AlekseyKorshuk commited on
Commit
d5a6f79
1 Parent(s): fb19960

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/snoop-dogg
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/91bd22f5e53a3ea3cb1436de8f4a3722.1000x1000x1.jpg&#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">Snoop Dogg</div>
22
+ <a href="https://genius.com/artists/snoop-dogg">
23
+ <div style="text-align: center; font-size: 14px;">@snoop-dogg</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 Snoop Dogg.
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/snoop-dogg).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/snoop-dogg")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/255rv52h/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 Snoop Dogg's lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/xlo6sfmn) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/xlo6sfmn/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/snoop-dogg')
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/snoop-dogg")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/snoop-dogg")
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": 3.417607307434082, "eval_runtime": 35.077, "eval_samples_per_second": 21.467, "eval_steps_per_second": 2.708, "epoch": 1.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82c220da81cdcb2810fb296930ad027595bc527561d769450b6c1004a1482d7f
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 sha256:26c89df95a623615699b8cb15d454e0e51988ed659e4edea185b59d09df7320d
3
+ size 995604017
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b799dfe236e2ce13953e8b7372b70f8194c3a1fbb7eba80985f1a7710b60b3
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca4efa8760670b265a20db81d357178a028968297f1568342afc561ffd367cfb
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b772c417587c5d01fc5e54458d542c1222437cf21ae50383dc362c9bbceaf117
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 +1,666 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.417607307434082,
3
+ "best_model_checkpoint": "output/snoop-dogg/checkpoint-538",
4
+ "epoch": 1.0,
5
+ "global_step": 538,
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": 0.00013717076261874923,
13
+ "loss": 4.1063,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 0.00013708307539699282,
19
+ "loss": 4.1679,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 0.00013693701307947525,
25
+ "loss": 4.0154,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.04,
30
+ "learning_rate": 0.0001367327001699768,
31
+ "loss": 3.9048,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.05,
36
+ "learning_rate": 0.00013647031082518634,
37
+ "loss": 3.9959,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.06,
42
+ "learning_rate": 0.00013615006870624992,
43
+ "loss": 3.8299,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.07,
48
+ "learning_rate": 0.00013577224678812164,
49
+ "loss": 3.7535,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.07,
54
+ "learning_rate": 0.00013533716712687914,
55
+ "loss": 3.7139,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.08,
60
+ "learning_rate": 0.0001348452005852027,
61
+ "loss": 3.5272,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.09,
66
+ "learning_rate": 0.00013429676651625084,
67
+ "loss": 3.9259,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.1,
72
+ "learning_rate": 0.0001336923324062034,
73
+ "loss": 3.646,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.11,
78
+ "learning_rate": 0.00013303241347577507,
79
+ "loss": 3.7353,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.12,
84
+ "learning_rate": 0.00013231757224104065,
85
+ "loss": 3.7269,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.13,
90
+ "learning_rate": 0.0001315484180339451,
91
+ "loss": 3.6971,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.14,
96
+ "learning_rate": 0.0001307256064829081,
97
+ "loss": 3.6029,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.15,
102
+ "learning_rate": 0.00012984983895396502,
