Training in progress, step 90, checkpoint
Browse files- checkpoint-90/README.md +202 -0
- checkpoint-90/adapter_config.json +34 -0
- checkpoint-90/adapter_model.safetensors +3 -0
- checkpoint-90/optimizer.pt +3 -0
- checkpoint-90/rng_state_0.pth +3 -0
- checkpoint-90/rng_state_1.pth +3 -0
- checkpoint-90/rng_state_2.pth +3 -0
- checkpoint-90/rng_state_3.pth +3 -0
- checkpoint-90/scheduler.pt +3 -0
- checkpoint-90/special_tokens_map.json +24 -0
- checkpoint-90/tokenizer.json +0 -0
- checkpoint-90/tokenizer.model +3 -0
- checkpoint-90/tokenizer_config.json +49 -0
- checkpoint-90/trainer_state.json +204 -0
- checkpoint-90/training_args.bin +3 -0
checkpoint-90/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-90/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": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"down_proj",
|
25 |
+
"q_proj",
|
26 |
+
"k_proj",
|
27 |
+
"o_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"up_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-90/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a171c7bc6c95a3acd96c7b49003d3ded8cbf339c5ec9ae678aebccba4d136b7
|
3 |
+
size 671149168
|
checkpoint-90/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22df96b3f3a6989e4d40658c05b96d96a7d33ff9e3243130fbb07609b3cae65f
|
3 |
+
size 1342555602
|
checkpoint-90/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:418a5f105ae834c3075024076916b2a9475918fe034c12d0dd5b6d91f1aba467
|
3 |
+
size 15024
|
checkpoint-90/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e07ace389d24bc1307b74f42a1e7b8f0117b0db853e2df64ff3f15cb92916a2
|
3 |
+
size 15024
|
checkpoint-90/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da6a990f346d7014dffb28fa2bc7d3b890bd3c53712503fce3656da48d3d6e50
|
3 |
+
size 15024
|
checkpoint-90/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e95f356ca38179b05993f55daece0223e96fa10b9a1b9ea2102a739211333f63
|
3 |
+
size 15024
|
checkpoint-90/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37942fbf08ffff475f8960a2ba3c0870c5267cfb134607d82b886bf603270159
|
3 |
+
size 1064
|
checkpoint-90/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-90/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-90/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-90/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-90/trainer_state.json
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.04710844159126282,
|
3 |
+
"best_model_checkpoint": "./mistral/22-04-24-Weni-WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.24-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-180_batch_8_2024-04-22_ppid_9/checkpoint-90",
|
4 |
+
"epoch": 2.903225806451613,
|
5 |
+
"eval_steps": 30,
|
6 |
+
"global_step": 90,
|
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": 18.102449417114258,
|
14 |
+
"learning_rate": 4.971264367816092e-06,
|
15 |
+
"logits/chosen": -1.8189502954483032,
|
16 |
+
"logits/rejected": -1.8384132385253906,
|
17 |
+
"logps/chosen": -183.32998657226562,
|
18 |
+
"logps/rejected": -217.82275390625,
|
19 |
+
"loss": 0.6772,
|
20 |
+
"rewards/accuracies": 0.3499999940395355,
|
21 |
+
"rewards/chosen": 0.028210829943418503,
|
22 |
+
"rewards/margins": 0.022311249747872353,
|
23 |
+
"rewards/rejected": 0.0058995820581912994,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.6451612903225806,
|
28 |
+
"grad_norm": 20.25644302368164,
|
29 |
+
"learning_rate": 4.71264367816092e-06,
|
30 |
+
"logits/chosen": -1.8640209436416626,
|
31 |
+
"logits/rejected": -1.8766177892684937,
|
32 |
+
"logps/chosen": -152.9895477294922,
|
33 |
+
"logps/rejected": -246.1815948486328,
|
34 |
+
"loss": 0.4471,
|
35 |
+
"rewards/accuracies": 0.949999988079071,
|
36 |
+
"rewards/chosen": 0.5268799662590027,
|
37 |
+
"rewards/margins": 0.6505464315414429,
|
38 |
+
"rewards/rejected": -0.12366630882024765,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.967741935483871,
|
43 |
+
"grad_norm": 23.647602081298828,
|
44 |
+
"learning_rate": 4.42528735632184e-06,
|
45 |
+
"logits/chosen": -1.8179765939712524,
|
46 |
+
"logits/rejected": -1.8386437892913818,
|
47 |
+
"logps/chosen": -154.68057250976562,
|
48 |
+
"logps/rejected": -222.60986328125,
|
49 |
+
"loss": 0.2964,
|
50 |
+
"rewards/accuracies": 0.949999988079071,
|
51 |
+
"rewards/chosen": 1.1595659255981445,
|
52 |
+
"rewards/margins": 1.5337896347045898,
|
53 |
+
"rewards/rejected": -0.3742235600948334,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.967741935483871,
|
58 |
+
"eval_logits/chosen": -1.922228217124939,
|
59 |
+
"eval_logits/rejected": -1.9377918243408203,
|
60 |
+
"eval_logps/chosen": -190.84751892089844,
|
61 |
+
"eval_logps/rejected": -194.19583129882812,
|
62 |
+
"eval_loss": 0.25011441111564636,
|
63 |
+
"eval_rewards/accuracies": 0.8571428656578064,
|
64 |
+
"eval_rewards/chosen": 0.8715044856071472,
|
65 |
+
"eval_rewards/margins": 1.0091807842254639,
|
66 |
+
"eval_rewards/rejected": -0.13767634332180023,
|
67 |
+
"eval_runtime": 15.9917,
|
68 |
+
"eval_samples_per_second": 1.751,
|
69 |
+
"eval_steps_per_second": 0.438,
|
70 |
+
"step": 30
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 1.2903225806451613,
|
74 |
+
"grad_norm": 14.360973358154297,
|
75 |
+
"learning_rate": 4.137931034482759e-06,
|
76 |
+
"logits/chosen": -1.7312577962875366,
|
77 |
+
"logits/rejected": -1.720571517944336,
|
78 |
+
"logps/chosen": -133.35958862304688,
|
79 |
+
"logps/rejected": -174.8995361328125,
|
80 |
+
"loss": 0.1702,
|
81 |
+
"rewards/accuracies": 0.949999988079071,
|
82 |
+
"rewards/chosen": 2.0476880073547363,
|
83 |
+
"rewards/margins": 2.6601643562316895,
|
84 |
+
"rewards/rejected": -0.6124762296676636,
|
85 |
+
"step": 40
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 1.6129032258064515,
|
89 |
+
"grad_norm": 7.5603814125061035,
|
90 |
+
"learning_rate": 3.850574712643678e-06,
|
91 |
+
"logits/chosen": -1.814079999923706,
|
92 |
+
"logits/rejected": -1.8412790298461914,
|
93 |
+
"logps/chosen": -135.43051147460938,
|
94 |
+
"logps/rejected": -218.2666473388672,
|
95 |
+
"loss": 0.1671,
|
96 |
+
"rewards/accuracies": 1.0,
|
97 |
+
"rewards/chosen": 2.6564764976501465,
|
98 |
+
"rewards/margins": 3.553129196166992,
|
99 |
+
"rewards/rejected": -0.8966524004936218,
|
100 |
+
"step": 50
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.935483870967742,
|
104 |
+
"grad_norm": 1.6607310771942139,
|
105 |
+
"learning_rate": 3.563218390804598e-06,
|
106 |
+
"logits/chosen": -1.8398892879486084,
|
107 |
+
"logits/rejected": -1.8503402471542358,
|
108 |
+
"logps/chosen": -147.40121459960938,
|
109 |
+
"logps/rejected": -175.20462036132812,
|
110 |
+
"loss": 0.1148,
|
111 |
+
"rewards/accuracies": 0.949999988079071,
|
112 |
+
"rewards/chosen": 2.9025120735168457,
|
113 |
+
"rewards/margins": 3.795964002609253,
|
114 |
+
"rewards/rejected": -0.8934518098831177,
|
115 |
+
"step": 60
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.935483870967742,
|
119 |
+
"eval_logits/chosen": -1.933964729309082,
|
120 |
