wangrongsheng
commited on
Commit
•
d824d87
1
Parent(s):
7b4eaac
Upload 12 files
Browse files- checkpoint-3000/README.md +204 -0
- checkpoint-3000/adapter_config.json +26 -0
- checkpoint-3000/adapter_model.safetensors +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/special_tokens_map.json +24 -0
- checkpoint-3000/tokenizer.json +0 -0
- checkpoint-3000/tokenizer.model +3 -0
- checkpoint-3000/tokenizer_config.json +45 -0
- checkpoint-3000/trainer_state.json +201 -0
- checkpoint-3000/training_args.bin +3 -0
checkpoint-3000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../Mixtral-8x7B-Instruct-v0.1
|
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 0.7.1
|
checkpoint-3000/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../Mixtral-8x7B-Instruct-v0.1",
|
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": 16.0,
|
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 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
checkpoint-3000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2564b0e412d10c638a7f55db0f192907eb486c22d85f414e45c1a01fe4bbb7ab
|
3 |
+
size 13648432
|
checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f629234b4d4b6e4136bfbf33d33a05afcc6735ecc88b96021ad0550d6e7fa2fa
|
3 |
+
size 27370618
|
checkpoint-3000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e525010bd3e301d1a9baf595cfa73054e1f986410ee07cfed9132d7c4ff963e9
|
3 |
+
size 14244
|
checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c17ca6ece7cdf07f80ff7a74d47d72acc281b79be86bd1dcced57844befb15ff
|
3 |
+
size 1064
|
checkpoint-3000/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-3000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3000/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-3000/tokenizer_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|
checkpoint-3000/trainer_state.json
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5438230762258679,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 4.999549488698767e-05,
|
14 |
+
"loss": 0.9367,
|
15 |
+
"step": 100
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.04,
|
19 |
+
"learning_rate": 4.998198117163414e-05,
|
20 |
+
"loss": 0.8539,
|
21 |
+
"step": 200
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.05,
|
25 |
+
"learning_rate": 4.995946372440459e-05,
|
26 |
+
"loss": 0.8563,
|
27 |
+
"step": 300
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.07,
|
31 |
+
"learning_rate": 4.99279506607906e-05,
|
32 |
+
"loss": 0.8552,
|
33 |
+
"step": 400
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.09,
|
37 |
+
"learning_rate": 4.9887453338385195e-05,
|
38 |
+
"loss": 0.8377,
|
39 |
+
"step": 500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.11,
|
43 |
+
"learning_rate": 4.98379863527895e-05,
|
44 |
+
"loss": 0.8346,
|
45 |
+
"step": 600
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.13,
|
49 |
+
"learning_rate": 4.9779567532352364e-05,
|
50 |
+
"loss": 0.8338,
|
51 |
+
"step": 700
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.15,
|
55 |
+
"learning_rate": 4.971221793174483e-05,
|
56 |
+
"loss": 0.8176,
|
57 |
+
"step": 800
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.16,
|
61 |
+
"learning_rate": 4.9635961824371865e-05,
|
62 |
+
"loss": 0.8297,
|
63 |
+
"step": 900
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.18,
|
67 |
+
"learning_rate": 4.9550826693624e-05,
|
68 |
+
"loss": 0.8337,
|
69 |
+
"step": 1000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.2,
|
73 |
+
"learning_rate": 4.945684322297207e-05,
|
74 |
+
"loss": 0.8243,
|
75 |
+
"step": 1100
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.22,
|
79 |
+
"learning_rate": 4.935404528490858e-05,
|
80 |
+
"loss": 0.8289,
|
81 |
+
"step": 1200
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.24,
|
85 |
+
"learning_rate": 4.924246992873982e-05,
|
86 |
+
"loss": 0.818,
|
87 |
+
"step": 1300
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.25,
|
91 |
+
"learning_rate": 4.9122157367232894e-05,
|
92 |
+
"loss": 0.8361,
|
93 |
+
"step": 1400
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.27,
|
97 |
+
"learning_rate": 4.899315096212272e-05,
|
98 |
+
"loss": 0.8055,
|
99 |
+
"step": 1500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.29,
|
103 |
+
"learning_rate": 4.8855497208484046e-05,
|
104 |
+
"loss": 0.8284,
|
105 |
+
"step": 1600
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.31,
|
109 |
+
"learning_rate": 4.8709245717974204e-05,
|
110 |
+
"loss": 0.8214,
|
111 |
+
"step": 1700
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.33,
|
115 |
+
"learning_rate": 4.8554449200952635e-05,
|
116 |
+
"loss": 0.8243,
|
117 |
+
"step": 1800
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.34,
|
121 |
+
"learning_rate": 4.8391163447483587e-05,
|
122 |
+
"loss": 0.8191,
|
123 |
+
"step": 1900
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.36,
|
127 |
+
"learning_rate": 4.821944730722887e-05,
|
128 |
+
"loss": 0.8106,
|
129 |
+
"step": 2000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.38,
|
133 |
+
"learning_rate": 4.803936266823792e-05,
|
134 |
+
"loss": 0.8217,
|
135 |
+
"step": 2100
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.4,
|
139 |
+
"learning_rate": 4.785097443464276e-05,
|
140 |
+
"loss": 0.8071,
|
141 |
+
"step": 2200
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.42,
|
145 |
+
"learning_rate": 4.765435050326602e-05,
|
146 |
+
"loss": 0.8164,
|
147 |
+
"step": 2300
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.44,
|
151 |
+
"learning_rate": 4.744956173915022e-05,
|
152 |
+
"loss": 0.8264,
|
153 |
+
"step": 2400
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.45,
|
157 |
+
"learning_rate": 4.7236681950017445e-05,
|
158 |
+
"loss": 0.8183,
|
159 |
+
"step": 2500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.47,
|
163 |
+
"learning_rate": 4.701578785966834e-05,
|
164 |
+
"loss": 0.8035,
|
165 |
+
"step": 2600
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.49,
|
169 |
+
"learning_rate": 4.678695908033017e-05,
|
170 |
+
"loss": 0.8019,
|
171 |
+
"step": 2700
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.51,
|
175 |
+
"learning_rate": 4.655027808396385e-05,
|
176 |
+
"loss": 0.8084,
|
177 |
+
"step": 2800
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.53,
|
181 |
+
"learning_rate": 4.6305830172540295e-05,
|
182 |
+
"loss": 0.8124,
|
183 |
+
"step": 2900
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.54,
|
187 |
+
"learning_rate": 4.6053703447296826e-05,
|
188 |
+
"loss": 0.8206,
|
189 |
+
"step": 3000
|
190 |
+
}
|
191 |
+
],
|
192 |
+
"logging_steps": 100,
|
193 |
+
"max_steps": 16548,
|
194 |
+
"num_input_tokens_seen": 0,
|
195 |
+
"num_train_epochs": 3,
|
196 |
+
"save_steps": 1000,
|
197 |
+
"total_flos": 2.70850483937917e+19,
|
198 |
+
"train_batch_size": 8,
|
199 |
+
"trial_name": null,
|
200 |
+
"trial_params": null
|
201 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa7a663df5d51189395ab17cd8d05c0ddf115d085be87877276d34700f9d01fc
|
3 |
+
size 4856
|