AlekseyKorshuk commited on
Commit
6d4515e
1 Parent(s): 144665e

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/kanye-west
5
+ tags:
6
+ - huggingartists
7
+ - lyrics
8
+ - lm-head
9
+ - causal-lm
10
+ widget:
11
+ - text: "I am"
12
+ ---
13
+
14
+ <div class="inline-flex flex-col" style="line-height: 1.5;">
15
+ <div class="flex">
16
+ <div
17
+ style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/cde6b08fe936280fe2b7d639703ffe36.459x459x1.png&#39;)">
18
+ </div>
19
+ </div>
20
+ <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
21
+ <div style="text-align: center; font-size: 16px; font-weight: 800">Kanye West</div>
22
+ <a href="https://genius.com/artists/kanye-west">
23
+ <div style="text-align: center; font-size: 14px;">@kanye-west</div>
24
+ </a>
25
+ </div>
26
+
27
+ I was made with [huggingartists](https://github.com/AlekseyKorshuk/huggingartists).
28
+
29
+ Create your own bot based on your favorite artist with [the demo](https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb)!
30
+
31
+ ## How does it work?
32
+
33
+ To understand how the model was developed, check the [W&B report](https://wandb.ai/huggingartists/huggingartists/reportlist).
34
+
35
+ ## Training data
36
+
37
+ The model was trained on lyrics from Kanye West.
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/kanye-west).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/kanye-west")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1nriijf4/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
49
+
50
+ ## Training procedure
51
+
52
+ The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Kanye West's lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2qxzz0h9) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2qxzz0h9/artifacts) is logged and versioned.
57
+
58
+ ## How to use
59
+
60
+ You can use this model directly with a pipeline for text generation:
61
+
62
+ ```python
63
+ from transformers import pipeline
64
+ generator = pipeline('text-generation',
65
+ model='huggingartists/kanye-west')
66
+ generator("I am", num_return_sequences=5)
67
+ ```
68
+
69
+ Or with Transformers library:
70
+
71
+ ```python
72
+ from transformers import AutoTokenizer, AutoModelWithLMHead
73
+
74
+ tokenizer = AutoTokenizer.from_pretrained("huggingartists/kanye-west")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/kanye-west")
77
+ ```
78
+
79
+ ## Limitations and bias
80
+
81
+ The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
82
+
83
+ In addition, the data present in the user's tweets further affects the text generated by the model.
84
+
85
+ ## About
86
+
87
+ *Built by Aleksey Korshuk*
88
+
89
+ [![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)
90
+
91
+ [![Follow](https://img.shields.io/twitter/follow/alekseykorshuk?style=social)](https://twitter.com/intent/follow?screen_name=alekseykorshuk)
92
+
93
+ [![Follow](https://img.shields.io/badge/dynamic/json?color=blue&label=Telegram%20Channel&query=%24.result&url=https%3A%2F%2Fapi.telegram.org%2Fbot1929545866%3AAAFGhV-KKnegEcLiyYJxsc4zV6C-bdPEBtQ%2FgetChatMemberCount%3Fchat_id%3D-1001253621662&style=social&logo=telegram)](https://t.me/joinchat/_CQ04KjcJ-4yZTky)
94
+
95
+ For more details, visit the project repository.