103
+ "loss": 3.6687,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.16,
108
+ "learning_rate": 0.00012892186195292147,
109
+ "loss": 3.5599,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.17,
114
+ "learning_rate": 0.00012794246648903024,
115
+ "loss": 3.4859,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.18,
120
+ "learning_rate": 0.00012691248740073373,
121
+ "loss": 3.7556,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.19,
126
+ "learning_rate": 0.00012583280264404602,
127
+ "loss": 3.6952,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.2,
132
+ "learning_rate": 0.00012470433254418178,
133
+ "loss": 3.7874,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.2,
138
+ "learning_rate": 0.00012352803901106928,
139
+ "loss": 3.6861,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.21,
144
+ "learning_rate": 0.00012230492471941668,
145
+ "loss": 3.7332,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.22,
150
+ "learning_rate": 0.00012103603225403036,
151
+ "loss": 3.6027,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.23,
156
+ "learning_rate": 0.00011972244322111374,
157
+ "loss": 3.6728,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.24,
162
+ "learning_rate": 0.00011836527732630418,
163
+ "loss": 3.6239,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.25,
168
+ "learning_rate": 0.00011696569142023398,
169
+ "loss": 3.6474,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.26,
174
+ "learning_rate": 0.00011552487851242871,
175
+ "loss": 3.6182,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.27,
180
+ "learning_rate": 0.00011404406675438398,
181
+ "loss": 3.6673,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.28,
186
+ "learning_rate": 0.00011252451839268661,
187
+ "loss": 3.6792,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.29,
192
+ "learning_rate": 0.00011096752869307368,
193
+ "loss": 3.7147,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.3,
198
+ "learning_rate": 0.0001093744248363455,
199
+ "loss": 3.7344,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.31,
204
+ "learning_rate": 0.0001077465647870744,
205
+ "loss": 3.672,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.32,
210
+ "learning_rate": 0.0001060853361360733,
211
+ "loss": 3.5366,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.33,
216
+ "learning_rate": 0.00010439215491761087,
217
+ "loss": 3.7628,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.33,
222
+ "learning_rate": 0.00010266846440238127,
223
+ "loss": 3.4477,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 0.34,
228
+ "learning_rate": 0.00010091573386725777,
229
+ "loss": 3.641,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 0.35,
234
+ "learning_rate": 9.913545734287838e-05,
235
+ "loss": 3.5141,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 0.36,
240
+ "learning_rate": 9.732915234013161e-05,
241
+ "loss": 3.7305,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 0.37,
246
+ "learning_rate": 9.549835855662742e-05,
247
+ "loss": 3.5619,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 0.38,
252
+ "learning_rate": 9.364463656425613e-05,
253
+ "loss": 3.4244,
254
+ "step": 205
255
+ },
256
+ {
257
+ "epoch": 0.39,
258
+ "learning_rate": 9.176956647895434e-05,
259
+ "loss": 3.5957,
260
+ "step": 210
261
+ },
262
+ {
263
+ "epoch": 0.4,
264
+ "learning_rate": 8.987474661381113e-05,
265
+ "loss": 3.579,
266
+ "step": 215
267
+ },
268
+ {
269
+ "epoch": 0.41,
270
+ "learning_rate": 8.79617921166632e-05,
271
+ "loss": 3.4737,
272
+ "step": 220
273
+ },
274
+ {
275
+ "epoch": 0.42,
276
+ "learning_rate": 8.603233359333994e-05,
277
+ "loss": 3.5314,
278
+ "step": 225
279
+ },
280
+ {
281
+ "epoch": 0.43,
282
+ "learning_rate": 8.408801571773217e-05,
283
+ "loss": 3.6413,
284
+ "step": 230
285
+ },
286
+ {
287
+ "epoch": 0.44,
288
+ "learning_rate": 8.213049582986904e-05,
289
+ "loss": 3.616,
290
+ "step": 235
291
+ },
292
+ {
293
+ "epoch": 0.45,
