Upload 12 files
Browse files- CooAI/config.json +39 -0
- CooAI/generation_config.json +6 -0
- CooAI/merges.txt +0 -0
- CooAI/model.safetensors +3 -0
- CooAI/optimizer.pt +3 -0
- CooAI/rng_state.pth +3 -0
- CooAI/scheduler.pt +3 -0
- CooAI/tokenizer.json +0 -0
- CooAI/tokenizer_config.json +1 -0
- CooAI/trainer_state.json +313 -0
- CooAI/training_args.bin +3 -0
- CooAI/vocab.json +0 -0
CooAI/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.41.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
CooAI/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
+
}
|
CooAI/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
CooAI/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:206d9cc0a5589d896e2bf2f61449f2e1178268a10e7d8736ba8dec713d08ffec
|
3 |
+
size 497774208
|
CooAI/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:525d2d855fbbadd01f7dd89aa810b59c3d79e2a61071b24d30588a57c96d3173
|
3 |
+
size 995638202
|
CooAI/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:217c766550b5552e73eeaff3774abe464ac268946bba2d2704c6a70eb56d8a1b
|
3 |
+
size 13990
|
CooAI/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4a04205f7cdd1cc7a9ab0f3d12f4fc10cf89be035061f167696baaedb2e6729
|
3 |
+
size 1064
|
CooAI/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
CooAI/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model_max_length": 1024}
|
CooAI/trainer_state.json
ADDED
@@ -0,0 +1,313 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.184598580010923,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 20000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.054614964500273075,
|
13 |
+
"grad_norm": 4.814465522766113,
|
14 |
+
"learning_rate": 4.908975059166212e-05,
|
15 |
+
"loss": 3.4784,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.10922992900054615,
|
20 |
+
"grad_norm": 3.5959620475769043,
|
21 |
+
"learning_rate": 4.817950118332423e-05,
|
22 |
+
"loss": 3.2029,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1638448935008192,
|
27 |
+
"grad_norm": 3.0341761112213135,
|
28 |
+
"learning_rate": 4.726925177498635e-05,
|
29 |
+
"loss": 3.0879,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2184598580010923,
|
34 |
+
"grad_norm": 2.8636319637298584,
|
35 |
+
"learning_rate": 4.6359002366648464e-05,
|
36 |
+
"loss": 3.0768,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2730748225013654,
|
41 |
+
"grad_norm": 3.1025149822235107,
|
42 |
+
"learning_rate": 4.544875295831058e-05,
|
43 |
+
"loss": 3.0656,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3276897870016384,
|
48 |
+
"grad_norm": 2.7527127265930176,
|
49 |
+
"learning_rate": 4.4538503549972694e-05,
|
50 |
+
"loss": 3.0202,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.3823047515019115,
|
55 |
+
"grad_norm": 2.2277674674987793,
|
56 |
+
"learning_rate": 4.362825414163481e-05,
|
57 |
+
"loss": 2.9937,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.4369197160021846,
|
62 |
+
"grad_norm": 2.731010913848877,
|
63 |
+
"learning_rate": 4.2718004733296925e-05,
|
64 |
+
"loss": 2.94,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.4915346805024577,
|
69 |
+
"grad_norm": 2.5954668521881104,
|
70 |
+
"learning_rate": 4.180775532495904e-05,
|
71 |
+
"loss": 2.9326,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.5461496450027308,
|
76 |
+
"grad_norm": 2.3241865634918213,
|
77 |
+
"learning_rate": 4.0897505916621156e-05,
|
78 |
+
"loss": 2.9252,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6007646095030038,
|
83 |
+
"grad_norm": 2.384614944458008,
|
84 |
+
"learning_rate": 3.998725650828327e-05,
|
85 |
+
"loss": 2.9063,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.6553795740032768,
|
90 |
+
"grad_norm": 2.5207371711730957,
|
91 |
+
"learning_rate": 3.907700709994539e-05,
|
92 |
+
"loss": 2.9557,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.70999453850355,
|
97 |
+
"grad_norm": 2.194120407104492,
|
98 |
+
"learning_rate": 3.81667576916075e-05,
|
99 |
+
"loss": 2.8886,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.764609503003823,
|
104 |
+
"grad_norm": 2.1685619354248047,
|
105 |
+
"learning_rate": 3.725650828326962e-05,
|
106 |
+
"loss": 2.8491,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.8192244675040962,
|
111 |
+
"grad_norm": 2.044222593307495,
|
112 |
+
"learning_rate": 3.634625887493173e-05,
|
113 |
+
"loss": 2.8707,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.8738394320043692,
|
118 |
+
"grad_norm": 2.3557591438293457,
|
119 |
+
"learning_rate": 3.543600946659385e-05,
|
120 |
+
"loss": 2.8858,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.9284543965046422,
|
125 |
+
"grad_norm": 1.9291545152664185,
|
126 |
+
"learning_rate": 3.452576005825596e-05,
|
127 |
+
"loss": 2.8572,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.9830693610049154,
|
132 |
+
"grad_norm": 2.1735591888427734,
|
133 |
+
"learning_rate": 3.361551064991808e-05,
|
134 |
+
"loss": 2.8521,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.0376843255051884,
|
139 |
+
"grad_norm": 2.6716625690460205,
|
140 |
+
"learning_rate": 3.2705261241580193e-05,
|
141 |
+
"loss": 2.7596,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.0922992900054616,
|
146 |
+
"grad_norm": 1.5268744230270386,
|
147 |
+
"learning_rate": 3.179501183324231e-05,
|
148 |
+
"loss": 2.7778,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.1469142545057345,
|
153 |
+
"grad_norm": 2.428257942199707,
|
154 |
+
"learning_rate": 3.0884762424904424e-05,
|
155 |
+
"loss": 2.7509,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.2015292190060076,
|
160 |
+
"grad_norm": 1.7924199104309082,
|
161 |
+
"learning_rate": 2.9974513016566543e-05,
|
162 |
+
"loss": 2.7447,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.2561441835062808,
|
167 |
+
"grad_norm": 2.095064640045166,
|
168 |
+
"learning_rate": 2.9064263608228655e-05,
|
169 |
+
"loss": 2.7205,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.3107591480065537,
|
174 |
+
"grad_norm": 2.2335567474365234,
|
175 |
+
"learning_rate": 2.815401419989077e-05,
|
176 |
+
"loss": 2.7687,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.3653741125068268,
|
181 |
+
"grad_norm": 2.109407901763916,
|
182 |
+
"learning_rate": 2.724376479155289e-05,
|
183 |
+
"loss": 2.7702,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.4199890770071,
|
188 |
+
"grad_norm": 2.305004596710205,
|
189 |
+
"learning_rate": 2.6333515383215e-05,
|
190 |
+
"loss": 2.7239,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.474604041507373,
|
195 |
+
"grad_norm": 1.714770793914795,
|
196 |
+
"learning_rate": 2.542326597487712e-05,
|
197 |
+
"loss": 2.7505,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.529219006007646,
|
202 |
+
"grad_norm": 2.0778112411499023,
|
203 |
+
"learning_rate": 2.451301656653923e-05,
|
204 |
+
"loss": 2.763,
|
205 |
+
"step": 14000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.5838339705079192,
|
209 |
+
"grad_norm": 2.4014670848846436,
|
210 |
+
"learning_rate": 2.3602767158201347e-05,
|
211 |
+
"loss": 2.7492,
|
212 |
+
"step": 14500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.638448935008192,
|
216 |
+
"grad_norm": 2.163849115371704,
|
217 |
+
"learning_rate": 2.2692517749863465e-05,
|
218 |
+
"loss": 2.7532,
|
219 |
+
"step": 15000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.6930638995084655,
|
223 |
+
"grad_norm": 2.1930949687957764,
|
224 |
+
"learning_rate": 2.178226834152558e-05,
|
225 |
+
"loss": 2.7308,
|
226 |
+
"step": 15500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.7476788640087384,
|
230 |
+
"grad_norm": 2.545933723449707,
|
231 |
+
"learning_rate": 2.0872018933187696e-05,
|
232 |
+
"loss": 2.729,
|
233 |
+
"step": 16000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.8022938285090113,
|
237 |
+
"grad_norm": 2.044917345046997,
|
238 |
+
"learning_rate": 1.996176952484981e-05,
|
239 |
+
"loss": 2.7375,
|
240 |
+
"step": 16500
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.8569087930092847,
|
244 |
+
"grad_norm": 2.2756001949310303,
|
245 |
+
"learning_rate": 1.9051520116511927e-05,
|
246 |
+
"loss": 2.7348,
|
247 |
+
"step": 17000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.9115237575095576,
|
251 |
+
"grad_norm": 2.0774707794189453,
|
252 |
+
"learning_rate": 1.8141270708174042e-05,
|
253 |
+
"loss": 2.7359,
|
254 |
+
"step": 17500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.9661387220098305,
|
258 |
+
"grad_norm": 2.198192834854126,
|
259 |
+
"learning_rate": 1.7231021299836157e-05,
|
260 |
+
"loss": 2.7389,
|
261 |
+
"step": 18000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.020753686510104,
|
265 |
+
"grad_norm": 2.573255777359009,
|
266 |
+
"learning_rate": 1.6320771891498273e-05,
|
267 |
+
"loss": 2.6663,
|
268 |
+
"step": 18500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 2.075368651010377,
|
272 |
+
"grad_norm": 2.2701830863952637,
|
273 |
+
"learning_rate": 1.5410522483160388e-05,
|
274 |
+
"loss": 2.6761,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 2.1299836155106497,
|
279 |
+
"grad_norm": 2.479576826095581,
|
280 |
+
"learning_rate": 1.4500273074822501e-05,
|
281 |
+
"loss": 2.6573,
|
282 |
+
"step": 19500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 2.184598580010923,
|
286 |
+
"grad_norm": 2.408147096633911,
|
287 |
+
"learning_rate": 1.3590023666484617e-05,
|
288 |
+
"loss": 2.6066,
|
289 |
+
"step": 20000
|
290 |
+
}
|
291 |
+
],
|
292 |
+
"logging_steps": 500,
|
293 |
+
"max_steps": 27465,
|
294 |
+
"num_input_tokens_seen": 0,
|
295 |
+
"num_train_epochs": 3,
|
296 |
+
"save_steps": 10000,
|
297 |
+
"stateful_callbacks": {
|
298 |
+
"TrainerControl": {
|
299 |
+
"args": {
|
300 |
+
"should_epoch_stop": false,
|
301 |
+
"should_evaluate": false,
|
302 |
+
"should_log": false,
|
303 |
+
"should_save": true,
|
304 |
+
"should_training_stop": false
|
305 |
+
},
|
306 |
+
"attributes": {}
|
307 |
+
}
|
308 |
+
},
|
309 |
+
"total_flos": 5225579347968000.0,
|
310 |
+
"train_batch_size": 4,
|
311 |
+
"trial_name": null,
|
312 |
+
"trial_params": null
|
313 |
+
}
|
CooAI/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc9294d163ea016c83e83c89cdc42e6dfb60d6571fea765a1f45b3dacc76f349
|
3 |
+
size 5048
|
CooAI/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|