AlekseyKorshuk
commited on
Commit
•
14ac1f8
1
Parent(s):
684741f
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 +1816 -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/25-17
|
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/4fedc5dd2830a874a5274bf1cac62002.1000x1000x1.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">25/17</div>
|
22 |
+
<a href="https://genius.com/artists/25-17">
|
23 |
+
<div style="text-align: center; font-size: 14px;">@25-17</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 25/17.
|
38 |
+
|
39 |
+
Dataset is available [here](https://huggingface.co/datasets/huggingartists/25-17).
|
40 |
+
And can be used with:
|
41 |
+
|
42 |
+
```python
|
43 |
+
from datasets import load_dataset
|
44 |
+
|
45 |
+
dataset = load_dataset("huggingartists/25-17")
|
46 |
+
```
|
47 |
+
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1iuytbjp/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 25/17's lyrics.
|
53 |
+
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/knv4l4gw) for full transparency and reproducibility.
|
55 |
+
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/knv4l4gw/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/25-17')
|
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/25-17")
|
75 |
+
|
76 |
+
model = AutoModelWithLMHead.from_pretrained("huggingartists/25-17")
|
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": "4.10.0",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
evaluation.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eval_loss": 1.6076909303665161, "eval_runtime": 11.2247, "eval_samples_per_second": 22.272, "eval_steps_per_second": 2.851, "epoch": 10.0}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e30f8e3e98d7e1eab1534464337cf1df83454afdc21bfc611403eca4b6a6b55
|
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 sha256:43b7fdb4985b5042f3736c16d0dd1a10c208219dfb95c8d516960509f84117c5
|
3 |
+
size 995604017
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:503e863a0ddc535df35fe61eb7291cc415bc6d4af03f7e5b2d6a23012047cd05
|
3 |
+
size 510403817
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8839fa7c1d5ac091af7e102d7073e13e2c146e3461199c57b41b7a67125b30f9
|
3 |
+
size 14567
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdcbe2cd667ec2ff2d044736131108f10674ad88ef2e532728468bea674f4cb8
|
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 +1,1816 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.6076909303665161,
|
3 |
+
"best_model_checkpoint": "output/25-17/checkpoint-1440",
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 1440,
|
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": 0.0001368696722497127,
|
13 |
+
"loss": 2.507,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"learning_rate": 0.0001358818702356616,
|
19 |
+
"loss": 2.2788,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.09,
|
24 |
+
"learning_rate": 0.00013424610703122953,
|
25 |
+
"loss": 2.1702,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.12,
|
30 |
+
"learning_rate": 0.00013197813593027427,
|
31 |
+
"loss": 2.0479,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.16,
|
36 |
+
"learning_rate": 0.00012909979873429716,
|
37 |
+
"loss": 2.0181,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.19,
|
42 |
+
"learning_rate": 0.0001256388154039546,
|
43 |
+
"loss": 2.0362,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.22,
|
48 |
+
"learning_rate": 0.00012162851710068375,
|
49 |
+
"loss": 2.1176,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.25,
|
54 |
+
"learning_rate": 0.00011710752518939715,
|
55 |
+
"loss": 1.9178,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.28,
|
60 |
+
"learning_rate": 0.00011211937929362608,
|
61 |
+
"loss": 2.0539,
|
62 |
+
"step": 45
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.31,
|
66 |
+
"learning_rate": 0.00010671211798514472,
|
67 |
+
"loss": 1.9318,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.34,
|
72 |
+
"learning_rate": 0.00010093781614626346,
|
73 |
+
"loss": 2.0317,
|
74 |
+
"step": 55
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.38,
|
78 |
+
"learning_rate": 9.485208346024516e-05,
|
79 |
+
"loss": 1.9618,
|
80 |
+
"step": 60
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.41,
|
84 |
+
"learning_rate": 8.851352885965611e-05,
|
85 |
+
"loss": 1.9205,
|
86 |
+
"step": 65
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.44,
|
90 |
+
"learning_rate": 8.19831960903064e-05,
|
91 |
+
"loss": 1.8521,
|
92 |
+
"step": 70
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.47,
|
96 |
+
"learning_rate": 7.532397582660788e-05,
|
97 |
+
"loss": 1.8699,
|
98 |
+
"step": 75
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.5,
|
102 |
+
"learning_rate": 6.86e-05,
|
103 |
+
"loss": 1.9852,
|
104 |
+
"step": 80
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.53,
|
108 |
+
"learning_rate": 6.187602417339214e-05,
|
109 |
+
"loss": 1.8576,
|
110 |
+
"step": 85
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.56,
|
114 |
+
"learning_rate": 5.52168039096936e-05,
|
115 |
+
"loss": 1.93,
|
116 |
+
"step": 90
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.59,
|
120 |
+
"learning_rate": 4.8686471140343896e-05,
|
121 |
+
"loss": 2.0017,
|
122 |
+
"step": 95
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.62,
|
126 |
+
"learning_rate": 4.2347916539754844e-05,
|
127 |
+
"loss": 1.9962,
|
128 |
+
"step": 100
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.66,
|
132 |
+
"learning_rate": 3.6262183853736556e-05,
|
133 |
+
"loss": 1.9731,
|
134 |
+
"step": 105
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.69,
|
138 |
+
"learning_rate": 3.0487882014855305e-05,
|
139 |
+
"loss": 1.9197,
|
140 |
+
"step": 110
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.72,
|
144 |
+
"learning_rate": 2.5080620706373927e-05,
|
145 |
+
"loss": 1.8595,
|
146 |
+
"step": 115
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.75,
|
150 |
+
"learning_rate": 2.0092474810602843e-05,
|
151 |
+
"loss": 1.925,
|
152 |
+
"step": 120
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.78,
|
156 |
+
"learning_rate": 1.557148289931624e-05,
|
157 |
+
"loss": 1.9259,
|
158 |
+
"step": 125
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.81,
|
162 |
+
"learning_rate": 1.1561184596045389e-05,
|
163 |
+
