Upload folder using huggingface_hub
Browse files- README.md +59 -0
- adapter_config.json +27 -0
- adapter_model.safetensors +3 -0
- all_results.json +7 -0
- checkpoint-100/README.md +204 -0
- checkpoint-100/adapter_config.json +27 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +24 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +45 -0
- checkpoint-100/trainer_state.json +141 -0
- checkpoint-100/training_args.bin +3 -0
- runs/Feb26_08-29-49_e48567a81c6c/events.out.tfevents.1708936364.e48567a81c6c.9041.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
- train_results.json +7 -0
- trainer_log.jsonl +31 -0
- trainer_state.json +210 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- llama-factory
|
6 |
+
- lora
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
9 |
+
model-index:
|
10 |
+
- name: train_2024-02-26-08-28-46
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# train_2024-02-26-08-28-46
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the docker_NL dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0002
|
39 |
+
- train_batch_size: 4
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 4
|
43 |
+
- total_train_batch_size: 16
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- num_epochs: 1.0
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- PEFT 0.8.2
|
56 |
+
- Transformers 4.37.2
|
57 |
+
- Pytorch 2.1.0+cu121
|
58 |
+
- Datasets 2.17.1
|
59 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a97ed10a3e2f7be387fb883bddfab1a1d050c36e6dc21963e74762678e29a045
|
3 |
+
size 13648432
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.1083572210361626,
|
4 |
+
"train_runtime": 702.143,
|
5 |
+
"train_samples_per_second": 3.439,
|
6 |
+
"train_steps_per_second": 0.215
|
7 |
+
}
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abcf32385dc16200df94be61fa230036c0b0b7c708bdd6b5341d0542418bcdfd
|
3 |
+
size 13648432
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f9187b3934f7a79bb52f568a729563f7e8683a7706a56840564aab4dde924d2
|
3 |
+
size 27370618
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f59e6cb274ddf6a80c0cda40964656d0c7bb8916758f90c754c15d3a248bfaf
|
3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35f52adf1fa501af84b48d31f630e1f3d29b636989b35ff5b721ff049022a89d
|
3 |
+
size 1064
|
checkpoint-100/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": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-100/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-100/tokenizer_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6622516556291391,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03,
|
13 |
+
"learning_rate": 0.00019945941475610623,
|
14 |
+
"loss": 0.6627,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.07,
|
19 |
+
"learning_rate": 0.00019784350367254322,
|
20 |
+
"loss": 0.3933,
|
21 |
+
"step": 10
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.1,
|
25 |
+
"learning_rate": 0.00019516973750305532,
|
26 |
+
"loss": 0.2526,
|
27 |
+
"step": 15
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.13,
|
31 |
+
"learning_rate": 0.0001914670242183795,
|
32 |
+
"loss": 0.2494,
|
33 |
+
"step": 20
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.17,
|
37 |
+
"learning_rate": 0.00018677539646179707,
|
38 |
+
"loss": 0.1195,
|
39 |
+
"step": 25
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.2,
|
43 |
+
"learning_rate": 0.00018114557872800905,
|
44 |
+
"loss": 0.1413,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.23,
|
49 |
+
"learning_rate": 0.00017463843894486937,
|
50 |
+
"loss": 0.1202,
|
51 |
+
"step": 35
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.26,
|
55 |
+
"learning_rate": 0.00016732433038731242,
|
56 |
+
"loss": 0.1129,
|
57 |
+
"step": 40
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.3,
|
61 |
+
"learning_rate": 0.0001592823310385073,
|
62 |
+
"loss": 0.1156,
|
63 |
+
"step": 45
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.33,
|
67 |
+
"learning_rate": 0.00015059938862204127,
|
68 |
+
"loss": 0.0889,
|
69 |
+
"step": 50
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.36,
|
73 |
+
"learning_rate": 0.00014136938054879283,
|
74 |
+
"loss": 0.0921,
|
75 |
+
"step": 55
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.4,
|
79 |
+
"learning_rate": 0.0001316920989420703,
|
80 |
+
"loss": 0.0577,
|
81 |
+
"step": 60
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.43,
|
85 |
+
"learning_rate": 0.00012167217171462566,
|
86 |
+
"loss": 0.0885,
|
87 |
+
"step": 65
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.46,
|
91 |
+
"learning_rate": 0.00011141793136253986,
|
92 |
+
"loss": 0.0795,
|
93 |
+
"step": 70
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5,
|
97 |
+
"learning_rate": 0.00010104024370624644,
|
98 |
+
"loss": 0.0613,
|
99 |
+
"step": 75
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.53,
|
103 |
+
"learning_rate": 9.065130924199998e-05,
|
104 |
+
"loss": 0.0661,
|
105 |
+
"step": 80
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.56,
|
109 |
+
"learning_rate": 8.036345006322359e-05,
|
110 |
+
"loss": 0.0333,
|
111 |
+
"step": 85
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.6,
|
115 |
+
"learning_rate": 7.028789546718326e-05,
|
116 |
+
"loss": 0.0512,
|
117 |
+
"step": 90
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.63,
|
121 |
+
"learning_rate": 6.053357937665237e-05,
|
122 |
+
"loss": 0.0553,
|
123 |
+
"step": 95
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.66,
|
127 |
+
"learning_rate": 5.1205962578487155e-05,
|
128 |
+
"loss": 0.0409,
|
129 |
+
"step": 100
|
130 |
+
}
|
131 |
+
],
|
132 |
+
"logging_steps": 5,
|
133 |
+
"max_steps": 151,
|
134 |
+
"num_input_tokens_seen": 0,
|
135 |
+
"num_train_epochs": 1,
|
136 |
+
"save_steps": 100,
|
137 |
+
"total_flos": 4563475407568896.0,
|
138 |
+
"train_batch_size": 4,
|
139 |
+
"trial_name": null,
|
140 |
+
"trial_params": null
|
141 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:958a44028e9e507765c0ff813e71751e7147b055850af6aaf4f50ff29284554d
|
3 |
+
size 4920
|
runs/Feb26_08-29-49_e48567a81c6c/events.out.tfevents.1708936364.e48567a81c6c.9041.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ef2c752dd899916e32cdf6f895cf43d68e83e66103e9613752108ac062a6f6c
|
3 |
+
size 9993
|
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": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.1083572210361626,
|
4 |
+
"train_runtime": 702.143,
|
5 |
+
"train_samples_per_second": 3.439,
|
6 |
+
"train_steps_per_second": 0.215
|
7 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 5, "total_steps": 151, "loss": 0.6627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019945941475610623, "epoch": 0.03, "percentage": 3.31, "elapsed_time": "0:00:23", "remaining_time": "0:11:18"}
|
2 |
+
{"current_steps": 10, "total_steps": 151, "loss": 0.3933, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019784350367254322, "epoch": 0.07, "percentage": 6.62, "elapsed_time": "0:00:44", "remaining_time": "0:10:29"}
|
3 |
+
{"current_steps": 15, "total_steps": 151, "loss": 0.2526, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019516973750305532, "epoch": 0.1, "percentage": 9.93, "elapsed_time": "0:01:07", "remaining_time": "0:10:10"}
|
4 |
+
{"current_steps": 20, "total_steps": 151, "loss": 0.2494, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001914670242183795, "epoch": 0.13, "percentage": 13.25, "elapsed_time": "0:01:29", "remaining_time": "0:09:44"}
|
5 |
+
{"current_steps": 25, "total_steps": 151, "loss": 0.1195, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018677539646179707, "epoch": 0.17, "percentage": 16.56, "elapsed_time": "0:01:53", "remaining_time": "0:09:29"}
|
6 |
+
{"current_steps": 30, "total_steps": 151, "loss": 0.1413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018114557872800905, "epoch": 0.2, "percentage": 19.87, "elapsed_time": "0:02:15", "remaining_time": "0:09:08"}
|
7 |
+
{"current_steps": 35, "total_steps": 151, "loss": 0.1202, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017463843894486937, "epoch": 0.23, "percentage": 23.18, "elapsed_time": "0:02:39", "remaining_time": "0:08:48"}
|
8 |
+
{"current_steps": 40, "total_steps": 151, "loss": 0.1129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016732433038731242, "epoch": 0.26, "percentage": 26.49, "elapsed_time": "0:03:02", "remaining_time": "0:08:27"}
|
9 |
+
{"current_steps": 45, "total_steps": 151, "loss": 0.1156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001592823310385073, "epoch": 0.3, "percentage": 29.8, "elapsed_time": "0:03:26", "remaining_time": "0:08:06"}
|
10 |
+
{"current_steps": 50, "total_steps": 151, "loss": 0.0889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015059938862204127, "epoch": 0.33, "percentage": 33.11, "elapsed_time": "0:03:50", "remaining_time": "0:07:46"}
|
11 |
+
{"current_steps": 55, "total_steps": 151, "loss": 0.0921, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014136938054879283, "epoch": 0.36, "percentage": 36.42, "elapsed_time": "0:04:14", "remaining_time": "0:07:23"}
|
12 |
+
{"current_steps": 60, "total_steps": 151, "loss": 0.0577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001316920989420703, "epoch": 0.4, "percentage": 39.74, "elapsed_time": "0:04:37", "remaining_time": "0:07:01"}
|
13 |
+
{"current_steps": 65, "total_steps": 151, "loss": 0.0885, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012167217171462566, "epoch": 0.43, "percentage": 43.05, "elapsed_time": "0:05:00", "remaining_time": "0:06:37"}
|
14 |
+
{"current_steps": 70, "total_steps": 151, "loss": 0.0795, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011141793136253986, "epoch": 0.46, "percentage": 46.36, "elapsed_time": "0:05:23", "remaining_time": "0:06:14"}
|
15 |
+
{"current_steps": 75, "total_steps": 151, "loss": 0.0613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010104024370624644, "epoch": 0.5, "percentage": 49.67, "elapsed_time": "0:05:46", "remaining_time": "0:05:51"}
|
16 |
+
{"current_steps": 80, "total_steps": 151, "loss": 0.0661, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.065130924199998e-05, "epoch": 0.53, "percentage": 52.98, "elapsed_time": "0:06:10", "remaining_time": "0:05:29"}
|
17 |
+
{"current_steps": 85, "total_steps": 151, "loss": 0.0333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.036345006322359e-05, "epoch": 0.56, "percentage": 56.29, "elapsed_time": "0:06:34", "remaining_time": "0:05:06"}
|
18 |
+
{"current_steps": 90, "total_steps": 151, "loss": 0.0512, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.028789546718326e-05, "epoch": 0.6, "percentage": 59.6, "elapsed_time": "0:06:58", "remaining_time": "0:04:43"}
|
19 |
+
{"current_steps": 95, "total_steps": 151, "loss": 0.0553, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.053357937665237e-05, "epoch": 0.63, "percentage": 62.91, "elapsed_time": "0:07:21", "remaining_time": "0:04:20"}
|
20 |
+
{"current_steps": 100, "total_steps": 151, "loss": 0.0409, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.1205962578487155e-05, "epoch": 0.66, "percentage": 66.23, "elapsed_time": "0:07:44", "remaining_time": "0:03:57"}
|
21 |
+
{"current_steps": 105, "total_steps": 151, "loss": 0.0592, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.240589251272342e-05, "epoch": 0.7, "percentage": 69.54, "elapsed_time": "0:08:08", "remaining_time": "0:03:33"}
|
22 |
+