294
+ "learning_rate": 8.016144252319865e-05,
295
+ "loss": 3.6094,
296
+ "step": 240
297
+ },
298
+ {
299
+ "epoch": 0.46,
300
+ "learning_rate": 7.818253422227576e-05,
301
+ "loss": 3.4714,
302
+ "step": 245
303
+ },
304
+ {
305
+ "epoch": 0.46,
306
+ "learning_rate": 7.619545775206993e-05,
307
+ "loss": 3.6148,
308
+ "step": 250
309
+ },
310
+ {
311
+ "epoch": 0.47,
312
+ "learning_rate": 7.420190690011274e-05,
313
+ "loss": 3.393,
314
+ "step": 255
315
+ },
316
+ {
317
+ "epoch": 0.48,
318
+ "learning_rate": 7.220358097271036e-05,
319
+ "loss": 3.7299,
320
+ "step": 260
321
+ },
322
+ {
323
+ "epoch": 0.49,
324
+ "learning_rate": 7.02021833464518e-05,
325
+ "loss": 3.5671,
326
+ "step": 265
327
+ },
328
+ {
329
+ "epoch": 0.5,
330
+ "learning_rate": 6.819942001624763e-05,
331
+ "loss": 3.5912,
332
+ "step": 270
333
+ },
334
+ {
335
+ "epoch": 0.51,
336
+ "learning_rate": 6.619699814113692e-05,
337
+ "loss": 3.4808,
338
+ "step": 275
339
+ },
340
+ {
341
+ "epoch": 0.52,
342
+ "learning_rate": 6.419662458910188e-05,
343
+ "loss": 3.5158,
344
+ "step": 280
345
+ },
346
+ {
347
+ "epoch": 0.53,
348
+ "learning_rate": 6.220000448213035e-05,
349
+ "loss": 3.4962,
350
+ "step": 285
351
+ },
352
+ {
353
+ "epoch": 0.54,
354
+ "learning_rate": 6.020883974276696e-05,
355
+ "loss": 3.5426,
356
+ "step": 290
357
+ },
358
+ {
359
+ "epoch": 0.55,
360
+ "learning_rate": 5.822482764339123e-05,
361
+ "loss": 3.4774,
362
+ "step": 295
363
+ },
364
+ {
365
+ "epoch": 0.56,
366
+ "learning_rate": 5.6249659359459626e-05,
367
+ "loss": 3.6775,
368
+ "step": 300
369
+ },
370
+ {
371
+ "epoch": 0.57,
372
+ "learning_rate": 5.4285018527944484e-05,
373
+ "loss": 3.4415,
374
+ "step": 305
375
+ },
376
+ {
377
+ "epoch": 0.58,
378
+ "learning_rate": 5.233257981219891e-05,
379
+ "loss": 3.2558,
380
+ "step": 310
381
+ },
382
+ {
383
+ "epoch": 0.59,
384
+ "learning_rate": 5.0394007474470735e-05,
385
+ "loss": 3.4333,
386
+ "step": 315
387
+ },
388
+ {
389
+ "epoch": 0.59,
390
+ "learning_rate": 4.8470953957282466e-05,
391
+ "loss": 3.4511,
392
+ "step": 320
393
+ },
394
+ {
395
+ "epoch": 0.6,
396
+ "learning_rate": 4.656505847488621e-05,
397
+ "loss": 3.439,
398
+ "step": 325
399
+ },
400
+ {
401
+ "epoch": 0.61,
402
+ "learning_rate": 4.4677945615994564e-05,
403
+ "loss": 3.5292,
404
+ "step": 330
405
+ },
406
+ {
407
+ "epoch": 0.62,
408
+ "learning_rate": 4.281122395897837e-05,
409
+ "loss": 3.5033,
410
+ "step": 335
411
+ },
412
+ {
413
+ "epoch": 0.63,
414
+ "learning_rate": 4.096648470071148e-05,
415
+ "loss": 3.4235,
416
+ "step": 340
417
+ },
418
+ {
419
+ "epoch": 0.64,
420
+ "learning_rate": 3.914530030023193e-05,
421
+ "loss": 3.4522,
422
+ "step": 345
423
+ },
424
+ {
425
+ "epoch": 0.65,
426
+ "learning_rate": 3.734922313837482e-05,
427
+ "loss": 3.4705,
428
+ "step": 350
429
+ },
430
+ {
431
+ "epoch": 0.66,
432
+ "learning_rate": 3.5579784194520246e-05,
433
+ "loss": 3.5511,
434
+ "step": 355
435
+ },
436
+ {
437
+ "epoch": 0.67,
438
+ "learning_rate": 3.383849174158367e-05,
439
+ "loss": 3.3867,
440
+ "step": 360
441
+ },
442
+ {
443
+ "epoch": 0.68,
444
+ "learning_rate": 3.2126830060361513e-05,
445
+ "loss": 3.6066,
446
+ "step": 365
447
+ },
448
+ {
449
+ "epoch": 0.69,
450
+ "learning_rate": 3.044625817432741e-05,
451
+ "loss": 3.3799,
452
+ "step": 370
453
+ },
454
+ {
455
+ "epoch": 0.7,
456
+ "learning_rate": 2.879820860595807e-05,
457
+ "loss": 3.3825,
458
+ "step": 375
459
+ },
460
+ {
461
+ "epoch": 0.71,
462
+ "learning_rate": 2.718408615564853e-05,
463
+ "loss": 3.4277,
464
+ "step": 380
465
+ },
466
+ {
467
+ "epoch": 0.72,
468
+ "learning_rate": 2.560526670425788e-05,
469
+ "loss": 3.6353,
470
+ "step": 385
471
+ },
472
+ {
473
+ "epoch": 0.72,
474
+ "learning_rate": 2.4063096040305828e-05,
475
+ "loss": 3.388,
476
+ "step": 390
477
+ },
478
+ {
479
+ "epoch": 0.73,
480
+ "learning_rate": 2.2558888712820237e-05,
481
+ "loss": 3.4079,
482
+ "step": 395
483
+ },
484
+ {
485
+ "epoch": 0.74,
486