"loss": 1.8582,
|
164 |
+
"step": 130
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.84,
|
168 |
+
"learning_rate": 8.100201265702852e-06,
|
169 |
+
"loss": 1.8858,
|
170 |
+
"step": 135
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.88,
|
174 |
+
"learning_rate": 5.22186406972573e-06,
|
175 |
+
"loss": 1.8995,
|
176 |
+
"step": 140
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.91,
|
180 |
+
"learning_rate": 2.953892968770475e-06,
|
181 |
+
"loss": 1.9137,
|
182 |
+
"step": 145
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.94,
|
186 |
+
"learning_rate": 1.3181297643383925e-06,
|
187 |
+
"loss": 1.8872,
|
188 |
+
"step": 150
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.97,
|
192 |
+
"learning_rate": 3.303277502872983e-07,
|
193 |
+
"loss": 1.8137,
|
194 |
+
"step": 155
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.0,
|
198 |
+
"learning_rate": 0.0,
|
199 |
+
"loss": 1.9111,
|
200 |
+
"step": 160
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.0,
|
204 |
+
"eval_loss": 1.8344975709915161,
|
205 |
+
"eval_runtime": 11.0703,
|
206 |
+
"eval_samples_per_second": 22.583,
|
207 |
+
"eval_steps_per_second": 2.891,
|
208 |
+
"step": 160
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 1.03,
|
212 |
+
"learning_rate": 3.303277502872907e-07,
|
213 |
+
"loss": 1.8983,
|
214 |
+
"step": 165
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 1.06,
|
218 |
+
"learning_rate": 1.3181297643383925e-06,
|
219 |
+
"loss": 1.8515,
|
220 |
+
"step": 170
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 1.09,
|
224 |
+
"learning_rate": 2.9538929687704672e-06,
|
225 |
+
"loss": 1.8853,
|
226 |
+
"step": 175
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.12,
|
230 |
+
"learning_rate": 5.2218640697257225e-06,
|
231 |
+
"loss": 1.8512,
|
232 |
+
"step": 180
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.16,
|
236 |
+
"learning_rate": 8.100201265702843e-06,
|
237 |
+
"loss": 1.8684,
|
238 |
+
"step": 185
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 1.19,
|
242 |
+
"learning_rate": 1.1561184596045382e-05,
|
243 |
+
"loss": 1.8168,
|
244 |
+
"step": 190
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.22,
|
248 |
+
"learning_rate": 1.5571482899316234e-05,
|
249 |
+
"loss": 1.876,
|
250 |
+
"step": 195
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 1.25,
|
254 |
+
"learning_rate": 2.009247481060283e-05,
|
255 |
+
"loss": 1.8544,
|
256 |
+
"step": 200
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 1.28,
|
260 |
+
"learning_rate": 2.508062070637389e-05,
|
261 |
+
"loss": 1.7766,
|
262 |
+
"step": 205
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 1.31,
|
266 |
+
"learning_rate": 3.048788201485529e-05,
|
267 |
+
"loss": 1.9737,
|
268 |
+
"step": 210
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.34,
|
272 |
+
"learning_rate": 3.626218385373654e-05,
|
273 |
+
"loss": 1.8173,
|
274 |
+
"step": 215
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.38,
|
278 |
+
"learning_rate": 4.234791653975481e-05,
|
279 |
+
"loss": 1.7998,
|
280 |
+
"step": 220
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 1.41,
|
284 |
+
"learning_rate": 4.8686471140343875e-05,
|
285 |
+
"loss": 1.8463,
|
286 |
+
"step": 225
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.44,
|
290 |
+
"learning_rate": 5.5216803909693576e-05,
|
291 |
+
"loss": 1.8385,
|
292 |
+
"step": 230
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 1.47,
|
296 |
+
"learning_rate": 6.187602417339216e-05,
|
297 |
+
"loss": 1.8556,
|
298 |
+
"step": 235
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 1.5,
|
302 |
+
"learning_rate": 6.859999999999999e-05,
|
303 |
+
"loss": 1.7617,
|
304 |
+
"step": 240
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.53,
|
308 |
+
"learning_rate": 7.532397582660782e-05,
|
309 |
+
"loss": 1.7911,
|
310 |
+
"step": 245
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.56,
|
314 |
+
"learning_rate": 8.19831960903064e-05,
|
315 |
+
"loss": 1.7528,
|
316 |
+
"step": 250
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.59,
|
320 |
+
"learning_rate": 8.85135288596561e-05,
|
321 |
+
"loss": 1.8805,
|
322 |
+
"step": 255
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 1.62,
|
326 |
+
"learning_rate": 9.485208346024518e-05,
|
327 |
+
"loss": 1.9808,
|
328 |
+
"step": 260
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.66,
|
332 |
+
"learning_rate": 0.00010093781614626343,
|
333 |
+
"loss": 1.8408,
|
334 |
+
"step": 265
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 1.69,
|
338 |
+
"learning_rate": 0.00010671211798514468,
|
339 |
+
"loss": 1.9133,
|
340 |
+
"step": 270
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 1.72,
|
344 |
+
"learning_rate": 0.00011211937929362609,
|
345 |
+
"loss": 1.8695,
|
346 |
+
"step": 275
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.75,
|
350 |
+
"learning_rate": 0.00011710752518939715,
|
351 |
+
"loss": 1.8373,
|
352 |
+
"step": 280
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.78,
|
356 |
+
"learning_rate": 0.00012162851710068373,
|
357 |
+
"loss": 1.7998,
|
358 |
+
"step": 285
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 1.81,
|
362 |
+
"learning_rate": 0.0001256388154039546,
|
363 |
+
"loss": 1.9473,
|
364 |
+
"step": 290
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 1.84,
|
368 |
+
"learning_rate": 0.00012909979873429716,
|
369 |
+
"loss": 1.8208,
|
370 |
+
"step": 295
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.88,
|
374 |
+
"learning_rate": 0.00013197813593027427,
|
375 |
+
"loss": 1.8304,
|
376 |
+
"step": 300
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 1.91,
|
380 |
+
"learning_rate": 0.00013424610703122953,
|
381 |
+
"loss": 1.7997,
|
382 |
+
"step": 305
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 1.94,
|
386 |
+
"learning_rate": 0.0001358818702356616,
|
387 |
+
"loss": 1.8045,
|
388 |
+
"step": 310
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.97,
|
392 |
+
"learning_rate": 0.0001368696722497127,
|
393 |
+
"loss": 1.8645,
|
394 |
+
"step": 315
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 2.0,
|
398 |
+
"learning_rate": 0.0001372,
|
399 |
+
"loss": 1.8994,
|
400 |
+
"step": 320
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 2.0,
|
404 |
+
"eval_loss": 1.8014581203460693,
|
405 |
+
