AlekseyKorshuk commited on
Commit
f1dbedf
1 Parent(s): 9bb7bb4

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/eminem
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/c674178296f3d65792a66f851fbc62fc.900x900x1.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">Eminem</div>
22
+ <a href="https://genius.com/artists/eminem">
23
+ <div style="text-align: center; font-size: 14px;">@eminem</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 Eminem.
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/eminem).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/eminem")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2l695pm1/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 Eminem's lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3pk4ea2u) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3pk4ea2u/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/eminem')
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/eminem")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/eminem")
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": "4.9.2",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 3.7048158645629883, "eval_runtime": 29.3569, "eval_samples_per_second": 22.346, "eval_steps_per_second": 2.793, "epoch": 1.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262ff390844a8a0d15cf1ac5ddf0c0f51bd950f9f01fdb4a18686cbfa1628688
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 sha256:2a9fa7f2a4e7ff45453dae447ffe05636eeee45a087bf41722388a6b4a91a547
3
+ size 995604017
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:820ebbeb7718d17ad5c349804b16925fad394702b9340fb9c1d111edf68f17e9
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91cf577609be35642d017de628b6109e240d8b6435db8740abfe22b6288bf5e
3
+ size 14567
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b44e5cb72f3e614f443e8ef7c3fb3c5f06bbee285da28e31095e8a027e0c62
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 +1,564 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.7048158645629883,
3
+ "best_model_checkpoint": "output/eminem/checkpoint-453",
4
+ "epoch": 1.0,
5
+ "global_step": 453,
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": 0.00013715876234566868,
13
+ "loss": 4.4386,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 0.00013703509896122095,
19
+ "loss": 4.1948,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 0.00013682915852268886,
25
+ "loss": 4.0957,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.04,
30
+ "learning_rate": 0.00013654118862484264,
31
+ "loss": 3.9438,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.06,
36
+ "learning_rate": 0.00013617153548351626,
37
+ "loss": 4.058,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.07,
42
+ "learning_rate": 0.00013572064351936462,
43
+ "loss": 4.0441,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.08,
48
+ "learning_rate": 0.00013518905482355273,
49
+ "loss": 3.872,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.09,
54
+ "learning_rate": 0.00013457740850601892,
55
+ "loss": 4.2427,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.1,
60
+ "learning_rate": 0.00013388643992709594,
61
+ "loss": 4.0466,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.11,
66
+ "learning_rate": 0.0001331169798134139,
67
+ "loss": 3.9197,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.12,
72
+ "learning_rate": 0.00013226995325914744,
73
+ "loss": 4.0498,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.13,
