Commit
•
0ee9a7e
1
Parent(s):
b7beb56
huggingartists
Browse files- README.md +97 -0
- config.json +42 -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 +1004 -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/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('https://images.genius.com/3c1f124fcbbc2857a95e513fb34cc5a8.400x400x1.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">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
|
|