"eval_runtime": 11.0626,
|
406 |
+
"eval_samples_per_second": 22.599,
|
407 |
+
"eval_steps_per_second": 2.893,
|
408 |
+
"step": 320
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.03,
|
412 |
+
"learning_rate": 0.0001368696722497127,
|
413 |
+
"loss": 1.7444,
|
414 |
+
"step": 325
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 2.06,
|
418 |
+
"learning_rate": 0.0001358818702356616,
|
419 |
+
"loss": 1.8609,
|
420 |
+
"step": 330
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 2.09,
|
424 |
+
"learning_rate": 0.00013424610703122953,
|
425 |
+
"loss": 1.6945,
|
426 |
+
"step": 335
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 2.12,
|
430 |
+
"learning_rate": 0.00013197813593027427,
|
431 |
+
"loss": 1.7166,
|
432 |
+
"step": 340
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 2.16,
|
436 |
+
"learning_rate": 0.00012909979873429716,
|
437 |
+
"loss": 1.738,
|
438 |
+
"step": 345
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 2.19,
|
442 |
+
"learning_rate": 0.0001256388154039546,
|
443 |
+
"loss": 1.8311,
|
444 |
+
"step": 350
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.22,
|
448 |
+
"learning_rate": 0.00012162851710068375,
|
449 |
+
"loss": 1.7936,
|
450 |
+
"step": 355
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.25,
|
454 |
+
"learning_rate": 0.00011710752518939717,
|
455 |
+
"loss": 1.7759,
|
456 |
+
"step": 360
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 2.28,
|
460 |
+
"learning_rate": 0.00011211937929362612,
|
461 |
+
"loss": 1.8082,
|
462 |
+
"step": 365
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 2.31,
|
466 |
+
"learning_rate": 0.00010671211798514472,
|
467 |
+
"loss": 1.7213,
|
468 |
+
"step": 370
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 2.34,
|
472 |
+
"learning_rate": 0.00010093781614626346,
|
473 |
+
"loss": 1.7968,
|
474 |
+
"step": 375
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 2.38,
|
478 |
+
"learning_rate": 9.48520834602452e-05,
|
479 |
+
"loss": 1.8208,
|
480 |
+
"step": 380
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 2.41,
|
484 |
+
"learning_rate": 8.851352885965613e-05,
|
485 |
+
"loss": 1.6572,
|
486 |
+
"step": 385
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 2.44,
|
490 |
+
"learning_rate": 8.198319609030645e-05,
|
491 |
+
"loss": 1.8122,
|
492 |
+
"step": 390
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.47,
|
496 |
+
"learning_rate": 7.532397582660786e-05,
|
497 |
+
"loss": 1.7665,
|
498 |
+
"step": 395
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 2.5,
|
502 |
+
"learning_rate": 6.860000000000001e-05,
|
503 |
+
"loss": 1.8777,
|
504 |
+
"step": 400
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 2.53,
|
508 |
+
"learning_rate": 6.187602417339219e-05,
|
509 |
+
"loss": 1.6834,
|
510 |
+
"step": 405
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 2.56,
|
514 |
+
"learning_rate": 5.5216803909693664e-05,
|
515 |
+
"loss": 1.7483,
|
516 |
+
"step": 410
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 2.59,
|
520 |
+
"learning_rate": 4.868647114034385e-05,
|
521 |
+
"loss": 1.6818,
|
522 |
+
"step": 415
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 2.62,
|
526 |
+
"learning_rate": 4.234791653975484e-05,
|
527 |
+
"loss": 1.7057,
|
528 |
+
"step": 420
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 2.66,
|
532 |
+
"learning_rate": 3.6262183853736576e-05,
|
533 |
+
"loss": 1.8172,
|
534 |
+
"step": 425
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 2.69,
|
538 |
+
"learning_rate": 3.0487882014855322e-05,
|
539 |
+
"loss": 1.7146,
|
540 |
+
"step": 430
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 2.72,
|
544 |
+
"learning_rate": 2.5080620706373965e-05,
|
545 |
+
"loss": 1.6912,
|
546 |
+
"step": 435
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 2.75,
|
550 |
+
"learning_rate": 2.0092474810602897e-05,
|
551 |
+
"loss": 1.7294,
|
552 |
+
"step": 440
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 2.78,
|
556 |
+
"learning_rate": 1.5571482899316234e-05,
|
557 |
+
"loss": 1.7523,
|
558 |
+
"step": 445
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 2.81,
|
562 |
+
"learning_rate": 1.1561184596045404e-05,
|
563 |
+
"loss": 1.768,
|
564 |
+
"step": 450
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 2.84,
|
568 |
+
"learning_rate": 8.100201265702858e-06,
|
569 |
+
"loss": 1.6234,
|
570 |
+
"step": 455
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 2.88,
|
574 |
+
"learning_rate": 5.221864069725753e-06,
|
575 |
+
"loss": 1.7473,
|
576 |
+
"step": 460
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 2.91,
|
580 |
+
"learning_rate": 2.9538929687704977e-06,
|
581 |
+
"loss": 1.8052,
|
582 |
+
"step": 465
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 2.94,
|
586 |
+
"learning_rate": 1.318129764338385e-06,
|
587 |
+
"loss": 1.6156,
|
588 |
+
"step": 470
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 2.97,
|
592 |
+
"learning_rate": 3.303277502872907e-07,
|
593 |
+
"loss": 1.6744,
|
594 |
+
"step": 475
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 3.0,
|
598 |
+
"learning_rate": 0.0,
|
599 |
+
"loss": 1.7333,
|
600 |
+
"step": 480
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 3.0,
|
604 |
+
"eval_loss": 1.7123054265975952,
|
605 |
+
"eval_runtime": 11.0761,
|
606 |
+
"eval_samples_per_second": 22.571,
|
607 |
+
"eval_steps_per_second": 2.889,
|
608 |
+
"step": 480
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 3.03,
|
612 |
+
"learning_rate": 3.303277502872907e-07,
|
613 |
+
"loss": 1.6392,
|
614 |
+
"step": 485
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 3.06,
|
618 |
+
"learning_rate": 1.3181297643383773e-06,
|
619 |
+
"loss": 1.6924,
|
620 |
+
"step": 490
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 3.09,
|
624 |
+
"learning_rate": 2.9538929687704825e-06,
|
625 |
+
"loss": 1.667,
|
626 |
+
"step": 495
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 3.12,
|
630 |
+
"learning_rate": 5.22186406972573e-06,
|
631 |
+
"loss": 1.6132,
|
632 |
+
"step": 500
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 3.16,
|
636 |
+
"learning_rate": 8.100201265702836e-06,
|
637 |
+
"loss": 1.6915,
|
638 |
+
"step": 505
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 3.19,
|
642 |
+
"learning_rate": 1.1561184596045374e-05,
|
643 |
+
