Jamesb1974
commited on
Commit
•
87eaae1
1
Parent(s):
bacfe45
Upload folder using huggingface_hub
Browse files- README.md +45 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- checkpoint-2122/README.md +202 -0
- checkpoint-2122/adapter_config.json +30 -0
- checkpoint-2122/adapter_model.safetensors +3 -0
- checkpoint-2122/merges.txt +0 -0
- checkpoint-2122/optimizer.pt +3 -0
- checkpoint-2122/pytorch_model.bin +3 -0
- checkpoint-2122/rng_state.pth +3 -0
- checkpoint-2122/scheduler.pt +3 -0
- checkpoint-2122/special_tokens_map.json +6 -0
- checkpoint-2122/tokenizer.json +0 -0
- checkpoint-2122/tokenizer_config.json +21 -0
- checkpoint-2122/trainer_state.json +609 -0
- checkpoint-2122/training_args.bin +3 -0
- checkpoint-2122/vocab.json +0 -0
- merges.txt +0 -0
- runs/Mar26_21-07-05_r-jamesb1974-46gb-csm03fyw-eac2c-v2jlf/events.out.tfevents.1711487236.r-jamesb1974-46gb-csm03fyw-eac2c-v2jlf.101.0 +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_attn",
|
24 |
+
"c_fc",
|
25 |
+
"c_proj"
|
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 sha256:6adbba39ed7890f2dc7022e8b1f5da268b2a33133e729f93b6529a0071d11d17
|
3 |
+
size 9449344
|
checkpoint-2122/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-2122/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_attn",
|
24 |
+
"c_fc",
|
25 |
+
"c_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
checkpoint-2122/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6adbba39ed7890f2dc7022e8b1f5da268b2a33133e729f93b6529a0071d11d17
|
3 |
+
size 9449344
|
checkpoint-2122/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2122/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02af03b8a4fbc6d88c1c61a8b4d2ffea746b62f71ab7c77dd029681bd1aeafda
|
3 |
+
size 18955258
|
checkpoint-2122/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-2122/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2faf27f4a283e8ac972b18b17e7f91259bfade49ca273f61d790749f04bcf1ec
|
3 |
+
size 14244
|
checkpoint-2122/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f82eb48e2c8ad1369b172507d96d62773cb93882a0790976d6449f7664bf25d0
|
3 |
+
size 1064
|
checkpoint-2122/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-2122/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2122/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-2122/trainer_state.json
ADDED
@@ -0,0 +1,609 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2122,
|
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": 1.5460187196731567,
|
14 |
+
"learning_rate": 3.5211267605633804e-06,
|
15 |
+
"loss": 2.7305,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.05,
|
20 |
+
"grad_norm": 1.3390659093856812,
|
21 |
+
"learning_rate": 7.042253521126761e-06,
|
22 |
+
"loss": 2.7192,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.07,
|
27 |
+
"grad_norm": 1.4170739650726318,
|
28 |
+
"learning_rate": 1.056338028169014e-05,
|
29 |
+
"loss": 2.6137,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09,
|
34 |
+
"grad_norm": 0.9075584411621094,
|
35 |
+
"learning_rate": 1.4084507042253522e-05,
|
36 |
+
"loss": 2.3702,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.12,
|
41 |
+
"grad_norm": 0.8087872862815857,
|
42 |
+
"learning_rate": 1.7605633802816902e-05,
|
43 |
+
"loss": 2.0872,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.14,
|
48 |
+
"grad_norm": 0.6687940359115601,
|
49 |
+
"learning_rate": 2.112676056338028e-05,
|
50 |
+
"loss": 1.9849,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.16,
|
55 |
+
"grad_norm": 0.48965755105018616,
|
56 |
+
"learning_rate": 2.464788732394366e-05,
|
57 |
+
"loss": 1.8513,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.19,
|
62 |
+
"grad_norm": 0.44189536571502686,
|
63 |
+
"learning_rate": 2.8169014084507043e-05,
|
64 |
+
"loss": 1.7901,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.21,
|
69 |
+
"grad_norm": 0.4670378863811493,
|
70 |
+
"learning_rate": 2.9827134625458355e-05,
|
71 |
+
"loss": 1.7426,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.24,
|
76 |
+
"grad_norm": 0.5341612100601196,
|
77 |
+
"learning_rate": 2.9434258774227347e-05,
|
78 |
+
"loss": 1.663,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.26,
|
83 |
+
"grad_norm": 0.32935911417007446,
|
84 |
+
"learning_rate": 2.9041382922996336e-05,
|
85 |
+
"loss": 1.6262,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.28,
|
90 |
+
"grad_norm": 0.49150750041007996,
|
91 |
+
"learning_rate": 2.864850707176532e-05,
|
92 |
+
"loss": 1.5616,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.31,
|
97 |
+
"grad_norm": 0.4343280792236328,
|
98 |
+
"learning_rate": 2.825563122053431e-05,
|
99 |
+
"loss": 1.554,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.33,
|
104 |
+
"grad_norm": 0.46223270893096924,
|
105 |
+
"learning_rate": 2.78627553693033e-05,
|
106 |
+
"loss": 1.4944,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.35,
|
111 |
+
"grad_norm": 0.5165560245513916,
|
112 |
+
"learning_rate": 2.7469879518072288e-05,
|
113 |
+
"loss": 1.4857,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.38,
|
118 |
+
"grad_norm": 0.4836352467536926,
|
119 |
+
"learning_rate": 2.707700366684128e-05,
|
120 |
+
"loss": 1.4545,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.4,
|
125 |
+
"grad_norm": 0.5089160799980164,
|
126 |
+
"learning_rate": 2.668412781561027e-05,
|
127 |
+
"loss": 1.3965,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.42,
|
132 |
+
"grad_norm": 0.4400924742221832,
|
133 |
+
"learning_rate": 2.6291251964379258e-05,
|
134 |
+
"loss": 1.3703,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.45,
|
139 |
+
"grad_norm": 0.520064115524292,
|
140 |
+
"learning_rate": 2.5898376113148247e-05,
|
141 |
+
"loss": 1.3869,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.47,
|
146 |
+
"grad_norm": 0.4993634819984436,
|
147 |
+
"learning_rate": 2.5505500261917232e-05,
|
148 |
+
"loss": 1.3827,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.49,
|
153 |
+
"grad_norm": 0.4747565686702728,
|
154 |
+
"learning_rate": 2.511262441068622e-05,
|
155 |
+
"loss": 1.3494,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.52,
|
160 |
+
"grad_norm": 0.45222511887550354,
|
161 |
+
"learning_rate": 2.4719748559455214e-05,
|
162 |
+
"loss": 1.3295,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.54,
|
167 |
+
"grad_norm": 0.5314898490905762,
|
168 |
+
"learning_rate": 2.4326872708224202e-05,
|
169 |
+
"loss": 1.2971,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.57,
|
174 |
+
"grad_norm": 0.4976591467857361,
|
175 |
+
"learning_rate": 2.393399685699319e-05,
|
176 |
+
"loss": 1.2882,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.59,
|
181 |
+
"grad_norm": 0.5847007632255554,
|
182 |
+
"learning_rate": 2.354112100576218e-05,
|
183 |
+
"loss": 1.3001,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.61,
|
188 |
+
"grad_norm": 0.4775733947753906,
|
189 |
+
"learning_rate": 2.314824515453117e-05,
|
190 |
+
"loss": 1.3185,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.64,
|
195 |
+
"grad_norm": 0.4997495710849762,
|
196 |
+
"learning_rate": 2.2755369303300158e-05,
|
197 |
+
"loss": 1.31,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.66,
|
202 |
+
"grad_norm": 0.46225643157958984,
|
203 |
+
"learning_rate": 2.2362493452069147e-05,
|
204 |
+
"loss": 1.2577,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.68,
|
209 |
+
"grad_norm": 0.5184119939804077,
|
210 |
+
"learning_rate": 2.1969617600838136e-05,
|
211 |
+
"loss": 1.2846,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.71,
|
216 |
+
"grad_norm": 0.5487437844276428,
|
217 |
+
"learning_rate": 2.1576741749607125e-05,
|
218 |
+
"loss": 1.234,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.73,
|
223 |
+
"grad_norm": 0.44502514600753784,
|
224 |
+
"learning_rate": 2.1183865898376113e-05,
|
225 |
+
"loss": 1.2652,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.75,
|
230 |
+
"grad_norm": 0.5340321660041809,
|
231 |
+
"learning_rate": 2.0790990047145102e-05,
|
232 |
+
"loss": 1.2302,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.78,
|
237 |
+
"grad_norm": 0.46381640434265137,
|
238 |
+
"learning_rate": 2.039811419591409e-05,
|
239 |
+
"loss": 1.2402,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.8,
|
244 |
+
"grad_norm": 0.5519339442253113,
|
245 |
+
"learning_rate": 2.0005238344683083e-05,
|
246 |
+
"loss": 1.2924,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.82,
|
251 |
+
"grad_norm": 0.47584566473960876,
|
252 |
+
"learning_rate": 1.9612362493452072e-05,
|
253 |
+
"loss": 1.2526,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.85,
|
258 |
+
"grad_norm": 0.5393884778022766,
|
259 |
+
"learning_rate": 1.9219486642221058e-05,
|
260 |
+
"loss": 1.188,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.87,
|
265 |
+
"grad_norm": 0.5071331858634949,
|
266 |
+
"learning_rate": 1.8826610790990047e-05,
|
267 |
+
"loss": 1.228,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.9,
|
272 |
+
"grad_norm": 0.5538953542709351,
|
273 |
+
"learning_rate": 1.8433734939759036e-05,
|
274 |
+
"loss": 1.238,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.92,
|
279 |
+
"grad_norm": 0.4920578598976135,
|
280 |
+
"learning_rate": 1.8040859088528024e-05,
|
281 |
+
"loss": 1.1884,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.94,
|
286 |
+
"grad_norm": 0.5614542961120605,
|
287 |
+
"learning_rate": 1.7647983237297017e-05,
|
288 |
+
"loss": 1.1734,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.97,
|
293 |
+
"grad_norm": 0.514637291431427,
|
294 |
+
"learning_rate": 1.7255107386066006e-05,
|
295 |
+
"loss": 1.1938,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.99,
|
300 |
+
"grad_norm": 0.6818568110466003,
|
301 |
+
"learning_rate": 1.6862231534834994e-05,
|
302 |
+
"loss": 1.2151,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.01,
|
307 |
+
"grad_norm": 0.5652730464935303,
|
308 |
+
"learning_rate": 1.646935568360398e-05,
|
309 |
+
"loss": 1.1932,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.04,
|
314 |
+
"grad_norm": 0.46096867322921753,
|
315 |
+
"learning_rate": 1.607647983237297e-05,
|
316 |
+
"loss": 1.1895,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.06,
|
321 |
+
"grad_norm": 0.5606017112731934,
|
322 |
+
"learning_rate": 1.5683603981141958e-05,
|
323 |
+
"loss": 1.1812,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.08,
|
328 |
+
"grad_norm": 0.6677452325820923,
|
329 |
+
"learning_rate": 1.5290728129910947e-05,
|
330 |
+
"loss": 1.2344,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.11,
|
335 |
+
"grad_norm": 0.4959929585456848,
|
336 |
+
"learning_rate": 1.4897852278679937e-05,
|
337 |
+
"loss": 1.1922,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.13,
|
342 |
+
"grad_norm": 0.5288898348808289,
|
343 |
+
"learning_rate": 1.4504976427448928e-05,
|
344 |
+
"loss": 1.1824,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.15,
|
349 |
+
"grad_norm": 0.49359196424484253,
|
350 |
+
"learning_rate": 1.4112100576217915e-05,
|
351 |
+
"loss": 1.2163,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.18,
|
356 |
+
"grad_norm": 0.5195351839065552,
|
357 |
+
"learning_rate": 1.3719224724986904e-05,
|
358 |
+
"loss": 1.1688,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.2,
|
363 |
+
"grad_norm": 0.5838152766227722,
|
364 |
+
"learning_rate": 1.3326348873755894e-05,
|
365 |
+
"loss": 1.1566,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.23,
|
370 |
+
"grad_norm": 0.5872088074684143,
|
371 |
+
"learning_rate": 1.2933473022524883e-05,
