Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- trainer_state.json +474 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/Qwen2-72B-Instruct-GPTQ-Int4
|
3 |
+
library_name: peft
|
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 0.12.0
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2-72B-Instruct-GPTQ-Int4",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
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": 16,
|
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": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"down_proj",
|
24 |
+
"k_proj",
|
25 |
+
"o_proj",
|
26 |
+
"up_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"q_proj",
|
29 |
+
"v_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 sha256:600ebe8f2029b921b217789989d024730ffb004eb4a37098a8099627225f2eff
|
3 |
+
size 422201952
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac3a66e4082eab22bf9843b8975ce209792fe752e51c3104db25ff2e0d51d282
|
3 |
+
size 844771794
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:040640ac721c2d51db640c3226cf4df9f2849cd7a69a094a6a9c44c1099abffa
|
3 |
+
size 15024
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4acc46791fbf144de252be0d227366627b72919cd348285cde497704a9e1c1ed
|
3 |
+
size 15024
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b840991b54b95df1203ac03b70b299a7d74921730b7348b39c0e64ee35dc3546
|
3 |
+
size 15024
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa9a41f0a8d648748387796c47778c9314f38c61029dcc40a2aa89ad544e3948
|
3 |
+
size 15024
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed19b0e006a4f52a0734134ba69ca8dfec011ede350e006576a100006a121b9f
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
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_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,474 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 63,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.047619047619047616,
|
13 |
+
"grad_norm": 2.636066198348999,
|
14 |
+
"learning_rate": 3.3333333333333333e-06,
|
15 |
+
"loss": 1.5447,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09523809523809523,
|
20 |
+
"grad_norm": 1.7816333770751953,
|
21 |
+
"learning_rate": 6.666666666666667e-06,
|
22 |
+
"loss": 1.1323,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.14285714285714285,
|
27 |
+
"grad_norm": 2.2745041847229004,
|
28 |
+
"learning_rate": 1e-05,
|
29 |
+
"loss": 1.2092,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.19047619047619047,
|
34 |
+
"grad_norm": 2.6683919429779053,
|
35 |
+
"learning_rate": 1.3333333333333333e-05,
|
36 |
+
"loss": 1.5569,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.23809523809523808,
|
41 |
+
"grad_norm": 2.3222100734710693,
|
42 |
+
"learning_rate": 1.6666666666666667e-05,
|
43 |
+
"loss": 1.4135,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2857142857142857,
|
48 |
+
"grad_norm": 2.067908525466919,
|
49 |
+
"learning_rate": 2e-05,
|
50 |
+
"loss": 1.2277,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.3333333333333333,
|
55 |
+
"grad_norm": 2.5608789920806885,
|
56 |
+
"learning_rate": 1.9984815164333163e-05,
|
57 |
+
"loss": 1.4595,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.38095238095238093,
|
62 |
+
"grad_norm": 2.3394458293914795,
|
63 |
+
"learning_rate": 1.9939306773179498e-05,
|
64 |
+
"loss": 1.0971,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.42857142857142855,
|
69 |
+
"grad_norm": 2.624566078186035,
|
70 |
+
"learning_rate": 1.9863613034027224e-05,
|
71 |
+
"loss": 1.3249,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.47619047619047616,
|
76 |
+
"grad_norm": 3.019270420074463,
|
77 |
+
"learning_rate": 1.9757963826274357e-05,
|
78 |
+
"loss": 1.1663,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.5238095238095238,
|
83 |
+
"grad_norm": 4.040117263793945,
|
84 |
+
"learning_rate": 1.9622680003092503e-05,
|
85 |
+
"loss": 1.3519,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5714285714285714,
|
90 |
+
"grad_norm": 5.076770782470703,
|
91 |
+
"learning_rate": 1.9458172417006347e-05,
|
92 |
+
"loss": 1.212,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.6190476190476191,
|
97 |
+
"grad_norm": 3.281177282333374,
|
98 |
+
"learning_rate": 1.9264940672148018e-05,
|
99 |
+
"loss": 0.8725,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.6666666666666666,
|
104 |
+
"grad_norm": 3.5001425743103027,
|
105 |
+
"learning_rate": 1.9043571606975776e-05,
|
106 |
+
"loss": 0.6642,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.7142857142857143,
|
111 |
+
"grad_norm": 2.4256069660186768,
|
112 |
+
"learning_rate": 1.879473751206489e-05,
|
113 |
+
"loss": 0.5313,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.7619047619047619,
|
118 |
+
"grad_norm": 2.3582112789154053,
|
119 |
+
"learning_rate": 1.851919408838327e-05,
|
120 |
+
"loss": 0.73,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.8095238095238095,
|
125 |
+
"grad_norm": 1.449530005455017,
|
126 |
+
"learning_rate": 1.821777815225245e-05,
|
127 |
+
"loss": 0.3238,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.8571428571428571,
|
132 |
+
"grad_norm": 2.057817220687866,
|
133 |
+
"learning_rate": 1.789140509396394e-05,
|
134 |
+
"loss": 0.3367,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.9047619047619048,
|
139 |
+
"grad_norm": 1.7016539573669434,
|
140 |
+
"learning_rate": 1.7541066097768965e-05,
|
141 |
+
"loss": 0.3914,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.9523809523809523,
|
146 |
+
"grad_norm": 1.2818858623504639,
|
147 |
+
"learning_rate": 1.7167825131684516e-05,
|
148 |
+
"loss": 0.1852,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.0,
|
153 |
+
"grad_norm": 0.9452447891235352,
|
154 |
+
"learning_rate": 1.6772815716257414e-05,
|
155 |
+
"loss": 0.1722,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.0476190476190477,
|
160 |
+
"grad_norm": 0.5685144662857056,
|
161 |
+
"learning_rate": 1.6357237482099682e-05,
|
162 |
+
"loss": 0.0953,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.0952380952380953,
|
167 |
+
"grad_norm": 0.6435515880584717,
|
168 |
+
"learning_rate": 1.5922352526649803e-05,
|
169 |
+
"loss": 0.1832,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.1428571428571428,
|
174 |
+
"grad_norm": 1.049676537513733,
|
175 |
+
"learning_rate": 1.5469481581224274e-05,
|
176 |
+
"loss": 0.402,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.1904761904761905,
|
181 |
+
"grad_norm": 0.9065538048744202,
|
182 |
+
"learning_rate": 1.5000000000000002e-05,
|
183 |
+
"loss": 0.2622,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.2380952380952381,
|
188 |
+
"grad_norm": 0.5284762978553772,
|
189 |
+
"learning_rate": 1.4515333583108896e-05,
|
190 |
+
"loss": 0.1086,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.2857142857142856,
|
195 |
+
"grad_norm": 0.7903798222541809,
|
196 |
+
"learning_rate": 1.4016954246529697e-05,
|
197 |
+
"loss": 0.0996,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.3333333333333333,
|
202 |
+
"grad_norm": 0.2656748294830322,
|
203 |
+
"learning_rate": 1.3506375551927546e-05,
|
204 |
+
"loss": 0.0154,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.380952380952381,
|
209 |
+
"grad_norm": 1.171624779701233,
|
210 |
+
"learning_rate": 1.2985148110016947e-05,
|
211 |
+
"loss": 0.2659,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.4285714285714286,
|
216 |
+
"grad_norm": 0.31690454483032227,
|
217 |
+
"learning_rate": 1.2454854871407993e-05,
|
218 |
+
"loss": 0.0673,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.4761904761904763,
|
223 |
+
"grad_norm": 0.7295234799385071,
|
224 |
+
"learning_rate": 1.1917106319237386e-05,
|
225 |
+
"loss": 0.2074,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.5238095238095237,
|
230 |
+
"grad_norm": 0.6296242475509644,
|
231 |
+
"learning_rate": 1.1373535578184083e-05,
|
232 |
+
"loss": 0.1208,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.5714285714285714,
|
237 |
+
"grad_norm": 1.0464074611663818,
|
238 |
+
"learning_rate": 1.0825793454723325e-05,
|
239 |
+
"loss": 0.2525,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.619047619047619,
|
244 |
+
"grad_norm": 0.4286152422428131,
|
245 |
+
"learning_rate": 1.0275543423681622e-05,
|
246 |
+
"loss": 0.1035,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.6666666666666665,
|
251 |
+
"grad_norm": 0.5248931646347046,
|
252 |
+
"learning_rate": 9.724456576318383e-06,
|
253 |
+
"loss": 0.1614,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.7142857142857144,
|
258 |
+
"grad_norm": 0.40034690499305725,
|
259 |
+
"learning_rate": 9.174206545276678e-06,
|
260 |
+
"loss": 0.1218,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.7619047619047619,
|
265 |
+
"grad_norm": 0.4369080662727356,
|
266 |
+
"learning_rate": 8.626464421815919e-06,
|
267 |
+
"loss": 0.06,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.8095238095238095,
|
272 |
+
"grad_norm": 1.110698938369751,
|
273 |
+
"learning_rate": 8.082893680762619e-06,
|
274 |
+
"loss": 0.3501,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.8571428571428572,
|
279 |
+
"grad_norm": 0.314057320356369,
|
280 |
+
"learning_rate": 7.545145128592009e-06,
|
281 |
+
"loss": 0.0499,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.9047619047619047,
|
286 |
+
"grad_norm": 0.9931963086128235,
|
287 |
+
"learning_rate": 7.014851889983058e-06,
|
288 |
+
"loss": 0.1744,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.9523809523809523,
|
293 |
+
"grad_norm": 0.31384727358818054,
|
294 |
+
"learning_rate": 6.4936244480724575e-06,
|
295 |
+
"loss": 0.0713,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.0,
|
300 |
+
"grad_norm": 0.4129275977611542,
|
301 |
+
"learning_rate": 5.983045753470308e-06,
|
302 |
+
"loss": 0.0776,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 2.0476190476190474,
|
307 |
+
"grad_norm": 0.31003817915916443,
|
308 |
+
"learning_rate": 5.484666416891109e-06,
|
309 |
+
"loss": 0.043,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 2.0952380952380953,
|
314 |
+
"grad_norm": 0.5723528265953064,
|
315 |
+
"learning_rate": 5.000000000000003e-06,
|
316 |
+
"loss": 0.0901,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 2.142857142857143,
|
321 |
+
"grad_norm": 0.6738455295562744,
|
322 |
+
"learning_rate": 4.530518418775734e-06,
|
323 |
+
"loss": 0.1227,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 2.1904761904761907,
|
328 |
+
"grad_norm": 0.5331130027770996,
|
329 |
+
"learning_rate": 4.077647473350201e-06,
|
330 |
+
"loss": 0.1491,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 2.238095238095238,
|
335 |
+
"grad_norm": 0.4636727571487427,
|
336 |
+
"learning_rate": 3.6427625179003223e-06,
|
337 |
+
"loss": 0.0874,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.2857142857142856,
|
342 |
+
"grad_norm": 0.5442101359367371,
|
343 |
+
"learning_rate": 3.2271842837425917e-06,
|
344 |
+
"loss": 0.1945,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.3333333333333335,
|
349 |
+
"grad_norm": 0.3890051543712616,
|
350 |
+
"learning_rate": 2.8321748683154893e-06,
|
351 |
+
"loss": 0.1032,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 2.380952380952381,
|
356 |
+
"grad_norm": 0.4027661085128784,
|
357 |
+
"learning_rate": 2.4589339022310386e-06,
|
358 |
+
"loss": 0.1239,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 2.4285714285714284,
|
363 |
+
"grad_norm": 0.5832112431526184,
|
364 |
+
"learning_rate": 2.1085949060360654e-06,
|
365 |
+
"loss": 0.1892,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 2.4761904761904763,
|
370 |
+
"grad_norm": 0.29090118408203125,
|
371 |
+
"learning_rate": 1.7822218477475496e-06,
|
372 |
+
"loss": 0.0538,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 2.5238095238095237,
|
377 |
+
"grad_norm": 1.1339997053146362,
|
378 |
+
"learning_rate": 1.4808059116167306e-06,
|
379 |
+
"loss": 0.256,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.571428571428571,
|
384 |
+
"grad_norm": 0.41949254274368286,
|
385 |
+
"learning_rate": 1.2052624879351105e-06,
|
386 |
+
"loss": 0.0908,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 2.619047619047619,
|
391 |
+
"grad_norm": 0.7024145126342773,
|
392 |
+
"learning_rate": 9.564283930242258e-07,
|
393 |
+
"loss": 0.1081,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 2.6666666666666665,
|
398 |
+
"grad_norm": 0.236419215798378,
|
399 |
+
"learning_rate": 7.350593278519824e-07,
|
400 |
+
"loss": 0.0255,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 2.7142857142857144,
|
405 |
+
"grad_norm": 0.49600574374198914,
|
406 |
+
"learning_rate": 5.418275829936537e-07,
|
407 |
+
"loss": 0.1057,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.761904761904762,
|
412 |
+
"grad_norm": 0.2218826860189438,
|
413 |
+
"learning_rate": 3.773199969074959e-07,
|
414 |
+
"loss": 0.0306,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 2.8095238095238093,
|
419 |
+
"grad_norm": 0.793448269367218,
|
420 |
+
"learning_rate": 2.420361737256438e-07,
|
421 |
+
"loss": 0.0991,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 2.857142857142857,
|
426 |
+
"grad_norm": 0.2536832094192505,
|
427 |
+
"learning_rate": 1.3638696597277678e-07,
|
428 |
+
"loss": 0.0382,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 2.9047619047619047,
|
433 |
+
"grad_norm": 0.38577455282211304,
|
434 |
+
"learning_rate": 6.069322682050516e-08,
|
435 |
+
"loss": 0.0753,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 2.9523809523809526,
|
440 |
+
"grad_norm": 0.2848428785800934,
|
441 |
+
"learning_rate": 1.518483566683826e-08,
|
442 |
+
"loss": 0.0502,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 3.0,
|
447 |
+
"grad_norm": 0.2466929852962494,
|
448 |
+
"learning_rate": 0.0,
|
449 |
+
"loss": 0.032,
|
450 |
+
"step": 63
|
451 |
+
}
|
452 |
+
],
|
453 |
+
"logging_steps": 1,
|
454 |
+
"max_steps": 63,
|
455 |
+
"num_input_tokens_seen": 0,
|
456 |
+
"num_train_epochs": 3,
|
457 |
+
"save_steps": 500,
|
458 |
+
"stateful_callbacks": {
|
459 |
+
"TrainerControl": {
|
460 |
+
"args": {
|
461 |
+
"should_epoch_stop": false,
|
462 |
+
"should_evaluate": false,
|
463 |
+
"should_log": false,
|
464 |
+
"should_save": true,
|
465 |
+
"should_training_stop": true
|
466 |
+
},
|
467 |
+
"attributes": {}
|
468 |
+
}
|
469 |
+
},
|
470 |
+
"total_flos": 2094121699246080.0,
|
471 |
+
"train_batch_size": 1,
|
472 |
+
"trial_name": null,
|
473 |
+
"trial_params": null
|
474 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b095e90ec5e64d67d5ab7a368204644dde642397348af163f9afd2525d257a8
|
3 |
+
size 6136
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|