AlekseyKorshuk commited on
Commit
0ee9a7e
1 Parent(s): b7beb56

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/taylor-swift
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/3c1f124fcbbc2857a95e513fb34cc5a8.400x400x1.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">Taylor Swift</div>
22
+ <a href="https://genius.com/artists/taylor-swift">
23
+ <div style="text-align: center; font-size: 14px;">@taylor-swift</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 Taylor Swift.
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/taylor-swift).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/taylor-swift")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/orx9pgcj/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 Taylor Swift's lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/13d0g1o4) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/13d0g1o4/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/taylor-swift')
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/taylor-swift")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/taylor-swift")
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 200,
33
+ "min_length": 100,
34
+ "temperature": 1.0,
35
+ "top_p": 0.95
36
+ }
37
+ },
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.12.2",
40
+ "use_cache": true,
41
+ "vocab_size": 50257
42
+ }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 2.1195662021636963, "eval_runtime": 2.7951, "eval_samples_per_second": 76.561, "eval_steps_per_second": 9.66, "epoch": 5.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283ca8f9344b855954167e60f2db67ac2afc241037fe870abcdcea59b7262caf
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 sha256:642b9dfcc4d3d148df04dbd5dd9fc2e06a625d5877f48239cd186fadbd82f0c0
3
+ size 995604017
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875d52e81b7c5b242a7496cd7be0fe29bfb0475bf80207c43583aeaede1cdaed
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8108166cfcb949d51c2438ab25802532e6d155d969ce33575bd2e1f5af1b15a0
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7733e18eff27c9a4da0b58764924ec541924a4be41ac9a645f4ee09be1782f09
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 +1,1004 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.1195662021636963,
3
+ "best_model_checkpoint": "output/taylor-swift/checkpoint-790",
4
+ "epoch": 5.0,
5
+ "global_step": 790,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 0.00013686126352583852,
13
+ "loss": 3.3494,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.06,
18
+ "learning_rate": 0.00013584839936279803,
19
+ "loss": 3.1755,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.09,
24
+ "learning_rate": 0.00013417141025243517,
25
+ "loss": 3.1276,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.13,
30
+ "learning_rate": 0.00013184685763435497,
31
+ "loss": 3.1339,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.16,
36
