Commit
•
254f473
1
Parent(s):
e3bec14
Initial commit
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- trainer_state.json +371 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
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 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.9.0
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/root/data/mist",
|
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": 0.2,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 32,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"gate_proj",
|
24 |
+
"down_proj",
|
25 |
+
"v_proj",
|
26 |
+
"up_proj",
|
27 |
+
"o_proj",
|
28 |
+
"lm_head",
|
29 |
+
"k_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a363db77cd1131f1c080c0bb3639500fd06e487f5665f0be76bce585506cdd8e
|
3 |
+
size 319015728
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d891324d1d48728e7fbf78395cd3c47b604336bffdcfc9fcd9f8b610b636339
|
3 |
+
size 57254236
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23841f15a6de978179c16b2c1a7bf437b510d884a9dd84b6520b91e3d6dac6b2
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db30ced47f9462c957ad6ad62e18e7733e592ff37955f32cdc53e4cde8b10dd8
|
3 |
+
size 1064
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,371 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0251447504387619,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 250,
|
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 |
+
"grad_norm": 0.0849609375,
|
14 |
+
"learning_rate": 3.8000000000000005e-06,
|
15 |
+
"loss": 1.2889,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04,
|
20 |
+
"grad_norm": 0.083984375,
|
21 |
+
"learning_rate": 7.600000000000001e-06,
|
22 |
+
"loss": 1.2871,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06,
|
27 |
+
"grad_norm": 0.08447265625,
|
28 |
+
"learning_rate": 1.1400000000000001e-05,
|
29 |
+
"loss": 1.2972,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.08,
|
34 |
+
"grad_norm": 0.0869140625,
|
35 |
+
"learning_rate": 1.5200000000000002e-05,
|
36 |
+
"loss": 1.2867,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.1,
|
41 |
+
"grad_norm": 0.0908203125,
|
42 |
+
"learning_rate": 1.9e-05,
|
43 |
+
"loss": 1.2884,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.12,
|
48 |
+
"grad_norm": 0.09130859375,
|
49 |
+
"learning_rate": 2.2800000000000002e-05,
|
50 |
+
"loss": 1.2734,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.14,
|
55 |
+
"grad_norm": 0.08642578125,
|
56 |
+
"learning_rate": 2.66e-05,
|
57 |
+
"loss": 1.2667,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.16,
|
62 |
+
"grad_norm": 0.0849609375,
|
63 |
+
"learning_rate": 3.0400000000000004e-05,
|
64 |
+
"loss": 1.2469,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.18,
|
69 |
+
"grad_norm": 0.08203125,
|
70 |
+
"learning_rate": 3.4200000000000005e-05,
|
71 |
+
"loss": 1.2343,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.21,
|
76 |
+
"grad_norm": 0.08935546875,
|
77 |
+
"learning_rate": 3.8e-05,
|
78 |
+
"loss": 1.2214,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.23,
|
83 |
+
"grad_norm": 0.087890625,
|
84 |
+
"learning_rate": 3.705e-05,
|
85 |
+
"loss": 1.2089,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.25,
|
90 |
+
"grad_norm": 0.0810546875,
|
91 |
+
"learning_rate": 3.61e-05,
|
92 |
+
"loss": 1.1902,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.27,
|
97 |
+
"grad_norm": 0.0810546875,
|
98 |
+
"learning_rate": 3.515e-05,
|
99 |
+
"loss": 1.18,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.29,
|
104 |
+
"grad_norm": 0.087890625,
|
105 |
+
"learning_rate": 3.4200000000000005e-05,
|
106 |
+
"loss": 1.1726,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.31,
|
111 |
+
"grad_norm": 0.0947265625,
|
112 |
+
"learning_rate": 3.325e-05,
|
113 |
+
"loss": 1.168,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.33,
|
118 |
+
"grad_norm": 0.099609375,
|
119 |
+
"learning_rate": 3.23e-05,
|
120 |
+
"loss": 1.1664,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.35,
|
125 |
+
"grad_norm": 0.103515625,
|
126 |
+
"learning_rate": 3.135e-05,
|
127 |
+
"loss": 1.1573,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.37,
|
132 |
+
"grad_norm": 0.10595703125,
|
133 |
+
"learning_rate": 3.0400000000000004e-05,
|
134 |
+
"loss": 1.1506,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.39,
|
139 |
+
"grad_norm": 0.10791015625,
|
140 |
+
"learning_rate": 2.945e-05,
|
141 |
+
"loss": 1.1515,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.41,
|
146 |
+
"grad_norm": 0.11474609375,
|
147 |
+
"learning_rate": 2.85e-05,
|
148 |
+
"loss": 1.1445,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.43,
|
153 |
+
"grad_norm": 0.12060546875,
|
154 |
+
"learning_rate": 2.7550000000000002e-05,
|
155 |
+
"loss": 1.1444,
|
156 |
+
"step": 105
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.45,
|
160 |
+
"grad_norm": 0.126953125,
|
161 |
+
"learning_rate": 2.66e-05,
|
162 |
+
"loss": 1.145,
|
163 |
+
"step": 110
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.47,
|
167 |
+
"grad_norm": 0.126953125,
|
168 |
+
"learning_rate": 2.5650000000000003e-05,
|
169 |
+
"loss": 1.1398,
|
170 |
+
"step": 115
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.49,
|
174 |
+
"grad_norm": 0.12890625,
|
175 |
+
"learning_rate": 2.47e-05,
|
176 |
+
"loss": 1.129,
|
177 |
+
"step": 120
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.51,
|
181 |
+
"grad_norm": 0.1123046875,
|
182 |
+
"learning_rate": 2.375e-05,
|
183 |
+
"loss": 1.1365,
|
184 |
+
"step": 125
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.53,
|
188 |
+
"grad_norm": 0.10791015625,
|
189 |
+
"learning_rate": 2.2800000000000002e-05,
|
190 |
+
"loss": 1.1243,
|
191 |
+
"step": 130
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.55,
|
195 |
+
"grad_norm": 0.09765625,
|
196 |
+
"learning_rate": 2.185e-05,
|
197 |
+
"loss": 1.1268,
|
198 |
+
"step": 135
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.57,
|
202 |
+
"grad_norm": 0.0771484375,
|
203 |
+
"learning_rate": 2.0900000000000003e-05,
|
204 |
+
"loss": 1.1283,
|
205 |
+
"step": 140
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.59,
|
209 |
+
"grad_norm": 0.0625,
|
210 |
+
"learning_rate": 1.995e-05,
|
211 |
+
"loss": 1.1224,
|
212 |
+
"step": 145
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.62,
|
216 |
+
"grad_norm": 0.0517578125,
|
217 |
+
"learning_rate": 1.9e-05,
|
218 |
+
"loss": 1.1284,
|
219 |
+
"step": 150
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.64,
|
223 |
+
"grad_norm": 0.044921875,
|
224 |
+
"learning_rate": 1.805e-05,
|
225 |
+
"loss": 1.1182,
|
226 |
+
"step": 155
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.66,
|
230 |
+
"grad_norm": 0.0419921875,
|
231 |
+
"learning_rate": 1.7100000000000002e-05,
|
232 |
+
"loss": 1.1255,
|
233 |
+
"step": 160
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.68,
|
237 |
+
"grad_norm": 0.04052734375,
|
238 |
+
"learning_rate": 1.615e-05,
|
239 |
+
"loss": 1.1197,
|
240 |
+
"step": 165
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.7,
|
244 |
+
"grad_norm": 0.0390625,
|
245 |
+
"learning_rate": 1.5200000000000002e-05,
|
246 |
+
"loss": 1.1243,
|
247 |
+
"step": 170
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.72,
|
251 |
+
"grad_norm": 0.037353515625,
|
252 |
+
"learning_rate": 1.425e-05,
|
253 |
+
"loss": 1.1249,
|
254 |
+
"step": 175
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.74,
|
258 |
+
"grad_norm": 0.03759765625,
|
259 |
+
"learning_rate": 1.33e-05,
|
260 |
+
"loss": 1.1235,
|
261 |
+
"step": 180
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.76,
|
265 |
+
"grad_norm": 0.037353515625,
|
266 |
+
"learning_rate": 1.235e-05,
|
267 |
+
"loss": 1.1184,
|
268 |
+
"step": 185
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.78,
|
272 |
+
"grad_norm": 0.036376953125,
|
273 |
+
"learning_rate": 1.1400000000000001e-05,
|
274 |
+
"loss": 1.1152,
|
275 |
+
"step": 190
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.8,
|
279 |
+
"grad_norm": 0.0361328125,
|
280 |
+
"learning_rate": 1.0450000000000002e-05,
|
281 |
+
"loss": 1.1201,
|
282 |
+
"step": 195
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.82,
|
286 |
+
"grad_norm": 0.035888671875,
|
287 |
+
"learning_rate": 9.5e-06,
|
288 |
+
"loss": 1.1206,
|
289 |
+
"step": 200
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.84,
|
293 |
+
"grad_norm": 0.034912109375,
|
294 |
+
"learning_rate": 8.550000000000001e-06,
|
295 |
+
"loss": 1.1155,
|
296 |
+
"step": 205
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.86,
|
300 |
+
"grad_norm": 0.033935546875,
|
301 |
+
"learning_rate": 7.600000000000001e-06,
|
302 |
+
"loss": 1.1136,
|
303 |
+
"step": 210
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.88,
|
307 |
+
"grad_norm": 0.03515625,
|
308 |
+
"learning_rate": 6.65e-06,
|
309 |
+
"loss": 1.1167,
|
310 |
+
"step": 215
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.9,
|
314 |
+
"grad_norm": 0.034423828125,
|
315 |
+
"learning_rate": 5.7000000000000005e-06,
|
316 |
+
"loss": 1.1177,
|
317 |
+
"step": 220
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.92,
|
321 |
+
"grad_norm": 0.0341796875,
|
322 |
+
"learning_rate": 4.75e-06,
|
323 |
+
"loss": 1.1191,
|
324 |
+
"step": 225
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.94,
|
328 |
+
"grad_norm": 0.03369140625,
|
329 |
+
"learning_rate": 3.8000000000000005e-06,
|
330 |
+
"loss": 1.1215,
|
331 |
+
"step": 230
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.96,
|
335 |
+
"grad_norm": 0.032958984375,
|
336 |
+
"learning_rate": 2.8500000000000002e-06,
|
337 |
+
"loss": 1.1171,
|
338 |
+
"step": 235
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.98,
|
342 |
+
"grad_norm": 0.033935546875,
|
343 |
+
"learning_rate": 1.9000000000000002e-06,
|
344 |
+
"loss": 1.119,
|
345 |
+
"step": 240
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.0,
|
349 |
+
"grad_norm": 0.033447265625,
|
350 |
+
"learning_rate": 9.500000000000001e-07,
|
351 |
+
"loss": 1.1161,
|
352 |
+
"step": 245
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.03,
|
356 |
+
"grad_norm": 0.035400390625,
|
357 |
+
"learning_rate": 0.0,
|
358 |
+
"loss": 1.1181,
|
359 |
+
"step": 250
|
360 |
+
}
|
361 |
+
],
|
362 |
+
"logging_steps": 5,
|
363 |
+
"max_steps": 250,
|
364 |
+
"num_input_tokens_seen": 0,
|
365 |
+
"num_train_epochs": 2,
|
366 |
+
"save_steps": 50,
|
367 |
+
"total_flos": 5.8437883477546985e+20,
|
368 |
+
"train_batch_size": 16,
|
369 |
+
"trial_name": null,
|
370 |
+
"trial_params": null
|
371 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d104c5210866ca6abbb662fc619affec98c6453f7ab44bec55a7e7f924998b13
|
3 |
+
size 4984
|