+ "learning_rate": 2.1093926910813165e-05,
487
+ "loss": 3.6123,
488
+ "step": 400
489
+ },
490
+ {
491
+ "epoch": 0.75,
492
+ "learning_rate": 1.966945937034066e-05,
493
+ "loss": 3.4731,
494
+ "step": 405
495
+ },
496
+ {
497
+ "epoch": 0.76,
498
+ "learning_rate": 1.828670031007799e-05,
499
+ "loss": 3.6209,
500
+ "step": 410
501
+ },
502
+ {
503
+ "epoch": 0.77,
504
+ "learning_rate": 1.694682839631735e-05,
505
+ "loss": 3.6534,
506
+ "step": 415
507
+ },
508
+ {
509
+ "epoch": 0.78,
510
+ "learning_rate": 1.5650985738270693e-05,
511
+ "loss": 3.5689,
512
+ "step": 420
513
+ },
514
+ {
515
+ "epoch": 0.79,
516
+ "learning_rate": 1.4400276914533763e-05,
517
+ "loss": 3.5702,
518
+ "step": 425
519
+ },
520
+ {
521
+ "epoch": 0.8,
522
+ "learning_rate": 1.319576803154135e-05,
523
+ "loss": 3.4445,
524
+ "step": 430
525
+ },
526
+ {
527
+ "epoch": 0.81,
528
+ "learning_rate": 1.2038485814816265e-05,
529
+ "loss": 3.3746,
530
+ "step": 435
531
+ },
532
+ {
533
+ "epoch": 0.82,
534
+ "learning_rate": 1.092941673378663e-05,
535
+ "loss": 3.5187,
536
+ "step": 440
537
+ },
538
+ {
539
+ "epoch": 0.83,
540
+ "learning_rate": 9.869506160917616e-06,
541
+ "loss": 3.4482,
542
+ "step": 445
543
+ },
544
+ {
545
+ "epoch": 0.84,
546
+ "learning_rate": 8.859657565874292e-06,
547
+ "loss": 3.5279,
548
+ "step": 450
549
+ },
550
+ {
551
+ "epoch": 0.85,
552
+ "learning_rate": 7.900731745402374e-06,
553
+ "loss": 3.4626,
554
+ "step": 455
555
+ },
556
+ {
557
+ "epoch": 0.86,
558
+ "learning_rate": 6.9935460895836276e-06,
559
+ "loss": 3.6454,
560
+ "step": 460
561
+ },
562
+ {
563
+ "epoch": 0.86,
564
+ "learning_rate": 6.138873885091061e-06,
565
+ "loss": 3.4554,
566
+ "step": 465
567
+ },
568
+ {
569
+ "epoch": 0.87,
570
+ "learning_rate": 5.3374436560379995e-06,
571
+ "loss": 3.4318,
572
+ "step": 470
573
+ },
574
+ {
575
+ "epoch": 0.88,
576
+ "learning_rate": 4.589938542982855e-06,
577
+ "loss": 3.5353,
578
+ "step": 475
579
+ },
580
+ {
581
+ "epoch": 0.89,
582
+ "learning_rate": 3.896995720618831e-06,
583
+ "loss": 3.3728,
584
+ "step": 480
585
+ },
586
+ {
587
+ "epoch": 0.9,
588
+ "learning_rate": 3.2592058546451155e-06,
589
+ "loss": 3.5394,
590
+ "step": 485
591
+ },
592
+ {
593
+ "epoch": 0.91,
594
+ "learning_rate": 2.677112598282391e-06,
595
+ "loss": 3.4868,
596
+ "step": 490
597
+ },
598
+ {
599
+ "epoch": 0.92,
600
+ "learning_rate": 2.1512121288618626e-06,
601
+ "loss": 3.3146,
602
+ "step": 495
603
+ },
604
+ {
605
+ "epoch": 0.93,
606
+ "learning_rate": 1.6819527248827737e-06,
607
+ "loss": 3.286,
608
+ "step": 500
609
+ },
610
+ {
611
+ "epoch": 0.94,
612
+ "learning_rate": 1.269734383899055e-06,
613
+ "loss": 3.3572,
614
+ "step": 505
615
+ },
616
+ {
617
+ "epoch": 0.95,
618
+ "learning_rate": 9.149084815606564e-07,
619
+ "loss": 3.4358,
620
+ "step": 510
621
+ },
622
+ {
623
+ "epoch": 0.96,
624
+ "learning_rate": 6.177774721003861e-07,
625
+ "loss": 3.404,
626
+ "step": 515
627
+ },
628
+ {
629
+ "epoch": 0.97,
630
+ "learning_rate": 3.7859463052128633e-07,
631
+ "loss": 3.4824,
632
+ "step": 520
633
+ },
634
+ {
635
+ "epoch": 0.98,
636
+ "learning_rate": 1.9756383670464207e-07,
637
+ "loss": 3.3723,
638
+ "step": 525
639
+ },
640
+ {
641
+ "epoch": 0.99,
642
+ "learning_rate": 7.483940162237093e-08,
643
+ "loss": 3.4703,
644
+ "step": 530
645
+ },
646
+ {
647
+ "epoch": 0.99,
648
+ "learning_rate": 1.0525935802102593e-08,
649
+ "loss": 3.3436,
650
+ "step": 535
651
+ },
652
+ {
653
+ "epoch": 1.0,
654
+ "eval_loss": 3.417607307434082,
655
+ "eval_runtime": 34.9657,
656
+ "eval_samples_per_second": 21.535,
657
+ "eval_steps_per_second": 2.717,
658
+ "step": 538
659
+ }
660
+ ],
661
+ "max_steps": 538,
662
+ "num_train_epochs": 1,
663
+ "total_flos": 561908514816000.0,
664
+ "trial_name": null,
665
+ "trial_params": null
666
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921fbeeaca9d2d7fa8d5c81ad9c59179822d44721ad18de326d17b3f14cc0e37
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff