AlekseyKorshuk commited on
Commit
1303f6e
1 Parent(s): 9dc5638

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/drake
5
+ tags:
6
+ - huggingartists
7
+ - lyrics
8
+ widget:
9
+ - text: "I am"
10
+ ---
11
+
12
+ <div class="inline-flex flex-col" style="line-height: 1.5;">
13
+ <div class="flex">
14
+ <div
15
+ 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/c6b5142a09ff5bd361d0f42a55692edc.1000x1000x1.jpg&#39;)">
16
+ </div>
17
+ </div>
18
+ <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
19
+ <div style="text-align: center; font-size: 16px; font-weight: 800">Drake</div>
20
+ <a href="https://genius.com/artists/drake">
21
+ <div style="text-align: center; font-size: 14px;">@drake</div>
22
+ </a>
23
+ </div>
24
+
25
+ I was made with [huggingartists](https://github.com/AlekseyKorshuk/huggingartists).
26
+
27
+ 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)!
28
+
29
+ ## How does it work?
30
+
31
+ To understand how the model was developed, check the [W&B report](https://wandb.ai/huggingartists/huggingartists/reportlist).
32
+
33
+ ## Training data
34
+
35
+ The model was trained on lyrics from Drake.
36
+
37
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/drake).
38
+ And can be used with:
39
+
40
+ ```python
41
+ from datasets import load_dataset
42
+
43
+ dataset = load_dataset("huggingartists/drake")
44
+ ```
45
+
46
+ Or with Transformers library:
47
+
48
+ ```python
49
+ from transformers import AutoTokenizer, AutoModelWithLMHead
50
+
51
+ tokenizer = AutoTokenizer.from_pretrained("huggingartists/drake")
52
+
53
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/drake")
54
+ ```
55
+
56
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1ba7t9q0/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
57
+
58
+ ## Training procedure
59
+
60
+ The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Drake's lyrics.
61
+
62
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/18yhidb2) for full transparency and reproducibility.
63
+
64
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/18yhidb2/artifacts) is logged and versioned.
65
+
66
+ ## How to use
67
+
68
+ You can use this model directly with a pipeline for text generation:
69
+
70
+ ```python
71
+ from transformers import pipeline
72
+ generator = pipeline('text-generation',
73
+ model='huggingartists/drake')
74
+ generator("I am", num_return_sequences=5)
75
+ ```
76
+
77
+ ## Limitations and bias
78
+
79
+ The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
80
+
81
+ In addition, the data present in the user's tweets further affects the text generated by the model.
82
+
83
+ ## About
84
+
85
+ *Built by Aleksey Korshuk*
86
+
87
+ [![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)
88
+
89
+ For more details, visit the project repository.
90
+
91
+ [![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": "4.9.1",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
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:f54b613b898ec9cd602b10294cad4372affedb9070359bf8fb1e1efc0c38351b
3
+ size 995604017
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d646844d7a1967fa54609f85a5452b8eae50cafd2f88c1e934be317c5f71252
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c479098b6ff1a7d6e1a01f9b8d8a54011a8cc009f5aa71d8d828ce9e600a222
3
+ size 14567
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dab3de057a89d68db2661a52fbf111edc97698719020db0127718fdc9badb3d
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 +1,478 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 386,
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": 0.0001371432064088578,
13
+ "loss": 4.0588,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 0.00013697291967368176,
19
+ "loss": 3.874,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 0.000136689421753516,
25
+ "loss": 3.7354,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.05,
30
+ "learning_rate": 0.0001362931820613334,
31
+ "loss": 3.678,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.06,
36
+ "learning_rate": 0.00013578485668678617,
37
+ "loss": 3.4762,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.08,
42
+ "learning_rate": 0.00013516528730985944,
43
+ "loss": 3.9075,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.09,
48
+ "learning_rate": 0.000134435499807226,
49
+ "loss": 3.8826,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.1,
54
+ "learning_rate": 0.00013359670255361022,
55