96
+
97
+ [![GitHub stars](https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social)](https://github.com/AlekseyKorshuk/huggingartists)
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 200,
32
+ "min_length": 100,
33
+ "temperature": 1.0,
34
+ "top_p": 0.95
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.10.2",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 3.426886558532715, "eval_runtime": 40.4126, "eval_samples_per_second": 22.072, "eval_steps_per_second": 2.771, "epoch": 1.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c397b32109b8c9119efbf9198333a04c7d3dc1d3635998f782cd23b936c4abe
3
+ size 497764120
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bc79c6c9f8fedb48a4ff5a95bad64b932f7dd5ff39c66b2aa3cfabfab436064
3
+ size 995604017
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3301b1feedf6fe9d822b04f8e9f8ed43f82e257ba739185c7687f7fe4b89008c
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bab3cfadfa486b6524b9320b4f4edb68d19a2ba31da2016e6b8447dd915fd53
3
+ size 14567
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:832488a71ca6e750947bd414fedb36c21eabb4cec011e1c50883c6f2174b85ee
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,660 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.426886558532715,
3
+ "best_model_checkpoint": "output/kanye-west/checkpoint-532",
4
+ "epoch": 1.0,
5
+ "global_step": 532,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 0.00013717009945820184,
13
+ "loss": 4.0869,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 0.0001370804238981834,
19
+ "loss": 3.916,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 0.00013693105149335086,
25
+ "loss": 3.8652,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.04,
30
+ "learning_rate": 0.00013672211245699381,
31
+ "loss": 3.7385,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.05,
36
+ "learning_rate": 0.0001364537889287738,
37
+ "loss": 3.9589,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.06,
42
+ "learning_rate": 0.0001361263148159465,
43
+ "loss": 3.7062,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.07,
48
+ "learning_rate": 0.0001357399755894565,
49
+ "loss": 3.7812,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.08,
54
+ "learning_rate": 0.00013529510803508195,
55
+ "loss": 3.7942,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.08,
60
+ "learning_rate": 0.00013479209995984626,
61
+ "loss": 3.5225,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.09,
66
+ "learning_rate": 0.0001342313898539529,
67
+ "loss": 3.5656,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.1,
72
+ "learning_rate": 0.00013361346650853767,
73
+ "loss": 3.6263,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.11,
78
+ "learning_rate": 0.0001329388685895719,
79
+ "loss": 3.4553,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.12,
84
+ "learning_rate": 0.0001322081841682881,
85
+ "loss": 3.5207,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.13,
90
+ "learning_rate": 0.00013142205020853694,
91
+ "loss": 3.6126,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.14,
96
+ "learning_rate": 0.0001305811520115232,
97
+ "loss": 3.7414,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.15,
102
+ "learning_rate": 0.0001296862226184039,
103
+ "loss": 3.7092,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.16,
108
+ "learning_rate": 0.0001287380421712702,
109
+ "loss": 3.6186,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.17,
114
+ "learning_rate": 0.0001277374372330694,
115
+ "loss": 3.5288,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.18,
120
+ "learning_rate": 0.00012668528006706028,
121
+ "loss": 3.6937,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.19,
126
+ "learning_rate": 0.0001255824878764301,
