},
|
333 |
{
|
334 |
+
"epoch": 7.464,
|
335 |
+
"grad_norm": 3.2819600105285645,
|
336 |
+
"learning_rate": 3.4436598358091577e-06,
|
337 |
+
"loss": 0.8174,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 7.624,
|
342 |
+
"grad_norm": 2.2935101985931396,
|
343 |
+
"learning_rate": 3.0291562705240107e-06,
|
344 |
+
"loss": 0.8107,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 7.784,
|
349 |
+
"grad_norm": 3.059847354888916,
|
350 |
+
"learning_rate": 2.6367430234880286e-06,
|
351 |
+
"loss": 0.8199,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 7.944,
|
356 |
+
"grad_norm": 2.7650320529937744,
|
357 |
+
"learning_rate": 2.2676636362076075e-06,
|
358 |
+
"loss": 0.819,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 8.096,
|
363 |
+
"grad_norm": 3.0527632236480713,
|
364 |
+
"learning_rate": 1.9230877061433505e-06,
|
365 |
+
"loss": 0.7425,
|
366 |
+
"step": 510
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 8.256,
|
370 |
+
"grad_norm": 2.6537036895751953,
|
371 |
+
"learning_rate": 1.60410718030361e-06,
|
372 |
+
"loss": 0.731,
|
373 |
+
"step": 520
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 8.416,
|
377 |
+
"grad_norm": 2.6983063220977783,
|
378 |
+
"learning_rate": 1.3117328949091634e-06,
|
379 |
+
"loss": 0.7354,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 8.576,
|
384 |
+
"grad_norm": 2.4979090690612793,
|
385 |
+
"learning_rate": 1.0468913720946084e-06,
|
386 |
+
"loss": 0.7442,
|
387 |
+
"step": 540
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 8.736,
|
391 |
+
"grad_norm": 2.457855463027954,
|
392 |
+
"learning_rate": 8.10421883797694e-07,
|
393 |
+
"loss": 0.7333,
|
394 |
+
"step": 550
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 8.896,
|
398 |
+
"grad_norm": 2.766944646835327,
|
399 |
+
"learning_rate": 6.030737921409169e-07,
|
400 |
+
"loss": 0.7399,
|
401 |
+
"step": 560
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 9.048,
|
405 |
+
"grad_norm": 2.2459168434143066,
|
406 |
+
"learning_rate": 4.2550417473364524e-07,
|
407 |
+
"loss": 0.6996,
|
408 |
+
"step": 570
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 9.208,
|
412 |
+
"grad_norm": 2.7171614170074463,
|
413 |
+
"learning_rate": 2.7827574242009434e-07,
|
414 |
+
"loss": 0.7126,
|
415 |
+
"step": 580
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 9.368,
|
419 |
+
"grad_norm": 2.6220312118530273,
|
420 |
+
"learning_rate": 1.6185505607171027e-07,
|
421 |
+
"loss": 0.6958,
|
422 |
+
"step": 590
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 9.528,
|
426 |
+
"grad_norm": 2.0688819885253906,
|
427 |
+
"learning_rate": 7.661104807487607e-08,
|
428 |
+
"loss": 0.7154,
|
429 |
+
"step": 600
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 9.688,
|
433 |
+
"grad_norm": 2.2390174865722656,
|
434 |
+
"learning_rate": 2.2813853199292745e-08,
|
435 |
+
"loss": 0.7047,
|
436 |
+
"step": 610
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 9.848,
|
440 |
+
"grad_norm": 2.2094919681549072,
|
441 |
+
"learning_rate": 6.339525519594159e-10,
|
442 |
+
"loss": 0.7091,
|
443 |
+
"step": 620
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 9.848,
|
447 |
+
"step": 620,
|
448 |
+
"total_flos": 2.117785669819433e+17,
|
449 |
+
"train_loss": 1.5235166057463616,
|
450 |
+
"train_runtime": 30234.6635,
|
451 |
+
"train_samples_per_second": 0.661,
|
452 |
+
"train_steps_per_second": 0.021
|
453 |
}
|
454 |
],
|
455 |
"logging_steps": 10,
|
456 |
+
"max_steps": 620,
|
457 |
"num_input_tokens_seen": 0,
|
458 |
+
"num_train_epochs": 10,
|
459 |
"save_steps": 1000,
|
460 |
"stateful_callbacks": {
|
461 |
"TrainerControl": {
|
|
|
469 |
"attributes": {}
|
470 |
}
|
471 |
},
|
472 |
+
"total_flos": 2.117785669819433e+17,
|
473 |
"train_batch_size": 4,
|
474 |
"trial_name": null,
|
475 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc68d428446e7b26c93265364a77e73cf5e5fd379067282b28ea225efb2cb018
|
3 |
size 5688
|