+ "learning_rate": 0.00012889769809041896,
37
+ "loss": 3.1666,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.19,
42
+ "learning_rate": 0.00012535305663245375,
43
+ "loss": 2.8811,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.22,
48
+ "learning_rate": 0.00012124793907240209,
49
+ "loss": 2.9824,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.25,
54
+ "learning_rate": 0.00011662288631546257,
55
+ "loss": 2.9442,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.28,
60
+ "learning_rate": 0.00011152357399031441,
61
+ "loss": 2.961,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.32,
66
+ "learning_rate": 0.000106000361370359,
67
+ "loss": 2.7762,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.35,
72
+ "learning_rate": 0.00010010779404069628,
73
+ "loss": 2.8665,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.38,
78
+ "learning_rate": 9.390406522234693e-05,
79
+ "loss": 2.9223,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.41,
84
+ "learning_rate": 8.745044107352033e-05,
85
+ "loss": 2.8602,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.44,
90
+ "learning_rate": 8.081065564347997e-05,
91
+ "loss": 2.8085,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.47,
96
+ "learning_rate": 7.405028145425961e-05,
97
+ "loss": 2.7651,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.51,
102
+ "learning_rate": 6.723608192617619e-05,
103
+ "loss": 2.7224,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.54,
108
+ "learning_rate": 6.043535204238934e-05,
109
+ "loss": 2.6702,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.57,
114
+ "learning_rate": 5.371525376390658e-05,
115
+ "loss": 2.8382,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.6,
120
+ "learning_rate": 4.714215275827523e-05,
121
+ "loss": 2.5947,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.63,
126
+ "learning_rate": 4.078096299222862e-05,
127
+ "loss": 2.7596,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.66,
132
+ "learning_rate": 3.4694505660892814e-05,
133
+ "loss": 2.8001,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.7,
138
+ "learning_rate": 2.894288878457539e-05,
139
+ "loss": 2.7797,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.73,
144
+ "learning_rate": 2.358291360005225e-05,
145
+ "loss": 2.6613,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.76,
150
+ "learning_rate": 1.8667513608652705e-05,
151
+ "loss": 2.6169,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.79,
156
+ "learning_rate": 1.424523182093601e-05,
157
+ "loss": 2.5101,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.82,
162
+ "learning_rate": 1.0359741360532426e-05,
163
+ "loss": 2.6278,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.85,
168
+ "learning_rate": 7.049414161522035e-06,
169
+ "loss": 2.8319,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.89,
174
+ "learning_rate": 4.346942018765275e-06,
175
+ "loss": 2.7047,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.92,
180
+ "learning_rate": 2.2790137335786513e-06,
181
+ "loss": 2.7375,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.95,
186
+ "learning_rate": 8.660515431675314e-07,
187
+ "loss": 2.9128,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.98,
192
+ "learning_rate": 1.2200943675939755e-07,
193
+ "loss": 2.6662,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 1.0,
198
+ "eval_loss": 2.5653560161590576,
199
+ "eval_runtime": 2.784,
200
+ "eval_samples_per_second": 76.868,
201
+ "eval_steps_per_second": 9.698,
202
+ "step": 158
203
+ },
204
+ {
205
+ "epoch": 1.01,
206
+ "learning_rate": 5.4235350207093555e-08,
207
+ "loss": 2.594,
208
+ "step": 160
209
+ },
210
+ {
211
+ "epoch": 1.04,
212
+ "learning_rate": 6.633985999863723e-07,
213
+ "loss": 2.722,
214
+ "step": 165
215
+ },
216
+ {
217
+ "epoch": 1.08,
218
+ "learning_rate": 1.94348327322787e-06,
219
+ "loss": 2.6618,
220
+ "step": 170
221
+ },
222
+ {
223
+ "epoch": 1.11,
224
+ "learning_rate": 3.881847639061565e-06,
225
+ "loss": 2.5415,
226
+ "step": 175
227
+ },
228
+ {
229
+ "epoch": 1.14,
230
+ "learning_rate": 6.459348994545111e-06,
231
+ "loss": 2.5807,
232
+ "step": 180
233
+ },
234
+ {
235
+ "epoch": 1.17,
236
+ "learning_rate": 9.650532712235251e-06,
237
+ "loss": 2.6543,
238
+ "step": 185
239
+ },
240
+ {
241
+ "epoch": 1.2,
242
+ "learning_rate": 1.3423883622425528e-05,
243
+ "loss": 2.5415,
244
+ "step": 190
245
+ },
246
+ {
247
+ "epoch": 1.23,
248
+ "learning_rate": 1.7742137247474782e-05,
249
+ "loss": 2.435,
250
+ "step": 195
251
+ },
252
+ {
253
+ "epoch": 1.27,
254
+ "learning_rate": 2.256264781457008e-05,
255
+ "loss": 2.629,
256
+ "step": 200
257
+ },
258
+ {
259
+ "epoch": 1.3,
260
+ "learning_rate": 2.783780941254068e-05,
261
+ "loss": 2.4759,
262
+ "step": 205
263
+ },
264
+ {
265
+ "epoch": 1.33,
266
+ "learning_rate": 3.3515526133505226e-05,
267
+ "loss": 2.5917,
268
+ "step": 210
269
+ },
270
+ {
271
+ "epoch": 1.36,
272
+ "learning_rate": 3.953972655637492e-05,
273
+ "loss": 2.6353,
274
+ "step": 215
275
+ },
276
+ {
277
+ "epoch": 1.39,
278
+ "learning_rate": 4.585091749132818e-05,
279
+ "loss": 2.6671,
280
+ "step": 220
281
+ },
282
+ {
283
+ "epoch": 1.42,
284
+ "learning_rate": 5.238677151664272e-05,
285
+ "loss": 2.4302,
286
+ "step": 225
287
+ },
288
+ {
289
+ "epoch": 1.46,
290
+ "learning_rate": 5.908274250554988e-05,
291
+ "loss": 2.65,
292
+ "step": 230
293
+ },
294
+ {
295
+ "epoch": 1.49,
296
+ "learning_rate": 6.587270306435089e-05,
297
+ "loss": 2.6803,
298
+ "step": 235
299
+ },
300
+ {
301
+ "epoch": 1.52,
302
+ "learning_rate": 7.268959758664963e-05,
303
+ "loss": 2.7479,
304
+ "step": 240
305
+ },
306
+ {
307
+ "epoch": 1.55,
308
+ "learning_rate": 7.946610447433497e-05,
309
+ "loss": 2.5183,
310
+ "step": 245
311
+ },
312
+ {
313
+ "epoch": 1.58,
314
+ "learning_rate": 8.613530098541655e-05,
315
+ "loss": 2.4577,