127
+ "loss": 3.4367,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.2,
132
+ "learning_rate": 0.00012443002200473538,
133
+ "loss": 3.6998,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.21,
138
+ "learning_rate": 0.0001232288870978644,
139
+ "loss": 3.6457,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.22,
144
+ "learning_rate": 0.00012198013022825123,
145
+ "loss": 3.7173,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.23,
150
+ "learning_rate": 0.00012068483998210507,
151
+ "loss": 3.6357,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.23,
156
+ "learning_rate": 0.00011934414551045056,
157
+ "loss": 3.5173,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.24,
162
+ "learning_rate": 0.00011795921554480633,
163
+ "loss": 3.5689,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.25,
168
+ "learning_rate": 0.00011653125737835967,
169
+ "loss": 3.7171,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.26,
174
+ "learning_rate": 0.00011506151581352585,
175
+ "loss": 3.5809,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.27,
180
+ "learning_rate": 0.00011355127207680896,
181
+ "loss": 3.6263,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.28,
186
+ "learning_rate": 0.0001120018427019109,
187
+ "loss": 3.2874,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.29,
192
+ "learning_rate": 0.00011041457838206164,
193
+ "loss": 3.5598,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.3,
198
+ "learning_rate": 0.00010879086279257143,
199
+ "loss": 3.4501,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.31,
204
+ "learning_rate": 0.00010713211138463122,
205
+ "loss": 3.5461,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.32,
210
+ "learning_rate": 0.00010543977015141323,
211
+ "loss": 3.7201,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.33,
216
+ "learning_rate": 0.00010371531436754662,
217
+ "loss": 3.5397,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.34,
222
+ "learning_rate": 0.0001019602473030677,
223
+ "loss": 3.4675,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 0.35,
228
+ "learning_rate": 0.00010017609891296537,
229
+ "loss": 3.5239,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 0.36,
234
+ "learning_rate": 9.836442450346448e-05,
235
+ "loss": 3.7958,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 0.37,
240
+ "learning_rate": 9.652680337620956e-05,
241
+ "loss": 3.4768,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 0.38,
246
+ "learning_rate": 9.466483745153069e-05,
247
+ "loss": 3.743,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 0.39,
252
+ "learning_rate": 9.278014987199233e-05,
253
+ "loss": 3.4125,
254
+ "step": 205
255
+ },
256
+ {
257
+ "epoch": 0.39,
258
+ "learning_rate": 9.08743835874413e-05,
259
+ "loss": 3.4941,
260
+ "step": 210
261
+ },
262
+ {
263
+ "epoch": 0.4,
264
+ "learning_rate": 8.894919992278866e-05,
265
+ "loss": 3.501,
266
+ "step": 215
267
+ },
268
+ {
269
+ "epoch": 0.41,
270
+ "learning_rate": 8.700627712977306e-05,
271
+ "loss": 3.5539,
272
+ "step": 220
273
+ },
274
+ {
275
+ "epoch": 0.42,
276
+ "learning_rate": 8.50473089239683e-05,
277
+ "loss": 3.6408,
278
+ "step": 225
279
+ },
280
+ {
281
+ "epoch": 0.43,
282
+ "learning_rate": 8.307400300831083e-05,
283
+ "loss": 3.4931,
284
+ "step": 230
285
+ },
286
+ {
287
+ "epoch": 0.44,
288
+ "learning_rate": 8.108807958443359e-05,
289
+ "loss": 3.5534,
290
+ "step": 235
291
+ },
292
+ {
293
+ "epoch": 0.45,
294
+ "learning_rate": 7.909126985310467e-05,
295
+ "loss": 3.4332,
296
+ "step": 240
297
+ },
298
+ {
299
+ "epoch": 0.46,
300
+ "learning_rate": 7.708531450507727e-05,
301
+ "loss": 3.3946,
302
+ "step": 245
303
+ },
304
+ {
305
+ "epoch": 0.47,
306
+ "learning_rate": 7.507196220366703e-05,
307
