Upload 8 files
Browse files- README.md +202 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
- trainer_state.json +488 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: HuggingFaceH4/zephyr-7b-beta
|
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 0.11.1
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
|
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": 16,
|
14 |
+
"lora_dropout": 0.0,
|
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 |
+
"o_proj",
|
24 |
+
"k_proj",
|
25 |
+
"q_proj",
|
26 |
+
"v_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2c53b8235c8dfade4183766d439ba596f96b0c0197b8ba50c8143832437a2ae
|
3 |
+
size 13665592
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"additional_special_tokens": [
|
32 |
+
"<unk>",
|
33 |
+
"<s>",
|
34 |
+
"</s>"
|
35 |
+
],
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
38 |
+
"clean_up_tokenization_spaces": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"legacy": true,
|
41 |
+
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_token": "</s>",
|
43 |
+
"sp_model_kwargs": {},
|
44 |
+
"spaces_between_special_tokens": false,
|
45 |
+
"tokenizer_class": "LlamaTokenizer",
|
46 |
+
"truncation_side": "left",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": true
|
49 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,488 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.22141432762146,
|
3 |
+
"best_model_checkpoint": "outputs/checkpoint-45",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 15,
|
6 |
+
"global_step": 59,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01694915254237288,
|
13 |
+
"grad_norm": 42.25,
|
14 |
+
"learning_rate": 0.001,
|
15 |
+
"loss": 2.0126,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.03389830508474576,
|
20 |
+
"grad_norm": 14.375,
|
21 |
+
"learning_rate": 0.001,
|
22 |
+
"loss": 1.8512,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.05084745762711865,
|
27 |
+
"grad_norm": 7.09375,
|
28 |
+
"learning_rate": 0.001,
|
29 |
+
"loss": 1.4776,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.06779661016949153,
|
34 |
+
"grad_norm": 6.9375,
|
35 |
+
"learning_rate": 0.001,
|
36 |
+
"loss": 1.4508,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.0847457627118644,
|
41 |
+
"grad_norm": 1.5625,
|
42 |
+
"learning_rate": 0.001,
|
43 |
+
"loss": 1.342,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.1016949152542373,
|
48 |
+
"grad_norm": 1.5234375,
|
49 |
+
"learning_rate": 0.001,
|
50 |
+
"loss": 1.3831,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.11864406779661017,
|
55 |
+
"grad_norm": 3.671875,
|
56 |
+
"learning_rate": 0.001,
|
57 |
+
"loss": 1.3233,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.13559322033898305,
|
62 |
+
"grad_norm": 16.875,
|
63 |
+
"learning_rate": 0.001,
|
64 |
+
"loss": 1.8094,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.15254237288135594,
|
69 |
+
"grad_norm": 6.8125,
|
70 |
+
"learning_rate": 0.001,
|
71 |
+
"loss": 1.4678,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.1694915254237288,
|
76 |
+
"grad_norm": 1.6796875,
|
77 |
+
"learning_rate": 0.001,
|
78 |
+
"loss": 1.3086,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.1864406779661017,
|
83 |
+
"grad_norm": 1.09375,
|
84 |
+
"learning_rate": 0.001,
|
85 |
+
"loss": 1.1842,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.2033898305084746,
|
90 |
+
"grad_norm": 1.28125,
|
91 |
+
"learning_rate": 0.001,
|
92 |
+
"loss": 1.2429,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.22033898305084745,
|
97 |
+
"grad_norm": 1.796875,
|
98 |
+
"learning_rate": 0.001,
|
99 |
+
"loss": 1.368,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.23728813559322035,
|
104 |
+
"grad_norm": 1.09375,
|
105 |
+
"learning_rate": 0.001,
|
106 |
+
"loss": 1.2236,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.2542372881355932,
|
111 |
+
"grad_norm": 1.21875,
|
112 |
+
"learning_rate": 0.001,
|
113 |
+
"loss": 1.2481,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.2542372881355932,
|
118 |
+
"eval_loss": 1.2657548189163208,
|
119 |
+
"eval_runtime": 2.241,
|
120 |
+
"eval_samples_per_second": 83.891,
|
121 |
+
"eval_steps_per_second": 10.71,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.2711864406779661,
|
126 |
+
"grad_norm": 1.3359375,
|
127 |
+
"learning_rate": 0.001,
|
128 |
+
"loss": 1.2124,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.288135593220339,
|
133 |
+
"grad_norm": 1.34375,
|
134 |
+
"learning_rate": 0.001,
|
135 |
+
"loss": 1.3263,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.3050847457627119,
|
140 |
+
"grad_norm": 1.140625,
|
141 |
+
"learning_rate": 0.001,
|
142 |
+
"loss": 1.2269,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.3220338983050847,
|
147 |
+
"grad_norm": 1.421875,
|
148 |
+
"learning_rate": 0.001,
|
149 |
+
"loss": 1.3701,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.3389830508474576,
|
154 |
+
"grad_norm": 1.53125,
|
155 |
+
"learning_rate": 0.001,
|
156 |
+
"loss": 1.2618,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.3559322033898305,
|
161 |
+
"grad_norm": 1.6484375,
|
162 |
+
"learning_rate": 0.001,
|
163 |
+
"loss": 1.3644,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.3728813559322034,
|
168 |
+
"grad_norm": 1.4921875,
|
169 |
+
"learning_rate": 0.001,
|
170 |
+
"loss": 1.3143,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.3898305084745763,
|
175 |
+
"grad_norm": 1.8125,
|
176 |
+
"learning_rate": 0.001,
|
177 |
+
"loss": 1.2497,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.4067796610169492,
|
182 |
+
"grad_norm": 1.3828125,
|
183 |
+
"learning_rate": 0.001,
|
184 |
+
"loss": 1.1473,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.423728813559322,
|
189 |
+
"grad_norm": 1.109375,
|
190 |
+
"learning_rate": 0.001,
|
191 |
+
"loss": 1.1923,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.4406779661016949,
|
196 |
+
"grad_norm": 1.390625,
|
197 |
+
"learning_rate": 0.001,
|
198 |
+
"loss": 1.2122,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.4576271186440678,
|
203 |
+
"grad_norm": 1.4375,
|
204 |
+
"learning_rate": 0.001,
|
205 |
+
"loss": 1.1393,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.4745762711864407,
|
210 |
+
"grad_norm": 1.1796875,
|
211 |
+
"learning_rate": 0.001,
|
212 |
+
"loss": 1.1894,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.4915254237288136,
|
217 |
+
"grad_norm": 7.3125,
|
218 |
+
"learning_rate": 0.001,
|
219 |
+
"loss": 1.2592,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.5084745762711864,
|
224 |
+
"grad_norm": 2.109375,
|
225 |
+
"learning_rate": 0.001,
|
226 |
+
"loss": 1.2445,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.5084745762711864,
|
231 |
+
"eval_loss": 1.2405431270599365,
|
232 |
+
"eval_runtime": 2.2457,
|
233 |
+
"eval_samples_per_second": 83.715,
|
234 |
+
"eval_steps_per_second": 10.687,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.5254237288135594,
|
239 |
+
"grad_norm": 3.921875,
|
240 |
+
"learning_rate": 0.001,
|
241 |
+
"loss": 1.2998,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.5423728813559322,
|
246 |
+
"grad_norm": 39.25,
|
247 |
+
"learning_rate": 0.001,
|
248 |
+
"loss": 1.626,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.559322033898305,
|
253 |
+
"grad_norm": 5.4375,
|
254 |
+
"learning_rate": 0.001,
|
255 |
+
"loss": 1.2702,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.576271186440678,
|
260 |
+
"grad_norm": 2.53125,
|
261 |
+
"learning_rate": 0.001,
|
262 |
+
"loss": 1.2658,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.5932203389830508,
|
267 |
+
"grad_norm": 28.5,
|
268 |
+
"learning_rate": 0.001,
|
269 |
+
"loss": 1.2946,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.6101694915254238,
|
274 |
+
"grad_norm": 31.25,
|
275 |
+
"learning_rate": 0.001,
|
276 |
+
"loss": 1.4802,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.6271186440677966,
|
281 |
+
"grad_norm": 5.59375,
|
282 |
+
"learning_rate": 0.001,
|
283 |
+
"loss": 1.5868,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.6440677966101694,
|
288 |
+
"grad_norm": 3.1875,
|
289 |
+
"learning_rate": 0.001,
|
290 |
+
"loss": 1.4699,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.6610169491525424,
|
295 |
+
"grad_norm": 2.625,
|
296 |
+
"learning_rate": 0.001,
|
297 |
+
"loss": 1.359,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.6779661016949152,
|
302 |
+
"grad_norm": 2.515625,
|
303 |
+
"learning_rate": 0.001,
|
304 |
+
"loss": 1.4783,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.6949152542372882,
|
309 |
+
"grad_norm": 1.6640625,
|
310 |
+
"learning_rate": 0.001,
|
311 |
+
"loss": 1.304,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.711864406779661,
|
316 |
+
"grad_norm": 1.6953125,
|
317 |
+
"learning_rate": 0.001,
|
318 |
+
"loss": 1.3992,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.7288135593220338,