316
+ "step": 250
317
+ },
318
+ {
319
+ "epoch": 1.61,
320
+ "learning_rate": 9.263132414287828e-05,
321
+ "loss": 2.6144,
322
+ "step": 255
323
+ },
324
+ {
325
+ "epoch": 1.65,
326
+ "learning_rate": 9.889002117761157e-05,
327
+ "loss": 2.3613,
328
+ "step": 260
329
+ },
330
+ {
331
+ "epoch": 1.68,
332
+ "learning_rate": 0.0001048495830818497,
333
+ "loss": 2.3438,
334
+ "step": 265
335
+ },
336
+ {
337
+ "epoch": 1.71,
338
+ "learning_rate": 0.000110451155016322,
339
+ "loss": 2.5456,
340
+ "step": 270
341
+ },
342
+ {
343
+ "epoch": 1.74,
344
+ "learning_rate": 0.00011563941754292792,
345
+ "loss": 2.4388,
346
+ "step": 275
347
+ },
348
+ {
349
+ "epoch": 1.77,
350
+ "learning_rate": 0.00012036313294285455,
351
+ "loss": 2.337,
352
+ "step": 280
353
+ },
354
+ {
355
+ "epoch": 1.8,
356
+ "learning_rate": 0.00012457565122486245,
357
+ "loss": 2.4888,
358
+ "step": 285
359
+ },
360
+ {
361
+ "epoch": 1.84,
362
+ "learning_rate": 0.00012823537082655537,
363
+ "loss": 2.5507,
364
+ "step": 290
365
+ },
366
+ {
367
+ "epoch": 1.87,
368
+ "learning_rate": 0.00013130614945888676,
369
+ "loss": 2.4084,
370
+ "step": 295
371
+ },
372
+ {
373
+ "epoch": 1.9,
374
+ "learning_rate": 0.0001337576610365259,
375
+ "loss": 2.5188,
376
+ "step": 300
377
+ },
378
+ {
379
+ "epoch": 1.93,
380
+ "learning_rate": 0.0001355656951691469,
381
+ "loss": 2.4279,
382
+ "step": 305
383
+ },
384
+ {
385
+ "epoch": 1.96,
386
+ "learning_rate": 0.00013671239625595536,
387
+ "loss": 2.4089,
388
+ "step": 310
389
+ },
390
+ {
391
+ "epoch": 1.99,
392
+ "learning_rate": 0.0001371864398222265,
393
+ "loss": 2.3992,
394
+ "step": 315
395
+ },
396
+ {
397
+ "epoch": 2.0,
398
+ "eval_loss": 2.427677631378174,
399
+ "eval_runtime": 2.7859,
400
+ "eval_samples_per_second": 76.814,
401
+ "eval_steps_per_second": 9.691,
402
+ "step": 316
403
+ },
404
+ {
405
+ "epoch": 2.03,
406
+ "learning_rate": 0.00013698314435640815,
407
+ "loss": 2.4731,
408
+ "step": 320
409
+ },
410
+ {
411
+ "epoch": 2.06,
412
+ "learning_rate": 0.00013610451754331968,
413
+ "loss": 2.5107,
414
+ "step": 325
415
+ },
416
+ {
417
+ "epoch": 2.09,
418
+ "learning_rate": 0.00013455923643686105,
419
+ "loss": 2.2137,
420
+ "step": 330
421
+ },
422
+ {
423
+ "epoch": 2.12,
424
+ "learning_rate": 0.00013236256176804074,
425
+ "loss": 2.433,
426
+ "step": 335
427
+ },
428
+ {
429
+ "epoch": 2.15,
430
+ "learning_rate": 0.00012953618723459046,
431
+ "loss": 2.2366,
432
+ "step": 340
433
+ },
434
+ {
435
+ "epoch": 2.18,
436
+ "learning_rate": 0.00012610802526053698,
437
+ "loss": 2.2305,
438
+ "step": 345
439
+ },
440
+ {
441
+ "epoch": 2.22,
442
+ "learning_rate": 0.0001221119313415056,
443
+ "loss": 2.0334,
444
+ "step": 350
445
+ },
446
+ {
447
+ "epoch": 2.25,
448
+ "learning_rate": 0.00011758736969803705,
449
+ "loss": 2.2182,
450
+ "step": 355
451
+ },
452
+ {
453
+ "epoch": 2.28,
454
+ "learning_rate": 0.00011257902353882629,