+ "loss": 3.5149,
308
+ "step": 250
309
+ },
310
+ {
311
+ "epoch": 0.48,
312
+ "learning_rate": 7.305296806037965e-05,
313
+ "loss": 3.5828,
314
+ "step": 255
315
+ },
316
+ {
317
+ "epoch": 0.49,
318
+ "learning_rate": 7.10300921049169e-05,
319
+ "loss": 3.5274,
320
+ "step": 260
321
+ },
322
+ {
323
+ "epoch": 0.5,
324
+ "learning_rate": 6.900509775089564e-05,
325
+ "loss": 3.5936,
326
+ "step": 265
327
+ },
328
+ {
329
+ "epoch": 0.51,
330
+ "learning_rate": 6.697975025861685e-05,
331
+ "loss": 3.75,
332
+ "step": 270
333
+ },
334
+ {
335
+ "epoch": 0.52,
336
+ "learning_rate": 6.495581519622486e-05,
337
+ "loss": 3.5977,
338
+ "step": 275
339
+ },
340
+ {
341
+ "epoch": 0.53,
342
+ "learning_rate": 6.293505690059801e-05,
343
+ "loss": 3.5072,
344
+ "step": 280
345
+ },
346
+ {
347
+ "epoch": 0.54,
348
+ "learning_rate": 6.0919236939313083e-05,
349
+ "loss": 3.402,
350
+ "step": 285
351
+ },
352
+ {
353
+ "epoch": 0.55,
354
+ "learning_rate": 5.8910112575023444e-05,
355
+ "loss": 3.4915,
356
+ "step": 290
357
+ },
358
+ {
359
+ "epoch": 0.55,
360
+ "learning_rate": 5.690943523359007e-05,
361
+ "loss": 3.428,
362
+ "step": 295
363
+ },
364
+ {
365
+ "epoch": 0.56,
366
+ "learning_rate": 5.4918948977300765e-05,
367
+ "loss": 3.4624,
368
+ "step": 300
369
+ },
370
+ {
371
+ "epoch": 0.57,
372
+ "learning_rate": 5.294038898450848e-05,
373
+ "loss": 3.5907,
374
+ "step": 305
375
+ },
376
+ {
377
+ "epoch": 0.58,
378
+ "learning_rate": 5.097548003701393e-05,
379
+ "loss": 3.3823,
380
+ "step": 310
381
+ },
382
+ {
383
+ "epoch": 0.59,
384
+ "learning_rate": 4.902593501651139e-05,
385
+ "loss": 3.392,
386
+ "step": 315
387
+ },
388
+ {
389
+ "epoch": 0.6,
390
+ "learning_rate": 4.709345341140823e-05,
391
+ "loss": 3.5123,
392
+ "step": 320
393
+ },
394
+ {
395
+ "epoch": 0.61,
396
+ "learning_rate": 4.517971983531982e-05,
397
+ "loss": 3.3342,
398
+ "step": 325
399
+ },
400
+ {
401
+ "epoch": 0.62,
402
+ "learning_rate": 4.3286402558531396e-05,
403
+ "loss": 3.3545,
404
+ "step": 330
405
+ },
406
+ {
407
+ "epoch": 0.63,
408
+ "learning_rate": 4.141515205370683e-05,
409
+ "loss": 3.4315,
410
+ "step": 335
411
+ },
412
+ {
413
+ "epoch": 0.64,
414
+ "learning_rate": 3.956759955711245e-05,
415
+ "loss": 3.3875,
416
+ "step": 340
417
+ },
418
+ {
419
+ "epoch": 0.65,
420
+ "learning_rate": 3.7745355646609715e-05,
421
+ "loss": 3.5645,
422
+ "step": 345
423
+ },
424
+ {
425
+ "epoch": 0.66,
426
+ "learning_rate": 3.5950008837656755e-05,
427
+ "loss": 3.6196,
428
+ "step": 350
429
+ },
430
+ {
431
+ "epoch": 0.67,
432
+ "learning_rate": 3.418312419854227e-05,
433
+ "loss": 3.3208,
434
+ "step": 355
435
+ },
436
+ {
437
+ "epoch": 0.68,
438
+ "learning_rate": 3.244624198605935e-05,
439
+ "loss": 3.4232,
440
+ "step": 360
441
+ },
442
+ {
443
+ "epoch": 0.69,
444
+ "learning_rate": 3.0740876302808455e-05,
445
+ "loss": 3.3791,
446
+ "step": 365
447
+ },
448
+ {
449
+ "epoch": 0.7,
450
+ "learning_rate": 2.9068513777299503e-05,
451
+ "loss": 3.4745,
452
+ "step": 370
453
+ },
454
+ {
455
+ "epoch": 0.7,
456
+ "learning_rate": 2.7430612268004742e-05,
457
+ "loss": 3.3075,
458
+ "step": 375
459
+ },
460
+ {
461
+ "epoch": 0.71,
462
+ "learning_rate": 2.5828599592490882e-05,
463
+ "loss": 3.4197,
464
+ "step": 380
465
+ },
466
+ {
467
+ "epoch": 0.72,
468
+ "learning_rate": 2.4263872282739445e-05,
469
+ "loss": 3.4358,
470
+ "step": 385
471
+ },
472
+ {
473
+ "epoch": 0.73,
474
+ "learning_rate": 2.2737794367739613e-05,
475
+ "loss": 3.6132,
476
+ "step": 390
477
+ },
478
+ {
479
+ "epoch": 0.74,
480
+ "learning_rate": 2.1251696184415103e-05,
481
+ "loss": 3.4919,
482
+ "step": 395
483
+ },
484
+ {
485
+ "epoch": 0.75,
486
+ "learning_rate": 1.980687321792179e-05,
487
+ "loss": 3.6213,
488
+ "step": 400