|
323 |
+
"grad_norm": 2.234375,
|
324 |
+
"learning_rate": 0.001,
|
325 |
+
"loss": 1.4327,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.7457627118644068,
|
330 |
+
"grad_norm": 3.9375,
|
331 |
+
"learning_rate": 0.001,
|
332 |
+
"loss": 1.2919,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.7627118644067796,
|
337 |
+
"grad_norm": 8.3125,
|
338 |
+
"learning_rate": 0.001,
|
339 |
+
"loss": 1.5113,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.7627118644067796,
|
344 |
+
"eval_loss": 1.22141432762146,
|
345 |
+
"eval_runtime": 2.2509,
|
346 |
+
"eval_samples_per_second": 83.524,
|
347 |
+
"eval_steps_per_second": 10.663,
|
348 |
+
"step": 45
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.7796610169491526,
|
352 |
+
"grad_norm": 3.3125,
|
353 |
+
"learning_rate": 0.001,
|
354 |
+
"loss": 1.3297,
|
355 |
+
"step": 46
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 0.7966101694915254,
|
359 |
+
"grad_norm": 6.25,
|
360 |
+
"learning_rate": 0.001,
|
361 |
+
"loss": 1.3788,
|
362 |
+
"step": 47
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.8135593220338984,
|
366 |
+
"grad_norm": 2.359375,
|
367 |
+
"learning_rate": 0.001,
|
368 |
+
"loss": 1.3912,
|
369 |
+
"step": 48
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.8305084745762712,
|
373 |
+
"grad_norm": 1.25,
|
374 |
+
"learning_rate": 0.001,
|
375 |
+
"loss": 1.3249,
|
376 |
+
"step": 49
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.847457627118644,
|
380 |
+
"grad_norm": 1.625,
|
381 |
+
"learning_rate": 0.001,
|
382 |
+
"loss": 1.3285,
|
383 |
+
"step": 50
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.864406779661017,
|
387 |
+
"grad_norm": 1.4140625,
|
388 |
+
"learning_rate": 0.001,
|
389 |
+
"loss": 1.2734,
|
390 |
+
"step": 51
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.8813559322033898,
|
394 |
+
"grad_norm": 1.3828125,
|
395 |
+
"learning_rate": 0.001,
|
396 |
+
"loss": 1.2826,
|
397 |
+
"step": 52
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.8983050847457628,
|
401 |
+
"grad_norm": 1.5,
|
402 |
+
"learning_rate": 0.001,
|
403 |
+
"loss": 1.1952,
|
404 |
+
"step": 53
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.9152542372881356,
|
408 |
+
"grad_norm": 1.2109375,
|
409 |
+
"learning_rate": 0.001,
|
410 |
+
"loss": 1.4186,
|
411 |
+
"step": 54
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.9322033898305084,
|
415 |
+
"grad_norm": 1.5078125,
|
416 |
+
"learning_rate": 0.001,
|
417 |
+
"loss": 1.3943,
|
418 |
+
"step": 55
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.9491525423728814,
|
422 |
+
"grad_norm": 1.796875,
|
423 |
+
"learning_rate": 0.001,
|
424 |
+
"loss": 1.3948,
|
425 |
+
"step": 56
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.9661016949152542,
|
429 |
+
"grad_norm": 1.7734375,
|
430 |
+
"learning_rate": 0.001,
|
431 |
+
"loss": 1.3806,
|
432 |
+
"step": 57
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.9830508474576272,
|
436 |
+
"grad_norm": 1.4609375,
|
437 |
+
"learning_rate": 0.001,
|
438 |
+
"loss": 1.4173,
|
439 |
+
"step": 58
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 1.0,
|
443 |
+
"grad_norm": 1.5234375,
|
444 |
+
"learning_rate": 0.001,
|
445 |
+
"loss": 1.3113,
|
446 |
+
"step": 59
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.0,
|
450 |
+
"step": 59,
|
451 |
+
"total_flos": 8392016473620480.0,
|
452 |
+
"train_loss": 1.3609151254265994,
|
453 |
+
"train_runtime": 66.1562,
|
454 |
+
"train_samples_per_second": 28.327,
|
455 |
+
"train_steps_per_second": 0.892
|
456 |
+
}
|
457 |
+
],
|
458 |
+
"logging_steps": 1,
|
459 |
+
"max_steps": 59,
|
460 |
+
"num_input_tokens_seen": 0,
|
461 |
+
"num_train_epochs": 1,
|
462 |
+
"save_steps": 15,
|
463 |
+
"stateful_callbacks": {
|
464 |
+
"EarlyStoppingCallback": {
|
465 |
+
"args": {
|
466 |
+
"early_stopping_patience": 5,
|
467 |
+
"early_stopping_threshold": 0.0
|
468 |
+
},
|
469 |
+
"attributes": {
|
470 |
+
"early_stopping_patience_counter": 1
|
471 |
+
}
|
472 |
+
},
|
473 |
+
"TrainerControl": {
|
474 |
+
"args": {
|
475 |
+
"should_epoch_stop": false,
|
476 |
+
"should_evaluate": false,
|
477 |
+
"should_log": false,
|
478 |
+
"should_save": true,
|
479 |
+
"should_training_stop": true
|
480 |
+
},
|
481 |
+
"attributes": {}
|
482 |
+
}
|
483 |
+
},
|
484 |
+
"total_flos": 8392016473620480.0,
|
485 |
+
"train_batch_size": 32,
|
486 |
+
"trial_name": null,
|
487 |
+
"trial_params": null
|
488 |
+
}
|