+
"eval_logits/rejected": -1.9501203298568726,
|
121 |
+
"eval_logps/chosen": -186.97340393066406,
|
122 |
+
"eval_logps/rejected": -197.0532989501953,
|
123 |
+
"eval_loss": 0.11131088435649872,
|
124 |
+
"eval_rewards/accuracies": 0.8571428656578064,
|
125 |
+
"eval_rewards/chosen": 1.6463254690170288,
|
126 |
+
"eval_rewards/margins": 2.355492115020752,
|
127 |
+
"eval_rewards/rejected": -0.7091667056083679,
|
128 |
+
"eval_runtime": 15.9564,
|
129 |
+
"eval_samples_per_second": 1.755,
|
130 |
+
"eval_steps_per_second": 0.439,
|
131 |
+
"step": 60
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 2.258064516129032,
|
135 |
+
"grad_norm": 1.0933343172073364,
|
136 |
+
"learning_rate": 3.2758620689655175e-06,
|
137 |
+
"logits/chosen": -1.8214714527130127,
|
138 |
+
"logits/rejected": -1.8398475646972656,
|
139 |
+
"logps/chosen": -123.23341369628906,
|
140 |
+
"logps/rejected": -169.8323974609375,
|
141 |
+
"loss": 0.0958,
|
142 |
+
"rewards/accuracies": 0.8999999761581421,
|
143 |
+
"rewards/chosen": 3.013068914413452,
|
144 |
+
"rewards/margins": 3.9151065349578857,
|
145 |
+
"rewards/rejected": -0.9020377993583679,
|
146 |
+
"step": 70
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.5806451612903225,
|
150 |
+
"grad_norm": 1.6529628038406372,
|
151 |
+
"learning_rate": 2.988505747126437e-06,
|
152 |
+
"logits/chosen": -1.8991115093231201,
|
153 |
+
"logits/rejected": -1.9303562641143799,
|
154 |
+
"logps/chosen": -126.10279846191406,
|
155 |
+
"logps/rejected": -249.8067169189453,
|
156 |
+
"loss": 0.0542,
|
157 |
+
"rewards/accuracies": 1.0,
|
158 |
+
"rewards/chosen": 2.2060089111328125,
|
159 |
+
"rewards/margins": 4.4772820472717285,
|
160 |
+
"rewards/rejected": -2.271273136138916,
|
161 |
+
"step": 80
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 2.903225806451613,
|
165 |
+
"grad_norm": 1.3197133541107178,
|
166 |
+
"learning_rate": 2.7011494252873567e-06,
|
167 |
+
"logits/chosen": -1.9221817255020142,
|
168 |
+
"logits/rejected": -1.926163911819458,
|
169 |
+
"logps/chosen": -130.5477752685547,
|
170 |
+
"logps/rejected": -212.64401245117188,
|
171 |
+
"loss": 0.0655,
|
172 |
+
"rewards/accuracies": 1.0,
|
173 |
+
"rewards/chosen": 3.013507127761841,
|
174 |
+
"rewards/margins": 4.679448127746582,
|
175 |
+
"rewards/rejected": -1.665941596031189,
|
176 |
+
"step": 90
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.903225806451613,
|
180 |
+
"eval_logits/chosen": -1.9456537961959839,
|
181 |
+
"eval_logits/rejected": -1.9615535736083984,
|
182 |
+
"eval_logps/chosen": -184.64419555664062,
|
183 |
+
"eval_logps/rejected": -200.91307067871094,
|
184 |
+
"eval_loss": 0.04710844159126282,
|
185 |
+
"eval_rewards/accuracies": 1.0,
|
186 |
+
"eval_rewards/chosen": 2.112164258956909,
|
187 |
+
"eval_rewards/margins": 3.5932810306549072,
|
188 |
+
"eval_rewards/rejected": -1.4811171293258667,
|
189 |
+
"eval_runtime": 15.9489,
|
190 |
+
"eval_samples_per_second": 1.756,
|
191 |
+
"eval_steps_per_second": 0.439,
|
192 |
+
"step": 90
|
193 |
+
}
|
194 |
+
],
|
195 |
+
"logging_steps": 10,
|
196 |
+
"max_steps": 180,
|
197 |
+
"num_input_tokens_seen": 0,
|
198 |
+
"num_train_epochs": 6,
|
199 |
+
"save_steps": 90,
|
200 |
+
"total_flos": 0.0,
|
201 |
+
"train_batch_size": 1,
|
202 |
+
"trial_name": null,
|
203 |
+
"trial_params": null
|
204 |
+
}
|
checkpoint-90/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baec7ea2b41466caf7e604a031129dac45a16ab7fc0b825bc8ae51c489e5f800
|
3 |
+
size 5432
|