+ "loss": 3.6832,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.12,
60
+ "learning_rate": 0.00013265028442097337,
61
+ "loss": 3.5663,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.13,
66
+ "learning_rate": 0.00013159781247883373,
67
+ "loss": 3.875,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.14,
72
+ "learning_rate": 0.00013044102939952857,
73
+ "loss": 3.6027,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.16,
78
+ "learning_rate": 0.00012918185057271526,
79
+ "loss": 3.7132,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.17,
84
+ "learning_rate": 0.0001278223609338884,
85
+ "loss": 3.5338,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.18,
90
+ "learning_rate": 0.00012636481151216485,
91
+ "loss": 3.8949,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.19,
96
+ "learning_rate": 0.0001248116157030527,
97
+ "loss": 3.5964,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.21,
102
+ "learning_rate": 0.0001231653452723755,
103
+ "loss": 3.7202,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.22,
108
+ "learning_rate": 0.00012142872609796847,
109
+ "loss": 3.6172,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.23,
114
+ "learning_rate": 0.00011960463365619783,
115
+ "loss": 3.4145,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.25,
120
+ "learning_rate": 0.00011769608826077622,
121
+ "loss": 3.555,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.26,
126
+ "learning_rate": 0.000115706250061758,
127
+ "loss": 3.4485,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.27,
132
+ "learning_rate": 0.00011363841381299484,
133
+ "loss": 3.7157,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.28,
138
+ "learning_rate": 0.000111496003416716,
139
+ "loss": 3.6139,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.3,
144
+ "learning_rate": 0.0001092825662542656,
145
+ "loss": 3.6335,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.31,
150
+ "learning_rate": 0.00010700176731238488,
151
+ "loss": 3.8618,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.32,
156
+ "learning_rate": 0.00010465738311476428,
157
+ "loss": 3.5889,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.34,
162
+ "learning_rate": 0.00010225329546891398,
163
+ "loss": 3.5039,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.35,
168
+ "learning_rate": 9.979348503870657e-05,
169
+ "loss": 3.456,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.36,
174
+ "learning_rate": 9.728202475323418e-05,
175
+ "loss": 3.5593,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.38,
180
+ "learning_rate": 9.472307306289397e-05,
181
+ "loss": 3.6619,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.39,
186
+ "learning_rate": 9.21208670538683e-05,
187
+ "loss": 3.2545,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.4,
192
+ "learning_rate": 8.94797154324004e-05,
193
+ "loss": 3.5664,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.41,
198
+ "learning_rate": 8.680399139048255e-05,
199
+ "loss": 3.6659,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.43,
204
+ "learning_rate": 8.409812536476914e-05,
205
+ "loss": 3.4141,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.44,
210
+ "learning_rate": 8.136659770070481e-05,
211
+ "loss": 3.3853,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.45,
216
+ "learning_rate": 7.86139312340139e-05,
217
+ "loss": 3.5356,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.47,
222
+ "learning_rate": 7.584468380183525e-05,
223
+ "loss": 3.6393,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 0.48,
228
+ "learning_rate": 7.306344069590158e-05,
229
+ "loss": 3.7593,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 0.49,
234
+ "learning_rate": 7.027480707026031e-05,
235
+ "loss": 3.6784,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 0.51,
240
+ "learning_rate": 6.748340031610621e-05,
241
+ "loss": 3.4365,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 0.52,
246
+ "learning_rate": 6.469384241635202e-05,
247
+ "loss": 3.4692,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 0.53,
252
+ "learning_rate": 6.191075229259615e-05,
253
+ "loss": 3.5463,
254
+ "step": 205
255
+ },
256
+ {
257
+ "epoch": 0.54,
258
+ "learning_rate": 5.9138738157159314e-05,
259
+ "loss": 3.4183,
260
+ "step": 210
261
+ },
262
+ {
263
+ "epoch": 0.56,
264
+ "learning_rate": 5.638238988285346e-05,
265
+ "loss": 3.6126,
266
+ "step": 215
267
+ },
268
+ {
269
+ "epoch": 0.57,
270
+ "learning_rate": 5.364627140311692e-05,
271
