Training in progress, step 180, checkpoint
Browse files- checkpoint-180/README.md +202 -0
- checkpoint-180/adapter_config.json +34 -0
- checkpoint-180/adapter_model.safetensors +3 -0
- checkpoint-180/optimizer.pt +3 -0
- checkpoint-180/rng_state_0.pth +3 -0
- checkpoint-180/rng_state_1.pth +3 -0
- checkpoint-180/rng_state_2.pth +3 -0
- checkpoint-180/rng_state_3.pth +3 -0
- checkpoint-180/scheduler.pt +3 -0
- checkpoint-180/special_tokens_map.json +24 -0
- checkpoint-180/tokenizer.json +0 -0
- checkpoint-180/tokenizer.model +3 -0
- checkpoint-180/tokenizer_config.json +49 -0
- checkpoint-180/trainer_state.json +387 -0
- checkpoint-180/training_args.bin +3 -0
checkpoint-180/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged
|
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-180/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged",
|
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": 0.1,
|
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 |
+
"v_proj",
|
24 |
+
"down_proj",
|
25 |
+
"k_proj",
|
26 |
+
"o_proj",
|
27 |
+
"q_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"up_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-180/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:328b1e951c7fd79cdee800f3245ba044a5cd6d04106a77b7b82e3cff721bb4fe
|
3 |
+
size 167832240
|
checkpoint-180/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25c0bbf99788d3f9193284708fce6b95445c4745a1129e791fcc14c2b01e545b
|
3 |
+
size 335922386
|
checkpoint-180/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae78313eb528c8d3695eebaf4de3539bd0a0bc6ee18c66af1ee183442f1758a0
|
3 |
+
size 15024
|
checkpoint-180/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b38031f60d9e88601d369ef46bcdcf2b5b03f2cb4ba93853bcb2328df7ebb7c
|
3 |
+
size 15024
|
checkpoint-180/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f58092375c93d237cd0e3149aecfbf83e2acdae46279e07a32920d01cb507e64
|
3 |
+
size 15024
|
checkpoint-180/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83cd4bbff9962da7ec6787fcea8d65df7096917f9a5902e249ba7aee8887fe5f
|
3 |
+
size 15024
|
checkpoint-180/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74f15868c98428b757deb41ceef3036d052c50d320ff1d3c76314d699ef0babc
|
3 |
+
size 1064
|
checkpoint-180/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-180/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-180/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-180/tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + message['content'] + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"max_lenght": 8192,
|
37 |
+
"max_length": 8192,
|
38 |
+
"model_max_length": 1000000000000000019884624838656,
|
39 |
+
"pad_token": "<unk>",
|
40 |
+
"padding": true,
|
41 |
+
"sp_model_kwargs": {},
|
42 |
+
"spaces_between_special_tokens": false,
|
43 |
+
"stride": 0,
|
44 |
+
"tokenizer_class": "LlamaTokenizer",
|
45 |
+
"truncation_side": "right",
|
46 |
+
"truncation_strategy": "longest_first",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
+
}
|
checkpoint-180/trainer_state.json
ADDED