"loss": 1.6571,
|
644 |
+
"step": 510
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 3.22,
|
648 |
+
"learning_rate": 1.5571482899316204e-05,
|
649 |
+
"loss": 1.5234,
|
650 |
+
"step": 515
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 3.25,
|
654 |
+
"learning_rate": 2.0092474810602867e-05,
|
655 |
+
"loss": 1.6652,
|
656 |
+
"step": 520
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 3.28,
|
660 |
+
"learning_rate": 2.5080620706373927e-05,
|
661 |
+
"loss": 1.6542,
|
662 |
+
"step": 525
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 3.31,
|
666 |
+
"learning_rate": 3.0487882014855275e-05,
|
667 |
+
"loss": 1.6505,
|
668 |
+
"step": 530
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 3.34,
|
672 |
+
"learning_rate": 3.626218385373653e-05,
|
673 |
+
"loss": 1.6654,
|
674 |
+
"step": 535
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 3.38,
|
678 |
+
"learning_rate": 4.234791653975479e-05,
|
679 |
+
"loss": 1.8283,
|
680 |
+
"step": 540
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 3.41,
|
684 |
+
"learning_rate": 4.868647114034381e-05,
|
685 |
+
"loss": 1.6716,
|
686 |
+
"step": 545
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 3.44,
|
690 |
+
"learning_rate": 5.5216803909693624e-05,
|
691 |
+
"loss": 1.7675,
|
692 |
+
"step": 550
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 3.47,
|
696 |
+
"learning_rate": 6.187602417339214e-05,
|
697 |
+
"loss": 1.6728,
|
698 |
+
"step": 555
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 3.5,
|
702 |
+
"learning_rate": 6.859999999999997e-05,
|
703 |
+
"loss": 1.6103,
|
704 |
+
"step": 560
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 3.53,
|
708 |
+
"learning_rate": 7.53239758266078e-05,
|
709 |
+
"loss": 1.6445,
|
710 |
+
"step": 565
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 3.56,
|
714 |
+
"learning_rate": 8.198319609030632e-05,
|
715 |
+
"loss": 1.6708,
|
716 |
+
"step": 570
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 3.59,
|
720 |
+
"learning_rate": 8.851352885965614e-05,
|
721 |
+
"loss": 1.7189,
|
722 |
+
"step": 575
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 3.62,
|
726 |
+
"learning_rate": 9.485208346024516e-05,
|
727 |
+
"loss": 1.7617,
|
728 |
+
"step": 580
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 3.66,
|
732 |
+
"learning_rate": 0.00010093781614626343,
|
733 |
+
"loss": 1.6343,
|
734 |
+
"step": 585
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 3.69,
|
738 |
+
"learning_rate": 0.00010671211798514468,
|
739 |
+
"loss": 1.7267,
|
740 |
+
"step": 590
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 3.72,
|
744 |
+
"learning_rate": 0.00011211937929362604,
|
745 |
+
"loss": 1.6865,
|
746 |
+
"step": 595
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 3.75,
|
750 |
+
"learning_rate": 0.0001171075251893971,
|
751 |
+
"loss": 1.6896,
|
752 |
+
"step": 600
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 3.78,
|
756 |
+
"learning_rate": 0.00012162851710068375,
|
757 |
+
"loss": 1.716,
|
758 |
+
"step": 605
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 3.81,
|
762 |
+
"learning_rate": 0.0001256388154039546,
|
763 |
+
"loss": 1.7558,
|
764 |
+
"step": 610
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 3.84,
|
768 |
+
"learning_rate": 0.00012909979873429713,
|
769 |
+
"loss": 1.749,
|
770 |
+
"step": 615
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 3.88,
|
774 |
+
"learning_rate": 0.00013197813593027427,
|
775 |
+
"loss": 1.8024,
|
776 |
+
"step": 620
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 3.91,
|
780 |
+
"learning_rate": 0.0001342461070312295,
|
781 |
+
"loss": 1.6423,
|
782 |
+
"step": 625
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 3.94,
|
786 |
+
"learning_rate": 0.0001358818702356616,
|
787 |
+
"loss": 1.713,
|
788 |
+
"step": 630
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 3.97,
|
792 |
+
"learning_rate": 0.0001368696722497127,
|
793 |
+
"loss": 1.7649,
|
794 |
+
"step": 635
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 4.0,
|
798 |
+
"learning_rate": 0.0001372,
|
799 |
+
"loss": 1.5134,
|
800 |
+
"step": 640
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 4.0,
|
804 |
+
"eval_loss": 1.7136940956115723,
|
805 |
+
"eval_runtime": 11.1178,
|
806 |
+
"eval_samples_per_second": 22.487,
|
807 |
+
"eval_steps_per_second": 2.878,
|
808 |
+
"step": 640
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 4.03,
|
812 |
+
"learning_rate": 0.0001368696722497127,
|
813 |
+
"loss": 1.6853,
|
814 |
+
"step": 645
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 4.06,
|
818 |
+
"learning_rate": 0.00013588187023566163,
|
819 |
+
"loss": 1.6863,
|
820 |
+
"step": 650
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 4.09,
|
824 |
+
"learning_rate": 0.00013424610703122953,
|
825 |
+
"loss": 1.7064,
|
826 |
+
"step": 655
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 4.12,
|
830 |
+
"learning_rate": 0.00013197813593027427,
|
831 |
+
"loss": 1.6835,
|
832 |
+
"step": 660
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 4.16,
|
836 |
+
"learning_rate": 0.0001290997987342972,
|
837 |
+
"loss": 1.571,
|
838 |
+
"step": 665
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 4.19,
|
842 |
+
"learning_rate": 0.00012563881540395464,
|
843 |
+
"loss": 1.5507,
|
844 |
+
"step": 670
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 4.22,
|
848 |
+
"learning_rate": 0.00012162851710068381,
|
849 |
+
"loss": 1.5875,
|
850 |
+
"step": 675
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 4.25,
|
854 |
+
"learning_rate": 0.00011710752518939714,
|
855 |
+
"loss": 1.705,
|
856 |
+
"step": 680
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 4.28,
|
860 |
+
"learning_rate": 0.00011211937929362608,
|
861 |
+
"loss": 1.6864,
|
862 |
+
"step": 685
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 4.31,
|
866 |
+
"learning_rate": 0.00010671211798514474,
|
867 |
+
"loss": 1.6228,
|
868 |
+
"step": 690
|
869 |
+
},
|
870 |
+
{
|
871 |
+
"epoch": 4.34,
|
872 |
+
"learning_rate": 0.00010093781614626347,
|
873 |
+
"loss": 1.6698,
|
874 |
+
"step": 695
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 4.38,
|
878 |
+
"learning_rate": 9.485208346024522e-05,
|
879 |
+
"loss": 1.4768,
|
880 |
+
"step": 700
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 4.41,
|
884 |
+
"learning_rate": 8.851352885965621e-05,
|
885 |
+
"loss": 1.636,
|
886 |
+
"step": 705
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 4.44,
|
890 |
+
"learning_rate": 8.198319609030639e-05,
|
891 |
+
"loss": 1.6327,
|
892 |
+
"step": 710
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 4.47,
|
896 |
+
"learning_rate": 7.532397582660788e-05,
|
897 |
+
"loss": 1.6404,
|
898 |
+
"step": 715
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 4.5,
|
902 |
+
"learning_rate": 6.860000000000003e-05,
|
903 |
+
"loss": 1.7279,
|
904 |
+
"step": 720
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 4.53,
|
908 |
+
"learning_rate": 6.18760241733922e-05,
|
909 |
+
"loss": 1.5857,
|
910 |
+
"step": 725
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 4.56,
|
914 |
+
"learning_rate": 5.5216803909693685e-05,
|
915 |
+
"loss": 1.5979,
|
916 |
+
"step": 730
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 4.59,
|
920 |
+
"learning_rate": 4.8686471140343875e-05,
|
921 |
+
"loss": 1.5906,
|
922 |
+
"step": 735
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 4.62,
|
926 |
+
"learning_rate": 4.234791653975485e-05,
|
927 |
+
"loss": 1.6215,
|
928 |
+
"step": 740
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 4.66,
|
932 |
+
"learning_rate": 3.626218385373659e-05,
|
933 |
+
"loss": 1.6579,
|
934 |
+
"step": 745
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 4.69,
|
938 |
+
"learning_rate": 3.0487882014855336e-05,
|
939 |
+
"loss": 1.6602,
|
940 |
+
"step": 750
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 4.72,
|
944 |
+
"learning_rate": 2.508062070637398e-05,
|
945 |
+
"loss": 1.6282,
|
946 |
+
"step": 755
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 4.75,
|
950 |
+
"learning_rate": 2.0092474810602914e-05,
|
951 |
+
"loss": 1.652,
|
952 |
+
"step": 760
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 4.78,
|
956 |
+
"learning_rate": 1.557148289931624e-05,
|
957 |
+
"loss": 1.5612,
|
958 |
+
"step": 765
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 4.81,
|
962 |
+
"learning_rate": 1.1561184596045413e-05,
|
963 |
+
"loss": 1.6313,
|
964 |
+
"step": 770
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 4.84,
|
968 |
+
"learning_rate": 8.100201265702867e-06,
|
969 |
+
"loss": 1.5685,
|
970 |
+
"step": 775
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 4.88,
|
974 |
+
"learning_rate": 5.221864069725753e-06,
|
975 |
+
"loss": 1.6143,
|
976 |
+
"step": 780
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 4.91,
|
980 |
+
"learning_rate": 2.9538929687704977e-06,
|
981 |
+
"loss": 1.5863,
|
982 |
+
"step": 785
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 4.94,
|
986 |
+
"learning_rate": 1.3181297643383925e-06,
|
987 |
+
"loss": 1.4505,
|
988 |
+
"step": 790
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 4.97,
|
992 |
+
"learning_rate": 3.303277502872983e-07,
|
993 |
+
"loss": 1.6715,
|
994 |
+
"step": 795
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 5.0,
|
998 |
+
"learning_rate": 0.0,
|
999 |
+
"loss": 1.5892,
|
1000 |
+
"step": 800
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 5.0,
|
1004 |
+
"eval_loss": 1.6500141620635986,
|
1005 |
+
"eval_runtime": 11.0924,
|
1006 |
+
"eval_samples_per_second": 22.538,
|
1007 |
+
"eval_steps_per_second": 2.885,
|
1008 |
+
"step": 800
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 5.03,
|
1012 |
+
"learning_rate": 3.303277502872907e-07,
|
1013 |
+
"loss": 1.4254,
|
1014 |
+
"step": 805
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 5.06,
|
1018 |
+
"learning_rate": 1.3181297643383773e-06,
|
1019 |
+
"loss": 1.5428,
|
1020 |
+
"step": 810
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 5.09,
|
1024 |
+
"learning_rate": 2.9538929687704367e-06,
|
1025 |
+
"loss": 1.5335,
|
1026 |
+
"step": 815
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 5.12,
|
1030 |
+
"learning_rate": 5.221864069725677e-06,
|
1031 |
+
"loss": 1.5308,
|
1032 |
+
"step": 820
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 5.16,
|
1036 |
+
"learning_rate": 8.100201265702767e-06,
|
1037 |
+
"loss": 1.5882,
|
1038 |
+
"step": 825
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 5.19,
|
1042 |
+
"learning_rate": 1.1561184596045435e-05,
|
1043 |
+
"loss": 1.5799,
|
1044 |
+
"step": 830
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 5.22,
|
1048 |
+
"learning_rate": 1.5571482899316272e-05,
|
1049 |
+
"loss": 1.5356,
|
1050 |
+
"step": 835
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 5.25,
|
1054 |
+
"learning_rate": 2.0092474810602853e-05,
|
1055 |
+
"loss": 1.5285,
|
1056 |
+
"step": 840
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 5.28,
|
1060 |
+
"learning_rate": 2.5080620706373914e-05,
|
1061 |
+
"loss": 1.5356,
|
1062 |
+
"step": 845
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 5.31,
|
1066 |
+
"learning_rate": 3.048788201485526e-05,
|
1067 |
+
"loss": 1.5041,
|
1068 |
+
"step": 850
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 5.34,
|
1072 |
+
"learning_rate": 3.6262183853736515e-05,
|
1073 |
+
"loss": 1.5689,
|
1074 |
+
"step": 855
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 5.38,
|
1078 |
+
"learning_rate": 4.2347916539754777e-05,
|
1079 |
+
"loss": 1.4609,
|
1080 |
+
"step": 860
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 5.41,
|
1084 |
+
"learning_rate": 4.868647114034379e-05,
|
1085 |
+
"loss": 1.6113,
|
1086 |
+
"step": 865
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 5.44,
|
1090 |
+
"learning_rate": 5.521680390969348e-05,
|
1091 |
+
"loss": 1.6169,
|
1092 |
+
"step": 870
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 5.47,
|
1096 |
+
"learning_rate": 6.1876024173392e-05,
|
1097 |
+
"loss": 1.6431,
|
1098 |
+
"step": 875
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 5.5,
|
1102 |
+
"learning_rate": 6.859999999999984e-05,
|
1103 |
+
"loss": 1.5976,
|
1104 |
+
"step": 880
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 5.53,
|
1108 |
+
"learning_rate": 7.532397582660791e-05,
|
1109 |
+
"loss": 1.5969,
|
1110 |
+
"step": 885
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 5.56,
|
1114 |
+
"learning_rate": 8.198319609030643e-05,
|
1115 |
+
"loss": 1.5681,
|
1116 |
+
"step": 890
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 5.59,
|
1120 |
+
"learning_rate": 8.851352885965613e-05,
|
1121 |
+
"loss": 1.6318,
|
1122 |
+
"step": 895
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 5.62,
|
1126 |
+
"learning_rate": 9.485208346024515e-05,
|
1127 |
+
"loss": 1.5222,
|
1128 |
+
"step": 900
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 5.66,
|
1132 |
+
"learning_rate": 0.00010093781614626339,
|
1133 |
+
"loss": 1.5517,
|
1134 |
+
"step": 905
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 5.69,
|
1138 |
+
"learning_rate": 0.00010671211798514466,
|
1139 |
+
"loss": 1.5481,
|
1140 |
+
"step": 910
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 5.72,
|
1144 |
+
"learning_rate": 0.00011211937929362601,
|
1145 |
+
"loss": 1.6196,
|
1146 |
+
"step": 915
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 5.75,
|
1150 |
+
"learning_rate": 0.00011710752518939709,
|
1151 |
+
"loss": 1.488,
|
1152 |
+
"step": 920
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 5.78,
|
1156 |
+
"learning_rate": 0.00012162851710068368,
|
1157 |
+
"loss": 1.6155,
|
1158 |
+
"step": 925
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 5.81,
|
1162 |
+
"learning_rate": 0.00012563881540395453,
|
1163 |
+
"loss": 1.628,
|
1164 |
+
"step": 930
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 5.84,
|
1168 |
+
"learning_rate": 0.0001290997987342972,
|
1169 |
+
"loss": 1.6143,
|
1170 |
+
"step": 935
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 5.88,
|
1174 |
+
"learning_rate": 0.0001319781359302743,
|
1175 |
+
"loss": 1.6028,
|
1176 |
+
"step": 940
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 5.91,
|
1180 |
+
"learning_rate": 0.00013424610703122953,
|
1181 |
+
"loss": 1.4802,
|
1182 |
+
"step": 945
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 5.94,
|
1186 |
+
"learning_rate": 0.0001358818702356616,
|
1187 |
+
"loss": 1.6464,
|
1188 |
+
"step": 950
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 5.97,
|
1192 |
+
"learning_rate": 0.0001368696722497127,
|
1193 |
+
"loss": 1.6216,
|
1194 |
+
"step": 955
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 6.0,
|
1198 |
+
"learning_rate": 0.0001372,
|
1199 |
+
"loss": 1.5782,
|
1200 |
+
"step": 960
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 6.0,
|
1204 |
+
"eval_loss": 1.6669092178344727,
|
1205 |
+
"eval_runtime": 11.103,
|
1206 |
+
"eval_samples_per_second": 22.517,
|
1207 |
+
"eval_steps_per_second": 2.882,
|
1208 |
+
"step": 960
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 6.03,
|
1212 |
+
"learning_rate": 0.00013686967224971273,
|
1213 |
+
"loss": 1.4996,
|
1214 |
+
"step": 965
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 6.06,
|
1218 |
+
"learning_rate": 0.00013588187023566163,
|
1219 |
+
"loss": 1.5676,
|
1220 |
+
"step": 970
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 6.09,
|
1224 |
+
"learning_rate": 0.00013424610703122958,
|
1225 |
+
"loss": 1.4658,
|
1226 |
+
"step": 975
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 6.12,
|
1230 |
+
"learning_rate": 0.00013197813593027432,
|
1231 |
+
"loss": 1.4962,
|
1232 |
+
"step": 980
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 6.16,
|
1236 |
+
"learning_rate": 0.00012909979873429724,
|
1237 |
+
"loss": 1.5933,
|
1238 |
+
"step": 985
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 6.19,
|
1242 |
+
"learning_rate": 0.00012563881540395458,
|
1243 |
+
"loss": 1.4505,
|
1244 |
+
"step": 990
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 6.22,
|
1248 |
+
"learning_rate": 0.00012162851710068373,
|
1249 |
+
"loss": 1.5865,
|
1250 |
+
"step": 995
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 6.25,
|
1254 |
+
"learning_rate": 0.00011710752518939715,
|
1255 |
+
"loss": 1.665,
|
1256 |
+
"step": 1000
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 6.28,
|
1260 |
+
"learning_rate": 0.00011211937929362609,
|
1261 |
+
"loss": 1.556,
|
1262 |
+
"step": 1005
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 6.31,
|
1266 |
+
"learning_rate": 0.00010671211798514474,
|
1267 |
+
"loss": 1.5632,
|
1268 |
+
"step": 1010
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 6.34,
|
1272 |
+
"learning_rate": 0.00010093781614626349,
|
1273 |
+
"loss": 1.5849,
|
1274 |
+
"step": 1015
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 6.38,
|
1278 |
+
"learning_rate": 9.485208346024524e-05,
|
1279 |
+
"loss": 1.5667,
|
1280 |
+
"step": 1020
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 6.41,
|
1284 |
+
"learning_rate": 8.851352885965622e-05,
|
1285 |
+
"loss": 1.4537,
|
1286 |
+
"step": 1025
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 6.44,
|
1290 |
+
"learning_rate": 8.198319609030653e-05,
|
1291 |
+
"loss": 1.4866,
|
1292 |
+
"step": 1030
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 6.47,
|
1296 |
+
"learning_rate": 7.532397582660802e-05,
|
1297 |
+
"loss": 1.4058,
|
1298 |
+
"step": 1035
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 6.5,
|
1302 |
+
"learning_rate": 6.859999999999993e-05,
|
1303 |
+
"loss": 1.4442,
|
1304 |
+
"step": 1040
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 6.53,
|
1308 |
+
"learning_rate": 6.18760241733921e-05,
|
1309 |
+
"loss": 1.4465,
|
1310 |
+
"step": 1045
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 6.56,
|
1314 |
+
"learning_rate": 5.5216803909693576e-05,
|
1315 |
+
"loss": 1.5129,
|
1316 |
+
"step": 1050
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 6.59,
|
1320 |
+
"learning_rate": 4.868647114034389e-05,
|
1321 |
+
"loss": 1.4484,
|
1322 |
+
"step": 1055
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 6.62,
|
1326 |
+
"learning_rate": 4.2347916539754865e-05,
|
1327 |
+
"loss": 1.6054,
|
1328 |
+
"step": 1060
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 6.66,
|
1332 |
+
"learning_rate": 3.62621838537366e-05,
|
1333 |
+
"loss": 1.6134,
|
1334 |
+
"step": 1065
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 6.69,
|
1338 |
+
"learning_rate": 3.0487882014855342e-05,
|
1339 |
+
"loss": 1.4736,
|
1340 |
+
"step": 1070
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 6.72,
|
1344 |
+
"learning_rate": 2.5080620706373995e-05,
|
1345 |
+
"loss": 1.5124,
|
1346 |
+
"step": 1075
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 6.75,
|
1350 |
+
"learning_rate": 2.009247481060292e-05,
|
1351 |
+
"loss": 1.528,
|
1352 |
+
"step": 1080
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 6.78,