{"current_steps": 110, "total_steps": 151, "loss": 0.0536, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.422851293981676e-05, "epoch": 0.73, "percentage": 72.85, "elapsed_time": "0:08:30", "remaining_time": "0:03:10"}
|
23 |
+
{"current_steps": 115, "total_steps": 151, "loss": 0.0275, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6762235274383772e-05, "epoch": 0.76, "percentage": 76.16, "elapsed_time": "0:08:54", "remaining_time": "0:02:47"}
|
24 |
+
{"current_steps": 120, "total_steps": 151, "loss": 0.0466, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.008778270707944e-05, "epoch": 0.79, "percentage": 79.47, "elapsed_time": "0:09:18", "remaining_time": "0:02:24"}
|
25 |
+
{"current_steps": 125, "total_steps": 151, "loss": 0.0328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4277317449282834e-05, "epoch": 0.83, "percentage": 82.78, "elapsed_time": "0:09:41", "remaining_time": "0:02:00"}
|
26 |
+
{"current_steps": 130, "total_steps": 151, "loss": 0.0299, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.393660536564408e-06, "epoch": 0.86, "percentage": 86.09, "elapsed_time": "0:10:05", "remaining_time": "0:01:37"}
|
27 |
+
{"current_steps": 135, "total_steps": 151, "loss": 0.0258, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.489612626189245e-06, "epoch": 0.89, "percentage": 89.4, "elapsed_time": "0:10:28", "remaining_time": "0:01:14"}
|
28 |
+
{"current_steps": 140, "total_steps": 151, "loss": 0.0374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.607383131993424e-06, "epoch": 0.93, "percentage": 92.72, "elapsed_time": "0:10:52", "remaining_time": "0:00:51"}
|
29 |
+
{"current_steps": 145, "total_steps": 151, "loss": 0.037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.781338686584927e-07, "epoch": 0.96, "percentage": 96.03, "elapsed_time": "0:11:14", "remaining_time": "0:00:27"}
|
30 |
+
{"current_steps": 150, "total_steps": 151, "loss": 0.0316, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.164213936770576e-08, "epoch": 0.99, "percentage": 99.34, "elapsed_time": "0:11:37", "remaining_time": "0:00:04"}
|
31 |
+
{"current_steps": 151, "total_steps": 151, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:11:42", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 151,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03,
|
13 |
+
"learning_rate": 0.00019945941475610623,
|
14 |
+
"loss": 0.6627,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.07,
|
19 |
+
"learning_rate": 0.00019784350367254322,
|
20 |
+
"loss": 0.3933,
|
21 |
+
"step": 10
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.1,
|
25 |
+
"learning_rate": 0.00019516973750305532,
|
26 |
+
"loss": 0.2526,
|
27 |
+
"step": 15
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.13,
|
31 |
+
"learning_rate": 0.0001914670242183795,
|
32 |
+
"loss": 0.2494,
|
33 |
+
"step": 20
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.17,
|
37 |
+
"learning_rate": 0.00018677539646179707,
|
38 |
+
"loss": 0.1195,
|
39 |
+
"step": 25
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.2,
|
43 |
+
"learning_rate": 0.00018114557872800905,
|
44 |
+
"loss": 0.1413,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.23,
|
49 |
+
"learning_rate": 0.00017463843894486937,
|
50 |
+
"loss": 0.1202,
|
51 |
+
"step": 35
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.26,
|
55 |
+
"learning_rate": 0.00016732433038731242,
|
56 |
+
"loss": 0.1129,
|
57 |
+
"step": 40
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.3,
|
61 |
+
"learning_rate": 0.0001592823310385073,
|
62 |
+
"loss": 0.1156,
|
63 |
+
"step": 45
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.33,
|
67 |
+
"learning_rate": 0.00015059938862204127,
|
68 |
+
"loss": 0.0889,
|
69 |
+
"step": 50
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.36,
