devilyouwei
commited on
Commit
·
2810c64
1
Parent(s):
75bec93
init model
Browse files- README.md +31 -3
- config.json +28 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- trainer_state.json +985 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- FacebookAI/roberta-base
|
| 7 |
+
pipeline_tag: sentence-similarity
|
| 8 |
+
tags:
|
| 9 |
+
- smart-contract
|
| 10 |
+
- web3
|
| 11 |
+
- software-engineering
|
| 12 |
+
- web3se
|
| 13 |
+
- embedding
|
| 14 |
+
- RoBERTa
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# SmartBERT V1 RoBERTa (2022)
|
| 18 |
+
|
| 19 |
+
## Overview
|
| 20 |
+
|
| 21 |
+
This **smart contract pre-trained model** is used to transfer smart contract _function-level_ code to embeddings.
|
| 22 |
+
|
| 23 |
+
It is trained by **[Sen Fang](https://github.com/TomasAndersonFang)** in 2022 on over **40,000** smart contracts.
|
| 24 |
+
|
| 25 |
+
Initialized with **RoBERTa**
|
| 26 |
+
|
| 27 |
+
Please update to [SmartBERT V2](https://huggingface.co/web3se/SmartBERT-v2)
|
| 28 |
+
|
| 29 |
+
## Thanks
|
| 30 |
+
|
| 31 |
+
- [Institute of Intelligent Computing Technology, Suzhou, CAS](http://iict.ac.cn/)
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.33.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
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 sha256:9d4009bbcead73bd6adf95005dcab234d0c10985513e41846c51c42e4e7b4ec3
|
| 3 |
+
size 997747845
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bab9d00acdcd6d5e8bbf72eea49e4d3ae0689f8c57e9ef170823d9a8b83b012f
|
| 3 |
+
size 498859189
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c1f7cf60bfd1534e335d412a7dbf8ddde8ac81d99ed0f1cc1582d1bd1436c88
|
| 3 |
+
size 14575
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:133770c1672a8bc74ae9648c1e9ea50d96adb32cda2c7f10c2a6833f0ff7c6ef
|
| 3 |
+
size 14583
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4071e5d23c5299e0ac70e6c0f1f63470851d6b4726043b1cafc970086b998bbf
|
| 3 |
+
size 14583
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ddc3b9940d4c6d44f531c376bd518e3cebf257f6afd57bdb29d34cc6f500a95
|
| 3 |
+
size 14583
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4deb3511e5a3efce40afdb541e7f66327be2b0e6e7e9586eba4bc3050b61692e
|
| 3 |
+
size 14583
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6e1eef2e768114c6219e0c0bba8dc9587718448959863a780ca87abffc9458c
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db409df85fde5944d1d14ecd87f53fd0681c8c1a22a40a8f28d70ad4329caeee
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"cls_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "<s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eos_token": {
|
| 20 |
+
"__type": "AddedToken",
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"errors": "replace",
|
| 28 |
+
"mask_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<mask>",
|
| 31 |
+
"lstrip": true,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"model_max_length": 512,
|
| 37 |
+
"name_or_path": "../codebert-base-mlm",
|
| 38 |
+
"pad_token": {
|
| 39 |
+
"__type": "AddedToken",
|
| 40 |
+
"content": "<pad>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": true,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"sep_token": {
|
| 47 |
+
"__type": "AddedToken",
|
| 48 |
+
"content": "</s>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": true,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
},
|
| 54 |
+
"special_tokens_map_file": "../codebert-base-mlm/special_tokens_map.json",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": {
|
| 58 |
+
"__type": "AddedToken",
|
| 59 |
+
"content": "<unk>",
|
| 60 |
+
"lstrip": false,
|
| 61 |
+
"normalized": true,
|
| 62 |
+
"rstrip": false,
|
| 63 |
+
"single_word": false
|
| 64 |
+
}
|
| 65 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,985 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.971509971509972,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 10500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"eval_loss": 0.3346759080886841,
|
| 14 |
+
"eval_runtime": 218.6538,
|
| 15 |
+
"eval_samples_per_second": 103.456,
|
| 16 |
+
"eval_steps_per_second": 6.467,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.19,
|
| 21 |
+
"eval_loss": 0.31195777654647827,
|
| 22 |
+
"eval_runtime": 218.3816,
|
| 23 |
+
"eval_samples_per_second": 103.585,
|
| 24 |
+