+ "loss": 3.5828,
272
+ "step": 220
273
+ },
274
+ {
275
+ "epoch": 0.58,
276
+ "learning_rate": 5.093491315510001e-05,
277
+ "loss": 3.4454,
278
+ "step": 225
279
+ },
280
+ {
281
+ "epoch": 0.6,
282
+ "learning_rate": 4.825280457821314e-05,
283
+ "loss": 3.5058,
284
+ "step": 230
285
+ },
286
+ {
287
+ "epoch": 0.61,
288
+ "learning_rate": 4.560438668055879e-05,
289
+ "loss": 3.4436,
290
+ "step": 235
291
+ },
292
+ {
293
+ "epoch": 0.62,
294
+ "learning_rate": 4.299404468555545e-05,
295
+ "loss": 3.3312,
296
+ "step": 240
297
+ },
298
+ {
299
+ "epoch": 0.63,
300
+ "learning_rate": 4.042610077092918e-05,
301
+ "loss": 3.4519,
302
+ "step": 245
303
+ },
304
+ {
305
+ "epoch": 0.65,
306
+ "learning_rate": 3.7904806912095865e-05,
307
+ "loss": 3.2724,
308
+ "step": 250
309
+ },
310
+ {
311
+ "epoch": 0.66,
312
+ "learning_rate": 3.543433784178337e-05,
313
+ "loss": 3.708,
314
+ "step": 255
315
+ },
316
+ {
317
+ "epoch": 0.67,
318
+ "learning_rate": 3.30187841375518e-05,
319
+ "loss": 3.3732,
320
+ "step": 260
321
+ },
322
+ {
323
+ "epoch": 0.69,
324
+ "learning_rate": 3.06621454486565e-05,
325
+ "loss": 3.6682,
326
+ "step": 265
327
+ },
328
+ {
329
+ "epoch": 0.7,
330
+ "learning_rate": 2.8368323873469696e-05,
331
+ "loss": 3.3303,
332
+ "step": 270
333
+ },
334
+ {
335
+ "epoch": 0.71,
336
+ "learning_rate": 2.614111749842566e-05,
337
+ "loss": 3.4287,
338
+ "step": 275
339
+ },
340
+ {
341
+ "epoch": 0.73,
342
+ "learning_rate": 2.39842141091877e-05,
343
+ "loss": 3.4274,
344
+ "step": 280
345
+ },
346
+ {
347
+ "epoch": 0.74,
348
+ "learning_rate": 2.1901185084450396e-05,
349
+ "loss": 3.3246,
350
+ "step": 285
351
+ },
352
+ {
353
+ "epoch": 0.75,
354
+ "learning_rate": 1.9895479482486794e-05,
355
+ "loss": 3.4282,
356
+ "step": 290
357
+ },
358
+ {
359
+ "epoch": 0.76,
360
+ "learning_rate": 1.7970418330233093e-05,
361
+ "loss": 3.2375,
362
+ "step": 295
363
+ },
364
+ {
365
+ "epoch": 0.78,
366
+ "learning_rate": 1.61291891243658e-05,
367
+ "loss": 3.581,
368
+ "step": 300
369
+ },
370
+ {
371
+ "epoch": 0.79,
372
+ "learning_rate": 1.4374840553477238e-05,
373
+ "loss": 3.42,
374
+ "step": 305
375
+ },
376
+ {
377
+ "epoch": 0.8,
378
+ "learning_rate": 1.2710277450088041e-05,
379
+ "loss": 3.4236,
380
+ "step": 310
381
+ },
382
+ {
383
+ "epoch": 0.82,
384
+ "learning_rate": 1.1138255980854819e-05,
385
+ "loss": 3.3657,
386
+ "step": 315
387
+ },
388
+ {
389
+ "epoch": 0.83,
390
+ "learning_rate": 9.661379082937688e-06,
391
+ "loss": 3.1107,
392
+ "step": 320
393
+ },
394
+ {
395
+ "epoch": 0.84,
396
+ "learning_rate": 8.282092154083231e-06,
397
+ "loss": 3.3076,
398
+ "step": 325
399
+ },
400
+ {
401
+ "epoch": 0.85,
402
+ "learning_rate": 7.002679003559785e-06,
403
+ "loss": 3.3086,
404
+ "step": 330
405
+ },
406
+ {
407
+ "epoch": 0.87,
408
+ "learning_rate": 5.825258070649407e-06,
409
+ "loss": 3.3643,
410
+ "step": 335
411
+ },
412
+ {
413
+ "epoch": 0.88,
414
+ "learning_rate": 4.7517789169574735e-06,
415
+ "loss": 3.348,
416
+ "step": 340
417
+ },
418
+ {
419
+ "epoch": 0.89,
420
+ "learning_rate": 3.7840189983485763e-06,
421
+ "loss": 3.391,
422
+ "step": 345
423
+ },
424
+ {
425
+ "epoch": 0.91,
426
+ "learning_rate": 2.9235807218530457e-06,
427
+ "loss": 3.2735,
428
+ "step": 350
429
+ },
430
+ {
431
+ "epoch": 0.92,
432
+ "learning_rate": 2.171888792417796e-06,
433
+ "loss": 3.576,
434
+ "step": 355
435
+ },
436
+ {
437
+ "epoch": 0.93,
438
+ "learning_rate": 1.5301878538942795e-06,
439
+ "loss": 3.2583,
440
+ "step": 360
441
+ },
442
+ {
443
+ "epoch": 0.95,
444
+ "learning_rate": 9.995404281699138e-07,
445
+ "loss": 3.5956,
446
+ "step": 365
447
+ },
448
+ {
449
+ "epoch": 0.96,
450
+ "learning_rate": 5.808251558551173e-07,
451
+ "loss": 3.7098,
452
+ "step": 370
453
+ },
454
+ {
455
+ "epoch": 0.97,
456
+ "learning_rate": 2.7473534143910847e-07,
457
+ "loss": 3.3973,
458
+ "step": 375
459
+ },
460
+ {
461
+ "epoch": 0.98,
462
+ "learning_rate": 8.177780532344056e-08,
463
+ "loss": 3.3842,
464
+ "step": 380
465
+ },
466
+ {
467
+ "epoch": 1.0,
468
+ "learning_rate": 2.2720446338799106e-09,
469
+ "loss": 3.2786,
470
+ "step": 385
471
+ }
472
+ ],
473
+ "max_steps": 386,
474
+ "num_train_epochs": 1,
475
+ "total_flos": 403042959360000.0,
476
+ "trial_name": null,
477
+ "trial_params": null
478
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:781ffb618640ff70dd3baac13df255d8dc426f031550cac003228fcbafce41fc
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff