Commit
•
bc4aa5d
1
Parent(s):
5cb5875
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 +320 -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/muse
|
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/26f575585ec649d88d09a1e402bb936b.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">Muse</div>
|
22 |
+
<a href="https://genius.com/artists/muse">
|
23 |
+
<div style="text-align: center; font-size: 14px;">@muse</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 Muse.
|
38 |
+
|
39 |
+
Dataset is available [here](https://huggingface.co/datasets/huggingartists/muse).
|
40 |
+
And can be used with:
|
41 |
+
|
42 |
+
```python
|
43 |
+
from datasets import load_dataset
|
44 |
+
|
45 |
+
dataset = load_dataset("huggingartists/muse")
|
46 |
+
```
|
47 |
+
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3w58rwod/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 Muse's lyrics.
|
53 |
+
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3j03atcr) for full transparency and reproducibility.
|
55 |
+
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3j03atcr/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/muse')
|
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/muse")
|
75 |
+
|
76 |
+
model = AutoModelWithLMHead.from_pretrained("huggingartists/muse")
|
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": "4.10.3",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
evaluation.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eval_loss": 2.3269803524017334, "eval_runtime": 2.0389, "eval_samples_per_second": 20.6, "eval_steps_per_second": 2.943, "epoch": 100.0}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b056be70daa0c9b157c0e26ac48b2f06c4e5212c52b9f67a36a83f017417f67d
|
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:e13d67d67e40251ee94e84a5741483ffc44566e986b76e3c0e77d65319fd10b3
|
3 |
+
size 995603825
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5f36b4aa1dea8901090d21c164984bd0ab489dc6a881344c90af543c12dcfee
|
3 |
+
size 510403817
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82f87ce21bae77d6d5460bfce067ada28ee1585e023f4af7e6e79850f7cfa5b9
|
3 |
+
size 14567
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94ddf4d086675f377d675c419847ad97dc0ca3884a3889ded4e2611e2e9cf05c
|
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 +1,320 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.3269803524017334,
|
3 |
+
"best_model_checkpoint": "output/muse/checkpoint-200",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"global_step": 200,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.2,
|
12 |
+
"learning_rate": 0.0001240985658141214,
|
13 |
+
"loss": 3.1279,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.4,
|
18 |
+
"learning_rate": 8.97985658141214e-05,
|
19 |
+
"loss": 2.8709,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.6,
|
24 |
+
"learning_rate": 4.740143418587861e-05,
|
25 |
+
"loss": 2.8349,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.8,
|
30 |
+
"learning_rate": 1.3101434185878613e-05,
|
31 |
+
"loss": 2.5989,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.0,
|
36 |
+
"learning_rate": 0.0,
|
37 |
+
"loss": 2.849,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.0,
|
42 |
+
"eval_loss": 2.7842092514038086,
|
43 |
+
"eval_runtime": 1.8206,
|
44 |
+
"eval_samples_per_second": 23.069,
|
45 |
+
"eval_steps_per_second": 3.296,
|
46 |
+
"step": 25
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.2,
|
50 |
+
"learning_rate": 1.3101434185878598e-05,
|
51 |
+
"loss": 2.4736,
|
52 |
+
"step": 30
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 1.4,
|
56 |
+
"learning_rate": 4.74014341858786e-05,
|
57 |
+
"loss": 2.628,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.6,
|
62 |
+
"learning_rate": 8.979856581412138e-05,
|
63 |
+
"loss": 2.6224,
|
64 |
+
"step": 40
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 1.8,
|
68 |
+
"learning_rate": 0.0001240985658141214,
|
69 |
+
"loss": 2.6052,
|
70 |
+
"step": 45
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 2.0,
|
74 |
+
"learning_rate": 0.0001372,
|
75 |
+
"loss": 2.4193,
|
76 |
+
"step": 50
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 2.0,
|
80 |
+
"eval_loss": 2.6401476860046387,
|
81 |
+
"eval_runtime": 1.8685,
|
82 |
+
"eval_samples_per_second": 22.478,
|
83 |
+
"eval_steps_per_second": 3.211,
|
84 |
+
"step": 50
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 2.2,
|
88 |
+
"learning_rate": 0.00012409856581412136,
|
89 |
+
"loss": 2.1791,
|
90 |
+
"step": 55
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.4,
|
94 |
+
"learning_rate": 8.979856581412141e-05,
|
95 |
+
"loss": 2.2449,
|
96 |
+
"step": 60
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 2.6,
|
100 |
+
"learning_rate": 4.7401434185878625e-05,
|
101 |
+
"loss": 2.1171,
|
102 |
+
"step": 65
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 2.8,
|
106 |
+
"learning_rate": 1.310143418587862e-05,
|
107 |
+
"loss": 2.1624,
|
108 |
+
"step": 70
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 3.0,
|
112 |
+
"learning_rate": 0.0,
|
113 |
+
"loss": 2.2355,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.0,
|
118 |
+
"eval_loss": 2.5702805519104004,
|
119 |
+
"eval_runtime": 1.8707,
|
120 |
+
"eval_samples_per_second": 22.451,
|
121 |
+
"eval_steps_per_second": 3.207,
|
122 |
+
"step": 75
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 3.2,
|
126 |
+
"learning_rate": 1.310143418587859e-05,
|
127 |
+
"loss": 2.1067,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.4,
|
132 |
+
"learning_rate": 4.740143418587858e-05,
|
133 |
+
"loss": 2.1021,
|
134 |
+
"step": 85
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.6,
|
138 |
+
"learning_rate": 8.979856581412137e-05,
|
139 |
+
"loss": 2.0876,
|
140 |
+
"step": 90
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 3.8,
|
144 |
+
"learning_rate": 0.00012409856581412136,
|
145 |
+
"loss": 2.0067,
|
146 |
+
"step": 95
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 4.0,
|
150 |
+
"learning_rate": 0.0001372,
|
151 |
+
"loss": 1.8774,
|
152 |
+
"step": 100
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 4.0,
|
156 |
+
"eval_loss": 2.4998016357421875,
|
157 |
+
"eval_runtime": 1.8837,
|
158 |
+
"eval_samples_per_second": 22.296,
|
159 |
+
"eval_steps_per_second": 3.185,
|
160 |
+
"step": 100
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 4.2,
|
164 |
+
"learning_rate": 0.00012409856581412142,
|
165 |
+
"loss": 1.8595,
|
166 |
+
"step": 105
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 4.4,
|
170 |
+
"learning_rate": 8.97985658141213e-05,
|
171 |
+
"loss": 1.8355,
|
172 |
+
"step": 110
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 4.6,
|
176 |
+
"learning_rate": 4.740143418587876e-05,
|
177 |
+
"loss": 1.8151,
|
178 |
+
"step": 115
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 4.8,
|
182 |
+
"learning_rate": 1.3101434185878628e-05,
|
183 |
+
"loss": 1.6825,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 5.0,
|
188 |
+
"learning_rate": 0.0,
|
189 |
+
"loss": 1.828,
|
190 |
+
"step": 125
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 5.0,
|
194 |
+
"eval_loss": 2.455634355545044,
|
195 |
+
"eval_runtime": 1.8736,
|
196 |
+
"eval_samples_per_second": 22.417,
|
197 |
+
"eval_steps_per_second": 3.202,
|
198 |
+
"step": 125
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 5.2,
|
202 |
+
"learning_rate": 1.3101434185878583e-05,
|
203 |
+
"loss": 1.7296,
|
204 |
+
"step": 130
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 5.4,
|
208 |
+
"learning_rate": 4.740143418587856e-05,
|
209 |
+
"loss": 1.5323,
|
210 |
+
"step": 135
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 5.6,
|
214 |
+
"learning_rate": 8.979856581412136e-05,
|
215 |
+
"loss": 1.7239,
|
216 |
+
"step": 140
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 5.8,
|
220 |
+
"learning_rate": 0.00012409856581412136,
|
221 |
+
"loss": 1.7961,
|
222 |
+
"step": 145
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 6.0,
|
226 |
+
"learning_rate": 0.0001372,
|
227 |
+
"loss": 1.5753,
|
228 |
+
"step": 150
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 6.0,
|
232 |
+
"eval_loss": 2.415633201599121,
|
233 |
+
"eval_runtime": 1.8716,
|
234 |
+
"eval_samples_per_second": 22.44,
|
235 |
+
"eval_steps_per_second": 3.206,
|
236 |
+
"step": 150
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 6.2,
|
240 |
+
"learning_rate": 0.00012409856581412142,
|
241 |
+
"loss": 1.5374,
|
242 |
+
"step": 155
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 6.4,
|
246 |
+
"learning_rate": 8.979856581412144e-05,
|
247 |
+
"loss": 1.5005,
|
248 |
+
"step": 160
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 6.6,
|
252 |
+
"learning_rate": 4.740143418587866e-05,
|
253 |
+
"loss": 1.3827,
|
254 |
+
"step": 165
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 6.8,
|
258 |
+
"learning_rate": 1.3101434185878644e-05,
|
259 |
+
"loss": 1.5368,
|
260 |
+
"step": 170
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 7.0,
|
264 |
+
"learning_rate": 0.0,
|
265 |
+
"loss": 1.4028,
|
266 |
+
"step": 175
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 7.0,
|
270 |
+
"eval_loss": 2.395447254180908,
|
271 |
+
"eval_runtime": 1.8726,
|
272 |
+
"eval_samples_per_second": 22.429,
|
273 |
+
"eval_steps_per_second": 3.204,
|
274 |
+
"step": 175
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 7.2,
|
278 |
+
"learning_rate": 1.3101434185878574e-05,
|
279 |
+
"loss": 1.4826,
|
280 |
+
"step": 180
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 7.4,
|
284 |
+
"learning_rate": 4.7401434185878544e-05,
|
285 |
+
"loss": 1.3107,
|
286 |
+
"step": 185
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 7.6,
|
290 |
+
"learning_rate": 8.979856581412133e-05,
|
291 |
+
"loss": 1.3342,
|
292 |
+
"step": 190
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 7.8,
|
296 |
+
"learning_rate": 0.00012409856581412136,
|
297 |
+
"loss": 1.3195,
|
298 |
+
"step": 195
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 8.0,
|
302 |
+
"learning_rate": 0.0001372,
|
303 |
+
"loss": 1.2922,
|
304 |
+
"step": 200
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 8.0,
|
308 |
+
"eval_loss": 2.3269803524017334,
|
309 |
+
"eval_runtime": 1.8745,
|
310 |
+
"eval_samples_per_second": 22.406,
|
311 |
+
"eval_steps_per_second": 3.201,
|
312 |
+
"step": 200
|
313 |
+
}
|
314 |
+
],
|
315 |
+
"max_steps": 2500,
|
316 |
+
"num_train_epochs": 100,
|
317 |
+
"total_flos": 209033625600000.0,
|
318 |
+
"trial_name": null,
|
319 |
+
"trial_params": null
|
320 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6271ac7a629656367a6532235ac16fadc9c75e5013ae73d36e2e159560675238
|
3 |
+
size 2671
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|