"eval_steps_per_second": 6.475,
|
| 25 |
+
"step": 200
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.28,
|
| 29 |
+
"eval_loss": 0.31596091389656067,
|
| 30 |
+
"eval_runtime": 220.5173,
|
| 31 |
+
"eval_samples_per_second": 102.582,
|
| 32 |
+
"eval_steps_per_second": 6.412,
|
| 33 |
+
"step": 300
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.38,
|
| 37 |
+
"eval_loss": 0.3161667287349701,
|
| 38 |
+
"eval_runtime": 218.5361,
|
| 39 |
+
"eval_samples_per_second": 103.512,
|
| 40 |
+
"eval_steps_per_second": 6.47,
|
| 41 |
+
"step": 400
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.47,
|
| 45 |
+
"learning_rate": 4.7625830959164296e-05,
|
| 46 |
+
"loss": 0.1792,
|
| 47 |
+
"step": 500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.47,
|
| 51 |
+
"eval_loss": 0.3097754120826721,
|
| 52 |
+
"eval_runtime": 219.0553,
|
| 53 |
+
"eval_samples_per_second": 103.266,
|
| 54 |
+
"eval_steps_per_second": 6.455,
|
| 55 |
+
"step": 500
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.57,
|
| 59 |
+
"eval_loss": 0.30482736229896545,
|
| 60 |
+
"eval_runtime": 218.842,
|
| 61 |
+
"eval_samples_per_second": 103.367,
|
| 62 |
+
"eval_steps_per_second": 6.461,
|
| 63 |
+
"step": 600
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.66,
|
| 67 |
+
"eval_loss": 0.3050496578216553,
|
| 68 |
+
"eval_runtime": 219.6074,
|
| 69 |
+
"eval_samples_per_second": 103.007,
|
| 70 |
+
"eval_steps_per_second": 6.439,
|
| 71 |
+
"step": 700
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.76,
|
| 75 |
+
"eval_loss": 0.30001184344291687,
|
| 76 |
+
"eval_runtime": 219.2072,
|
| 77 |
+
"eval_samples_per_second": 103.195,
|
| 78 |
+
"eval_steps_per_second": 6.451,
|
| 79 |
+
"step": 800
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.85,
|
| 83 |
+
"eval_loss": 0.3052184283733368,
|
| 84 |
+
"eval_runtime": 219.1722,
|
| 85 |
+
"eval_samples_per_second": 103.211,
|
| 86 |
+
"eval_steps_per_second": 6.452,
|
| 87 |
+
"step": 900
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.95,
|
| 91 |
+
"learning_rate": 4.5251661918328584e-05,
|
| 92 |
+
"loss": 0.1198,
|
| 93 |
+
"step": 1000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.95,
|
| 97 |
+
"eval_loss": 0.3005639314651489,
|
| 98 |
+
"eval_runtime": 218.7588,
|
| 99 |
+
"eval_samples_per_second": 103.406,
|
| 100 |
+
"eval_steps_per_second": 6.464,
|
| 101 |
+
"step": 1000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.04,
|
| 105 |
+
"eval_loss": 0.29650744795799255,
|
| 106 |
+
"eval_runtime": 218.5819,
|
| 107 |
+
"eval_samples_per_second": 103.49,
|
| 108 |
+
"eval_steps_per_second": 6.469,
|
| 109 |
+
"step": 1100
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.14,
|
| 113 |
+
"eval_loss": 0.2948579788208008,
|
| 114 |
+
"eval_runtime": 219.004,
|
| 115 |
+
"eval_samples_per_second": 103.29,
|
| 116 |
+
"eval_steps_per_second": 6.457,
|
| 117 |
+
"step": 1200
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.23,
|
| 121 |
+
"eval_loss": 0.28149962425231934,
|
| 122 |
+
"eval_runtime": 218.3331,
|
| 123 |
+
"eval_samples_per_second": 103.608,
|
| 124 |
+
"eval_steps_per_second": 6.476,
|
| 125 |
+
"step": 1300
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.33,
|
| 129 |
+
"eval_loss": 0.28821900486946106,
|
| 130 |
+
"eval_runtime": 218.9147,
|
| 131 |
+
"eval_samples_per_second": 103.333,
|
| 132 |
+
"eval_steps_per_second": 6.459,
|
| 133 |
+
"step": 1400
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.42,
|
| 137 |
+
"learning_rate": 4.287749287749288e-05,
|
| 138 |
+
"loss": 0.1092,
|
| 139 |
+
"step": 1500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.42,
|
| 143 |
+
"eval_loss": 0.28900569677352905,
|
| 144 |
+
"eval_runtime": 218.7775,
|
| 145 |
+
"eval_samples_per_second": 103.397,
|
| 146 |
+
"eval_steps_per_second": 6.463,
|
| 147 |
+
"step": 1500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.52,
|
| 151 |
+
"eval_loss": 0.2834137976169586,
|
| 152 |
+
"eval_runtime": 218.2122,
|
| 153 |
+
"eval_samples_per_second": 103.665,
|
| 154 |
+
"eval_steps_per_second": 6.48,
|
| 155 |
+
"step": 1600
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.61,
|
| 159 |
+
"eval_loss": 0.2864611744880676,
|
| 160 |
+
"eval_runtime": 220.2143,
|
| 161 |
+
"eval_samples_per_second": 102.723,
|
| 162 |
+
"eval_steps_per_second": 6.421,
|
| 163 |
+
"step": 1700
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.71,
|
| 167 |
+
"eval_loss": 0.28005194664001465,
|
| 168 |
+
"eval_runtime": 218.8438,
|
| 169 |
+
"eval_samples_per_second": 103.366,
|
| 170 |
+
"eval_steps_per_second": 6.461,
|
| 171 |
+
"step": 1800
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.8,
|
| 175 |
+
"eval_loss": 0.28052985668182373,
|
| 176 |
+
"eval_runtime": 220.1784,
|
| 177 |
+
"eval_samples_per_second": 102.739,
|
| 178 |
+
"eval_steps_per_second": 6.422,
|
| 179 |
+
"step": 1900
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.9,
|
| 183 |
+
"learning_rate": 4.050332383665717e-05,
|
| 184 |
+
"loss": 0.099,
|
| 185 |
+
"step": 2000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.9,
|
| 189 |
+
"eval_loss": 0.2817462384700775,
|
| 190 |
+
"eval_runtime": 219.1612,
|
| 191 |
+
"eval_samples_per_second": 103.216,
|
| 192 |
+
"eval_steps_per_second": 6.452,
|
| 193 |
+
"step": 2000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.99,
|
| 197 |
+
"eval_loss": 0.2855830788612366,
|
| 198 |
+
"eval_runtime": 218.4225,
|
| 199 |
+
"eval_samples_per_second": 103.565,
|
| 200 |
+
"eval_steps_per_second": 6.474,
|
| 201 |
+
"step": 2100
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.09,
|
| 205 |
+
"eval_loss": 0.2786203622817993,
|
| 206 |
+
"eval_runtime": 220.2549,
|
| 207 |
+
"eval_samples_per_second": 102.704,
|
| 208 |
+
"eval_steps_per_second": 6.42,
|
| 209 |
+
"step": 2200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.18,
|
| 213 |
+
"eval_loss": 0.282156765460968,
|
| 214 |
+
"eval_runtime": 218.8776,
|
| 215 |
+
"eval_samples_per_second": 103.35,
|
| 216 |
+
"eval_steps_per_second": 6.46,
|
| 217 |
+
"step": 2300
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.28,
|
| 221 |
+
"eval_loss": 0.2802504599094391,
|
| 222 |
+
"eval_runtime": 218.6184,
|
| 223 |
+
"eval_samples_per_second": 103.473,
|
| 224 |
+
"eval_steps_per_second": 6.468,
|
| 225 |
+
"step": 2400
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.37,
|
| 229 |
+
"learning_rate": 3.8129154795821466e-05,
|
| 230 |
+
"loss": 0.094,
|
| 231 |
+
"step": 2500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.37,
|
| 235 |
+
"eval_loss": 0.28312984108924866,
|
| 236 |
+
"eval_runtime": 219.677,
|
| 237 |
+
"eval_samples_per_second": 102.974,
|
| 238 |
+
"eval_steps_per_second": 6.437,
|
| 239 |
+
"step": 2500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.47,
|
| 243 |
+
"eval_loss": 0.2841149866580963,
|
| 244 |
+
"eval_runtime": 219.3064,
|
| 245 |
+
"eval_samples_per_second": 103.148,
|
| 246 |
+
"eval_steps_per_second": 6.448,
|
| 247 |
+
"step": 2600
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.56,
|
| 251 |
+
"eval_loss": 0.2737499177455902,
|
| 252 |
+
"eval_runtime": 218.5172,
|
| 253 |
+
"eval_samples_per_second": 103.52,
|
| 254 |
+
"eval_steps_per_second": 6.471,
|
| 255 |
+
"step": 2700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.66,
|
| 259 |
+
"eval_loss": 0.27663424611091614,
|
| 260 |
+
"eval_runtime": 219.4686,
|
| 261 |
+
"eval_samples_per_second": 103.072,
|
| 262 |
+
"eval_steps_per_second": 6.443,
|
| 263 |
+
"step": 2800
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.75,
|
| 267 |
+
"eval_loss": 0.27256855368614197,
|
| 268 |
+
"eval_runtime": 218.7767,
|
| 269 |
+
"eval_samples_per_second": 103.398,
|
| 270 |
+
"eval_steps_per_second": 6.463,
|
| 271 |
+
"step": 2900
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.85,
|
| 275 |
+
"learning_rate": 3.575498575498576e-05,
|
| 276 |
+
"loss": 0.0891,
|
| 277 |
+
"step": 3000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.85,
|
| 281 |
+
"eval_loss": 0.27302590012550354,
|
| 282 |
+
"eval_runtime": 218.602,
|
| 283 |
+
"eval_samples_per_second": 103.48,
|
| 284 |
+
"eval_steps_per_second": 6.468,
|
| 285 |
+
"step": 3000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.94,
|
| 289 |
+
"eval_loss": 0.27365198731422424,
|
| 290 |
+
"eval_runtime": 219.6229,
|
| 291 |
+
"eval_samples_per_second": 102.999,
|
| 292 |
+
"eval_steps_per_second": 6.438,
|
| 293 |
+
"step": 3100
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.04,
|
| 297 |
+
"eval_loss": 0.26861417293548584,
|
| 298 |
+
"eval_runtime": 219.0414,
|
| 299 |
+
"eval_samples_per_second": 103.273,
|
| 300 |
+
"eval_steps_per_second": 6.455,
|
| 301 |
+
"step": 3200
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 3.13,
|
| 305 |
+
"eval_loss": 0.2664526700973511,
|
| 306 |
+
"eval_runtime": 218.6581,
|
| 307 |
+
"eval_samples_per_second": 103.454,
|
| 308 |
+
"eval_steps_per_second": 6.467,
|
| 309 |
+
"step": 3300
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.23,
|
| 313 |
+
"eval_loss": 0.27480828762054443,
|
| 314 |
+
"eval_runtime": 220.5641,
|
| 315 |
+
"eval_samples_per_second": 102.56,
|
| 316 |
+
"eval_steps_per_second": 6.411,
|
| 317 |
+
"step": 3400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.32,
|
| 321 |
+
"learning_rate": 3.338081671415005e-05,
|
| 322 |
+
"loss": 0.0862,
|
| 323 |
+
"step": 3500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.32,
|
| 327 |
+
"eval_loss": 0.26794129610061646,
|
| 328 |
+
"eval_runtime": 218.5638,
|
| 329 |
+
"eval_samples_per_second": 103.498,
|
| 330 |
+
"eval_steps_per_second": 6.47,
|
| 331 |
+
"step": 3500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 3.42,
|
| 335 |
+
"eval_loss": 0.2703064978122711,
|
| 336 |
+
"eval_runtime": 218.4977,
|
| 337 |
+
"eval_samples_per_second": 103.53,
|
| 338 |
+
"eval_steps_per_second": 6.471,
|
| 339 |
+
"step": 3600
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.51,
|
| 343 |
+
"eval_loss": 0.2635132670402527,
|
| 344 |
+
"eval_runtime": 219.2033,
|
| 345 |
+
"eval_samples_per_second": 103.196,
|
| 346 |
+
"eval_steps_per_second": 6.451,
|
| 347 |
+
"step": 3700
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.61,
|
| 351 |
+
"eval_loss": 0.27066901326179504,
|
| 352 |
+
"eval_runtime": 219.2382,
|
| 353 |
+
"eval_samples_per_second": 103.18,
|
| 354 |
+
"eval_steps_per_second": 6.45,
|
| 355 |
+
"step": 3800
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 3.7,
|
| 359 |
+
"eval_loss": 0.26447921991348267,
|
| 360 |
+
"eval_runtime": 219.2131,
|
| 361 |
+
"eval_samples_per_second": 103.192,
|
| 362 |
+
"eval_steps_per_second": 6.45,
|
| 363 |
+
"step": 3900
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.8,
|
| 367 |
+
"learning_rate": 3.100664767331434e-05,
|
| 368 |
+
"loss": 0.0838,
|
| 369 |
+
"step": 4000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 3.8,
|
| 373 |
+
"eval_loss": 0.2692434787750244,
|
| 374 |
+
"eval_runtime": 219.4395,
|
| 375 |
+
"eval_samples_per_second": 103.085,
|
| 376 |
+
"eval_steps_per_second": 6.444,
|
| 377 |
+
"step": 4000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.89,
|
| 381 |
+
"eval_loss": 0.2642222046852112,
|
| 382 |
+
"eval_runtime": 219.413,
|
| 383 |
+
"eval_samples_per_second": 103.098,
|
| 384 |
+
"eval_steps_per_second": 6.444,
|
| 385 |
+
"step": 4100
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 3.99,
|
| 389 |
+
"eval_loss": 0.2643529176712036,
|
| 390 |
+
"eval_runtime": 219.2041,
|
| 391 |
+
"eval_samples_per_second": 103.196,
|
| 392 |
+
"eval_steps_per_second": 6.451,
|
| 393 |
+
"step": 4200
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.08,
|
| 397 |
+
"eval_loss": 0.25718453526496887,
|
| 398 |
+
"eval_runtime": 219.1679,
|
| 399 |
+
"eval_samples_per_second": 103.213,
|
| 400 |
+
"eval_steps_per_second": 6.452,
|
| 401 |
+
"step": 4300
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.18,
|
| 405 |
+
"eval_loss": 0.26762890815734863,
|
| 406 |
+
"eval_runtime": 218.6308,
|
| 407 |
+
"eval_samples_per_second": 103.467,
|
| 408 |
+
"eval_steps_per_second": 6.468,
|
| 409 |
+
"step": 4400
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.27,
|
| 413 |
+
"learning_rate": 2.863247863247863e-05,
|
| 414 |
+
"loss": 0.0761,
|
| 415 |
+
"step": 4500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.27,
|
| 419 |
+
"eval_loss": 0.26568803191185,
|
| 420 |
+
"eval_runtime": 220.7096,
|
| 421 |
+
"eval_samples_per_second": 102.492,
|
| 422 |
+
"eval_steps_per_second": 6.407,
|
| 423 |
+
"step": 4500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.37,
|
| 427 |
+
"eval_loss": 0.26290062069892883,
|
| 428 |
+
"eval_runtime": 219.3895,
|
| 429 |
+
"eval_samples_per_second": 103.109,
|
| 430 |
+
"eval_steps_per_second": 6.445,
|
| 431 |
+
"step": 4600
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 4.46,
|
| 435 |
+
"eval_loss": 0.26172617077827454,
|
| 436 |
+
"eval_runtime": 219.4776,
|
| 437 |
+
"eval_samples_per_second": 103.067,
|
| 438 |
+
"eval_steps_per_second": 6.443,
|
| 439 |
+
"step": 4700
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 4.56,
