Training in progress, step 90, checkpoint
Browse files- checkpoint-90/README.md +202 -0
- checkpoint-90/adapter_config.json +29 -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/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-1.0.6-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 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Weni/WeniGPT-Agents-Mistral-1.0.6-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": 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 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-90/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a892d26346c063902e64ba5778f5b190e1b2455949a8e2c6e672e9e4f8b508ca
|
3 |
+
size 13648432
|
checkpoint-90/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e7a2870edc54942cf418f7081cbfb1a18d3a6347d25da75598b9d84558e493c
|
3 |
+
size 27370618
|
checkpoint-90/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7e52325e9d729519836af640f8f754a93ee06730fb2953b5309434b53b17562
|
3 |
+
size 14512
|
checkpoint-90/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a93593cf0342eb47876986e1063102e1546354426a2324c46ddcf1cbecae803
|
3 |
+
size 14512
|
checkpoint-90/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:916b804c69069807b0eeaa294264595c1f4635584c56d1d79e9f07ff130168b8
|
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": 0.464372456073761,
|
3 |
+
"best_model_checkpoint": "./mistral/21-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.11-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-366_batch_4_2024-04-21_ppid_9/checkpoint-90",
|
4 |
+
"epoch": 1.4634146341463414,
|
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": 0.16260162601626016,
|
13 |
+
"grad_norm": 11.074726104736328,
|
14 |
+
"learning_rate": 3.6363636363636366e-06,
|
15 |
+
"logits/chosen": -1.7639459371566772,
|
16 |
+
"logits/rejected": -1.8396574258804321,
|
17 |
+
"logps/chosen": -186.35623168945312,
|
18 |
+
"logps/rejected": -242.7454376220703,
|
19 |
+
"loss": 0.6923,
|
20 |
+
"rewards/accuracies": 0.550000011920929,
|
21 |
+
"rewards/chosen": 0.0025298120453953743,
|
22 |
+
"rewards/margins": 0.002917728153988719,
|
23 |
+
"rewards/rejected": -0.000387916574254632,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.3252032520325203,
|
28 |
+
"grad_norm": 13.123202323913574,
|
29 |
+
"learning_rate": 4.9154929577464795e-06,
|
30 |
+
"logits/chosen": -1.8020210266113281,
|
31 |
+
"logits/rejected": -1.827330231666565,
|
32 |
+
"logps/chosen": -179.5525665283203,
|
33 |
+
"logps/rejected": -159.48426818847656,
|
34 |
+
"loss": 0.6821,
|
35 |
+
"rewards/accuracies": 1.0,
|
36 |
+
"rewards/chosen": 0.0269151721149683,
|
37 |
+
"rewards/margins": 0.020867865532636642,
|
38 |
+
"rewards/rejected": 0.00604730611667037,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.4878048780487805,
|
43 |
+
"grad_norm": 14.401883125305176,
|
44 |
+
"learning_rate": 4.774647887323944e-06,
|
45 |
+
"logits/chosen": -1.7544463872909546,
|
46 |
+
"logits/rejected": -1.8119304180145264,
|
47 |
+
"logps/chosen": -131.93418884277344,
|
48 |
+
"logps/rejected": -186.62869262695312,
|
49 |
+
"loss": 0.6531,
|
50 |
+
"rewards/accuracies": 0.949999988079071,
|
51 |
+
"rewards/chosen": 0.0737195536494255,
|
52 |
+
"rewards/margins": 0.08270301669836044,
|
53 |
+
"rewards/rejected": -0.008983459323644638,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.4878048780487805,
|
58 |
+
"eval_logits/chosen": -1.7289739847183228,
|
59 |
+
"eval_logits/rejected": -1.7717361450195312,
|
60 |
+
"eval_logps/chosen": -135.4998321533203,
|
61 |
+
"eval_logps/rejected": -185.3151397705078,
|
62 |
+
"eval_loss": 0.6393889784812927,
|
63 |
+
"eval_rewards/accuracies": 0.7857142686843872,
|
64 |
+
"eval_rewards/chosen": 0.12710317969322205,
|
65 |
+
"eval_rewards/margins": 0.1346290558576584,
|
66 |
+
"eval_rewards/rejected": -0.007525864988565445,
|
67 |
+
"eval_runtime": 17.3728,
|
68 |
+
"eval_samples_per_second": 1.612,
|
69 |
+
"eval_steps_per_second": 0.806,
|
70 |
+
"step": 30
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 0.6504065040650406,
|
74 |
+
"grad_norm": 15.026944160461426,
|
75 |
+
"learning_rate": 4.647887323943662e-06,
|
76 |
+
"logits/chosen": -1.8521251678466797,
|
77 |
+
"logits/rejected": -1.9095609188079834,
|
78 |
+
"logps/chosen": -167.38348388671875,
|
79 |
+
"logps/rejected": -215.0012969970703,
|
80 |
+
"loss": 0.6343,
|
81 |
+
"rewards/accuracies": 0.800000011920929,
|
82 |
+
"rewards/chosen": 0.11476834118366241,
|
83 |
+
"rewards/margins": 0.10640791803598404,
|
84 |
+
"rewards/rejected": 0.008360415697097778,
|
85 |
+
"step": 40