78
+ "learning_rate": 0.00013134637861380834,
79
+ "loss": 3.9624,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.14,
84
+ "learning_rate": 0.0001303473662579206,
85
+ "loss": 3.8491,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.15,
90
+ "learning_rate": 0.00012927411726804995,
91
+ "loss": 3.8877,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.17,
96
+ "learning_rate": 0.00012812792197279278,
97
+ "loss": 3.9778,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.18,
102
+ "learning_rate": 0.00012691015840146053,
103
+ "loss": 3.9312,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.19,
108
+ "learning_rate": 0.00012562229062732468,
109
+ "loss": 3.8452,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.2,
114
+ "learning_rate": 0.00012426586700741422,
115
+ "loss": 3.9473,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.21,
120
+ "learning_rate": 0.00012284251832098172,
121
+ "loss": 4.0293,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.22,
126
+ "learning_rate": 0.00012135395580887633,
127
+ "loss": 3.8128,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.23,
132
+ "learning_rate": 0.00011980196911618039,
133
+ "loss": 4.0833,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.24,
138
+ "learning_rate": 0.0001181884241405837,
139
+ "loss": 3.7779,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.25,
144
+ "learning_rate": 0.00011651526078908192,
145
+ "loss": 3.8247,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.26,
150
+ "learning_rate": 0.00011478449064569633,
151
+ "loss": 3.9986,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.28,
156
+ "learning_rate": 0.00011299819455301873,
157
+ "loss": 4.0396,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.29,
162
+ "learning_rate": 0.0001111585201104895,
163
+ "loss": 3.8924,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.3,
168
+ "learning_rate": 0.000109267679092416,
169
+ "loss": 3.8117,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.31,
174
+ "learning_rate": 0.00010732794478883606,
175
+ "loss": 3.9015,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.32,
180
+ "learning_rate": 0.00010534164927242335,
181
+ "loss": 3.7786,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.33,
186
+ "learning_rate": 0.0001033111805947203,
187
+ "loss": 4.0211,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.34,
192
+ "learning_rate": 0.00010123897991506982,
193
+ "loss": 3.8728,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.35,
198
+ "learning_rate": 9.912753856569734e-05,
199
+ "loss": 3.9266,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.36,
204
+ "learning_rate": 9.697939505647188e-05,
205
+ "loss": 3.9463,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.38,
210
+ "learning_rate": 9.479713202294696e-05,
211
+ "loss": 3.7152,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.39,
216
+ "learning_rate": 9.258337312135107e-05,
217
+ "loss": 3.9496,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.4,
222
+ "learning_rate": 9.034077987426021e-05,
223
+ "loss": 3.7439,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 0.41,
228
+ "learning_rate": 8.807204847074523e-05,
229
+ "loss": 3.7879,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 0.42,
234
+ "learning_rate": 8.577990652484077e-05,
235
+ "loss": 3.7768,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 0.43,
240
+ "learning_rate": 8.34671097962332e-05,
241
+ "loss": 3.6851,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 0.44,
246
+ "learning_rate": 8.113643887711011e-05,
247
+ "loss": 3.7911,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 0.45,
252
+ "learning_rate": 7.879069584915438e-05,
253
+ "loss": 3.6839,
254
+ "step": 205
255
+ },
256
+ {
257
+ "epoch": 0.46,
258
+ "learning_rate": 7.643270091470234e-05,
259
+ "loss": 3.7319,
260
+ "step": 210
261
+ },
262
+ {
263
+ "epoch": 0.47,
264
+ "learning_rate": 7.406528900611617e-05,
265
+ "loss": 3.6703,
266
+ "step": 215
267
+ },
268
+ {
269
+ "epoch": 0.49,
270
+ "learning_rate": 7.169130637744674e-05,
271
+ "loss": 3.7467,
272
+ "step": 220
273
+ },
274
+ {
275
+ "epoch": 0.5,
276
+ "learning_rate": 6.931360718248504e-05,
277
+ "loss": 3.8521,
278
+ "step": 225
279
+ },
280
+ {
281
+ "epoch": 0.51,
282
+ "learning_rate": 6.693505004331577e-05,
283
+ "loss": 3.6709,
284
+ "step": 230
285
+ },
286
+ {
287
+ "epoch": 0.52,
288
+ "learning_rate": 6.455849461349907e-05,
289
+ "loss": 3.6242,
290
+ "step": 235
291
+ },
292
+ {
293
+ "epoch": 0.53,
294
+ "learning_rate": 6.218679814001198e-05,
295
+ "loss": 3.6225,
296
+ "step": 240
297
+ },
298
+ {
299
+ "epoch": 0.54,
300
+ "learning_rate": 5.9822812028083505e-05,
301
+ "loss": 3.8016,
302
+ "step": 245
303
+ },
304
+ {
305
+ "epoch": 0.55,
306
+ "learning_rate": 5.746937841305257e-05,
307
+ "loss": 3.6923,
308
+ "step": 250
309
+ },
310
+ {
311
+ "epoch": 0.56,
312
+ "learning_rate": 5.512932674337138e-05,
313
+ "loss": 3.894,
314
+ "step": 255
315
+ },
316
+ {
317
+ "epoch": 0.57,
318
+ "learning_rate": 5.280547037886122e-05,
319
+ "loss": 3.7461,
320
+ "step": 260
321
+ },
322
+ {
323
+ "epoch": 0.58,
324
+ "learning_rate": 5.050060320831149e-05,
325
+ "loss": 3.5966,
326
+ "step": 265
327
+ },
328
+ {
329
+ "epoch": 0.6,
330
+ "learning_rate": 4.821749629048772e-05,
331
+ "loss": 3.7551,
332
+ "step": 270
333
+ },
334
+ {
335
+ "epoch": 0.61,
336
+ "learning_rate": 4.595889452258756e-05,
337
+ "loss": 3.8694,
338
+ "step": 275
339
+ },
340
+ {
341
+ "epoch": 0.62,
342
+ "learning_rate": 4.372751334014969e-05,
343
+ "loss": 3.7224,
344
+ "step": 280
345
+ },
346
+ {
347
+ "epoch": 0.63,
348
+ "learning_rate": 4.1526035452383523e-05,
349
+ "loss": 3.915,
350
+ "step": 285
351
+ },
352
+ {
353
+ "epoch": 0.64,
354
+ "learning_rate": 3.935710761684453e-05,
355
+ "loss": 3.8484,
356
+ "step": 290
357
+ },
358
+ {
359
+ "epoch": 0.65,
360
+ "learning_rate": 3.722333745733311e-05,
361
+ "loss": 3.7062,
362
+ "step": 295
363
+ },
364
+ {
365
+ "epoch": 0.66,
366
+ "learning_rate": 3.512729032884219e-05,
367
+ "loss": 3.676,
368
+ "step": 300
369
+ },
370
+ {
371
+ "epoch": 0.67,
372
+ "learning_rate": 3.3071486233323674e-05,
373
+ "loss": 3.6448,
374
+ "step": 305
375
+ },
376
+ {
377
+ "epoch": 0.68,
378
+ "learning_rate": 3.105839678998049e-05,
379
+ "loss": 3.9731,
380
+ "step": 310
381
+ },
382
+ {
383
+ "epoch": 0.7,
384
+ "learning_rate": 2.9090442263728265e-05,
385
+ "loss": 3.6278,
386
+ "step": 315
387
+ },
388
+ {
389
+ "epoch": 0.71,
390
+ "learning_rate": 2.716998865539764e-05,
391
+ "loss": 3.6389,
392
+ "step": 320
393
+ },
394
+ {
395
+ "epoch": 0.72,
396
+ "learning_rate": 2.5299344857176957e-05,
397
+ "loss": 3.6411,
398
+ "step": 325
399
+ },
400
+ {
401
+ "epoch": 0.73,
402
+ "learning_rate": 2.3480759876714295e-05,
403
+ "loss": 3.7764,
404
+ "step": 330
405
+ },
406
+ {
407
+ "epoch": 0.74,
408
+ "learning_rate": 2.1716420133216482e-05,