@@ -0,0 +1,387 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.021960575133562088,
|
3 |
+
"best_model_checkpoint": "./mistral/21-04-24-Weni-WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.15-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-180_batch_8_2024-04-21_ppid_9/checkpoint-180",
|
4 |
+
"epoch": 5.806451612903226,
|
5 |
+
"eval_steps": 30,
|
6 |
+
"global_step": 180,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.3225806451612903,
|
13 |
+
"grad_norm": 76.17081451416016,
|
14 |
+
"learning_rate": 4.166666666666667e-06,
|
15 |
+
"logits/chosen": -1.8212074041366577,
|
16 |
+
"logits/rejected": -1.836817979812622,
|
17 |
+
"logps/chosen": -181.83949279785156,
|
18 |
+
"logps/rejected": -258.220458984375,
|
19 |
+
"loss": 0.6886,
|
20 |
+
"rewards/accuracies": 0.25,
|
21 |
+
"rewards/chosen": 0.009336434304714203,
|
22 |
+
"rewards/margins": 0.0099251177161932,
|
23 |
+
"rewards/rejected": -0.0005886839935556054,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.6451612903225806,
|
28 |
+
"grad_norm": 40.539878845214844,
|
29 |
+
"learning_rate": 4.741379310344828e-06,
|
30 |
+
"logits/chosen": -1.8025119304656982,
|
31 |
+
"logits/rejected": -1.8262531757354736,
|
32 |
+
"logps/chosen": -148.07679748535156,
|
33 |
+
"logps/rejected": -243.6903839111328,
|
34 |
+
"loss": 0.4144,
|
35 |
+
"rewards/accuracies": 0.949999988079071,
|
36 |
+
"rewards/chosen": 0.695365846157074,
|
37 |
+
"rewards/margins": 0.7868010997772217,
|
38 |
+
"rewards/rejected": -0.09143529087305069,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.967741935483871,
|
43 |
+
"grad_norm": 13.742331504821777,
|
44 |
+
"learning_rate": 4.454022988505747e-06,
|
45 |
+
"logits/chosen": -1.7753016948699951,
|
46 |
+
"logits/rejected": -1.787701964378357,
|
47 |
+
"logps/chosen": -138.11192321777344,
|
48 |
+
"logps/rejected": -181.8013153076172,
|
49 |
+
"loss": 0.2469,
|
50 |
+
"rewards/accuracies": 0.949999988079071,
|
51 |
+
"rewards/chosen": 1.8171169757843018,
|
52 |
+
"rewards/margins": 2.026198387145996,
|
53 |
+
"rewards/rejected": -0.20908141136169434,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.967741935483871,
|
58 |
+
"eval_logits/chosen": -1.8694961071014404,
|
59 |
+
"eval_logits/rejected": -1.8717602491378784,
|
60 |
+
"eval_logps/chosen": -128.06077575683594,
|
61 |
+
"eval_logps/rejected": -171.74044799804688,
|
62 |
+
"eval_loss": 0.2019422948360443,
|
63 |
+
"eval_rewards/accuracies": 1.0,
|
64 |
+
"eval_rewards/chosen": 1.950033187866211,
|
65 |
+
"eval_rewards/margins": 2.1478688716888428,
|
66 |
+
"eval_rewards/rejected": -0.19783565402030945,
|
67 |
+
"eval_runtime": 17.0291,
|
68 |
+
"eval_samples_per_second": 1.644,
|
69 |
+
"eval_steps_per_second": 0.411,
|
70 |
+
"step": 30
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 1.2903225806451613,
|
74 |
+
"grad_norm": 25.29999542236328,
|
75 |
+
"learning_rate": 4.166666666666667e-06,
|
76 |
+
"logits/chosen": -1.832271933555603,
|
77 |
+
"logits/rejected": -1.852087378501892,
|
78 |
+
"logps/chosen": -138.46139526367188,
|
79 |
+
"logps/rejected": -207.39346313476562,
|
80 |
+
"loss": 0.1054,
|
81 |
+
"rewards/accuracies": 1.0,
|
82 |
+
"rewards/chosen": 2.361999034881592,
|
83 |
+
"rewards/margins": 3.551447629928589,
|
84 |
+
"rewards/rejected": -1.1894484758377075,
|
85 |
+
"step": 40
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 1.6129032258064515,
|
89 |
+
"grad_norm": 22.02225112915039,
|
90 |
+
"learning_rate": 3.8793103448275865e-06,
|
91 |
+
"logits/chosen": -1.784176230430603,
|
92 |
+
"logits/rejected": -1.8057140111923218,
|
93 |
+
"logps/chosen": -140.75958251953125,
|
94 |
+
"logps/rejected": -195.9730224609375,
|
95 |
+
"loss": 0.0913,
|
96 |
+
"rewards/accuracies": 0.949999988079071,
|
97 |
+
"rewards/chosen": 2.6018612384796143,
|
98 |
+
"rewards/margins": 3.601649522781372,
|
99 |
+
"rewards/rejected": -0.9997884631156921,
|
100 |
+
"step": 50
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.935483870967742,
|
104 |
+
"grad_norm": 3.1534383296966553,
|
105 |
+
"learning_rate": 3.5919540229885056e-06,
|
106 |
+
"logits/chosen": -1.8954330682754517,
|
107 |
+
"logits/rejected": -1.9075534343719482,
|
108 |
+
"logps/chosen": -144.24533081054688,
|
109 |
+
"logps/rejected": -241.29345703125,
|
110 |
+
"loss": 0.1276,
|
111 |
+
"rewards/accuracies": 0.8500000238418579,
|
112 |
+
"rewards/chosen": 2.946927785873413,
|
113 |
+
"rewards/margins": 4.766872406005859,
|
114 |
+
"rewards/rejected": -1.8199446201324463,
|
115 |
+
"step": 60
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.935483870967742,
|
119 |
+
"eval_logits/chosen": -1.8808324337005615,
|
120 |
+
"eval_logits/rejected": -1.8824094533920288,
|
121 |
+
"eval_logps/chosen": -123.88575744628906,
|
122 |
+
"eval_logps/rejected": -172.878173828125,
|
123 |
+
"eval_loss": 0.09369345754384995,
|
124 |
+
"eval_rewards/accuracies": 1.0,
|
125 |
+
"eval_rewards/chosen": 3.2025339603424072,
|
126 |
+
"eval_rewards/margins": 3.741692066192627,
|
127 |
+
"eval_rewards/rejected": -0.5391579866409302,
|
128 |
+
"eval_runtime": 16.97,
|
129 |
+
"eval_samples_per_second": 1.65,
|
130 |
+
"eval_steps_per_second": 0.412,
|
131 |
+
"step": 60
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 2.258064516129032,
|
135 |
+
"grad_norm": 2.812629461288452,
|
136 |
+
"learning_rate": 3.3045977011494256e-06,
|
137 |
+
"logits/chosen": -1.7766342163085938,
|
138 |
+
"logits/rejected": -1.7891451120376587,
|
139 |
+
"logps/chosen": -117.1172103881836,
|
140 |
+
"logps/rejected": -197.6320037841797,
|
141 |
+
"loss": 0.0476,
|
142 |
+
"rewards/accuracies": 1.0,
|
143 |
+
"rewards/chosen": 4.011519432067871,
|
144 |
+
"rewards/margins": 5.832650184631348,
|
145 |
+
"rewards/rejected": -1.8211311101913452,
|
146 |
+
"step": 70
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.5806451612903225,
|
150 |
+
"grad_norm": 7.378849506378174,
|
151 |
+
"learning_rate": 3.017241379310345e-06,
|
152 |
+
"logits/chosen": -1.873382568359375,
|
153 |
+
"logits/rejected": -1.8968416452407837,
|
154 |
+
"logps/chosen": -115.59322357177734,
|
155 |
+
"logps/rejected": -202.29922485351562,
|
156 |
+
"loss": 0.0422,
|
157 |
+
"rewards/accuracies": 1.0,
|
158 |
+
"rewards/chosen": 3.784104824066162,
|
159 |
+
"rewards/margins": 5.744203090667725,
|
160 |
+
"rewards/rejected": -1.9600980281829834,
|
161 |
+
"step": 80
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 2.903225806451613,
|
165 |
+
"grad_norm": 1.8571914434432983,
|
166 |
+
"learning_rate": 2.729885057471265e-06,
|
167 |
+
"logits/chosen": -1.8314573764801025,
|
168 |
+
"logits/rejected": -1.8384296894073486,
|
169 |
+
"logps/chosen": -135.9064483642578,
|
170 |
+
"logps/rejected": -216.98532104492188,
|
171 |
+
"loss": 0.0187,
|
172 |
+
"rewards/accuracies": 1.0,
|
173 |
+
"rewards/chosen": 3.950857639312744,
|
174 |
+
"rewards/margins": 6.437536716461182,
|
175 |
+
"rewards/rejected": -2.4866783618927,
|
176 |
+
"step": 90
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.903225806451613,
|
180 |
+
"eval_logits/chosen": -1.8896868228912354,
|
181 |
+
"eval_logits/rejected": -1.8911399841308594,
|
182 |
+
"eval_logps/chosen": -121.66944885253906,
|
183 |
+
"eval_logps/rejected": -175.50460815429688,
|
184 |
+
"eval_loss": 0.05724393203854561,
|
185 |
+
"eval_rewards/accuracies": 1.0,
|
186 |
+
"eval_rewards/chosen": 3.8674278259277344,
|
187 |
+
"eval_rewards/margins": 5.194509029388428,
|
188 |
+
"eval_rewards/rejected": -1.3270814418792725,
|
189 |
+
"eval_runtime": 16.9692,
|
190 |
+
"eval_samples_per_second": 1.65,
|
191 |
+
"eval_steps_per_second": 0.413,
|
192 |
+
"step": 90
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 3.225806451612903,
|
196 |
+
"grad_norm": 5.707949638366699,
|
197 |
+
"learning_rate": 2.4425287356321844e-06,
|
198 |
+
"logits/chosen": -1.8123356103897095,
|
199 |
+
"logits/rejected": -1.836766242980957,
|
200 |
+
"logps/chosen": -168.2237548828125,
|
201 |
+
"logps/rejected": -232.3643035888672,
|
202 |
+
"loss": 0.0175,
|
203 |
+
"rewards/accuracies": 1.0,
|
204 |
+
"rewards/chosen": 4.8013739585876465,
|
205 |
+
"rewards/margins": 7.281676292419434,
|
206 |
+
"rewards/rejected": -2.4803037643432617,
|
207 |
+
"step": 100
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 3.5483870967741935,
|
211 |
+
"grad_norm": 3.4297404289245605,
|
212 |
+
"learning_rate": 2.1551724137931035e-06,
|
213 |
+
"logits/chosen": -1.8724552392959595,
|
214 |
+
"logits/rejected": -1.890865683555603,
|
215 |
+
"logps/chosen": -181.77548217773438,
|
216 |
+
"logps/rejected": -284.026611328125,
|
217 |
+
"loss": 0.0052,
|
218 |
+
"rewards/accuracies": 1.0,
|
219 |
+
"rewards/chosen": 4.642284393310547,
|
220 |
+
"rewards/margins": 8.698179244995117,
|
221 |
+
"rewards/rejected": -4.0558953285217285,
|
222 |
+
"step": 110
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 3.870967741935484,
|
226 |
+
"grad_norm": 0.28286024928092957,
|
227 |
+
"learning_rate": 1.8678160919540231e-06,
|
228 |
+
"logits/chosen": -1.8464359045028687,
|
229 |
+
"logits/rejected": -1.8764251470565796,
|
230 |
+
"logps/chosen": -131.70431518554688,
|
231 |
+
"logps/rejected": -235.42318725585938,
|
232 |
+
"loss": 0.0118,
|
233 |
+
"rewards/accuracies": 1.0,
|
234 |
+
"rewards/chosen": 4.332093238830566,
|
235 |
+
"rewards/margins": 7.9131927490234375,
|
236 |
+
"rewards/rejected": -3.581099271774292,
|
237 |
+
"step": 120
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 3.870967741935484,
|
241 |
+
"eval_logits/chosen": -1.8917609453201294,
|
242 |
+
"eval_logits/rejected": -1.8926684856414795,
|
243 |
+
"eval_logps/chosen": -120.6841049194336,
|
244 |
+
"eval_logps/rejected": -178.48434448242188,
|
245 |
+
"eval_loss": 0.029182463884353638,
|
246 |
+
"eval_rewards/accuracies": 1.0,
|
247 |
+
"eval_rewards/chosen": 4.163033962249756,
|
248 |
+
"eval_rewards/margins": 6.384037494659424,
|
249 |
+
"eval_rewards/rejected": -2.221003770828247,
|
250 |
+
"eval_runtime": 16.9634,
|
251 |
+
"eval_samples_per_second": 1.651,
|
252 |
+
"eval_steps_per_second": 0.413,
|
253 |
+
"step": 120
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 4.193548387096774,
|
257 |
+
"grad_norm": 0.30069565773010254,
|
258 |
+
"learning_rate": 1.5804597701149427e-06,
|
259 |
+
"logits/chosen": -1.8492038249969482,
|
260 |
+
"logits/rejected": -1.8685414791107178,
|
261 |
+
"logps/chosen": -164.83790588378906,
|
262 |
+
"logps/rejected": -238.30447387695312,
|
263 |
+
"loss": 0.0108,
|
264 |
+
"rewards/accuracies": 1.0,
|
265 |
+
"rewards/chosen": 5.031315326690674,
|
266 |
+
"rewards/margins": 8.202493667602539,
|
267 |
+
"rewards/rejected": -3.171177387237549,
|
268 |
+
"step": 130
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 4.516129032258064,
|
272 |
+
"grad_norm": 0.09980618953704834,
|
273 |
+
"learning_rate": 1.2931034482758623e-06,
|
274 |
+
"logits/chosen": -1.9228675365447998,
|
275 |
+
"logits/rejected": -1.9402902126312256,
|
276 |
+
"logps/chosen": -167.69627380371094,
|
277 |
+
"logps/rejected": -252.85574340820312,
|
278 |
+
"loss": 0.0283,
|
279 |
+
"rewards/accuracies": 1.0,
|
280 |
+
"rewards/chosen": 3.7600669860839844,
|
281 |
+
"rewards/margins": 8.49266242980957,
|
282 |
+
"rewards/rejected": -4.7325944900512695,
|
283 |
+
"step": 140
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 4.838709677419355,
|
287 |
+
"grad_norm": 0.5666964054107666,
|
288 |
+
"learning_rate": 1.0057471264367817e-06,
|
289 |
+
"logits/chosen": -1.8569101095199585,
|
290 |
+
"logits/rejected": -1.872945785522461,
|
291 |
+
"logps/chosen": -123.6576156616211,
|
292 |
+
"logps/rejected": -158.0116424560547,
|
293 |
+
"loss": 0.0058,
|
294 |
+
"rewards/accuracies": 1.0,
|
295 |
+
"rewards/chosen": 4.758939743041992,
|
296 |
+
"rewards/margins": 8.25415325164795,
|
297 |
+
"rewards/rejected": -3.4952139854431152,
|
298 |
+
"step": 150
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 4.838709677419355,
|
302 |
+
"eval_logits/chosen": -1.8856004476547241,
|
303 |
+
"eval_logits/rejected": -1.8862718343734741,
|
304 |
+
"eval_logps/chosen": -120.60621643066406,
|
305 |
+
"eval_logps/rejected": -180.44931030273438,
|
306 |
+
"eval_loss": 0.024126578122377396,
|
307 |
+
"eval_rewards/accuracies": 1.0,
|
308 |
+
"eval_rewards/chosen": 4.186400890350342,
|
309 |
+
"eval_rewards/margins": 6.99689245223999,
|
310 |
+
"eval_rewards/rejected": -2.8104913234710693,
|
311 |
+
"eval_runtime": 16.9717,
|
312 |
+
"eval_samples_per_second": 1.65,
|
313 |
+
"eval_steps_per_second": 0.412,
|
314 |
+
"step": 150
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 5.161290322580645,
|
318 |
+
"grad_norm": 27.14858055114746,
|
319 |
+
"learning_rate": 7.183908045977011e-07,
|
320 |
+
"logits/chosen": -1.8459736108779907,
|
321 |
+
"logits/rejected": -1.8586574792861938,
|
322 |
+
"logps/chosen": -133.19772338867188,
|
323 |
+
"logps/rejected": -223.07730102539062,
|
324 |
+
"loss": 0.0116,
|
325 |
+
"rewards/accuracies": 1.0,
|
326 |
+
"rewards/chosen": 4.50647497177124,
|
327 |
+
"rewards/margins": 8.688131332397461,
|
328 |
+
"rewards/rejected": -4.181654930114746,
|
329 |
+
"step": 160
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 5.483870967741936,
|
333 |
+
"grad_norm": 1.2454370260238647,
|
334 |
+
"learning_rate": 4.3103448275862073e-07,
|
335 |
+
"logits/chosen": -1.8669620752334595,
|
336 |
+
"logits/rejected": -1.8916997909545898,
|
337 |
+
"logps/chosen": -118.95484924316406,
|
338 |
+
"logps/rejected": -204.902099609375,
|
339 |
+
"loss": 0.0162,
|
340 |
+
"rewards/accuracies": 1.0,
|
341 |
+
"rewards/chosen": 3.7229111194610596,
|
342 |
+
"rewards/margins": 8.270120620727539,
|
343 |
+
"rewards/rejected": -4.5472092628479,
|
344 |
+
"step": 170
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 5.806451612903226,
|
348 |
+
"grad_norm": 1.3749877214431763,
|
349 |
+
"learning_rate": 1.4367816091954023e-07,
|
350 |
+
"logits/chosen": -1.8054790496826172,
|
351 |
+
"logits/rejected": -1.8216861486434937,
|
352 |
+
"logps/chosen": -116.97957611083984,
|
353 |
+
"logps/rejected": -225.5679473876953,
|
354 |
+
"loss": 0.0058,
|
355 |
+
"rewards/accuracies": 1.0,
|
356 |
+
"rewards/chosen": 4.90813684463501,
|
357 |
+
"rewards/margins": 9.645859718322754,
|
358 |
+
"rewards/rejected": -4.737723350524902,
|
359 |
+
"step": 180
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 5.806451612903226,
|
363 |
+
"eval_logits/chosen": -1.8866546154022217,
|
364 |
+
"eval_logits/rejected": -1.8871468305587769,
|
365 |
+
"eval_logps/chosen": -120.53617095947266,
|
366 |
+
"eval_logps/rejected": -180.97348022460938,
|
367 |
+
"eval_loss": 0.021960575133562088,
|
368 |
+
"eval_rewards/accuracies": 1.0,
|
369 |
+
"eval_rewards/chosen": 4.207414627075195,
|
370 |
+
"eval_rewards/margins": 7.175161838531494,
|
371 |
+
"eval_rewards/rejected": -2.967747211456299,
|
372 |
+
"eval_runtime": 16.9698,
|
373 |
+
"eval_samples_per_second": 1.65,
|
374 |
+
"eval_steps_per_second": 0.412,
|
375 |
+
"step": 180
|
376 |
+
}
|
377 |
+
],
|
378 |
+
"logging_steps": 10,
|
379 |
+
"max_steps": 180,
|
380 |
+
"num_input_tokens_seen": 0,
|
381 |
+
"num_train_epochs": 6,
|
382 |
+
"save_steps": 90,
|
383 |
+
"total_flos": 0.0,
|
384 |
+
"train_batch_size": 1,
|
385 |
+
"trial_name": null,
|
386 |
+
"trial_params": null
|
387 |
+
}
|
checkpoint-180/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d820e4ac8244824e226f350adbf946348a128d5fdf2ced2087647822264933d3
|
3 |
+
size 5432
|