455
+ "loss": 2.4565,
456
+ "step": 360
457
+ },
458
+ {
459
+ "epoch": 2.31,
460
+ "learning_rate": 0.00010713635378280492,
461
+ "loss": 2.3876,
462
+ "step": 365
463
+ },
464
+ {
465
+ "epoch": 2.34,
466
+ "learning_rate": 0.00010131311059799552,
467
+ "loss": 2.3244,
468
+ "step": 370
469
+ },
470
+ {
471
+ "epoch": 2.37,
472
+ "learning_rate": 9.516680258103397e-05,
473
+ "loss": 2.1224,
474
+ "step": 375
475
+ },
476
+ {
477
+ "epoch": 2.41,
478
+ "learning_rate": 8.875812881958139e-05,
479
+ "loss": 2.1287,
480
+ "step": 380
481
+ },
482
+ {
483
+ "epoch": 2.44,
484
+ "learning_rate": 8.215037944640755e-05,
485
+ "loss": 2.3755,
486
+ "step": 385
487
+ },
488
+ {
489
+ "epoch": 2.47,
490
+ "learning_rate": 7.540881060509307e-05,
491
+ "loss": 2.1973,
492
+ "step": 390
493
+ },
494
+ {
495
+ "epoch": 2.5,
496
+ "learning_rate": 6.860000000000001e-05,
497
+ "loss": 2.3247,
498
+ "step": 395
499
+ },
500
+ {
501
+ "epoch": 2.53,
502
+ "learning_rate": 6.179118939490698e-05,
503
+ "loss": 2.0219,
504
+ "step": 400
505
+ },
506
+ {
507
+ "epoch": 2.56,
508
+ "learning_rate": 5.504962055359254e-05,
509
+ "loss": 2.2227,
510
+ "step": 405
511
+ },
512
+ {
513
+ "epoch": 2.59,
514
+ "learning_rate": 4.844187118041858e-05,
515
+ "loss": 2.0213,
516
+ "step": 410
517
+ },
518
+ {
519
+ "epoch": 2.63,
520
+ "learning_rate": 4.203319741896607e-05,
521
+ "loss": 2.4335,
522
+ "step": 415
523
+ },
524
+ {
525
+ "epoch": 2.66,
526
+ "learning_rate": 3.5886889402004514e-05,
527
+ "loss": 2.1705,
528
+ "step": 420
529
+ },
530
+ {
531
+ "epoch": 2.69,
532
+ "learning_rate": 3.006364621719512e-05,
533
+ "loss": 2.0096,
534
+ "step": 425
535
+ },
536
+ {
537
+ "epoch": 2.72,
538
+ "learning_rate": 2.462097646117378e-05,
539
+ "loss": 2.233,
540
+ "step": 430
541
+ },
542
+ {
543
+ "epoch": 2.75,
544
+ "learning_rate": 1.9612630301962937e-05,
545
+ "loss": 2.2407,
546
+ "step": 435
547
+ },
548
+ {
549
+ "epoch": 2.78,
550
+ "learning_rate": 1.508806865849441e-05,
551
+ "loss": 2.1925,
552
+ "step": 440
553
+ },
554
+ {
555
+ "epoch": 2.82,
556
+ "learning_rate": 1.1091974739463048e-05,
557
+ "loss": 2.0939,
558
+ "step": 445
559
+ },
560
+ {
561
+ "epoch": 2.85,
562
+ "learning_rate": 7.66381276540956e-06,
563
+ "loss": 2.1105,
564
+ "step": 450
565
+ },
566
+ {
567
+ "epoch": 2.88,
568
+ "learning_rate": 4.8374382319592885e-06,
569
+ "loss": 2.1558,
570
+ "step": 455
571
+ },
572
+ {
573
+ "epoch": 2.91,
574
+ "learning_rate": 2.6407635631389823e-06,
575
+ "loss": 2.3444,
576
+ "step": 460
577
+ },
578
+ {
579
+ "epoch": 2.94,
580
+ "learning_rate": 1.0954824566803356e-06,
581
+ "loss": 2.0945,
582
+ "step": 465
583
+ },
584
+ {
585
+ "epoch": 2.97,
586
+ "learning_rate": 2.168556435918659e-07,
587
+ "loss": 1.9806,
588
+ "step": 470
589
+ },
590
+ {
591
+ "epoch": 3.0,
592
+ "eval_loss": 2.2620296478271484,
593
+ "eval_runtime": 2.784,
594
+ "eval_samples_per_second": 76.867,
595
+ "eval_steps_per_second": 9.698,
596
+ "step": 474
597
+ },
598
+ {
599
+ "epoch": 3.01,
600
+ "learning_rate": 1.3560177773502823e-08,
601
+ "loss": 1.9753,
602
+ "step": 475
603
+ },
604
+ {
605
+ "epoch": 3.04,
606
+ "learning_rate": 4.87603744044624e-07,
607
+ "loss": 2.0561,
608
+ "step": 480
609
+ },
610
+ {
611
+ "epoch": 3.07,
612
+ "learning_rate": 1.6343048308530896e-06,
613
+ "loss": 2.0054,
614
+ "step": 485
615
+ },
616
+ {
617
+ "epoch": 3.1,
618
+ "learning_rate": 3.4423389634741234e-06,
619
+ "loss": 2.0684,
620
+ "step": 490
621
+ },
622
+ {
623
+ "epoch": 3.13,
624
+ "learning_rate": 5.893850541113203e-06,
625
+ "loss": 1.8837,
626
+ "step": 495
627
+ },
628
+ {
629
+ "epoch": 3.16,
630
+ "learning_rate": 8.964629173444626e-06,
631
+ "loss": 1.9202,
632
+ "step": 500
633
+ },
634
+ {
635
+ "epoch": 3.2,
636
+ "learning_rate": 1.2624348775137553e-05,
637
+ "loss": 1.9576,
638
+ "step": 505
639
+ },
640
+ {
641
+ "epoch": 3.23,
642
+ "learning_rate": 1.6836867057145347e-05,
643
+ "loss": 2.1642,
644
+ "step": 510
645
+ },
646
+ {
647
+ "epoch": 3.26,
648
+ "learning_rate": 2.156058245707209e-05,
649
+ "loss": 2.2199,
650
+ "step": 515
651
+ },
652
+ {
653
+ "epoch": 3.29,
654
+ "learning_rate": 2.6748844983678075e-05,
655
+ "loss": 2.24,
656
+ "step": 520
657
+ },
658
+ {
659
+ "epoch": 3.32,
660
+ "learning_rate": 3.235041691815028e-05,
661
+ "loss": 2.2476,
662
+ "step": 525
663
+ },
664
+ {
665
+ "epoch": 3.35,
666
+ "learning_rate": 3.830997882238844e-05,
667
+ "loss": 1.9431,
668
+ "step": 530
669
+ },
670
+ {
671
+ "epoch": 3.39,
672
+ "learning_rate": 4.456867585712155e-05,
673
+ "loss": 1.9221,
674
+ "step": 535
675
+ },
676
+ {
677
+ "epoch": 3.42,
678
+ "learning_rate": 5.1064699014583464e-05,
679
+ "loss": 1.8139,
680
+ "step": 540
681
+ },
682
+ {
683
+ "epoch": 3.45,
684
+ "learning_rate": 5.773389552566511e-05,
685
+ "loss": 2.0033,
686
+ "step": 545
687
+ },
688
+ {
689
+ "epoch": 3.48,
690
+ "learning_rate": 6.451040241335031e-05,
691
+ "loss": 2.0651,
692
+ "step": 550
693
+ },
694
+ {
695
+ "epoch": 3.51,
696
+ "learning_rate": 7.132729693564907e-05,
697
+ "loss": 2.034,
698
+ "step": 555
699
+ },
700
+ {
701
+ "epoch": 3.54,
702
+ "learning_rate": 7.811725749444997e-05,
703
+ "loss": 1.8939,
704
+ "step": 560
705
+ },
706
+ {
707
+ "epoch": 3.58,
708
+ "learning_rate": 8.481322848335718e-05,
709
+ "loss": 2.2029,
710
+ "step": 565
711
+ },
712
+ {
713
+ "epoch": 3.61,
714
+ "learning_rate": 9.134908250867189e-05,
715
+ "loss": 1.9256,
716
+ "step": 570
717
+ },
718
+ {
719
+ "epoch": 3.64,
720
+ "learning_rate": 9.766027344362499e-05,
721
+ "loss": 1.9943,
722
+ "step": 575
723
+ },
724
+ {
725
+ "epoch": 3.67,
726
+ "learning_rate": 0.00010368447386649474,
727
+ "loss": 1.9552,
728
+ "step": 580
729
+ },
730
+ {
731
+ "epoch": 3.7,
732
+ "learning_rate": 0.00010936219058745934,
733
+ "loss": 1.9243,
734
+ "step": 585
735
+ },
736