409
+ "loss": 3.7769,
410
+ "step": 335
411
+ },
412
+ {
413
+ "epoch": 0.75,
414
+ "learning_rate": 2.0008446828796293e-05,
415
+ "loss": 3.528,
416
+ "step": 340
417
+ },
418
+ {
419
+ "epoch": 0.76,
420
+ "learning_rate": 1.8358893398227267e-05,
421
+ "loss": 3.819,
422
+ "step": 345
423
+ },
424
+ {
425
+ "epoch": 0.77,
426
+ "learning_rate": 1.6769743040173313e-05,
427
+ "loss": 3.6014,
428
+ "step": 350
429
+ },
430
+ {
431
+ "epoch": 0.78,
432
+ "learning_rate": 1.5242906332860249e-05,
433
+ "loss": 3.6993,
434
+ "step": 355
435
+ },
436
+ {
437
+ "epoch": 0.79,
438
+ "learning_rate": 1.3780218937056495e-05,
439
+ "loss": 3.7919,
440
+ "step": 360
441
+ },
442
+ {
443
+ "epoch": 0.81,
444
+ "learning_rate": 1.2383439389124231e-05,
445
+ "loss": 3.6903,
446
+ "step": 365
447
+ },
448
+ {
449
+ "epoch": 0.82,
450
+ "learning_rate": 1.105424698679451e-05,
451
+ "loss": 3.4355,
452
+ "step": 370
453
+ },
454
+ {
455
+ "epoch": 0.83,
456
+ "learning_rate": 9.794239770208025e-06,
457
+ "loss": 3.7661,
458
+ "step": 375
459
+ },
460
+ {
461
+ "epoch": 0.84,
462
+ "learning_rate": 8.604932600649156e-06,
463
+ "loss": 4.0533,
464
+ "step": 380
465
+ },
466
+ {
467
+ "epoch": 0.85,
468
+ "learning_rate": 7.487755339282637e-06,
469
+ "loss": 3.7796,
470
+ "step": 385
471
+ },
472
+ {
473
+ "epoch": 0.86,
474
+ "learning_rate": 6.444051128083183e-06,
475
+ "loss": 3.7312,
476
+ "step": 390
477
+ },
478
+ {
479
+ "epoch": 0.87,
480
+ "learning_rate": 5.4750747750241e-06,
481
+ "loss": 3.7231,
482
+ "step": 395
483
+ },
484
+ {
485
+ "epoch": 0.88,
486
+ "learning_rate": 4.581991245466992e-06,
487
+ "loss": 3.7788,
488
+ "step": 400
489
+ },
490
+ {
491
+ "epoch": 0.89,
492
+ "learning_rate": 3.7658742615658213e-06,
493
+ "loss": 3.7838,
494
+ "step": 405
495
+ },
496
+ {
497
+ "epoch": 0.91,
498
+ "learning_rate": 3.027705011369445e-06,
499
+ "loss": 3.7598,
500
+ "step": 410
501
+ },
502
+ {
503
+ "epoch": 0.92,
504
+ "learning_rate": 2.3683709691745994e-06,
505
+ "loss": 3.954,
506
+ "step": 415
507
+ },
508
+ {
509
+ "epoch": 0.93,
510
+ "learning_rate": 1.7886648285474887e-06,
511
+ "loss": 3.7673,
512
+ "step": 420
513
+ },
514
+ {
515
+ "epoch": 0.94,
516
+ "learning_rate": 1.289283549296875e-06,
517
+ "loss": 3.8811,
518
+ "step": 425
519
+ },
520
+ {
521
+ "epoch": 0.95,
522
+ "learning_rate": 8.708275195444353e-07,
523
+ "loss": 3.6489,
524
+ "step": 430
525
+ },
526
+ {
527
+ "epoch": 0.96,
528
+ "learning_rate": 5.337998338997259e-07,
529
+ "loss": 3.6089,
530
+ "step": 435
531
+ },
532
+ {
533
+ "epoch": 0.97,
534
+ "learning_rate": 2.786056886076668e-07,
535
+ "loss": 3.5491,
536
+ "step": 440
537
+ },
538
+ {
539
+ "epoch": 0.98,
540
+ "learning_rate": 1.0555189439568316e-07,
541
+ "loss": 3.7324,
542
+ "step": 445
543
+ },
544
+ {
545
+ "epoch": 0.99,
546
+ "learning_rate": 1.484650760624615e-08,
547
+ "loss": 3.7782,
548
+ "step": 450
549
+ },
550
+ {
551
+ "epoch": 1.0,
552
+ "eval_loss": 3.7048158645629883,
553
+ "eval_runtime": 29.3019,
554
+ "eval_samples_per_second": 22.388,
555
+ "eval_steps_per_second": 2.798,
556
+ "step": 453
557
+ }
558
+ ],
559
+ "max_steps": 453,
560
+ "num_train_epochs": 1,
561
+ "total_flos": 473069223936000.0,
562
+ "trial_name": null,
563
+ "trial_params": null
564
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88afb1791286823d1557961f7a8392ea79a53d89533284d93c6a6575791bb1ea
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff