Upload 216 files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1000/README.md +204 -0
- checkpoint-1000/adapter_config.json +26 -0
- checkpoint-1000/adapter_model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +18 -0
- checkpoint-1000/tokenization_chatglm.py +300 -0
- checkpoint-1000/tokenizer.model +3 -0
- checkpoint-1000/tokenizer_config.json +41 -0
- checkpoint-1000/trainer_state.json +1221 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1500/README.md +204 -0
- checkpoint-1500/adapter_config.json +26 -0
- checkpoint-1500/adapter_model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/special_tokens_map.json +18 -0
- checkpoint-1500/tokenization_chatglm.py +300 -0
- checkpoint-1500/tokenizer.model +3 -0
- checkpoint-1500/tokenizer_config.json +41 -0
- checkpoint-1500/trainer_state.json +1821 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/README.md +204 -0
- checkpoint-2000/adapter_config.json +26 -0
- checkpoint-2000/adapter_model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/special_tokens_map.json +18 -0
- checkpoint-2000/tokenization_chatglm.py +300 -0
- checkpoint-2000/tokenizer.model +3 -0
- checkpoint-2000/tokenizer_config.json +41 -0
- checkpoint-2000/trainer_state.json +2421 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/README.md +204 -0
- checkpoint-2500/adapter_config.json +26 -0
- checkpoint-2500/adapter_model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/special_tokens_map.json +18 -0
- checkpoint-2500/tokenization_chatglm.py +300 -0
- checkpoint-2500/tokenizer.model +3 -0
- checkpoint-2500/tokenizer_config.json +41 -0
- checkpoint-2500/trainer_state.json +3021 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-3000/README.md +204 -0
- checkpoint-3000/adapter_config.json +26 -0
checkpoint-1000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chatglm3-6b-base
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-1000/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chatglm3-6b-base",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"query_key_value"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM",
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
checkpoint-1000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d53edf161f3a07e2d551714247c93fc284b893fb5528a49a55fadf70ff8eed41
|
3 |
+
size 7807744
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7670653bcd7d18fd04a1f4d7fbb09d9a94c9d2796d6ae96f3b88f0a70245ba2b
|
3 |
+
size 15644485
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:092276df08ab03d1c657bebf8c8ca092758eefddc44fbdcfe4fa09446ad954a3
|
3 |
+
size 14575
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a724eb8dd004def7e4c5b752d32b5f2b92570d2204069c06be7d67c6e7933312
|
3 |
+
size 627
|
checkpoint-1000/special_tokens_map.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|user|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|observation|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
]
|
18 |
+
}
|
checkpoint-1000/tokenization_chatglm.py
ADDED
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import json
|
2 |
+
import os
|
3 |
+
import re
|
4 |
+
from typing import List, Optional, Union, Dict
|
5 |
+
from sentencepiece import SentencePieceProcessor
|
6 |
+
from transformers import PreTrainedTokenizer
|
7 |
+
from transformers.utils import logging, PaddingStrategy
|
8 |
+
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
|
9 |
+
|
10 |
+
|
11 |
+
class SPTokenizer:
|
12 |
+
def __init__(self, model_path: str):
|
13 |
+
# reload tokenizer
|
14 |
+
assert os.path.isfile(model_path), model_path
|
15 |
+
self.sp_model = SentencePieceProcessor(model_file=model_path)
|
16 |
+
|
17 |
+
# BOS / EOS token IDs
|
18 |
+
self.n_words: int = self.sp_model.vocab_size()
|
19 |
+
self.bos_id: int = self.sp_model.bos_id()
|
20 |
+
self.eos_id: int = self.sp_model.eos_id()
|
21 |
+
self.pad_id: int = self.sp_model.unk_id()
|
22 |
+
assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
|
23 |
+
|
24 |
+
role_special_tokens = ["<|system|>", "<|user|>", "<|assistant|>", "<|observation|>"]
|
25 |
+
special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"] + role_special_tokens
|
26 |
+
self.special_tokens = {}
|
27 |
+
self.index_special_tokens = {}
|
28 |
+
for token in special_tokens:
|
29 |
+
self.special_tokens[token] = self.n_words
|
30 |
+
self.index_special_tokens[self.n_words] = token
|
31 |
+
self.n_words += 1
|
32 |
+
self.role_special_token_expression = "|".join([re.escape(token) for token in role_special_tokens])
|
33 |
+
|
34 |
+
def tokenize(self, s: str, encode_special_tokens=False):
|
35 |
+
if encode_special_tokens:
|
36 |
+
last_index = 0
|
37 |
+
t = []
|
38 |
+
for match in re.finditer(self.role_special_token_expression, s):
|
39 |
+
if last_index < match.start():
|
40 |
+
t.extend(self.sp_model.EncodeAsPieces(s[last_index:match.start()]))
|
41 |
+
t.append(s[match.start():match.end()])
|
42 |
+
last_index = match.end()
|
43 |
+
if last_index < len(s):
|
44 |
+
t.extend(self.sp_model.EncodeAsPieces(s[last_index:]))
|
45 |
+
return t
|
46 |
+
else:
|
47 |
+
return self.sp_model.EncodeAsPieces(s)
|
48 |
+
|
49 |
+
def encode(self, s: str, bos: bool = False, eos: bool = False) -> List[int]:
|
50 |
+
assert type(s) is str
|
51 |
+
t = self.sp_model.encode(s)
|
52 |
+
if bos:
|
53 |
+
t = [self.bos_id] + t
|
54 |
+
if eos:
|
55 |
+
t = t + [self.eos_id]
|
56 |
+
return t
|
57 |
+
|
58 |
+
def decode(self, t: List[int]) -> str:
|
59 |
+
text, buffer = "", []
|
60 |
+
for token in t:
|
61 |
+
if token in self.index_special_tokens:
|
62 |
+
if buffer:
|
63 |
+
text += self.sp_model.decode(buffer)
|
64 |
+
buffer = []
|
65 |
+
text += self.index_special_tokens[token]
|
66 |
+
else:
|
67 |
+
buffer.append(token)
|
68 |
+
if buffer:
|
69 |
+
text += self.sp_model.decode(buffer)
|
70 |
+
return text
|
71 |
+
|
72 |
+
def decode_tokens(self, tokens: List[str]) -> str:
|
73 |
+
text = self.sp_model.DecodePieces(tokens)
|
74 |
+
return text
|
75 |
+
|
76 |
+
def convert_token_to_id(self, token):
|
77 |
+
""" Converts a token (str) in an id using the vocab. """
|
78 |
+
if token in self.special_tokens:
|
79 |
+
return self.special_tokens[token]
|
80 |
+
return self.sp_model.PieceToId(token)
|
81 |
+
|
82 |
+
def convert_id_to_token(self, index):
|
83 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
84 |
+
if index in self.index_special_tokens:
|
85 |
+
return self.index_special_tokens[index]
|
86 |
+
if index in [self.eos_id, self.bos_id, self.pad_id] or index < 0:
|
87 |
+
return ""
|
88 |
+
return self.sp_model.IdToPiece(index)
|
89 |
+
|
90 |
+
|
91 |
+
class ChatGLMTokenizer(PreTrainedTokenizer):
|
92 |
+
vocab_files_names = {"vocab_file": "tokenizer.model"}
|
93 |
+
|
94 |
+
model_input_names = ["input_ids", "attention_mask", "position_ids"]
|
95 |
+
|
96 |
+
def __init__(self, vocab_file, padding_side="left", clean_up_tokenization_spaces=False, encode_special_tokens=False,
|
97 |
+
**kwargs):
|
98 |
+
self.name = "GLMTokenizer"
|
99 |
+
|
100 |
+
self.vocab_file = vocab_file
|
101 |
+
self.tokenizer = SPTokenizer(vocab_file)
|
102 |
+
self.special_tokens = {
|
103 |
+
"<bos>": self.tokenizer.bos_id,
|
104 |
+
"<eos>": self.tokenizer.eos_id,
|
105 |
+
"<pad>": self.tokenizer.pad_id
|
106 |
+
}
|
107 |
+
self.encode_special_tokens = encode_special_tokens
|
108 |
+
super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
109 |
+
encode_special_tokens=encode_special_tokens,
|
110 |
+
**kwargs)
|
111 |
+
|
112 |
+
def get_command(self, token):
|
113 |
+
if token in self.special_tokens:
|
114 |
+
return self.special_tokens[token]
|
115 |
+
assert token in self.tokenizer.special_tokens, f"{token} is not a special token for {self.name}"
|
116 |
+
return self.tokenizer.special_tokens[token]
|
117 |
+
|
118 |
+
@property
|
119 |
+
def unk_token(self) -> str:
|
120 |
+
return "<unk>"
|
121 |
+
|
122 |
+
@property
|
123 |
+
def pad_token(self) -> str:
|
124 |
+
return "<unk>"
|
125 |
+
|
126 |
+
@property
|
127 |
+
def pad_token_id(self):
|
128 |
+
return self.get_command("<pad>")
|
129 |
+
|
130 |
+
@property
|
131 |
+
def eos_token(self) -> str:
|
132 |
+
return "</s>"
|
133 |
+
|
134 |
+
@property
|
135 |
+
def eos_token_id(self):
|
136 |
+
return self.get_command("<eos>")
|
137 |
+
|
138 |
+
@property
|
139 |
+
def vocab_size(self):
|
140 |
+
return self.tokenizer.n_words
|
141 |
+
|
142 |
+
def get_vocab(self):
|
143 |
+
""" Returns vocab as a dict """
|
144 |
+
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
145 |
+
vocab.update(self.added_tokens_encoder)
|
146 |
+
return vocab
|
147 |
+
|
148 |
+
def _tokenize(self, text, **kwargs):
|
149 |
+
return self.tokenizer.tokenize(text, encode_special_tokens=self.encode_special_tokens)
|
150 |
+
|
151 |
+
def _convert_token_to_id(self, token):
|
152 |
+
""" Converts a token (str) in an id using the vocab. """
|
153 |
+
return self.tokenizer.convert_token_to_id(token)
|
154 |
+
|
155 |
+
def _convert_id_to_token(self, index):
|
156 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
157 |
+
return self.tokenizer.convert_id_to_token(index)
|
158 |
+
|
159 |
+
def convert_tokens_to_string(self, tokens: List[str]) -> str:
|
160 |
+
return self.tokenizer.decode_tokens(tokens)
|
161 |
+
|
162 |
+
def save_vocabulary(self, save_directory, filename_prefix=None):
|
163 |
+
"""
|
164 |
+
Save the vocabulary and special tokens file to a directory.
|
165 |
+
|
166 |
+
Args:
|
167 |
+
save_directory (`str`):
|
168 |
+
The directory in which to save the vocabulary.
|
169 |
+
filename_prefix (`str`, *optional*):
|
170 |
+
An optional prefix to add to the named of the saved files.
|
171 |
+
|
172 |
+
Returns:
|
173 |
+
`Tuple(str)`: Paths to the files saved.
|
174 |
+
"""
|
175 |
+
if os.path.isdir(save_directory):
|
176 |
+
vocab_file = os.path.join(
|
177 |
+
save_directory, self.vocab_files_names["vocab_file"]
|
178 |
+
)
|
179 |
+
else:
|
180 |
+
vocab_file = save_directory
|
181 |
+
|
182 |
+
with open(self.vocab_file, 'rb') as fin:
|
183 |
+
proto_str = fin.read()
|
184 |
+
|
185 |
+
with open(vocab_file, "wb") as writer:
|
186 |
+
writer.write(proto_str)
|
187 |
+
|
188 |
+
return (vocab_file,)
|
189 |
+
|
190 |
+
def get_prefix_tokens(self):
|
191 |
+
prefix_tokens = [self.get_command("[gMASK]"), self.get_command("sop")]
|
192 |
+
return prefix_tokens
|
193 |
+
|
194 |
+
def build_single_message(self, role, metadata, message):
|
195 |
+
assert role in ["system", "user", "assistant", "observation"], role
|
196 |
+
role_tokens = [self.get_command(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n")
|
197 |
+
message_tokens = self.tokenizer.encode(message)
|
198 |
+
tokens = role_tokens + message_tokens
|
199 |
+
return tokens
|
200 |
+
|
201 |
+
def build_chat_input(self, query, history=None, role="user"):
|
202 |
+
if history is None:
|
203 |
+
history = []
|
204 |
+
input_ids = []
|
205 |
+
for item in history:
|
206 |
+
content = item["content"]
|
207 |
+
if item["role"] == "system" and "tools" in item:
|
208 |
+
content = content + "\n" + json.dumps(item["tools"], indent=4, ensure_ascii=False)
|
209 |
+
input_ids.extend(self.build_single_message(item["role"], item.get("metadata", ""), content))
|
210 |
+
input_ids.extend(self.build_single_message(role, "", query))
|
211 |
+
input_ids.extend([self.get_command("<|assistant|>")])
|
212 |
+
return self.batch_encode_plus([input_ids], return_tensors="pt", is_split_into_words=True)
|
213 |
+
|
214 |
+
def build_inputs_with_special_tokens(
|
215 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
216 |
+
) -> List[int]:
|
217 |
+
"""
|
218 |
+
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
|
219 |
+
adding special tokens. A BERT sequence has the following format:
|
220 |
+
|
221 |
+
- single sequence: `[CLS] X [SEP]`
|
222 |
+
- pair of sequences: `[CLS] A [SEP] B [SEP]`
|
223 |
+
|
224 |
+
Args:
|
225 |
+
token_ids_0 (`List[int]`):
|
226 |
+
List of IDs to which the special tokens will be added.
|
227 |
+
token_ids_1 (`List[int]`, *optional*):
|
228 |
+
Optional second list of IDs for sequence pairs.
|
229 |
+
|
230 |
+
Returns:
|
231 |
+
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
|
232 |
+
"""
|
233 |
+
prefix_tokens = self.get_prefix_tokens()
|
234 |
+
token_ids_0 = prefix_tokens + token_ids_0
|
235 |
+
if token_ids_1 is not None:
|
236 |
+
token_ids_0 = token_ids_0 + token_ids_1 + [self.get_command("<eos>")]
|
237 |
+
return token_ids_0
|
238 |
+
|
239 |
+
def _pad(
|
240 |
+
self,
|
241 |
+
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
|
242 |
+
max_length: Optional[int] = None,
|
243 |
+
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
244 |
+
pad_to_multiple_of: Optional[int] = None,
|
245 |
+
return_attention_mask: Optional[bool] = None,
|
246 |
+
) -> dict:
|
247 |
+
"""
|
248 |
+
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
|
249 |
+
|
250 |
+
Args:
|
251 |
+
encoded_inputs:
|
252 |
+
Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
|
253 |
+
max_length: maximum length of the returned list and optionally padding length (see below).
|
254 |
+
Will truncate by taking into account the special tokens.
|
255 |
+
padding_strategy: PaddingStrategy to use for padding.
|
256 |
+
|
257 |
+
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
|
258 |
+
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
|
259 |
+
- PaddingStrategy.DO_NOT_PAD: Do not pad
|
260 |
+
The tokenizer padding sides are defined in self.padding_side:
|
261 |
+
|
262 |
+
- 'left': pads on the left of the sequences
|
263 |
+
- 'right': pads on the right of the sequences
|
264 |
+
pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
|
265 |
+
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
|
266 |
+
`>= 7.5` (Volta).
|
267 |
+
return_attention_mask:
|
268 |
+
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
|
269 |
+
"""
|
270 |
+
# Load from model defaults
|
271 |
+
assert self.padding_side == "left"
|
272 |
+
|
273 |
+
required_input = encoded_inputs[self.model_input_names[0]]
|
274 |
+
seq_length = len(required_input)
|
275 |
+
|
276 |
+
if padding_strategy == PaddingStrategy.LONGEST:
|
277 |
+
max_length = len(required_input)
|
278 |
+
|
279 |
+
if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
|
280 |
+
max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
|
281 |
+
|
282 |
+
needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
|
283 |
+
|
284 |
+
# Initialize attention mask if not present.
|
285 |
+
if "attention_mask" not in encoded_inputs:
|
286 |
+
encoded_inputs["attention_mask"] = [1] * seq_length
|
287 |
+
|
288 |
+
if "position_ids" not in encoded_inputs:
|
289 |
+
encoded_inputs["position_ids"] = list(range(seq_length))
|
290 |
+
|
291 |
+
if needs_to_be_padded:
|
292 |
+
difference = max_length - len(required_input)
|
293 |
+
|
294 |
+
if "attention_mask" in encoded_inputs:
|
295 |
+
encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
|
296 |
+
if "position_ids" in encoded_inputs:
|
297 |
+
encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
|
298 |
+
encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
|
299 |
+
|
300 |
+
return encoded_inputs
|
checkpoint-1000/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
checkpoint-1000/tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"64795": {
|
4 |
+
"content": "<|user|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"64797": {
|
12 |
+
"content": "<|observation|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
}
|
19 |
+
},
|
20 |
+
"additional_special_tokens": [
|
21 |
+
"<|user|>",
|
22 |
+
"<|observation|>"
|
23 |
+
],
|
24 |
+
"auto_map": {
|
25 |
+
"AutoTokenizer": [
|
26 |
+
"tokenization_chatglm.ChatGLMTokenizer",
|
27 |
+
null
|
28 |
+
]
|
29 |
+
},
|
30 |
+
"clean_up_tokenization_spaces": false,
|
31 |
+
"do_lower_case": false,
|
32 |
+
"encode_special_tokens": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"remove_space": false,
|
38 |
+
"split_special_tokens": false,
|
39 |
+
"tokenizer_class": "ChatGLMTokenizer",
|
40 |
+
"unk_token": "<unk>"
|
41 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,1221 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5018190942165349,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.9999980101927616e-05,
|
14 |
+
"loss": 3.2533,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4.99999204077421e-05,
|
20 |
+
"loss": 3.2279,
|
21 |
+
"step": 10
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 4.999978982687695e-05,
|
26 |
+
"loss": 3.193,
|
27 |
+
"step": 15
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 4.9999597065062966e-05,
|
32 |
+
"loss": 3.2863,
|
33 |
+
"step": 20
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 4.999934212277958e-05,
|
38 |
+
"loss": 3.1724,
|
39 |
+
"step": 25
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 4.999902500066093e-05,
|
44 |
+
"loss": 3.1088,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 4.999864569949576e-05,
|
50 |
+
"loss": 3.3241,
|
51 |
+
"step": 35
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 4.99982042202275e-05,
|
56 |
+
"loss": 3.1904,
|
57 |
+
"step": 40
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 4.999770056395421e-05,
|
62 |
+
"loss": 2.9254,
|
63 |
+
"step": 45
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 4.999713473192863e-05,
|
68 |
+
"loss": 3.1845,
|
69 |
+
"step": 50
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 4.999650672555812e-05,
|
74 |
+
"loss": 2.8475,
|
75 |
+
"step": 55
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 4.9995816546404695e-05,
|
80 |
+
"loss": 3.0486,
|
81 |
+
"step": 60
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 4.9995064196185014e-05,
|
86 |
+
"loss": 2.6464,
|
87 |
+
"step": 65
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 4.9994249676770364e-05,
|
92 |
+
"loss": 3.0446,
|
93 |
+
"step": 70
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 4.999337299018667e-05,
|
98 |
+
"loss": 3.375,
|
99 |
+
"step": 75
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 4.999243413861447e-05,
|
104 |
+
"loss": 2.8787,
|
105 |
+
"step": 80
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 4.999143312438893e-05,
|
110 |
+
"loss": 3.014,
|
111 |
+
"step": 85
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.05,
|
115 |
+
"learning_rate": 4.999036994999985e-05,
|
116 |
+
"loss": 2.8288,
|
117 |
+
"step": 90
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 4.9989244618091596e-05,
|
122 |
+
"loss": 3.1879,
|
123 |
+
"step": 95
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 4.998805713146317e-05,
|
128 |
+
"loss": 2.9749,
|
129 |
+
"step": 100
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 4.9986807493068165e-05,
|
134 |
+
"loss": 2.6304,
|
135 |
+
"step": 105
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06,
|
139 |
+
"learning_rate": 4.998549570601475e-05,
|
140 |
+
"loss": 2.943,
|
141 |
+
"step": 110
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 4.998412177356568e-05,
|
146 |
+
"loss": 2.7595,
|
147 |
+
"step": 115
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 4.9982685699138275e-05,
|
152 |
+
"loss": 2.7377,
|
153 |
+
"step": 120
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 4.9981187486304423e-05,
|
158 |
+
"loss": 2.9878,
|
159 |
+
"step": 125
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07,
|
163 |
+
"learning_rate": 4.997962713879058e-05,
|
164 |
+
"loss": 2.7882,
|
165 |
+
"step": 130
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.07,
|
169 |
+
"learning_rate": 4.997800466047772e-05,
|
170 |
+
"loss": 2.7802,
|
171 |
+
"step": 135
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 4.997632005540138e-05,
|
176 |
+
"loss": 3.0129,
|
177 |
+
"step": 140
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 4.997457332775159e-05,
|
182 |
+
"loss": 2.9444,
|
183 |
+
"step": 145
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.08,
|
187 |
+
"learning_rate": 4.997276448187294e-05,
|
188 |
+
"loss": 2.9664,
|
189 |
+
"step": 150
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.08,
|
193 |
+
"learning_rate": 4.9970893522264476e-05,
|
194 |
+
"loss": 2.7367,
|
195 |
+
"step": 155
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 4.996896045357977e-05,
|
200 |
+
"loss": 2.7012,
|
201 |
+
"step": 160
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 4.9966965280626856e-05,
|
206 |
+
"loss": 2.8493,
|
207 |
+
"step": 165
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.09,
|
211 |
+
"learning_rate": 4.996490800836825e-05,
|
212 |
+
"loss": 2.9274,
|
213 |
+
"step": 170
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09,
|
217 |
+
"learning_rate": 4.996278864192092e-05,
|
218 |
+
"loss": 2.8093,
|
219 |
+
"step": 175
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 4.9960607186556286e-05,
|
224 |
+
"loss": 3.1782,
|
225 |
+
"step": 180
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 4.995836364770018e-05,
|
230 |
+
"loss": 2.7507,
|
231 |
+
"step": 185
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.1,
|
235 |
+
"learning_rate": 4.995605803093287e-05,
|
236 |
+
"loss": 2.6724,
|
237 |
+
"step": 190
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.1,
|
241 |
+
"learning_rate": 4.9953690341989026e-05,
|
242 |
+
"loss": 3.0258,
|
243 |
+
"step": 195
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 4.9951260586757694e-05,
|
248 |
+
"loss": 3.1134,
|
249 |
+
"step": 200
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1,
|
253 |
+
"learning_rate": 4.9948768771282314e-05,
|
254 |
+
"loss": 2.9937,
|
255 |
+
"step": 205
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11,
|
259 |
+
"learning_rate": 4.9946214901760665e-05,
|
260 |
+
"loss": 2.7394,
|
261 |
+
"step": 210
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.11,
|
265 |
+
"learning_rate": 4.99435989845449e-05,
|
266 |
+
"loss": 2.9696,
|
267 |
+
"step": 215
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 4.994092102614146e-05,
|
272 |
+
"loss": 2.753,
|
273 |
+
"step": 220
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.11,
|
277 |
+
"learning_rate": 4.993818103321113e-05,
|
278 |
+
"loss": 3.0759,
|
279 |
+
"step": 225
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.12,
|
283 |
+
"learning_rate": 4.9935379012568985e-05,
|
284 |
+
"loss": 2.7512,
|
285 |
+
"step": 230
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.12,
|
289 |
+
"learning_rate": 4.993251497118438e-05,
|
290 |
+
"loss": 2.8656,
|
291 |
+
"step": 235
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 4.992958891618091e-05,
|
296 |
+
"loss": 2.6628,
|
297 |
+
"step": 240
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.12,
|
301 |
+
"learning_rate": 4.992660085483645e-05,
|
302 |
+
"loss": 2.8012,
|
303 |
+
"step": 245
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.13,
|
307 |
+
"learning_rate": 4.992355079458307e-05,
|
308 |
+
"loss": 2.8141,
|
309 |
+
"step": 250
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.13,
|
313 |
+
"learning_rate": 4.992043874300706e-05,
|
314 |
+
"loss": 2.9083,
|
315 |
+
"step": 255
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.13,
|
319 |
+
"learning_rate": 4.991726470784891e-05,
|
320 |
+
"loss": 2.5846,
|
321 |
+
"step": 260
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.13,
|
325 |
+
"learning_rate": 4.991402869700325e-05,
|
326 |
+
"loss": 2.8088,
|
327 |
+
"step": 265
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.14,
|
331 |
+
"learning_rate": 4.991073071851889e-05,
|
332 |
+
"loss": 2.9979,
|
333 |
+
"step": 270
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.14,
|
337 |
+
"learning_rate": 4.990737078059875e-05,
|
338 |
+
"loss": 3.0171,
|
339 |
+
"step": 275
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.14,
|
343 |
+
"learning_rate": 4.990394889159986e-05,
|
344 |
+
"loss": 2.9278,
|
345 |
+
"step": 280
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.14,
|
349 |
+
"learning_rate": 4.9900465060033364e-05,
|
350 |
+
"loss": 2.7998,
|
351 |
+
"step": 285
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.15,
|
355 |
+
"learning_rate": 4.989691929456443e-05,
|
356 |
+
"loss": 2.721,
|
357 |
+
"step": 290
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.15,
|
361 |
+
"learning_rate": 4.9893311604012306e-05,
|
362 |
+
"loss": 3.0291,
|
363 |
+
"step": 295
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.15,
|
367 |
+
"learning_rate": 4.988964199735024e-05,
|
368 |
+
"loss": 2.9777,
|
369 |
+
"step": 300
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.15,
|
373 |
+
"learning_rate": 4.988591048370552e-05,
|
374 |
+
"loss": 2.318,
|
375 |
+
"step": 305
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.16,
|
379 |
+
"learning_rate": 4.988211707235936e-05,
|
380 |
+
"loss": 3.0332,
|
381 |
+
"step": 310
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.16,
|
385 |
+
"learning_rate": 4.987826177274697e-05,
|
386 |
+
"loss": 2.4888,
|
387 |
+
"step": 315
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.16,
|
391 |
+
"learning_rate": 4.987434459445748e-05,
|
392 |
+
"loss": 2.9259,
|
393 |
+
"step": 320
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.16,
|
397 |
+
"learning_rate": 4.987036554723391e-05,
|
398 |
+
"loss": 2.9568,
|
399 |
+
"step": 325
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.17,
|
403 |
+
"learning_rate": 4.98663246409732e-05,
|
404 |
+
"loss": 2.8708,
|
405 |
+
"step": 330
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.17,
|
409 |
+
"learning_rate": 4.986222188572611e-05,
|
410 |
+
"loss": 2.7848,
|
411 |
+
"step": 335
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.17,
|
415 |
+
"learning_rate": 4.985805729169728e-05,
|
416 |
+
"loss": 2.6178,
|
417 |
+
"step": 340
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.17,
|
421 |
+
"learning_rate": 4.985383086924511e-05,
|
422 |
+
"loss": 2.8326,
|
423 |
+
"step": 345
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.18,
|
427 |
+
"learning_rate": 4.984954262888182e-05,
|
428 |
+
"loss": 2.8845,
|
429 |
+
"step": 350
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.18,
|
433 |
+
"learning_rate": 4.9845192581273365e-05,
|
434 |
+
"loss": 2.6151,
|
435 |
+
"step": 355
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.18,
|
439 |
+
"learning_rate": 4.984078073723944e-05,
|
440 |
+
"loss": 2.8474,
|
441 |
+
"step": 360
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.18,
|
445 |
+
"learning_rate": 4.9836307107753455e-05,
|
446 |
+
"loss": 2.808,
|
447 |
+
"step": 365
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.19,
|
451 |
+
"learning_rate": 4.983177170394248e-05,
|
452 |
+
"loss": 2.8491,
|
453 |
+
"step": 370
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.19,
|
457 |
+
"learning_rate": 4.9827174537087226e-05,
|
458 |
+
"loss": 2.7764,
|
459 |
+
"step": 375
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.19,
|
463 |
+
"learning_rate": 4.982251561862205e-05,
|
464 |
+
"loss": 2.7582,
|
465 |
+
"step": 380
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.19,
|
469 |
+
"learning_rate": 4.981779496013489e-05,
|
470 |
+
"loss": 2.5379,
|
471 |
+
"step": 385
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.2,
|
475 |
+
"learning_rate": 4.981301257336723e-05,
|
476 |
+
"loss": 2.9937,
|
477 |
+
"step": 390
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.2,
|
481 |
+
"learning_rate": 4.980816847021412e-05,
|
482 |
+
"loss": 2.8574,
|
483 |
+
"step": 395
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.2,
|
487 |
+
"learning_rate": 4.980326266272409e-05,
|
488 |
+
"loss": 2.9369,
|
489 |
+
"step": 400
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.2,
|
493 |
+
"learning_rate": 4.979829516309915e-05,
|
494 |
+
"loss": 2.836,
|
495 |
+
"step": 405
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.21,
|
499 |
+
"learning_rate": 4.979326598369477e-05,
|
500 |
+
"loss": 2.9369,
|
501 |
+
"step": 410
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.21,
|
505 |
+
"learning_rate": 4.9788175137019814e-05,
|
506 |
+
"loss": 2.6667,
|
507 |
+
"step": 415
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.21,
|
511 |
+
"learning_rate": 4.9783022635736534e-05,
|
512 |
+
"loss": 2.999,
|
513 |
+
"step": 420
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.21,
|
517 |
+
"learning_rate": 4.977780849266054e-05,
|
518 |
+
"loss": 2.907,
|
519 |
+
"step": 425
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.22,
|
523 |
+
"learning_rate": 4.9772532720760744e-05,
|
524 |
+
"loss": 2.8028,
|
525 |
+
"step": 430
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.22,
|
529 |
+
"learning_rate": 4.976719533315937e-05,
|
530 |
+
"loss": 2.7999,
|
531 |
+
"step": 435
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.22,
|
535 |
+
"learning_rate": 4.976179634313187e-05,
|
536 |
+
"loss": 2.8918,
|
537 |
+
"step": 440
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.22,
|
541 |
+
"learning_rate": 4.9756335764106944e-05,
|
542 |
+
"loss": 2.7926,
|
543 |
+
"step": 445
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.23,
|
547 |
+
"learning_rate": 4.975081360966646e-05,
|
548 |
+
"loss": 2.6709,
|
549 |
+
"step": 450
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.23,
|
553 |
+
"learning_rate": 4.9745229893545436e-05,
|
554 |
+
"loss": 2.8248,
|
555 |
+
"step": 455
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.23,
|
559 |
+
"learning_rate": 4.973958462963203e-05,
|
560 |
+
"loss": 3.1146,
|
561 |
+
"step": 460
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.23,
|
565 |
+
"learning_rate": 4.973387783196747e-05,
|
566 |
+
"loss": 2.9991,
|
567 |
+
"step": 465
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.24,
|
571 |
+
"learning_rate": 4.972810951474605e-05,
|
572 |
+
"loss": 2.7726,
|
573 |
+
"step": 470
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.24,
|
577 |
+
"learning_rate": 4.972227969231505e-05,
|
578 |
+
"loss": 2.9025,
|
579 |
+
"step": 475
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.24,
|
583 |
+
"learning_rate": 4.971638837917475e-05,
|
584 |
+
"loss": 2.6521,
|
585 |
+
"step": 480
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.24,
|
589 |
+
"learning_rate": 4.971043558997839e-05,
|
590 |
+
"loss": 2.9511,
|
591 |
+
"step": 485
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.25,
|
595 |
+
"learning_rate": 4.9704421339532075e-05,
|
596 |
+
"loss": 2.6938,
|
597 |
+
"step": 490
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.25,
|
601 |
+
"learning_rate": 4.969834564279482e-05,
|
602 |
+
"loss": 2.8533,
|
603 |
+
"step": 495
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.25,
|
607 |
+
"learning_rate": 4.9692208514878444e-05,
|
608 |
+
"loss": 2.6411,
|
609 |
+
"step": 500
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.25,
|
613 |
+
"learning_rate": 4.968600997104758e-05,
|
614 |
+
"loss": 2.6486,
|
615 |
+
"step": 505
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.26,
|
619 |
+
"learning_rate": 4.967975002671961e-05,
|
620 |
+
"loss": 2.8561,
|
621 |
+
"step": 510
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.26,
|
625 |
+
"learning_rate": 4.967342869746463e-05,
|
626 |
+
"loss": 2.6984,
|
627 |
+
"step": 515
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.26,
|
631 |
+
"learning_rate": 4.9667045999005424e-05,
|
632 |
+
"loss": 2.91,
|
633 |
+
"step": 520
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.26,
|
637 |
+
"learning_rate": 4.966060194721742e-05,
|
638 |
+
"loss": 2.7205,
|
639 |
+
"step": 525
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.27,
|
643 |
+
"learning_rate": 4.965409655812865e-05,
|
644 |
+
"loss": 2.7634,
|
645 |
+
"step": 530
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.27,
|
649 |
+
"learning_rate": 4.9647529847919684e-05,
|
650 |
+
"loss": 2.9647,
|
651 |
+
"step": 535
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.27,
|
655 |
+
"learning_rate": 4.964090183292364e-05,
|
656 |
+
"loss": 2.6357,
|
657 |
+
"step": 540
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.27,
|
661 |
+
"learning_rate": 4.963421252962609e-05,
|
662 |
+
"loss": 3.0285,
|
663 |
+
"step": 545
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.28,
|
667 |
+
"learning_rate": 4.96274619546651e-05,
|
668 |
+
"loss": 2.9895,
|
669 |
+
"step": 550
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.28,
|
673 |
+
"learning_rate": 4.962065012483106e-05,
|
674 |
+
"loss": 2.7286,
|
675 |
+
"step": 555
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.28,
|
679 |
+
"learning_rate": 4.961377705706677e-05,
|
680 |
+
"loss": 3.1337,
|
681 |
+
"step": 560
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.28,
|
685 |
+
"learning_rate": 4.960684276846733e-05,
|
686 |
+
"loss": 2.8268,
|
687 |
+
"step": 565
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.29,
|
691 |
+
"learning_rate": 4.959984727628011e-05,
|
692 |
+
"loss": 2.5851,
|
693 |
+
"step": 570
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.29,
|
697 |
+
"learning_rate": 4.959279059790471e-05,
|
698 |
+
"loss": 2.9359,
|
699 |
+
"step": 575
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.29,
|
703 |
+
"learning_rate": 4.958567275089291e-05,
|
704 |
+
"loss": 2.8842,
|
705 |
+
"step": 580
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.29,
|
709 |
+
"learning_rate": 4.957849375294864e-05,
|
710 |
+
"loss": 2.6186,
|
711 |
+
"step": 585
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.3,
|
715 |
+
"learning_rate": 4.957125362192794e-05,
|
716 |
+
"loss": 3.0116,
|
717 |
+
"step": 590
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.3,
|
721 |
+
"learning_rate": 4.956395237583887e-05,
|
722 |
+
"loss": 2.7045,
|
723 |
+
"step": 595
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.3,
|
727 |
+
"learning_rate": 4.9556590032841526e-05,
|
728 |
+
"loss": 2.8766,
|
729 |
+
"step": 600
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.3,
|
733 |
+
"learning_rate": 4.954916661124797e-05,
|
734 |
+
"loss": 2.7858,
|
735 |
+
"step": 605
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.31,
|
739 |
+
"learning_rate": 4.954168212952216e-05,
|
740 |
+
"loss": 2.7379,
|
741 |
+
"step": 610
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.31,
|
745 |
+
"learning_rate": 4.953413660627995e-05,
|
746 |
+
"loss": 2.475,
|
747 |
+
"step": 615
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.31,
|
751 |
+
"learning_rate": 4.9526530060289e-05,
|
752 |
+
"loss": 2.8357,
|
753 |
+
"step": 620
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.31,
|
757 |
+
"learning_rate": 4.951886251046876e-05,
|
758 |
+
"loss": 2.9284,
|
759 |
+
"step": 625
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.32,
|
763 |
+
"learning_rate": 4.951113397589042e-05,
|
764 |
+
"loss": 2.8144,
|
765 |
+
"step": 630
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.32,
|
769 |
+
"learning_rate": 4.9503344475776846e-05,
|
770 |
+
"loss": 2.6845,
|
771 |
+
"step": 635
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.32,
|
775 |
+
"learning_rate": 4.9495494029502535e-05,
|
776 |
+
"loss": 2.8937,
|
777 |
+
"step": 640
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.32,
|
781 |
+
"learning_rate": 4.9487582656593575e-05,
|
782 |
+
"loss": 3.0325,
|
783 |
+
"step": 645
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.33,
|
787 |
+
"learning_rate": 4.94796103767276e-05,
|
788 |
+
"loss": 2.7058,
|
789 |
+
"step": 650
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.33,
|
793 |
+
"learning_rate": 4.9471577209733746e-05,
|
794 |
+
"loss": 2.6162,
|
795 |
+
"step": 655
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.33,
|
799 |
+
"learning_rate": 4.946348317559257e-05,
|
800 |
+
"loss": 3.0129,
|
801 |
+
"step": 660
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.33,
|
805 |
+
"learning_rate": 4.945532829443603e-05,
|
806 |
+
"loss": 2.7587,
|
807 |
+
"step": 665
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.34,
|
811 |
+
"learning_rate": 4.944711258654742e-05,
|
812 |
+
"loss": 2.8915,
|
813 |
+
"step": 670
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.34,
|
817 |
+
"learning_rate": 4.943883607236135e-05,
|
818 |
+
"loss": 2.7343,
|
819 |
+
"step": 675
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.34,
|
823 |
+
"learning_rate": 4.943049877246364e-05,
|
824 |
+
"loss": 2.881,
|
825 |
+
"step": 680
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.34,
|
829 |
+
"learning_rate": 4.942210070759131e-05,
|
830 |
+
"loss": 2.488,
|
831 |
+
"step": 685
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.35,
|
835 |
+
"learning_rate": 4.941364189863253e-05,
|
836 |
+
"loss": 2.896,
|
837 |
+
"step": 690
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.35,
|
841 |
+
"learning_rate": 4.940512236662654e-05,
|
842 |
+
"loss": 2.7757,
|
843 |
+
"step": 695
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.35,
|
847 |
+
"learning_rate": 4.9396542132763634e-05,
|
848 |
+
"loss": 2.6271,
|
849 |
+
"step": 700
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.35,
|
853 |
+
"learning_rate": 4.938790121838506e-05,
|
854 |
+
"loss": 2.6804,
|
855 |
+
"step": 705
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.36,
|
859 |
+
"learning_rate": 4.937919964498302e-05,
|
860 |
+
"loss": 2.7313,
|
861 |
+
"step": 710
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.36,
|
865 |
+
"learning_rate": 4.937043743420058e-05,
|
866 |
+
"loss": 2.9277,
|
867 |
+
"step": 715
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.36,
|
871 |
+
"learning_rate": 4.9361614607831605e-05,
|
872 |
+
"loss": 2.6366,
|
873 |
+
"step": 720
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.36,
|
877 |
+
"learning_rate": 4.935273118782078e-05,
|
878 |
+
"loss": 3.0556,
|
879 |
+
"step": 725
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.37,
|
883 |
+
"learning_rate": 4.934378719626345e-05,
|
884 |
+
"loss": 3.0182,
|
885 |
+
"step": 730
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.37,
|
889 |
+
"learning_rate": 4.933478265540564e-05,
|
890 |
+
"loss": 2.824,
|
891 |
+
"step": 735
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.37,
|
895 |
+
"learning_rate": 4.932571758764398e-05,
|
896 |
+
"loss": 2.636,
|
897 |
+
"step": 740
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.37,
|
901 |
+
"learning_rate": 4.931659201552563e-05,
|
902 |
+
"loss": 2.7025,
|
903 |
+
"step": 745
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.38,
|
907 |
+
"learning_rate": 4.930740596174827e-05,
|
908 |
+
"loss": 2.8919,
|
909 |
+
"step": 750
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.38,
|
913 |
+
"learning_rate": 4.9298159449159965e-05,
|
914 |
+
"loss": 2.8434,
|
915 |
+
"step": 755
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.38,
|
919 |
+
"learning_rate": 4.928885250075921e-05,
|
920 |
+
"loss": 2.9448,
|
921 |
+
"step": 760
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.38,
|
925 |
+
"learning_rate": 4.927948513969478e-05,
|
926 |
+
"loss": 2.7312,
|
927 |
+
"step": 765
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.39,
|
931 |
+
"learning_rate": 4.927005738926573e-05,
|
932 |
+
"loss": 2.8688,
|
933 |
+
"step": 770
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.39,
|
937 |
+
"learning_rate": 4.926056927292132e-05,
|
938 |
+
"loss": 2.8639,
|
939 |
+
"step": 775
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.39,
|
943 |
+
"learning_rate": 4.925102081426095e-05,
|
944 |
+
"loss": 2.7809,
|
945 |
+
"step": 780
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.39,
|
949 |
+
"learning_rate": 4.9241412037034115e-05,
|
950 |
+
"loss": 3.0111,
|
951 |
+
"step": 785
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.4,
|
955 |
+
"learning_rate": 4.9231742965140314e-05,
|
956 |
+
"loss": 2.7252,
|
957 |
+
"step": 790
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.4,
|
961 |
+
"learning_rate": 4.922201362262905e-05,
|
962 |
+
"loss": 2.9717,
|
963 |
+
"step": 795
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.4,
|
967 |
+
"learning_rate": 4.92122240336997e-05,
|
968 |
+
"loss": 2.7191,
|
969 |
+
"step": 800
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.4,
|
973 |
+
"learning_rate": 4.920237422270153e-05,
|
974 |
+
"loss": 2.9346,
|
975 |
+
"step": 805
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.41,
|
979 |
+
"learning_rate": 4.9192464214133536e-05,
|
980 |
+
"loss": 2.7967,
|
981 |
+
"step": 810
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.41,
|
985 |
+
"learning_rate": 4.9182494032644496e-05,
|
986 |
+
"loss": 2.7326,
|
987 |
+
"step": 815
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.41,
|
991 |
+
"learning_rate": 4.917246370303284e-05,
|
992 |
+
"loss": 2.8933,
|
993 |
+
"step": 820
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.41,
|
997 |
+
"learning_rate": 4.9162373250246575e-05,
|
998 |
+
"loss": 2.7939,
|
999 |
+
"step": 825
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.42,
|
1003 |
+
"learning_rate": 4.9152222699383273e-05,
|
1004 |
+
"loss": 2.7807,
|
1005 |
+
"step": 830
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.42,
|
1009 |
+
"learning_rate": 4.9142012075689994e-05,
|
1010 |
+
"loss": 2.6996,
|
1011 |
+
"step": 835
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.42,
|
1015 |
+
"learning_rate": 4.913174140456319e-05,
|
1016 |
+
"loss": 2.7569,
|
1017 |
+
"step": 840
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.42,
|
1021 |
+
"learning_rate": 4.912141071154869e-05,
|
1022 |
+
"loss": 2.9347,
|
1023 |
+
"step": 845
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.43,
|
1027 |
+
"learning_rate": 4.911102002234159e-05,
|
1028 |
+
"loss": 2.7251,
|
1029 |
+
"step": 850
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.43,
|
1033 |
+
"learning_rate": 4.910056936278623e-05,
|
1034 |
+
"loss": 3.1228,
|
1035 |
+
"step": 855
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.43,
|
1039 |
+
"learning_rate": 4.90900587588761e-05,
|
1040 |
+
"loss": 2.9902,
|
1041 |
+
"step": 860
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.43,
|
1045 |
+
"learning_rate": 4.9079488236753803e-05,
|
1046 |
+
"loss": 2.5095,
|
1047 |
+
"step": 865
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.44,
|
1051 |
+
"learning_rate": 4.906885782271095e-05,
|
1052 |
+
"loss": 2.7523,
|
1053 |
+
"step": 870
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.44,
|
1057 |
+
"learning_rate": 4.905816754318814e-05,
|
1058 |
+
"loss": 2.6656,
|
1059 |
+
"step": 875
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.44,
|
1063 |
+
"learning_rate": 4.9047417424774874e-05,
|
1064 |
+
"loss": 2.8454,
|
1065 |
+
"step": 880
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.44,
|
1069 |
+
"learning_rate": 4.903660749420946e-05,
|
1070 |
+
"loss": 2.8194,
|
1071 |
+
"step": 885
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.45,
|
1075 |
+
"learning_rate": 4.9025737778379025e-05,
|
1076 |
+
"loss": 2.8421,
|
1077 |
+
"step": 890
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.45,
|
1081 |
+
"learning_rate": 4.9014808304319326e-05,
|
1082 |
+
"loss": 2.9656,
|
1083 |
+
"step": 895
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.45,
|
1087 |
+
"learning_rate": 4.900381909921482e-05,
|
1088 |
+
"loss": 2.7484,
|
1089 |
+
"step": 900
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.45,
|
1093 |
+
"learning_rate": 4.899277019039849e-05,
|
1094 |
+
"loss": 2.9044,
|
1095 |
+
"step": 905
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.46,
|
1099 |
+
"learning_rate": 4.898166160535186e-05,
|
1100 |
+
"loss": 2.8016,
|
1101 |
+
"step": 910
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.46,
|
1105 |
+
"learning_rate": 4.8970493371704826e-05,
|
1106 |
+
"loss": 2.6278,
|
1107 |
+
"step": 915
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.46,
|
1111 |
+
"learning_rate": 4.895926551723569e-05,
|
1112 |
+
"loss": 2.7214,
|
1113 |
+
"step": 920
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.46,
|
1117 |
+
"learning_rate": 4.8947978069871036e-05,
|
1118 |
+
"loss": 2.7679,
|
1119 |
+
"step": 925
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.47,
|
1123 |
+
"learning_rate": 4.8936631057685654e-05,
|
1124 |
+
"loss": 2.7196,
|
1125 |
+
"step": 930
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.47,
|
1129 |
+
"learning_rate": 4.8925224508902514e-05,
|
1130 |
+
"loss": 2.7866,
|
1131 |
+
"step": 935
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.47,
|
1135 |
+
"learning_rate": 4.8913758451892644e-05,
|
1136 |
+
"loss": 2.72,
|
1137 |
+
"step": 940
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.47,
|
1141 |
+
"learning_rate": 4.89022329151751e-05,
|
1142 |
+
"loss": 2.752,
|
1143 |
+
"step": 945
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.48,
|
1147 |
+
"learning_rate": 4.8890647927416887e-05,
|
1148 |
+
"loss": 3.0487,
|
1149 |
+
"step": 950
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.48,
|
1153 |
+
"learning_rate": 4.8879003517432857e-05,
|
1154 |
+
"loss": 2.8928,
|
1155 |
+
"step": 955
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.48,
|
1159 |
+
"learning_rate": 4.886729971418568e-05,
|
1160 |
+
"loss": 2.7793,
|
1161 |
+
"step": 960
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.48,
|
1165 |
+
"learning_rate": 4.8855536546785726e-05,
|
1166 |
+
"loss": 2.537,
|
1167 |
+
"step": 965
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.49,
|
1171 |
+
"learning_rate": 4.884371404449105e-05,
|
1172 |
+
"loss": 2.8345,
|
1173 |
+
"step": 970
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.49,
|
1177 |
+
"learning_rate": 4.8831832236707284e-05,
|
1178 |
+
"loss": 2.9673,
|
1179 |
+
"step": 975
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.49,
|
1183 |
+
"learning_rate": 4.8819891152987546e-05,
|
1184 |
+
"loss": 2.8295,
|
1185 |
+
"step": 980
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.49,
|
1189 |
+
"learning_rate": 4.880789082303241e-05,
|
1190 |
+
"loss": 3.0753,
|
1191 |
+
"step": 985
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.5,
|
1195 |
+
"learning_rate": 4.879583127668979e-05,
|
1196 |
+
"loss": 2.6748,
|
1197 |
+
"step": 990
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.5,
|
1201 |
+
"learning_rate": 4.878371254395492e-05,
|
1202 |
+
"loss": 2.8115,
|
1203 |
+
"step": 995
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.5,
|
1207 |
+
"learning_rate": 4.877153465497022e-05,
|
1208 |
+
"loss": 2.7039,
|
1209 |
+
"step": 1000
|
1210 |
+
}
|
1211 |
+
],
|
1212 |
+
"logging_steps": 5,
|
1213 |
+
"max_steps": 9960,
|
1214 |
+
"num_input_tokens_seen": 0,
|
1215 |
+
"num_train_epochs": 5,
|
1216 |
+
"save_steps": 500,
|
1217 |
+
"total_flos": 5.320804662283469e+16,
|
1218 |
+
"train_batch_size": 1,
|
1219 |
+
"trial_name": null,
|
1220 |
+
"trial_params": null
|
1221 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:939ee45e9035366dc4952c5158e7d3a0d3426acdbfb5014d53ad1e260b19a19f
|
3 |
+
size 4475
|
checkpoint-1500/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chatglm3-6b-base
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-1500/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chatglm3-6b-base",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"query_key_value"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM",
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
checkpoint-1500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84490235df6826161e1e701ff9a1c761a3a25670fd30944a4b41f5c5ec1504b0
|
3 |
+
size 7807744
|
checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6a722ed8329e8f09783e7b151a4b15eb1b7717e70e9a6487f0a9b6f72685224
|
3 |
+
size 15644485
|
checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4d4bea37dabe731e99dacf209629d05725ac46e96f42aecaad63dd5bf6d55f7
|
3 |
+
size 14575
|
checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c08c85a6d7b0767f91057e7c98cc42bdfa246f54b1e5570219edec6128d8b66
|
3 |
+
size 627
|
checkpoint-1500/special_tokens_map.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|user|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|observation|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
]
|
18 |
+
}
|
checkpoint-1500/tokenization_chatglm.py
ADDED
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import json
|
2 |
+
import os
|
3 |
+
import re
|
4 |
+
from typing import List, Optional, Union, Dict
|
5 |
+
from sentencepiece import SentencePieceProcessor
|
6 |
+
from transformers import PreTrainedTokenizer
|
7 |
+
from transformers.utils import logging, PaddingStrategy
|
8 |
+
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
|
9 |
+
|
10 |
+
|
11 |
+
class SPTokenizer:
|
12 |
+
def __init__(self, model_path: str):
|
13 |
+
# reload tokenizer
|
14 |
+
assert os.path.isfile(model_path), model_path
|
15 |
+
self.sp_model = SentencePieceProcessor(model_file=model_path)
|
16 |
+
|
17 |
+
# BOS / EOS token IDs
|
18 |
+
self.n_words: int = self.sp_model.vocab_size()
|
19 |
+
self.bos_id: int = self.sp_model.bos_id()
|
20 |
+
self.eos_id: int = self.sp_model.eos_id()
|
21 |
+
self.pad_id: int = self.sp_model.unk_id()
|
22 |
+
assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
|
23 |
+
|
24 |
+
role_special_tokens = ["<|system|>", "<|user|>", "<|assistant|>", "<|observation|>"]
|
25 |
+
special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"] + role_special_tokens
|
26 |
+
self.special_tokens = {}
|
27 |
+
self.index_special_tokens = {}
|
28 |
+
for token in special_tokens:
|
29 |
+
self.special_tokens[token] = self.n_words
|
30 |
+
self.index_special_tokens[self.n_words] = token
|
31 |
+
self.n_words += 1
|
32 |
+
self.role_special_token_expression = "|".join([re.escape(token) for token in role_special_tokens])
|
33 |
+
|
34 |
+
def tokenize(self, s: str, encode_special_tokens=False):
|
35 |
+
if encode_special_tokens:
|
36 |
+
last_index = 0
|
37 |
+
t = []
|
38 |
+
for match in re.finditer(self.role_special_token_expression, s):
|
39 |
+
if last_index < match.start():
|
40 |
+
t.extend(self.sp_model.EncodeAsPieces(s[last_index:match.start()]))
|
41 |
+
t.append(s[match.start():match.end()])
|
42 |
+
last_index = match.end()
|
43 |
+
if last_index < len(s):
|
44 |
+
t.extend(self.sp_model.EncodeAsPieces(s[last_index:]))
|
45 |
+
return t
|
46 |
+
else:
|
47 |
+
return self.sp_model.EncodeAsPieces(s)
|
48 |
+
|
49 |
+
def encode(self, s: str, bos: bool = False, eos: bool = False) -> List[int]:
|
50 |
+
assert type(s) is str
|
51 |
+
t = self.sp_model.encode(s)
|
52 |
+
if bos:
|
53 |
+
t = [self.bos_id] + t
|
54 |
+
if eos:
|
55 |
+
t = t + [self.eos_id]
|
56 |
+
return t
|
57 |
+
|
58 |
+
def decode(self, t: List[int]) -> str:
|
59 |
+
text, buffer = "", []
|
60 |
+
for token in t:
|
61 |
+
if token in self.index_special_tokens:
|
62 |
+
if buffer:
|
63 |
+
text += self.sp_model.decode(buffer)
|
64 |
+
buffer = []
|
65 |
+
text += self.index_special_tokens[token]
|
66 |
+
else:
|
67 |
+
buffer.append(token)
|
68 |
+
if buffer:
|
69 |
+
text += self.sp_model.decode(buffer)
|
70 |
+
return text
|
71 |
+
|
72 |
+
def decode_tokens(self, tokens: List[str]) -> str:
|
73 |
+
text = self.sp_model.DecodePieces(tokens)
|
74 |
+
return text
|
75 |
+
|
76 |
+
def convert_token_to_id(self, token):
|
77 |
+
""" Converts a token (str) in an id using the vocab. """
|
78 |
+
if token in self.special_tokens:
|
79 |
+
return self.special_tokens[token]
|
80 |
+
return self.sp_model.PieceToId(token)
|
81 |
+
|
82 |
+
def convert_id_to_token(self, index):
|
83 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
84 |
+
if index in self.index_special_tokens:
|
85 |
+
return self.index_special_tokens[index]
|
86 |
+
if index in [self.eos_id, self.bos_id, self.pad_id] or index < 0:
|
87 |
+
return ""
|
88 |
+
return self.sp_model.IdToPiece(index)
|
89 |
+
|
90 |
+
|
91 |
+
class ChatGLMTokenizer(PreTrainedTokenizer):
|
92 |
+
vocab_files_names = {"vocab_file": "tokenizer.model"}
|
93 |
+
|
94 |
+
model_input_names = ["input_ids", "attention_mask", "position_ids"]
|
95 |
+
|
96 |
+
def __init__(self, vocab_file, padding_side="left", clean_up_tokenization_spaces=False, encode_special_tokens=False,
|
97 |
+
**kwargs):
|
98 |
+
self.name = "GLMTokenizer"
|
99 |
+
|
100 |
+
self.vocab_file = vocab_file
|
101 |
+
self.tokenizer = SPTokenizer(vocab_file)
|
102 |
+
self.special_tokens = {
|
103 |
+
"<bos>": self.tokenizer.bos_id,
|
104 |
+
"<eos>": self.tokenizer.eos_id,
|
105 |
+
"<pad>": self.tokenizer.pad_id
|
106 |
+
}
|
107 |
+
self.encode_special_tokens = encode_special_tokens
|
108 |
+
super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
109 |
+
encode_special_tokens=encode_special_tokens,
|
110 |
+
**kwargs)
|
111 |
+
|
112 |
+
def get_command(self, token):
|
113 |
+
if token in self.special_tokens:
|
114 |
+
return self.special_tokens[token]
|
115 |
+
assert token in self.tokenizer.special_tokens, f"{token} is not a special token for {self.name}"
|
116 |
+
return self.tokenizer.special_tokens[token]
|
117 |
+
|
118 |
+
@property
|
119 |
+
def unk_token(self) -> str:
|
120 |
+
return "<unk>"
|
121 |
+
|
122 |
+
@property
|
123 |
+
def pad_token(self) -> str:
|
124 |
+
return "<unk>"
|
125 |
+
|
126 |
+
@property
|
127 |
+
def pad_token_id(self):
|
128 |
+
return self.get_command("<pad>")
|
129 |
+
|
130 |
+
@property
|
131 |
+
def eos_token(self) -> str:
|
132 |
+
return "</s>"
|
133 |
+
|
134 |
+
@property
|
135 |
+
def eos_token_id(self):
|
136 |
+
return self.get_command("<eos>")
|
137 |
+
|
138 |
+
@property
|
139 |
+
def vocab_size(self):
|
140 |
+
return self.tokenizer.n_words
|
141 |
+
|
142 |
+
def get_vocab(self):
|
143 |
+
""" Returns vocab as a dict """
|
144 |
+
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
145 |
+
vocab.update(self.added_tokens_encoder)
|
146 |
+
return vocab
|
147 |
+
|
148 |
+
def _tokenize(self, text, **kwargs):
|
149 |
+
return self.tokenizer.tokenize(text, encode_special_tokens=self.encode_special_tokens)
|
150 |
+
|
151 |
+
def _convert_token_to_id(self, token):
|
152 |
+
""" Converts a token (str) in an id using the vocab. """
|
153 |
+
return self.tokenizer.convert_token_to_id(token)
|
154 |
+
|
155 |
+
def _convert_id_to_token(self, index):
|
156 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
157 |
+
return self.tokenizer.convert_id_to_token(index)
|
158 |
+
|
159 |
+
def convert_tokens_to_string(self, tokens: List[str]) -> str:
|
160 |
+
return self.tokenizer.decode_tokens(tokens)
|
161 |
+
|
162 |
+
def save_vocabulary(self, save_directory, filename_prefix=None):
|
163 |
+
"""
|
164 |
+
Save the vocabulary and special tokens file to a directory.
|
165 |
+
|
166 |
+
Args:
|
167 |
+
save_directory (`str`):
|
168 |
+
The directory in which to save the vocabulary.
|
169 |
+
filename_prefix (`str`, *optional*):
|
170 |
+
An optional prefix to add to the named of the saved files.
|
171 |
+
|
172 |
+
Returns:
|
173 |
+
`Tuple(str)`: Paths to the files saved.
|
174 |
+
"""
|
175 |
+
if os.path.isdir(save_directory):
|
176 |
+
vocab_file = os.path.join(
|
177 |
+
save_directory, self.vocab_files_names["vocab_file"]
|
178 |
+
)
|
179 |
+
else:
|
180 |
+
vocab_file = save_directory
|
181 |
+
|
182 |
+
with open(self.vocab_file, 'rb') as fin:
|
183 |
+
proto_str = fin.read()
|
184 |
+
|
185 |
+
with open(vocab_file, "wb") as writer:
|
186 |
+
writer.write(proto_str)
|
187 |
+
|
188 |
+
return (vocab_file,)
|
189 |
+
|
190 |
+
def get_prefix_tokens(self):
|
191 |
+
prefix_tokens = [self.get_command("[gMASK]"), self.get_command("sop")]
|
192 |
+
return prefix_tokens
|
193 |
+
|
194 |
+
def build_single_message(self, role, metadata, message):
|
195 |
+
assert role in ["system", "user", "assistant", "observation"], role
|
196 |
+
role_tokens = [self.get_command(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n")
|
197 |
+
message_tokens = self.tokenizer.encode(message)
|
198 |
+
tokens = role_tokens + message_tokens
|
199 |
+
return tokens
|
200 |
+
|
201 |
+
def build_chat_input(self, query, history=None, role="user"):
|
202 |
+
if history is None:
|
203 |
+
history = []
|
204 |
+
input_ids = []
|
205 |
+
for item in history:
|
206 |
+
content = item["content"]
|
207 |
+
if item["role"] == "system" and "tools" in item:
|
208 |
+
content = content + "\n" + json.dumps(item["tools"], indent=4, ensure_ascii=False)
|
209 |
+
input_ids.extend(self.build_single_message(item["role"], item.get("metadata", ""), content))
|
210 |
+
input_ids.extend(self.build_single_message(role, "", query))
|
211 |
+
input_ids.extend([self.get_command("<|assistant|>")])
|
212 |
+
return self.batch_encode_plus([input_ids], return_tensors="pt", is_split_into_words=True)
|
213 |
+
|
214 |
+
def build_inputs_with_special_tokens(
|
215 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
216 |
+
) -> List[int]:
|
217 |
+
"""
|
218 |
+
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
|
219 |
+
adding special tokens. A BERT sequence has the following format:
|
220 |
+
|
221 |
+
- single sequence: `[CLS] X [SEP]`
|
222 |
+
- pair of sequences: `[CLS] A [SEP] B [SEP]`
|
223 |
+
|
224 |
+
Args:
|
225 |
+
token_ids_0 (`List[int]`):
|
226 |
+
List of IDs to which the special tokens will be added.
|
227 |
+
token_ids_1 (`List[int]`, *optional*):
|
228 |
+
Optional second list of IDs for sequence pairs.
|
229 |
+
|
230 |
+
Returns:
|
231 |
+
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
|
232 |
+
"""
|
233 |
+
prefix_tokens = self.get_prefix_tokens()
|
234 |
+
token_ids_0 = prefix_tokens + token_ids_0
|
235 |
+
if token_ids_1 is not None:
|
236 |
+
token_ids_0 = token_ids_0 + token_ids_1 + [self.get_command("<eos>")]
|
237 |
+
return token_ids_0
|
238 |
+
|
239 |
+
def _pad(
|
240 |
+
self,
|
241 |
+
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
|
242 |
+
max_length: Optional[int] = None,
|
243 |
+
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
244 |
+
pad_to_multiple_of: Optional[int] = None,
|
245 |
+
return_attention_mask: Optional[bool] = None,
|
246 |
+
) -> dict:
|
247 |
+
"""
|
248 |
+
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
|
249 |
+
|
250 |
+
Args:
|
251 |
+
encoded_inputs:
|
252 |
+
Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
|
253 |
+
max_length: maximum length of the returned list and optionally padding length (see below).
|
254 |
+
Will truncate by taking into account the special tokens.
|
255 |
+
padding_strategy: PaddingStrategy to use for padding.
|
256 |
+
|
257 |
+
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
|
258 |
+
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
|
259 |
+
- PaddingStrategy.DO_NOT_PAD: Do not pad
|
260 |
+
The tokenizer padding sides are defined in self.padding_side:
|
261 |
+
|
262 |
+
- 'left': pads on the left of the sequences
|
263 |
+
- 'right': pads on the right of the sequences
|
264 |
+
pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
|
265 |
+
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
|
266 |
+
`>= 7.5` (Volta).
|
267 |
+
return_attention_mask:
|
268 |
+
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
|
269 |
+
"""
|
270 |
+
# Load from model defaults
|
271 |
+
assert self.padding_side == "left"
|
272 |
+
|
273 |
+
required_input = encoded_inputs[self.model_input_names[0]]
|
274 |
+
seq_length = len(required_input)
|
275 |
+
|
276 |
+
if padding_strategy == PaddingStrategy.LONGEST:
|
277 |
+
max_length = len(required_input)
|
278 |
+
|
279 |
+
if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
|
280 |
+
max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
|
281 |
+
|
282 |
+
needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
|
283 |
+
|
284 |
+
# Initialize attention mask if not present.
|
285 |
+
if "attention_mask" not in encoded_inputs:
|
286 |
+
encoded_inputs["attention_mask"] = [1] * seq_length
|
287 |
+
|
288 |
+
if "position_ids" not in encoded_inputs:
|
289 |
+
encoded_inputs["position_ids"] = list(range(seq_length))
|
290 |
+
|
291 |
+
if needs_to_be_padded:
|
292 |
+
difference = max_length - len(required_input)
|
293 |
+
|
294 |
+
if "attention_mask" in encoded_inputs:
|
295 |
+
encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
|
296 |
+
if "position_ids" in encoded_inputs:
|
297 |
+
encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
|
298 |
+
encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
|
299 |
+
|
300 |
+
return encoded_inputs
|
checkpoint-1500/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
checkpoint-1500/tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"64795": {
|
4 |
+
"content": "<|user|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"64797": {
|
12 |
+
"content": "<|observation|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
}
|
19 |
+
},
|
20 |
+
"additional_special_tokens": [
|
21 |
+
"<|user|>",
|
22 |
+
"<|observation|>"
|
23 |
+
],
|
24 |
+
"auto_map": {
|
25 |
+
"AutoTokenizer": [
|
26 |
+
"tokenization_chatglm.ChatGLMTokenizer",
|
27 |
+
null
|
28 |
+
]
|
29 |
+
},
|
30 |
+
"clean_up_tokenization_spaces": false,
|
31 |
+
"do_lower_case": false,
|
32 |
+
"encode_special_tokens": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"remove_space": false,
|
38 |
+
"split_special_tokens": false,
|
39 |
+
"tokenizer_class": "ChatGLMTokenizer",
|
40 |
+
"unk_token": "<unk>"
|
41 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,1821 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7527286413248024,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.9999980101927616e-05,
|
14 |
+
"loss": 3.2533,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4.99999204077421e-05,
|
20 |
+
"loss": 3.2279,
|
21 |
+
"step": 10
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 4.999978982687695e-05,
|
26 |
+
"loss": 3.193,
|
27 |
+
"step": 15
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 4.9999597065062966e-05,
|
32 |
+
"loss": 3.2863,
|
33 |
+
"step": 20
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 4.999934212277958e-05,
|
38 |
+
"loss": 3.1724,
|
39 |
+
"step": 25
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 4.999902500066093e-05,
|
44 |
+
"loss": 3.1088,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 4.999864569949576e-05,
|
50 |
+
"loss": 3.3241,
|
51 |
+
"step": 35
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 4.99982042202275e-05,
|
56 |
+
"loss": 3.1904,
|
57 |
+
"step": 40
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 4.999770056395421e-05,
|
62 |
+
"loss": 2.9254,
|
63 |
+
"step": 45
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 4.999713473192863e-05,
|
68 |
+
"loss": 3.1845,
|
69 |
+
"step": 50
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 4.999650672555812e-05,
|
74 |
+
"loss": 2.8475,
|
75 |
+
"step": 55
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 4.9995816546404695e-05,
|
80 |
+
"loss": 3.0486,
|
81 |
+
"step": 60
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 4.9995064196185014e-05,
|
86 |
+
"loss": 2.6464,
|
87 |
+
"step": 65
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 4.9994249676770364e-05,
|
92 |
+
"loss": 3.0446,
|
93 |
+
"step": 70
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 4.999337299018667e-05,
|
98 |
+
"loss": 3.375,
|
99 |
+
"step": 75
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 4.999243413861447e-05,
|
104 |
+
"loss": 2.8787,
|
105 |
+
"step": 80
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 4.999143312438893e-05,
|
110 |
+
"loss": 3.014,
|
111 |
+
"step": 85
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.05,
|
115 |
+
"learning_rate": 4.999036994999985e-05,
|
116 |
+
"loss": 2.8288,
|
117 |
+
"step": 90
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 4.9989244618091596e-05,
|
122 |
+
"loss": 3.1879,
|
123 |
+
"step": 95
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 4.998805713146317e-05,
|
128 |
+
"loss": 2.9749,
|
129 |
+
"step": 100
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 4.9986807493068165e-05,
|
134 |
+
"loss": 2.6304,
|
135 |
+
"step": 105
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06,
|
139 |
+
"learning_rate": 4.998549570601475e-05,
|
140 |
+
"loss": 2.943,
|
141 |
+
"step": 110
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 4.998412177356568e-05,
|
146 |
+
"loss": 2.7595,
|
147 |
+
"step": 115
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 4.9982685699138275e-05,
|
152 |
+
"loss": 2.7377,
|
153 |
+
"step": 120
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 4.9981187486304423e-05,
|
158 |
+
"loss": 2.9878,
|
159 |
+
"step": 125
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07,
|
163 |
+
"learning_rate": 4.997962713879058e-05,
|
164 |
+
"loss": 2.7882,
|
165 |
+
"step": 130
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.07,
|
169 |
+
"learning_rate": 4.997800466047772e-05,
|
170 |
+
"loss": 2.7802,
|
171 |
+
"step": 135
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 4.997632005540138e-05,
|
176 |
+
"loss": 3.0129,
|
177 |
+
"step": 140
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 4.997457332775159e-05,
|
182 |
+
"loss": 2.9444,
|
183 |
+
"step": 145
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.08,
|
187 |
+
"learning_rate": 4.997276448187294e-05,
|
188 |
+
"loss": 2.9664,
|
189 |
+
"step": 150
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.08,
|
193 |
+
"learning_rate": 4.9970893522264476e-05,
|
194 |
+
"loss": 2.7367,
|
195 |
+
"step": 155
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 4.996896045357977e-05,
|
200 |
+
"loss": 2.7012,
|
201 |
+
"step": 160
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 4.9966965280626856e-05,
|
206 |
+
"loss": 2.8493,
|
207 |
+
"step": 165
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.09,
|
211 |
+
"learning_rate": 4.996490800836825e-05,
|
212 |
+
"loss": 2.9274,
|
213 |
+
"step": 170
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09,
|
217 |
+
"learning_rate": 4.996278864192092e-05,
|
218 |
+
"loss": 2.8093,
|
219 |
+
"step": 175
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 4.9960607186556286e-05,
|
224 |
+
"loss": 3.1782,
|
225 |
+
"step": 180
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 4.995836364770018e-05,
|
230 |
+
"loss": 2.7507,
|
231 |
+
"step": 185
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.1,
|
235 |
+
"learning_rate": 4.995605803093287e-05,
|
236 |
+
"loss": 2.6724,
|
237 |
+
"step": 190
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.1,
|
241 |
+
"learning_rate": 4.9953690341989026e-05,
|
242 |
+
"loss": 3.0258,
|
243 |
+
"step": 195
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 4.9951260586757694e-05,
|
248 |
+
"loss": 3.1134,
|
249 |
+
"step": 200
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1,
|
253 |
+
"learning_rate": 4.9948768771282314e-05,
|
254 |
+
"loss": 2.9937,
|
255 |
+
"step": 205
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11,
|
259 |
+
"learning_rate": 4.9946214901760665e-05,
|
260 |
+
"loss": 2.7394,
|
261 |
+
"step": 210
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.11,
|
265 |
+
"learning_rate": 4.99435989845449e-05,
|
266 |
+
"loss": 2.9696,
|
267 |
+
"step": 215
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 4.994092102614146e-05,
|
272 |
+
"loss": 2.753,
|
273 |
+
"step": 220
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.11,
|
277 |
+
"learning_rate": 4.993818103321113e-05,
|
278 |
+
"loss": 3.0759,
|
279 |
+
"step": 225
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.12,
|
283 |
+
"learning_rate": 4.9935379012568985e-05,
|
284 |
+
"loss": 2.7512,
|
285 |
+
"step": 230
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.12,
|
289 |
+
"learning_rate": 4.993251497118438e-05,
|
290 |
+
"loss": 2.8656,
|
291 |
+
"step": 235
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 4.992958891618091e-05,
|
296 |
+
"loss": 2.6628,
|
297 |
+
"step": 240
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.12,
|
301 |
+
"learning_rate": 4.992660085483645e-05,
|
302 |
+
"loss": 2.8012,
|
303 |
+
"step": 245
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.13,
|
307 |
+
"learning_rate": 4.992355079458307e-05,
|
308 |
+
"loss": 2.8141,
|
309 |
+
"step": 250
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.13,
|
313 |
+
"learning_rate": 4.992043874300706e-05,
|
314 |
+
"loss": 2.9083,
|
315 |
+
"step": 255
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.13,
|
319 |
+
"learning_rate": 4.991726470784891e-05,
|
320 |
+
"loss": 2.5846,
|
321 |
+
"step": 260
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.13,
|
325 |
+
"learning_rate": 4.991402869700325e-05,
|
326 |
+
"loss": 2.8088,
|
327 |
+
"step": 265
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.14,
|
331 |
+
"learning_rate": 4.991073071851889e-05,
|
332 |
+
"loss": 2.9979,
|
333 |
+
"step": 270
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.14,
|
337 |
+
"learning_rate": 4.990737078059875e-05,
|
338 |
+
"loss": 3.0171,
|
339 |
+
"step": 275
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.14,
|
343 |
+
"learning_rate": 4.990394889159986e-05,
|
344 |
+
"loss": 2.9278,
|
345 |
+
"step": 280
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.14,
|
349 |
+
"learning_rate": 4.9900465060033364e-05,
|
350 |
+
"loss": 2.7998,
|
351 |
+
"step": 285
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.15,
|
355 |
+
"learning_rate": 4.989691929456443e-05,
|
356 |
+
"loss": 2.721,
|
357 |
+
"step": 290
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.15,
|
361 |
+
"learning_rate": 4.9893311604012306e-05,
|
362 |
+
"loss": 3.0291,
|
363 |
+
"step": 295
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.15,
|
367 |
+
"learning_rate": 4.988964199735024e-05,
|
368 |
+
"loss": 2.9777,
|
369 |
+
"step": 300
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.15,
|
373 |
+
"learning_rate": 4.988591048370552e-05,
|
374 |
+
"loss": 2.318,
|
375 |
+
"step": 305
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.16,
|
379 |
+
"learning_rate": 4.988211707235936e-05,
|
380 |
+
"loss": 3.0332,
|
381 |
+
"step": 310
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.16,
|
385 |
+
"learning_rate": 4.987826177274697e-05,
|
386 |
+
"loss": 2.4888,
|
387 |
+
"step": 315
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.16,
|
391 |
+
"learning_rate": 4.987434459445748e-05,
|
392 |
+
"loss": 2.9259,
|
393 |
+
"step": 320
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.16,
|
397 |
+
"learning_rate": 4.987036554723391e-05,
|
398 |
+
"loss": 2.9568,
|
399 |
+
"step": 325
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.17,
|
403 |
+
"learning_rate": 4.98663246409732e-05,
|
404 |
+
"loss": 2.8708,
|
405 |
+
"step": 330
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.17,
|
409 |
+
"learning_rate": 4.986222188572611e-05,
|
410 |
+
"loss": 2.7848,
|
411 |
+
"step": 335
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.17,
|
415 |
+
"learning_rate": 4.985805729169728e-05,
|
416 |
+
"loss": 2.6178,
|
417 |
+
"step": 340
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.17,
|
421 |
+
"learning_rate": 4.985383086924511e-05,
|
422 |
+
"loss": 2.8326,
|
423 |
+
"step": 345
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.18,
|
427 |
+
"learning_rate": 4.984954262888182e-05,
|
428 |
+
"loss": 2.8845,
|
429 |
+
"step": 350
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.18,
|
433 |
+
"learning_rate": 4.9845192581273365e-05,
|
434 |
+
"loss": 2.6151,
|
435 |
+
"step": 355
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.18,
|
439 |
+
"learning_rate": 4.984078073723944e-05,
|
440 |
+
"loss": 2.8474,
|
441 |
+
"step": 360
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.18,
|
445 |
+
"learning_rate": 4.9836307107753455e-05,
|
446 |
+
"loss": 2.808,
|
447 |
+
"step": 365
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.19,
|
451 |
+
"learning_rate": 4.983177170394248e-05,
|
452 |
+
"loss": 2.8491,
|
453 |
+
"step": 370
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.19,
|
457 |
+
"learning_rate": 4.9827174537087226e-05,
|
458 |
+
"loss": 2.7764,
|
459 |
+
"step": 375
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.19,
|
463 |
+
"learning_rate": 4.982251561862205e-05,
|
464 |
+
"loss": 2.7582,
|
465 |
+
"step": 380
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.19,
|
469 |
+
"learning_rate": 4.981779496013489e-05,
|
470 |
+
"loss": 2.5379,
|
471 |
+
"step": 385
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.2,
|
475 |
+
"learning_rate": 4.981301257336723e-05,
|
476 |
+
"loss": 2.9937,
|
477 |
+
"step": 390
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.2,
|
481 |
+
"learning_rate": 4.980816847021412e-05,
|
482 |
+
"loss": 2.8574,
|
483 |
+
"step": 395
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.2,
|
487 |
+
"learning_rate": 4.980326266272409e-05,
|
488 |
+
"loss": 2.9369,
|
489 |
+
"step": 400
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.2,
|
493 |
+
"learning_rate": 4.979829516309915e-05,
|
494 |
+
"loss": 2.836,
|
495 |
+
"step": 405
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.21,
|
499 |
+
"learning_rate": 4.979326598369477e-05,
|
500 |
+
"loss": 2.9369,
|
501 |
+
"step": 410
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.21,
|
505 |
+
"learning_rate": 4.9788175137019814e-05,
|
506 |
+
"loss": 2.6667,
|
507 |
+
"step": 415
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.21,
|
511 |
+
"learning_rate": 4.9783022635736534e-05,
|
512 |
+
"loss": 2.999,
|
513 |
+
"step": 420
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.21,
|
517 |
+
"learning_rate": 4.977780849266054e-05,
|
518 |
+
"loss": 2.907,
|
519 |
+
"step": 425
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.22,
|
523 |
+
"learning_rate": 4.9772532720760744e-05,
|
524 |
+
"loss": 2.8028,
|
525 |
+
"step": 430
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.22,
|
529 |
+
"learning_rate": 4.976719533315937e-05,
|
530 |
+
"loss": 2.7999,
|
531 |
+
"step": 435
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.22,
|
535 |
+
"learning_rate": 4.976179634313187e-05,
|
536 |
+
"loss": 2.8918,
|
537 |
+
"step": 440
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.22,
|
541 |
+
"learning_rate": 4.9756335764106944e-05,
|
542 |
+
"loss": 2.7926,
|
543 |
+
"step": 445
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.23,
|
547 |
+
"learning_rate": 4.975081360966646e-05,
|
548 |
+
"loss": 2.6709,
|
549 |
+
"step": 450
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.23,
|
553 |
+
"learning_rate": 4.9745229893545436e-05,
|
554 |
+
"loss": 2.8248,
|
555 |
+
"step": 455
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.23,
|
559 |
+
"learning_rate": 4.973958462963203e-05,
|
560 |
+
"loss": 3.1146,
|
561 |
+
"step": 460
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.23,
|
565 |
+
"learning_rate": 4.973387783196747e-05,
|
566 |
+
"loss": 2.9991,
|
567 |
+
"step": 465
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.24,
|
571 |
+
"learning_rate": 4.972810951474605e-05,
|
572 |
+
"loss": 2.7726,
|
573 |
+
"step": 470
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.24,
|
577 |
+
"learning_rate": 4.972227969231505e-05,
|
578 |
+
"loss": 2.9025,
|
579 |
+
"step": 475
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.24,
|
583 |
+
"learning_rate": 4.971638837917475e-05,
|
584 |
+
"loss": 2.6521,
|
585 |
+
"step": 480
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.24,
|
589 |
+
"learning_rate": 4.971043558997839e-05,
|
590 |
+
"loss": 2.9511,
|
591 |
+
"step": 485
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.25,
|
595 |
+
"learning_rate": 4.9704421339532075e-05,
|
596 |
+
"loss": 2.6938,
|
597 |
+
"step": 490
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.25,
|
601 |
+
"learning_rate": 4.969834564279482e-05,
|
602 |
+
"loss": 2.8533,
|
603 |
+
"step": 495
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.25,
|
607 |
+
"learning_rate": 4.9692208514878444e-05,
|
608 |
+
"loss": 2.6411,
|
609 |
+
"step": 500
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.25,
|
613 |
+
"learning_rate": 4.968600997104758e-05,
|
614 |
+
"loss": 2.6486,
|
615 |
+
"step": 505
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.26,
|
619 |
+
"learning_rate": 4.967975002671961e-05,
|
620 |
+
"loss": 2.8561,
|
621 |
+
"step": 510
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.26,
|
625 |
+
"learning_rate": 4.967342869746463e-05,
|
626 |
+
"loss": 2.6984,
|
627 |
+
"step": 515
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.26,
|
631 |
+
"learning_rate": 4.9667045999005424e-05,
|
632 |
+
"loss": 2.91,
|
633 |
+
"step": 520
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.26,
|
637 |
+
"learning_rate": 4.966060194721742e-05,
|
638 |
+
"loss": 2.7205,
|
639 |
+
"step": 525
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.27,
|
643 |
+
"learning_rate": 4.965409655812865e-05,
|
644 |
+
"loss": 2.7634,
|
645 |
+
"step": 530
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.27,
|
649 |
+
"learning_rate": 4.9647529847919684e-05,
|
650 |
+
"loss": 2.9647,
|
651 |
+
"step": 535
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.27,
|
655 |
+
"learning_rate": 4.964090183292364e-05,
|
656 |
+
"loss": 2.6357,
|
657 |
+
"step": 540
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.27,
|
661 |
+
"learning_rate": 4.963421252962609e-05,