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 0.8130081300813008,
|
89 |
+
"grad_norm": 15.622106552124023,
|
90 |
+
"learning_rate": 4.507042253521127e-06,
|
91 |
+
"logits/chosen": -1.7336807250976562,
|
92 |
+
"logits/rejected": -1.7874727249145508,
|
93 |
+
"logps/chosen": -151.20423889160156,
|
94 |
+
"logps/rejected": -212.6553192138672,
|
95 |
+
"loss": 0.5966,
|
96 |
+
"rewards/accuracies": 0.949999988079071,
|
97 |
+
"rewards/chosen": 0.16852515935897827,
|
98 |
+
"rewards/margins": 0.19663922488689423,
|
99 |
+
"rewards/rejected": -0.0281140748411417,
|
100 |
+
"step": 50
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.975609756097561,
|
104 |
+
"grad_norm": 15.992025375366211,
|
105 |
+
"learning_rate": 4.3661971830985915e-06,
|
106 |
+
"logits/chosen": -1.8077377080917358,
|
107 |
+
"logits/rejected": -1.8177680969238281,
|
108 |
+
"logps/chosen": -166.0524139404297,
|
109 |
+
"logps/rejected": -166.77749633789062,
|
110 |
+
"loss": 0.5732,
|
111 |
+
"rewards/accuracies": 0.8999999761581421,
|
112 |
+
"rewards/chosen": 0.28099626302719116,
|
113 |
+
"rewards/margins": 0.25574439764022827,
|
114 |
+
"rewards/rejected": 0.0252518467605114,
|
115 |
+
"step": 60
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.975609756097561,
|
119 |
+
"eval_logits/chosen": -1.734244465827942,
|
120 |
+
"eval_logits/rejected": -1.7778174877166748,
|
121 |
+
"eval_logps/chosen": -133.12557983398438,
|
122 |
+
"eval_logps/rejected": -185.54177856445312,
|
123 |
+
"eval_loss": 0.5475863218307495,
|
124 |
+
"eval_rewards/accuracies": 0.7857142686843872,
|
125 |
+
"eval_rewards/chosen": 0.36452820897102356,
|
126 |
+
"eval_rewards/margins": 0.39471906423568726,
|
127 |
+
"eval_rewards/rejected": -0.030190791934728622,
|
128 |
+
"eval_runtime": 17.4075,
|
129 |
+
"eval_samples_per_second": 1.609,
|
130 |
+
"eval_steps_per_second": 0.804,
|
131 |
+
"step": 60
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 1.1382113821138211,
|
135 |
+
"grad_norm": 13.867135047912598,
|
136 |
+
"learning_rate": 4.225352112676057e-06,
|
137 |
+
"logits/chosen": -1.8027187585830688,
|
138 |
+
"logits/rejected": -1.882067084312439,
|
139 |
+
"logps/chosen": -174.7197723388672,
|
140 |
+
"logps/rejected": -223.87844848632812,
|
141 |
+
"loss": 0.5589,
|
142 |
+
"rewards/accuracies": 0.949999988079071,
|
143 |
+
"rewards/chosen": 0.2828216254711151,
|
144 |
+
"rewards/margins": 0.361534059047699,
|
145 |
+
"rewards/rejected": -0.07871242612600327,
|
146 |
+
"step": 70
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.3008130081300813,
|
150 |
+
"grad_norm": 14.660954475402832,
|
151 |
+
"learning_rate": 4.0845070422535216e-06,
|
152 |
+
"logits/chosen": -1.8306058645248413,
|
153 |
+
"logits/rejected": -1.8653805255889893,
|
154 |
+
"logps/chosen": -170.78506469726562,
|
155 |
+
"logps/rejected": -210.1864013671875,
|
156 |
+
"loss": 0.4755,
|
157 |
+
"rewards/accuracies": 0.949999988079071,
|
158 |
+
"rewards/chosen": 0.4126508831977844,
|
159 |
+
"rewards/margins": 0.48294001817703247,
|
160 |
+
"rewards/rejected": -0.07028912007808685,
|
161 |
+
"step": 80
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 1.4634146341463414,
|
165 |
+
"grad_norm": 15.84911060333252,
|
166 |
+
"learning_rate": 3.943661971830986e-06,
|
167 |
+
"logits/chosen": -1.7707087993621826,
|
168 |
+
"logits/rejected": -1.81671142578125,
|
169 |
+
"logps/chosen": -143.22067260742188,
|
170 |
+
"logps/rejected": -205.97433471679688,
|
171 |
+
"loss": 0.5252,
|
172 |
+
"rewards/accuracies": 1.0,
|
173 |
+
"rewards/chosen": 0.4095473885536194,
|
174 |
+
"rewards/margins": 0.5323301553726196,
|
175 |
+
"rewards/rejected": -0.12278278172016144,
|
176 |
+
"step": 90
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.4634146341463414,
|
180 |
+
"eval_logits/chosen": -1.74051034450531,
|
181 |
+
"eval_logits/rejected": -1.7852736711502075,
|
182 |
+
"eval_logps/chosen": -130.74990844726562,
|
183 |
+
"eval_logps/rejected": -186.0896759033203,
|
184 |
+
"eval_loss": 0.464372456073761,
|
185 |
+
"eval_rewards/accuracies": 0.7857142686843872,
|
186 |
+
"eval_rewards/chosen": 0.6020953059196472,
|
187 |
+
"eval_rewards/margins": 0.6870760321617126,
|
188 |
+
"eval_rewards/rejected": -0.08498072624206543,
|
189 |
+
"eval_runtime": 17.3793,
|
190 |
+
"eval_samples_per_second": 1.611,
|
191 |
+
"eval_steps_per_second": 0.806,
|
192 |
+
"step": 90
|
193 |
+
}
|
194 |
+
],
|
195 |
+
"logging_steps": 10,
|
196 |
+
"max_steps": 366,
|
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:bf8c76b4f04172f1a1c03f6305eb134da8232cf806bf7a1d6bdf346f63c45ce3
|
3 |
+
size 5432
|