|
| 443 |
+
"eval_loss": 0.26161935925483704,
|
| 444 |
+
"eval_runtime": 219.3677,
|
| 445 |
+
"eval_samples_per_second": 103.119,
|
| 446 |
+
"eval_steps_per_second": 6.446,
|
| 447 |
+
"step": 4800
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 4.65,
|
| 451 |
+
"eval_loss": 0.2620932459831238,
|
| 452 |
+
"eval_runtime": 218.6157,
|
| 453 |
+
"eval_samples_per_second": 103.474,
|
| 454 |
+
"eval_steps_per_second": 6.468,
|
| 455 |
+
"step": 4900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.75,
|
| 459 |
+
"learning_rate": 2.6258309591642926e-05,
|
| 460 |
+
"loss": 0.0741,
|
| 461 |
+
"step": 5000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 4.75,
|
| 465 |
+
"eval_loss": 0.26253631711006165,
|
| 466 |
+
"eval_runtime": 218.59,
|
| 467 |
+
"eval_samples_per_second": 103.486,
|
| 468 |
+
"eval_steps_per_second": 6.469,
|
| 469 |
+
"step": 5000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 4.84,
|
| 473 |
+
"eval_loss": 0.25699007511138916,
|
| 474 |
+
"eval_runtime": 219.4178,
|
| 475 |
+
"eval_samples_per_second": 103.096,
|
| 476 |
+
"eval_steps_per_second": 6.444,
|
| 477 |
+
"step": 5100
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.94,
|
| 481 |
+
"eval_loss": 0.2583966851234436,
|
| 482 |
+
"eval_runtime": 218.5589,
|
| 483 |
+
"eval_samples_per_second": 103.501,
|
| 484 |
+
"eval_steps_per_second": 6.47,
|
| 485 |
+
"step": 5200
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 5.03,
|
| 489 |
+
"eval_loss": 0.25885534286499023,
|
| 490 |
+
"eval_runtime": 219.0916,
|
| 491 |
+
"eval_samples_per_second": 103.249,
|
| 492 |
+
"eval_steps_per_second": 6.454,
|
| 493 |
+
"step": 5300
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 5.13,
|
| 497 |
+
"eval_loss": 0.25685915350914,
|
| 498 |
+
"eval_runtime": 219.2049,
|
| 499 |
+
"eval_samples_per_second": 103.196,
|
| 500 |
+
"eval_steps_per_second": 6.451,
|
| 501 |
+
"step": 5400
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 5.22,
|
| 505 |
+
"learning_rate": 2.388414055080722e-05,
|
| 506 |
+
"loss": 0.0769,
|
| 507 |
+
"step": 5500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 5.22,
|
| 511 |
+
"eval_loss": 0.2619025707244873,
|
| 512 |
+
"eval_runtime": 219.3928,
|
| 513 |
+
"eval_samples_per_second": 103.107,
|
| 514 |
+
"eval_steps_per_second": 6.445,
|
| 515 |
+
"step": 5500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 5.32,
|
| 519 |
+
"eval_loss": 0.25433388352394104,
|
| 520 |
+
"eval_runtime": 219.2766,
|
| 521 |
+
"eval_samples_per_second": 103.162,
|
| 522 |
+
"eval_steps_per_second": 6.448,
|
| 523 |
+
"step": 5600
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 5.41,
|
| 527 |
+
"eval_loss": 0.25473591685295105,
|
| 528 |
+
"eval_runtime": 219.1683,
|
| 529 |
+
"eval_samples_per_second": 103.213,
|
| 530 |
+
"eval_steps_per_second": 6.452,
|
| 531 |
+
"step": 5700
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 5.51,
|
| 535 |
+
"eval_loss": 0.2583990693092346,
|
| 536 |
+
"eval_runtime": 218.8181,
|
| 537 |
+
"eval_samples_per_second": 103.378,
|
| 538 |
+
"eval_steps_per_second": 6.462,
|
| 539 |
+
"step": 5800
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 5.6,
|
| 543 |
+
"eval_loss": 0.2513364255428314,
|
| 544 |
+
"eval_runtime": 219.6254,
|
| 545 |
+
"eval_samples_per_second": 102.998,
|
| 546 |
+
"eval_steps_per_second": 6.438,
|
| 547 |
+
"step": 5900
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.7,
|
| 551 |
+
"learning_rate": 2.150997150997151e-05,
|
| 552 |
+
"loss": 0.0701,
|
| 553 |
+
"step": 6000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 5.7,
|
| 557 |
+
"eval_loss": 0.25798743963241577,
|
| 558 |
+
"eval_runtime": 218.5917,
|
| 559 |
+
"eval_samples_per_second": 103.485,
|
| 560 |
+
"eval_steps_per_second": 6.469,
|
| 561 |
+
"step": 6000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 5.79,
|
| 565 |
+
"eval_loss": 0.252897173166275,
|
| 566 |
+
"eval_runtime": 218.8327,
|
| 567 |
+
"eval_samples_per_second": 103.371,
|
| 568 |
+
"eval_steps_per_second": 6.462,
|
| 569 |
+
"step": 6100
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.89,
|
| 573 |
+
"eval_loss": 0.25619062781333923,
|
| 574 |
+
"eval_runtime": 218.7633,
|
| 575 |
+
"eval_samples_per_second": 103.404,
|
| 576 |
+
"eval_steps_per_second": 6.464,
|
| 577 |
+
"step": 6200
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 5.98,