|
662 |
+
"loss": 3.0285,
|
663 |
+
"step": 545
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.28,
|
667 |
+
"learning_rate": 4.96274619546651e-05,
|
668 |
+
"loss": 2.9895,
|
669 |
+
"step": 550
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.28,
|
673 |
+
"learning_rate": 4.962065012483106e-05,
|
674 |
+
"loss": 2.7286,
|
675 |
+
"step": 555
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.28,
|
679 |
+
"learning_rate": 4.961377705706677e-05,
|
680 |
+
"loss": 3.1337,
|
681 |
+
"step": 560
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.28,
|
685 |
+
"learning_rate": 4.960684276846733e-05,
|
686 |
+
"loss": 2.8268,
|
687 |
+
"step": 565
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.29,
|
691 |
+
"learning_rate": 4.959984727628011e-05,
|
692 |
+
"loss": 2.5851,
|
693 |
+
"step": 570
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.29,
|
697 |
+
"learning_rate": 4.959279059790471e-05,
|
698 |
+
"loss": 2.9359,
|
699 |
+
"step": 575
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.29,
|
703 |
+
"learning_rate": 4.958567275089291e-05,
|
704 |
+
"loss": 2.8842,
|
705 |
+
"step": 580
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.29,
|
709 |
+
"learning_rate": 4.957849375294864e-05,
|
710 |
+
"loss": 2.6186,
|
711 |
+
"step": 585
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.3,
|
715 |
+
"learning_rate": 4.957125362192794e-05,
|
716 |
+
"loss": 3.0116,
|
717 |
+
"step": 590
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.3,
|
721 |
+
"learning_rate": 4.956395237583887e-05,
|
722 |
+
"loss": 2.7045,
|
723 |
+
"step": 595
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.3,
|
727 |
+
"learning_rate": 4.9556590032841526e-05,
|
728 |
+
"loss": 2.8766,
|
729 |
+
"step": 600
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.3,
|
733 |
+
"learning_rate": 4.954916661124797e-05,
|
734 |
+
"loss": 2.7858,
|
735 |
+
"step": 605
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.31,
|
739 |
+
"learning_rate": 4.954168212952216e-05,
|
740 |
+
"loss": 2.7379,
|
741 |
+
"step": 610
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.31,
|
745 |
+
"learning_rate": 4.953413660627995e-05,
|
746 |
+
"loss": 2.475,
|
747 |
+
"step": 615
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.31,
|
751 |
+
"learning_rate": 4.9526530060289e-05,
|
752 |
+
"loss": 2.8357,
|
753 |
+
"step": 620
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.31,
|
757 |
+
"learning_rate": 4.951886251046876e-05,
|
758 |
+
"loss": 2.9284,
|
759 |
+
"step": 625
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.32,
|
763 |
+
"learning_rate": 4.951113397589042e-05,
|
764 |
+
"loss": 2.8144,
|
765 |
+
"step": 630
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.32,
|
769 |
+
"learning_rate": 4.9503344475776846e-05,
|
770 |
+
"loss": 2.6845,
|
771 |
+
"step": 635
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.32,
|
775 |
+
"learning_rate": 4.9495494029502535e-05,
|
776 |
+
"loss": 2.8937,
|
777 |
+
"step": 640
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.32,
|
781 |
+
"learning_rate": 4.9487582656593575e-05,
|
782 |
+
"loss": 3.0325,
|
783 |
+
"step": 645
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.33,
|
787 |
+
"learning_rate": 4.94796103767276e-05,
|
788 |
+
"loss": 2.7058,
|
789 |
+
"step": 650
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.33,
|
793 |
+
"learning_rate": 4.9471577209733746e-05,
|
794 |
+
"loss": 2.6162,
|
795 |
+
"step": 655
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.33,
|
799 |
+
"learning_rate": 4.946348317559257e-05,
|
800 |
+
"loss": 3.0129,
|
801 |
+
"step": 660
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.33,
|
805 |
+
"learning_rate": 4.945532829443603e-05,
|
806 |
+
"loss": 2.7587,
|
807 |
+
"step": 665
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.34,
|
811 |
+
"learning_rate": 4.944711258654742e-05,
|
812 |
+
"loss": 2.8915,
|
813 |
+
"step": 670
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.34,
|
817 |
+
"learning_rate": 4.943883607236135e-05,
|
818 |
+
"loss": 2.7343,
|
819 |
+
"step": 675
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.34,
|
823 |
+
"learning_rate": 4.943049877246364e-05,
|
824 |
+
"loss": 2.881,
|
825 |
+
"step": 680
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.34,
|
829 |
+
"learning_rate": 4.942210070759131e-05,
|
830 |
+
"loss": 2.488,
|
831 |
+
"step": 685
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.35,
|
835 |
+
"learning_rate": 4.941364189863253e-05,
|
836 |
+
"loss": 2.896,
|
837 |
+
"step": 690
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.35,
|
841 |
+
"learning_rate": 4.940512236662654e-05,
|
842 |
+
"loss": 2.7757,
|
843 |
+
"step": 695
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.35,
|
847 |
+
"learning_rate": 4.9396542132763634e-05,
|
848 |
+
"loss": 2.6271,
|
849 |
+
"step": 700
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.35,
|
853 |
+
"learning_rate": 4.938790121838506e-05,
|
854 |
+
"loss": 2.6804,
|
855 |
+
"step": 705
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.36,
|
859 |
+
"learning_rate": 4.937919964498302e-05,
|
860 |
+
"loss": 2.7313,
|
861 |
+
"step": 710
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.36,
|
865 |
+
"learning_rate": 4.937043743420058e-05,
|
866 |
+
"loss": 2.9277,
|
867 |
+
"step": 715
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.36,
|
871 |
+
"learning_rate": 4.9361614607831605e-05,
|
872 |
+
"loss": 2.6366,
|
873 |
+
"step": 720
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.36,
|
877 |
+
"learning_rate": 4.935273118782078e-05,
|
878 |
+
"loss": 3.0556,
|
879 |
+
"step": 725
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.37,
|
883 |
+
"learning_rate": 4.934378719626345e-05,
|
884 |
+
"loss": 3.0182,
|
885 |
+
"step": 730
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.37,
|
889 |
+
"learning_rate": 4.933478265540564e-05,
|
890 |
+
"loss": 2.824,
|
891 |
+
"step": 735
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.37,
|
895 |
+
"learning_rate": 4.932571758764398e-05,
|
896 |
+
"loss": 2.636,
|
897 |
+
"step": 740
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.37,
|
901 |
+
"learning_rate": 4.931659201552563e-05,
|
902 |
+
"loss": 2.7025,
|
903 |
+
"step": 745
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.38,
|
907 |
+
"learning_rate": 4.930740596174827e-05,
|
908 |
+
"loss": 2.8919,
|
909 |
+
"step": 750
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.38,
|
913 |
+
"learning_rate": 4.9298159449159965e-05,
|
914 |
+
"loss": 2.8434,
|
915 |
+
"step": 755
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.38,
|
919 |
+
"learning_rate": 4.928885250075921e-05,
|
920 |
+
"loss": 2.9448,
|
921 |
+
"step": 760
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.38,
|
925 |
+
"learning_rate": 4.927948513969478e-05,
|
926 |
+
"loss": 2.7312,
|
927 |
+
"step": 765
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.39,
|
931 |
+
"learning_rate": 4.927005738926573e-05,
|
932 |
+
"loss": 2.8688,
|
933 |
+
"step": 770
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.39,
|
937 |
+
"learning_rate": 4.926056927292132e-05,
|
938 |
+
"loss": 2.8639,
|
939 |
+
"step": 775
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.39,
|
943 |
+
"learning_rate": 4.925102081426095e-05,
|
944 |
+
"loss": 2.7809,
|
945 |
+
"step": 780
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.39,
|
949 |
+
"learning_rate": 4.9241412037034115e-05,
|
950 |
+
"loss": 3.0111,
|
951 |
+
"step": 785
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.4,
|
955 |
+
"learning_rate": 4.9231742965140314e-05,
|
956 |
+
"loss": 2.7252,
|
957 |
+
"step": 790
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.4,
|
961 |
+
"learning_rate": 4.922201362262905e-05,
|
962 |
+
"loss": 2.9717,
|
963 |
+
"step": 795
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.4,
|
967 |
+
"learning_rate": 4.92122240336997e-05,
|
968 |
+
"loss": 2.7191,
|
969 |
+
"step": 800
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.4,
|
973 |
+
"learning_rate": 4.920237422270153e-05,
|
974 |
+
"loss": 2.9346,
|
975 |
+
"step": 805
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.41,
|
979 |
+
"learning_rate": 4.9192464214133536e-05,
|
980 |
+
"loss": 2.7967,
|
981 |
+
"step": 810
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.41,
|
985 |
+
"learning_rate": 4.9182494032644496e-05,
|
986 |
+
"loss": 2.7326,
|
987 |
+
"step": 815
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.41,
|
991 |
+
"learning_rate": 4.917246370303284e-05,
|
992 |
+
"loss": 2.8933,
|
993 |
+
"step": 820
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.41,
|
997 |
+
"learning_rate": 4.9162373250246575e-05,
|
998 |
+
"loss": 2.7939,
|
999 |
+
"step": 825
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.42,
|
1003 |
+
"learning_rate": 4.9152222699383273e-05,
|
1004 |
+
"loss": 2.7807,
|
1005 |
+
"step": 830
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.42,
|
1009 |
+
"learning_rate": 4.9142012075689994e-05,
|
1010 |
+
"loss": 2.6996,
|
1011 |
+
"step": 835
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.42,
|
1015 |
+
"learning_rate": 4.913174140456319e-05,
|
1016 |
+
"loss": 2.7569,
|
1017 |
+
"step": 840
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.42,
|
1021 |
+
"learning_rate": 4.912141071154869e-05,
|
1022 |
+
"loss": 2.9347,
|
1023 |
+
"step": 845
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.43,
|
1027 |
+
"learning_rate": 4.911102002234159e-05,
|
1028 |
+
"loss": 2.7251,
|
1029 |
+
"step": 850
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.43,
|
1033 |
+
"learning_rate": 4.910056936278623e-05,
|
1034 |
+
"loss": 3.1228,
|
1035 |
+
"step": 855
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.43,
|
1039 |
+
"learning_rate": 4.90900587588761e-05,
|
1040 |
+
"loss": 2.9902,
|
1041 |
+
"step": 860
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.43,
|
1045 |
+
"learning_rate": 4.9079488236753803e-05,
|
1046 |
+
"loss": 2.5095,
|
1047 |
+
"step": 865
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.44,
|
1051 |
+
"learning_rate": 4.906885782271095e-05,
|
1052 |
+
"loss": 2.7523,
|
1053 |
+
"step": 870
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.44,
|
1057 |
+
"learning_rate": 4.905816754318814e-05,
|
1058 |
+
"loss": 2.6656,
|
1059 |
+
"step": 875
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.44,
|
1063 |
+
"learning_rate": 4.9047417424774874e-05,
|
1064 |
+
"loss": 2.8454,
|
1065 |
+
"step": 880
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.44,
|
1069 |
+
"learning_rate": 4.903660749420946e-05,
|
1070 |
+
"loss": 2.8194,
|
1071 |
+
"step": 885
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.45,
|
1075 |
+
"learning_rate": 4.9025737778379025e-05,
|
1076 |
+
"loss": 2.8421,
|
1077 |
+
"step": 890
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.45,
|
1081 |
+
"learning_rate": 4.9014808304319326e-05,
|
1082 |
+
"loss": 2.9656,
|
1083 |
+
"step": 895
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.45,
|
1087 |
+
"learning_rate": 4.900381909921482e-05,
|
1088 |
+
"loss": 2.7484,
|
1089 |
+
"step": 900
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.45,
|
1093 |
+
"learning_rate": 4.899277019039849e-05,
|
1094 |
+
"loss": 2.9044,
|
1095 |
+
"step": 905
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.46,
|
1099 |
+
"learning_rate": 4.898166160535186e-05,
|
1100 |
+
"loss": 2.8016,
|
1101 |
+
"step": 910
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.46,
|
1105 |
+
"learning_rate": 4.8970493371704826e-05,
|
1106 |
+
"loss": 2.6278,
|
1107 |
+
"step": 915
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.46,
|
1111 |
+
"learning_rate": 4.895926551723569e-05,
|
1112 |
+
"loss": 2.7214,
|
1113 |
+
"step": 920
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.46,
|
1117 |
+
"learning_rate": 4.8947978069871036e-05,
|
1118 |
+
"loss": 2.7679,
|
1119 |
+
"step": 925
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.47,
|
1123 |
+
"learning_rate": 4.8936631057685654e-05,
|
1124 |
+
"loss": 2.7196,
|
1125 |
+
"step": 930
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.47,
|
1129 |
+
"learning_rate": 4.8925224508902514e-05,
|
1130 |
+
"loss": 2.7866,
|
1131 |
+
"step": 935
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.47,
|
1135 |
+
"learning_rate": 4.8913758451892644e-05,
|
1136 |
+
"loss": 2.72,
|
1137 |
+
"step": 940
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.47,
|
1141 |
+
"learning_rate": 4.89022329151751e-05,
|
1142 |
+
"loss": 2.752,
|
1143 |
+
"step": 945
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.48,
|
1147 |
+
"learning_rate": 4.8890647927416887e-05,
|
1148 |
+
"loss": 3.0487,
|
1149 |
+
"step": 950
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.48,
|
1153 |
+
"learning_rate": 4.8879003517432857e-05,
|
1154 |
+
"loss": 2.8928,
|
1155 |
+
"step": 955
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.48,
|
1159 |
+
"learning_rate": 4.886729971418568e-05,
|
1160 |
+
"loss": 2.7793,
|
1161 |
+
"step": 960
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.48,
|
1165 |
+
"learning_rate": 4.8855536546785726e-05,
|
1166 |
+
"loss": 2.537,
|
1167 |
+
"step": 965
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.49,
|
1171 |
+
"learning_rate": 4.884371404449105e-05,
|
1172 |
+
"loss": 2.8345,
|
1173 |
+
"step": 970
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.49,
|
1177 |
+
"learning_rate": 4.8831832236707284e-05,
|
1178 |
+
"loss": 2.9673,
|
1179 |
+
"step": 975
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.49,
|
1183 |
+
"learning_rate": 4.8819891152987546e-05,
|
1184 |
+
"loss": 2.8295,
|
1185 |
+
"step": 980
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.49,
|
1189 |
+
"learning_rate": 4.880789082303241e-05,
|
1190 |
+
"loss": 3.0753,
|
1191 |
+
"step": 985
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.5,
|
1195 |
+
"learning_rate": 4.879583127668979e-05,
|
1196 |
+
"loss": 2.6748,
|
1197 |
+
"step": 990
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.5,
|
1201 |
+
"learning_rate": 4.878371254395492e-05,
|
1202 |
+
"loss": 2.8115,
|
1203 |
+
"step": 995
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.5,
|
1207 |
+
"learning_rate": 4.877153465497022e-05,
|
1208 |
+
"loss": 2.7039,
|
1209 |
+
"step": 1000
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.5,
|
1213 |
+
"learning_rate": 4.8759297640025235e-05,
|
1214 |
+
"loss": 2.9469,
|
1215 |
+
"step": 1005
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.51,
|
1219 |
+
"learning_rate": 4.874700152955661e-05,
|
1220 |
+
"loss": 2.9745,
|
1221 |
+
"step": 1010
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.51,
|
1225 |
+
"learning_rate": 4.8734646354147936e-05,
|
1226 |
+
"loss": 2.9341,
|
1227 |
+
"step": 1015
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.51,
|
1231 |
+
"learning_rate": 4.8722232144529754e-05,
|
1232 |
+
"loss": 3.0511,
|
1233 |
+
"step": 1020
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.51,
|
1237 |
+
"learning_rate": 4.870975893157941e-05,
|
1238 |
+
"loss": 2.5396,
|
1239 |
+
"step": 1025
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.52,
|
1243 |
+
"learning_rate": 4.8697226746321004e-05,
|
1244 |
+
"loss": 2.6699,
|
1245 |
+
"step": 1030
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 0.52,
|
1249 |
+
"learning_rate": 4.868463561992532e-05,
|
1250 |
+
"loss": 2.4887,
|
1251 |
+
"step": 1035
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 0.52,
|
1255 |
+
"learning_rate": 4.867198558370977e-05,
|
1256 |
+
"loss": 2.4773,
|
1257 |
+
"step": 1040
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.52,
|
1261 |
+
"learning_rate": 4.865927666913825e-05,
|
1262 |
+
"loss": 2.7612,
|
1263 |
+
"step": 1045
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.53,
|
1267 |
+
"learning_rate": 4.864650890782113e-05,
|
1268 |
+
"loss": 2.9116,
|
1269 |
+
"step": 1050
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.53,
|
1273 |
+
"learning_rate": 4.863368233151514e-05,
|
1274 |
+
"loss": 2.8205,
|
1275 |
+
"step": 1055
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 0.53,
|
1279 |
+
"learning_rate": 4.862079697212329e-05,
|
1280 |
+
"loss": 2.6711,
|
1281 |
+
"step": 1060
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 0.53,
|
1285 |
+
"learning_rate": 4.8607852861694804e-05,
|
1286 |
+
"loss": 3.1138,
|
1287 |
+
"step": 1065
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 0.54,
|
1291 |
+
"learning_rate": 4.859485003242503e-05,
|
1292 |
+
"loss": 2.5603,
|
1293 |
+
"step": 1070
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 0.54,
|
1297 |
+
"learning_rate": 4.858178851665539e-05,
|
1298 |
+
"loss": 2.7981,
|
1299 |
+
"step": 1075
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.54,
|
1303 |
+
"learning_rate": 4.856866834687323e-05,
|
1304 |
+
"loss": 2.507,
|
1305 |
+
"step": 1080
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.54,
|
1309 |
+
"learning_rate": 4.855548955571183e-05,
|
1310 |
+
"loss": 3.0315,
|
1311 |
+
"step": 1085
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.55,
|
1315 |
+
"learning_rate": 4.8542252175950244e-05,
|
1316 |
+
"loss": 2.75,
|
1317 |
+
"step": 1090
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 0.55,
|
1321 |
+
"learning_rate": 4.852895624051326e-05,
|
1322 |
+
"loss": 2.6794,
|
1323 |
+
"step": 1095
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 0.55,
|
1327 |
+
"learning_rate": 4.851560178247132e-05,
|
1328 |
+
"loss": 2.8278,
|
1329 |
+
"step": 1100
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.55,
|
1333 |
+
"learning_rate": 4.850218883504041e-05,
|
1334 |
+
"loss": 2.6993,
|
1335 |
+
"step": 1105
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 0.56,
|
1339 |
+
"learning_rate": 4.8488717431582005e-05,
|
1340 |
+
"loss": 2.875,
|
1341 |
+
"step": 1110
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.56,
|
1345 |
+
"learning_rate": 4.8475187605602974e-05,
|
1346 |
+
"loss": 2.6057,
|
1347 |
+
"step": 1115
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.56,
|
1351 |
+
"learning_rate": 4.84615993907555e-05,
|
1352 |
+
"loss": 2.847,
|
1353 |
+
"step": 1120
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.56,
|
1357 |
+
"learning_rate": 4.844795282083697e-05,
|
1358 |
+
"loss": 2.7652,
|
1359 |
+
"step": 1125
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.57,
|
1363 |
+
"learning_rate": 4.843424792978997e-05,
|
1364 |
+
"loss": 2.8128,
|
1365 |
+
"step": 1130
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 0.57,
|
1369 |
+
"learning_rate": 4.842048475170209e-05,
|
1370 |
+
"loss": 2.7077,
|
1371 |
+
"step": 1135
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.57,
|
1375 |
+
"learning_rate": 4.840666332080592e-05,
|
1376 |
+
"loss": 2.7081,
|
1377 |
+
"step": 1140
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 0.57,
|
1381 |
+
"learning_rate": 4.8392783671478934e-05,
|
1382 |
+
"loss": 2.6479,
|
1383 |
+
"step": 1145
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.58,
|
1387 |
+
"learning_rate": 4.837884583824342e-05,
|
1388 |
+
"loss": 2.667,
|
1389 |
+
"step": 1150
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.58,
|
1393 |
+
"learning_rate": 4.836484985576638e-05,
|
1394 |
+
"loss": 2.7514,
|
1395 |
+
"step": 1155
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.58,
|
1399 |
+
"learning_rate": 4.835079575885944e-05,
|
1400 |
+
"loss": 2.5058,
|
1401 |
+
"step": 1160
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 0.58,
|
1405 |
+
"learning_rate": 4.833668358247876e-05,
|
1406 |
+
"loss": 2.6183,
|
1407 |
+
"step": 1165
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 0.59,
|
1411 |
+
"learning_rate": 4.8322513361725006e-05,
|
1412 |
+
"loss": 2.9959,
|
1413 |
+
"step": 1170
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.59,
|
1417 |
+
"learning_rate": 4.830828513184317e-05,
|
1418 |
+
"loss": 2.5714,
|
1419 |
+
"step": 1175
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.59,
|
1423 |
+
"learning_rate": 4.8293998928222536e-05,
|
1424 |
+
"loss": 2.965,
|
1425 |
+
"step": 1180
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.59,
|
1429 |
+
"learning_rate": 4.827965478639661e-05,
|
1430 |
+
"loss": 2.2106,
|
1431 |
+
"step": 1185
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.6,
|
1435 |
+
"learning_rate": 4.8265252742042965e-05,
|
1436 |
+
"loss": 2.7456,
|
1437 |
+
"step": 1190
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.6,
|
1441 |
+
"learning_rate": 4.8250792830983225e-05,
|
1442 |
+
"loss": 2.5694,
|
1443 |
+
"step": 1195
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 0.6,
|
1447 |
+
"learning_rate": 4.8236275089182936e-05,
|
1448 |
+
"loss": 2.6826,
|
1449 |
+
"step": 1200
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.6,
|
1453 |
+
"learning_rate": 4.8221699552751465e-05,
|
1454 |
+
"loss": 2.878,
|
1455 |
+
"step": 1205
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 0.61,
|
1459 |
+
"learning_rate": 4.820706625794196e-05,
|
1460 |
+
"loss": 2.8191,
|
1461 |
+
"step": 1210
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 0.61,
|
1465 |
+
"learning_rate": 4.81923752411512e-05,
|
1466 |
+
"loss": 2.739,
|
1467 |
+
"step": 1215
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.61,
|
1471 |
+
"learning_rate": 4.8177626538919565e-05,
|
1472 |
+
"loss": 3.0544,
|
1473 |
+
"step": 1220
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.61,
|
1477 |
+
"learning_rate": 4.8162820187930875e-05,
|
1478 |
+
"loss": 2.8393,
|
1479 |
+
"step": 1225
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.62,
|
1483 |
+
"learning_rate": 4.814795622501237e-05,
|
1484 |
+
"loss": 2.4457,
|
1485 |
+
"step": 1230
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 0.62,
|
1489 |
+
"learning_rate": 4.813303468713456e-05,
|
1490 |
+
"loss": 2.8575,
|
1491 |
+
"step": 1235
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 0.62,
|
1495 |
+
"learning_rate": 4.8118055611411197e-05,
|
1496 |
+
"loss": 2.8307,
|
1497 |
+
"step": 1240
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 0.62,
|
1501 |
+
"learning_rate": 4.810301903509909e-05,
|
1502 |
+
"loss": 2.7951,
|
1503 |
+
"step": 1245
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 0.63,
|
1507 |
+
"learning_rate": 4.8087924995598125e-05,
|
1508 |
+
"loss": 2.8456,
|
1509 |
+
"step": 1250
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.63,
|
1513 |
+
"learning_rate": 4.807277353045106e-05,
|
1514 |
+
"loss": 2.3564,
|
1515 |
+
"step": 1255
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.63,
|
1519 |
+
"learning_rate": 4.8057564677343524e-05,
|
1520 |
+
"loss": 2.5076,
|
1521 |
+
"step": 1260
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.63,
|
1525 |
+
"learning_rate": 4.8042298474103884e-05,
|
1526 |
+
"loss": 2.605,
|
1527 |
+
"step": 1265
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 0.64,
|
1531 |
+
"learning_rate": 4.8026974958703116e-05,
|
1532 |
+
"loss": 2.4782,
|
1533 |
+
"step": 1270
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 0.64,
|
1537 |
+
"learning_rate": 4.8011594169254784e-05,
|
1538 |
+
"loss": 2.7193,
|
1539 |
+
"step": 1275
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.64,
|
1543 |
+
"learning_rate": 4.799615614401488e-05,
|
1544 |
+
"loss": 2.8284,
|
1545 |
+
"step": 1280
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 0.64,
|
1549 |
+
"learning_rate": 4.798066092138178e-05,
|
1550 |
+
"loss": 2.5378,
|
1551 |
+
"step": 1285
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.65,
|
1555 |
+
"learning_rate": 4.796510853989612e-05,
|
1556 |
+
"loss": 2.7396,
|
1557 |
+
"step": 1290
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.65,
|
1561 |
+
"learning_rate": 4.794949903824069e-05,
|
1562 |
+
"loss": 2.7948,
|
1563 |
+
"step": 1295
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.65,
|
1567 |
+
"learning_rate": 4.793383245524035e-05,
|
1568 |
+
"loss": 2.7818,
|
1569 |
+
"step": 1300
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.65,
|
1573 |
+
"learning_rate": 4.791810882986197e-05,
|
1574 |
+
"loss": 2.7334,
|
1575 |
+
"step": 1305
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 0.66,
|
1579 |
+
"learning_rate": 4.7902328201214256e-05,
|
1580 |
+
"loss": 2.4824,
|
1581 |
+
"step": 1310
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 0.66,
|
1585 |
+
"learning_rate": 4.7886490608547727e-05,
|
1586 |
+
"loss": 2.6131,
|
1587 |
+
"step": 1315
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 0.66,
|
1591 |
+
"learning_rate": 4.7870596091254584e-05,
|
1592 |
+
"loss": 2.7778,
|
1593 |
+
"step": 1320
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.66,
|
1597 |
+
"learning_rate": 4.7854644688868594e-05,
|
1598 |
+
"loss": 2.5263,
|
1599 |
+
"step": 1325
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.67,
|
1603 |
+
"learning_rate": 4.783863644106502e-05,
|
1604 |
+
"loss": 2.7825,
|
1605 |
+
"step": 1330
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.67,
|
1609 |
+
"learning_rate": 4.782257138766053e-05,
|
1610 |
+
"loss": 2.7902,
|
1611 |
+
"step": 1335
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 0.67,
|
1615 |
+
"learning_rate": 4.7806449568613066e-05,
|
1616 |
+
"loss": 2.8333,
|
1617 |
+
"step": 1340
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 0.67,
|
1621 |
+
"learning_rate": 4.779027102402177e-05,
|
1622 |
+
"loss": 2.856,
|
1623 |
+
"step": 1345
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 0.68,
|
1627 |
+
"learning_rate": 4.777403579412686e-05,
|
1628 |
+
"loss": 2.8021,
|
1629 |
+
"step": 1350
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.68,
|
1633 |
+
"learning_rate": 4.775774391930956e-05,
|
1634 |
+
"loss": 2.6639,
|
1635 |
+
"step": 1355
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.68,
|
1639 |
+
"learning_rate": 4.7741395440091976e-05,
|
1640 |
+
"loss": 2.5226,
|
1641 |
+
"step": 1360
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.68,
|
1645 |
+
"learning_rate": 4.772499039713702e-05,
|
1646 |
+
"loss": 2.6803,
|
1647 |
+
"step": 1365
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.69,
|
1651 |
+
"learning_rate": 4.7708528831248274e-05,
|
1652 |
+
"loss": 2.4608,
|
1653 |
+
"step": 1370
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 0.69,
|
1657 |
+
"learning_rate": 4.769201078336991e-05,
|
1658 |
+
"loss": 2.786,
|
1659 |
+
"step": 1375
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.69,
|
1663 |
+
"learning_rate": 4.7675436294586586e-05,
|
1664 |
+
"loss": 2.8294,
|
1665 |
+
"step": 1380
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.7,
|
1669 |
+
"learning_rate": 4.7658805406123356e-05,
|
1670 |
+
"loss": 2.6776,
|
1671 |
+
"step": 1385
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 0.7,
|
1675 |
+
"learning_rate": 4.7642118159345544e-05,
|
1676 |
+
"loss": 2.8003,
|
1677 |
+
"step": 1390
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.7,
|
1681 |
+
"learning_rate": 4.762537459575865e-05,
|
1682 |
+
"loss": 2.7796,
|
1683 |
+
"step": 1395
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.7,
|
1687 |
+
"learning_rate": 4.7608574757008245e-05,
|
1688 |
+
"loss": 2.9156,
|
1689 |
+
"step": 1400
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.71,
|
1693 |
+
"learning_rate": 4.7591718684879883e-05,
|
1694 |
+
"loss": 3.0521,
|
1695 |
+
"step": 1405
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 0.71,
|
1699 |
+
"learning_rate": 4.7574806421298976e-05,
|
1700 |
+
"loss": 2.6469,
|
1701 |
+
"step": 1410
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 0.71,
|
1705 |
+
"learning_rate": 4.755783800833071e-05,
|
1706 |
+
"loss": 2.8512,
|
1707 |
+
"step": 1415
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.71,
|
1711 |
+
"learning_rate": 4.754081348817991e-05,
|
1712 |
+
"loss": 2.66,
|
1713 |
+
"step": 1420
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 0.72,
|
1717 |
+
"learning_rate": 4.752373290319096e-05,
|
1718 |
+
"loss": 2.6625,
|
1719 |
+
"step": 1425
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.72,
|
1723 |
+
"learning_rate": 4.7506596295847716e-05,
|
1724 |
+
"loss": 2.6711,
|
1725 |
+
"step": 1430
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.72,
|
1729 |
+
"learning_rate": 4.7489403708773346e-05,
|
1730 |
+
"loss": 2.8951,
|
1731 |
+
"step": 1435
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.72,
|
1735 |
+
"learning_rate": 4.747215518473026e-05,
|
1736 |
+
"loss": 2.7375,
|
1737 |
+
"step": 1440
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 0.73,
|
1741 |
+
"learning_rate": 4.745485076662e-05,
|
1742 |
+
"loss": 2.8037,
|
1743 |
+
"step": 1445
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 0.73,
|
1747 |
+
"learning_rate": 4.743749049748315e-05,
|
1748 |
+
"loss": 2.5375,
|
1749 |
+
"step": 1450
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.73,
|
1753 |
+
"learning_rate": 4.742007442049918e-05,
|
1754 |
+
"loss": 2.7664,
|
1755 |
+
"step": 1455
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 0.73,
|
1759 |
+
"learning_rate": 4.7402602578986374e-05,
|
1760 |
+
"loss": 2.9644,
|
1761 |
+
"step": 1460
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.74,
|
1765 |
+
"learning_rate": 4.738507501640175e-05,
|
1766 |
+
"loss": 2.8212,
|
1767 |
+
"step": 1465
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.74,
|
1771 |
+
"learning_rate": 4.736749177634087e-05,
|
1772 |
+
"loss": 2.7201,
|
1773 |
+
"step": 1470
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.74,
|
1777 |
+
"learning_rate": 4.734985290253782e-05,
|
1778 |
+
"loss": 2.7087,
|
1779 |
+
"step": 1475
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.74,
|
1783 |
+
"learning_rate": 4.7332158438865035e-05,
|
1784 |
+
"loss": 2.5502,
|
1785 |
+
"step": 1480
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 0.75,
|
1789 |
+
"learning_rate": 4.731440842933322e-05,
|
1790 |
+
"loss": 2.7607,
|
1791 |
+
"step": 1485
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.75,
|
1795 |
+
"learning_rate": 4.729660291809126e-05,
|
1796 |
+
"loss": 2.5601,
|
1797 |
+
"step": 1490
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 0.75,
|
1801 |
+
"learning_rate": 4.727874194942606e-05,
|
1802 |
+
"loss": 2.5562,
|
1803 |
+
"step": 1495
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.75,
|
1807 |
+
"learning_rate": 4.7260825567762486e-05,
|
1808 |
+
"loss": 2.5539,
|
1809 |
+
"step": 1500
|
1810 |
+
}
|
1811 |
+
],
|
1812 |
+
"logging_steps": 5,
|
1813 |
+
"max_steps": 9960,
|
1814 |
+
"num_input_tokens_seen": 0,
|
1815 |
+
"num_train_epochs": 5,
|
1816 |
+
"save_steps": 500,
|
1817 |
+
"total_flos": 7.938917340256666e+16,
|
1818 |
+
"train_batch_size": 1,
|
1819 |
+
"trial_name": null,
|
1820 |
+
"trial_params": null
|
1821 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:939ee45e9035366dc4952c5158e7d3a0d3426acdbfb5014d53ad1e260b19a19f
|
3 |
+
size 4475
|
checkpoint-2000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chatglm3-6b-base
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-2000/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chatglm3-6b-base",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"query_key_value"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM",
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
checkpoint-2000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c587894dfb0d6a36b1b2b2bd92c9853c7e8efe4659095de4b7806907caa047f
|
3 |
+
size 7807744
|
checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8fdc41063e12d72eb10d41d8c4ee533b99fd680d9681612b843ce985e48672e
|
3 |
+
size 15644485
|
checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44baa97c777d40935f5d263141ec5c7c84944e0c2da4b888420b7db30896fc13
|
3 |
+
size 14575
|
checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a9fc87da7bbd820e1299c4cd3906d309a71ffb7d550c30c19efae928b59c8ee
|
3 |
+
size 627
|
checkpoint-2000/special_tokens_map.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|user|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|observation|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
]
|
18 |
+
}
|
checkpoint-2000/tokenization_chatglm.py
ADDED
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import json
|
2 |
+
import os
|
3 |
+
import re
|
4 |
+
from typing import List, Optional, Union, Dict
|
5 |
+
from sentencepiece import SentencePieceProcessor
|
6 |
+
from transformers import PreTrainedTokenizer
|
7 |
+
from transformers.utils import logging, PaddingStrategy
|
8 |
+
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
|
9 |
+
|
10 |
+
|
11 |
+
class SPTokenizer:
|
12 |
+
def __init__(self, model_path: str):
|
13 |
+
# reload tokenizer
|
14 |
+
assert os.path.isfile(model_path), model_path
|
15 |
+
self.sp_model = SentencePieceProcessor(model_file=model_path)
|
16 |
+
|
17 |
+
# BOS / EOS token IDs
|
18 |
+
self.n_words: int = self.sp_model.vocab_size()
|
19 |
+
self.bos_id: int = self.sp_model.bos_id()
|
20 |
+
self.eos_id: int = self.sp_model.eos_id()
|
21 |
+
self.pad_id: int = self.sp_model.unk_id()
|
22 |
+
assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
|
23 |
+
|
24 |
+
role_special_tokens = ["<|system|>", "<|user|>", "<|assistant|>", "<|observation|>"]
|
25 |
+
special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"] + role_special_tokens
|
26 |
+
self.special_tokens = {}
|
27 |
+
self.index_special_tokens = {}
|
28 |
+
for token in special_tokens:
|
29 |
+
self.special_tokens[token] = self.n_words
|
30 |
+
self.index_special_tokens[self.n_words] = token
|
31 |
+
self.n_words += 1
|
32 |
+
self.role_special_token_expression = "|".join([re.escape(token) for token in role_special_tokens])
|
33 |
+
|
34 |
+
def tokenize(self, s: str, encode_special_tokens=False):
|
35 |
+
if encode_special_tokens:
|
36 |
+
last_index = 0
|
37 |
+
t = []
|
38 |
+
for match in re.finditer(self.role_special_token_expression, s):
|
39 |
+
if last_index < match.start():
|
40 |
+
t.extend(self.sp_model.EncodeAsPieces(s[last_index:match.start()]))
|
41 |
+
t.append(s[match.start():match.end()])
|
42 |
+
last_index = match.end()
|
43 |
+
if last_index < len(s):
|
44 |
+
t.extend(self.sp_model.EncodeAsPieces(s[last_index:]))
|
45 |
+
return t
|
46 |
+
else:
|
47 |
+
return self.sp_model.EncodeAsPieces(s)
|
48 |
+
|
49 |
+
def encode(self, s: str, bos: bool = False, eos: bool = False) -> List[int]:
|
50 |
+
assert type(s) is str
|
51 |
+
t = self.sp_model.encode(s)
|
52 |
+
if bos:
|
53 |
+
t = [self.bos_id] + t
|
54 |
+
if eos:
|
55 |
+
t = t + [self.eos_id]
|
56 |
+
return t
|
57 |
+
|
58 |
+
def decode(self, t: List[int]) -> str:
|
59 |
+
text, buffer = "", []
|
60 |
+
for token in t:
|
61 |
+
if token in self.index_special_tokens:
|
62 |
+
if buffer:
|
63 |
+
text += self.sp_model.decode(buffer)
|
64 |
+
buffer = []
|
65 |
+
text += self.index_special_tokens[token]
|
66 |
+
else:
|
67 |
+
buffer.append(token)
|
68 |
+
if buffer:
|
69 |
+
text += self.sp_model.decode(buffer)
|
70 |
+
return text
|
71 |
+
|
72 |
+
def decode_tokens(self, tokens: List[str]) -> str:
|
73 |
+
text = self.sp_model.DecodePieces(tokens)
|
74 |
+
return text
|
75 |
+
|
76 |
+
def convert_token_to_id(self, token):
|
77 |
+
""" Converts a token (str) in an id using the vocab. """
|
78 |
+
if token in self.special_tokens:
|
79 |
+
return self.special_tokens[token]
|
80 |
+
return self.sp_model.PieceToId(token)
|
81 |
+
|
82 |
+
def convert_id_to_token(self, index):
|
83 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
84 |
+
if index in self.index_special_tokens:
|
85 |
+
return self.index_special_tokens[index]
|
86 |
+
if index in [self.eos_id, self.bos_id, self.pad_id] or index < 0:
|
87 |
+
return ""
|
88 |
+
return self.sp_model.IdToPiece(index)
|
89 |
+
|
90 |
+
|
91 |
+
class ChatGLMTokenizer(PreTrainedTokenizer):
|
92 |
+
vocab_files_names = {"vocab_file": "tokenizer.model"}
|
93 |
+
|
94 |
+
model_input_names = ["input_ids", "attention_mask", "position_ids"]
|
95 |
+
|
96 |
+
def __init__(self, vocab_file, padding_side="left", clean_up_tokenization_spaces=False, encode_special_tokens=False,
|
97 |
+
**kwargs):
|
98 |
+
self.name = "GLMTokenizer"
|
99 |
+
|
100 |
+
self.vocab_file = vocab_file
|
101 |
+
self.tokenizer = SPTokenizer(vocab_file)
|
102 |
+
self.special_tokens = {
|
103 |
+
"<bos>": self.tokenizer.bos_id,
|
104 |
+
"<eos>": self.tokenizer.eos_id,
|
105 |
+
"<pad>": self.tokenizer.pad_id
|
106 |
+
}
|
107 |
+
self.encode_special_tokens = encode_special_tokens
|
108 |
+
super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
109 |
+
encode_special_tokens=encode_special_tokens,
|
110 |
+
**kwargs)
|
111 |
+
|
112 |
+
def get_command(self, token):
|
113 |
+
if token in self.special_tokens:
|
114 |
+
return self.special_tokens[token]
|
115 |
+
assert token in self.tokenizer.special_tokens, f"{token} is not a special token for {self.name}"
|
116 |
+
return self.tokenizer.special_tokens[token]
|
117 |
+
|
118 |
+
@property
|
119 |
+
def unk_token(self) -> str:
|
120 |
+
return "<unk>"
|
121 |
+
|
122 |
+
@property
|
123 |
+
def pad_token(self) -> str:
|
124 |
+
return "<unk>"
|
125 |
+
|
126 |
+
@property
|
127 |
+
def pad_token_id(self):
|
128 |
+
return self.get_command("<pad>")
|
129 |
+
|
130 |
+
@property
|
131 |
+
def eos_token(self) -> str:
|
132 |
+
return "</s>"
|
133 |
+
|
134 |
+
@property
|
135 |
+
def eos_token_id(self):
|
136 |
+
return self.get_command("<eos>")
|
137 |
+
|
138 |
+
@property
|
139 |
+
def vocab_size(self):
|
140 |
+
return self.tokenizer.n_words
|
141 |
+
|
142 |
+
def get_vocab(self):
|
143 |
+
""" Returns vocab as a dict """
|
144 |
+
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
145 |
+
vocab.update(self.added_tokens_encoder)
|
146 |
+
return vocab
|
147 |
+
|
148 |
+
def _tokenize(self, text, **kwargs):
|
149 |
+
return self.tokenizer.tokenize(text, encode_special_tokens=self.encode_special_tokens)
|
150 |
+
|
151 |
+
def _convert_token_to_id(self, token):
|
152 |
+
""" Converts a token (str) in an id using the vocab. """
|
153 |
+
return self.tokenizer.convert_token_to_id(token)
|
154 |
+
|
155 |
+
def _convert_id_to_token(self, index):
|
156 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
157 |
+
return self.tokenizer.convert_id_to_token(index)
|
158 |
+
|
159 |
+
def convert_tokens_to_string(self, tokens: List[str]) -> str:
|
160 |
+
return self.tokenizer.decode_tokens(tokens)
|
161 |
+
|
162 |
+
def save_vocabulary(self, save_directory, filename_prefix=None):
|
163 |
+
"""
|
164 |
+
Save the vocabulary and special tokens file to a directory.
|
165 |
+
|
166 |
+
Args:
|
167 |
+
save_directory (`str`):
|
168 |
+
The directory in which to save the vocabulary.
|
169 |
+
filename_prefix (`str`, *optional*):
|
170 |
+
An optional prefix to add to the named of the saved files.
|
171 |
+
|
172 |
+
Returns:
|
173 |
+
`Tuple(str)`: Paths to the files saved.
|
174 |
+
"""
|
175 |
+
if os.path.isdir(save_directory):
|
176 |
+
vocab_file = os.path.join(
|
177 |
+
save_directory, self.vocab_files_names["vocab_file"]
|
178 |
+
)
|
179 |
+
else:
|
180 |
+
vocab_file = save_directory
|
181 |
+
|
182 |
+
with open(self.vocab_file, 'rb') as fin:
|
183 |
+
proto_str = fin.read()
|
184 |
+
|
185 |
+
with open(vocab_file, "wb") as writer:
|
186 |
+
writer.write(proto_str)
|
187 |
+
|
188 |
+
return (vocab_file,)
|
189 |
+
|
190 |
+
def get_prefix_tokens(self):
|
191 |
+
prefix_tokens = [self.get_command("[gMASK]"), self.get_command("sop")]
|
192 |
+
return prefix_tokens
|
193 |
+
|
194 |
+
def build_single_message(self, role, metadata, message):
|
195 |
+
assert role in ["system", "user", "assistant", "observation"], role
|
196 |
+
role_tokens = [self.get_command(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n")
|
197 |
+
message_tokens = self.tokenizer.encode(message)
|
198 |
+
tokens = role_tokens + message_tokens
|
199 |
+
return tokens
|
200 |
+
|
201 |
+
def build_chat_input(self, query, history=None, role="user"):
|
202 |
+
if history is None:
|
203 |
+
history = []
|
204 |
+
input_ids = []
|
205 |
+
for item in history:
|
206 |
+
content = item["content"]
|
207 |
+
if item["role"] == "system" and "tools" in item:
|
208 |
+
content = content + "\n" + json.dumps(item["tools"], indent=4, ensure_ascii=False)
|
209 |
+
input_ids.extend(self.build_single_message(item["role"], item.get("metadata", ""), content))
|
210 |
+
input_ids.extend(self.build_single_message(role, "", query))
|
211 |
+
input_ids.extend([self.get_command("<|assistant|>")])
|
212 |
+
return self.batch_encode_plus([input_ids], return_tensors="pt", is_split_into_words=True)
|
213 |
+
|
214 |
+
def build_inputs_with_special_tokens(
|
215 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
216 |
+
) -> List[int]:
|
217 |
+
"""
|
218 |
+
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
|
219 |
+
adding special tokens. A BERT sequence has the following format:
|
220 |
+
|
221 |
+
- single sequence: `[CLS] X [SEP]`
|
222 |
+
- pair of sequences: `[CLS] A [SEP] B [SEP]`
|
223 |
+
|
224 |
+
Args:
|
225 |
+
token_ids_0 (`List[int]`):
|
226 |
+
List of IDs to which the special tokens will be added.
|
227 |
+
token_ids_1 (`List[int]`, *optional*):
|
228 |
+
Optional second list of IDs for sequence pairs.
|
229 |
+
|
230 |
+
Returns:
|
231 |
+
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
|
232 |
+
"""
|
233 |
+
prefix_tokens = self.get_prefix_tokens()
|
234 |
+
token_ids_0 = prefix_tokens + token_ids_0
|
235 |
+
if token_ids_1 is not None:
|
236 |
+
token_ids_0 = token_ids_0 + token_ids_1 + [self.get_command("<eos>")]
|
237 |
+
return token_ids_0
|
238 |
+
|
239 |
+
def _pad(
|
240 |
+
self,
|
241 |
+
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
|
242 |
+
max_length: Optional[int] = None,
|
243 |
+
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
244 |
+
pad_to_multiple_of: Optional[int] = None,
|
245 |
+
return_attention_mask: Optional[bool] = None,
|
246 |
+
) -> dict:
|
247 |
+
"""
|
248 |
+
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
|
249 |
+
|
250 |
+
Args:
|
251 |
+
encoded_inputs:
|
252 |
+
Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
|
253 |
+
max_length: maximum length of the returned list and optionally padding length (see below).
|
254 |
+
Will truncate by taking into account the special tokens.
|
255 |
+
padding_strategy: PaddingStrategy to use for padding.
|
256 |
+
|
257 |
+
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
|
258 |
+
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
|
259 |
+
- PaddingStrategy.DO_NOT_PAD: Do not pad
|
260 |
+
The tokenizer padding sides are defined in self.padding_side:
|
261 |
+
|
262 |
+
- 'left': pads on the left of the sequences
|
263 |
+
- 'right': pads on the right of the sequences
|
264 |
+
pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
|
265 |
+
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
|
266 |
+
`>= 7.5` (Volta).
|
267 |
+
return_attention_mask:
|
268 |
+
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
|
269 |
+
"""
|
270 |
+
# Load from model defaults
|
271 |
+
assert self.padding_side == "left"
|
272 |
+
|
273 |
+
required_input = encoded_inputs[self.model_input_names[0]]
|
274 |
+
seq_length = len(required_input)
|
275 |
+
|
276 |
+
if padding_strategy == PaddingStrategy.LONGEST:
|
277 |
+
max_length = len(required_input)
|
278 |
+
|
279 |
+
if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
|
280 |
+
max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
|
281 |
+
|
282 |
+
needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
|
283 |
+
|
284 |
+
# Initialize attention mask if not present.
|
285 |
+
if "attention_mask" not in encoded_inputs:
|
286 |
+
encoded_inputs["attention_mask"] = [1] * seq_length
|
287 |
+
|
288 |
+
if "position_ids" not in encoded_inputs:
|
289 |
+
encoded_inputs["position_ids"] = list(range(seq_length))
|
290 |
+
|
291 |
+
if needs_to_be_padded:
|
292 |
+
difference = max_length - len(required_input)
|
293 |
+
|
294 |
+
if "attention_mask" in encoded_inputs:
|
295 |
+
encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
|
296 |
+
if "position_ids" in encoded_inputs:
|
297 |
+
encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
|
298 |
+
encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
|
299 |
+
|
300 |
+
return encoded_inputs
|
checkpoint-2000/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
checkpoint-2000/tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"64795": {
|
4 |
+
"content": "<|user|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"64797": {
|
12 |
+
"content": "<|observation|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
}
|
19 |
+
},
|
20 |
+
"additional_special_tokens": [
|
21 |
+
"<|user|>",
|
22 |
+
"<|observation|>"
|
23 |
+
],
|
24 |
+
"auto_map": {
|
25 |
+
"AutoTokenizer": [
|
26 |
+
"tokenization_chatglm.ChatGLMTokenizer",
|
27 |
+
null
|
28 |
+
]
|
29 |
+
},
|
30 |
+
"clean_up_tokenization_spaces": false,
|
31 |
+
"do_lower_case": false,
|
32 |
+
"encode_special_tokens": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"remove_space": false,
|
38 |
+
"split_special_tokens": false,
|
39 |
+
"tokenizer_class": "ChatGLMTokenizer",
|
40 |
+
"unk_token": "<unk>"
|
41 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,2421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0036381884330698,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.9999980101927616e-05,
|
14 |
+
"loss": 3.2533,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4.99999204077421e-05,
|
20 |
+
"loss": 3.2279,
|
21 |
+
"step": 10
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 4.999978982687695e-05,
|
26 |
+
"loss": 3.193,
|
27 |
+
"step": 15
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 4.9999597065062966e-05,
|
32 |
+
"loss": 3.2863,
|
33 |
+
"step": 20
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 4.999934212277958e-05,
|
38 |
+
"loss": 3.1724,
|
39 |
+
"step": 25
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 4.999902500066093e-05,
|
44 |
+
"loss": 3.1088,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 4.999864569949576e-05,
|
50 |
+
"loss": 3.3241,
|
51 |
+
"step": 35
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 4.99982042202275e-05,
|
56 |
+
"loss": 3.1904,
|
57 |
+
"step": 40
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 4.999770056395421e-05,
|
62 |
+
"loss": 2.9254,
|
63 |
+
"step": 45
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 4.999713473192863e-05,
|
68 |
+
"loss": 3.1845,
|
69 |
+
"step": 50
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 4.999650672555812e-05,
|
74 |
+
"loss": 2.8475,
|
75 |
+
"step": 55
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 4.9995816546404695e-05,
|
80 |
+
"loss": 3.0486,
|
81 |
+
"step": 60
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 4.9995064196185014e-05,
|
86 |
+
"loss": 2.6464,
|
87 |
+
"step": 65
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 4.9994249676770364e-05,
|
92 |
+
"loss": 3.0446,
|
93 |
+
"step": 70
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 4.999337299018667e-05,
|
98 |
+
"loss": 3.375,
|
99 |
+
"step": 75
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 4.999243413861447e-05,
|
104 |
+
"loss": 2.8787,
|
105 |
+
"step": 80
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 4.999143312438893e-05,
|
110 |
+
"loss": 3.014,
|
111 |
+
"step": 85
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.05,
|
115 |
+
"learning_rate": 4.999036994999985e-05,
|
116 |
+
"loss": 2.8288,
|
117 |
+
"step": 90
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 4.9989244618091596e-05,
|
122 |
+
"loss": 3.1879,
|
123 |
+
"step": 95
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 4.998805713146317e-05,
|
128 |
+
"loss": 2.9749,
|
129 |
+
"step": 100
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 4.9986807493068165e-05,
|
134 |
+
"loss": 2.6304,
|
135 |
+
"step": 105
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06,
|
139 |
+
"learning_rate": 4.998549570601475e-05,
|
140 |
+
"loss": 2.943,
|
141 |
+
"step": 110
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 4.998412177356568e-05,
|
146 |
+
"loss": 2.7595,
|
147 |
+
"step": 115
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 4.9982685699138275e-05,
|
152 |
+
"loss": 2.7377,
|
153 |
+
"step": 120
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 4.9981187486304423e-05,
|
158 |
+
"loss": 2.9878,
|
159 |
+
"step": 125
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07,
|
163 |
+
"learning_rate": 4.997962713879058e-05,
|
164 |
+
"loss": 2.7882,
|
165 |
+
"step": 130
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.07,
|
169 |
+
"learning_rate": 4.997800466047772e-05,
|
170 |
+
"loss": 2.7802,
|
171 |
+
"step": 135
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 4.997632005540138e-05,
|
176 |
+
"loss": 3.0129,
|
177 |
+
"step": 140
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 4.997457332775159e-05,
|
182 |
+
"loss": 2.9444,
|
183 |
+
"step": 145
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.08,
|
187 |
+
"learning_rate": 4.997276448187294e-05,
|
188 |
+
"loss": 2.9664,
|
189 |
+
"step": 150
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.08,
|
193 |
+
"learning_rate": 4.9970893522264476e-05,
|
194 |
+
"loss": 2.7367,
|
195 |
+
"step": 155
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 4.996896045357977e-05,
|
200 |
+
"loss": 2.7012,
|
201 |
+
"step": 160
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 4.9966965280626856e-05,
|
206 |
+
"loss": 2.8493,
|
207 |
+
"step": 165
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.09,
|
211 |
+
"learning_rate": 4.996490800836825e-05,
|
212 |
+
"loss": 2.9274,
|
213 |
+
"step": 170
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09,
|
217 |
+
"learning_rate": 4.996278864192092e-05,
|
218 |
+
"loss": 2.8093,
|
219 |
+
"step": 175
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 4.9960607186556286e-05,
|
224 |
+
"loss": 3.1782,
|
225 |
+
"step": 180
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 4.995836364770018e-05,
|
230 |
+
"loss": 2.7507,
|
231 |
+
"step": 185
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.1,
|
235 |
+
"learning_rate": 4.995605803093287e-05,
|
236 |
+
"loss": 2.6724,
|
237 |
+
"step": 190
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.1,
|
241 |
+
"learning_rate": 4.9953690341989026e-05,
|
242 |
+
"loss": 3.0258,
|
243 |
+
"step": 195
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 4.9951260586757694e-05,
|
248 |
+
"loss": 3.1134,
|
249 |
+
"step": 200
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1,
|
253 |
+
"learning_rate": 4.9948768771282314e-05,
|
254 |
+
"loss": 2.9937,
|
255 |
+
"step": 205
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11,
|
259 |
+
"learning_rate": 4.9946214901760665e-05,
|
260 |
+
"loss": 2.7394,
|
261 |
+
"step": 210
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.11,
|
265 |
+
"learning_rate": 4.99435989845449e-05,
|
266 |
+
"loss": 2.9696,
|
267 |
+
"step": 215
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 4.994092102614146e-05,
|
272 |
+
"loss": 2.753,
|
273 |
+
"step": 220
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.11,
|
277 |
+
"learning_rate": 4.993818103321113e-05,
|
278 |
+
"loss": 3.0759,
|
279 |
+
"step": 225
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.12,
|
283 |
+
"learning_rate": 4.9935379012568985e-05,
|
284 |
+
"loss": 2.7512,
|
285 |
+
"step": 230
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.12,
|
289 |
+
"learning_rate": 4.993251497118438e-05,
|
290 |
+
"loss": 2.8656,
|
291 |
+
"step": 235
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 4.992958891618091e-05,
|
296 |
+
"loss": 2.6628,
|
297 |
+
"step": 240
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.12,
|
301 |
+
"learning_rate": 4.992660085483645e-05,
|
302 |
+
"loss": 2.8012,
|
303 |
+
"step": 245
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.13,
|
307 |
+
"learning_rate": 4.992355079458307e-05,
|
308 |
+
"loss": 2.8141,
|
309 |
+
"step": 250
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.13,
|
313 |
+
"learning_rate": 4.992043874300706e-05,
|
314 |
+
"loss": 2.9083,
|
315 |
+
"step": 255
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.13,
|
319 |
+
"learning_rate": 4.991726470784891e-05,
|
320 |
+
"loss": 2.5846,
|
321 |
+
"step": 260
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.13,
|
325 |
+
"learning_rate": 4.991402869700325e-05,
|
326 |
+
"loss": 2.8088,
|
327 |
+
"step": 265
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.14,
|
331 |
+
"learning_rate": 4.991073071851889e-05,
|
332 |
+
"loss": 2.9979,
|
333 |
+
"step": 270
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.14,
|
337 |
+
"learning_rate": 4.990737078059875e-05,
|
338 |
+
"loss": 3.0171,
|
339 |
+
"step": 275
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.14,
|
343 |
+
"learning_rate": 4.990394889159986e-05,
|
344 |
+
"loss": 2.9278,
|
345 |
+
"step": 280
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.14,
|
349 |
+
"learning_rate": 4.9900465060033364e-05,
|
350 |
+
"loss": 2.7998,
|
351 |
+
"step": 285
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.15,
|
355 |
+
"learning_rate": 4.989691929456443e-05,
|
356 |
+
"loss": 2.721,
|
357 |
+
"step": 290
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.15,
|
361 |
+
"learning_rate": 4.9893311604012306e-05,
|
362 |
+
"loss": 3.0291,
|
363 |
+
"step": 295
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.15,
|
367 |
+
"learning_rate": 4.988964199735024e-05,
|
368 |
+
"loss": 2.9777,
|
369 |
+
"step": 300
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.15,
|
373 |
+
"learning_rate": 4.988591048370552e-05,
|
374 |
+
"loss": 2.318,
|
375 |
+
"step": 305
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.16,
|
379 |
+
"learning_rate": 4.988211707235936e-05,
|
380 |
+
"loss": 3.0332,
|
381 |
+
"step": 310
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.16,
|
385 |
+
"learning_rate": 4.987826177274697e-05,
|
386 |
+
"loss": 2.4888,
|
387 |
+
"step": 315
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.16,
|
391 |
+
"learning_rate": 4.987434459445748e-05,
|
392 |
+
"loss": 2.9259,
|
393 |
+
"step": 320
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.16,
|
397 |
+
"learning_rate": 4.987036554723391e-05,
|
398 |
+
"loss": 2.9568,
|
399 |
+
"step": 325
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.17,
|
403 |
+
"learning_rate": 4.98663246409732e-05,
|
404 |
+
"loss": 2.8708,
|
405 |
+
"step": 330
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.17,
|
409 |
+
"learning_rate": 4.986222188572611e-05,
|
410 |
+
"loss": 2.7848,
|
411 |
+
"step": 335
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.17,
|
415 |
+
"learning_rate": 4.985805729169728e-05,
|
416 |
+
"loss": 2.6178,
|
417 |
+
"step": 340
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.17,
|
421 |
+
"learning_rate": 4.985383086924511e-05,
|
422 |
+
"loss": 2.8326,
|
423 |
+
"step": 345
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.18,
|
427 |
+
"learning_rate": 4.984954262888182e-05,
|
428 |
+
"loss": 2.8845,
|
429 |
+
"step": 350
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.18,
|
433 |
+
"learning_rate": 4.9845192581273365e-05,
|
434 |
+
"loss": 2.6151,
|
435 |
+
"step": 355
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.18,
|
439 |
+
"learning_rate": 4.984078073723944e-05,
|
440 |
+
"loss": 2.8474,
|
441 |
+
"step": 360
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.18,
|
445 |
+
"learning_rate": 4.9836307107753455e-05,
|
446 |
+
"loss": 2.808,
|
447 |
+
"step": 365
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.19,
|
451 |
+
"learning_rate": 4.983177170394248e-05,
|
452 |
+
"loss": 2.8491,
|
453 |
+
"step": 370
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.19,
|
457 |
+
"learning_rate": 4.9827174537087226e-05,
|
458 |
+
"loss": 2.7764,
|
459 |
+
"step": 375
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.19,
|
463 |
+
"learning_rate": 4.982251561862205e-05,
|
464 |
+
"loss": 2.7582,
|
465 |
+
"step": 380
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.19,
|
469 |
+
"learning_rate": 4.981779496013489e-05,
|
470 |
+
"loss": 2.5379,
|
471 |
+
"step": 385
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.2,
|
475 |
+
"learning_rate": 4.981301257336723e-05,
|
476 |
+
"loss": 2.9937,
|
477 |
+
"step": 390
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.2,
|
481 |
+
"learning_rate": 4.980816847021412e-05,
|
482 |
+
"loss": 2.8574,
|
483 |
+
"step": 395
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.2,
|
487 |
+
"learning_rate": 4.980326266272409e-05,
|
488 |
+
"loss": 2.9369,
|
489 |
+
"step": 400
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.2,
|
493 |
+
"learning_rate": 4.979829516309915e-05,
|
494 |
+
"loss": 2.836,
|
495 |
+
"step": 405
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.21,
|
499 |
+
"learning_rate": 4.979326598369477e-05,
|
500 |
+
"loss": 2.9369,
|
501 |
+
"step": 410
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.21,
|
505 |
+
"learning_rate": 4.9788175137019814e-05,
|
506 |
+
"loss": 2.6667,
|
507 |
+
"step": 415
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.21,
|
511 |
+
"learning_rate": 4.9783022635736534e-05,
|
512 |
+
"loss": 2.999,
|
513 |
+
"step": 420
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.21,
|
517 |
+
"learning_rate": 4.977780849266054e-05,
|
518 |
+
"loss": 2.907,
|
519 |
+
"step": 425
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.22,
|
523 |
+
"learning_rate": 4.9772532720760744e-05,
|
524 |
+
"loss": 2.8028,
|
525 |
+
"step": 430
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.22,
|
529 |
+
"learning_rate": 4.976719533315937e-05,
|
530 |
+
"loss": 2.7999,
|
531 |
+
"step": 435
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.22,
|
535 |
+
"learning_rate": 4.976179634313187e-05,
|
536 |
+
"loss": 2.8918,
|
537 |
+
"step": 440
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.22,
|
541 |
+
"learning_rate": 4.9756335764106944e-05,
|
542 |
+
"loss": 2.7926,
|
543 |
+
"step": 445
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.23,
|
547 |
+
"learning_rate": 4.975081360966646e-05,
|
548 |
+
"loss": 2.6709,
|
549 |
+
"step": 450
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.23,
|
553 |
+
"learning_rate": 4.9745229893545436e-05,
|
554 |
+
"loss": 2.8248,
|
555 |
+
"step": 455
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.23,
|
559 |
+
"learning_rate": 4.973958462963203e-05,
|
560 |
+
"loss": 3.1146,
|
561 |
+
"step": 460
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.23,
|
565 |
+
"learning_rate": 4.973387783196747e-05,
|
566 |
+
"loss": 2.9991,
|
567 |
+
"step": 465
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.24,
|
571 |
+
"learning_rate": 4.972810951474605e-05,
|
572 |
+
"loss": 2.7726,
|
573 |
+
"step": 470
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.24,
|
577 |
+
"learning_rate": 4.972227969231505e-05,
|
578 |
+
"loss": 2.9025,
|
579 |
+
"step": 475
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.24,
|
583 |
+
"learning_rate": 4.971638837917475e-05,
|
584 |
+
"loss": 2.6521,
|
585 |
+
"step": 480
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.24,
|
589 |
+
"learning_rate": 4.971043558997839e-05,
|
590 |
+
"loss": 2.9511,
|
591 |
+
"step": 485
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.25,
|
595 |
+
"learning_rate": 4.9704421339532075e-05,
|
596 |
+
"loss": 2.6938,
|
597 |
+
"step": 490
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.25,
|
601 |
+
"learning_rate": 4.969834564279482e-05,
|
602 |
+
"loss": 2.8533,
|
603 |
+
"step": 495
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.25,
|
607 |
+
"learning_rate": 4.9692208514878444e-05,
|
608 |
+
"loss": 2.6411,
|
609 |
+
"step": 500
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.25,
|
613 |
+
"learning_rate": 4.968600997104758e-05,
|
614 |
+
"loss": 2.6486,
|
615 |
+
"step": 505
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.26,
|
619 |
+
"learning_rate": 4.967975002671961e-05,
|
620 |
+
"loss": 2.8561,
|
621 |
+
"step": 510
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.26,
|
625 |
+
"learning_rate": 4.967342869746463e-05,
|
626 |
+
"loss": 2.6984,
|
627 |
+
"step": 515
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.26,
|
631 |
+
"learning_rate": 4.9667045999005424e-05,
|
632 |
+
"loss": 2.91,
|
633 |
+
"step": 520
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.26,
|
637 |
+
"learning_rate": 4.966060194721742e-05,
|
638 |
+
"loss": 2.7205,
|
639 |
+
"step": 525
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.27,
|
643 |
+
"learning_rate": 4.965409655812865e-05,
|
644 |
+
"loss": 2.7634,
|
645 |
+
"step": 530
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.27,
|
649 |
+
"learning_rate": 4.9647529847919684e-05,
|
650 |
+
"loss": 2.9647,
|
651 |
+
"step": 535
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.27,
|
655 |
+
"learning_rate": 4.964090183292364e-05,
|
656 |
+
"loss": 2.6357,
|
657 |
+
"step": 540
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.27,
|
661 |
+
"learning_rate": 4.963421252962609e-05,
|
662 |
+
"loss": 3.0285,
|
663 |
+
"step": 545
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.28,
|
667 |
+
"learning_rate": 4.96274619546651e-05,
|
668 |
+
"loss": 2.9895,
|
669 |
+
"step": 550
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.28,
|
673 |
+
"learning_rate": 4.962065012483106e-05,
|
674 |
+
"loss": 2.7286,
|
675 |
+
"step": 555
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.28,
|
679 |
+
"learning_rate": 4.961377705706677e-05,
|
680 |
+
"loss": 3.1337,
|
681 |
+
"step": 560
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.28,
|
685 |
+
"learning_rate": 4.960684276846733e-05,
|
686 |
+
"loss": 2.8268,
|
687 |
+
"step": 565
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.29,
|
691 |
+
"learning_rate": 4.959984727628011e-05,
|
692 |
+
"loss": 2.5851,
|
693 |
+
"step": 570
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.29,
|
697 |
+
"learning_rate": 4.959279059790471e-05,
|
698 |
+
"loss": 2.9359,
|
699 |
+
"step": 575
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.29,
|
703 |
+
"learning_rate": 4.958567275089291e-05,
|
704 |
+
"loss": 2.8842,
|
705 |
+
"step": 580
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.29,
|
709 |
+
"learning_rate": 4.957849375294864e-05,
|
710 |
+
"loss": 2.6186,
|
711 |
+
"step": 585
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.3,
|
715 |
+
"learning_rate": 4.957125362192794e-05,
|
716 |
+
"loss": 3.0116,
|
717 |
+
"step": 590
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.3,
|
721 |
+
"learning_rate": 4.956395237583887e-05,
|
722 |
+
"loss": 2.7045,
|
723 |
+
"step": 595
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.3,
|
727 |
+
"learning_rate": 4.9556590032841526e-05,
|
728 |
+
"loss": 2.8766,
|
729 |
+
"step": 600
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.3,
|
733 |
+
"learning_rate": 4.954916661124797e-05,
|
734 |
+
"loss": 2.7858,
|
735 |
+
"step": 605
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.31,
|
739 |
+
"learning_rate": 4.954168212952216e-05,
|
740 |
+
"loss": 2.7379,
|
741 |
+
"step": 610
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.31,
|
745 |
+
"learning_rate": 4.953413660627995e-05,
|
746 |
+
"loss": 2.475,
|
747 |
+
"step": 615
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.31,
|
751 |
+
"learning_rate": 4.9526530060289e-05,
|
752 |
+
"loss": 2.8357,
|
753 |
+
"step": 620
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.31,
|
757 |
+
"learning_rate": 4.951886251046876e-05,
|
758 |
+
"loss": 2.9284,
|
759 |
+
"step": 625
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.32,
|
763 |
+
"learning_rate": 4.951113397589042e-05,
|
764 |
+
"loss": 2.8144,
|
765 |
+
"step": 630
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.32,
|
769 |
+
"learning_rate": 4.9503344475776846e-05,
|
770 |
+
"loss": 2.6845,
|
771 |
+
"step": 635
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.32,
|
775 |
+
"learning_rate": 4.9495494029502535e-05,
|
776 |
+
"loss": 2.8937,
|
777 |
+
"step": 640
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.32,
|
781 |
+
"learning_rate": 4.9487582656593575e-05,
|
782 |
+
"loss": 3.0325,
|
783 |
+
"step": 645
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.33,
|
787 |
+
"learning_rate": 4.94796103767276e-05,
|
788 |
+
"loss": 2.7058,
|
789 |
+
"step": 650
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.33,
|
793 |
+
"learning_rate": 4.9471577209733746e-05,
|
794 |
+
"loss": 2.6162,
|
795 |
+
"step": 655
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.33,
|
799 |
+
"learning_rate": 4.946348317559257e-05,
|
800 |
+
"loss": 3.0129,
|
801 |
+
"step": 660
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.33,
|
805 |
+
"learning_rate": 4.945532829443603e-05,
|
806 |
+
"loss": 2.7587,
|
807 |
+
"step": 665
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.34,
|
811 |
+
"learning_rate": 4.944711258654742e-05,
|
812 |
+
"loss": 2.8915,
|
813 |
+
"step": 670
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.34,
|
817 |
+
"learning_rate": 4.943883607236135e-05,
|
818 |
+
"loss": 2.7343,
|
819 |
+
"step": 675
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.34,
|
823 |
+
"learning_rate": 4.943049877246364e-05,
|
824 |
+
"loss": 2.881,
|
825 |
+
"step": 680
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.34,
|
829 |
+
"learning_rate": 4.942210070759131e-05,
|
830 |
+
"loss": 2.488,
|
831 |
+
"step": 685
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.35,
|
835 |
+
"learning_rate": 4.941364189863253e-05,
|
836 |
+
"loss": 2.896,
|
837 |
+
"step": 690
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.35,
|
841 |
+
"learning_rate": 4.940512236662654e-05,
|
842 |
+
"loss": 2.7757,
|
843 |
+
"step": 695
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.35,
|
847 |
+
"learning_rate": 4.9396542132763634e-05,
|
848 |
+
"loss": 2.6271,
|
849 |
+
"step": 700
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.35,
|
853 |
+
"learning_rate": 4.938790121838506e-05,
|
854 |
+
"loss": 2.6804,
|
855 |
+
"step": 705
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.36,
|
859 |
+
"learning_rate": 4.937919964498302e-05,
|
860 |
+
"loss": 2.7313,
|
861 |
+
"step": 710
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.36,
|
865 |
+
"learning_rate": 4.937043743420058e-05,
|
866 |
+
"loss": 2.9277,
|
867 |
+
"step": 715
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.36,
|
871 |
+
"learning_rate": 4.9361614607831605e-05,
|
872 |
+
"loss": 2.6366,
|
873 |
+
"step": 720
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.36,
|
877 |
+
"learning_rate": 4.935273118782078e-05,
|
878 |
+
"loss": 3.0556,
|
879 |
+
"step": 725
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.37,
|
883 |
+
"learning_rate": 4.934378719626345e-05,
|
884 |
+
"loss": 3.0182,
|
885 |
+
"step": 730
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.37,
|
889 |
+
"learning_rate": 4.933478265540564e-05,
|
890 |
+
"loss": 2.824,
|
891 |
+
"step": 735
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.37,
|
895 |
+
"learning_rate": 4.932571758764398e-05,
|
896 |
+
"loss": 2.636,
|
897 |
+
"step": 740
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.37,
|
901 |
+
"learning_rate": 4.931659201552563e-05,
|
902 |
+
"loss": 2.7025,
|
903 |
+
"step": 745
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.38,
|
907 |
+
"learning_rate": 4.930740596174827e-05,
|
908 |
+
"loss": 2.8919,
|
909 |
+
"step": 750
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.38,
|
913 |
+
"learning_rate": 4.9298159449159965e-05,
|
914 |
+
"loss": 2.8434,
|
915 |
+
"step": 755
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.38,
|
919 |
+
"learning_rate": 4.928885250075921e-05,
|
920 |
+
"loss": 2.9448,
|
921 |
+
"step": 760
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.38,
|
925 |
+
"learning_rate": 4.927948513969478e-05,
|
926 |
+
"loss": 2.7312,
|
927 |
+
"step": 765
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.39,
|
931 |
+
"learning_rate": 4.927005738926573e-05,
|
932 |
+
"loss": 2.8688,
|
933 |
+
"step": 770
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.39,
|
937 |
+
"learning_rate": 4.926056927292132e-05,
|
938 |
+
"loss": 2.8639,
|
939 |
+
"step": 775
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.39,
|
943 |
+
"learning_rate": 4.925102081426095e-05,
|
944 |
+
"loss": 2.7809,
|
945 |
+
"step": 780
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.39,
|
949 |
+
"learning_rate": 4.9241412037034115e-05,
|
950 |
+
"loss": 3.0111,
|
951 |
+
"step": 785
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.4,
|
955 |
+
"learning_rate": 4.9231742965140314e-05,
|
956 |
+
"loss": 2.7252,
|
957 |
+
"step": 790
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.4,
|
961 |
+
"learning_rate": 4.922201362262905e-05,
|
962 |
+
"loss": 2.9717,
|
963 |
+
"step": 795
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.4,
|
967 |
+
"learning_rate": 4.92122240336997e-05,
|
968 |
+
"loss": 2.7191,
|
969 |
+
"step": 800
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.4,
|
973 |
+
"learning_rate": 4.920237422270153e-05,
|
974 |
+
"loss": 2.9346,
|
975 |
+
"step": 805
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.41,
|
979 |
+
"learning_rate": 4.9192464214133536e-05,
|
980 |
+
"loss": 2.7967,
|
981 |
+
"step": 810
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.41,
|
985 |
+
"learning_rate": 4.9182494032644496e-05,
|
986 |
+
"loss": 2.7326,
|
987 |
+
"step": 815
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.41,
|
991 |
+
"learning_rate": 4.917246370303284e-05,
|
992 |
+
"loss": 2.8933,
|
993 |
+
"step": 820
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.41,
|
997 |
+
"learning_rate": 4.9162373250246575e-05,
|
998 |
+
"loss": 2.7939,
|
999 |
+
"step": 825
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.42,
|
1003 |
+
"learning_rate": 4.9152222699383273e-05,
|
1004 |
+
"loss": 2.7807,
|
1005 |
+
"step": 830
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.42,
|
1009 |
+
"learning_rate": 4.9142012075689994e-05,
|
1010 |
+
"loss": 2.6996,
|
1011 |
+
"step": 835
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.42,
|
1015 |
+
"learning_rate": 4.913174140456319e-05,
|
1016 |
+
"loss": 2.7569,
|
1017 |
+
"step": 840
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.42,
|
1021 |
+
"learning_rate": 4.912141071154869e-05,
|
1022 |
+
"loss": 2.9347,
|
1023 |
+
"step": 845
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.43,
|
1027 |
+
"learning_rate": 4.911102002234159e-05,
|
1028 |
+
"loss": 2.7251,
|
1029 |
+
"step": 850
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.43,
|
1033 |
+
"learning_rate": 4.910056936278623e-05,
|
1034 |
+
"loss": 3.1228,
|
1035 |
+
"step": 855
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.43,
|
1039 |
+
"learning_rate": 4.90900587588761e-05,
|
1040 |
+
"loss": 2.9902,
|
1041 |
+
"step": 860
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.43,
|
1045 |
+
"learning_rate": 4.9079488236753803e-05,
|
1046 |
+
"loss": 2.5095,
|
1047 |
+
"step": 865
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.44,
|
1051 |
+
"learning_rate": 4.906885782271095e-05,
|
1052 |
+
"loss": 2.7523,
|
1053 |
+
"step": 870
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.44,
|
1057 |
+
"learning_rate": 4.905816754318814e-05,
|
1058 |
+
"loss": 2.6656,
|
1059 |
+
"step": 875
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.44,
|
1063 |
+
"learning_rate": 4.9047417424774874e-05,
|
1064 |
+
"loss": 2.8454,
|
1065 |
+
"step": 880
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.44,
|
1069 |
+
"learning_rate": 4.903660749420946e-05,
|
1070 |
+
"loss": 2.8194,
|
1071 |
+
"step": 885
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.45,
|
1075 |
+
"learning_rate": 4.9025737778379025e-05,
|
1076 |
+
"loss": 2.8421,
|
1077 |
+
"step": 890
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.45,
|
1081 |
+
"learning_rate": 4.9014808304319326e-05,
|
1082 |
+
"loss": 2.9656,
|
1083 |
+
"step": 895
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.45,
|
1087 |
+
"learning_rate": 4.900381909921482e-05,
|
1088 |
+
"loss": 2.7484,
|
1089 |
+
"step": 900
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.45,
|
1093 |
+
"learning_rate": 4.899277019039849e-05,
|
1094 |
+
"loss": 2.9044,
|
1095 |
+
"step": 905
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.46,
|
1099 |
+
"learning_rate": 4.898166160535186e-05,
|
1100 |
+
"loss": 2.8016,
|
1101 |
+
"step": 910
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.46,
|
1105 |
+
"learning_rate": 4.8970493371704826e-05,
|
1106 |
+
"loss": 2.6278,
|
1107 |
+
"step": 915
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.46,
|
1111 |
+
"learning_rate": 4.895926551723569e-05,
|
1112 |
+
"loss": 2.7214,
|
1113 |
+
"step": 920
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.46,
|
1117 |
+
"learning_rate": 4.8947978069871036e-05,
|
1118 |
+
"loss": 2.7679,
|
1119 |
+
"step": 925
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.47,
|
1123 |
+
"learning_rate": 4.8936631057685654e-05,
|
1124 |
+
"loss": 2.7196,
|
1125 |
+
"step": 930
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.47,
|
1129 |
+
"learning_rate": 4.8925224508902514e-05,
|
1130 |
+
"loss": 2.7866,
|
1131 |
+
"step": 935
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.47,
|
1135 |
+
"learning_rate": 4.8913758451892644e-05,
|
1136 |
+
"loss": 2.72,
|
1137 |
+
"step": 940
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.47,
|
1141 |
+
"learning_rate": 4.89022329151751e-05,
|
1142 |
+
"loss": 2.752,
|
1143 |
+
"step": 945
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.48,
|
1147 |
+
"learning_rate": 4.8890647927416887e-05,
|
1148 |
+
"loss": 3.0487,
|
1149 |
+
"step": 950
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.48,
|
1153 |
+
"learning_rate": 4.8879003517432857e-05,
|
1154 |
+
"loss": 2.8928,
|
1155 |
+
"step": 955
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.48,
|
1159 |
+
"learning_rate": 4.886729971418568e-05,
|
1160 |
+
"loss": 2.7793,
|
1161 |
+
"step": 960
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.48,
|
1165 |
+
"learning_rate": 4.8855536546785726e-05,
|
1166 |
+
"loss": 2.537,
|
1167 |
+
"step": 965
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.49,
|
1171 |
+
"learning_rate": 4.884371404449105e-05,
|
1172 |
+
"loss": 2.8345,
|
1173 |
+
"step": 970
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.49,
|
1177 |
+
"learning_rate": 4.8831832236707284e-05,
|
1178 |
+
"loss": 2.9673,
|
1179 |
+
"step": 975
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.49,
|
1183 |
+
"learning_rate": 4.8819891152987546e-05,
|
1184 |
+
"loss": 2.8295,
|
1185 |
+
"step": 980
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.49,
|
1189 |
+
"learning_rate": 4.880789082303241e-05,
|
1190 |
+
"loss": 3.0753,
|
1191 |
+
"step": 985
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.5,
|
1195 |
+
"learning_rate": 4.879583127668979e-05,
|
1196 |
+
"loss": 2.6748,
|
1197 |
+
"step": 990
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.5,
|
1201 |
+
"learning_rate": 4.878371254395492e-05,
|
1202 |
+
"loss": 2.8115,
|
1203 |
+
"step": 995
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.5,
|
1207 |
+
"learning_rate": 4.877153465497022e-05,
|
1208 |
+
"loss": 2.7039,
|
1209 |
+
"step": 1000
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.5,
|
1213 |
+
"learning_rate": 4.8759297640025235e-05,
|
1214 |
+
"loss": 2.9469,
|
1215 |
+
"step": 1005
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.51,
|
1219 |
+
"learning_rate": 4.874700152955661e-05,
|
1220 |
+
"loss": 2.9745,
|
1221 |
+
"step": 1010
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.51,
|
1225 |
+
"learning_rate": 4.8734646354147936e-05,
|
1226 |
+
"loss": 2.9341,
|
1227 |
+
"step": 1015
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.51,
|
1231 |
+
"learning_rate": 4.8722232144529754e-05,
|
1232 |
+
"loss": 3.0511,
|
1233 |
+
"step": 1020
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.51,
|
1237 |
+
"learning_rate": 4.870975893157941e-05,
|
1238 |
+
"loss": 2.5396,
|
1239 |
+
"step": 1025
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.52,
|
1243 |
+
"learning_rate": 4.8697226746321004e-05,
|
1244 |
+
"loss": 2.6699,
|
1245 |
+
"step": 1030
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 0.52,
|
1249 |
+
"learning_rate": 4.868463561992532e-05,
|
1250 |
+
"loss": 2.4887,
|
1251 |
+
"step": 1035
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 0.52,
|
1255 |
+
"learning_rate": 4.867198558370977e-05,
|
1256 |
+
"loss": 2.4773,
|
1257 |
+
"step": 1040
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.52,
|
1261 |
+
"learning_rate": 4.865927666913825e-05,
|
1262 |
+
"loss": 2.7612,
|
1263 |
+
"step": 1045
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.53,
|
1267 |
+
"learning_rate": 4.864650890782113e-05,
|
1268 |
+
"loss": 2.9116,
|
1269 |
+
"step": 1050
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.53,
|
1273 |
+
"learning_rate": 4.863368233151514e-05,
|
1274 |
+
"loss": 2.8205,
|
1275 |
+
"step": 1055
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 0.53,
|
1279 |
+
"learning_rate": 4.862079697212329e-05,
|
1280 |
+
"loss": 2.6711,
|
1281 |
+
"step": 1060
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 0.53,
|
1285 |
+
"learning_rate": 4.8607852861694804e-05,
|
1286 |
+
"loss": 3.1138,
|
1287 |
+
"step": 1065
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 0.54,
|
1291 |
+
"learning_rate": 4.859485003242503e-05,
|
1292 |
+
"loss": 2.5603,
|
1293 |
+
"step": 1070
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 0.54,
|
1297 |
+
"learning_rate": 4.858178851665539e-05,
|
1298 |
+
"loss": 2.7981,
|
1299 |
+
"step": 1075
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.54,
|
1303 |
+
"learning_rate": 4.856866834687323e-05,
|
1304 |
+
"loss": 2.507,
|
1305 |
+
"step": 1080
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.54,
|
1309 |
+
"learning_rate": 4.855548955571183e-05,
|
1310 |
+
"loss": 3.0315,
|
1311 |
+
"step": 1085
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.55,
|
1315 |
+
"learning_rate": 4.8542252175950244e-05,
|
1316 |
+
"loss": 2.75,
|
1317 |
+
"step": 1090
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 0.55,
|
1321 |
+
"learning_rate": 4.852895624051326e-05,
|
1322 |
+
"loss": 2.6794,
|
1323 |
+
"step": 1095
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 0.55,
|
1327 |
+
"learning_rate": 4.851560178247132e-05,
|
1328 |
+
"loss": 2.8278,
|
1329 |
+
"step": 1100
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.55,
|
1333 |
+
"learning_rate": 4.850218883504041e-05,
|
1334 |
+
"loss": 2.6993,
|
1335 |
+
"step": 1105
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 0.56,
|
1339 |
+
"learning_rate": 4.8488717431582005e-05,
|
1340 |
+
"loss": 2.875,
|
1341 |
+
"step": 1110
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.56,
|
1345 |
+
"learning_rate": 4.8475187605602974e-05,
|
1346 |
+
"loss": 2.6057,
|
1347 |
+
"step": 1115
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.56,
|
1351 |
+
"learning_rate": 4.84615993907555e-05,
|
1352 |
+
"loss": 2.847,
|
1353 |
+
"step": 1120
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.56,
|
1357 |
+
"learning_rate": 4.844795282083697e-05,
|
1358 |
+
"loss": 2.7652,
|
1359 |
+
"step": 1125
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.57,
|
1363 |
+
"learning_rate": 4.843424792978997e-05,
|
1364 |
+
"loss": 2.8128,
|
1365 |
+
"step": 1130
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 0.57,
|
1369 |
+
"learning_rate": 4.842048475170209e-05,
|
1370 |
+
"loss": 2.7077,
|
1371 |
+
"step": 1135
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.57,
|
1375 |
+
"learning_rate": 4.840666332080592e-05,
|
1376 |
+
"loss": 2.7081,
|
1377 |
+
"step": 1140
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 0.57,
|
1381 |
+
"learning_rate": 4.8392783671478934e-05,
|
1382 |
+
"loss": 2.6479,
|
1383 |
+
"step": 1145
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.58,
|
1387 |
+
"learning_rate": 4.837884583824342e-05,
|
1388 |
+
"loss": 2.667,
|
1389 |
+
"step": 1150
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.58,
|
1393 |
+
"learning_rate": 4.836484985576638e-05,
|
1394 |
+
"loss": 2.7514,
|
1395 |
+
"step": 1155
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.58,
|
1399 |
+
"learning_rate": 4.835079575885944e-05,
|
1400 |
+
"loss": 2.5058,
|
1401 |
+
"step": 1160
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 0.58,
|
1405 |
+
"learning_rate": 4.833668358247876e-05,
|
1406 |
+
"loss": 2.6183,
|
1407 |
+
"step": 1165
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 0.59,
|
1411 |
+
"learning_rate": 4.8322513361725006e-05,
|
1412 |
+
"loss": 2.9959,
|
1413 |
+
"step": 1170
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.59,
|
1417 |
+
"learning_rate": 4.830828513184317e-05,
|
1418 |
+
"loss": 2.5714,
|
1419 |
+
"step": 1175
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.59,
|
1423 |
+
"learning_rate": 4.8293998928222536e-05,
|
1424 |
+
"loss": 2.965,
|
1425 |
+
"step": 1180
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.59,
|
1429 |
+
"learning_rate": 4.827965478639661e-05,
|
1430 |
+
"loss": 2.2106,
|
1431 |
+
"step": 1185
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.6,
|
1435 |
+
"learning_rate": 4.8265252742042965e-05,
|
1436 |
+
"loss": 2.7456,
|
1437 |
+
"step": 1190
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.6,
|
1441 |
+
"learning_rate": 4.8250792830983225e-05,
|
1442 |
+
"loss": 2.5694,
|
1443 |
+
"step": 1195
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 0.6,
|
1447 |
+
"learning_rate": 4.8236275089182936e-05,
|
1448 |
+
"loss": 2.6826,
|
1449 |
+
"step": 1200
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.6,
|
1453 |
+
"learning_rate": 4.8221699552751465e-05,
|
1454 |
+
"loss": 2.878,
|
1455 |
+
"step": 1205
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 0.61,
|
1459 |
+
"learning_rate": 4.820706625794196e-05,
|
1460 |
+
"loss": 2.8191,
|
1461 |
+
"step": 1210
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 0.61,
|
1465 |
+
"learning_rate": 4.81923752411512e-05,
|
1466 |
+
"loss": 2.739,
|
1467 |
+
"step": 1215
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.61,
|
1471 |
+
"learning_rate": 4.8177626538919565e-05,
|
1472 |
+
"loss": 3.0544,
|
1473 |
+
"step": 1220
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.61,
|
1477 |
+
"learning_rate": 4.8162820187930875e-05,
|
1478 |
+
"loss": 2.8393,
|
1479 |
+
"step": 1225
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.62,
|
1483 |
+
"learning_rate": 4.814795622501237e-05,
|
1484 |
+
"loss": 2.4457,
|
1485 |
+
"step": 1230
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 0.62,
|
1489 |
+
"learning_rate": 4.813303468713456e-05,
|
1490 |
+
"loss": 2.8575,
|
1491 |
+
"step": 1235
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 0.62,
|
1495 |
+
"learning_rate": 4.8118055611411197e-05,
|
1496 |
+
"loss": 2.8307,
|
1497 |
+
"step": 1240
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 0.62,
|
1501 |
+
"learning_rate": 4.810301903509909e-05,
|
1502 |
+
"loss": 2.7951,
|
1503 |
+
"step": 1245
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 0.63,
|
1507 |
+
"learning_rate": 4.8087924995598125e-05,
|
1508 |
+
"loss": 2.8456,
|
1509 |
+
"step": 1250
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.63,
|
1513 |
+
"learning_rate": 4.807277353045106e-05,
|
1514 |
+
"loss": 2.3564,
|
1515 |
+
"step": 1255
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.63,
|
1519 |
+
"learning_rate": 4.8057564677343524e-05,
|
1520 |
+
"loss": 2.5076,
|
1521 |
+
"step": 1260
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.63,
|
1525 |
+
"learning_rate": 4.8042298474103884e-05,
|
1526 |
+
"loss": 2.605,
|
1527 |
+
"step": 1265
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 0.64,
|
1531 |
+
"learning_rate": 4.8026974958703116e-05,
|
1532 |
+
"loss": 2.4782,
|
1533 |
+
"step": 1270
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 0.64,
|
1537 |
+
"learning_rate": 4.8011594169254784e-05,
|
1538 |
+
"loss": 2.7193,
|
1539 |
+
"step": 1275
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.64,
|
1543 |
+
"learning_rate": 4.799615614401488e-05,
|
1544 |
+
"loss": 2.8284,
|
1545 |
+
"step": 1280
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 0.64,
|
1549 |
+
"learning_rate": 4.798066092138178e-05,
|
1550 |
+
"loss": 2.5378,
|
1551 |
+
"step": 1285
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.65,
|
1555 |
+
"learning_rate": 4.796510853989612e-05,
|
1556 |
+
"loss": 2.7396,
|
1557 |
+
"step": 1290
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.65,
|
1561 |
+
"learning_rate": 4.794949903824069e-05,
|
1562 |
+
"loss": 2.7948,
|
1563 |
+
"step": 1295
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.65,
|
1567 |
+
"learning_rate": 4.793383245524035e-05,
|
1568 |
+
"loss": 2.7818,
|
1569 |
+
"step": 1300
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.65,
|
1573 |
+
"learning_rate": 4.791810882986197e-05,
|
1574 |
+
"loss": 2.7334,
|
1575 |
+
"step": 1305
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 0.66,
|
1579 |
+
"learning_rate": 4.7902328201214256e-05,
|
1580 |
+
"loss": 2.4824,
|
1581 |
+
"step": 1310
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 0.66,
|
1585 |
+
"learning_rate": 4.7886490608547727e-05,
|
1586 |
+
"loss": 2.6131,
|
1587 |
+
"step": 1315
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 0.66,
|
1591 |
+
"learning_rate": 4.7870596091254584e-05,
|
1592 |
+
"loss": 2.7778,
|
1593 |
+
"step": 1320
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.66,
|
1597 |
+
"learning_rate": 4.7854644688868594e-05,
|
1598 |
+
"loss": 2.5263,
|
1599 |
+
"step": 1325
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.67,
|
1603 |
+
"learning_rate": 4.783863644106502e-05,
|
1604 |
+
"loss": 2.7825,
|
1605 |
+
"step": 1330
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.67,
|
1609 |
+
"learning_rate": 4.782257138766053e-05,
|
1610 |
+
"loss": 2.7902,
|
1611 |
+
"step": 1335
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 0.67,
|
1615 |
+
"learning_rate": 4.7806449568613066e-05,
|
1616 |
+
"loss": 2.8333,
|
1617 |
+
"step": 1340
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 0.67,
|
1621 |
+
"learning_rate": 4.779027102402177e-05,
|
1622 |
+
"loss": 2.856,
|
1623 |
+
"step": 1345
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 0.68,
|
1627 |
+
"learning_rate": 4.777403579412686e-05,
|
1628 |
+
"loss": 2.8021,
|
1629 |
+
"step": 1350
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.68,
|
1633 |
+
"learning_rate": 4.775774391930956e-05,
|
1634 |
+
"loss": 2.6639,
|
1635 |
+
"step": 1355
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.68,
|
1639 |
+
"learning_rate": 4.7741395440091976e-05,
|
1640 |
+
"loss": 2.5226,
|
1641 |
+
"step": 1360
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.68,
|
1645 |
+
"learning_rate": 4.772499039713702e-05,
|
1646 |
+
"loss": 2.6803,
|
1647 |
+
"step": 1365
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.69,
|
1651 |
+
"learning_rate": 4.7708528831248274e-05,
|
1652 |
+
"loss": 2.4608,
|
1653 |
+
"step": 1370
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 0.69,
|
1657 |
+
"learning_rate": 4.769201078336991e-05,
|
1658 |
+
"loss": 2.786,
|
1659 |
+
"step": 1375
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.69,
|
1663 |
+
"learning_rate": 4.7675436294586586e-05,
|
1664 |
+
"loss": 2.8294,
|
1665 |
+
"step": 1380
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.7,
|
1669 |
+
"learning_rate": 4.7658805406123356e-05,
|
1670 |
+
"loss": 2.6776,
|
1671 |
+
"step": 1385
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 0.7,
|
1675 |
+
"learning_rate": 4.7642118159345544e-05,
|
1676 |
+
"loss": 2.8003,
|
1677 |
+
"step": 1390
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.7,
|
1681 |
+
"learning_rate": 4.762537459575865e-05,
|
1682 |
+
"loss": 2.7796,
|
1683 |
+
"step": 1395
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.7,
|
1687 |
+
"learning_rate": 4.7608574757008245e-05,
|
1688 |
+
"loss": 2.9156,
|
1689 |
+
"step": 1400
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.71,
|
1693 |
+
"learning_rate": 4.7591718684879883e-05,
|
1694 |
+
"loss": 3.0521,
|
1695 |
+
"step": 1405
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 0.71,
|
1699 |
+
"learning_rate": 4.7574806421298976e-05,
|
1700 |
+
"loss": 2.6469,
|
1701 |
+
"step": 1410
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 0.71,
|
1705 |
+
"learning_rate": 4.755783800833071e-05,
|
1706 |
+
"loss": 2.8512,
|
1707 |
+
"step": 1415
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.71,
|
1711 |
+
"learning_rate": 4.754081348817991e-05,
|
1712 |
+
"loss": 2.66,
|
1713 |
+
"step": 1420
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 0.72,
|
1717 |
+
"learning_rate": 4.752373290319096e-05,
|
1718 |
+
"loss": 2.6625,
|
1719 |
+
"step": 1425
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.72,
|
1723 |
+
"learning_rate": 4.7506596295847716e-05,
|
1724 |
+
"loss": 2.6711,
|
1725 |
+
"step": 1430
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.72,
|
1729 |
+
"learning_rate": 4.7489403708773346e-05,
|
1730 |
+
"loss": 2.8951,
|
1731 |
+
"step": 1435
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.72,
|
1735 |
+
"learning_rate": 4.747215518473026e-05,
|
1736 |
+
"loss": 2.7375,
|
1737 |
+
"step": 1440
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 0.73,
|
1741 |
+
"learning_rate": 4.745485076662e-05,
|
1742 |
+
"loss": 2.8037,
|
1743 |
+
"step": 1445
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 0.73,
|
1747 |
+
"learning_rate": 4.743749049748315e-05,
|
1748 |
+
"loss": 2.5375,
|
1749 |
+
"step": 1450
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.73,
|
1753 |
+
"learning_rate": 4.742007442049918e-05,
|
1754 |
+
"loss": 2.7664,
|
1755 |
+
"step": 1455
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 0.73,
|
1759 |
+
"learning_rate": 4.7402602578986374e-05,
|
1760 |
+
"loss": 2.9644,
|
1761 |
+
"step": 1460
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.74,
|
1765 |
+
"learning_rate": 4.738507501640175e-05,
|
1766 |
+
"loss": 2.8212,
|
1767 |
+
"step": 1465
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.74,
|
1771 |
+
"learning_rate": 4.736749177634087e-05,
|
1772 |
+
"loss": 2.7201,
|
1773 |
+
"step": 1470
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.74,
|
1777 |
+
"learning_rate": 4.734985290253782e-05,
|
1778 |
+
"loss": 2.7087,
|
1779 |
+
"step": 1475
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.74,
|
1783 |
+
"learning_rate": 4.7332158438865035e-05,
|
1784 |
+
"loss": 2.5502,
|
1785 |
+
"step": 1480
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 0.75,
|
1789 |
+
"learning_rate": 4.731440842933322e-05,
|
1790 |
+
"loss": 2.7607,
|
1791 |
+
"step": 1485
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.75,
|
1795 |
+
"learning_rate": 4.729660291809126e-05,
|
1796 |
+
"loss": 2.5601,
|
1797 |
+
"step": 1490
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 0.75,
|
1801 |
+
"learning_rate": 4.727874194942606e-05,
|
1802 |
+
"loss": 2.5562,
|
1803 |
+
"step": 1495
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.75,
|
1807 |
+
"learning_rate": 4.7260825567762486e-05,
|
1808 |
+
"loss": 2.5539,
|
1809 |
+
"step": 1500
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.76,
|
1813 |
+
"learning_rate": 4.7242853817663204e-05,
|
1814 |
+
"loss": 2.6405,
|
1815 |
+
"step": 1505
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.76,
|
1819 |
+
"learning_rate": 4.72248267438286e-05,
|
1820 |
+
"loss": 2.9237,
|
1821 |
+
"step": 1510
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 0.76,
|
1825 |
+
"learning_rate": 4.72067443910967e-05,
|
1826 |
+
"loss": 3.0453,
|
1827 |
+
"step": 1515
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 0.76,
|
1831 |
+
"learning_rate": 4.718860680444297e-05,
|
1832 |
+
"loss": 2.7176,
|
1833 |
+
"step": 1520
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 0.77,
|
1837 |
+
"learning_rate": 4.71704140289803e-05,
|
1838 |
+
"loss": 2.6713,
|
1839 |
+
"step": 1525
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.77,
|
1843 |
+
"learning_rate": 4.715216610995883e-05,
|
1844 |
+
"loss": 2.7284,
|
1845 |
+
"step": 1530
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.77,
|
1849 |
+
"learning_rate": 4.713386309276585e-05,
|
1850 |
+
"loss": 2.5022,
|
1851 |
+
"step": 1535
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 0.77,
|
1855 |
+
"learning_rate": 4.7115505022925706e-05,
|
1856 |
+
"loss": 2.8323,
|
1857 |
+
"step": 1540
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.78,
|
1861 |
+
"learning_rate": 4.7097091946099666e-05,
|
1862 |
+
"loss": 2.7005,
|
1863 |
+
"step": 1545
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 0.78,
|
1867 |
+
"learning_rate": 4.7078623908085825e-05,
|
1868 |
+
"loss": 2.8142,
|
1869 |
+
"step": 1550
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.78,
|
1873 |
+
"learning_rate": 4.7060100954818974e-05,
|
1874 |
+
"loss": 2.8505,
|
1875 |
+
"step": 1555
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 0.78,
|
1879 |
+
"learning_rate": 4.70415231323705e-05,
|
1880 |
+
"loss": 2.5892,
|
1881 |
+
"step": 1560
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 0.79,
|
1885 |
+
"learning_rate": 4.7022890486948236e-05,
|
1886 |
+
"loss": 2.8951,
|
1887 |
+
"step": 1565
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.79,
|
1891 |
+
"learning_rate": 4.700420306489641e-05,
|
1892 |
+
"loss": 2.7551,
|
1893 |
+
"step": 1570
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 0.79,
|
1897 |
+
"learning_rate": 4.698546091269547e-05,
|
1898 |
+
"loss": 2.6814,
|
1899 |
+
"step": 1575
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.79,
|
1903 |
+
"learning_rate": 4.696666407696201e-05,
|
1904 |
+
"loss": 2.8698,
|
1905 |
+
"step": 1580
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 0.8,
|
1909 |
+
"learning_rate": 4.694781260444862e-05,
|
1910 |
+
"loss": 2.8389,
|
1911 |
+
"step": 1585
|
1912 |
+
},
|
1913 |
+
{
|
1914 |
+
"epoch": 0.8,
|
1915 |
+
"learning_rate": 4.6928906542043786e-05,
|
1916 |
+
"loss": 2.8353,
|
1917 |
+
"step": 1590
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 0.8,
|
1921 |
+
"learning_rate": 4.690994593677179e-05,
|
1922 |
+
"loss": 2.6565,
|
1923 |
+
"step": 1595
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 0.8,
|
1927 |
+
"learning_rate": 4.689093083579256e-05,
|
1928 |
+
"loss": 2.6958,
|
1929 |
+
"step": 1600
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.81,
|
1933 |
+
"learning_rate": 4.687186128640157e-05,
|
1934 |
+
"loss": 2.6768,
|
1935 |
+
"step": 1605
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 0.81,
|
1939 |
+
"learning_rate": 4.685273733602975e-05,
|
1940 |
+
"loss": 2.734,
|
1941 |
+
"step": 1610
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.81,
|
1945 |
+
"learning_rate": 4.6833559032243284e-05,
|
1946 |
+
"loss": 2.5348,
|
1947 |
+
"step": 1615
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 0.81,
|
1951 |
+
"learning_rate": 4.6814326422743594e-05,
|
1952 |
+
"loss": 2.7775,
|
1953 |
+
"step": 1620
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 0.82,
|
1957 |
+
"learning_rate": 4.679503955536715e-05,
|
1958 |
+
"loss": 2.6578,
|
1959 |
+
"step": 1625
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.82,
|
1963 |
+
"learning_rate": 4.6775698478085393e-05,
|
1964 |
+
"loss": 2.8792,
|
1965 |
+
"step": 1630
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 0.82,
|
1969 |
+
"learning_rate": 4.675630323900458e-05,
|
1970 |
+
"loss": 2.7883,
|
1971 |
+
"step": 1635
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.82,
|
1975 |
+
"learning_rate": 4.67368538863657e-05,
|
1976 |
+
"loss": 2.8824,
|
1977 |
+
"step": 1640
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 0.83,
|
1981 |
+
"learning_rate": 4.671735046854433e-05,
|
1982 |
+
"loss": 2.6775,
|
1983 |
+
"step": 1645
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.83,
|
1987 |
+
"learning_rate": 4.669779303405051e-05,
|
1988 |
+
"loss": 2.5658,
|
1989 |
+
"step": 1650
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 0.83,
|
1993 |
+
"learning_rate": 4.667818163152864e-05,
|
1994 |
+
"loss": 2.5262,
|
1995 |
+
"step": 1655
|
1996 |
+
},
|
1997 |
+
{
|
1998 |
+
"epoch": 0.83,
|
1999 |
+
"learning_rate": 4.665851630975736e-05,
|
2000 |
+
"loss": 2.5749,
|
2001 |
+
"step": 1660
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 0.84,
|
2005 |
+
"learning_rate": 4.6638797117649424e-05,
|
2006 |
+
"loss": 2.8718,
|
2007 |
+
"step": 1665
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 0.84,
|
2011 |
+
"learning_rate": 4.661902410425155e-05,
|
2012 |
+
"loss": 2.8039,
|
2013 |
+
"step": 1670
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 0.84,
|
2017 |
+
"learning_rate": 4.659919731874435e-05,
|
2018 |
+
"loss": 2.8089,
|
2019 |
+
"step": 1675
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.84,
|
2023 |
+
"learning_rate": 4.6579316810442174e-05,
|
2024 |
+
"loss": 2.8144,
|
2025 |
+
"step": 1680
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.85,
|
2029 |
+
"learning_rate": 4.6559382628792995e-05,
|
2030 |
+
"loss": 2.5963,
|
2031 |
+
"step": 1685
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 0.85,
|
2035 |
+
"learning_rate": 4.653939482337828e-05,
|
2036 |
+
"loss": 2.5755,
|
2037 |
+
"step": 1690
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 0.85,
|
2041 |
+
"learning_rate": 4.651935344391286e-05,
|
2042 |
+
"loss": 2.7631,
|
2043 |
+
"step": 1695
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 0.85,
|
2047 |
+
"learning_rate": 4.649925854024486e-05,
|
2048 |
+
"loss": 2.8117,
|
2049 |
+
"step": 1700
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 0.86,
|
2053 |
+
"learning_rate": 4.647911016235549e-05,
|
2054 |
+
"loss": 2.7352,
|
2055 |
+
"step": 1705
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 0.86,
|
2059 |
+
"learning_rate": 4.6458908360358985e-05,
|
2060 |
+
"loss": 2.5572,
|
2061 |
+
"step": 1710
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 0.86,
|
2065 |
+
"learning_rate": 4.643865318450246e-05,
|
2066 |
+
"loss": 2.8372,
|
2067 |
+
"step": 1715
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.86,
|
2071 |
+
"learning_rate": 4.6418344685165774e-05,
|
2072 |
+
"loss": 2.7892,
|
2073 |
+
"step": 1720
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 0.87,
|
2077 |
+
"learning_rate": 4.639798291286143e-05,
|
2078 |
+
"loss": 2.7832,
|
2079 |
+
"step": 1725
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 0.87,
|
2083 |
+
"learning_rate": 4.637756791823442e-05,
|
2084 |
+
"loss": 2.5401,
|
2085 |
+
"step": 1730
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 0.87,
|
2089 |
+
"learning_rate": 4.635709975206213e-05,
|
2090 |
+
"loss": 2.9286,
|
2091 |
+
"step": 1735
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 0.87,
|
2095 |
+
"learning_rate": 4.633657846525417e-05,
|
2096 |
+
"loss": 2.6474,
|
2097 |
+
"step": 1740
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 0.88,
|
2101 |
+
"learning_rate": 4.6316004108852305e-05,
|
2102 |
+
"loss": 2.5047,
|
2103 |
+
"step": 1745
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 0.88,
|
2107 |
+
"learning_rate": 4.629537673403029e-05,
|
2108 |
+
"loss": 2.8374,
|
2109 |
+
"step": 1750
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.88,
|
2113 |
+
"learning_rate": 4.627469639209373e-05,
|
2114 |
+
"loss": 2.634,
|
2115 |
+
"step": 1755
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 0.88,
|
2119 |
+
"learning_rate": 4.6253963134480006e-05,
|
2120 |
+
"loss": 2.6884,
|
2121 |
+
"step": 1760
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 0.89,
|
2125 |
+
"learning_rate": 4.623317701275809e-05,
|
2126 |
+
"loss": 2.6334,
|
2127 |
+
"step": 1765
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 0.89,
|
2131 |
+
"learning_rate": 4.621233807862844e-05,
|
2132 |
+
"loss": 2.764,
|
2133 |
+
"step": 1770
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 0.89,
|
2137 |
+
"learning_rate": 4.6191446383922886e-05,
|
2138 |
+
"loss": 3.0864,
|
2139 |
+
"step": 1775
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 0.89,
|
2143 |
+
"learning_rate": 4.617050198060448e-05,
|
2144 |
+
"loss": 2.7964,
|
2145 |
+
"step": 1780
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 0.9,
|
2149 |
+
"learning_rate": 4.6149504920767376e-05,
|
2150 |
+
"loss": 2.4538,
|
2151 |
+
"step": 1785
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.9,
|
2155 |
+
"learning_rate": 4.6128455256636706e-05,
|
2156 |
+
"loss": 2.7352,
|
2157 |
+
"step": 1790
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 0.9,
|
2161 |
+
"learning_rate": 4.6107353040568416e-05,
|
2162 |
+
"loss": 2.6893,
|
2163 |
+
"step": 1795
|
2164 |
+
},
|
2165 |
+
{
|
2166 |
+
"epoch": 0.9,
|
2167 |
+
"learning_rate": 4.6086198325049185e-05,
|
2168 |
+
"loss": 2.8609,
|
2169 |
+
"step": 1800
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 0.91,
|
2173 |
+
"learning_rate": 4.6064991162696275e-05,
|
2174 |
+
"loss": 2.5285,
|
2175 |
+
"step": 1805
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"epoch": 0.91,
|
2179 |
+
"learning_rate": 4.604373160625739e-05,
|
2180 |
+
"loss": 2.5707,
|
2181 |
+
"step": 1810
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 0.91,
|
2185 |
+
"learning_rate": 4.602241970861053e-05,
|
2186 |
+
"loss": 2.7198,
|
2187 |
+
"step": 1815
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 0.91,
|
2191 |
+
"learning_rate": 4.6001055522763926e-05,
|
2192 |
+
"loss": 2.855,
|
2193 |
+
"step": 1820
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.92,
|
2197 |
+
"learning_rate": 4.597963910185582e-05,
|
2198 |
+
"loss": 2.4175,
|
2199 |
+
"step": 1825
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 0.92,
|
2203 |
+
"learning_rate": 4.595817049915441e-05,
|
2204 |
+
"loss": 2.5444,
|
2205 |
+
"step": 1830
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 0.92,
|
2209 |
+
"learning_rate": 4.5936649768057646e-05,
|
2210 |
+
"loss": 2.6893,
|
2211 |
+
"step": 1835
|
2212 |
+
},
|
2213 |
+
{
|
2214 |
+
"epoch": 0.92,
|
2215 |
+
"learning_rate": 4.591507696209318e-05,
|
2216 |
+
"loss": 2.6725,
|
2217 |
+
"step": 1840
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 0.93,
|
2221 |
+
"learning_rate": 4.589345213491817e-05,
|
2222 |
+
"loss": 2.834,
|
2223 |
+
"step": 1845
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 0.93,
|
2227 |
+
"learning_rate": 4.587177534031914e-05,
|
2228 |
+
"loss": 2.8259,
|
2229 |
+
"step": 1850
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 0.93,
|
2233 |
+
"learning_rate": 4.585004663221188e-05,
|
2234 |
+
"loss": 2.6146,
|
2235 |
+
"step": 1855
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.93,
|
2239 |
+
"learning_rate": 4.582826606464134e-05,
|
2240 |
+
"loss": 2.4673,
|
2241 |
+
"step": 1860
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 0.94,
|
2245 |
+
"learning_rate": 4.5806433691781416e-05,
|
2246 |
+
"loss": 2.9178,
|
2247 |
+
"step": 1865
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 0.94,
|
2251 |
+
"learning_rate": 4.578454956793487e-05,
|
2252 |
+
"loss": 2.9224,
|
2253 |
+
"step": 1870
|
2254 |
+
},
|
2255 |
+
{
|
2256 |
+
"epoch": 0.94,
|
2257 |
+
"learning_rate": 4.576261374753318e-05,
|
2258 |
+
"loss": 2.7987,
|
2259 |
+
"step": 1875
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 0.94,
|
2263 |
+
"learning_rate": 4.574062628513642e-05,
|
2264 |
+
"loss": 2.3848,
|
2265 |
+
"step": 1880
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 0.95,
|
2269 |
+
"learning_rate": 4.57185872354331e-05,
|
2270 |
+
"loss": 2.6054,
|
2271 |
+
"step": 1885
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 0.95,
|
2275 |
+
"learning_rate": 4.569649665324003e-05,
|
2276 |
+
"loss": 2.6743,
|
2277 |
+
"step": 1890
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.95,
|
2281 |
+
"learning_rate": 4.567435459350222e-05,
|
2282 |
+
"loss": 2.9375,
|
2283 |
+
"step": 1895
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 0.95,
|
2287 |
+
"learning_rate": 4.565216111129269e-05,
|
2288 |
+
"loss": 2.9372,
|
2289 |
+
"step": 1900
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 0.96,
|
2293 |
+
"learning_rate": 4.562991626181239e-05,
|
2294 |
+
"loss": 2.669,
|
2295 |
+
"step": 1905
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 0.96,
|
2299 |
+
"learning_rate": 4.560762010039001e-05,
|
2300 |
+
"loss": 2.7644,
|
2301 |
+
"step": 1910
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"epoch": 0.96,
|
2305 |
+
"learning_rate": 4.558527268248187e-05,
|
2306 |
+
"loss": 2.6886,
|
2307 |
+
"step": 1915
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 0.96,
|
2311 |
+
"learning_rate": 4.55628740636718e-05,
|
2312 |
+
"loss": 2.8618,
|
2313 |
+
"step": 1920
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.97,
|
2317 |
+
"learning_rate": 4.554042429967095e-05,
|
2318 |
+
"loss": 2.8411,
|
2319 |
+
"step": 1925
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.97,
|
2323 |
+
"learning_rate": 4.55179234463177e-05,
|
2324 |
+
"loss": 2.6047,
|
2325 |
+
"step": 1930
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 0.97,
|
2329 |
+
"learning_rate": 4.5495371559577496e-05,
|
2330 |
+
"loss": 2.8675,
|
2331 |
+
"step": 1935
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 0.97,
|
2335 |
+
"learning_rate": 4.547276869554271e-05,
|
2336 |
+
"loss": 2.751,
|
2337 |
+
"step": 1940
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 0.98,
|
2341 |
+
"learning_rate": 4.545011491043253e-05,
|
2342 |
+
"loss": 2.8638,
|
2343 |
+
"step": 1945
|
2344 |
+
},
|
2345 |
+
{
|
2346 |
+
"epoch": 0.98,
|
2347 |
+
"learning_rate": 4.5427410260592775e-05,
|
2348 |
+
"loss": 2.5092,
|
2349 |
+
"step": 1950
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 0.98,
|
2353 |
+
"learning_rate": 4.540465480249579e-05,
|
2354 |
+
"loss": 2.5059,
|
2355 |
+
"step": 1955
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 0.98,
|
2359 |
+
"learning_rate": 4.5381848592740285e-05,
|
2360 |
+
"loss": 2.9433,
|
2361 |
+
"step": 1960
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 0.99,
|
2365 |
+
"learning_rate": 4.535899168805121e-05,
|
2366 |
+
"loss": 2.6959,
|
2367 |
+
"step": 1965
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 0.99,
|
2371 |
+
"learning_rate": 4.533608414527961e-05,
|
2372 |
+
"loss": 2.552,
|
2373 |
+
"step": 1970
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 0.99,
|
2377 |
+
"learning_rate": 4.5313126021402465e-05,
|
2378 |
+
"loss": 2.7169,
|
2379 |
+
"step": 1975
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 0.99,
|
2383 |
+
"learning_rate": 4.529011737352258e-05,
|
2384 |
+
"loss": 2.5672,
|
2385 |
+
"step": 1980
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 1.0,
|
2389 |
+
"learning_rate": 4.526705825886841e-05,
|
2390 |
+
"loss": 2.6434,
|
2391 |
+
"step": 1985
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 1.0,
|
2395 |
+
"learning_rate": 4.5243948734793947e-05,
|
2396 |
+
"loss": 2.8062,
|
2397 |
+
"step": 1990
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 1.0,
|
2401 |
+
"learning_rate": 4.5220788858778556e-05,
|
2402 |
+
"loss": 2.6929,
|
2403 |
+
"step": 1995
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 1.0,
|
2407 |
+
"learning_rate": 4.519757868842684e-05,
|
2408 |
+
"loss": 2.5837,
|
2409 |
+
"step": 2000
|
2410 |
+
}
|
2411 |
+
],
|
2412 |
+
"logging_steps": 5,
|
2413 |
+
"max_steps": 9960,
|
2414 |
+
"num_input_tokens_seen": 0,
|
2415 |
+
"num_train_epochs": 5,
|
2416 |
+
"save_steps": 500,
|
2417 |
+
"total_flos": 1.0586878161626726e+17,
|
2418 |
+
"train_batch_size": 1,
|
2419 |
+
"trial_name": null,
|
2420 |
+
"trial_params": null
|
2421 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:939ee45e9035366dc4952c5158e7d3a0d3426acdbfb5014d53ad1e260b19a19f
|
3 |
+
size 4475
|
checkpoint-2500/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chatglm3-6b-base
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-2500/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chatglm3-6b-base",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"query_key_value"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM",
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
checkpoint-2500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d40bc7150f5ecf32de16baf18217bae81b4927e8bfdd73a03a697fb34ae256da
|
3 |
+
size 7807744
|
checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ea1db76a2f24e5349ca56065395a53258d6acb5f690b358d35067da24c96f32
|
3 |
+
size 15644485
|
checkpoint-2500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0423f88bd1e68d212dffb01bfbbae16c786b716d88f4e45eb7c085b41fde4a35
|
3 |
+
size 14575
|
checkpoint-2500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24559f8836de5461d15dc4bbc244e10bf347c0266d3ef00c7465dff3b9068e19
|
3 |
+
size 627
|
checkpoint-2500/special_tokens_map.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|user|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|observation|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
]
|
18 |
+
}
|
checkpoint-2500/tokenization_chatglm.py
ADDED
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import json
|
2 |
+
import os
|
3 |
+
import re
|
4 |
+
from typing import List, Optional, Union, Dict
|
5 |
+
from sentencepiece import SentencePieceProcessor
|
6 |
+
from transformers import PreTrainedTokenizer
|
7 |
+
from transformers.utils import logging, PaddingStrategy
|
8 |
+
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
|
9 |
+
|
10 |
+
|
11 |
+
class SPTokenizer:
|
12 |
+
def __init__(self, model_path: str):
|
13 |
+
# reload tokenizer
|
14 |
+
assert os.path.isfile(model_path), model_path
|
15 |
+
self.sp_model = SentencePieceProcessor(model_file=model_path)
|
16 |
+
|
17 |
+
# BOS / EOS token IDs
|
18 |
+
self.n_words: int = self.sp_model.vocab_size()
|
19 |
+
self.bos_id: int = self.sp_model.bos_id()
|
20 |
+
self.eos_id: int = self.sp_model.eos_id()
|
21 |
+
self.pad_id: int = self.sp_model.unk_id()
|
22 |
+
assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
|
23 |
+
|
24 |
+
role_special_tokens = ["<|system|>", "<|user|>", "<|assistant|>", "<|observation|>"]
|
25 |
+
special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"] + role_special_tokens
|
26 |
+
self.special_tokens = {}
|
27 |
+
self.index_special_tokens = {}
|
28 |
+
for token in special_tokens:
|
29 |
+
self.special_tokens[token] = self.n_words
|
30 |
+
self.index_special_tokens[self.n_words] = token
|
31 |
+
self.n_words += 1
|
32 |
+
self.role_special_token_expression = "|".join([re.escape(token) for token in role_special_tokens])
|
33 |
+
|
34 |
+
def tokenize(self, s: str, encode_special_tokens=False):
|
35 |
+
if encode_special_tokens:
|
36 |
+
last_index = 0
|
37 |
+
t = []
|
38 |
+
for match in re.finditer(self.role_special_token_expression, s):
|
39 |
+
if last_index < match.start():
|
40 |
+
t.extend(self.sp_model.EncodeAsPieces(s[last_index:match.start()]))
|
41 |
+
t.append(s[match.start():match.end()])
|
42 |
+
last_index = match.end()
|
43 |
+
if last_index < len(s):
|
44 |
+
t.extend(self.sp_model.EncodeAsPieces(s[last_index:]))
|
45 |
+
return t
|
46 |
+
else:
|
47 |
+
return self.sp_model.EncodeAsPieces(s)
|
48 |
+
|
49 |
+
def encode(self, s: str, bos: bool = False, eos: bool = False) -> List[int]:
|
50 |
+
assert type(s) is str
|
51 |
+
t = self.sp_model.encode(s)
|
52 |
+
if bos:
|
53 |
+
t = [self.bos_id] + t
|
54 |
+
if eos:
|
55 |
+
t = t + [self.eos_id]
|
56 |
+
return t
|
57 |
+
|
58 |
+
def decode(self, t: List[int]) -> str:
|
59 |
+
text, buffer = "", []
|
60 |
+
for token in t:
|
61 |
+
if token in self.index_special_tokens:
|
62 |
+
if buffer:
|
63 |
+
text += self.sp_model.decode(buffer)
|
64 |
+
buffer = []
|
65 |
+
text += self.index_special_tokens[token]
|
66 |
+
else:
|
67 |
+
buffer.append(token)
|
68 |
+
if buffer:
|
69 |
+
text += self.sp_model.decode(buffer)
|
70 |
+
return text
|
71 |
+
|
72 |
+
def decode_tokens(self, tokens: List[str]) -> str:
|
73 |
+
text = self.sp_model.DecodePieces(tokens)
|
74 |
+
return text
|
75 |
+
|
76 |
+
def convert_token_to_id(self, token):
|
77 |
+
""" Converts a token (str) in an id using the vocab. """
|
78 |
+
if token in self.special_tokens:
|
79 |
+
return self.special_tokens[token]
|
80 |
+
return self.sp_model.PieceToId(token)
|
81 |
+
|
82 |
+
def convert_id_to_token(self, index):
|
83 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
84 |
+
if index in self.index_special_tokens:
|
85 |
+
return self.index_special_tokens[index]
|
86 |
+
if index in [self.eos_id, self.bos_id, self.pad_id] or index < 0:
|
87 |
+
return ""
|
88 |
+
return self.sp_model.IdToPiece(index)
|
89 |
+
|
90 |
+
|
91 |
+
class ChatGLMTokenizer(PreTrainedTokenizer):
|
92 |
+
vocab_files_names = {"vocab_file": "tokenizer.model"}
|
93 |
+
|
94 |
+
model_input_names = ["input_ids", "attention_mask", "position_ids"]
|
95 |
+
|
96 |
+
def __init__(self, vocab_file, padding_side="left", clean_up_tokenization_spaces=False, encode_special_tokens=False,
|
97 |
+
**kwargs):
|
98 |
+
self.name = "GLMTokenizer"
|
99 |
+
|
100 |
+
self.vocab_file = vocab_file
|
101 |
+
self.tokenizer = SPTokenizer(vocab_file)
|
102 |
+
self.special_tokens = {
|
103 |
+
"<bos>": self.tokenizer.bos_id,
|
104 |
+
"<eos>": self.tokenizer.eos_id,
|
105 |
+
"<pad>": self.tokenizer.pad_id
|
106 |
+
}
|
107 |
+
self.encode_special_tokens = encode_special_tokens
|
108 |
+
super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
109 |
+
encode_special_tokens=encode_special_tokens,
|
110 |
+
**kwargs)
|
111 |
+
|
112 |
+
def get_command(self, token):
|
113 |
+
if token in self.special_tokens:
|
114 |
+
return self.special_tokens[token]
|
115 |
+
assert token in self.tokenizer.special_tokens, f"{token} is not a special token for {self.name}"
|
116 |
+
return self.tokenizer.special_tokens[token]
|
117 |
+
|
118 |
+
@property
|
119 |
+
def unk_token(self) -> str:
|
120 |
+
return "<unk>"
|
121 |
+
|
122 |
+
@property
|
123 |
+
def pad_token(self) -> str:
|
124 |
+
return "<unk>"
|
125 |
+
|
126 |
+
@property
|
127 |
+
def pad_token_id(self):
|
128 |
+
return self.get_command("<pad>")
|
129 |
+
|
130 |
+
@property
|
131 |
+
def eos_token(self) -> str:
|
132 |
+
return "</s>"
|
133 |
+
|
134 |
+
@property
|
135 |
+
def eos_token_id(self):
|
136 |
+
return self.get_command("<eos>")
|
137 |
+
|
138 |
+
@property
|
139 |
+
def vocab_size(self):
|
140 |
+
return self.tokenizer.n_words
|
141 |
+
|
142 |
+
def get_vocab(self):
|
143 |
+
""" Returns vocab as a dict """
|
144 |
+
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
145 |
+
vocab.update(self.added_tokens_encoder)
|
146 |
+
return vocab
|
147 |
+
|
148 |
+
def _tokenize(self, text, **kwargs):
|
149 |
+
return self.tokenizer.tokenize(text, encode_special_tokens=self.encode_special_tokens)
|
150 |
+
|
151 |
+
def _convert_token_to_id(self, token):
|
152 |
+
""" Converts a token (str) in an id using the vocab. """
|
153 |
+
return self.tokenizer.convert_token_to_id(token)
|
154 |
+
|
155 |
+
def _convert_id_to_token(self, index):
|
156 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
157 |
+
return self.tokenizer.convert_id_to_token(index)
|
158 |
+
|
159 |
+
def convert_tokens_to_string(self, tokens: List[str]) -> str:
|
160 |
+
return self.tokenizer.decode_tokens(tokens)
|
161 |
+
|
162 |
+
def save_vocabulary(self, save_directory, filename_prefix=None):
|
163 |
+
"""
|
164 |
+
Save the vocabulary and special tokens file to a directory.
|
165 |
+
|
166 |
+
Args:
|
167 |
+
save_directory (`str`):
|
168 |
+
The directory in which to save the vocabulary.
|
169 |
+
filename_prefix (`str`, *optional*):
|
170 |
+
An optional prefix to add to the named of the saved files.
|
171 |
+
|
172 |
+
Returns:
|
173 |
+
`Tuple(str)`: Paths to the files saved.
|
174 |
+
"""
|
175 |
+
if os.path.isdir(save_directory):
|
176 |
+
vocab_file = os.path.join(
|
177 |
+
save_directory, self.vocab_files_names["vocab_file"]
|
178 |
+
)
|
179 |
+
else:
|
180 |
+
vocab_file = save_directory
|
181 |
+
|
182 |
+
with open(self.vocab_file, 'rb') as fin:
|
183 |
+
proto_str = fin.read()
|
184 |
+
|
185 |
+
with open(vocab_file, "wb") as writer:
|
186 |
+
writer.write(proto_str)
|
187 |
+
|
188 |
+
return (vocab_file,)
|
189 |
+
|
190 |
+
def get_prefix_tokens(self):
|
191 |
+
prefix_tokens = [self.get_command("[gMASK]"), self.get_command("sop")]
|
192 |
+
return prefix_tokens
|
193 |
+
|
194 |
+
def build_single_message(self, role, metadata, message):
|
195 |
+
assert role in ["system", "user", "assistant", "observation"], role
|
196 |
+
role_tokens = [self.get_command(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n")
|
197 |
+
message_tokens = self.tokenizer.encode(message)
|
198 |
+
tokens = role_tokens + message_tokens
|
199 |
+
return tokens
|
200 |
+
|
201 |
+
def build_chat_input(self, query, history=None, role="user"):
|
202 |
+
if history is None:
|
203 |
+
history = []
|
204 |
+
input_ids = []
|
205 |
+
for item in history:
|
206 |
+
content = item["content"]
|
207 |
+
if item["role"] == "system" and "tools" in item:
|
208 |
+
content = content + "\n" + json.dumps(item["tools"], indent=4, ensure_ascii=False)
|
209 |
+
input_ids.extend(self.build_single_message(item["role"], item.get("metadata", ""), content))
|
210 |
+
input_ids.extend(self.build_single_message(role, "", query))
|
211 |
+
input_ids.extend([self.get_command("<|assistant|>")])
|
212 |
+
return self.batch_encode_plus([input_ids], return_tensors="pt", is_split_into_words=True)
|
213 |
+
|
214 |
+
def build_inputs_with_special_tokens(
|
215 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
216 |
+
) -> List[int]:
|
217 |
+
"""
|
218 |
+
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
|
219 |
+
adding special tokens. A BERT sequence has the following format:
|
220 |
+
|
221 |
+
- single sequence: `[CLS] X [SEP]`
|
222 |
+
- pair of sequences: `[CLS] A [SEP] B [SEP]`
|
223 |
+
|
224 |
+
Args:
|
225 |
+
token_ids_0 (`List[int]`):
|
226 |
+
List of IDs to which the special tokens will be added.
|
227 |
+
token_ids_1 (`List[int]`, *optional*):
|
228 |
+
Optional second list of IDs for sequence pairs.
|
229 |
+
|
230 |
+
Returns:
|
231 |
+
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
|
232 |
+
"""
|
233 |
+
prefix_tokens = self.get_prefix_tokens()
|
234 |
+
token_ids_0 = prefix_tokens + token_ids_0
|
235 |
+
if token_ids_1 is not None:
|
236 |
+
token_ids_0 = token_ids_0 + token_ids_1 + [self.get_command("<eos>")]
|
237 |
+
return token_ids_0
|
238 |
+
|
239 |
+
def _pad(
|
240 |
+
self,
|
241 |
+
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
|
242 |
+
max_length: Optional[int] = None,
|
243 |
+
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
244 |
+
pad_to_multiple_of: Optional[int] = None,
|
245 |
+
return_attention_mask: Optional[bool] = None,
|
246 |
+
) -> dict:
|
247 |
+
"""
|
248 |
+
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
|
249 |
+
|
250 |
+
Args:
|
251 |
+
encoded_inputs:
|
252 |
+
Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
|
253 |
+
max_length: maximum length of the returned list and optionally padding length (see below).
|
254 |
+
Will truncate by taking into account the special tokens.
|
255 |
+
padding_strategy: PaddingStrategy to use for padding.
|
256 |
+
|
257 |
+
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
|
258 |
+
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
|
259 |
+
- PaddingStrategy.DO_NOT_PAD: Do not pad
|
260 |
+
The tokenizer padding sides are defined in self.padding_side:
|
261 |
+
|
262 |
+
- 'left': pads on the left of the sequences
|
263 |
+
- 'right': pads on the right of the sequences
|
264 |
+
pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
|
265 |
+
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
|
266 |
+
`>= 7.5` (Volta).
|
267 |
+
return_attention_mask:
|
268 |
+
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
|
269 |
+
"""
|
270 |
+
# Load from model defaults
|
271 |
+
assert self.padding_side == "left"
|
272 |
+
|
273 |
+
required_input = encoded_inputs[self.model_input_names[0]]
|
274 |
+
seq_length = len(required_input)
|
275 |
+
|
276 |
+
if padding_strategy == PaddingStrategy.LONGEST:
|
277 |
+
max_length = len(required_input)
|
278 |
+
|
279 |
+
if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
|
280 |
+
max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
|
281 |
+
|
282 |
+
needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
|
283 |
+
|
284 |
+
# Initialize attention mask if not present.
|
285 |
+
if "attention_mask" not in encoded_inputs:
|
286 |
+
encoded_inputs["attention_mask"] = [1] * seq_length
|
287 |
+
|
288 |
+
if "position_ids" not in encoded_inputs:
|
289 |
+
encoded_inputs["position_ids"] = list(range(seq_length))
|
290 |
+
|
291 |
+
if needs_to_be_padded:
|
292 |
+
difference = max_length - len(required_input)
|
293 |
+
|
294 |
+
if "attention_mask" in encoded_inputs:
|
295 |
+
encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
|
296 |
+
if "position_ids" in encoded_inputs:
|
297 |
+
encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
|
298 |
+
encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
|
299 |
+
|
300 |
+
return encoded_inputs
|
checkpoint-2500/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
checkpoint-2500/tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"64795": {
|
4 |
+
"content": "<|user|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"64797": {
|
12 |
+
"content": "<|observation|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
}
|
19 |
+
},
|
20 |
+
"additional_special_tokens": [
|
21 |
+
"<|user|>",
|
22 |
+
"<|observation|>"
|
23 |
+
],
|
24 |
+
"auto_map": {
|
25 |
+
"AutoTokenizer": [
|
26 |
+
"tokenization_chatglm.ChatGLMTokenizer",
|
27 |
+
null
|
28 |
+
]
|
29 |
+
},
|
30 |
+
"clean_up_tokenization_spaces": false,
|
31 |
+
"do_lower_case": false,
|
32 |
+
"encode_special_tokens": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"remove_space": false,
|
38 |
+
"split_special_tokens": false,
|
39 |
+
"tokenizer_class": "ChatGLMTokenizer",
|
40 |
+
"unk_token": "<unk>"
|
41 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
@@ -0,0 +1,3021 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2545477355413372,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.9999980101927616e-05,
|
14 |
+
"loss": 3.2533,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4.99999204077421e-05,
|
20 |
+
"loss": 3.2279,
|
21 |
+
"step": 10
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 4.999978982687695e-05,
|
26 |
+
"loss": 3.193,
|
27 |
+
"step": 15
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 4.9999597065062966e-05,
|
32 |
+
"loss": 3.2863,
|
33 |
+
"step": 20
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 4.999934212277958e-05,
|
38 |
+
"loss": 3.1724,
|
39 |
+
"step": 25
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 4.999902500066093e-05,
|
44 |
+
"loss": 3.1088,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 4.999864569949576e-05,
|
50 |
+
"loss": 3.3241,
|
51 |
+
"step": 35
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 4.99982042202275e-05,
|
56 |
+
"loss": 3.1904,
|
57 |
+
"step": 40
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 4.999770056395421e-05,
|
62 |
+
"loss": 2.9254,
|
63 |
+
"step": 45
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 4.999713473192863e-05,
|
68 |
+
"loss": 3.1845,
|
69 |
+
"step": 50
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 4.999650672555812e-05,
|
74 |
+
"loss": 2.8475,
|
75 |
+
"step": 55
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 4.9995816546404695e-05,
|
80 |
+
"loss": 3.0486,
|
81 |
+
"step": 60
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 4.9995064196185014e-05,
|
86 |
+
"loss": 2.6464,
|
87 |
+
"step": 65
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 4.9994249676770364e-05,
|
92 |
+
"loss": 3.0446,
|
93 |
+
"step": 70
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 4.999337299018667e-05,
|
98 |
+
"loss": 3.375,
|
99 |
+
"step": 75
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 4.999243413861447e-05,
|
104 |
+
"loss": 2.8787,
|
105 |
+
"step": 80
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 4.999143312438893e-05,
|
110 |
+
"loss": 3.014,
|
111 |
+
"step": 85
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.05,
|
115 |
+
"learning_rate": 4.999036994999985e-05,
|
116 |
+
"loss": 2.8288,
|
117 |
+
"step": 90
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 4.9989244618091596e-05,
|
122 |
+
"loss": 3.1879,
|
123 |
+
"step": 95
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 4.998805713146317e-05,
|
128 |
+
"loss": 2.9749,
|
129 |
+
"step": 100
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 4.9986807493068165e-05,
|
134 |
+
"loss": 2.6304,
|
135 |
+
"step": 105
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06,
|
139 |
+
"learning_rate": 4.998549570601475e-05,
|
140 |
+
"loss": 2.943,
|
141 |
+
"step": 110
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 4.998412177356568e-05,
|
146 |
+
"loss": 2.7595,
|
147 |
+
"step": 115
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 4.9982685699138275e-05,
|
152 |
+
"loss": 2.7377,
|
153 |
+
"step": 120
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 4.9981187486304423e-05,
|
158 |
+
"loss": 2.9878,
|
159 |
+
"step": 125
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07,
|
163 |
+
"learning_rate": 4.997962713879058e-05,
|
164 |
+
"loss": 2.7882,
|
165 |
+
"step": 130
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.07,
|
169 |
+
"learning_rate": 4.997800466047772e-05,
|
170 |
+
"loss": 2.7802,
|
171 |
+
"step": 135
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 4.997632005540138e-05,
|
176 |
+
"loss": 3.0129,
|
177 |
+
"step": 140
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 4.997457332775159e-05,
|
182 |
+
"loss": 2.9444,
|
183 |
+
"step": 145
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.08,
|
187 |
+
"learning_rate": 4.997276448187294e-05,
|
188 |
+
"loss": 2.9664,
|
189 |
+
"step": 150
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.08,
|
193 |
+
"learning_rate": 4.9970893522264476e-05,
|
194 |
+
"loss": 2.7367,
|
195 |
+
"step": 155
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 4.996896045357977e-05,
|
200 |
+
"loss": 2.7012,
|
201 |
+
"step": 160
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 4.9966965280626856e-05,
|
206 |
+
"loss": 2.8493,
|
207 |
+
"step": 165
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.09,
|
211 |
+
"learning_rate": 4.996490800836825e-05,
|
212 |
+
"loss": 2.9274,
|
213 |
+
"step": 170
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09,
|
217 |
+
"learning_rate": 4.996278864192092e-05,
|
218 |
+
"loss": 2.8093,
|
219 |
+
"step": 175
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 4.9960607186556286e-05,
|
224 |
+
"loss": 3.1782,
|
225 |
+
"step": 180
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.09,
|
229 |
+
"learning_rate": 4.995836364770018e-05,
|
230 |
+
"loss": 2.7507,
|
231 |
+
"step": 185
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.1,
|
235 |
+
"learning_rate": 4.995605803093287e-05,
|
236 |
+
"loss": 2.6724,
|
237 |
+
"step": 190
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.1,
|
241 |
+
"learning_rate": 4.9953690341989026e-05,
|
242 |
+
"loss": 3.0258,
|
243 |
+
"step": 195
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 4.9951260586757694e-05,
|
248 |
+
"loss": 3.1134,
|
249 |
+
"step": 200
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1,
|
253 |
+
"learning_rate": 4.9948768771282314e-05,
|
254 |
+
"loss": 2.9937,
|
255 |
+
"step": 205
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11,
|
259 |
+
"learning_rate": 4.9946214901760665e-05,
|
260 |
+
"loss": 2.7394,
|
261 |
+
"step": 210
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.11,
|
265 |
+
"learning_rate": 4.99435989845449e-05,
|
266 |
+
"loss": 2.9696,
|
267 |
+
"step": 215
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 4.994092102614146e-05,
|
272 |
+
"loss": 2.753,
|
273 |
+
"step": 220
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.11,
|
277 |
+
"learning_rate": 4.993818103321113e-05,
|
278 |
+
"loss": 3.0759,
|
279 |
+
"step": 225
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.12,
|
283 |
+
"learning_rate": 4.9935379012568985e-05,
|
284 |
+
"loss": 2.7512,
|
285 |
+
"step": 230
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.12,
|
289 |
+
"learning_rate": 4.993251497118438e-05,
|
290 |
+
"loss": 2.8656,
|
291 |
+
"step": 235
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 4.992958891618091e-05,
|
296 |
+
"loss": 2.6628,
|
297 |
+
"step": 240
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.12,
|
301 |
+
"learning_rate": 4.992660085483645e-05,
|
302 |
+
"loss": 2.8012,
|
303 |
+
"step": 245
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.13,
|
307 |
+
"learning_rate": 4.992355079458307e-05,
|
308 |
+
"loss": 2.8141,
|
309 |
+
"step": 250
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.13,
|
313 |
+
"learning_rate": 4.992043874300706e-05,
|
314 |
+
"loss": 2.9083,
|
315 |
+
"step": 255
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.13,
|
319 |
+
"learning_rate": 4.991726470784891e-05,
|
320 |
+
"loss": 2.5846,
|
321 |
+
"step": 260
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.13,
|
325 |
+
"learning_rate": 4.991402869700325e-05,
|
326 |
+
"loss": 2.8088,
|
327 |
+
"step": 265
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.14,
|
331 |
+
"learning_rate": 4.991073071851889e-05,
|
332 |
+
"loss": 2.9979,
|
333 |
+
"step": 270
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.14,
|
337 |
+
"learning_rate": 4.990737078059875e-05,
|
338 |
+
"loss": 3.0171,
|
339 |
+
"step": 275
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.14,
|
343 |
+
"learning_rate": 4.990394889159986e-05,
|
344 |
+
"loss": 2.9278,
|
345 |
+
"step": 280
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.14,
|
349 |
+
"learning_rate": 4.9900465060033364e-05,
|
350 |
+
"loss": 2.7998,
|
351 |
+
"step": 285
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.15,
|
355 |
+
"learning_rate": 4.989691929456443e-05,
|
356 |
+
"loss": 2.721,
|
357 |
+
"step": 290
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.15,
|
361 |
+
"learning_rate": 4.9893311604012306e-05,
|
362 |
+
"loss": 3.0291,
|
363 |
+
"step": 295
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.15,
|
367 |
+
"learning_rate": 4.988964199735024e-05,
|
368 |
+
"loss": 2.9777,
|
369 |
+
"step": 300
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.15,
|
373 |
+
"learning_rate": 4.988591048370552e-05,
|
374 |
+
"loss": 2.318,
|
375 |
+
"step": 305
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.16,
|
379 |
+
"learning_rate": 4.988211707235936e-05,
|
380 |
+
"loss": 3.0332,
|
381 |
+
"step": 310
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.16,
|
385 |
+
"learning_rate": 4.987826177274697e-05,
|
386 |
+
"loss": 2.4888,
|
387 |
+
"step": 315
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.16,
|
391 |
+
"learning_rate": 4.987434459445748e-05,
|
392 |
+
"loss": 2.9259,
|
393 |
+
"step": 320
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.16,
|
397 |
+
"learning_rate": 4.987036554723391e-05,
|
398 |
+
"loss": 2.9568,
|
399 |
+
"step": 325
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.17,
|
403 |
+
"learning_rate": 4.98663246409732e-05,
|
404 |
+
"loss": 2.8708,
|
405 |
+
"step": 330
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.17,
|
409 |
+
"learning_rate": 4.986222188572611e-05,
|
410 |
+
"loss": 2.7848,
|
411 |
+
"step": 335
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.17,
|
415 |
+
"learning_rate": 4.985805729169728e-05,
|
416 |
+
"loss": 2.6178,
|
417 |
+
"step": 340
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.17,
|
421 |
+
"learning_rate": 4.985383086924511e-05,
|
422 |
+
"loss": 2.8326,
|
423 |
+
"step": 345
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.18,
|
427 |
+
"learning_rate": 4.984954262888182e-05,
|
428 |
+
"loss": 2.8845,
|
429 |
+
"step": 350
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.18,
|
433 |
+
"learning_rate": 4.9845192581273365e-05,
|
434 |
+
"loss": 2.6151,
|
435 |
+
"step": 355
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.18,
|
439 |
+
"learning_rate": 4.984078073723944e-05,
|
440 |
+
"loss": 2.8474,
|
441 |
+
"step": 360
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.18,
|
445 |
+
"learning_rate": 4.9836307107753455e-05,
|
446 |
+
"loss": 2.808,
|
447 |
+
"step": 365
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.19,
|
451 |
+
"learning_rate": 4.983177170394248e-05,
|
452 |
+
"loss": 2.8491,
|
453 |
+
"step": 370
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.19,
|
457 |
+
"learning_rate": 4.9827174537087226e-05,
|
458 |
+
"loss": 2.7764,
|
459 |
+
"step": 375
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.19,
|
463 |
+
"learning_rate": 4.982251561862205e-05,
|
464 |
+
"loss": 2.7582,
|
465 |
+
"step": 380
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.19,
|
469 |
+
"learning_rate": 4.981779496013489e-05,
|
470 |
+
"loss": 2.5379,
|
471 |
+
"step": 385
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.2,
|
475 |
+
"learning_rate": 4.981301257336723e-05,
|
476 |
+
"loss": 2.9937,
|
477 |
+
"step": 390
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.2,
|
481 |
+
"learning_rate": 4.980816847021412e-05,
|
482 |
+
"loss": 2.8574,
|
483 |
+
"step": 395
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.2,
|
487 |
+
"learning_rate": 4.980326266272409e-05,
|
488 |
+
"loss": 2.9369,
|
489 |
+
"step": 400
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.2,
|
493 |
+
"learning_rate": 4.979829516309915e-05,
|
494 |
+
"loss": 2.836,
|
495 |
+
"step": 405
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.21,
|
499 |
+
"learning_rate": 4.979326598369477e-05,
|
500 |
+
"loss": 2.9369,
|
501 |
+
"step": 410
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.21,
|
505 |
+
"learning_rate": 4.9788175137019814e-05,
|
506 |
+
"loss": 2.6667,
|
507 |
+
"step": 415
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.21,
|
511 |
+
"learning_rate": 4.9783022635736534e-05,
|
512 |
+
"loss": 2.999,
|
513 |
+
"step": 420
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.21,
|
517 |
+
"learning_rate": 4.977780849266054e-05,
|
518 |
+
"loss": 2.907,
|
519 |
+
"step": 425
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.22,
|
523 |
+
"learning_rate": 4.9772532720760744e-05,
|
524 |
+
"loss": 2.8028,
|
525 |
+
"step": 430
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.22,
|
529 |
+
"learning_rate": 4.976719533315937e-05,
|
530 |
+
"loss": 2.7999,
|
531 |
+
"step": 435
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.22,
|
535 |
+
"learning_rate": 4.976179634313187e-05,
|
536 |
+
"loss": 2.8918,
|
537 |
+
"step": 440
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.22,
|
541 |
+
"learning_rate": 4.9756335764106944e-05,
|
542 |
+
"loss": 2.7926,
|
543 |
+
"step": 445
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.23,
|
547 |
+
"learning_rate": 4.975081360966646e-05,
|
548 |
+
"loss": 2.6709,
|
549 |
+
"step": 450
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.23,
|
553 |
+
"learning_rate": 4.9745229893545436e-05,
|
554 |
+
"loss": 2.8248,
|
555 |
+
"step": 455
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.23,
|
559 |
+
"learning_rate": 4.973958462963203e-05,
|
560 |
+
"loss": 3.1146,
|
561 |
+
"step": 460
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.23,
|
565 |
+
"learning_rate": 4.973387783196747e-05,
|
566 |
+
"loss": 2.9991,
|
567 |
+
"step": 465
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.24,
|
571 |
+
"learning_rate": 4.972810951474605e-05,
|
572 |
+
"loss": 2.7726,
|
573 |
+
"step": 470
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.24,
|
577 |
+
"learning_rate": 4.972227969231505e-05,
|
578 |
+
"loss": 2.9025,
|
579 |
+
"step": 475
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.24,
|
583 |
+
"learning_rate": 4.971638837917475e-05,
|
584 |
+
"loss": 2.6521,
|
585 |
+
"step": 480
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.24,
|
589 |
+
"learning_rate": 4.971043558997839e-05,
|
590 |
+
"loss": 2.9511,
|
591 |
+
"step": 485
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.25,
|
595 |
+
"learning_rate": 4.9704421339532075e-05,
|
596 |
+
"loss": 2.6938,
|
597 |
+
"step": 490
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.25,
|
601 |
+
"learning_rate": 4.969834564279482e-05,
|
602 |
+
"loss": 2.8533,
|
603 |
+
"step": 495
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.25,
|
607 |
+
"learning_rate": 4.9692208514878444e-05,
|
608 |
+
"loss": 2.6411,
|
609 |
+
"step": 500
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.25,
|
613 |
+
"learning_rate": 4.968600997104758e-05,
|
614 |
+
"loss": 2.6486,
|
615 |
+
"step": 505
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.26,
|
619 |
+
"learning_rate": 4.967975002671961e-05,
|
620 |
+
"loss": 2.8561,
|
621 |
+
"step": 510
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.26,
|
625 |
+
"learning_rate": 4.967342869746463e-05,
|
626 |
+
"loss": 2.6984,
|
627 |
+
"step": 515
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.26,
|
631 |
+
"learning_rate": 4.9667045999005424e-05,
|
632 |
+
"loss": 2.91,
|
633 |
+
"step": 520
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.26,
|
637 |
+
"learning_rate": 4.966060194721742e-05,
|
638 |
+
"loss": 2.7205,
|
639 |
+
"step": 525
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.27,
|
643 |
+
"learning_rate": 4.965409655812865e-05,
|
644 |
+
"loss": 2.7634,
|
645 |
+
"step": 530
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.27,
|
649 |
+
"learning_rate": 4.9647529847919684e-05,
|
650 |
+
"loss": 2.9647,
|
651 |
+
"step": 535
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.27,
|
655 |
+
"learning_rate": 4.964090183292364e-05,
|
656 |
+
"loss": 2.6357,
|
657 |
+
"step": 540
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.27,
|
661 |
+
"learning_rate": 4.963421252962609e-05,
|
662 |
+
"loss": 3.0285,
|
663 |
+
"step": 545
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.28,
|
667 |
+
"learning_rate": 4.96274619546651e-05,
|
668 |
+
"loss": 2.9895,
|
669 |
+
"step": 550
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.28,
|
673 |
+
"learning_rate": 4.962065012483106e-05,
|
674 |
+
"loss": 2.7286,
|
675 |
+
"step": 555
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.28,
|
679 |
+
"learning_rate": 4.961377705706677e-05,
|
680 |
+
"loss": 3.1337,
|
681 |
+
"step": 560
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.28,
|
685 |
+
"learning_rate": 4.960684276846733e-05,
|
686 |
+
"loss": 2.8268,
|
687 |
+
"step": 565
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.29,
|
691 |
+
"learning_rate": 4.959984727628011e-05,
|
692 |
+
"loss": 2.5851,
|
693 |
+
"step": 570
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.29,
|
697 |
+
"learning_rate": 4.959279059790471e-05,
|
698 |
+
"loss": 2.9359,
|
699 |
+
"step": 575
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.29,
|
703 |
+
"learning_rate": 4.958567275089291e-05,
|
704 |
+
"loss": 2.8842,
|
705 |
+
"step": 580
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.29,
|
709 |
+
"learning_rate": 4.957849375294864e-05,
|
710 |
+
"loss": 2.6186,
|
711 |
+
"step": 585
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.3,
|
715 |
+
"learning_rate": 4.957125362192794e-05,
|
716 |
+
"loss": 3.0116,
|
717 |
+
"step": 590
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.3,
|
721 |
+
"learning_rate": 4.956395237583887e-05,
|
722 |
+
"loss": 2.7045,
|
723 |
+
"step": 595
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.3,
|
727 |
+
"learning_rate": 4.9556590032841526e-05,
|
728 |
+
"loss": 2.8766,
|
729 |
+
"step": 600
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.3,
|
733 |
+
"learning_rate": 4.954916661124797e-05,
|
734 |
+
"loss": 2.7858,
|
735 |
+
"step": 605
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.31,
|
739 |
+
"learning_rate": 4.954168212952216e-05,
|
740 |
+
"loss": 2.7379,
|
741 |
+
"step": 610
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.31,
|
745 |
+
"learning_rate": 4.953413660627995e-05,
|
746 |
+
"loss": 2.475,
|
747 |
+
"step": 615
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.31,
|
751 |
+
"learning_rate": 4.9526530060289e-05,
|
752 |
+
"loss": 2.8357,
|
753 |
+
"step": 620
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.31,
|
757 |
+
"learning_rate": 4.951886251046876e-05,
|
758 |
+
"loss": 2.9284,
|
759 |
+
"step": 625
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.32,
|
763 |
+
"learning_rate": 4.951113397589042e-05,
|
764 |
+
"loss": 2.8144,
|
765 |
+
"step": 630
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.32,
|
769 |
+
"learning_rate": 4.9503344475776846e-05,
|
770 |
+
"loss": 2.6845,
|
771 |
+
"step": 635
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.32,
|
775 |
+
"learning_rate": 4.9495494029502535e-05,
|
776 |
+
"loss": 2.8937,
|
777 |
+
"step": 640
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.32,
|
781 |
+
"learning_rate": 4.9487582656593575e-05,
|
782 |
+
"loss": 3.0325,
|
783 |
+
"step": 645
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.33,
|
787 |
+
"learning_rate": 4.94796103767276e-05,
|
788 |
+
"loss": 2.7058,
|
789 |
+
"step": 650
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.33,
|
793 |
+
"learning_rate": 4.9471577209733746e-05,
|
794 |
+
"loss": 2.6162,
|
795 |
+
"step": 655
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.33,
|
799 |
+
"learning_rate": 4.946348317559257e-05,
|
800 |
+
"loss": 3.0129,
|
801 |
+
"step": 660
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.33,
|
805 |
+
"learning_rate": 4.945532829443603e-05,
|
806 |
+
"loss": 2.7587,
|
807 |
+
"step": 665
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.34,
|
811 |
+
"learning_rate": 4.944711258654742e-05,
|
812 |
+
"loss": 2.8915,
|
813 |
+
"step": 670
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.34,
|
817 |
+
"learning_rate": 4.943883607236135e-05,
|
818 |
+
"loss": 2.7343,
|
819 |
+
"step": 675
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.34,
|
823 |
+
"learning_rate": 4.943049877246364e-05,
|
824 |
+
"loss": 2.881,
|
825 |
+
"step": 680
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.34,
|
829 |
+
"learning_rate": 4.942210070759131e-05,
|
830 |
+
"loss": 2.488,
|
831 |
+
"step": 685
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.35,
|
835 |
+
"learning_rate": 4.941364189863253e-05,
|
836 |
+
"loss": 2.896,
|
837 |
+
"step": 690
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.35,
|
841 |
+
"learning_rate": 4.940512236662654e-05,
|
842 |
+
"loss": 2.7757,
|
843 |
+
"step": 695
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.35,
|
847 |
+
"learning_rate": 4.9396542132763634e-05,
|
848 |
+
"loss": 2.6271,
|
849 |
+
"step": 700
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.35,
|
853 |
+
"learning_rate": 4.938790121838506e-05,
|
854 |
+
"loss": 2.6804,
|
855 |
+
"step": 705
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.36,
|
859 |
+
"learning_rate": 4.937919964498302e-05,
|
860 |
+
"loss": 2.7313,
|
861 |
+
"step": 710
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.36,
|
865 |
+
"learning_rate": 4.937043743420058e-05,
|
866 |
+
"loss": 2.9277,
|
867 |
+
"step": 715
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.36,
|
871 |
+
"learning_rate": 4.9361614607831605e-05,
|
872 |
+
"loss": 2.6366,
|
873 |
+
"step": 720
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.36,
|
877 |
+
"learning_rate": 4.935273118782078e-05,
|
878 |
+
"loss": 3.0556,
|
879 |
+
"step": 725
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.37,
|
883 |
+
"learning_rate": 4.934378719626345e-05,
|
884 |
+
"loss": 3.0182,
|
885 |
+
"step": 730
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.37,
|
889 |
+
"learning_rate": 4.933478265540564e-05,
|
890 |
+
"loss": 2.824,
|
891 |
+
"step": 735
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.37,
|
895 |
+
"learning_rate": 4.932571758764398e-05,
|
896 |
+
"loss": 2.636,
|
897 |
+
"step": 740
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.37,
|
901 |
+
"learning_rate": 4.931659201552563e-05,
|
902 |
+
"loss": 2.7025,
|
903 |
+
"step": 745
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.38,
|
907 |
+
"learning_rate": 4.930740596174827e-05,
|
908 |
+
"loss": 2.8919,
|
909 |
+
"step": 750
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.38,
|
913 |
+
"learning_rate": 4.9298159449159965e-05,
|
914 |
+
"loss": 2.8434,
|
915 |
+
"step": 755
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.38,
|
919 |
+
"learning_rate": 4.928885250075921e-05,
|
920 |
+
"loss": 2.9448,
|
921 |
+
"step": 760
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.38,
|
925 |
+
"learning_rate": 4.927948513969478e-05,
|
926 |
+
"loss": 2.7312,
|
927 |
+
"step": 765
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.39,
|
931 |
+
"learning_rate": 4.927005738926573e-05,
|
932 |
+
"loss": 2.8688,
|
933 |
+
"step": 770
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.39,
|
937 |
+
"learning_rate": 4.926056927292132e-05,
|
938 |
+
"loss": 2.8639,
|
939 |
+
"step": 775
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.39,
|
943 |
+
"learning_rate": 4.925102081426095e-05,
|
944 |
+
"loss": 2.7809,
|
945 |
+
"step": 780
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.39,
|
949 |
+
"learning_rate": 4.9241412037034115e-05,
|
950 |
+
"loss": 3.0111,
|
951 |
+
"step": 785
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.4,
|
955 |
+
"learning_rate": 4.9231742965140314e-05,
|
956 |
+
"loss": 2.7252,
|
957 |
+
"step": 790
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.4,
|
961 |
+
"learning_rate": 4.922201362262905e-05,
|
962 |
+
"loss": 2.9717,
|
963 |
+
"step": 795
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.4,
|
967 |
+
"learning_rate": 4.92122240336997e-05,
|
968 |
+
"loss": 2.7191,
|
969 |
+
"step": 800
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.4,
|
973 |
+
"learning_rate": 4.920237422270153e-05,
|
974 |
+
"loss": 2.9346,
|
975 |
+
"step": 805
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.41,
|
979 |
+
"learning_rate": 4.9192464214133536e-05,
|
980 |
+
"loss": 2.7967,
|
981 |
+
"step": 810
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.41,
|
985 |
+
"learning_rate": 4.9182494032644496e-05,
|
986 |
+
"loss": 2.7326,
|
987 |
+
"step": 815
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.41,
|
991 |
+
"learning_rate": 4.917246370303284e-05,
|
992 |
+
"loss": 2.8933,
|
993 |
+
"step": 820
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.41,
|
997 |
+
"learning_rate": 4.9162373250246575e-05,
|
998 |
+
"loss": 2.7939,
|
999 |
+
"step": 825
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.42,
|
1003 |
+
"learning_rate": 4.9152222699383273e-05,
|
1004 |
+
"loss": 2.7807,
|
1005 |
+
"step": 830
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.42,
|
1009 |
+
"learning_rate": 4.9142012075689994e-05,
|
1010 |
+
"loss": 2.6996,
|
1011 |
+
"step": 835
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.42,
|
1015 |
+
"learning_rate": 4.913174140456319e-05,
|
1016 |
+
"loss": 2.7569,
|
1017 |
+
"step": 840
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.42,
|
1021 |
+
"learning_rate": 4.912141071154869e-05,
|
1022 |
+
"loss": 2.9347,
|
1023 |
+
"step": 845
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.43,
|
1027 |
+
"learning_rate": 4.911102002234159e-05,
|
1028 |
+
"loss": 2.7251,
|
1029 |
+
"step": 850
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.43,
|
1033 |
+
"learning_rate": 4.910056936278623e-05,
|
1034 |
+
"loss": 3.1228,
|
1035 |
+
"step": 855
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.43,
|
1039 |
+
"learning_rate": 4.90900587588761e-05,
|
1040 |
+
"loss": 2.9902,
|
1041 |
+
"step": 860
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.43,
|
1045 |
+
"learning_rate": 4.9079488236753803e-05,
|
1046 |
+
"loss": 2.5095,
|
1047 |
+
"step": 865
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.44,
|
1051 |
+
"learning_rate": 4.906885782271095e-05,
|
1052 |
+
"loss": 2.7523,
|
1053 |
+
"step": 870
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.44,
|
1057 |
+
"learning_rate": 4.905816754318814e-05,
|
1058 |
+
"loss": 2.6656,
|
1059 |
+
"step": 875
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.44,
|
1063 |
+
"learning_rate": 4.9047417424774874e-05,
|
1064 |
+
"loss": 2.8454,
|
1065 |
+
"step": 880
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.44,
|
1069 |
+
"learning_rate": 4.903660749420946e-05,
|
1070 |
+
"loss": 2.8194,
|
1071 |
+
"step": 885
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.45,
|
1075 |
+
"learning_rate": 4.9025737778379025e-05,
|
1076 |
+
"loss": 2.8421,
|
1077 |
+
"step": 890
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.45,
|
1081 |
+
"learning_rate": 4.9014808304319326e-05,
|
1082 |
+
"loss": 2.9656,
|
1083 |
+
"step": 895
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.45,
|
1087 |
+
"learning_rate": 4.900381909921482e-05,
|
1088 |
+
"loss": 2.7484,
|
1089 |
+
"step": 900
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.45,
|
1093 |
+
"learning_rate": 4.899277019039849e-05,
|
1094 |
+
"loss": 2.9044,
|
1095 |
+
"step": 905
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.46,
|
1099 |
+
"learning_rate": 4.898166160535186e-05,
|
1100 |
+
"loss": 2.8016,
|
1101 |
+
"step": 910
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.46,
|
1105 |
+
"learning_rate": 4.8970493371704826e-05,
|
1106 |
+
"loss": 2.6278,
|
1107 |
+
"step": 915
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.46,
|
1111 |
+
"learning_rate": 4.895926551723569e-05,
|
1112 |
+
"loss": 2.7214,
|
1113 |
+
"step": 920
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.46,
|
1117 |
+
"learning_rate": 4.8947978069871036e-05,
|
1118 |
+
"loss": 2.7679,
|
1119 |
+
"step": 925
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.47,
|
1123 |
+
"learning_rate": 4.8936631057685654e-05,
|
1124 |
+
"loss": 2.7196,
|
1125 |
+
"step": 930
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.47,
|
1129 |
+
"learning_rate": 4.8925224508902514e-05,
|
1130 |
+
"loss": 2.7866,
|
1131 |
+
"step": 935
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.47,
|
1135 |
+
"learning_rate": 4.8913758451892644e-05,
|
1136 |
+
"loss": 2.72,
|
1137 |
+
"step": 940
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.47,
|
1141 |
+
"learning_rate": 4.89022329151751e-05,
|
1142 |
+
"loss": 2.752,
|
1143 |
+
"step": 945
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.48,
|
1147 |
+
"learning_rate": 4.8890647927416887e-05,
|
1148 |
+
"loss": 3.0487,
|
1149 |
+
"step": 950
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.48,
|
1153 |
+
"learning_rate": 4.8879003517432857e-05,
|
1154 |
+
"loss": 2.8928,
|
1155 |
+
"step": 955
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.48,
|
1159 |
+
"learning_rate": 4.886729971418568e-05,
|
1160 |
+
"loss": 2.7793,
|
1161 |
+
"step": 960
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.48,
|
1165 |
+
"learning_rate": 4.8855536546785726e-05,
|
1166 |
+
"loss": 2.537,
|
1167 |
+
"step": 965
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.49,
|
1171 |
+
"learning_rate": 4.884371404449105e-05,
|
1172 |
+
"loss": 2.8345,
|
1173 |
+
"step": 970
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.49,
|
1177 |
+
"learning_rate": 4.8831832236707284e-05,
|
1178 |
+
"loss": 2.9673,
|
1179 |
+
"step": 975
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.49,
|
1183 |
+
"learning_rate": 4.8819891152987546e-05,
|
1184 |
+
"loss": 2.8295,
|
1185 |
+
"step": 980
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.49,
|
1189 |
+
"learning_rate": 4.880789082303241e-05,
|
1190 |
+
"loss": 3.0753,
|
1191 |
+
"step": 985
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.5,
|
1195 |
+
"learning_rate": 4.879583127668979e-05,
|
1196 |
+
"loss": 2.6748,
|
1197 |
+
"step": 990
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.5,
|
1201 |
+
"learning_rate": 4.878371254395492e-05,
|
1202 |
+
"loss": 2.8115,
|
1203 |
+
"step": 995
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.5,
|
1207 |
+
"learning_rate": 4.877153465497022e-05,
|
1208 |
+
"loss": 2.7039,
|
1209 |
+
"step": 1000
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.5,
|
1213 |
+
"learning_rate": 4.8759297640025235e-05,
|
1214 |
+
"loss": 2.9469,
|
1215 |
+
"step": 1005
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.51,
|
1219 |
+
"learning_rate": 4.874700152955661e-05,
|
1220 |
+
"loss": 2.9745,
|
1221 |
+
"step": 1010
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.51,
|
1225 |
+
"learning_rate": 4.8734646354147936e-05,
|
1226 |
+
"loss": 2.9341,
|
1227 |
+
"step": 1015
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.51,
|
1231 |
+
"learning_rate": 4.8722232144529754e-05,
|
1232 |
+
"loss": 3.0511,
|
1233 |
+
"step": 1020
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.51,
|
1237 |
+
"learning_rate": 4.870975893157941e-05,
|
1238 |
+
"loss": 2.5396,
|
1239 |
+
"step": 1025
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.52,
|
1243 |
+
"learning_rate": 4.8697226746321004e-05,
|
1244 |
+
"loss": 2.6699,
|
1245 |
+
"step": 1030
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 0.52,
|
1249 |
+
"learning_rate": 4.868463561992532e-05,
|
1250 |
+
"loss": 2.4887,
|
1251 |
+
"step": 1035
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 0.52,
|
1255 |
+
"learning_rate": 4.867198558370977e-05,
|
1256 |
+
"loss": 2.4773,
|
1257 |
+
"step": 1040
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.52,
|
1261 |
+
"learning_rate": 4.865927666913825e-05,
|
1262 |
+
"loss": 2.7612,
|
1263 |
+
"step": 1045
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.53,
|
1267 |
+
"learning_rate": 4.864650890782113e-05,
|
1268 |
+
"loss": 2.9116,
|
1269 |
+
"step": 1050
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.53,
|
1273 |
+
"learning_rate": 4.863368233151514e-05,
|
1274 |
+
"loss": 2.8205,
|
1275 |
+
"step": 1055
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 0.53,
|
1279 |
+
"learning_rate": 4.862079697212329e-05,
|
1280 |
+
"loss": 2.6711,
|
1281 |
+
"step": 1060
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 0.53,
|
1285 |
+
"learning_rate": 4.8607852861694804e-05,
|
1286 |
+
"loss": 3.1138,
|
1287 |
+
"step": 1065
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 0.54,
|
1291 |
+
"learning_rate": 4.859485003242503e-05,
|
1292 |
+
"loss": 2.5603,
|
1293 |
+
"step": 1070
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 0.54,
|
1297 |
+
"learning_rate": 4.858178851665539e-05,
|
1298 |
+
"loss": 2.7981,
|
1299 |
+
"step": 1075
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.54,
|
1303 |
+
"learning_rate": 4.856866834687323e-05,
|
1304 |
+
"loss": 2.507,
|
1305 |
+
"step": 1080
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.54,
|
1309 |
+
"learning_rate": 4.855548955571183e-05,
|
1310 |
+
"loss": 3.0315,
|
1311 |
+
"step": 1085
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.55,
|
1315 |
+
"learning_rate": 4.8542252175950244e-05,
|
1316 |
+
"loss": 2.75,
|
1317 |
+
"step": 1090
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 0.55,
|
1321 |
+
"learning_rate": 4.852895624051326e-05,
|
1322 |
+
"loss": 2.6794,
|
1323 |
+
"step": 1095
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 0.55,
|
1327 |
+
"learning_rate": 4.851560178247132e-05,
|
1328 |
+
"loss": 2.8278,
|
1329 |
+
"step": 1100
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.55,
|
1333 |
+
"learning_rate": 4.850218883504041e-05,
|
1334 |
+
"loss": 2.6993,
|
1335 |
+
"step": 1105
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 0.56,
|
1339 |
+
"learning_rate": 4.8488717431582005e-05,
|
1340 |
+
"loss": 2.875,
|
1341 |
+
"step": 1110
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.56,
|
1345 |
+
"learning_rate": 4.8475187605602974e-05,
|
1346 |
+
"loss": 2.6057,
|
1347 |
+
"step": 1115
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.56,
|
1351 |
+
"learning_rate": 4.84615993907555e-05,
|
1352 |
+
"loss": 2.847,
|
1353 |
+
"step": 1120
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.56,
|
1357 |
+
"learning_rate": 4.844795282083697e-05,
|
1358 |
+
"loss": 2.7652,
|
1359 |
+
"step": 1125
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.57,
|
1363 |
+
"learning_rate": 4.843424792978997e-05,
|
1364 |
+
"loss": 2.8128,
|
1365 |
+
"step": 1130
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 0.57,
|
1369 |
+
"learning_rate": 4.842048475170209e-05,
|
1370 |
+
"loss": 2.7077,
|
1371 |
+
"step": 1135
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.57,
|
1375 |
+
"learning_rate": 4.840666332080592e-05,
|
1376 |
+
"loss": 2.7081,
|
1377 |
+
"step": 1140
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 0.57,
|
1381 |
+
"learning_rate": 4.8392783671478934e-05,
|
1382 |
+
"loss": 2.6479,
|
1383 |
+
"step": 1145
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.58,
|
1387 |
+
"learning_rate": 4.837884583824342e-05,
|
1388 |
+
"loss": 2.667,
|
1389 |
+
"step": 1150
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.58,
|
1393 |
+
"learning_rate": 4.836484985576638e-05,
|
1394 |
+
"loss": 2.7514,
|
1395 |
+
"step": 1155
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.58,
|
1399 |
+
"learning_rate": 4.835079575885944e-05,
|
1400 |
+
"loss": 2.5058,
|
1401 |
+
"step": 1160
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 0.58,
|
1405 |
+
"learning_rate": 4.833668358247876e-05,
|
1406 |
+
"loss": 2.6183,
|
1407 |
+
"step": 1165
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 0.59,
|
1411 |
+
"learning_rate": 4.8322513361725006e-05,
|
1412 |
+
"loss": 2.9959,
|
1413 |
+
"step": 1170
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.59,
|
1417 |
+
"learning_rate": 4.830828513184317e-05,
|
1418 |
+
"loss": 2.5714,
|
1419 |
+
"step": 1175
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.59,
|
1423 |
+
"learning_rate": 4.8293998928222536e-05,
|
1424 |
+
"loss": 2.965,
|
1425 |
+
"step": 1180
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.59,
|
1429 |
+
"learning_rate": 4.827965478639661e-05,
|
1430 |
+
"loss": 2.2106,
|
1431 |
+
"step": 1185
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.6,
|
1435 |
+
"learning_rate": 4.8265252742042965e-05,
|
1436 |
+
"loss": 2.7456,
|
1437 |
+
"step": 1190
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.6,
|
1441 |
+
"learning_rate": 4.8250792830983225e-05,
|
1442 |
+
"loss": 2.5694,
|
1443 |
+
"step": 1195
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 0.6,
|
1447 |
+
"learning_rate": 4.8236275089182936e-05,
|
1448 |
+
"loss": 2.6826,
|
1449 |
+
"step": 1200
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.6,
|
1453 |
+
"learning_rate": 4.8221699552751465e-05,
|
1454 |
+
"loss": 2.878,
|
1455 |
+
"step": 1205
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 0.61,
|
1459 |
+
"learning_rate": 4.820706625794196e-05,
|
1460 |
+
"loss": 2.8191,
|
1461 |
+
"step": 1210
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 0.61,
|
1465 |
+
"learning_rate": 4.81923752411512e-05,
|
1466 |
+
"loss": 2.739,
|
1467 |
+
"step": 1215
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.61,
|
1471 |
+
"learning_rate": 4.8177626538919565e-05,
|
1472 |
+
"loss": 3.0544,
|
1473 |
+
"step": 1220
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.61,
|
1477 |
+
"learning_rate": 4.8162820187930875e-05,
|
1478 |
+
"loss": 2.8393,
|
1479 |
+
"step": 1225
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.62,
|
1483 |
+
"learning_rate": 4.814795622501237e-05,
|
1484 |
+
"loss": 2.4457,
|
1485 |
+
"step": 1230
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 0.62,
|
1489 |
+
"learning_rate": 4.813303468713456e-05,
|
1490 |
+
"loss": 2.8575,
|
1491 |
+
"step": 1235
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 0.62,
|
1495 |
+
"learning_rate": 4.8118055611411197e-05,
|
1496 |
+
"loss": 2.8307,
|
1497 |
+
"step": 1240
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 0.62,
|
1501 |
+
"learning_rate": 4.810301903509909e-05,
|
1502 |
+
"loss": 2.7951,
|
1503 |
+
"step": 1245
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 0.63,
|
1507 |
+
"learning_rate": 4.8087924995598125e-05,
|
1508 |
+
"loss": 2.8456,
|
1509 |
+
"step": 1250
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.63,
|
1513 |
+
"learning_rate": 4.807277353045106e-05,
|
1514 |
+
"loss": 2.3564,
|
1515 |
+
"step": 1255
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.63,
|
1519 |
+
"learning_rate": 4.8057564677343524e-05,
|
1520 |
+
"loss": 2.5076,
|
1521 |
+
"step": 1260
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.63,
|
1525 |
+
"learning_rate": 4.8042298474103884e-05,
|
1526 |
+
"loss": 2.605,
|
1527 |
+
"step": 1265
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 0.64,
|
1531 |
+
"learning_rate": 4.8026974958703116e-05,
|
1532 |
+
"loss": 2.4782,
|
1533 |
+
"step": 1270
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 0.64,
|
1537 |
+
"learning_rate": 4.8011594169254784e-05,
|
1538 |
+
"loss": 2.7193,
|
1539 |
+
"step": 1275
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.64,
|
1543 |
+
"learning_rate": 4.799615614401488e-05,
|
1544 |
+
"loss": 2.8284,
|
1545 |
+
"step": 1280
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 0.64,
|
1549 |
+
"learning_rate": 4.798066092138178e-05,
|
1550 |
+
"loss": 2.5378,
|
1551 |
+
"step": 1285
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.65,
|
1555 |
+
"learning_rate": 4.796510853989612e-05,
|
1556 |
+
"loss": 2.7396,
|
1557 |
+
"step": 1290
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.65,
|
1561 |
+
"learning_rate": 4.794949903824069e-05,
|
1562 |
+
"loss": 2.7948,
|
1563 |
+
"step": 1295
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.65,
|
1567 |
+
"learning_rate": 4.793383245524035e-05,
|
1568 |
+
"loss": 2.7818,
|
1569 |
+
"step": 1300
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.65,
|
1573 |
+
"learning_rate": 4.791810882986197e-05,
|
1574 |
+
"loss": 2.7334,
|
1575 |
+
"step": 1305
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 0.66,
|
1579 |
+
"learning_rate": 4.7902328201214256e-05,
|
1580 |
+
"loss": 2.4824,
|
1581 |
+
"step": 1310
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 0.66,
|
1585 |
+
"learning_rate": 4.7886490608547727e-05,
|
1586 |
+
"loss": 2.6131,
|
1587 |
+
"step": 1315
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 0.66,
|
1591 |
+
"learning_rate": 4.7870596091254584e-05,
|
1592 |
+
"loss": 2.7778,
|
1593 |
+
"step": 1320
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.66,
|
1597 |
+
"learning_rate": 4.7854644688868594e-05,
|
1598 |
+
"loss": 2.5263,
|
1599 |
+
"step": 1325
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.67,
|
1603 |
+
"learning_rate": 4.783863644106502e-05,
|
1604 |
+
"loss": 2.7825,
|
1605 |
+
"step": 1330
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.67,
|
1609 |
+
"learning_rate": 4.782257138766053e-05,
|
1610 |
+
"loss": 2.7902,
|
1611 |
+
"step": 1335
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 0.67,
|
1615 |
+
"learning_rate": 4.7806449568613066e-05,
|
1616 |
+
"loss": 2.8333,
|
1617 |
+
"step": 1340
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 0.67,
|
1621 |
+
"learning_rate": 4.779027102402177e-05,
|
1622 |
+
"loss": 2.856,
|
1623 |
+
"step": 1345
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 0.68,
|
1627 |
+
"learning_rate": 4.777403579412686e-05,
|
1628 |
+
"loss": 2.8021,
|
1629 |
+
"step": 1350
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.68,
|
1633 |
+
"learning_rate": 4.775774391930956e-05,
|
1634 |
+
"loss": 2.6639,
|
1635 |
+
"step": 1355
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.68,
|
1639 |
+
"learning_rate": 4.7741395440091976e-05,
|
1640 |
+
"loss": 2.5226,
|
1641 |
+
"step": 1360
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.68,
|
1645 |
+
"learning_rate": 4.772499039713702e-05,
|
1646 |
+
"loss": 2.6803,
|
1647 |
+
"step": 1365
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.69,
|
1651 |
+
"learning_rate": 4.7708528831248274e-05,
|
1652 |
+
"loss": 2.4608,
|
1653 |
+
"step": 1370
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 0.69,
|
1657 |
+
"learning_rate": 4.769201078336991e-05,
|
1658 |
+
"loss": 2.786,
|
1659 |
+
"step": 1375
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.69,
|
1663 |
+
"learning_rate": 4.7675436294586586e-05,
|
1664 |
+
"loss": 2.8294,
|
1665 |
+
"step": 1380
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.7,
|
1669 |
+
"learning_rate": 4.7658805406123356e-05,
|
1670 |
+
"loss": 2.6776,
|
1671 |
+
"step": 1385
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 0.7,
|
1675 |
+
"learning_rate": 4.7642118159345544e-05,
|
1676 |
+
"loss": 2.8003,
|
1677 |
+
"step": 1390
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.7,
|
1681 |
+
"learning_rate": 4.762537459575865e-05,
|
1682 |
+
"loss": 2.7796,
|
1683 |
+
"step": 1395
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.7,
|
1687 |
+
"learning_rate": 4.7608574757008245e-05,
|
1688 |
+
"loss": 2.9156,
|
1689 |
+
"step": 1400
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.71,
|
1693 |
+
"learning_rate": 4.7591718684879883e-05,
|
1694 |
+
"loss": 3.0521,
|
1695 |
+
"step": 1405
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 0.71,
|
1699 |
+
"learning_rate": 4.7574806421298976e-05,
|
1700 |
+
"loss": 2.6469,
|
1701 |
+
"step": 1410
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 0.71,
|
1705 |
+
"learning_rate": 4.755783800833071e-05,
|
1706 |
+
"loss": 2.8512,
|
1707 |
+
"step": 1415
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.71,
|
1711 |
+
"learning_rate": 4.754081348817991e-05,
|
1712 |
+
"loss": 2.66,
|
1713 |
+
"step": 1420
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 0.72,
|
1717 |
+
"learning_rate": 4.752373290319096e-05,
|
1718 |
+
"loss": 2.6625,
|
1719 |
+
"step": 1425
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.72,
|
1723 |
+
"learning_rate": 4.7506596295847716e-05,
|
1724 |
+
"loss": 2.6711,
|
1725 |
+
"step": 1430
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.72,
|
1729 |
+
"learning_rate": 4.7489403708773346e-05,
|
1730 |
+
"loss": 2.8951,
|
1731 |
+
"step": 1435
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.72,
|
1735 |
+
"learning_rate": 4.747215518473026e-05,
|
1736 |
+
"loss": 2.7375,
|
1737 |
+
"step": 1440
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 0.73,
|
1741 |
+
"learning_rate": 4.745485076662e-05,
|
1742 |
+
"loss": 2.8037,
|
1743 |
+
"step": 1445
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 0.73,
|
1747 |
+
"learning_rate": 4.743749049748315e-05,
|
1748 |
+
"loss": 2.5375,
|
1749 |
+
"step": 1450
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.73,
|
1753 |
+
"learning_rate": 4.742007442049918e-05,
|
1754 |
+
"loss": 2.7664,
|
1755 |
+
"step": 1455
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 0.73,
|
1759 |
+
"learning_rate": 4.7402602578986374e-05,
|
1760 |
+
"loss": 2.9644,
|
1761 |
+
"step": 1460
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.74,
|
1765 |
+
"learning_rate": 4.738507501640175e-05,
|
1766 |
+
"loss": 2.8212,
|
1767 |
+
"step": 1465
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.74,
|
1771 |
+
"learning_rate": 4.736749177634087e-05,
|
1772 |
+
"loss": 2.7201,
|
1773 |
+
"step": 1470
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.74,
|
1777 |
+
"learning_rate": 4.734985290253782e-05,
|
1778 |
+
"loss": 2.7087,
|
1779 |
+
"step": 1475
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.74,
|
1783 |
+
"learning_rate": 4.7332158438865035e-05,
|
1784 |
+
"loss": 2.5502,
|
1785 |
+
"step": 1480
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 0.75,
|
1789 |
+
"learning_rate": 4.731440842933322e-05,
|
1790 |
+
"loss": 2.7607,
|
1791 |
+
"step": 1485
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.75,
|
1795 |
+
"learning_rate": 4.729660291809126e-05,
|
1796 |
+
"loss": 2.5601,
|
1797 |
+
"step": 1490
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 0.75,
|
1801 |
+
"learning_rate": 4.727874194942606e-05,
|
1802 |
+
"loss": 2.5562,
|
1803 |
+
"step": 1495
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.75,
|
1807 |
+
"learning_rate": 4.7260825567762486e-05,
|
1808 |
+
"loss": 2.5539,
|
1809 |
+
"step": 1500
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.76,
|
1813 |
+
"learning_rate": 4.7242853817663204e-05,
|
1814 |
+
"loss": 2.6405,
|
1815 |
+
"step": 1505
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.76,
|
1819 |
+
"learning_rate": 4.72248267438286e-05,
|
1820 |
+
"loss": 2.9237,
|
1821 |
+
"step": 1510
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 0.76,
|
1825 |
+
"learning_rate": 4.72067443910967e-05,
|
1826 |
+
"loss": 3.0453,
|
1827 |
+
"step": 1515
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 0.76,
|
1831 |
+
"learning_rate": 4.718860680444297e-05,
|
1832 |
+
"loss": 2.7176,
|
1833 |
+
"step": 1520
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 0.77,
|
1837 |
+
"learning_rate": 4.71704140289803e-05,
|
1838 |
+
"loss": 2.6713,
|
1839 |
+
"step": 1525
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.77,
|
1843 |
+
"learning_rate": 4.715216610995883e-05,
|
1844 |
+
"loss": 2.7284,
|
1845 |
+
"step": 1530
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.77,
|
1849 |
+
"learning_rate": 4.713386309276585e-05,
|
1850 |
+
"loss": 2.5022,
|
1851 |
+
"step": 1535
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 0.77,
|
1855 |
+
"learning_rate": 4.7115505022925706e-05,
|
1856 |
+
"loss": 2.8323,
|
1857 |
+
"step": 1540
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.78,
|
1861 |
+
"learning_rate": 4.7097091946099666e-05,
|
1862 |
+
"loss": 2.7005,
|
1863 |
+
"step": 1545
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 0.78,
|
1867 |
+
"learning_rate": 4.7078623908085825e-05,
|
1868 |
+
"loss": 2.8142,
|
1869 |
+
"step": 1550
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.78,
|
1873 |
+
"learning_rate": 4.7060100954818974e-05,
|
1874 |
+
"loss": 2.8505,
|
1875 |
+
"step": 1555
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 0.78,
|
1879 |
+
"learning_rate": 4.70415231323705e-05,
|
1880 |
+
"loss": 2.5892,
|
1881 |
+
"step": 1560
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 0.79,
|
1885 |
+
"learning_rate": 4.7022890486948236e-05,
|
1886 |
+
"loss": 2.8951,
|
1887 |
+
"step": 1565
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.79,
|
1891 |
+
"learning_rate": 4.700420306489641e-05,
|
1892 |
+
"loss": 2.7551,
|
1893 |
+
"step": 1570
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 0.79,
|
1897 |
+
"learning_rate": 4.698546091269547e-05,
|
1898 |
+
"loss": 2.6814,
|
1899 |
+
"step": 1575
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.79,
|
1903 |
+
"learning_rate": 4.696666407696201e-05,
|
1904 |
+
"loss": 2.8698,
|
1905 |
+
"step": 1580
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 0.8,
|
1909 |
+
"learning_rate": 4.694781260444862e-05,
|
1910 |
+
"loss": 2.8389,
|
1911 |
+
"step": 1585
|
1912 |
+
},
|
1913 |
+
{
|
1914 |
+
"epoch": 0.8,
|
1915 |
+
"learning_rate": 4.6928906542043786e-05,
|
1916 |
+
"loss": 2.8353,
|
1917 |
+
"step": 1590
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 0.8,
|
1921 |
+
"learning_rate": 4.690994593677179e-05,
|
1922 |
+
"loss": 2.6565,
|
1923 |
+
"step": 1595
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 0.8,
|
1927 |
+
"learning_rate": 4.689093083579256e-05,
|
1928 |
+
"loss": 2.6958,
|
1929 |
+
"step": 1600
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.81,
|
1933 |
+
"learning_rate": 4.687186128640157e-05,
|
1934 |
+
"loss": 2.6768,
|
1935 |
+
"step": 1605
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 0.81,
|
1939 |
+
"learning_rate": 4.685273733602975e-05,
|
1940 |
+
"loss": 2.734,
|
1941 |
+
"step": 1610
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.81,
|
1945 |
+
"learning_rate": 4.6833559032243284e-05,
|
1946 |
+
"loss": 2.5348,
|
1947 |
+
"step": 1615
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 0.81,
|
1951 |
+
"learning_rate": 4.6814326422743594e-05,
|
1952 |
+
"loss": 2.7775,
|
1953 |
+
"step": 1620
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 0.82,
|
1957 |
+
"learning_rate": 4.679503955536715e-05,
|
1958 |
+
"loss": 2.6578,
|
1959 |
+
"step": 1625
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.82,
|
1963 |
+
"learning_rate": 4.6775698478085393e-05,
|
1964 |
+
"loss": 2.8792,
|
1965 |
+
"step": 1630
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 0.82,
|
1969 |
+
"learning_rate": 4.675630323900458e-05,
|
1970 |
+
"loss": 2.7883,
|
1971 |
+
"step": 1635
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.82,
|
1975 |
+
"learning_rate": 4.67368538863657e-05,
|
1976 |
+
"loss": 2.8824,
|
1977 |
+
"step": 1640
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 0.83,
|
1981 |
+
"learning_rate": 4.671735046854433e-05,
|
1982 |
+
"loss": 2.6775,
|
1983 |
+
"step": 1645
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.83,
|
1987 |
+
"learning_rate": 4.669779303405051e-05,
|
1988 |
+
"loss": 2.5658,
|
1989 |
+
"step": 1650
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 0.83,
|
1993 |
+
"learning_rate": 4.667818163152864e-05,
|
1994 |
+
"loss": 2.5262,
|
1995 |
+
"step": 1655
|
1996 |
+
},
|
1997 |
+
{
|
1998 |
+
"epoch": 0.83,
|
1999 |
+
"learning_rate": 4.665851630975736e-05,
|
2000 |
+
"loss": 2.5749,
|
2001 |
+
"step": 1660
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 0.84,
|
2005 |
+
"learning_rate": 4.6638797117649424e-05,
|
2006 |
+
"loss": 2.8718,
|
2007 |
+
"step": 1665
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 0.84,
|
2011 |
+
"learning_rate": 4.661902410425155e-05,
|
2012 |
+
"loss": 2.8039,
|
2013 |
+
"step": 1670
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 0.84,
|
2017 |
+
"learning_rate": 4.659919731874435e-05,
|
2018 |
+
"loss": 2.8089,
|
2019 |
+
"step": 1675
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.84,
|
2023 |
+
"learning_rate": 4.6579316810442174e-05,
|
2024 |
+
"loss": 2.8144,
|
2025 |
+
"step": 1680
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.85,
|
2029 |
+
"learning_rate": 4.6559382628792995e-05,
|
2030 |
+
"loss": 2.5963,
|
2031 |
+
"step": 1685
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 0.85,
|
2035 |
+
"learning_rate": 4.653939482337828e-05,
|
2036 |
+
"loss": 2.5755,
|
2037 |
+
"step": 1690
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 0.85,
|
2041 |
+
"learning_rate": 4.651935344391286e-05,
|
2042 |
+
"loss": 2.7631,
|
2043 |
+
"step": 1695
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 0.85,
|
2047 |
+
"learning_rate": 4.649925854024486e-05,
|
2048 |
+
"loss": 2.8117,
|
2049 |
+
"step": 1700
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 0.86,
|
2053 |
+
"learning_rate": 4.647911016235549e-05,
|
2054 |
+
"loss": 2.7352,
|
2055 |
+
"step": 1705
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 0.86,
|
2059 |
+
"learning_rate": 4.6458908360358985e-05,
|
2060 |
+
"loss": 2.5572,
|
2061 |
+
"step": 1710
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 0.86,
|
2065 |
+
"learning_rate": 4.643865318450246e-05,
|
2066 |
+
"loss": 2.8372,
|
2067 |
+
"step": 1715
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.86,
|
2071 |
+
"learning_rate": 4.6418344685165774e-05,
|
2072 |
+
"loss": 2.7892,
|
2073 |
+
"step": 1720
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 0.87,
|
2077 |
+
"learning_rate": 4.639798291286143e-05,
|
2078 |
+
"loss": 2.7832,
|
2079 |
+
"step": 1725
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 0.87,
|
2083 |
+
"learning_rate": 4.637756791823442e-05,
|
2084 |
+
"loss": 2.5401,
|
2085 |
+
"step": 1730
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 0.87,
|
2089 |
+
"learning_rate": 4.635709975206213e-05,
|
2090 |
+
"loss": 2.9286,
|
2091 |
+
"step": 1735
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 0.87,
|
2095 |
+
"learning_rate": 4.633657846525417e-05,
|
2096 |
+
"loss": 2.6474,
|
2097 |
+
"step": 1740
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 0.88,
|
2101 |
+
"learning_rate": 4.6316004108852305e-05,
|
2102 |
+
"loss": 2.5047,
|
2103 |
+
"step": 1745
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 0.88,
|
2107 |
+
"learning_rate": 4.629537673403029e-05,
|
2108 |
+
"loss": 2.8374,
|
2109 |
+
"step": 1750
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.88,
|
2113 |
+
"learning_rate": 4.627469639209373e-05,
|
2114 |
+
"loss": 2.634,
|
2115 |
+
"step": 1755
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 0.88,
|
2119 |
+
"learning_rate": 4.6253963134480006e-05,
|
2120 |
+
"loss": 2.6884,
|
2121 |
+
"step": 1760
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 0.89,
|
2125 |
+
"learning_rate": 4.623317701275809e-05,
|
2126 |
+
"loss": 2.6334,
|
2127 |
+
"step": 1765
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 0.89,
|
2131 |
+
"learning_rate": 4.621233807862844e-05,
|
2132 |
+
"loss": 2.764,
|
2133 |
+
"step": 1770
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 0.89,
|
2137 |
+
"learning_rate": 4.6191446383922886e-05,
|
2138 |
+
"loss": 3.0864,
|
2139 |
+
"step": 1775
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 0.89,
|
2143 |
+
"learning_rate": 4.617050198060448e-05,
|
2144 |
+
"loss": 2.7964,
|
2145 |
+
"step": 1780
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 0.9,
|
2149 |
+
"learning_rate": 4.6149504920767376e-05,
|
2150 |
+
"loss": 2.4538,
|
2151 |
+
"step": 1785
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.9,
|
2155 |
+
"learning_rate": 4.6128455256636706e-05,
|
2156 |
+
"loss": 2.7352,
|
2157 |
+
"step": 1790
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 0.9,
|
2161 |
+
"learning_rate": 4.6107353040568416e-05,
|
2162 |
+
"loss": 2.6893,
|
2163 |
+
"step": 1795
|
2164 |
+
},
|
2165 |
+
{
|
2166 |
+
"epoch": 0.9,
|
2167 |
+
"learning_rate": 4.6086198325049185e-05,
|
2168 |
+
"loss": 2.8609,
|
2169 |
+
"step": 1800
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 0.91,
|
2173 |
+
"learning_rate": 4.6064991162696275e-05,
|
2174 |
+
"loss": 2.5285,
|
2175 |
+
"step": 1805
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"epoch": 0.91,
|
2179 |
+
"learning_rate": 4.604373160625739e-05,
|
2180 |
+
"loss": 2.5707,
|
2181 |
+
"step": 1810
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 0.91,
|
2185 |
+
"learning_rate": 4.602241970861053e-05,
|
2186 |
+
"loss": 2.7198,
|
2187 |
+
"step": 1815
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 0.91,
|
2191 |
+
"learning_rate": 4.6001055522763926e-05,
|
2192 |
+
"loss": 2.855,
|
2193 |
+
"step": 1820
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.92,
|
2197 |
+
"learning_rate": 4.597963910185582e-05,
|
2198 |
+
"loss": 2.4175,
|
2199 |
+
"step": 1825
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 0.92,
|
2203 |
+
"learning_rate": 4.595817049915441e-05,
|
2204 |
+
"loss": 2.5444,
|
2205 |
+
"step": 1830
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 0.92,
|
2209 |
+
"learning_rate": 4.5936649768057646e-05,
|
2210 |
+
"loss": 2.6893,
|
2211 |
+
"step": 1835
|
2212 |
+
},
|
2213 |
+
{
|
2214 |
+
"epoch": 0.92,
|
2215 |
+
"learning_rate": 4.591507696209318e-05,
|
2216 |
+
"loss": 2.6725,
|
2217 |
+
"step": 1840
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 0.93,
|
2221 |
+
"learning_rate": 4.589345213491817e-05,
|
2222 |
+
"loss": 2.834,
|
2223 |
+
"step": 1845
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 0.93,
|
2227 |
+
"learning_rate": 4.587177534031914e-05,
|
2228 |
+
"loss": 2.8259,
|
2229 |
+
"step": 1850
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 0.93,
|
2233 |
+
"learning_rate": 4.585004663221188e-05,
|
2234 |
+
"loss": 2.6146,
|
2235 |
+
"step": 1855
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.93,
|
2239 |
+
"learning_rate": 4.582826606464134e-05,
|
2240 |
+
"loss": 2.4673,
|
2241 |
+
"step": 1860
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 0.94,
|
2245 |
+
"learning_rate": 4.5806433691781416e-05,
|
2246 |
+
"loss": 2.9178,
|
2247 |
+
"step": 1865
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 0.94,
|
2251 |
+
"learning_rate": 4.578454956793487e-05,
|
2252 |
+
"loss": 2.9224,
|
2253 |
+
"step": 1870
|
2254 |
+
},
|
2255 |
+
{
|
2256 |
+
"epoch": 0.94,
|
2257 |
+
"learning_rate": 4.576261374753318e-05,
|
2258 |
+
"loss": 2.7987,
|
2259 |
+
"step": 1875
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 0.94,
|
2263 |
+
"learning_rate": 4.574062628513642e-05,
|
2264 |
+
"loss": 2.3848,
|
2265 |
+
"step": 1880
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 0.95,
|
2269 |
+
"learning_rate": 4.57185872354331e-05,
|
2270 |
+
"loss": 2.6054,
|
2271 |
+
"step": 1885
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 0.95,
|
2275 |
+
"learning_rate": 4.569649665324003e-05,
|
2276 |
+
"loss": 2.6743,
|
2277 |
+
"step": 1890
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.95,
|
2281 |
+
"learning_rate": 4.567435459350222e-05,
|
2282 |
+
"loss": 2.9375,
|
2283 |
+
"step": 1895
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 0.95,
|
2287 |
+
"learning_rate": 4.565216111129269e-05,
|
2288 |
+
"loss": 2.9372,
|
2289 |
+
"step": 1900
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 0.96,
|
2293 |
+
"learning_rate": 4.562991626181239e-05,
|
2294 |
+
"loss": 2.669,
|
2295 |
+
"step": 1905
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 0.96,
|
2299 |
+
"learning_rate": 4.560762010039001e-05,
|
2300 |
+
"loss": 2.7644,
|
2301 |
+
"step": 1910
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"epoch": 0.96,
|
2305 |
+
"learning_rate": 4.558527268248187e-05,
|
2306 |
+
"loss": 2.6886,
|
2307 |
+
"step": 1915
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 0.96,
|
2311 |
+
"learning_rate": 4.55628740636718e-05,
|
2312 |
+
"loss": 2.8618,
|
2313 |
+
"step": 1920
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.97,
|
2317 |
+
"learning_rate": 4.554042429967095e-05,
|
2318 |
+
"loss": 2.8411,
|
2319 |
+
"step": 1925
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.97,
|
2323 |
+
"learning_rate": 4.55179234463177e-05,
|
2324 |
+
"loss": 2.6047,
|
2325 |
+
"step": 1930
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 0.97,
|
2329 |
+
"learning_rate": 4.5495371559577496e-05,
|
2330 |
+
"loss": 2.8675,
|
2331 |
+
"step": 1935
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 0.97,
|
2335 |
+
"learning_rate": 4.547276869554271e-05,
|
2336 |
+
"loss": 2.751,
|
2337 |
+
"step": 1940
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 0.98,
|
2341 |
+
"learning_rate": 4.545011491043253e-05,
|
2342 |
+
"loss": 2.8638,
|
2343 |
+
"step": 1945
|
2344 |
+
},
|
2345 |
+
{
|
2346 |
+
"epoch": 0.98,
|
2347 |
+
"learning_rate": 4.5427410260592775e-05,
|
2348 |
+
"loss": 2.5092,
|
2349 |
+
"step": 1950
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 0.98,
|
2353 |
+
"learning_rate": 4.540465480249579e-05,
|
2354 |
+
"loss": 2.5059,
|
2355 |
+
"step": 1955
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 0.98,
|
2359 |
+
"learning_rate": 4.5381848592740285e-05,
|
2360 |
+
"loss": 2.9433,
|
2361 |
+
"step": 1960
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 0.99,
|
2365 |
+
"learning_rate": 4.535899168805121e-05,
|
2366 |
+
"loss": 2.6959,
|
2367 |
+
"step": 1965
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 0.99,
|
2371 |
+
"learning_rate": 4.533608414527961e-05,
|
2372 |
+
"loss": 2.552,
|
2373 |
+
"step": 1970
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 0.99,
|
2377 |
+
"learning_rate": 4.5313126021402465e-05,
|
2378 |
+
"loss": 2.7169,
|
2379 |
+
"step": 1975
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 0.99,
|
2383 |
+
"learning_rate": 4.529011737352258e-05,
|
2384 |
+
"loss": 2.5672,
|
2385 |
+
"step": 1980
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 1.0,
|
2389 |
+
"learning_rate": 4.526705825886841e-05,
|
2390 |
+
"loss": 2.6434,
|
2391 |
+
"step": 1985
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 1.0,
|
2395 |
+
"learning_rate": 4.5243948734793947e-05,
|
2396 |
+
"loss": 2.8062,
|
2397 |
+
"step": 1990
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 1.0,
|
2401 |
+
"learning_rate": 4.5220788858778556e-05,
|
2402 |
+
"loss": 2.6929,
|
2403 |
+
"step": 1995
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 1.0,
|
2407 |
+
"learning_rate": 4.519757868842684e-05,
|
2408 |
+
"loss": 2.5837,
|
2409 |
+
"step": 2000
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 1.01,
|
2413 |
+
"learning_rate": 4.517431828146852e-05,
|
2414 |
+
"loss": 2.821,
|
2415 |
+
"step": 2005
|
2416 |
+
},
|
2417 |
+
{
|
2418 |
+
"epoch": 1.01,
|
2419 |
+
"learning_rate": 4.515100769575824e-05,
|
2420 |
+
"loss": 2.7913,
|
2421 |
+
"step": 2010
|
2422 |
+
},
|
2423 |
+
{
|
2424 |
+
"epoch": 1.01,
|
2425 |
+
"learning_rate": 4.512764698927545e-05,
|
2426 |
+
"loss": 2.699,
|
2427 |
+
"step": 2015
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"epoch": 1.01,
|
2431 |
+
"learning_rate": 4.5104236220124286e-05,
|
2432 |
+
"loss": 2.6574,
|
2433 |
+
"step": 2020
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 1.02,
|
2437 |
+
"learning_rate": 4.508077544653338e-05,
|
2438 |
+
"loss": 2.5909,
|
2439 |
+
"step": 2025
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 1.02,
|
2443 |
+
"learning_rate": 4.5057264726855765e-05,
|
2444 |
+
"loss": 2.5695,
|
2445 |
+
"step": 2030
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 1.02,
|
2449 |
+
"learning_rate": 4.5033704119568675e-05,
|
2450 |
+
"loss": 2.4937,
|
2451 |
+
"step": 2035
|
2452 |
+
},
|
2453 |
+
{
|
2454 |
+
"epoch": 1.02,
|
2455 |
+
"learning_rate": 4.501009368327344e-05,
|
2456 |
+
"loss": 2.7253,
|
2457 |
+
"step": 2040
|
2458 |
+
},
|
2459 |
+
{
|
2460 |
+
"epoch": 1.03,
|
2461 |
+
"learning_rate": 4.4986433476695334e-05,
|
2462 |
+
"loss": 2.8681,
|
2463 |
+
"step": 2045
|
2464 |
+
},
|
2465 |
+
{
|
2466 |
+
"epoch": 1.03,
|
2467 |
+
"learning_rate": 4.496272355868341e-05,
|
2468 |
+
"loss": 2.74,
|
2469 |
+
"step": 2050
|
2470 |
+
},
|
2471 |
+
{
|
2472 |
+
"epoch": 1.03,
|
2473 |
+
"learning_rate": 4.4938963988210365e-05,
|
2474 |
+
"loss": 2.7439,
|
2475 |
+
"step": 2055
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 1.03,
|
2479 |
+
"learning_rate": 4.491515482437242e-05,
|
2480 |
+
"loss": 2.9539,
|
2481 |
+
"step": 2060
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 1.04,
|
2485 |
+
"learning_rate": 4.4891296126389104e-05,
|
2486 |
+
"loss": 2.8165,
|
2487 |
+
"step": 2065
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 1.04,
|
2491 |
+
"learning_rate": 4.48673879536032e-05,
|
2492 |
+
"loss": 2.601,
|
2493 |
+
"step": 2070
|
2494 |
+
},
|
2495 |
+
{
|
2496 |
+
"epoch": 1.04,
|
2497 |
+
"learning_rate": 4.484343036548051e-05,
|
2498 |
+
"loss": 2.5189,
|
2499 |
+
"step": 2075
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"epoch": 1.04,
|
2503 |
+
"learning_rate": 4.481942342160976e-05,
|
2504 |
+
"loss": 2.6276,
|
2505 |
+
"step": 2080
|
2506 |
+
},
|
2507 |
+
{
|
2508 |
+
"epoch": 1.05,
|
2509 |
+
"learning_rate": 4.479536718170243e-05,
|
2510 |
+
"loss": 2.5027,
|
2511 |
+
"step": 2085
|
2512 |
+
},
|
2513 |
+
{
|
2514 |
+
"epoch": 1.05,
|
2515 |
+
"learning_rate": 4.477126170559262e-05,
|
2516 |
+
"loss": 2.8654,
|
2517 |
+
"step": 2090
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 1.05,
|
2521 |
+
"learning_rate": 4.474710705323688e-05,
|
2522 |
+
"loss": 2.8511,
|
2523 |
+
"step": 2095
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 1.05,
|
2527 |
+
"learning_rate": 4.47229032847141e-05,
|
2528 |
+
"loss": 2.6129,
|
2529 |
+
"step": 2100
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 1.06,
|
2533 |
+
"learning_rate": 4.469865046022531e-05,
|
2534 |
+
"loss": 2.8964,
|
2535 |
+
"step": 2105
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 1.06,
|
2539 |
+
"learning_rate": 4.4674348640093554e-05,
|
2540 |
+
"loss": 2.7502,
|
2541 |
+
"step": 2110
|
2542 |
+
},
|
2543 |
+
{
|
2544 |
+
"epoch": 1.06,
|
2545 |
+
"learning_rate": 4.4649997884763765e-05,
|
2546 |
+
"loss": 2.591,
|
2547 |
+
"step": 2115
|
2548 |
+
},
|
2549 |
+
{
|
2550 |
+
"epoch": 1.06,
|
2551 |
+
"learning_rate": 4.462559825480257e-05,
|
2552 |
+
"loss": 2.7982,
|
2553 |
+
"step": 2120
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 1.07,
|
2557 |
+
"learning_rate": 4.460114981089815e-05,
|
2558 |
+
"loss": 2.576,
|
2559 |
+
"step": 2125
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 1.07,
|
2563 |
+
"learning_rate": 4.457665261386014e-05,
|
2564 |
+
"loss": 2.692,
|
2565 |
+
"step": 2130
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 1.07,
|
2569 |
+
"learning_rate": 4.455210672461938e-05,
|
2570 |
+
"loss": 2.5818,
|
2571 |
+
"step": 2135
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 1.07,
|
2575 |
+
"learning_rate": 4.452751220422787e-05,
|
2576 |
+
"loss": 2.6792,
|
2577 |
+
"step": 2140
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 1.08,
|
2581 |
+
"learning_rate": 4.450286911385856e-05,
|
2582 |
+
"loss": 2.8352,
|
2583 |
+
"step": 2145
|
2584 |
+
},
|
2585 |
+
{
|
2586 |
+
"epoch": 1.08,
|
2587 |
+
"learning_rate": 4.4478177514805166e-05,
|
2588 |
+
"loss": 2.5787,
|
2589 |
+
"step": 2150
|
2590 |
+
},
|
2591 |
+
{
|
2592 |
+
"epoch": 1.08,
|
2593 |
+
"learning_rate": 4.4453437468482103e-05,
|
2594 |
+
"loss": 2.655,
|
2595 |
+
"step": 2155
|
2596 |
+
},
|
2597 |
+
{
|
2598 |
+
"epoch": 1.08,
|
2599 |
+
"learning_rate": 4.442864903642428e-05,
|
2600 |
+
"loss": 2.7664,
|
2601 |
+
"step": 2160
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 1.09,
|
2605 |
+
"learning_rate": 4.440381228028692e-05,
|
2606 |
+
"loss": 2.7231,
|
2607 |
+
"step": 2165
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 1.09,
|
2611 |
+
"learning_rate": 4.437892726184548e-05,
|
2612 |
+
"loss": 2.416,
|
2613 |
+
"step": 2170
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 1.09,
|
2617 |
+
"learning_rate": 4.4353994042995446e-05,
|
2618 |
+
"loss": 2.4619,
|
2619 |
+
"step": 2175
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 1.09,
|
2623 |
+
"learning_rate": 4.4329012685752183e-05,
|
2624 |
+
"loss": 2.7816,
|
2625 |
+
"step": 2180
|
2626 |
+
},
|
2627 |
+
{
|
2628 |
+
"epoch": 1.1,
|
2629 |
+
"learning_rate": 4.430398325225078e-05,
|
2630 |
+
"loss": 2.8678,
|
2631 |
+
"step": 2185
|
2632 |
+
},
|
2633 |
+
{
|
2634 |
+
"epoch": 1.1,
|
2635 |
+
"learning_rate": 4.427890580474594e-05,
|
2636 |
+
"loss": 2.6007,
|
2637 |
+
"step": 2190
|
2638 |
+
},
|
2639 |
+
{
|
2640 |
+
"epoch": 1.1,
|
2641 |
+
"learning_rate": 4.4253780405611754e-05,
|
2642 |
+
"loss": 2.8195,
|
2643 |
+
"step": 2195
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 1.1,
|
2647 |
+
"learning_rate": 4.42286071173416e-05,
|
2648 |
+
"loss": 2.5117,
|
2649 |
+
"step": 2200
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 1.11,
|
2653 |
+
"learning_rate": 4.4203386002547956e-05,
|
2654 |
+
"loss": 2.5527,
|
2655 |
+
"step": 2205
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 1.11,
|
2659 |
+
"learning_rate": 4.417811712396226e-05,
|
2660 |
+
"loss": 2.662,
|
2661 |
+
"step": 2210
|
2662 |
+
},
|
2663 |
+
{
|
2664 |
+
"epoch": 1.11,
|
2665 |
+
"learning_rate": 4.415280054443477e-05,
|
2666 |
+
"loss": 2.7563,
|
2667 |
+
"step": 2215
|
2668 |
+
},
|
2669 |
+
{
|
2670 |
+
"epoch": 1.11,
|
2671 |
+
"learning_rate": 4.4127436326934354e-05,
|
2672 |
+
"loss": 2.5118,
|
2673 |
+
"step": 2220
|
2674 |
+
},
|
2675 |
+
{
|
2676 |
+
"epoch": 1.12,
|
2677 |
+
"learning_rate": 4.41020245345484e-05,
|
2678 |
+
"loss": 2.7208,
|
2679 |
+
"step": 2225
|
2680 |
+
},
|
2681 |
+
{
|
2682 |
+
"epoch": 1.12,
|
2683 |
+
"learning_rate": 4.4076565230482607e-05,
|
2684 |
+
"loss": 2.649,
|
2685 |
+
"step": 2230
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 1.12,
|
2689 |
+
"learning_rate": 4.4051058478060856e-05,
|
2690 |
+
"loss": 2.652,
|
2691 |
+
"step": 2235
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 1.12,
|
2695 |
+
"learning_rate": 4.402550434072505e-05,
|
2696 |
+
"loss": 2.6885,
|
2697 |
+
"step": 2240
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 1.13,
|
2701 |
+
"learning_rate": 4.3999902882034935e-05,
|
2702 |
+
"loss": 2.8545,
|
2703 |
+
"step": 2245
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 1.13,
|
2707 |
+
"learning_rate": 4.397425416566797e-05,
|
2708 |
+
"loss": 2.9435,
|
2709 |
+
"step": 2250
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 1.13,
|
2713 |
+
"learning_rate": 4.3948558255419146e-05,
|
2714 |
+
"loss": 2.6555,
|
2715 |
+
"step": 2255
|
2716 |
+
},
|
2717 |
+
{
|
2718 |
+
"epoch": 1.13,
|
2719 |
+
"learning_rate": 4.392281521520085e-05,
|
2720 |
+
"loss": 2.6108,
|
2721 |
+
"step": 2260
|
2722 |
+
},
|
2723 |
+
{
|
2724 |
+
"epoch": 1.14,
|
2725 |
+
"learning_rate": 4.389702510904269e-05,
|
2726 |
+
"loss": 2.6256,
|
2727 |
+
"step": 2265
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 1.14,
|
2731 |
+
"learning_rate": 4.387118800109133e-05,
|
2732 |
+
"loss": 2.7996,
|
2733 |
+
"step": 2270
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 1.14,
|
2737 |
+
"learning_rate": 4.384530395561035e-05,
|
2738 |
+
"loss": 2.6649,
|
2739 |
+
"step": 2275
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 1.14,
|
2743 |
+
"learning_rate": 4.381937303698006e-05,
|
2744 |
+
"loss": 3.0073,
|
2745 |
+
"step": 2280
|
2746 |
+
},
|
2747 |
+
{
|
2748 |
+
"epoch": 1.15,
|
2749 |
+
"learning_rate": 4.379339530969738e-05,
|
2750 |
+
"loss": 2.8493,
|
2751 |
+
"step": 2285
|
2752 |
+
},
|
2753 |
+
{
|
2754 |
+
"epoch": 1.15,
|
2755 |
+
"learning_rate": 4.3767370838375635e-05,
|
2756 |
+
"loss": 2.5572,
|
2757 |
+
"step": 2290
|
2758 |
+
},
|
2759 |
+
{
|
2760 |
+
"epoch": 1.15,
|
2761 |
+
"learning_rate": 4.374129968774443e-05,
|
2762 |
+
"loss": 2.3837,
|
2763 |
+
"step": 2295
|
2764 |
+
},
|
2765 |
+
{
|
2766 |
+
"epoch": 1.15,
|
2767 |
+
"learning_rate": 4.371518192264946e-05,
|
2768 |
+
"loss": 2.4604,
|
2769 |
+
"step": 2300
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 1.16,
|
2773 |
+
"learning_rate": 4.3689017608052374e-05,
|
2774 |
+
"loss": 2.8866,
|
2775 |
+
"step": 2305
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 1.16,
|
2779 |
+
"learning_rate": 4.3662806809030585e-05,
|
2780 |
+
"loss": 2.8943,
|
2781 |
+
"step": 2310
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 1.16,
|
2785 |
+
"learning_rate": 4.3636549590777144e-05,
|
2786 |
+
"loss": 2.7629,
|
2787 |
+
"step": 2315
|
2788 |
+
},
|
2789 |
+
{
|
2790 |
+
"epoch": 1.16,
|
2791 |
+
"learning_rate": 4.361024601860054e-05,
|
2792 |
+
"loss": 2.8629,
|
2793 |
+
"step": 2320
|
2794 |
+
},
|
2795 |
+
{
|
2796 |
+
"epoch": 1.17,
|
2797 |
+
"learning_rate": 4.3583896157924574e-05,
|
2798 |
+
"loss": 2.7952,
|
2799 |
+
"step": 2325
|
2800 |
+
},
|
2801 |
+
{
|
2802 |
+
"epoch": 1.17,
|
2803 |
+
"learning_rate": 4.355750007428817e-05,
|
2804 |
+
"loss": 2.2057,
|
2805 |
+
"step": 2330
|
2806 |
+
},
|
2807 |
+
{
|
2808 |
+
"epoch": 1.17,
|
2809 |
+
"learning_rate": 4.3531057833345216e-05,
|
2810 |
+
"loss": 2.9143,
|
2811 |
+
"step": 2335
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 1.17,
|
2815 |
+
"learning_rate": 4.3504569500864424e-05,
|
2816 |
+
"loss": 2.5354,
|
2817 |
+
"step": 2340
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 1.18,
|
2821 |
+
"learning_rate": 4.347803514272911e-05,
|
2822 |
+
"loss": 2.7451,
|
2823 |
+
"step": 2345
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 1.18,
|
2827 |
+
"learning_rate": 4.3451454824937113e-05,
|
2828 |
+
"loss": 3.0827,
|
2829 |
+
"step": 2350
|
2830 |
+
},
|
2831 |
+
{
|
2832 |
+
"epoch": 1.18,
|
2833 |
+
"learning_rate": 4.3424828613600555e-05,
|
2834 |
+
"loss": 2.5842,
|
2835 |
+
"step": 2355
|
2836 |
+
},
|
2837 |
+
{
|
2838 |
+
"epoch": 1.18,
|
2839 |
+
"learning_rate": 4.339815657494572e-05,
|
2840 |
+
"loss": 2.4492,
|
2841 |
+
"step": 2360
|
2842 |
+
},
|
2843 |
+
{
|
2844 |
+
"epoch": 1.19,
|
2845 |
+
"learning_rate": 4.3371438775312865e-05,
|
2846 |
+
"loss": 2.5067,
|
2847 |
+
"step": 2365
|
2848 |
+
},
|
2849 |
+
{
|
2850 |
+
"epoch": 1.19,
|
2851 |
+
"learning_rate": 4.334467528115608e-05,
|
2852 |
+
"loss": 2.5902,
|
2853 |
+
"step": 2370
|
2854 |
+
},
|
2855 |
+
{
|
2856 |
+
"epoch": 1.19,
|
2857 |
+
"learning_rate": 4.33178661590431e-05,
|
2858 |
+
"loss": 2.8618,
|
2859 |
+
"step": 2375
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 1.19,
|
2863 |
+
"learning_rate": 4.329101147565515e-05,
|
2864 |
+
"loss": 2.6831,
|
2865 |
+
"step": 2380
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 1.2,
|
2869 |
+
"learning_rate": 4.3264111297786794e-05,
|
2870 |
+
"loss": 2.7531,
|
2871 |
+
"step": 2385
|
2872 |
+
},
|
2873 |
+
{
|
2874 |
+
"epoch": 1.2,
|
2875 |
+
"learning_rate": 4.323716569234572e-05,
|
2876 |
+
"loss": 2.819,
|
2877 |
+
"step": 2390
|
2878 |
+
},
|
2879 |
+
{
|
2880 |
+
"epoch": 1.2,
|
2881 |
+
"learning_rate": 4.321017472635263e-05,
|
2882 |
+
"loss": 2.6319,
|
2883 |
+
"step": 2395
|
2884 |
+
},
|
2885 |
+
{
|
2886 |
+
"epoch": 1.2,
|
2887 |
+
"learning_rate": 4.318313846694105e-05,
|
2888 |
+
"loss": 2.3078,
|
2889 |
+
"step": 2400
|
2890 |
+
},
|
2891 |
+
{
|
2892 |
+
"epoch": 1.21,
|
2893 |
+
"learning_rate": 4.315605698135714e-05,
|
2894 |
+
"loss": 2.7962,
|
2895 |
+
"step": 2405
|
2896 |
+
},
|
2897 |
+
{
|
2898 |
+
"epoch": 1.21,
|
2899 |
+
"learning_rate": 4.312893033695958e-05,
|
2900 |
+
"loss": 2.8479,
|
2901 |
+
"step": 2410
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 1.21,
|
2905 |
+
"learning_rate": 4.310175860121936e-05,
|
2906 |
+
"loss": 2.6289,
|
2907 |
+
"step": 2415
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 1.21,
|
2911 |
+
"learning_rate": 4.30745418417196e-05,
|
2912 |
+
"loss": 2.7003,
|
2913 |
+
"step": 2420
|
2914 |
+
},
|
2915 |
+
{
|
2916 |
+
"epoch": 1.22,
|
2917 |
+
"learning_rate": 4.304728012615543e-05,
|
2918 |
+
"loss": 2.4947,
|
2919 |
+
"step": 2425
|
2920 |
+
},
|
2921 |
+
{
|
2922 |
+
"epoch": 1.22,
|
2923 |
+
"learning_rate": 4.3019973522333815e-05,
|
2924 |
+
"loss": 2.6911,
|
2925 |
+
"step": 2430
|
2926 |
+
},
|
2927 |
+
{
|
2928 |
+
"epoch": 1.22,
|
2929 |
+
"learning_rate": 4.2992622098173334e-05,
|
2930 |
+
"loss": 2.6931,
|
2931 |
+
"step": 2435
|
2932 |
+
},
|
2933 |
+
{
|
2934 |
+
"epoch": 1.22,
|
2935 |
+
"learning_rate": 4.296522592170406e-05,
|
2936 |
+
"loss": 2.774,
|
2937 |
+
"step": 2440
|
2938 |
+
},
|
2939 |
+
{
|
2940 |
+
"epoch": 1.23,
|
2941 |
+
"learning_rate": 4.293778506106737e-05,
|
2942 |
+
"loss": 2.759,
|
2943 |
+
"step": 2445
|
2944 |
+
},
|
2945 |
+
{
|
2946 |
+
"epoch": 1.23,
|
2947 |
+
"learning_rate": 4.29102995845158e-05,
|
2948 |
+
"loss": 2.5543,
|
2949 |
+
"step": 2450
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 1.23,
|
2953 |
+
"learning_rate": 4.288276956041284e-05,
|
2954 |
+
"loss": 2.7702,
|
2955 |
+
"step": 2455
|
2956 |
+
},
|
2957 |
+
{
|
2958 |
+
"epoch": 1.23,
|
2959 |
+
"learning_rate": 4.285519505723278e-05,
|
2960 |
+
"loss": 2.835,
|
2961 |
+
"step": 2460
|
2962 |
+
},
|
2963 |
+
{
|
2964 |
+
"epoch": 1.24,
|
2965 |
+
"learning_rate": 4.282757614356055e-05,
|
2966 |
+
"loss": 2.6516,
|
2967 |
+
"step": 2465
|
2968 |
+
},
|
2969 |
+
{
|
2970 |
+
"epoch": 1.24,
|
2971 |
+
"learning_rate": 4.2799912888091544e-05,
|
2972 |
+
"loss": 2.7392,
|
2973 |
+
"step": 2470
|
2974 |
+
},
|
2975 |
+
{
|
2976 |
+
"epoch": 1.24,
|
2977 |
+
"learning_rate": 4.277220535963143e-05,
|
2978 |
+
"loss": 2.6522,
|
2979 |
+
"step": 2475
|
2980 |
+
},
|
2981 |
+
{
|
2982 |
+
"epoch": 1.24,
|
2983 |
+
"learning_rate": 4.274445362709601e-05,
|
2984 |
+
"loss": 2.6514,
|
2985 |
+
"step": 2480
|
2986 |
+
},
|
2987 |
+
{
|
2988 |
+
"epoch": 1.25,
|
2989 |
+
"learning_rate": 4.271665775951104e-05,
|
2990 |
+
"loss": 2.7507,
|
2991 |
+
"step": 2485
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 1.25,
|
2995 |
+
"learning_rate": 4.2688817826012005e-05,
|
2996 |
+
"loss": 3.0499,
|
2997 |
+
"step": 2490
|
2998 |
+
},
|
2999 |
+
{
|
3000 |
+
"epoch": 1.25,
|
3001 |
+
"learning_rate": 4.2660933895844055e-05,
|
3002 |
+
"loss": 2.6927,
|
3003 |
+
"step": 2495
|
3004 |
+
},
|
3005 |
+
{
|
3006 |
+
"epoch": 1.25,
|
3007 |
+
"learning_rate": 4.2633006038361736e-05,
|
3008 |
+
"loss": 2.8456,
|
3009 |
+
"step": 2500
|
3010 |
+
}
|
3011 |
+
],
|
3012 |
+
"logging_steps": 5,
|
3013 |
+
"max_steps": 9960,
|
3014 |
+
"num_input_tokens_seen": 0,
|
3015 |
+
"num_train_epochs": 5,
|
3016 |
+
"save_steps": 500,
|
3017 |
+
"total_flos": 1.3252546968069734e+17,
|
3018 |
+
"train_batch_size": 1,
|
3019 |
+
"trial_name": null,
|
3020 |
+
"trial_params": null
|
3021 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:939ee45e9035366dc4952c5158e7d3a0d3426acdbfb5014d53ad1e260b19a19f
|
3 |
+
size 4475
|
checkpoint-3000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chatglm3-6b-base
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-3000/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chatglm3-6b-base",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"query_key_value"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM",
|
25 |
+
"use_rslora": false
|
26 |
+
}
|