Commit
•
af98d26
1
Parent(s):
d3ad80e
huggingartists
Browse files- README.md +97 -0
- config.json +41 -0
- evaluation.txt +1 -0
- flax_model.msgpack +3 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +476 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
datasets:
|
4 |
+
- huggingartists/ed-sheeran
|
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('https://images.genius.com/b501daeff73d1b17610f47a5668f690a.1000x1000x1.jpg')">
|
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">Ed Sheeran</div>
|
22 |
+
<a href="https://genius.com/artists/ed-sheeran">
|
23 |
+
<div style="text-align: center; font-size: 14px;">@ed-sheeran</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 Ed Sheeran.
|
38 |
+
|
39 |
+
Dataset is available [here](https://huggingface.co/datasets/huggingartists/ed-sheeran).
|
40 |
+
And can be used with:
|
41 |
+
|
42 |
+
```python
|
43 |
+
from datasets import load_dataset
|
44 |
+
|
45 |
+
dataset = load_dataset("huggingartists/ed-sheeran")
|
46 |
+
```
|
47 |
+
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3nju68bo/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 Ed Sheeran's lyrics.
|
53 |
+
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3hu7zc76) for full transparency and reproducibility.
|
55 |
+
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3hu7zc76/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/ed-sheeran')
|
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/ed-sheeran")
|
75 |
+
|
76 |
+
model = AutoModelWithLMHead.from_pretrained("huggingartists/ed-sheeran")
|
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": 2.1315526962280273, "eval_runtime": 11.1681, "eval_samples_per_second": 21.49, "eval_steps_per_second": 2.686, "epoch": 2.0}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bd1e4b49be5befa1e0dbcd6c7522e02801edd0fede34bd98acb08ce188ee96e
|
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 sha256:40f6c163ebfd9d1f5bca6cc2a2eaf04603e6288a20821dde9af5d248ebf1dd74
|
3 |
+
size 995604017
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba0181cf09ea3b425c4d8d9e0d448c5bafda7f05108f2754231fda63ed3e32bd
|
3 |
+
size 510403817
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b908ae1e55b6327d6aa8ff7f06da00f6831d10c19233f0dc3e7021e5ab3b73ee
|
3 |
+
size 14567
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:245f47138040c4359eaa56bc85661c2cf7a49e523f034d3012d8002bb94e80f1
|
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 +1,476 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.1315526962280273,
|
3 |
+
"best_model_checkpoint": "output/ed-sheeran/checkpoint-370",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 370,
|
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": 0.0001369528677140173,
|
13 |
+
"loss": 3.3545,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.05,
|
18 |
+
"learning_rate": 0.0001362132514498528,
|
19 |
+
"loss": 3.1766,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.08,
|
24 |
+
"learning_rate": 0.00013498648015963804,
|
25 |
+
"loss": 3.1549,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.11,
|
30 |
+
"learning_rate": 0.00013328139275863037,
|
31 |
+
"loss": 3.3386,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.14,
|
36 |
+
"learning_rate": 0.0001311102744406261,
|
37 |
+
"loss": 2.866,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.16,
|
42 |
+
"learning_rate": 0.00012848876816285752,
|
43 |
+
"loss": 3.055,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.19,
|
48 |
+
"learning_rate": 0.00012543576193812758,
|
49 |
+
"loss": 3.0083,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.22,
|
54 |
+
"learning_rate": 0.00012197325274624495,
|
55 |
+
"loss": 3.0672,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.24,
|
60 |
+
"learning_rate": 0.00011812618804528037,
|
61 |
+
"loss": 2.8137,
|
62 |
+
"step": 45
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.27,
|
66 |
+
"learning_rate": 0.00011392228602455959,
|
67 |
+
"loss": 2.8218,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.3,
|
72 |
+
"learning_rate": 0.00010939183589447406,
|
73 |
+
"loss": 2.878,
|
74 |
+
"step": 55
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.32,
|
78 |
+
"learning_rate": 0.0001045674796520261,
|
79 |
+
"loss": 2.7698,
|
80 |
+
"step": 60
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.35,
|
84 |
+
"learning_rate": 9.948397689449238e-05,
|
85 |
+
"loss": 2.6731,
|
86 |
+
"step": 65
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.38,
|
90 |
+
"learning_rate": 9.417795437572918e-05,
|
91 |
+
"loss": 2.809,
|
92 |
+
"step": 70
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.41,
|
96 |
+
"learning_rate": 8.868764210957135e-05,
|
97 |
+
"loss": 3.0541,
|
98 |
+
"step": 75
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.43,
|
102 |
+
"learning_rate": 8.305259792170682e-05,
|
103 |
+
"loss": 2.9041,
|
104 |
+
"step": 80
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.46,
|
108 |
+
"learning_rate": 7.731342243463588e-05,
|
109 |
+
"loss": 2.5536,
|
110 |
+
"step": 85
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.49,
|
114 |
+
"learning_rate": 7.151146653925577e-05,
|
115 |
+
"loss": 2.6507,
|
116 |
+
"step": 90
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.51,
|
120 |
+
"learning_rate": 6.568853346074425e-05,
|
121 |
+
"loss": 2.5611,
|
122 |
+
"step": 95
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.54,
|
126 |
+
"learning_rate": 5.9886577565364115e-05,
|
127 |
+
"loss": 3.0623,
|
128 |
+
"step": 100
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.57,
|
132 |
+
"learning_rate": 5.4147402078293195e-05,
|
133 |
+
"loss": 2.8889,
|
134 |
+
"step": 105
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.59,
|
138 |
+
"learning_rate": 4.851235789042865e-05,
|
139 |
+
"loss": 2.5995,
|
140 |
+
"step": 110
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.62,
|
144 |
+
"learning_rate": 4.3022045624270836e-05,
|
145 |
+
"loss": 2.6762,
|
146 |
+
"step": 115
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.65,
|
150 |
+
"learning_rate": 3.77160231055076e-05,
|
151 |
+
"loss": 2.5995,
|
152 |
+
"step": 120
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.68,
|
156 |
+
"learning_rate": 3.263252034797391e-05,
|
157 |
+
"loss": 2.867,
|
158 |
+
"step": 125
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.7,
|
162 |
+
"learning_rate": 2.780816410552594e-05,
|
163 |
+
"loss": 2.8132,
|
164 |
+
"step": 130
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.73,
|
168 |
+
"learning_rate": 2.3277713975440426e-05,
|
169 |
+
"loss": 2.5726,
|
170 |
+
"step": 135
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.76,
|
174 |
+
"learning_rate": 1.9073811954719624e-05,
|
175 |
+
"loss": 2.3264,
|
176 |
+
"step": 140
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.78,
|
180 |
+
"learning_rate": 1.5226747253755063e-05,
|
181 |
+
"loss": 2.6873,
|
182 |
+
"step": 145
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.81,
|
186 |
+
"learning_rate": 1.1764238061872434e-05,
|
187 |
+
"loss": 2.6771,
|
188 |
+
"step": 150
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.84,
|
192 |
+
"learning_rate": 8.711231837142493e-06,
|
193 |
+
"loss": 2.7493,
|
194 |
+
"step": 155
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.86,
|
198 |
+
"learning_rate": 6.089725559373884e-06,
|
199 |
+
"loss": 2.6171,
|
200 |
+
"step": 160
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.89,
|
204 |
+
"learning_rate": 3.9186072413696235e-06,
|
205 |
+
"loss": 2.3292,
|
206 |
+
"step": 165
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.92,
|
210 |
+
"learning_rate": 2.2135198403619775e-06,
|
211 |
+
"loss": 2.8869,
|
212 |
+
"step": 170
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.95,
|
216 |
+
"learning_rate": 9.867485501471999e-07,
|
217 |
+
"loss": 2.572,
|
218 |
+
"step": 175
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.97,
|
222 |
+
"learning_rate": 2.471322859826806e-07,
|
223 |
+
"loss": 2.7326,
|
224 |
+
"step": 180
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.0,
|
228 |
+
"learning_rate": 0.0,
|
229 |
+
"loss": 2.5258,
|
230 |
+
"step": 185
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.0,
|
234 |
+
"eval_loss": 2.3434901237487793,
|
235 |
+
"eval_runtime": 11.1383,
|
236 |
+
"eval_samples_per_second": 21.547,
|
237 |
+
"eval_steps_per_second": 2.693,
|
238 |
+
"step": 185
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 1.03,
|
242 |
+
"learning_rate": 2.471322859826806e-07,
|
243 |
+
"loss": 2.821,
|
244 |
+
"step": 190
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.05,
|
248 |
+
"learning_rate": 9.867485501471922e-07,
|
249 |
+
"loss": 2.4731,
|
250 |
+
"step": 195
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 1.08,
|
254 |
+
"learning_rate": 2.2135198403619775e-06,
|
255 |
+
"loss": 2.2909,
|
256 |
+
"step": 200
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 1.11,
|
260 |
+
"learning_rate": 3.9186072413696235e-06,
|
261 |
+
"loss": 2.4008,
|
262 |
+
"step": 205
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 1.14,
|
266 |
+
"learning_rate": 6.0897255593738765e-06,
|
267 |
+
"loss": 2.7587,
|
268 |
+
"step": 210
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.16,
|
272 |
+
"learning_rate": 8.711231837142484e-06,
|
273 |
+
"loss": 2.4763,
|
274 |
+
"step": 215
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.19,
|
278 |
+
"learning_rate": 1.1764238061872427e-05,
|
279 |
+
"loss": 2.6535,
|
280 |
+
"step": 220
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 1.22,
|
284 |
+
"learning_rate": 1.5226747253755048e-05,
|
285 |
+
"loss": 2.4901,
|
286 |
+
"step": 225
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.24,
|
290 |
+
"learning_rate": 1.907381195471961e-05,
|
291 |
+
"loss": 2.5176,
|
292 |
+
"step": 230
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 1.27,
|
296 |
+
"learning_rate": 2.327771397544039e-05,
|
297 |
+
"loss": 2.214,
|
298 |
+
"step": 235
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 1.3,
|
302 |
+
"learning_rate": 2.7808164105525947e-05,
|
303 |
+
"loss": 2.4581,
|
304 |
+
"step": 240
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.32,
|
308 |
+
"learning_rate": 3.263252034797388e-05,
|
309 |
+
"loss": 2.4393,
|
310 |
+
"step": 245
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.35,
|
314 |
+
"learning_rate": 3.771602310550759e-05,
|
315 |
+
"loss": 2.3357,
|
316 |
+
"step": 250
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.38,
|
320 |
+
"learning_rate": 4.302204562427082e-05,
|
321 |
+
"loss": 2.1878,
|
322 |
+
"step": 255
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 1.41,
|
326 |
+
"learning_rate": 4.851235789042865e-05,
|
327 |
+
"loss": 2.5465,
|
328 |
+
"step": 260
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.43,
|
332 |
+
"learning_rate": 5.4147402078293195e-05,
|
333 |
+
"loss": 2.3914,
|
334 |
+
"step": 265
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 1.46,
|
338 |
+
"learning_rate": 5.988657756536409e-05,
|
339 |
+
"loss": 2.4728,
|
340 |
+
"step": 270
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 1.49,
|
344 |
+
"learning_rate": 6.56885334607442e-05,
|
345 |
+
"loss": 2.4695,
|
346 |
+
"step": 275
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.51,
|
350 |
+
"learning_rate": 7.151146653925577e-05,
|
351 |
+
"loss": 2.4773,
|
352 |
+
"step": 280
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.54,
|
356 |
+
"learning_rate": 7.731342243463588e-05,
|
357 |
+
"loss": 2.4631,
|
358 |
+
"step": 285
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 1.57,
|
362 |
+
"learning_rate": 8.305259792170678e-05,
|
363 |
+
"loss": 2.5178,
|
364 |
+
"step": 290
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 1.59,
|
368 |
+
"learning_rate": 8.868764210957132e-05,
|
369 |
+
"loss": 2.5653,
|
370 |
+
"step": 295
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.62,
|
374 |
+
"learning_rate": 9.417795437572915e-05,
|
375 |
+
"loss": 2.5981,
|
376 |
+
"step": 300
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 1.65,
|
380 |
+
"learning_rate": 9.948397689449238e-05,
|
381 |
+
"loss": 2.5919,
|
382 |
+
"step": 305
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 1.68,
|
386 |
+
"learning_rate": 0.0001045674796520261,
|
387 |
+
"loss": 2.4098,
|
388 |
+
"step": 310
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.7,
|
392 |
+
"learning_rate": 0.00010939183589447404,
|
393 |
+
"loss": 2.2096,
|
394 |
+
"step": 315
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.73,
|
398 |
+
"learning_rate": 0.00011392228602455961,
|
399 |
+
"loss": 2.5258,
|
400 |
+
"step": 320
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 1.76,
|
404 |
+
"learning_rate": 0.00011812618804528036,
|
405 |
+
"loss": 2.3155,
|
406 |
+
"step": 325
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 1.78,
|
410 |
+
"learning_rate": 0.00012197325274624495,
|
411 |
+
"loss": 2.2606,
|
412 |
+
"step": 330
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.81,
|
416 |
+
"learning_rate": 0.00012543576193812755,
|
417 |
+
"loss": 2.2948,
|
418 |
+
"step": 335
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 1.84,
|
422 |
+
"learning_rate": 0.00012848876816285752,
|
423 |
+
"loss": 2.5757,
|
424 |
+
"step": 340
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 1.86,
|
428 |
+
"learning_rate": 0.0001311102744406261,
|
429 |
+
"loss": 2.1925,
|
430 |
+
"step": 345
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.89,
|
434 |
+
"learning_rate": 0.00013328139275863037,
|
435 |
+
"loss": 2.1671,
|
436 |
+
"step": 350
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.92,
|
440 |
+
"learning_rate": 0.00013498648015963801,
|
441 |
+
"loss": 2.729,
|
442 |
+
"step": 355
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"epoch": 1.95,
|
446 |
+
"learning_rate": 0.0001362132514498528,
|
447 |
+
"loss": 2.2679,
|
448 |
+
"step": 360
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 1.97,
|
452 |
+
"learning_rate": 0.0001369528677140173,
|
453 |
+
"loss": 2.0086,
|
454 |
+
"step": 365
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 2.0,
|
458 |
+
"learning_rate": 0.0001372,
|
459 |
+
"loss": 2.2398,
|
460 |
+
"step": 370
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 2.0,
|
464 |
+
"eval_loss": 2.1315526962280273,
|
465 |
+
"eval_runtime": 11.157,
|
466 |
+
"eval_samples_per_second": 21.511,
|
467 |
+
"eval_steps_per_second": 2.689,
|
468 |
+
"step": 370
|
469 |
+
}
|
470 |
+
],
|
471 |
+
"max_steps": 370,
|
472 |
+
"num_train_epochs": 2,
|
473 |
+
"total_flos": 386450915328000.0,
|
474 |
+
"trial_name": null,
|
475 |
+
"trial_params": null
|
476 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4492ed4b88afe77a3ce33ee9e16201f5c860c1fb236ce0e002a1931bd9e7fdb
|
3 |
+
size 2671
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|