+ {
737
+ "epoch": 3.73,
738
+ "learning_rate": 0.00011463735218542983,
739
+ "loss": 1.8552,
740
+ "step": 590
741
+ },
742
+ {
743
+ "epoch": 3.77,
744
+ "learning_rate": 0.00011945786275252523,
745
+ "loss": 2.067,
746
+ "step": 595
747
+ },
748
+ {
749
+ "epoch": 3.8,
750
+ "learning_rate": 0.00012377611637757444,
751
+ "loss": 2.0837,
752
+ "step": 600
753
+ },
754
+ {
755
+ "epoch": 3.83,
756
+ "learning_rate": 0.0001275494672877647,
757
+ "loss": 2.0373,
758
+ "step": 605
759
+ },
760
+ {
761
+ "epoch": 3.86,
762
+ "learning_rate": 0.0001307406510054549,
763
+ "loss": 1.8866,
764
+ "step": 610
765
+ },
766
+ {
767
+ "epoch": 3.89,
768
+ "learning_rate": 0.0001333181523609384,
769
+ "loss": 2.045,
770
+ "step": 615
771
+ },
772
+ {
773
+ "epoch": 3.92,
774
+ "learning_rate": 0.00013525651672677215,
775
+ "loss": 2.0499,
776
+ "step": 620
777
+ },
778
+ {
779
+ "epoch": 3.96,
780
+ "learning_rate": 0.00013653660140001365,
781
+ "loss": 1.9574,
782
+ "step": 625
783
+ },
784
+ {
785
+ "epoch": 3.99,
786
+ "learning_rate": 0.0001371457646497929,
787
+ "loss": 2.1066,
788
+ "step": 630
789
+ },
790
+ {
791
+ "epoch": 4.0,
792
+ "eval_loss": 2.209007978439331,
793
+ "eval_runtime": 2.7857,
794
+ "eval_samples_per_second": 76.822,
795
+ "eval_steps_per_second": 9.692,
796
+ "step": 632
797
+ },
798
+ {
799
+ "epoch": 4.02,
800
+ "learning_rate": 0.0001370779905632406,
801
+ "loss": 1.8936,
802
+ "step": 635
803
+ },
804
+ {
805
+ "epoch": 4.05,
806
+ "learning_rate": 0.00013633394845683248,
807
+ "loss": 1.9616,
808
+ "step": 640
809
+ },
810
+ {
811
+ "epoch": 4.08,
812
+ "learning_rate": 0.00013492098626642133,
813
+ "loss": 1.7865,
814
+ "step": 645
815
+ },
816
+ {
817
+ "epoch": 4.11,
818
+ "learning_rate": 0.00013285305798123475,
819
+ "loss": 1.8786,
820
+ "step": 650
821
+ },
822
+ {
823
+ "epoch": 4.15,
824
+ "learning_rate": 0.00013015058583847798,
825
+ "loss": 1.9233,
826
+ "step": 655
827
+ },
828
+ {
829
+ "epoch": 4.18,
830
+ "learning_rate": 0.00012684025863946756,
831
+ "loss": 1.8903,
832
+ "step": 660
833
+ },
834
+ {
835
+ "epoch": 4.21,
836
+ "learning_rate": 0.000122954768179064,
837
+ "loss": 1.895,
838
+ "step": 665
839
+ },
840
+ {
841
+ "epoch": 4.24,
842
+ "learning_rate": 0.00011853248639134728,
843
+ "loss": 1.8842,
844
+ "step": 670
845
+ },
846
+ {
847
+ "epoch": 4.27,
848
+ "learning_rate": 0.00011361708639994783,
849
+ "loss": 1.7602,
850
+ "step": 675
851
+ },
852
+ {
853
+ "epoch": 4.3,
854
+ "learning_rate": 0.00010825711121542465,
855
+ "loss": 1.7436,
856
+ "step": 680
857
+ },
858
+ {
859
+ "epoch": 4.34,
860
+ "learning_rate": 0.00010250549433910721,
861
+ "loss": 1.8129,
862
+ "step": 685
863
+ },
864
+ {
865
+ "epoch": 4.37,
866
+ "learning_rate": 9.64190370077714e-05,
867
+ "loss": 1.7891,
868
+ "step": 690
869
+ },
870
+ {
871
+ "epoch": 4.4,
872
+ "learning_rate": 9.005784724172477e-05,
873
+ "loss": 1.8476,
874
+ "step": 695
