Jamesb1974
commited on
Commit
•
011e93a
1
Parent(s):
f8c3de3
Upload folder using huggingface_hub
Browse files- README.md +45 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- checkpoint-1692/README.md +202 -0
- checkpoint-1692/adapter_config.json +30 -0
- checkpoint-1692/adapter_model.safetensors +3 -0
- checkpoint-1692/merges.txt +0 -0
- checkpoint-1692/optimizer.pt +3 -0
- checkpoint-1692/pytorch_model.bin +3 -0
- checkpoint-1692/rng_state.pth +3 -0
- checkpoint-1692/scheduler.pt +3 -0
- checkpoint-1692/special_tokens_map.json +6 -0
- checkpoint-1692/tokenizer.json +0 -0
- checkpoint-1692/tokenizer_config.json +21 -0
- checkpoint-1692/trainer_state.json +490 -0
- checkpoint-1692/training_args.bin +3 -0
- checkpoint-1692/vocab.json +0 -0
- merges.txt +0 -0
- runs/Mar26_18-00-07_r-jamesb1974-gpu01-qp88jhm1-82ea1-9m4x0/events.out.tfevents.1711476024.r-jamesb1974-gpu01-qp88jhm1-82ea1-9m4x0.59.0 +2 -2
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
- training_args.bin +3 -0
- training_params.json +47 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation-inference
|
5 |
+
- text-generation
|
6 |
+
- peft
|
7 |
+
library_name: transformers
|
8 |
+
widget:
|
9 |
+
- messages:
|
10 |
+
- role: user
|
11 |
+
content: What is your favorite condiment?
|
12 |
+
license: other
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
18 |
+
|
19 |
+
# Usage
|
20 |
+
|
21 |
+
```python
|
22 |
+
|
23 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
24 |
+
|
25 |
+
model_path = "PATH_TO_THIS_REPO"
|
26 |
+
|
27 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
28 |
+
model = AutoModelForCausalLM.from_pretrained(
|
29 |
+
model_path,
|
30 |
+
device_map="auto",
|
31 |
+
torch_dtype='auto'
|
32 |
+
).eval()
|
33 |
+
|
34 |
+
# Prompt content: "hi"
|
35 |
+
messages = [
|
36 |
+
{"role": "user", "content": "hi"}
|
37 |
+
]
|
38 |
+
|
39 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
40 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
41 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
42 |
+
|
43 |
+
# Model response: "Hello! How can I assist you today?"
|
44 |
+
print(response)
|
45 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "openai-community/gpt2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"c_fc",
|
24 |
+
"c_proj",
|
25 |
+
"c_attn"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c45a42f905fd1a44e0ed514b32e7ea28948b7639bde566d64504aea76396253
|
3 |
+
size 9449344
|
checkpoint-1692/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: openai-community/gpt2
|
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 0.10.0
|
checkpoint-1692/adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "openai-community/gpt2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"c_fc",
|
24 |
+
"c_proj",
|
25 |
+
"c_attn"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
checkpoint-1692/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c45a42f905fd1a44e0ed514b32e7ea28948b7639bde566d64504aea76396253
|
3 |
+
size 9449344
|
checkpoint-1692/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1692/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8f07406ffd023ba533bd7135ce04312d2b3f0610df44424616068187be6ea99
|
3 |
+
size 18955258
|
checkpoint-1692/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
3 |
+
size 888
|
checkpoint-1692/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:925aad33224612bec594f1cb1bdb1388a6482a077657ac2c1e61d18b0b3c0cea
|
3 |
+
size 14244
|
checkpoint-1692/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fbae99cde5719c20e99dd79ca88cef840dc6e53000088c57d9cc3d755302753
|
3 |
+
size 1064
|
checkpoint-1692/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
checkpoint-1692/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1692/tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
20 |
+
"unk_token": "<|endoftext|>"
|
21 |
+
}
|
checkpoint-1692/trainer_state.json
ADDED
@@ -0,0 +1,490 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.997342781222321,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1692,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"grad_norm": 1.2252470254898071,
|
14 |
+
"learning_rate": 4.411764705882353e-06,
|
15 |
+
"loss": 2.746,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09,
|
20 |
+
"grad_norm": 1.2458932399749756,
|
21 |
+
"learning_rate": 8.823529411764707e-06,
|
22 |
+
"loss": 2.7375,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.13,
|
27 |
+
"grad_norm": 0.9806848764419556,
|
28 |
+
"learning_rate": 1.323529411764706e-05,
|
29 |
+
"loss": 2.6088,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.18,
|
34 |
+
"grad_norm": 0.7579270601272583,
|
35 |
+
"learning_rate": 1.7647058823529414e-05,
|
36 |
+
"loss": 2.3883,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.22,
|
41 |
+
"grad_norm": 0.5973591804504395,
|
42 |
+
"learning_rate": 2.2058823529411766e-05,
|
43 |
+
"loss": 2.148,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.27,
|
48 |
+
"grad_norm": 0.4005584120750427,
|
49 |
+
"learning_rate": 2.647058823529412e-05,
|
50 |
+
"loss": 1.9697,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.31,
|
55 |
+
"grad_norm": 0.30321258306503296,
|
56 |
+
"learning_rate": 2.990144546649146e-05,
|
57 |
+
"loss": 1.8807,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.35,
|
62 |
+
"grad_norm": 0.33162617683410645,
|
63 |
+
"learning_rate": 2.9408672798948752e-05,
|
64 |
+
"loss": 1.788,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.4,
|
69 |
+
"grad_norm": 0.35974565148353577,
|
70 |
+
"learning_rate": 2.8915900131406044e-05,
|
71 |
+
"loss": 1.7825,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.44,
|
76 |
+
"grad_norm": 0.33461177349090576,
|
77 |
+
"learning_rate": 2.842312746386334e-05,
|
78 |
+
"loss": 1.7241,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.49,
|
83 |
+
"grad_norm": 0.31440624594688416,
|
84 |
+
"learning_rate": 2.793035479632063e-05,
|
85 |
+
"loss": 1.6708,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.53,
|
90 |
+
"grad_norm": 0.32463395595550537,
|
91 |
+
"learning_rate": 2.7437582128777926e-05,
|
92 |
+
"loss": 1.6098,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.58,
|
97 |
+
"grad_norm": 0.35138121247291565,
|
98 |
+
"learning_rate": 2.6944809461235218e-05,
|
99 |
+
"loss": 1.5992,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.62,
|
104 |
+
"grad_norm": 0.3213985562324524,
|
105 |
+
"learning_rate": 2.645203679369251e-05,
|
106 |
+
"loss": 1.5133,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.66,
|
111 |
+
"grad_norm": 0.30699512362480164,
|
112 |
+
"learning_rate": 2.5959264126149805e-05,
|
113 |
+
"loss": 1.4807,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.71,
|
118 |
+
"grad_norm": 0.3282407522201538,
|
119 |
+
"learning_rate": 2.5466491458607097e-05,
|
120 |
+
"loss": 1.4928,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.75,
|
125 |
+
"grad_norm": 0.36608022451400757,
|
126 |
+
"learning_rate": 2.4973718791064392e-05,
|
127 |
+
"loss": 1.4802,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.8,
|
132 |
+
"grad_norm": 0.38351428508758545,
|
133 |
+
"learning_rate": 2.4480946123521684e-05,
|
134 |
+
"loss": 1.4886,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.84,
|
139 |
+
"grad_norm": 0.3251235783100128,
|
140 |
+
"learning_rate": 2.3988173455978975e-05,
|
141 |
+
"loss": 1.4557,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.89,
|
146 |
+
"grad_norm": 0.3361181914806366,
|
147 |
+
"learning_rate": 2.349540078843627e-05,
|
148 |
+
"loss": 1.3857,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.93,
|
153 |
+
"grad_norm": 0.36659279465675354,
|
154 |
+
"learning_rate": 2.3002628120893562e-05,
|
155 |
+
"loss": 1.4257,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.97,
|
160 |
+
"grad_norm": 0.4663073420524597,
|
161 |
+
"learning_rate": 2.2509855453350857e-05,
|
162 |
+
"loss": 1.4516,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.02,
|
167 |
+
"grad_norm": 0.3494812846183777,
|
168 |
+
"learning_rate": 2.201708278580815e-05,
|
169 |
+
"loss": 1.3714,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.06,
|
174 |
+
"grad_norm": 0.3586205542087555,
|
175 |
+
"learning_rate": 2.152431011826544e-05,
|
176 |
+
"loss": 1.3569,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.11,
|
181 |
+
"grad_norm": 0.38619765639305115,
|
182 |
+
"learning_rate": 2.1031537450722736e-05,
|
183 |
+
"loss": 1.3331,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.15,
|
188 |
+
"grad_norm": 0.3586406111717224,
|
189 |
+
"learning_rate": 2.0538764783180025e-05,
|
190 |
+
"loss": 1.3446,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.2,
|
195 |
+
"grad_norm": 0.33255332708358765,
|
196 |
+
"learning_rate": 2.004599211563732e-05,
|
197 |
+
"loss": 1.3421,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.24,
|
202 |
+
"grad_norm": 0.362377792596817,
|
203 |
+
"learning_rate": 1.955321944809461e-05,
|
204 |
+
"loss": 1.3543,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.28,
|
209 |
+
"grad_norm": 0.43340814113616943,
|
210 |
+
"learning_rate": 1.9060446780551903e-05,
|
211 |
+
"loss": 1.3592,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.33,
|
216 |
+
"grad_norm": 0.43384671211242676,
|
217 |
+
"learning_rate": 1.85676741130092e-05,
|
218 |
+
"loss": 1.3393,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.37,
|
223 |
+
"grad_norm": 0.6346977353096008,
|
224 |
+
"learning_rate": 1.807490144546649e-05,
|
225 |
+
"loss": 1.3142,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.42,
|
230 |
+
"grad_norm": 0.37973758578300476,
|
231 |
+
"learning_rate": 1.7582128777923785e-05,
|
232 |
+
"loss": 1.3279,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.46,
|
237 |
+
"grad_norm": 0.3827611207962036,
|
238 |
+
"learning_rate": 1.7089356110381077e-05,
|
239 |
+
"loss": 1.3263,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.51,
|
244 |
+
"grad_norm": 0.4215668737888336,
|
245 |
+
"learning_rate": 1.659658344283837e-05,
|
246 |
+
"loss": 1.3353,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.55,
|
251 |
+
"grad_norm": 0.3658856153488159,
|
252 |
+
"learning_rate": 1.6103810775295664e-05,
|
253 |
+
"loss": 1.3144,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.59,
|
258 |
+
"grad_norm": 0.3511466383934021,
|
259 |
+
"learning_rate": 1.5611038107752956e-05,
|
260 |
+
"loss": 1.2621,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.64,
|
265 |
+
"grad_norm": 0.3667345941066742,
|
266 |
+
"learning_rate": 1.511826544021025e-05,
|
267 |
+
"loss": 1.2563,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.68,
|
272 |
+
"grad_norm": 0.40708670020103455,
|
273 |
+
"learning_rate": 1.4625492772667543e-05,
|
274 |
+
"loss": 1.2945,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.73,
|
279 |
+
"grad_norm": 0.42138373851776123,
|
280 |
+
"learning_rate": 1.4132720105124836e-05,
|
281 |
+
"loss": 1.3062,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.77,
|
286 |
+
"grad_norm": 0.35037311911582947,
|
287 |
+
"learning_rate": 1.3639947437582128e-05,
|
288 |
+
"loss": 1.2745,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.82,
|
293 |
+
"grad_norm": 0.48709043860435486,
|
294 |
+
"learning_rate": 1.3147174770039422e-05,
|
295 |
+
"loss": 1.3324,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.86,
|
300 |
+
"grad_norm": 0.38190776109695435,
|
301 |
+
"learning_rate": 1.2654402102496715e-05,
|
302 |
+
"loss": 1.2465,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.9,
|
307 |
+
"grad_norm": 0.4355185329914093,
|
308 |
+
"learning_rate": 1.2161629434954009e-05,
|
309 |
+
"loss": 1.2555,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.95,
|
314 |
+
"grad_norm": 0.41925591230392456,
|
315 |
+
"learning_rate": 1.16688567674113e-05,
|
316 |
+
"loss": 1.2977,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.99,
|
321 |
+
"grad_norm": 0.3973592221736908,
|
322 |
+
"learning_rate": 1.1176084099868594e-05,
|
323 |
+
"loss": 1.2695,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 2.04,
|
328 |
+
"grad_norm": 0.35202836990356445,
|
329 |
+
"learning_rate": 1.0683311432325887e-05,
|
330 |
+
"loss": 1.3174,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 2.08,
|
335 |
+
"grad_norm": 0.40330058336257935,
|
336 |
+
"learning_rate": 1.019053876478318e-05,
|
337 |
+
"loss": 1.2708,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.13,
|
342 |
+
"grad_norm": 0.37632250785827637,
|
343 |
+
"learning_rate": 9.697766097240474e-06,
|
344 |
+
"loss": 1.2483,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.17,
|
349 |
+
"grad_norm": 0.3991636633872986,
|
350 |
+
"learning_rate": 9.204993429697766e-06,
|
351 |
+
"loss": 1.2635,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 2.21,
|
356 |
+
"grad_norm": 0.400860071182251,
|
357 |
+
"learning_rate": 8.71222076215506e-06,
|
358 |
+
"loss": 1.2464,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 2.26,
|
363 |
+
"grad_norm": 0.40742385387420654,
|
364 |
+
"learning_rate": 8.219448094612353e-06,
|
365 |
+
"loss": 1.2532,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 2.3,
|
370 |
+
"grad_norm": 0.4327584207057953,
|
371 |
+
"learning_rate": 7.726675427069646e-06,
|
372 |
+
"loss": 1.2771,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 2.35,
|
377 |
+
"grad_norm": 0.3787235915660858,
|
378 |
+
"learning_rate": 7.233902759526938e-06,
|
379 |
+
"loss": 1.2508,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.39,
|
384 |
+
"grad_norm": 0.423367977142334,
|
385 |
+
"learning_rate": 6.741130091984232e-06,
|
386 |
+
"loss": 1.2382,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 2.44,
|
391 |
+
"grad_norm": 0.3932174742221832,
|
392 |
+
"learning_rate": 6.248357424441524e-06,
|
393 |
+
"loss": 1.2759,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 2.48,
|
398 |
+
"grad_norm": 0.40788665413856506,
|
399 |
+
"learning_rate": 5.755584756898818e-06,
|
400 |
+
"loss": 1.2471,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 2.52,
|
405 |
+
"grad_norm": 0.456950843334198,
|
406 |
+
"learning_rate": 5.26281208935611e-06,
|
407 |
+
"loss": 1.2384,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.57,
|
412 |
+
"grad_norm": 0.36899831891059875,
|
413 |
+
"learning_rate": 4.770039421813404e-06,
|
414 |
+
"loss": 1.1969,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 2.61,
|
419 |
+
"grad_norm": 0.44063258171081543,
|
420 |
+
"learning_rate": 4.277266754270697e-06,
|
421 |
+
"loss": 1.2758,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 2.66,
|
426 |
+
"grad_norm": 0.3583914339542389,
|
427 |
+
"learning_rate": 3.784494086727989e-06,
|
428 |
+
"loss": 1.2332,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 2.7,
|
433 |
+
"grad_norm": 0.4087056517601013,
|
434 |
+
"learning_rate": 3.2917214191852826e-06,
|
435 |
+
"loss": 1.2646,
|
436 |
+
"step": 1525
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 2.75,
|
440 |
+
"grad_norm": 0.44617870450019836,
|
441 |
+
"learning_rate": 2.7989487516425756e-06,
|
442 |
+
"loss": 1.2265,
|
443 |
+
"step": 1550
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.79,
|
447 |
+
"grad_norm": 0.4349097013473511,
|
448 |
+
"learning_rate": 2.3061760840998687e-06,
|
449 |
+
"loss": 1.2976,
|
450 |
+
"step": 1575
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.83,
|
454 |
+
"grad_norm": 0.4503318965435028,
|
455 |
+
"learning_rate": 1.8134034165571617e-06,
|
456 |
+
"loss": 1.2467,
|
457 |
+
"step": 1600
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.88,
|
461 |
+
"grad_norm": 0.40000948309898376,
|
462 |
+
"learning_rate": 1.3206307490144548e-06,
|
463 |
+
"loss": 1.2146,
|
464 |
+
"step": 1625
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.92,
|
468 |
+
"grad_norm": 0.39695021510124207,
|
469 |
+
"learning_rate": 8.278580814717477e-07,
|
470 |
+
"loss": 1.263,
|
471 |
+
"step": 1650
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.97,
|
475 |
+
"grad_norm": 0.4137335419654846,
|
476 |
+
"learning_rate": 3.3508541392904077e-07,
|
477 |
+
"loss": 1.2436,
|
478 |
+
"step": 1675
|
479 |
+
}
|
480 |
+
],
|
481 |
+
"logging_steps": 25,
|
482 |
+
"max_steps": 1692,
|
483 |
+
"num_input_tokens_seen": 0,
|
484 |
+
"num_train_epochs": 3,
|
485 |
+
"save_steps": 500,
|
486 |
+
"total_flos": 7269909176254464.0,
|
487 |
+
"train_batch_size": 2,
|
488 |
+
"trial_name": null,
|
489 |
+
"trial_params": null
|
490 |
+
}
|
checkpoint-1692/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:953094f01ab6d37b2bbf13141e6a433f2078dd9c306db72d93d975e7c18eff3b
|
3 |
+
size 4984
|
checkpoint-1692/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar26_18-00-07_r-jamesb1974-gpu01-qp88jhm1-82ea1-9m4x0/events.out.tfevents.1711476024.r-jamesb1974-gpu01-qp88jhm1-82ea1-9m4x0.59.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fdde2d5d3706c3199b65e35dc4f00418a6902c3f3a4cb0f4cb422c1a7e4b1da
|
3 |
+
size 19859
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
20 |
+
"unk_token": "<|endoftext|>"
|
21 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:953094f01ab6d37b2bbf13141e6a433f2078dd9c306db72d93d975e7c18eff3b
|
3 |
+
size 4984
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "openai-community/gpt2",
|
3 |
+
"project_name": "com-gpt2-ep2-bs2-sft",
|
4 |
+
"data_path": "com-gpt2-ep2-bs2-sft/autotrain-data",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": true,
|
8 |
+
"block_size": 1024,
|
9 |
+
"model_max_length": 2048,
|
10 |
+
"padding": "right",
|
11 |
+
"trainer": "sft",
|
12 |
+
"use_flash_attention_2": false,
|
13 |
+
"log": "tensorboard",
|
14 |
+
"disable_gradient_checkpointing": false,
|
15 |
+
"logging_steps": -1,
|
16 |
+
"evaluation_strategy": "epoch",
|
17 |
+
"save_total_limit": 1,
|
18 |
+
"save_strategy": "epoch",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "fp16",
|
21 |
+
"lr": 3e-05,
|
22 |
+
"epochs": 3,
|
23 |
+
"batch_size": 2,
|
24 |
+
"warmup_ratio": 0.1,
|
25 |
+
"gradient_accumulation": 4,
|
26 |
+
"optimizer": "adamw_torch",
|
27 |
+
"scheduler": "linear",
|
28 |
+
"weight_decay": 0.0,
|
29 |
+
"max_grad_norm": 1.0,
|
30 |
+
"seed": 42,
|
31 |
+
"chat_template": "none",
|
32 |
+
"quantization": "int4",
|
33 |
+
"target_modules": "all-linear",
|
34 |
+
"merge_adapter": false,
|
35 |
+
"peft": true,
|
36 |
+
"lora_r": 16,
|
37 |
+
"lora_alpha": 32,
|
38 |
+
"lora_dropout": 0.05,
|
39 |
+
"model_ref": null,
|
40 |
+
"dpo_beta": 0.1,
|
41 |
+
"prompt_text_column": "autotrain_prompt",
|
42 |
+
"text_column": "autotrain_text",
|
43 |
+
"rejected_text_column": "autotrain_rejected_text",
|
44 |
+
"push_to_hub": true,
|
45 |
+
"repo_id": "Jamesb1974/com-gpt2-ep2-bs2-sft",
|
46 |
+
"username": "Jamesb1974"
|
47 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|