|
73 |
+
"learning_rate": 0.00014136938054879283,
|
74 |
+
"loss": 0.0921,
|
75 |
+
"step": 55
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.4,
|
79 |
+
"learning_rate": 0.0001316920989420703,
|
80 |
+
"loss": 0.0577,
|
81 |
+
"step": 60
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.43,
|
85 |
+
"learning_rate": 0.00012167217171462566,
|
86 |
+
"loss": 0.0885,
|
87 |
+
"step": 65
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.46,
|
91 |
+
"learning_rate": 0.00011141793136253986,
|
92 |
+
"loss": 0.0795,
|
93 |
+
"step": 70
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5,
|
97 |
+
"learning_rate": 0.00010104024370624644,
|
98 |
+
"loss": 0.0613,
|
99 |
+
"step": 75
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.53,
|
103 |
+
"learning_rate": 9.065130924199998e-05,
|
104 |
+
"loss": 0.0661,
|
105 |
+
"step": 80
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.56,
|
109 |
+
"learning_rate": 8.036345006322359e-05,
|
110 |
+
"loss": 0.0333,
|
111 |
+
"step": 85
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.6,
|
115 |
+
"learning_rate": 7.028789546718326e-05,
|
116 |
+
"loss": 0.0512,
|
117 |
+
"step": 90
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.63,
|
121 |
+
"learning_rate": 6.053357937665237e-05,
|
122 |
+
"loss": 0.0553,
|
123 |
+
"step": 95
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.66,
|
127 |
+
"learning_rate": 5.1205962578487155e-05,
|
128 |
+
"loss": 0.0409,
|
129 |
+
"step": 100
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.7,
|
133 |
+
"learning_rate": 4.240589251272342e-05,
|
134 |
+
"loss": 0.0592,
|
135 |
+
"step": 105
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.73,
|
139 |
+
"learning_rate": 3.422851293981676e-05,
|
140 |
+
"loss": 0.0536,
|
141 |
+
"step": 110
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.76,
|
145 |
+
"learning_rate": 2.6762235274383772e-05,
|
146 |
+
"loss": 0.0275,
|
147 |
+
"step": 115
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.79,
|
151 |
+
"learning_rate": 2.008778270707944e-05,
|
152 |
+
"loss": 0.0466,
|
153 |
+
"step": 120
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.83,
|
157 |
+
"learning_rate": 1.4277317449282834e-05,
|
158 |
+
"loss": 0.0328,
|
159 |
+
"step": 125
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.86,
|
163 |
+
"learning_rate": 9.393660536564408e-06,
|
164 |
+
"loss": 0.0299,
|
165 |
+
"step": 130
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.89,
|
169 |
+
"learning_rate": 5.489612626189245e-06,
|
170 |
+
"loss": 0.0258,
|
171 |
+
"step": 135
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.93,
|
175 |
+
"learning_rate": 2.607383131993424e-06,
|
176 |
+
"loss": 0.0374,
|
177 |
+
"step": 140
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.96,
|
181 |
+
"learning_rate": 7.781338686584927e-07,
|
182 |
+
"loss": 0.037,
|
183 |
+
"step": 145
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.99,
|
187 |
+
"learning_rate": 2.164213936770576e-08,
|
188 |
+
"loss": 0.0316,
|
189 |
+
"step": 150
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 1.0,
|
193 |
+
"step": 151,
|
194 |
+
"total_flos": 6843505735041024.0,
|
195 |
+
"train_loss": 0.1083572210361626,
|
196 |
+
"train_runtime": 702.143,
|
197 |
+
"train_samples_per_second": 3.439,
|
198 |
+
"train_steps_per_second": 0.215
|
199 |
+
}
|
200 |
+
],
|
201 |
+
"logging_steps": 5,
|
202 |
+
"max_steps": 151,
|
203 |
+
"num_input_tokens_seen": 0,
|
204 |
+
"num_train_epochs": 1,
|
205 |
+
"save_steps": 100,
|
206 |
+
"total_flos": 6843505735041024.0,
|
207 |
+
"train_batch_size": 4,
|
208 |
+
"trial_name": null,
|
209 |
+
"trial_params": null
|
210 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:958a44028e9e507765c0ff813e71751e7147b055850af6aaf4f50ff29284554d
|
3 |
+
size 4920
|