|
1356 |
+
"learning_rate": 1.5571482899316333e-05,
|
1357 |
+
"loss": 1.602,
|
1358 |
+
"step": 1085
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 6.81,
|
1362 |
+
"learning_rate": 1.1561184596045489e-05,
|
1363 |
+
"loss": 1.5229,
|
1364 |
+
"step": 1090
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 6.84,
|
1368 |
+
"learning_rate": 8.100201265702821e-06,
|
1369 |
+
"loss": 1.5871,
|
1370 |
+
"step": 1095
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 6.88,
|
1374 |
+
"learning_rate": 5.221864069725715e-06,
|
1375 |
+
"loss": 1.5468,
|
1376 |
+
"step": 1100
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 6.91,
|
1380 |
+
"learning_rate": 2.9538929687704672e-06,
|
1381 |
+
"loss": 1.4325,
|
1382 |
+
"step": 1105
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 6.94,
|
1386 |
+
"learning_rate": 1.3181297643383925e-06,
|
1387 |
+
"loss": 1.5777,
|
1388 |
+
"step": 1110
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 6.97,
|
1392 |
+
"learning_rate": 3.303277502872983e-07,
|
1393 |
+
"loss": 1.5088,
|
1394 |
+
"step": 1115
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 7.0,
|
1398 |
+
"learning_rate": 0.0,
|
1399 |
+
"loss": 1.4601,
|
1400 |
+
"step": 1120
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 7.0,
|
1404 |
+
"eval_loss": 1.6244831085205078,
|
1405 |
+
"eval_runtime": 11.094,
|
1406 |
+
"eval_samples_per_second": 22.535,
|
1407 |
+
"eval_steps_per_second": 2.884,
|
1408 |
+
"step": 1120
|
1409 |
+
},
|
1410 |
+
{
|
1411 |
+
"epoch": 7.03,
|
1412 |
+
"learning_rate": 3.303277502872831e-07,
|
1413 |
+
"loss": 1.487,
|
1414 |
+
"step": 1125
|
1415 |
+
},
|
1416 |
+
{
|
1417 |
+
"epoch": 7.06,
|
1418 |
+
"learning_rate": 1.3181297643383697e-06,
|
1419 |
+
"loss": 1.4971,
|
1420 |
+
"step": 1130
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 7.09,
|
1424 |
+
"learning_rate": 2.9538929687704367e-06,
|
1425 |
+
"loss": 1.4361,
|
1426 |
+
"step": 1135
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 7.12,
|
1430 |
+
"learning_rate": 5.221864069725669e-06,
|
1431 |
+
"loss": 1.4751,
|
1432 |
+
"step": 1140
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 7.16,
|
1436 |
+
"learning_rate": 8.10020126570276e-06,
|
1437 |
+
"loss": 1.3822,
|
1438 |
+
"step": 1145
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 7.19,
|
1442 |
+
"learning_rate": 1.156118459604542e-05,
|
1443 |
+
"loss": 1.4882,
|
1444 |
+
"step": 1150
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 7.22,
|
1448 |
+
"learning_rate": 1.5571482899316258e-05,
|
1449 |
+
"loss": 1.4465,
|
1450 |
+
"step": 1155
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 7.25,
|
1454 |
+
"learning_rate": 2.0092474810602836e-05,
|
1455 |
+
"loss": 1.3924,
|
1456 |
+
"step": 1160
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 7.28,
|
1460 |
+
"learning_rate": 2.5080620706373904e-05,
|
1461 |
+
"loss": 1.4828,
|
1462 |
+
"step": 1165
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"epoch": 7.31,
|
1466 |
+
"learning_rate": 3.0487882014855254e-05,
|
1467 |
+
"loss": 1.4428,
|
1468 |
+
"step": 1170
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 7.34,
|
1472 |
+
"learning_rate": 3.6262183853736495e-05,
|
1473 |
+
"loss": 1.6162,
|
1474 |
+
"step": 1175
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 7.38,
|
1478 |
+
"learning_rate": 4.234791653975476e-05,
|
1479 |
+
"loss": 1.368,
|
1480 |
+
"step": 1180
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 7.41,
|
1484 |
+
"learning_rate": 4.868647114034377e-05,
|
1485 |
+
"loss": 1.4922,
|
1486 |
+
"step": 1185
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 7.44,
|
1490 |
+
"learning_rate": 5.521680390969347e-05,
|
1491 |
+
"loss": 1.4195,
|
1492 |
+
"step": 1190
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 7.47,
|
1496 |
+
"learning_rate": 6.187602417339198e-05,
|
1497 |
+
"loss": 1.4896,
|
1498 |
+
"step": 1195
|
1499 |
+
},
|
1500 |
+
{
|
1501 |
+
"epoch": 7.5,
|
1502 |
+
"learning_rate": 6.859999999999982e-05,
|
1503 |
+
"loss": 1.4594,
|
1504 |
+
"step": 1200
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 7.53,
|
1508 |
+
"learning_rate": 7.53239758266079e-05,
|
1509 |
+
"loss": 1.4228,
|
1510 |
+
"step": 1205
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 7.56,
|
1514 |
+
"learning_rate": 8.19831960903064e-05,
|
1515 |
+
"loss": 1.4571,
|
1516 |
+
"step": 1210
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 7.59,
|
1520 |
+
"learning_rate": 8.851352885965611e-05,
|
1521 |
+
"loss": 1.4634,
|
1522 |
+
"step": 1215
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 7.62,
|
1526 |
+
"learning_rate": 9.485208346024514e-05,
|
1527 |
+
"loss": 1.5054,
|
1528 |
+
"step": 1220
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 7.66,
|
1532 |
+
"learning_rate": 0.00010093781614626339,
|
1533 |
+
"loss": 1.4162,
|
1534 |
+
"step": 1225
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 7.69,
|
1538 |
+
"learning_rate": 0.00010671211798514465,
|
1539 |
+
"loss": 1.5479,
|
1540 |
+
"step": 1230
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 7.72,
|
1544 |
+
"learning_rate": 0.00011211937929362601,
|
1545 |
+
"loss": 1.4107,
|
1546 |
+
"step": 1235
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 7.75,
|
1550 |
+
"learning_rate": 0.00011710752518939706,
|
1551 |
+
"loss": 1.4738,
|
1552 |
+
"step": 1240
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 7.78,
|
1556 |
+
"learning_rate": 0.00012162851710068366,
|
1557 |
+
"loss": 1.4738,
|
1558 |
+
"step": 1245
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 7.81,
|
1562 |
+
"learning_rate": 0.0001256388154039545,
|
1563 |
+
"loss": 1.497,
|
1564 |
+
"step": 1250
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 7.84,
|
1568 |
+
"learning_rate": 0.0001290997987342972,
|
1569 |
+
"loss": 1.5329,
|
1570 |
+
"step": 1255
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 7.88,
|
1574 |
+
"learning_rate": 0.0001319781359302743,
|
1575 |
+
"loss": 1.4608,
|
1576 |
+
"step": 1260
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"epoch": 7.91,
|
1580 |
+
"learning_rate": 0.00013424610703122953,
|
1581 |
+
"loss": 1.5795,
|
1582 |
+
"step": 1265
|
1583 |
+
},
|
1584 |
+
{
|
1585 |
+
"epoch": 7.94,
|
1586 |
+
"learning_rate": 0.0001358818702356616,
|
1587 |
+
"loss": 1.5419,
|
1588 |
+
"step": 1270
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 7.97,
|
1592 |
+
"learning_rate": 0.0001368696722497127,
|
1593 |
+
"loss": 1.4443,
|
1594 |
+
"step": 1275
|
1595 |
+
},
|
1596 |
+
{
|
1597 |
+
"epoch": 8.0,
|
1598 |
+
"learning_rate": 0.0001372,
|
1599 |
+
"loss": 1.4799,
|
1600 |
+
"step": 1280
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 8.0,
|
1604 |
+
"eval_loss": 1.6402026414871216,
|
1605 |
+
"eval_runtime": 11.1984,
|
1606 |
+
"eval_samples_per_second": 22.325,
|
1607 |
+
"eval_steps_per_second": 2.858,
|
1608 |
+
"step": 1280
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 8.03,
|
1612 |
+
"learning_rate": 0.00013686967224971273,
|
1613 |
+
"loss": 1.4584,
|
1614 |
+
"step": 1285
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 8.06,
|
1618 |
+
"learning_rate": 0.00013588187023566163,
|
1619 |
+
"loss": 1.4089,
|
1620 |
+
"step": 1290
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 8.09,
|
1624 |
+
"learning_rate": 0.00013424610703122958,
|
1625 |
+
"loss": 1.55,
|
1626 |
+
"step": 1295
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 8.12,
|
1630 |
+
"learning_rate": 0.00013197813593027432,
|
1631 |
+
"loss": 1.4449,
|
1632 |
+
"step": 1300
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 8.16,
|
1636 |
+
"learning_rate": 0.00012909979873429724,
|
1637 |
+
"loss": 1.367,
|
1638 |
+
"step": 1305
|
1639 |
+
},
|
1640 |
+
{
|
1641 |
+
"epoch": 8.19,
|
1642 |
+
"learning_rate": 0.00012563881540395458,
|
1643 |
+
"loss": 1.5241,
|
1644 |
+
"step": 1310
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 8.22,
|
1648 |
+
"learning_rate": 0.00012162851710068375,
|
1649 |
+
"loss": 1.5117,
|
1650 |
+
"step": 1315
|
1651 |
+
},
|
1652 |
+
{
|
1653 |
+
"epoch": 8.25,
|
1654 |
+
"learning_rate": 0.00011710752518939715,
|
1655 |
+
"loss": 1.4418,
|
1656 |
+
"step": 1320
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 8.28,
|
1660 |
+
"learning_rate": 0.00011211937929362609,
|
1661 |
+
"loss": 1.5439,
|
1662 |
+
"step": 1325
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 8.31,
|
1666 |
+
"learning_rate": 0.00010671211798514476,
|
1667 |
+
"loss": 1.3722,
|
1668 |
+
"step": 1330
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 8.34,
|
1672 |
+
"learning_rate": 0.0001009378161462635,
|
1673 |
+
"loss": 1.4284,
|
1674 |
+
"step": 1335
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 8.38,
|
1678 |
+
"learning_rate": 9.485208346024526e-05,
|
1679 |
+
"loss": 1.516,
|
1680 |
+
"step": 1340
|
1681 |
+
},
|
1682 |
+
{
|
1683 |
+
"epoch": 8.41,
|
1684 |
+
"learning_rate": 8.851352885965623e-05,
|
1685 |
+
"loss": 1.3386,
|
1686 |
+
"step": 1345
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 8.44,
|
1690 |
+
"learning_rate": 8.198319609030655e-05,
|
1691 |
+
"loss": 1.4559,
|
1692 |
+
"step": 1350
|
1693 |
+
},
|
1694 |
+
{
|
1695 |
+
"epoch": 8.47,
|
1696 |
+
"learning_rate": 7.532397582660803e-05,
|
1697 |
+
"loss": 1.6084,
|
1698 |
+
"step": 1355
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 8.5,
|
1702 |
+
"learning_rate": 6.859999999999995e-05,
|
1703 |
+
"loss": 1.4138,
|
1704 |
+
"step": 1360
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 8.53,
|
1708 |
+
"learning_rate": 6.187602417339212e-05,
|
1709 |
+
"loss": 1.3939,
|
1710 |
+
"step": 1365
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 8.56,
|
1714 |
+
"learning_rate": 5.5216803909693596e-05,
|
1715 |
+
"loss": 1.4058,
|
1716 |
+
"step": 1370
|
1717 |
+
},
|
1718 |
+
{
|
1719 |
+
"epoch": 8.59,
|
1720 |
+
"learning_rate": 4.86864711403439e-05,
|
1721 |
+
"loss": 1.4439,
|
1722 |
+
"step": 1375
|
1723 |
+
},
|
1724 |
+
{
|
1725 |
+
"epoch": 8.62,
|
1726 |
+
"learning_rate": 4.2347916539754885e-05,
|
1727 |
+
"loss": 1.345,
|
1728 |
+
"step": 1380
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 8.66,
|
1732 |
+
"learning_rate": 3.626218385373662e-05,
|
1733 |
+
"loss": 1.4172,
|
1734 |
+
"step": 1385
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 8.69,
|
1738 |
+
"learning_rate": 3.048788201485536e-05,
|
1739 |
+
"loss": 1.4024,
|
1740 |
+
"step": 1390
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 8.72,
|
1744 |
+
"learning_rate": 2.5080620706374002e-05,
|
1745 |
+
"loss": 1.4443,
|
1746 |
+
"step": 1395
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 8.75,
|
1750 |
+
"learning_rate": 2.0092474810602934e-05,
|
1751 |
+
"loss": 1.4758,
|
1752 |
+
"step": 1400
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 8.78,
|
1756 |
+
"learning_rate": 1.5571482899316343e-05,
|
1757 |
+
"loss": 1.4565,
|
1758 |
+
"step": 1405
|
1759 |
+
},
|
1760 |
+
{
|
1761 |
+
"epoch": 8.81,
|
1762 |
+
"learning_rate": 1.1561184596045496e-05,
|
1763 |
+
"loss": 1.3571,
|
1764 |
+
"step": 1410
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 8.84,
|
1768 |
+
"learning_rate": 8.100201265702828e-06,
|
1769 |
+
"loss": 1.478,
|
1770 |
+
"step": 1415
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 8.88,
|
1774 |
+
"learning_rate": 5.2218640697257225e-06,
|
1775 |
+
"loss": 1.452,
|
1776 |
+
"step": 1420
|
1777 |
+
},
|
1778 |
+
{
|
1779 |
+
"epoch": 8.91,
|
1780 |
+
"learning_rate": 2.953892968770475e-06,
|
1781 |
+
"loss": 1.3222,
|
1782 |
+
"step": 1425
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 8.94,
|
1786 |
+
"learning_rate": 1.3181297643384001e-06,
|
1787 |
+
"loss": 1.426,
|
1788 |
+
"step": 1430
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 8.97,
|
1792 |
+
"learning_rate": 3.303277502872983e-07,
|
1793 |
+
"loss": 1.4787,
|
1794 |
+
"step": 1435
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 9.0,
|
1798 |
+
"learning_rate": 0.0,
|
1799 |
+
"loss": 1.353,
|
1800 |
+
"step": 1440
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 9.0,
|
1804 |
+
"eval_loss": 1.6076909303665161,
|
1805 |
+
"eval_runtime": 11.1829,
|
1806 |
+
"eval_samples_per_second": 22.355,
|
1807 |
+
"eval_steps_per_second": 2.862,
|
1808 |
+
"step": 1440
|
1809 |
+
}
|
1810 |
+
],
|
1811 |
+
"max_steps": 1600,
|
1812 |
+
"num_train_epochs": 10,
|
1813 |
+
"total_flos": 1505042104320000.0,
|
1814 |
+
"trial_name": null,
|
1815 |
+
"trial_params": null
|
1816 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d9e8519120986eb1d1f30afb0305057db89e930c94baca8b50a3f1a1d7fbf77
|
3 |
+
size 2671
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|