|
| 581 |
+
"eval_loss": 0.25197675824165344,
|
| 582 |
+
"eval_runtime": 218.5961,
|
| 583 |
+
"eval_samples_per_second": 103.483,
|
| 584 |
+
"eval_steps_per_second": 6.469,
|
| 585 |
+
"step": 6300
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 6.08,
|
| 589 |
+
"eval_loss": 0.2581734359264374,
|
| 590 |
+
"eval_runtime": 219.6175,
|
| 591 |
+
"eval_samples_per_second": 103.002,
|
| 592 |
+
"eval_steps_per_second": 6.438,
|
| 593 |
+
"step": 6400
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 6.17,
|
| 597 |
+
"learning_rate": 1.91358024691358e-05,
|
| 598 |
+
"loss": 0.0684,
|
| 599 |
+
"step": 6500
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 6.17,
|
| 603 |
+
"eval_loss": 0.2550990581512451,
|
| 604 |
+
"eval_runtime": 218.6851,
|
| 605 |
+
"eval_samples_per_second": 103.441,
|
| 606 |
+
"eval_steps_per_second": 6.466,
|
| 607 |
+
"step": 6500
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 6.27,
|
| 611 |
+
"eval_loss": 0.2555626332759857,
|
| 612 |
+
"eval_runtime": 219.3776,
|
| 613 |
+
"eval_samples_per_second": 103.114,
|
| 614 |
+
"eval_steps_per_second": 6.446,
|
| 615 |
+
"step": 6600
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 6.36,
|
| 619 |
+
"eval_loss": 0.25543132424354553,
|
| 620 |
+
"eval_runtime": 218.6367,
|
| 621 |
+
"eval_samples_per_second": 103.464,
|
| 622 |
+
"eval_steps_per_second": 6.467,
|
| 623 |
+
"step": 6700
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 6.46,
|
| 627 |
+
"eval_loss": 0.25568485260009766,
|
| 628 |
+
"eval_runtime": 219.9462,
|
| 629 |
+
"eval_samples_per_second": 102.848,
|
| 630 |
+
"eval_steps_per_second": 6.429,
|
| 631 |
+
"step": 6800
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 6.55,
|
| 635 |
+
"eval_loss": 0.25582244992256165,
|
| 636 |
+
"eval_runtime": 218.6889,
|
| 637 |
+
"eval_samples_per_second": 103.439,
|
| 638 |
+
"eval_steps_per_second": 6.466,
|
| 639 |
+
"step": 6900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 6.65,
|
| 643 |
+
"learning_rate": 1.6761633428300098e-05,
|
| 644 |
+
"loss": 0.0662,
|
| 645 |
+
"step": 7000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 6.65,
|
| 649 |
+
"eval_loss": 0.25293371081352234,
|
| 650 |
+
"eval_runtime": 219.8419,
|
| 651 |
+
"eval_samples_per_second": 102.897,
|
| 652 |
+
"eval_steps_per_second": 6.432,
|
| 653 |
+
"step": 7000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 6.74,
|
| 657 |
+
"eval_loss": 0.249311164021492,
|
| 658 |
+
"eval_runtime": 219.1307,
|
| 659 |
+
"eval_samples_per_second": 103.231,
|
| 660 |
+
"eval_steps_per_second": 6.453,
|
| 661 |
+
"step": 7100
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 6.84,
|
| 665 |
+
"eval_loss": 0.25428083539009094,
|
| 666 |
+
"eval_runtime": 218.6179,
|
| 667 |
+
"eval_samples_per_second": 103.473,
|
| 668 |
+
"eval_steps_per_second": 6.468,
|
| 669 |
+
"step": 7200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 6.93,
|
| 673 |
+
"eval_loss": 0.25905051827430725,
|
| 674 |
+
"eval_runtime": 219.7362,
|
| 675 |
+
"eval_samples_per_second": 102.946,
|
| 676 |
+
"eval_steps_per_second": 6.435,
|
| 677 |
+
"step": 7300
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 7.03,
|
| 681 |
+
"eval_loss": 0.25161299109458923,
|
| 682 |
+
"eval_runtime": 218.5372,
|
| 683 |
+
"eval_samples_per_second": 103.511,
|
| 684 |
+
"eval_steps_per_second": 6.47,
|
| 685 |
+
"step": 7400
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 7.12,
|
| 689 |
+
"learning_rate": 1.4387464387464389e-05,
|
| 690 |
+
"loss": 0.0659,
|
| 691 |
+
"step": 7500
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 7.12,
|
| 695 |
+
"eval_loss": 0.2567010223865509,
|
| 696 |
+
"eval_runtime": 219.8696,
|
| 697 |
+
"eval_samples_per_second": 102.884,
|
| 698 |
+
"eval_steps_per_second": 6.431,
|
| 699 |
+
"step": 7500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 7.22,
|
| 703 |
+
"eval_loss": 0.2568127512931824,
|
| 704 |
+
"eval_runtime": 218.4916,
|
| 705 |
+
"eval_samples_per_second": 103.533,
|
| 706 |
+
"eval_steps_per_second": 6.472,
|
| 707 |
+
"step": 7600
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 7.31,
|
| 711 |
+
"eval_loss": 0.24921847879886627,
|
| 712 |
+
"eval_runtime": 219.9605,
|
| 713 |
+
"eval_samples_per_second": 102.841,
|
| 714 |
+
"eval_steps_per_second": 6.428,
|
| 715 |
+
"step": 7700