875
+ },
876
+ {
877
+ "epoch": 4.43,
878
+ "learning_rate": 8.348474623609351e-05,
879
+ "loss": 2.0649,
880
+ "step": 700
881
+ },
882
+ {
883
+ "epoch": 4.46,
884
+ "learning_rate": 7.676464795761073e-05,
885
+ "loss": 1.9673,
886
+ "step": 705
887
+ },
888
+ {
889
+ "epoch": 4.49,
890
+ "learning_rate": 6.996391807382385e-05,
891
+ "loss": 2.0106,
892
+ "step": 710
893
+ },
894
+ {
895
+ "epoch": 4.53,
896
+ "learning_rate": 6.314971854574042e-05,
897
+ "loss": 1.8144,
898
+ "step": 715
899
+ },
900
+ {
901
+ "epoch": 4.56,
902
+ "learning_rate": 5.638934435652005e-05,
903
+ "loss": 1.8997,
904
+ "step": 720
905
+ },
906
+ {
907
+ "epoch": 4.59,
908
+ "learning_rate": 4.974955892647975e-05,
909
+ "loss": 1.6943,
910
+ "step": 725
911
+ },
912
+ {
913
+ "epoch": 4.62,
914
+ "learning_rate": 4.329593477765313e-05,
915
+ "loss": 1.784,
916
+ "step": 730
917
+ },
918
+ {
919
+ "epoch": 4.65,
920
+ "learning_rate": 3.709220595930377e-05,
921
+ "loss": 1.7719,
922
+ "step": 735
923
+ },
924
+ {
925
+ "epoch": 4.68,
926
+ "learning_rate": 3.119963862964102e-05,
927
+ "loss": 1.6203,
928
+ "step": 740
929
+ },
930
+ {
931
+ "epoch": 4.72,
932
+ "learning_rate": 2.5676426009685593e-05,
933
+ "loss": 1.7432,
934
+ "step": 745
935
+ },
936
+ {
937
+ "epoch": 4.75,
938
+ "learning_rate": 2.0577113684537407e-05,
939
+ "loss": 1.6835,
940
+ "step": 750
941
+ },
942
+ {
943
+ "epoch": 4.78,
944
+ "learning_rate": 1.5952060927597964e-05,
945
+ "loss": 1.8013,
946
+ "step": 755
947
+ },
948
+ {
949
+ "epoch": 4.81,
950
+ "learning_rate": 1.1846943367546308e-05,
951
+ "loss": 1.6429,
952
+ "step": 760
953
+ },
954
+ {
955
+ "epoch": 4.84,
956
+ "learning_rate": 8.302301909581063e-06,
957
+ "loss": 1.8303,
958
+ "step": 765
959
+ },
960
+ {
961
+ "epoch": 4.87,
962
+ "learning_rate": 5.353142365645029e-06,
963
+ "loss": 1.6484,
964
+ "step": 770
965
+ },
966
+ {
967
+ "epoch": 4.91,
968
+ "learning_rate": 3.0285897475648074e-06,
969
+ "loss": 1.7701,
970
+ "step": 775
971
+ },
972
+ {
973
+ "epoch": 4.94,
974
+ "learning_rate": 1.3516006372019799e-06,
975
+ "loss": 1.7971,
976
+ "step": 780
977
+ },
978
+ {
979
+ "epoch": 4.97,
980
+ "learning_rate": 3.3873647416147947e-07,
981
+ "loss": 1.8325,
982
+ "step": 785
983
+ },
984
+ {
985
+ "epoch": 5.0,
986
+ "learning_rate": 0.0,
987
+ "loss": 1.7255,
988
+ "step": 790
989
+ },
990
+ {
991
+ "epoch": 5.0,
992
+ "eval_loss": 2.1195662021636963,
993
+ "eval_runtime": 2.7825,
994
+ "eval_samples_per_second": 76.91,
995
+ "eval_steps_per_second": 9.704,
996
+ "step": 790
997
+ }
998
+ ],
999
+ "max_steps": 790,
1000
+ "num_train_epochs": 5,
1001
+ "total_flos": 825029591040000.0,
1002
+ "trial_name": null,
1003
+ "trial_params": null
1004
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfb6e247e098310914adb6ffa99cbac18054688ed991eef0c2acb3531d8319c
3
+ size 2863
vocab.json ADDED
The diff for this file is too large to render. See raw diff