|
372 |
+
"loss": 1.1685,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.25,
|
377 |
+
"grad_norm": 0.5522224307060242,
|
378 |
+
"learning_rate": 1.254059717129387e-05,
|
379 |
+
"loss": 1.1745,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.27,
|
384 |
+
"grad_norm": 0.56575608253479,
|
385 |
+
"learning_rate": 1.2147721320062861e-05,
|
386 |
+
"loss": 1.1895,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.3,
|
391 |
+
"grad_norm": 0.5466055870056152,
|
392 |
+
"learning_rate": 1.175484546883185e-05,
|
393 |
+
"loss": 1.1445,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.32,
|
398 |
+
"grad_norm": 0.5417299866676331,
|
399 |
+
"learning_rate": 1.1361969617600839e-05,
|
400 |
+
"loss": 1.2091,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.34,
|
405 |
+
"grad_norm": 0.6165823936462402,
|
406 |
+
"learning_rate": 1.0969093766369827e-05,
|
407 |
+
"loss": 1.1533,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.37,
|
412 |
+
"grad_norm": 0.6337828636169434,
|
413 |
+
"learning_rate": 1.0576217915138816e-05,
|
414 |
+
"loss": 1.1721,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.39,
|
419 |
+
"grad_norm": 0.5324290990829468,
|
420 |
+
"learning_rate": 1.0183342063907805e-05,
|
421 |
+
"loss": 1.2054,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.41,
|
426 |
+
"grad_norm": 0.5414568185806274,
|
427 |
+
"learning_rate": 9.790466212676796e-06,
|
428 |
+
"loss": 1.164,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.44,
|
433 |
+
"grad_norm": 0.5330114364624023,
|
434 |
+
"learning_rate": 9.397590361445783e-06,
|
435 |
+
"loss": 1.1632,
|
436 |
+
"step": 1525
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.46,
|
440 |
+
"grad_norm": 0.4752555787563324,
|
441 |
+
"learning_rate": 9.004714510214772e-06,
|
442 |
+
"loss": 1.123,
|
443 |
+
"step": 1550
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.48,
|
447 |
+
"grad_norm": 0.5737998485565186,
|
448 |
+
"learning_rate": 8.61183865898376e-06,
|
449 |
+
"loss": 1.168,
|
450 |
+
"step": 1575
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 1.51,
|
454 |
+
"grad_norm": 0.5172936320304871,
|
455 |
+
"learning_rate": 8.218962807752751e-06,
|
456 |
+
"loss": 1.1856,
|
457 |
+
"step": 1600
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 1.53,
|
461 |
+
"grad_norm": 0.6017385721206665,
|
462 |
+
"learning_rate": 7.826086956521738e-06,
|
463 |
+
"loss": 1.1571,
|
464 |
+
"step": 1625
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.56,
|
468 |
+
"grad_norm": 0.6177796125411987,
|
469 |
+
"learning_rate": 7.433211105290728e-06,
|
470 |
+
"loss": 1.166,
|
471 |
+
"step": 1650
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.58,
|
475 |
+
"grad_norm": 0.5164004564285278,
|
476 |
+
"learning_rate": 7.040335254059718e-06,
|
477 |
+
"loss": 1.1979,
|
478 |
+
"step": 1675
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 1.6,
|
482 |
+
"grad_norm": 0.6410110592842102,
|
483 |
+
"learning_rate": 6.647459402828706e-06,
|
484 |
+
"loss": 1.156,
|
485 |
+
"step": 1700
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 1.63,
|
489 |
+
"grad_norm": 0.5372936129570007,
|
490 |
+
"learning_rate": 6.254583551597696e-06,
|
491 |
+
"loss": 1.1532,
|
492 |
+
"step": 1725
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 1.65,
|
496 |
+
"grad_norm": 0.6036843657493591,
|
497 |
+
"learning_rate": 5.8617077003666845e-06,
|
498 |
+
"loss": 1.1793,
|
499 |
+
"step": 1750
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 1.67,
|
503 |
+
"grad_norm": 0.6881660223007202,
|
504 |
+
"learning_rate": 5.468831849135673e-06,
|
505 |
+
"loss": 1.1709,
|
506 |
+
"step": 1775
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.7,
|
510 |
+
"grad_norm": 0.5717695951461792,
|
511 |
+
"learning_rate": 5.075955997904662e-06,
|
512 |
+
"loss": 1.1441,
|
513 |
+
"step": 1800
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.72,
|
517 |
+
"grad_norm": 0.5951740145683289,
|
518 |
+
"learning_rate": 4.683080146673651e-06,
|
519 |
+
"loss": 1.1855,
|
520 |
+
"step": 1825
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 1.74,
|
524 |
+
"grad_norm": 0.628299355506897,
|
525 |
+
"learning_rate": 4.29020429544264e-06,
|
526 |
+
"loss": 1.1888,
|
527 |
+
"step": 1850
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 1.77,
|
531 |
+
"grad_norm": 0.5050541758537292,
|
532 |
+
"learning_rate": 3.89732844421163e-06,
|
533 |
+
"loss": 1.1396,
|
534 |
+
"step": 1875
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 1.79,
|
538 |
+
"grad_norm": 0.5191190838813782,
|
539 |
+
"learning_rate": 3.504452592980618e-06,
|
540 |
+
"loss": 1.1955,
|
541 |
+
"step": 1900
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 1.81,
|
545 |
+
"grad_norm": 0.5869964957237244,
|
546 |
+
"learning_rate": 3.111576741749607e-06,
|
547 |
+
"loss": 1.1314,
|
548 |
+
"step": 1925
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 1.84,
|
552 |
+
"grad_norm": 0.5007169842720032,
|
553 |
+
"learning_rate": 2.718700890518596e-06,
|
554 |
+
"loss": 1.1516,
|
555 |
+
"step": 1950
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 1.86,
|
559 |
+
"grad_norm": 0.6014929413795471,
|
560 |
+
"learning_rate": 2.325825039287585e-06,
|
561 |
+
"loss": 1.1901,
|
562 |
+
"step": 1975
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.89,
|
566 |
+
"grad_norm": 0.8301869034767151,
|
567 |
+
"learning_rate": 1.932949188056574e-06,
|
568 |
+
"loss": 1.1197,
|
569 |
+
"step": 2000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.91,
|
573 |
+
"grad_norm": 0.5901632905006409,
|
574 |
+
"learning_rate": 1.5400733368255633e-06,
|
575 |
+
"loss": 1.1843,
|
576 |
+
"step": 2025
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 1.93,
|
580 |
+
"grad_norm": 0.580962598323822,
|
581 |
+
"learning_rate": 1.1471974855945522e-06,
|
582 |
+
"loss": 1.1456,
|
583 |
+
"step": 2050
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 1.96,
|
587 |
+
"grad_norm": 0.5481582283973694,
|
588 |
+
"learning_rate": 7.543216343635412e-07,
|
589 |
+
"loss": 1.1644,
|
590 |
+
"step": 2075
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 1.98,
|
594 |
+
"grad_norm": 0.5194025039672852,
|
595 |
+
"learning_rate": 3.6144578313253016e-07,
|
596 |
+
"loss": 1.1581,
|
597 |
+
"step": 2100
|
598 |
+
}
|
599 |
+
],
|
600 |
+
"logging_steps": 25,
|
601 |
+
"max_steps": 2122,
|
602 |
+
"num_input_tokens_seen": 0,
|
603 |
+
"num_train_epochs": 2,
|
604 |
+
"save_steps": 500,
|
605 |
+
"total_flos": 4558731463360512.0,
|
606 |
+
"train_batch_size": 1,
|
607 |
+
"trial_name": null,
|
608 |
+
"trial_params": null
|
609 |
+
}
|
checkpoint-2122/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:916812ad12ac77022527466c667c77f4e94068a5590f4830656e6c505a265766
|
3 |
+
size 4984
|
checkpoint-2122/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_21-07-05_r-jamesb1974-46gb-csm03fyw-eac2c-v2jlf/events.out.tfevents.1711487236.r-jamesb1974-46gb-csm03fyw-eac2c-v2jlf.101.0
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:eba1baf9d6316e071e5013fa685d63df8f6b1acdf9196a51fa5164de5e5781f7
|
3 |
+
size 23451
|
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 sha256:916812ad12ac77022527466c667c77f4e94068a5590f4830656e6c505a265766
|
3 |
+
size 4984
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "openai-community/gpt2",
|
3 |
+
"project_name": "autotrain-gtp2-600-sft",
|
4 |
+
"data_path": "autotrain-gtp2-600-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": 2,
|
23 |
+
"batch_size": 1,
|
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/autotrain-gtp2-600-sft",
|
46 |
+
"username": "Jamesb1974"
|
47 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|