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 7.41,
|
| 719 |
+
"eval_loss": 0.24751408398151398,
|
| 720 |
+
"eval_runtime": 218.5269,
|
| 721 |
+
"eval_samples_per_second": 103.516,
|
| 722 |
+
"eval_steps_per_second": 6.471,
|
| 723 |
+
"step": 7800
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 7.5,
|
| 727 |
+
"eval_loss": 0.24565500020980835,
|
| 728 |
+
"eval_runtime": 219.112,
|
| 729 |
+
"eval_samples_per_second": 103.239,
|
| 730 |
+
"eval_steps_per_second": 6.453,
|
| 731 |
+
"step": 7900
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 7.6,
|
| 735 |
+
"learning_rate": 1.2013295346628681e-05,
|
| 736 |
+
"loss": 0.0641,
|
| 737 |
+
"step": 8000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 7.6,
|
| 741 |
+
"eval_loss": 0.2555699646472931,
|
| 742 |
+
"eval_runtime": 218.4879,
|
| 743 |
+
"eval_samples_per_second": 103.534,
|
| 744 |
+
"eval_steps_per_second": 6.472,
|
| 745 |
+
"step": 8000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 7.69,
|
| 749 |
+
"eval_loss": 0.25907498598098755,
|
| 750 |
+
"eval_runtime": 218.8796,
|
| 751 |
+
"eval_samples_per_second": 103.349,
|
| 752 |
+
"eval_steps_per_second": 6.46,
|
| 753 |
+
"step": 8100
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 7.79,
|
| 757 |
+
"eval_loss": 0.2498636245727539,
|
| 758 |
+
"eval_runtime": 218.2333,
|
| 759 |
+
"eval_samples_per_second": 103.655,
|
| 760 |
+
"eval_steps_per_second": 6.479,
|
| 761 |
+
"step": 8200
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 7.88,
|
| 765 |
+
"eval_loss": 0.24620996415615082,
|
| 766 |
+
"eval_runtime": 218.4049,
|
| 767 |
+
"eval_samples_per_second": 103.574,
|
| 768 |
+
"eval_steps_per_second": 6.474,
|
| 769 |
+
"step": 8300
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 7.98,
|
| 773 |
+
"eval_loss": 0.2514709234237671,
|
| 774 |
+
"eval_runtime": 218.5279,
|
| 775 |
+
"eval_samples_per_second": 103.515,
|
| 776 |
+
"eval_steps_per_second": 6.471,
|
| 777 |
+
"step": 8400
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 8.07,
|
| 781 |
+
"learning_rate": 9.639126305792973e-06,
|
| 782 |
+
"loss": 0.0614,
|
| 783 |
+
"step": 8500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 8.07,
|
| 787 |
+
"eval_loss": 0.24893517792224884,
|
| 788 |
+
"eval_runtime": 218.4312,
|
| 789 |
+
"eval_samples_per_second": 103.561,
|
| 790 |
+
"eval_steps_per_second": 6.473,
|
| 791 |
+
"step": 8500
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 8.17,
|
| 795 |
+
"eval_loss": 0.24635082483291626,
|
| 796 |
+
"eval_runtime": 218.6536,
|
| 797 |
+
"eval_samples_per_second": 103.456,
|
| 798 |
+
"eval_steps_per_second": 6.467,
|
| 799 |
+
"step": 8600
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 8.26,
|
| 803 |
+
"eval_loss": 0.24810662865638733,
|
| 804 |
+
"eval_runtime": 218.4312,
|
| 805 |
+
"eval_samples_per_second": 103.561,
|
| 806 |
+
"eval_steps_per_second": 6.473,
|
| 807 |
+
"step": 8700
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 8.36,
|
| 811 |
+
"eval_loss": 0.24930644035339355,
|
| 812 |
+
"eval_runtime": 218.7482,
|
| 813 |
+
"eval_samples_per_second": 103.411,
|
| 814 |
+
"eval_steps_per_second": 6.464,
|
| 815 |
+
"step": 8800
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 8.45,
|
| 819 |
+
"eval_loss": 0.24013535678386688,
|
| 820 |
+
"eval_runtime": 218.398,
|
| 821 |
+
"eval_samples_per_second": 103.577,
|
| 822 |
+
"eval_steps_per_second": 6.474,
|
| 823 |
+
"step": 8900
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 8.55,
|
| 827 |
+
"learning_rate": 7.264957264957266e-06,
|
| 828 |
+
"loss": 0.0609,
|
| 829 |
+
"step": 9000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 8.55,
|
| 833 |
+
"eval_loss": 0.2461770623922348,
|
| 834 |
+
"eval_runtime": 218.9012,
|
| 835 |
+
"eval_samples_per_second": 103.339,
|
| 836 |
+
"eval_steps_per_second": 6.46,
|
| 837 |
+
"step": 9000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 8.64,
|
| 841 |
+
"eval_loss": 0.24963241815567017,
|
| 842 |
+
"eval_runtime": 218.2697,
|
| 843 |
+
"eval_samples_per_second": 103.638,
|
| 844 |
+
"eval_steps_per_second": 6.478,
|
| 845 |
+
"step": 9100
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 8.74,
|
| 849 |
+
"eval_loss": 0.24689340591430664,
|
| 850 |
+
"eval_runtime": 218.5291,
|
| 851 |
+
"eval_samples_per_second": 103.515,
|
| 852 |
+
"eval_steps_per_second": 6.471,
|
| 853 |
+
"step": 9200
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 8.83,
|
| 857 |
+
"eval_loss": 0.2498210072517395,
|
| 858 |
+
"eval_runtime": 218.2515,
|
| 859 |
+
"eval_samples_per_second": 103.646,
|
| 860 |
+
"eval_steps_per_second": 6.479,
|
| 861 |
+
"step": 9300
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 8.93,
|
| 865 |
+
"eval_loss": 0.24612723290920258,
|
| 866 |
+
"eval_runtime": 218.3684,
|
| 867 |
+
"eval_samples_per_second": 103.591,
|
| 868 |
+
"eval_steps_per_second": 6.475,
|
| 869 |
+
"step": 9400
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 9.02,
|
| 873 |
+
"learning_rate": 4.890788224121558e-06,
|
| 874 |
+
"loss": 0.0588,
|
| 875 |
+
"step": 9500
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 9.02,
|
| 879 |
+
"eval_loss": 0.247446671128273,
|
| 880 |
+
"eval_runtime": 218.2559,
|
| 881 |
+
"eval_samples_per_second": 103.644,
|
| 882 |
+
"eval_steps_per_second": 6.479,
|
| 883 |
+
"step": 9500
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 9.12,
|
| 887 |
+
"eval_loss": 0.24682562053203583,
|
| 888 |
+
"eval_runtime": 218.332,
|
| 889 |
+
"eval_samples_per_second": 103.608,
|
| 890 |
+
"eval_steps_per_second": 6.476,
|
| 891 |
+
"step": 9600
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 9.21,
|
| 895 |
+
"eval_loss": 0.2363210916519165,
|
| 896 |
+
"eval_runtime": 218.2595,
|
| 897 |
+
"eval_samples_per_second": 103.643,
|
| 898 |
+
"eval_steps_per_second": 6.479,
|
| 899 |
+
"step": 9700
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 9.31,
|
| 903 |
+
"eval_loss": 0.24492982029914856,
|
| 904 |
+
"eval_runtime": 218.2962,
|
| 905 |
+
"eval_samples_per_second": 103.625,
|
| 906 |
+
"eval_steps_per_second": 6.477,
|
| 907 |
+
"step": 9800
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 9.4,
|
| 911 |
+
"eval_loss": 0.247760608792305,
|
| 912 |
+
"eval_runtime": 218.2063,
|
| 913 |
+
"eval_samples_per_second": 103.668,
|
| 914 |
+
"eval_steps_per_second": 6.48,
|
| 915 |
+
"step": 9900
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 9.5,
|
| 919 |
+
"learning_rate": 2.51661918328585e-06,
|
| 920 |
+
"loss": 0.0604,
|
| 921 |
+
"step": 10000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 9.5,
|
| 925 |
+
"eval_loss": 0.24903397262096405,
|
| 926 |
+
"eval_runtime": 218.2843,
|
| 927 |
+
"eval_samples_per_second": 103.631,
|
| 928 |
+
"eval_steps_per_second": 6.478,
|
| 929 |
+
"step": 10000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 9.59,
|
| 933 |
+
"eval_loss": 0.25066474080085754,
|
| 934 |
+
"eval_runtime": 218.2601,
|
| 935 |
+
"eval_samples_per_second": 103.642,
|
| 936 |
+
"eval_steps_per_second": 6.479,
|
| 937 |
+
"step": 10100
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 9.69,
|
| 941 |
+
"eval_loss": 0.24707233905792236,
|
| 942 |
+
"eval_runtime": 218.2446,
|
| 943 |
+
"eval_samples_per_second": 103.65,
|
| 944 |
+
"eval_steps_per_second": 6.479,
|
| 945 |
+
"step": 10200
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 9.78,
|
| 949 |
+
"eval_loss": 0.24911357462406158,
|
| 950 |
+
"eval_runtime": 218.2948,
|
| 951 |
+
"eval_samples_per_second": 103.626,
|
| 952 |
+
"eval_steps_per_second": 6.477,
|
| 953 |
+
"step": 10300
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 9.88,
|
| 957 |
+
"eval_loss": 0.24460090696811676,
|
| 958 |
+
"eval_runtime": 218.238,
|
| 959 |
+
"eval_samples_per_second": 103.653,
|
| 960 |
+
"eval_steps_per_second": 6.479,
|
| 961 |
+
"step": 10400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 9.97,
|
| 965 |
+
"learning_rate": 1.4245014245014247e-07,
|
| 966 |
+
"loss": 0.0573,
|
| 967 |
+
"step": 10500
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 9.97,
|
| 971 |
+
"eval_loss": 0.24572330713272095,
|
| 972 |
+
"eval_runtime": 218.3788,
|
| 973 |
+
"eval_samples_per_second": 103.586,
|
| 974 |
+
"eval_steps_per_second": 6.475,
|
| 975 |
+
"step": 10500
|
| 976 |
+
}
|
| 977 |
+
],
|
| 978 |
+
"logging_steps": 500,
|
| 979 |
+
"max_steps": 10530,
|
| 980 |
+
"num_train_epochs": 10,
|
| 981 |
+
"save_steps": 100,
|
| 982 |
+
"total_flos": 1.7676748920639283e+17,
|
| 983 |
+
"trial_name": null,
|
| 984 |
+
"trial_params": null
|
| 985 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b0da450342b037e604e0cf49e4db05d8c1bf2a6735c6da8cce707f438b68765
|
| 3 |
+
size 4027
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|