489
+ },
490
+ {
491
+ "epoch": 0.76,
492
+ "learning_rate": 1.8404584972326772e-05,
493
+ "loss": 3.3808,
494
+ "step": 405
495
+ },
496
+ {
497
+ "epoch": 0.77,
498
+ "learning_rate": 1.704605387265335e-05,
499
+ "loss": 3.4937,
500
+ "step": 410
501
+ },
502
+ {
503
+ "epoch": 0.78,
504
+ "learning_rate": 1.573246419924937e-05,
505
+ "loss": 3.5387,
506
+ "step": 415
507
+ },
508
+ {
509
+ "epoch": 0.79,
510
+ "learning_rate": 1.4464961055407408e-05,
511
+ "loss": 3.5004,
512
+ "step": 420
513
+ },
514
+ {
515
+ "epoch": 0.8,
516
+ "learning_rate": 1.3244649369137107e-05,
517
+ "loss": 3.2293,
518
+ "step": 425
519
+ },
520
+ {
521
+ "epoch": 0.81,
522
+ "learning_rate": 1.2072592929959826e-05,
523
+ "loss": 3.4326,
524
+ "step": 430
525
+ },
526
+ {
527
+ "epoch": 0.82,
528
+ "learning_rate": 1.0949813461565069e-05,
529
+ "loss": 3.3648,
530
+ "step": 435
531
+ },
532
+ {
533
+ "epoch": 0.83,
534
+ "learning_rate": 9.87728973113722e-06,
535
+ "loss": 3.5226,
536
+ "step": 440
537
+ },
538
+ {
539
+ "epoch": 0.84,
540
+ "learning_rate": 8.855956696129068e-06,
541
+ "loss": 3.464,
542
+ "step": 445
543
+ },
544
+ {
545
+ "epoch": 0.85,
546
+ "learning_rate": 7.88670468922587e-06,
547
+ "loss": 3.3838,
548
+ "step": 450
549
+ },
550
+ {
551
+ "epoch": 0.86,
552
+ "learning_rate": 6.97037864221025e-06,
553
+ "loss": 3.6019,
554
+ "step": 455
555
+ },
556
+ {
557
+ "epoch": 0.86,
558
+ "learning_rate": 6.107777349404974e-06,
559
+ "loss": 3.3959,
560
+ "step": 460
561
+ },
562
+ {
563
+ "epoch": 0.87,
564
+ "learning_rate": 5.299652771335096e-06,
565
+ "loss": 3.2737,
566
+ "step": 465
567
+ },
568
+ {
569
+ "epoch": 0.88,
570
+ "learning_rate": 4.546709379217107e-06,
571
+ "loss": 3.5271,
572
+ "step": 470
573
+ },
574
+ {
575
+ "epoch": 0.89,
576
+ "learning_rate": 3.849603540845984e-06,
577
+ "loss": 3.1793,
578
+ "step": 475
579
+ },
580
+ {
581
+ "epoch": 0.9,
582
+ "learning_rate": 3.2089429484158363e-06,
583
+ "loss": 3.5368,
584
+ "step": 480
585
+ },
586
+ {
587
+ "epoch": 0.91,
588
+ "learning_rate": 2.625286088772771e-06,
589
+ "loss": 3.4441,
590
+ "step": 485
591
+ },
592
+ {
593
+ "epoch": 0.92,
594
+ "learning_rate": 2.0991417565619363e-06,
595
+ "loss": 3.3483,
596
+ "step": 490
597
+ },
598
+ {
599
+ "epoch": 0.93,
600
+ "learning_rate": 1.6309686106928596e-06,
601
+ "loss": 3.5513,
602
+ "step": 495
603
+ },
604
+ {
605
+ "epoch": 0.94,
606
+ "learning_rate": 1.221174774510045e-06,
607
+ "loss": 3.3951,
608
+ "step": 500
609
+ },
610
+ {
611
+ "epoch": 0.95,
612
+ "learning_rate": 8.701174800172293e-07,
613
+ "loss": 3.5312,
614
+ "step": 505
615
+ },
616
+ {
617
+ "epoch": 0.96,
618
+ "learning_rate": 5.78102756465344e-07,
619
+ "loss": 3.4318,
620
+ "step": 510
621
+ },
622
+ {
623
+ "epoch": 0.97,
624
+ "learning_rate": 3.45385163575888e-07,
625
+ "loss": 3.4111,
626
+ "step": 515
627
+ },
628
+ {
629
+ "epoch": 0.98,
630
+ "learning_rate": 1.7216756963205766e-07,
631
+ "loss": 3.2725,
632
+ "step": 520
633
+ },
634
+ {
635
+ "epoch": 0.99,
636
+ "learning_rate": 5.860097463115006e-08,
637
+ "loss": 3.6447,
638
+ "step": 525
639
+ },
640
+ {
641
+ "epoch": 1.0,
642
+ "learning_rate": 4.784378652498966e-09,
643
+ "loss": 3.4154,
644
+ "step": 530
645
+ },
646
+ {
647
+ "epoch": 1.0,
648
+ "eval_loss": 3.426886558532715,
649
+ "eval_runtime": 40.4727,
650
+ "eval_samples_per_second": 22.04,
651
+ "eval_steps_per_second": 2.767,
652
+ "step": 532
653
+ }
654
+ ],
655
+ "max_steps": 532,
656
+ "num_train_epochs": 1,
657
+ "total_flos": 555637506048000.0,
658
+ "trial_name": null,
659
+ "trial_params": null
660
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e4834c8ab0301a41d1c08550c723db54a908586d28b697502acc43205b130e
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff