Upload folder using huggingface_hub
Browse files- README.md +60 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- all_results.json +9 -0
- checkpoint-100/README.md +202 -0
- checkpoint-100/adapter_config.json +34 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/added_tokens.json +5 -0
- checkpoint-100/merges.txt +0 -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 +20 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer_config.json +44 -0
- checkpoint-100/trainer_state.json +193 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-100/vocab.json +0 -0
- checkpoint-200/README.md +202 -0
- checkpoint-200/adapter_config.json +34 -0
- checkpoint-200/adapter_model.safetensors +3 -0
- checkpoint-200/added_tokens.json +5 -0
- checkpoint-200/merges.txt +0 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +20 -0
- checkpoint-200/tokenizer.json +0 -0
- checkpoint-200/tokenizer_config.json +44 -0
- checkpoint-200/trainer_state.json +353 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-200/vocab.json +0 -0
- merges.txt +0 -0
- running_log.txt +431 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- train_results.json +9 -0
- trainer_config.yaml +33 -0
- trainer_log.jsonl +49 -0
- trainer_state.json +427 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- llama-factory
|
6 |
+
- lora
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: Qwen/Qwen2-7B-Instruct-GPTQ-Int8
|
9 |
+
model-index:
|
10 |
+
- name: train_2024-06-06-20-45-21
|
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_2024-06-06-20-45-21
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [Qwen/Qwen2-7B-Instruct-GPTQ-Int8](https://huggingface.co/Qwen/Qwen2-7B-Instruct-GPTQ-Int8) on the train 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: 5e-05
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- gradient_accumulation_steps: 8
|
44 |
+
- total_train_batch_size: 16
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: cosine
|
47 |
+
- num_epochs: 3.0
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
|
53 |
+
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- PEFT 0.11.1
|
57 |
+
- Transformers 4.41.2
|
58 |
+
- Pytorch 2.2.1+cu121
|
59 |
+
- Datasets 2.19.2
|
60 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2-7B-Instruct-GPTQ-Int8",
|
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,
|
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 |
+
"q_proj",
|
24 |
+
"o_proj",
|
25 |
+
"k_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"down_proj",
|
28 |
+
"up_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48043b5bc91911c85972e5443a152db4f35149af33dfda32e60cb3f44980791f
|
3 |
+
size 80792096
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.4033333333333333,
|
3 |
+
"num_input_tokens_seen": 1371584,
|
4 |
+
"total_flos": 4652852538507264.0,
|
5 |
+
"train_loss": 0.040362141964849364,
|
6 |
+
"train_runtime": 4583.2214,
|
7 |
+
"train_samples_per_second": 6.284,
|
8 |
+
"train_steps_per_second": 0.393
|
9 |
+
}
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Qwen/Qwen2-7B-Instruct-GPTQ-Int8
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2-7B-Instruct-GPTQ-Int8",
|
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,
|
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 |
+
"q_proj",
|
24 |
+
"o_proj",
|
25 |
+
"k_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"down_proj",
|
28 |
+
"up_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aa41c3c376d848d3ec7f6f5942a0889043579d8d9b7e3cbdc99958e3187f30c
|
3 |
+
size 80792096
|
checkpoint-100/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-100/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b18c0080066dc37db88ab1910d6819e385367d313ac13470421cb138868d32d7
|
3 |
+
size 161810282
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
|
3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4051a10dbe4591782639bebdd97dd1262fdf358a1617c8c89f93f1b5f9d6a96
|
3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-100/tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"padding_side": "right",
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
+
"unk_token": null
|
44 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.16666666666666666,
|
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": 0.008333333333333333,
|
13 |
+
"grad_norm": 0.48900601267814636,
|
14 |
+
"learning_rate": 4.999904807660428e-05,
|
15 |
+
"loss": 0.4212,
|
16 |
+
"num_input_tokens_seen": 30064,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.016666666666666666,
|
21 |
+
"grad_norm": 0.3595407009124756,
|
22 |
+
"learning_rate": 4.9996192378909786e-05,
|
23 |
+
"loss": 0.2803,
|
24 |
+
"num_input_tokens_seen": 57376,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.025,
|
29 |
+
"grad_norm": 0.2623545527458191,
|
30 |
+
"learning_rate": 4.999143312438893e-05,
|
31 |
+
"loss": 0.1484,
|
32 |
+
"num_input_tokens_seen": 86160,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.03333333333333333,
|
37 |
+
"grad_norm": 0.2743065357208252,
|
38 |
+
"learning_rate": 4.99847706754774e-05,
|
39 |
+
"loss": 0.1151,
|
40 |
+
"num_input_tokens_seen": 110592,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.041666666666666664,
|
45 |
+
"grad_norm": 0.2651338577270508,
|
46 |
+
"learning_rate": 4.997620553954645e-05,
|
47 |
+
"loss": 0.0751,
|
48 |
+
"num_input_tokens_seen": 138880,
|
49 |
+
"step": 25
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.05,
|
53 |
+
"grad_norm": 0.10798148065805435,
|
54 |
+
"learning_rate": 4.996573836886435e-05,
|
55 |
+
"loss": 0.0471,
|
56 |
+
"num_input_tokens_seen": 169600,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.058333333333333334,
|
61 |
+
"grad_norm": 0.1552838534116745,
|
62 |
+
"learning_rate": 4.9953369960546676e-05,
|
63 |
+
"loss": 0.0368,
|
64 |
+
"num_input_tokens_seen": 201664,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.06666666666666667,
|
69 |
+
"grad_norm": 0.11832074075937271,
|
70 |
+
"learning_rate": 4.993910125649561e-05,
|
71 |
+
"loss": 0.0311,
|
72 |
+
"num_input_tokens_seen": 229936,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.075,
|
77 |
+
"grad_norm": 0.10593917220830917,
|
78 |
+
"learning_rate": 4.99229333433282e-05,
|
79 |
+
"loss": 0.0262,
|
80 |
+
"num_input_tokens_seen": 259088,
|
81 |
+
"step": 45
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.08333333333333333,
|
85 |
+
"grad_norm": 0.09650842100381851,
|
86 |
+
"learning_rate": 4.990486745229364e-05,
|
87 |
+
"loss": 0.0244,
|
88 |
+
"num_input_tokens_seen": 289824,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.09166666666666666,
|
93 |
+
"grad_norm": 0.14155137538909912,
|
94 |
+
"learning_rate": 4.988490495917947e-05,
|
95 |
+
"loss": 0.0266,
|
96 |
+
"num_input_tokens_seen": 317760,
|
97 |
+
"step": 55
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.1,
|
101 |
+
"grad_norm": 0.1490347981452942,
|
102 |
+
"learning_rate": 4.9867570427929354e-05,
|
103 |
+
"loss": 0.0283,
|
104 |
+
"num_input_tokens_seen": 343120,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.10833333333333334,
|
109 |
+
"grad_norm": 0.17539122700691223,
|
110 |
+
"learning_rate": 4.984419797901491e-05,
|
111 |
+
"loss": 0.0265,
|
112 |
+
"num_input_tokens_seen": 371600,
|
113 |
+
"step": 65
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.11666666666666667,
|
117 |
+
"grad_norm": 0.1336919367313385,
|
118 |
+
"learning_rate": 4.981893354823614e-05,
|
119 |
+
"loss": 0.0235,
|
120 |
+
"num_input_tokens_seen": 398720,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.125,
|
125 |
+
"grad_norm": 0.12203177809715271,
|
126 |
+
"learning_rate": 4.979177905957726e-05,
|
127 |
+
"loss": 0.0229,
|
128 |
+
"num_input_tokens_seen": 426416,
|
129 |
+
"step": 75
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.13333333333333333,
|
133 |
+
"grad_norm": 0.2557654082775116,
|
134 |
+
"learning_rate": 4.976273658095772e-05,
|
135 |
+
"loss": 0.0238,
|
136 |
+
"num_input_tokens_seen": 452944,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.14166666666666666,
|
141 |
+
"grad_norm": 0.13327105343341827,
|
142 |
+
"learning_rate": 4.9731808324074717e-05,
|
143 |
+
"loss": 0.0208,
|
144 |
+
"num_input_tokens_seen": 480896,
|
145 |
+
"step": 85
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.15,
|
149 |
+
"grad_norm": 0.1262751668691635,
|
150 |
+
"learning_rate": 4.969899664423473e-05,
|
151 |
+
"loss": 0.0191,
|
152 |
+
"num_input_tokens_seen": 510096,
|
153 |
+
"step": 90
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.15833333333333333,
|
157 |
+
"grad_norm": 0.16084067523479462,
|
158 |
+
"learning_rate": 4.966430404017424e-05,
|
159 |
+
"loss": 0.0205,
|
160 |
+
"num_input_tokens_seen": 536672,
|
161 |
+
"step": 95
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.16666666666666666,
|
165 |
+
"grad_norm": 0.15870437026023865,
|
166 |
+
"learning_rate": 4.962773315386935e-05,
|
167 |
+
"loss": 0.0193,
|
168 |
+
"num_input_tokens_seen": 566528,
|
169 |
+
"step": 100
|
170 |
+
}
|
171 |
+
],
|
172 |
+
"logging_steps": 5,
|
173 |
+
"max_steps": 1800,
|
174 |
+
"num_input_tokens_seen": 566528,
|
175 |
+
"num_train_epochs": 3,
|
176 |
+
"save_steps": 100,
|
177 |
+
"stateful_callbacks": {
|
178 |
+
"TrainerControl": {
|
179 |
+
"args": {
|
180 |
+
"should_epoch_stop": false,
|
181 |
+
"should_evaluate": false,
|
182 |
+
"should_log": false,
|
183 |
+
"should_save": true,
|
184 |
+
"should_training_stop": false
|
185 |
+
},
|
186 |
+
"attributes": {}
|
187 |
+
}
|
188 |
+
},
|
189 |
+
"total_flos": 1921844563148800.0,
|
190 |
+
"train_batch_size": 2,
|
191 |
+
"trial_name": null,
|
192 |
+
"trial_params": null
|
193 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e38936a74c731e02f619889aeaa58a6ba812a6fabdbd18f67b624b496070c73c
|
3 |
+
size 5304
|
checkpoint-100/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Qwen/Qwen2-7B-Instruct-GPTQ-Int8
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2-7B-Instruct-GPTQ-Int8",
|
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,
|
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 |
+
"q_proj",
|
24 |
+
"o_proj",
|
25 |
+
"k_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"down_proj",
|
28 |
+
"up_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-200/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a8e39f94ccd45abcb35fbe6819e17966752fbc56ed8611b2f52f0223a375fce
|
3 |
+
size 80792096
|
checkpoint-200/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-200/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d90e504f03babc630dad632743174fddb6b74a308e728929f72a3919541acba5
|
3 |
+
size 161810282
|
checkpoint-200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
|
3 |
+
size 14244
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72b988391a95053a053fa51ffca08c28862e9f89c4be3fa722e090ac1914d17c
|
3 |
+
size 1064
|
checkpoint-200/special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
checkpoint-200/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-200/tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"padding_side": "right",
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
+
"unk_token": null
|
44 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,353 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3333333333333333,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.008333333333333333,
|
13 |
+
"grad_norm": 0.48900601267814636,
|
14 |
+
"learning_rate": 4.999904807660428e-05,
|
15 |
+
"loss": 0.4212,
|
16 |
+
"num_input_tokens_seen": 30064,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.016666666666666666,
|
21 |
+
"grad_norm": 0.3595407009124756,
|
22 |
+
"learning_rate": 4.9996192378909786e-05,
|
23 |
+
"loss": 0.2803,
|
24 |
+
"num_input_tokens_seen": 57376,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.025,
|
29 |
+
"grad_norm": 0.2623545527458191,
|
30 |
+
"learning_rate": 4.999143312438893e-05,
|
31 |
+
"loss": 0.1484,
|
32 |
+
"num_input_tokens_seen": 86160,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.03333333333333333,
|
37 |
+
"grad_norm": 0.2743065357208252,
|
38 |
+
"learning_rate": 4.99847706754774e-05,
|
39 |
+
"loss": 0.1151,
|
40 |
+
"num_input_tokens_seen": 110592,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.041666666666666664,
|
45 |
+
"grad_norm": 0.2651338577270508,
|
46 |
+
"learning_rate": 4.997620553954645e-05,
|
47 |
+
"loss": 0.0751,
|
48 |
+
"num_input_tokens_seen": 138880,
|
49 |
+
"step": 25
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.05,
|
53 |
+
"grad_norm": 0.10798148065805435,
|
54 |
+
"learning_rate": 4.996573836886435e-05,
|
55 |
+
"loss": 0.0471,
|
56 |
+
"num_input_tokens_seen": 169600,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.058333333333333334,
|
61 |
+
"grad_norm": 0.1552838534116745,
|
62 |
+
"learning_rate": 4.9953369960546676e-05,
|
63 |
+
"loss": 0.0368,
|
64 |
+
"num_input_tokens_seen": 201664,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.06666666666666667,
|
69 |
+
"grad_norm": 0.11832074075937271,
|
70 |
+
"learning_rate": 4.993910125649561e-05,
|
71 |
+
"loss": 0.0311,
|
72 |
+
"num_input_tokens_seen": 229936,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.075,
|
77 |
+
"grad_norm": 0.10593917220830917,
|
78 |
+
"learning_rate": 4.99229333433282e-05,
|
79 |
+
"loss": 0.0262,
|
80 |
+
"num_input_tokens_seen": 259088,
|
81 |
+
"step": 45
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.08333333333333333,
|
85 |
+
"grad_norm": 0.09650842100381851,
|
86 |
+
"learning_rate": 4.990486745229364e-05,
|
87 |
+
"loss": 0.0244,
|
88 |
+
"num_input_tokens_seen": 289824,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.09166666666666666,
|
93 |
+
"grad_norm": 0.14155137538909912,
|
94 |
+
"learning_rate": 4.988490495917947e-05,
|
95 |
+
"loss": 0.0266,
|
96 |
+
"num_input_tokens_seen": 317760,
|
97 |
+
"step": 55
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.1,
|
101 |
+
"grad_norm": 0.1490347981452942,
|
102 |
+
"learning_rate": 4.9867570427929354e-05,
|
103 |
+
"loss": 0.0283,
|
104 |
+
"num_input_tokens_seen": 343120,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.10833333333333334,
|
109 |
+
"grad_norm": 0.17539122700691223,
|
110 |
+
"learning_rate": 4.984419797901491e-05,
|
111 |
+
"loss": 0.0265,
|
112 |
+
"num_input_tokens_seen": 371600,
|
113 |
+
"step": 65
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.11666666666666667,
|
117 |
+
"grad_norm": 0.1336919367313385,
|
118 |
+
"learning_rate": 4.981893354823614e-05,
|
119 |
+
"loss": 0.0235,
|
120 |
+
"num_input_tokens_seen": 398720,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.125,
|
125 |
+
"grad_norm": 0.12203177809715271,
|
126 |
+
"learning_rate": 4.979177905957726e-05,
|
127 |
+
"loss": 0.0229,
|
128 |
+
"num_input_tokens_seen": 426416,
|
129 |
+
"step": 75
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.13333333333333333,
|
133 |
+
"grad_norm": 0.2557654082775116,
|
134 |
+
"learning_rate": 4.976273658095772e-05,
|
135 |
+
"loss": 0.0238,
|
136 |
+
"num_input_tokens_seen": 452944,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.14166666666666666,
|
141 |
+
"grad_norm": 0.13327105343341827,
|
142 |
+
"learning_rate": 4.9731808324074717e-05,
|
143 |
+
"loss": 0.0208,
|
144 |
+
"num_input_tokens_seen": 480896,
|
145 |
+
"step": 85
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.15,
|
149 |
+
"grad_norm": 0.1262751668691635,
|
150 |
+
"learning_rate": 4.969899664423473e-05,
|
151 |
+
"loss": 0.0191,
|
152 |
+
"num_input_tokens_seen": 510096,
|
153 |
+
"step": 90
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.15833333333333333,
|
157 |
+
"grad_norm": 0.16084067523479462,
|
158 |
+
"learning_rate": 4.966430404017424e-05,
|
159 |
+
"loss": 0.0205,
|
160 |
+
"num_input_tokens_seen": 536672,
|
161 |
+
"step": 95
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.16666666666666666,
|
165 |
+
"grad_norm": 0.15870437026023865,
|
166 |
+
"learning_rate": 4.962773315386935e-05,
|
167 |
+
"loss": 0.0193,
|
168 |
+
"num_input_tokens_seen": 566528,
|
169 |
+
"step": 100
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.175,
|
173 |
+
"grad_norm": 0.07833187282085419,
|
174 |
+
"learning_rate": 4.9589286770334654e-05,
|
175 |
+
"loss": 0.024,
|
176 |
+
"num_input_tokens_seen": 593584,
|
177 |
+
"step": 105
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.18333333333333332,
|
181 |
+
"grad_norm": 0.09176061302423477,
|
182 |
+
"learning_rate": 4.954896781741109e-05,
|
183 |
+
"loss": 0.0206,
|
184 |
+
"num_input_tokens_seen": 620992,
|
185 |
+
"step": 110
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.19166666666666668,
|
189 |
+
"grad_norm": 0.08285439014434814,
|
190 |
+
"learning_rate": 4.9506779365543046e-05,
|
191 |
+
"loss": 0.0188,
|
192 |
+
"num_input_tokens_seen": 647504,
|
193 |
+
"step": 115
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.2,
|
197 |
+
"grad_norm": 0.13359522819519043,
|
198 |
+
"learning_rate": 4.9462724627544466e-05,
|
199 |
+
"loss": 0.0183,
|
200 |
+
"num_input_tokens_seen": 676336,
|
201 |
+
"step": 120
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.20833333333333334,
|
205 |
+
"grad_norm": 0.07570718228816986,
|
206 |
+
"learning_rate": 4.94168069583542e-05,
|
207 |
+
"loss": 0.0189,
|
208 |
+
"num_input_tokens_seen": 701488,
|
209 |
+
"step": 125
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.21666666666666667,
|
213 |
+
"grad_norm": 0.11286037415266037,
|
214 |
+
"learning_rate": 4.936902985478055e-05,
|
215 |
+
"loss": 0.0213,
|
216 |
+
"num_input_tokens_seen": 731152,
|
217 |
+
"step": 130
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.225,
|
221 |
+
"grad_norm": 0.17183929681777954,
|
222 |
+
"learning_rate": 4.931939695523492e-05,
|
223 |
+
"loss": 0.0214,
|
224 |
+
"num_input_tokens_seen": 757792,
|
225 |
+
"step": 135
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.23333333333333334,
|
229 |
+
"grad_norm": 0.11746834218502045,
|
230 |
+
"learning_rate": 4.926791203945477e-05,
|
231 |
+
"loss": 0.0214,
|
232 |
+
"num_input_tokens_seen": 786064,
|
233 |
+
"step": 140
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.24166666666666667,
|
237 |
+
"grad_norm": 0.09453292936086655,
|
238 |
+
"learning_rate": 4.9214579028215776e-05,
|
239 |
+
"loss": 0.0203,
|
240 |
+
"num_input_tokens_seen": 814640,
|
241 |
+
"step": 145
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.25,
|
245 |
+
"grad_norm": 0.2074723094701767,
|
246 |
+
"learning_rate": 4.915940198303324e-05,
|
247 |
+
"loss": 0.0194,
|
248 |
+
"num_input_tokens_seen": 842656,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.25833333333333336,
|
253 |
+
"grad_norm": 0.15371476113796234,
|
254 |
+
"learning_rate": 4.910238510585276e-05,
|
255 |
+
"loss": 0.0158,
|
256 |
+
"num_input_tokens_seen": 868512,
|
257 |
+
"step": 155
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.26666666666666666,
|
261 |
+
"grad_norm": 0.07177837193012238,
|
262 |
+
"learning_rate": 4.9043532738730284e-05,
|
263 |
+
"loss": 0.0172,
|
264 |
+
"num_input_tokens_seen": 896416,
|
265 |
+
"step": 160
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.275,
|
269 |
+
"grad_norm": 0.07891824096441269,
|
270 |
+
"learning_rate": 4.898284936350144e-05,
|
271 |
+
"loss": 0.0193,
|
272 |
+
"num_input_tokens_seen": 924720,
|
273 |
+
"step": 165
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.2833333333333333,
|
277 |
+
"grad_norm": 0.08302944153547287,
|
278 |
+
"learning_rate": 4.892033960144019e-05,
|
279 |
+
"loss": 0.0189,
|
280 |
+
"num_input_tokens_seen": 955584,
|
281 |
+
"step": 170
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.2916666666666667,
|
285 |
+
"grad_norm": 0.25554358959198,
|
286 |
+
"learning_rate": 4.8856008212906925e-05,
|
287 |
+
"loss": 0.019,
|
288 |
+
"num_input_tokens_seen": 985072,
|
289 |
+
"step": 175
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.3,
|
293 |
+
"grad_norm": 0.1445908546447754,
|
294 |
+
"learning_rate": 4.878986009698596e-05,
|
295 |
+
"loss": 0.0168,
|
296 |
+
"num_input_tokens_seen": 1013296,
|
297 |
+
"step": 180
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.30833333333333335,
|
301 |
+
"grad_norm": 0.21417762339115143,
|
302 |
+
"learning_rate": 4.8721900291112415e-05,
|
303 |
+
"loss": 0.0194,
|
304 |
+
"num_input_tokens_seen": 1043664,
|
305 |
+
"step": 185
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.31666666666666665,
|
309 |
+
"grad_norm": 0.1550753116607666,
|
310 |
+
"learning_rate": 4.8652133970688636e-05,
|
311 |
+
"loss": 0.0155,
|
312 |
+
"num_input_tokens_seen": 1070912,
|
313 |
+
"step": 190
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.325,
|
317 |
+
"grad_norm": 0.132898211479187,
|
318 |
+
"learning_rate": 4.858056644869002e-05,
|
319 |
+
"loss": 0.0193,
|
320 |
+
"num_input_tokens_seen": 1097856,
|
321 |
+
"step": 195
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.3333333333333333,
|
325 |
+
"grad_norm": 0.09164389222860336,
|
326 |
+
"learning_rate": 4.850720317526047e-05,
|
327 |
+
"loss": 0.0164,
|
328 |
+
"num_input_tokens_seen": 1126128,
|
329 |
+
"step": 200
|
330 |
+
}
|
331 |
+
],
|
332 |
+
"logging_steps": 5,
|
333 |
+
"max_steps": 1800,
|
334 |
+
"num_input_tokens_seen": 1126128,
|
335 |
+
"num_train_epochs": 3,
|
336 |
+
"save_steps": 100,
|
337 |
+
"stateful_callbacks": {
|
338 |
+
"TrainerControl": {
|
339 |
+
"args": {
|
340 |
+
"should_epoch_stop": false,
|
341 |
+
"should_evaluate": false,
|
342 |
+
"should_log": false,
|
343 |
+
"should_save": true,
|
344 |
+
"should_training_stop": false
|
345 |
+
},
|
346 |
+
"attributes": {}
|
347 |
+
}
|
348 |
+
},
|
349 |
+
"total_flos": 3820187115585536.0,
|
350 |
+
"train_batch_size": 2,
|
351 |
+
"trial_name": null,
|
352 |
+
"trial_params": null
|
353 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e38936a74c731e02f619889aeaa58a6ba812a6fabdbd18f67b624b496070c73c
|
3 |
+
size 5304
|
checkpoint-200/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
running_log.txt
ADDED
@@ -0,0 +1,431 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file vocab.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/vocab.json
|
2 |
+
|
3 |
+
06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file merges.txt from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/merges.txt
|
4 |
+
|
5 |
+
06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/tokenizer.json
|
6 |
+
|
7 |
+
06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json from cache at None
|
8 |
+
|
9 |
+
06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json from cache at None
|
10 |
+
|
11 |
+
06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/tokenizer_config.json
|
12 |
+
|
13 |
+
06/06/2024 20:45:49 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
14 |
+
|
15 |
+
06/06/2024 20:45:49 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
|
16 |
+
|
17 |
+
06/06/2024 20:45:49 - INFO - llamafactory.data.loader - Loading dataset train.json...
|
18 |
+
|
19 |
+
06/06/2024 20:45:49 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/config.json
|
20 |
+
|
21 |
+
06/06/2024 20:45:49 - INFO - transformers.configuration_utils - Model config Qwen2Config {
|
22 |
+
"_name_or_path": "Qwen/Qwen2-7B-Instruct-GPTQ-Int8",
|
23 |
+
"architectures": [
|
24 |
+
"Qwen2ForCausalLM"
|
25 |
+
],
|
26 |
+
"attention_dropout": 0.0,
|
27 |
+
"bos_token_id": 151643,
|
28 |
+
"eos_token_id": 151645,
|
29 |
+
"hidden_act": "silu",
|
30 |
+
"hidden_size": 3584,
|
31 |
+
"initializer_range": 0.02,
|
32 |
+
"intermediate_size": 18944,
|
33 |
+
"max_position_embeddings": 32768,
|
34 |
+
"max_window_layers": 28,
|
35 |
+
"model_type": "qwen2",
|
36 |
+
"num_attention_heads": 28,
|
37 |
+
"num_hidden_layers": 28,
|
38 |
+
"num_key_value_heads": 4,
|
39 |
+
"quantization_config": {
|
40 |
+
"batch_size": 1,
|
41 |
+
"bits": 8,
|
42 |
+
"block_name_to_quantize": null,
|
43 |
+
"cache_block_outputs": true,
|
44 |
+
"damp_percent": 0.1,
|
45 |
+
"dataset": null,
|
46 |
+
"desc_act": false,
|
47 |
+
"exllama_config": {
|
48 |
+
"version": 1
|
49 |
+
},
|
50 |
+
"group_size": 128,
|
51 |
+
"max_input_length": null,
|
52 |
+
"model_seqlen": null,
|
53 |
+
"module_name_preceding_first_block": null,
|
54 |
+
"modules_in_block_to_quantize": null,
|
55 |
+
"pad_token_id": null,
|
56 |
+
"quant_method": "gptq",
|
57 |
+
"sym": true,
|
58 |
+
"tokenizer": null,
|
59 |
+
"true_sequential": true,
|
60 |
+
"use_cuda_fp16": false,
|
61 |
+
"use_exllama": true
|
62 |
+
},
|
63 |
+
"rms_norm_eps": 1e-06,
|
64 |
+
"rope_theta": 1000000.0,
|
65 |
+
"sliding_window": 131072,
|
66 |
+
"tie_word_embeddings": false,
|
67 |
+
"torch_dtype": "float16",
|
68 |
+
"transformers_version": "4.41.2",
|
69 |
+
"use_cache": true,
|
70 |
+
"use_sliding_window": false,
|
71 |
+
"vocab_size": 152064
|
72 |
+
}
|
73 |
+
|
74 |
+
|
75 |
+
06/06/2024 20:45:49 - WARNING - llamafactory.model.model_utils.attention - FlashAttention-2 is not installed.
|
76 |
+
|
77 |
+
06/06/2024 20:45:49 - INFO - llamafactory.model.model_utils.quantization - Loading 8-bit GPTQ-quantized model.
|
78 |
+
|
79 |
+
06/06/2024 20:45:49 - INFO - transformers.modeling_utils - loading weights file model.safetensors from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/model.safetensors.index.json
|
80 |
+
|
81 |
+
06/06/2024 20:46:15 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.float16.
|
82 |
+
|
83 |
+
06/06/2024 20:46:15 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
|
84 |
+
"bos_token_id": 151643,
|
85 |
+
"eos_token_id": 151645,
|
86 |
+
"use_cache": false
|
87 |
+
}
|
88 |
+
|
89 |
+
|
90 |
+
06/06/2024 20:46:41 - WARNING - transformers.modeling_utils - Some weights of the model checkpoint at Qwen/Qwen2-7B-Instruct-GPTQ-Int8 were not used when initializing Qwen2ForCausalLM: ['model.layers.0.mlp.down_proj.bias', 'model.layers.0.mlp.gate_proj.bias', 'model.layers.0.mlp.up_proj.bias', 'model.layers.0.self_attn.o_proj.bias', 'model.layers.1.mlp.down_proj.bias', 'model.layers.1.mlp.gate_proj.bias', 'model.layers.1.mlp.up_proj.bias', 'model.layers.1.self_attn.o_proj.bias', 'model.layers.10.mlp.down_proj.bias', 'model.layers.10.mlp.gate_proj.bias', 'model.layers.10.mlp.up_proj.bias', 'model.layers.10.self_attn.o_proj.bias', 'model.layers.11.mlp.down_proj.bias', 'model.layers.11.mlp.gate_proj.bias', 'model.layers.11.mlp.up_proj.bias', 'model.layers.11.self_attn.o_proj.bias', 'model.layers.12.mlp.down_proj.bias', 'model.layers.12.mlp.gate_proj.bias', 'model.layers.12.mlp.up_proj.bias', 'model.layers.12.self_attn.o_proj.bias', 'model.layers.13.mlp.down_proj.bias', 'model.layers.13.mlp.gate_proj.bias', 'model.layers.13.mlp.up_proj.bias', 'model.layers.13.self_attn.o_proj.bias', 'model.layers.14.mlp.down_proj.bias', 'model.layers.14.mlp.gate_proj.bias', 'model.layers.14.mlp.up_proj.bias', 'model.layers.14.self_attn.o_proj.bias', 'model.layers.15.mlp.down_proj.bias', 'model.layers.15.mlp.gate_proj.bias', 'model.layers.15.mlp.up_proj.bias', 'model.layers.15.self_attn.o_proj.bias', 'model.layers.16.mlp.down_proj.bias', 'model.layers.16.mlp.gate_proj.bias', 'model.layers.16.mlp.up_proj.bias', 'model.layers.16.self_attn.o_proj.bias', 'model.layers.17.mlp.down_proj.bias', 'model.layers.17.mlp.gate_proj.bias', 'model.layers.17.mlp.up_proj.bias', 'model.layers.17.self_attn.o_proj.bias', 'model.layers.18.mlp.down_proj.bias', 'model.layers.18.mlp.gate_proj.bias', 'model.layers.18.mlp.up_proj.bias', 'model.layers.18.self_attn.o_proj.bias', 'model.layers.19.mlp.down_proj.bias', 'model.layers.19.mlp.gate_proj.bias', 'model.layers.19.mlp.up_proj.bias', 'model.layers.19.self_attn.o_proj.bias', 'model.layers.2.mlp.down_proj.bias', 'model.layers.2.mlp.gate_proj.bias', 'model.layers.2.mlp.up_proj.bias', 'model.layers.2.self_attn.o_proj.bias', 'model.layers.20.mlp.down_proj.bias', 'model.layers.20.mlp.gate_proj.bias', 'model.layers.20.mlp.up_proj.bias', 'model.layers.20.self_attn.o_proj.bias', 'model.layers.21.mlp.down_proj.bias', 'model.layers.21.mlp.gate_proj.bias', 'model.layers.21.mlp.up_proj.bias', 'model.layers.21.self_attn.o_proj.bias', 'model.layers.22.mlp.down_proj.bias', 'model.layers.22.mlp.gate_proj.bias', 'model.layers.22.mlp.up_proj.bias', 'model.layers.22.self_attn.o_proj.bias', 'model.layers.23.mlp.down_proj.bias', 'model.layers.23.mlp.gate_proj.bias', 'model.layers.23.mlp.up_proj.bias', 'model.layers.23.self_attn.o_proj.bias', 'model.layers.24.mlp.down_proj.bias', 'model.layers.24.mlp.gate_proj.bias', 'model.layers.24.mlp.up_proj.bias', 'model.layers.24.self_attn.o_proj.bias', 'model.layers.25.mlp.down_proj.bias', 'model.layers.25.mlp.gate_proj.bias', 'model.layers.25.mlp.up_proj.bias', 'model.layers.25.self_attn.o_proj.bias', 'model.layers.26.mlp.down_proj.bias', 'model.layers.26.mlp.gate_proj.bias', 'model.layers.26.mlp.up_proj.bias', 'model.layers.26.self_attn.o_proj.bias', 'model.layers.27.mlp.down_proj.bias', 'model.layers.27.mlp.gate_proj.bias', 'model.layers.27.mlp.up_proj.bias', 'model.layers.27.self_attn.o_proj.bias', 'model.layers.3.mlp.down_proj.bias', 'model.layers.3.mlp.gate_proj.bias', 'model.layers.3.mlp.up_proj.bias', 'model.layers.3.self_attn.o_proj.bias', 'model.layers.4.mlp.down_proj.bias', 'model.layers.4.mlp.gate_proj.bias', 'model.layers.4.mlp.up_proj.bias', 'model.layers.4.self_attn.o_proj.bias', 'model.layers.5.mlp.down_proj.bias', 'model.layers.5.mlp.gate_proj.bias', 'model.layers.5.mlp.up_proj.bias', 'model.layers.5.self_attn.o_proj.bias', 'model.layers.6.mlp.down_proj.bias', 'model.layers.6.mlp.gate_proj.bias', 'model.layers.6.mlp.up_proj.bias', 'model.layers.6.self_attn.o_proj.bias', 'model.layers.7.mlp.down_proj.bias', 'model.layers.7.mlp.gate_proj.bias', 'model.layers.7.mlp.up_proj.bias', 'model.layers.7.self_attn.o_proj.bias', 'model.layers.8.mlp.down_proj.bias', 'model.layers.8.mlp.gate_proj.bias', 'model.layers.8.mlp.up_proj.bias', 'model.layers.8.self_attn.o_proj.bias', 'model.layers.9.mlp.down_proj.bias', 'model.layers.9.mlp.gate_proj.bias', 'model.layers.9.mlp.up_proj.bias', 'model.layers.9.self_attn.o_proj.bias']
|
91 |
+
- This IS expected if you are initializing Qwen2ForCausalLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
|
92 |
+
- This IS NOT expected if you are initializing Qwen2ForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
|
93 |
+
|
94 |
+
06/06/2024 20:46:41 - INFO - transformers.modeling_utils - All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-7B-Instruct-GPTQ-Int8.
|
95 |
+
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
|
96 |
+
|
97 |
+
06/06/2024 20:46:41 - INFO - transformers.generation.configuration_utils - loading configuration file generation_config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/generation_config.json
|
98 |
+
|
99 |
+
06/06/2024 20:46:41 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
|
100 |
+
"bos_token_id": 151643,
|
101 |
+
"do_sample": true,
|
102 |
+
"eos_token_id": [
|
103 |
+
151645,
|
104 |
+
151643
|
105 |
+
],
|
106 |
+
"pad_token_id": 151643,
|
107 |
+
"repetition_penalty": 1.05,
|
108 |
+
"top_p": 0.8
|
109 |
+
}
|
110 |
+
|
111 |
+
|
112 |
+
06/06/2024 20:46:41 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
113 |
+
|
114 |
+
06/06/2024 20:46:41 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
115 |
+
|
116 |
+
06/06/2024 20:46:41 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
117 |
+
|
118 |
+
06/06/2024 20:46:41 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
|
119 |
+
|
120 |
+
06/06/2024 20:46:41 - INFO - llamafactory.model.model_utils.misc - Found linear modules: q_proj,o_proj,k_proj,gate_proj,down_proj,up_proj,v_proj
|
121 |
+
|
122 |
+
06/06/2024 20:46:42 - INFO - llamafactory.model.loader - trainable params: 20185088 || all params: 1110384128 || trainable%: 1.8178
|
123 |
+
|
124 |
+
06/06/2024 20:46:42 - INFO - transformers.trainer - Using auto half precision backend
|
125 |
+
|
126 |
+
06/06/2024 20:46:42 - INFO - transformers.trainer - ***** Running training *****
|
127 |
+
|
128 |
+
06/06/2024 20:46:42 - INFO - transformers.trainer - Num examples = 9,600
|
129 |
+
|
130 |
+
06/06/2024 20:46:42 - INFO - transformers.trainer - Num Epochs = 3
|
131 |
+
|
132 |
+
06/06/2024 20:46:42 - INFO - transformers.trainer - Instantaneous batch size per device = 2
|
133 |
+
|
134 |
+
06/06/2024 20:46:42 - INFO - transformers.trainer - Total train batch size (w. parallel, distributed & accumulation) = 16
|
135 |
+
|
136 |
+
06/06/2024 20:46:42 - INFO - transformers.trainer - Gradient Accumulation steps = 8
|
137 |
+
|
138 |
+
06/06/2024 20:46:42 - INFO - transformers.trainer - Total optimization steps = 1,800
|
139 |
+
|
140 |
+
06/06/2024 20:46:42 - INFO - transformers.trainer - Number of trainable parameters = 20,185,088
|
141 |
+
|
142 |
+
06/06/2024 20:48:17 - INFO - llamafactory.extras.callbacks - {'loss': 0.4212, 'learning_rate': 4.9999e-05, 'epoch': 0.01, 'throughput': 317.96}
|
143 |
+
|
144 |
+
06/06/2024 20:49:49 - INFO - llamafactory.extras.callbacks - {'loss': 0.2803, 'learning_rate': 4.9996e-05, 'epoch': 0.02, 'throughput': 307.70}
|
145 |
+
|
146 |
+
06/06/2024 20:51:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.1484, 'learning_rate': 4.9991e-05, 'epoch': 0.03, 'throughput': 305.82}
|
147 |
+
|
148 |
+
06/06/2024 20:52:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.1151, 'learning_rate': 4.9985e-05, 'epoch': 0.03, 'throughput': 297.64}
|
149 |
+
|
150 |
+
06/06/2024 20:54:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.0751, 'learning_rate': 4.9976e-05, 'epoch': 0.04, 'throughput': 297.62}
|
151 |
+
|
152 |
+
06/06/2024 20:56:07 - INFO - llamafactory.extras.callbacks - {'loss': 0.0471, 'learning_rate': 4.9966e-05, 'epoch': 0.05, 'throughput': 300.36}
|
153 |
+
|
154 |
+
06/06/2024 20:57:47 - INFO - llamafactory.extras.callbacks - {'loss': 0.0368, 'learning_rate': 4.9953e-05, 'epoch': 0.06, 'throughput': 303.39}
|
155 |
+
|
156 |
+
06/06/2024 20:59:22 - INFO - llamafactory.extras.callbacks - {'loss': 0.0311, 'learning_rate': 4.9939e-05, 'epoch': 0.07, 'throughput': 302.60}
|
157 |
+
|
158 |
+
06/06/2024 21:00:58 - INFO - llamafactory.extras.callbacks - {'loss': 0.0262, 'learning_rate': 4.9923e-05, 'epoch': 0.07, 'throughput': 302.73}
|
159 |
+
|
160 |
+
06/06/2024 21:02:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.0244, 'learning_rate': 4.9905e-05, 'epoch': 0.08, 'throughput': 303.83}
|
161 |
+
|
162 |
+
06/06/2024 21:04:11 - INFO - llamafactory.extras.callbacks - {'loss': 0.0266, 'learning_rate': 4.9885e-05, 'epoch': 0.09, 'throughput': 303.09}
|
163 |
+
|
164 |
+
06/06/2024 21:05:46 - INFO - llamafactory.extras.callbacks - {'loss': 0.0283, 'learning_rate': 4.9868e-05, 'epoch': 0.10, 'throughput': 300.01}
|
165 |
+
|
166 |
+
06/06/2024 21:07:21 - INFO - llamafactory.extras.callbacks - {'loss': 0.0265, 'learning_rate': 4.9844e-05, 'epoch': 0.11, 'throughput': 299.96}
|
167 |
+
|
168 |
+
06/06/2024 21:08:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.0235, 'learning_rate': 4.9819e-05, 'epoch': 0.12, 'throughput': 299.39}
|
169 |
+
|
170 |
+
06/06/2024 21:10:28 - INFO - llamafactory.extras.callbacks - {'loss': 0.0229, 'learning_rate': 4.9792e-05, 'epoch': 0.12, 'throughput': 299.15}
|
171 |
+
|
172 |
+
06/06/2024 21:12:01 - INFO - llamafactory.extras.callbacks - {'loss': 0.0238, 'learning_rate': 4.9763e-05, 'epoch': 0.13, 'throughput': 298.31}
|
173 |
+
|
174 |
+
06/06/2024 21:13:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0208, 'learning_rate': 4.9732e-05, 'epoch': 0.14, 'throughput': 298.24}
|
175 |
+
|
176 |
+
06/06/2024 21:15:11 - INFO - llamafactory.extras.callbacks - {'loss': 0.0191, 'learning_rate': 4.9699e-05, 'epoch': 0.15, 'throughput': 298.57}
|
177 |
+
|
178 |
+
06/06/2024 21:16:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.0205, 'learning_rate': 4.9664e-05, 'epoch': 0.16, 'throughput': 298.01}
|
179 |
+
|
180 |
+
06/06/2024 21:18:20 - INFO - llamafactory.extras.callbacks - {'loss': 0.0193, 'learning_rate': 4.9628e-05, 'epoch': 0.17, 'throughput': 298.56}
|
181 |
+
|
182 |
+
06/06/2024 21:18:20 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-100
|
183 |
+
|
184 |
+
06/06/2024 21:18:20 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/config.json
|
185 |
+
|
186 |
+
06/06/2024 21:18:20 - INFO - transformers.configuration_utils - Model config Qwen2Config {
|
187 |
+
"architectures": [
|
188 |
+
"Qwen2ForCausalLM"
|
189 |
+
],
|
190 |
+
"attention_dropout": 0.0,
|
191 |
+
"bos_token_id": 151643,
|
192 |
+
"eos_token_id": 151645,
|
193 |
+
"hidden_act": "silu",
|
194 |
+
"hidden_size": 3584,
|
195 |
+
"initializer_range": 0.02,
|
196 |
+
"intermediate_size": 18944,
|
197 |
+
"max_position_embeddings": 32768,
|
198 |
+
"max_window_layers": 28,
|
199 |
+
"model_type": "qwen2",
|
200 |
+
"num_attention_heads": 28,
|
201 |
+
"num_hidden_layers": 28,
|
202 |
+
"num_key_value_heads": 4,
|
203 |
+
"quantization_config": {
|
204 |
+
"batch_size": 1,
|
205 |
+
"bits": 8,
|
206 |
+
"block_name_to_quantize": null,
|
207 |
+
"cache_block_outputs": true,
|
208 |
+
"damp_percent": 0.1,
|
209 |
+
"dataset": null,
|
210 |
+
"desc_act": false,
|
211 |
+
"exllama_config": {
|
212 |
+
"version": 1
|
213 |
+
},
|
214 |
+
"group_size": 128,
|
215 |
+
"max_input_length": null,
|
216 |
+
"model_seqlen": null,
|
217 |
+
"module_name_preceding_first_block": null,
|
218 |
+
"modules_in_block_to_quantize": null,
|
219 |
+
"pad_token_id": null,
|
220 |
+
"quant_method": "gptq",
|
221 |
+
"sym": true,
|
222 |
+
"tokenizer": null,
|
223 |
+
"true_sequential": true,
|
224 |
+
"use_cuda_fp16": false,
|
225 |
+
"use_exllama": true
|
226 |
+
},
|
227 |
+
"rms_norm_eps": 1e-06,
|
228 |
+
"rope_theta": 1000000.0,
|
229 |
+
"sliding_window": 131072,
|
230 |
+
"tie_word_embeddings": false,
|
231 |
+
"torch_dtype": "float16",
|
232 |
+
"transformers_version": "4.41.2",
|
233 |
+
"use_cache": true,
|
234 |
+
"use_sliding_window": false,
|
235 |
+
"vocab_size": 152064
|
236 |
+
}
|
237 |
+
|
238 |
+
|
239 |
+
06/06/2024 21:18:20 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-100/tokenizer_config.json
|
240 |
+
|
241 |
+
06/06/2024 21:18:20 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-100/special_tokens_map.json
|
242 |
+
|
243 |
+
06/06/2024 21:19:53 - INFO - llamafactory.extras.callbacks - {'loss': 0.0240, 'learning_rate': 4.9589e-05, 'epoch': 0.17, 'throughput': 298.12}
|
244 |
+
|
245 |
+
06/06/2024 21:21:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.0206, 'learning_rate': 4.9549e-05, 'epoch': 0.18, 'throughput': 297.89}
|
246 |
+
|
247 |
+
06/06/2024 21:22:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0188, 'learning_rate': 4.9507e-05, 'epoch': 0.19, 'throughput': 297.43}
|
248 |
+
|
249 |
+
06/06/2024 21:24:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0183, 'learning_rate': 4.9463e-05, 'epoch': 0.20, 'throughput': 297.64}
|
250 |
+
|
251 |
+
06/06/2024 21:26:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.0189, 'learning_rate': 4.9417e-05, 'epoch': 0.21, 'throughput': 297.06}
|
252 |
+
|
253 |
+
06/06/2024 21:27:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.0213, 'learning_rate': 4.9369e-05, 'epoch': 0.22, 'throughput': 297.53}
|
254 |
+
|
255 |
+
06/06/2024 21:29:12 - INFO - llamafactory.extras.callbacks - {'loss': 0.0214, 'learning_rate': 4.9319e-05, 'epoch': 0.23, 'throughput': 297.22}
|
256 |
+
|
257 |
+
06/06/2024 21:30:47 - INFO - llamafactory.extras.callbacks - {'loss': 0.0214, 'learning_rate': 4.9268e-05, 'epoch': 0.23, 'throughput': 297.22}
|
258 |
+
|
259 |
+
06/06/2024 21:32:22 - INFO - llamafactory.extras.callbacks - {'loss': 0.0203, 'learning_rate': 4.9215e-05, 'epoch': 0.24, 'throughput': 297.36}
|
260 |
+
|
261 |
+
06/06/2024 21:33:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.0194, 'learning_rate': 4.9159e-05, 'epoch': 0.25, 'throughput': 297.35}
|
262 |
+
|
263 |
+
06/06/2024 21:35:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.0158, 'learning_rate': 4.9102e-05, 'epoch': 0.26, 'throughput': 296.96}
|
264 |
+
|
265 |
+
06/06/2024 21:37:01 - INFO - llamafactory.extras.callbacks - {'loss': 0.0172, 'learning_rate': 4.9044e-05, 'epoch': 0.27, 'throughput': 296.94}
|
266 |
+
|
267 |
+
06/06/2024 21:38:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0193, 'learning_rate': 4.8983e-05, 'epoch': 0.28, 'throughput': 297.06}
|
268 |
+
|
269 |
+
06/06/2024 21:40:13 - INFO - llamafactory.extras.callbacks - {'loss': 0.0189, 'learning_rate': 4.8920e-05, 'epoch': 0.28, 'throughput': 297.62}
|
270 |
+
|
271 |
+
06/06/2024 21:41:49 - INFO - llamafactory.extras.callbacks - {'loss': 0.0190, 'learning_rate': 4.8856e-05, 'epoch': 0.29, 'throughput': 297.91}
|
272 |
+
|
273 |
+
06/06/2024 21:43:23 - INFO - llamafactory.extras.callbacks - {'loss': 0.0168, 'learning_rate': 4.8790e-05, 'epoch': 0.30, 'throughput': 297.99}
|
274 |
+
|
275 |
+
06/06/2024 21:45:00 - INFO - llamafactory.extras.callbacks - {'loss': 0.0194, 'learning_rate': 4.8722e-05, 'epoch': 0.31, 'throughput': 298.39}
|
276 |
+
|
277 |
+
06/06/2024 21:46:33 - INFO - llamafactory.extras.callbacks - {'loss': 0.0155, 'learning_rate': 4.8652e-05, 'epoch': 0.32, 'throughput': 298.24}
|
278 |
+
|
279 |
+
06/06/2024 21:48:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.0193, 'learning_rate': 4.8581e-05, 'epoch': 0.33, 'throughput': 298.10}
|
280 |
+
|
281 |
+
06/06/2024 21:49:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.0164, 'learning_rate': 4.8507e-05, 'epoch': 0.33, 'throughput': 298.12}
|
282 |
+
|
283 |
+
06/06/2024 21:49:40 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-200
|
284 |
+
|
285 |
+
06/06/2024 21:49:40 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/config.json
|
286 |
+
|
287 |
+
06/06/2024 21:49:40 - INFO - transformers.configuration_utils - Model config Qwen2Config {
|
288 |
+
"architectures": [
|
289 |
+
"Qwen2ForCausalLM"
|
290 |
+
],
|
291 |
+
"attention_dropout": 0.0,
|
292 |
+
"bos_token_id": 151643,
|
293 |
+
"eos_token_id": 151645,
|
294 |
+
"hidden_act": "silu",
|
295 |
+
"hidden_size": 3584,
|
296 |
+
"initializer_range": 0.02,
|
297 |
+
"intermediate_size": 18944,
|
298 |
+
"max_position_embeddings": 32768,
|
299 |
+
"max_window_layers": 28,
|
300 |
+
"model_type": "qwen2",
|
301 |
+
"num_attention_heads": 28,
|
302 |
+
"num_hidden_layers": 28,
|
303 |
+
"num_key_value_heads": 4,
|
304 |
+
"quantization_config": {
|
305 |
+
"batch_size": 1,
|
306 |
+
"bits": 8,
|
307 |
+
"block_name_to_quantize": null,
|
308 |
+
"cache_block_outputs": true,
|
309 |
+
"damp_percent": 0.1,
|
310 |
+
"dataset": null,
|
311 |
+
"desc_act": false,
|
312 |
+
"exllama_config": {
|
313 |
+
"version": 1
|
314 |
+
},
|
315 |
+
"group_size": 128,
|
316 |
+
"max_input_length": null,
|
317 |
+
"model_seqlen": null,
|
318 |
+
"module_name_preceding_first_block": null,
|
319 |
+
"modules_in_block_to_quantize": null,
|
320 |
+
"pad_token_id": null,
|
321 |
+
"quant_method": "gptq",
|
322 |
+
"sym": true,
|
323 |
+
"tokenizer": null,
|
324 |
+
"true_sequential": true,
|
325 |
+
"use_cuda_fp16": false,
|
326 |
+
"use_exllama": true
|
327 |
+
},
|
328 |
+
"rms_norm_eps": 1e-06,
|
329 |
+
"rope_theta": 1000000.0,
|
330 |
+
"sliding_window": 131072,
|
331 |
+
"tie_word_embeddings": false,
|
332 |
+
"torch_dtype": "float16",
|
333 |
+
"transformers_version": "4.41.2",
|
334 |
+
"use_cache": true,
|
335 |
+
"use_sliding_window": false,
|
336 |
+
"vocab_size": 152064
|
337 |
+
}
|
338 |
+
|
339 |
+
|
340 |
+
06/06/2024 21:49:40 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-200/tokenizer_config.json
|
341 |
+
|
342 |
+
06/06/2024 21:49:40 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-200/special_tokens_map.json
|
343 |
+
|
344 |
+
06/06/2024 21:51:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.0140, 'learning_rate': 4.8432e-05, 'epoch': 0.34, 'throughput': 298.66}
|
345 |
+
|
346 |
+
06/06/2024 21:52:51 - INFO - llamafactory.extras.callbacks - {'loss': 0.0154, 'learning_rate': 4.8355e-05, 'epoch': 0.35, 'throughput': 298.57}
|
347 |
+
|
348 |
+
06/06/2024 21:54:25 - INFO - llamafactory.extras.callbacks - {'loss': 0.0147, 'learning_rate': 4.8276e-05, 'epoch': 0.36, 'throughput': 298.63}
|
349 |
+
|
350 |
+
06/06/2024 21:55:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0185, 'learning_rate': 4.8196e-05, 'epoch': 0.37, 'throughput': 298.72}
|
351 |
+
|
352 |
+
06/06/2024 21:57:34 - INFO - llamafactory.extras.callbacks - {'loss': 0.0160, 'learning_rate': 4.8114e-05, 'epoch': 0.38, 'throughput': 298.74}
|
353 |
+
|
354 |
+
06/06/2024 21:59:07 - INFO - llamafactory.extras.callbacks - {'loss': 0.0168, 'learning_rate': 4.8030e-05, 'epoch': 0.38, 'throughput': 298.65}
|
355 |
+
|
356 |
+
06/06/2024 22:00:38 - INFO - llamafactory.extras.callbacks - {'loss': 0.0154, 'learning_rate': 4.7944e-05, 'epoch': 0.39, 'throughput': 298.39}
|
357 |
+
|
358 |
+
06/06/2024 22:02:21 - INFO - llamafactory.extras.callbacks - {'loss': 0.0149, 'learning_rate': 4.7856e-05, 'epoch': 0.40, 'throughput': 299.32}
|
359 |
+
|
360 |
+
06/06/2024 22:03:05 - INFO - transformers.trainer -
|
361 |
+
|
362 |
+
Training completed. Do not forget to share your model on huggingface.co/models =)
|
363 |
+
|
364 |
+
|
365 |
+
|
366 |
+
06/06/2024 22:03:05 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21
|
367 |
+
|
368 |
+
06/06/2024 22:03:06 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/config.json
|
369 |
+
|
370 |
+
06/06/2024 22:03:06 - INFO - transformers.configuration_utils - Model config Qwen2Config {
|
371 |
+
"architectures": [
|
372 |
+
"Qwen2ForCausalLM"
|
373 |
+
],
|
374 |
+
"attention_dropout": 0.0,
|
375 |
+
"bos_token_id": 151643,
|
376 |
+
"eos_token_id": 151645,
|
377 |
+
"hidden_act": "silu",
|
378 |
+
"hidden_size": 3584,
|
379 |
+
"initializer_range": 0.02,
|
380 |
+
"intermediate_size": 18944,
|
381 |
+
"max_position_embeddings": 32768,
|
382 |
+
"max_window_layers": 28,
|
383 |
+
"model_type": "qwen2",
|
384 |
+
"num_attention_heads": 28,
|
385 |
+
"num_hidden_layers": 28,
|
386 |
+
"num_key_value_heads": 4,
|
387 |
+
"quantization_config": {
|
388 |
+
"batch_size": 1,
|
389 |
+
"bits": 8,
|
390 |
+
"block_name_to_quantize": null,
|
391 |
+
"cache_block_outputs": true,
|
392 |
+
"damp_percent": 0.1,
|
393 |
+
"dataset": null,
|
394 |
+
"desc_act": false,
|
395 |
+
"exllama_config": {
|
396 |
+
"version": 1
|
397 |
+
},
|
398 |
+
"group_size": 128,
|
399 |
+
"max_input_length": null,
|
400 |
+
"model_seqlen": null,
|
401 |
+
"module_name_preceding_first_block": null,
|
402 |
+
"modules_in_block_to_quantize": null,
|
403 |
+
"pad_token_id": null,
|
404 |
+
"quant_method": "gptq",
|
405 |
+
"sym": true,
|
406 |
+
"tokenizer": null,
|
407 |
+
"true_sequential": true,
|
408 |
+
"use_cuda_fp16": false,
|
409 |
+
"use_exllama": true
|
410 |
+
},
|
411 |
+
"rms_norm_eps": 1e-06,
|
412 |
+
"rope_theta": 1000000.0,
|
413 |
+
"sliding_window": 131072,
|
414 |
+
"tie_word_embeddings": false,
|
415 |
+
"torch_dtype": "float16",
|
416 |
+
"transformers_version": "4.41.2",
|
417 |
+
"use_cache": true,
|
418 |
+
"use_sliding_window": false,
|
419 |
+
"vocab_size": 152064
|
420 |
+
}
|
421 |
+
|
422 |
+
|
423 |
+
06/06/2024 22:03:06 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/tokenizer_config.json
|
424 |
+
|
425 |
+
06/06/2024 22:03:06 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/special_tokens_map.json
|
426 |
+
|
427 |
+
06/06/2024 22:03:06 - WARNING - llamafactory.extras.ploting - No metric eval_loss to plot.
|
428 |
+
|
429 |
+
06/06/2024 22:03:06 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields:
|
430 |
+
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
|
431 |
+
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"padding_side": "right",
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
+
"unk_token": null
|
44 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.4033333333333333,
|
3 |
+
"num_input_tokens_seen": 1371584,
|
4 |
+
"total_flos": 4652852538507264.0,
|
5 |
+
"train_loss": 0.040362141964849364,
|
6 |
+
"train_runtime": 4583.2214,
|
7 |
+
"train_samples_per_second": 6.284,
|
8 |
+
"train_steps_per_second": 0.393
|
9 |
+
}
|
trainer_config.yaml
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
cutoff_len: 1024
|
2 |
+
dataset: train
|
3 |
+
dataset_dir: data
|
4 |
+
ddp_timeout: 180000000
|
5 |
+
do_train: true
|
6 |
+
finetuning_type: lora
|
7 |
+
flash_attn: fa2
|
8 |
+
fp16: true
|
9 |
+
gradient_accumulation_steps: 8
|
10 |
+
include_num_input_tokens_seen: true
|
11 |
+
learning_rate: 5.0e-05
|
12 |
+
logging_steps: 5
|
13 |
+
lora_alpha: 16
|
14 |
+
lora_dropout: 0
|
15 |
+
lora_rank: 8
|
16 |
+
lora_target: all
|
17 |
+
lr_scheduler_type: cosine
|
18 |
+
max_grad_norm: 1.0
|
19 |
+
max_samples: 100000
|
20 |
+
model_name_or_path: Qwen/Qwen2-7B-Instruct-GPTQ-Int8
|
21 |
+
num_train_epochs: 3.0
|
22 |
+
optim: adamw_torch
|
23 |
+
output_dir: saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21
|
24 |
+
packing: false
|
25 |
+
per_device_train_batch_size: 2
|
26 |
+
plot_loss: true
|
27 |
+
preprocessing_num_workers: 16
|
28 |
+
quantization_bit: 8
|
29 |
+
report_to: none
|
30 |
+
save_steps: 100
|
31 |
+
stage: sft
|
32 |
+
template: qwen
|
33 |
+
warmup_steps: 0
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 5, "total_steps": 1800, "loss": 0.4212, "learning_rate": 4.999904807660428e-05, "epoch": 0.008333333333333333, "percentage": 0.28, "elapsed_time": "0:01:34", "remaining_time": "9:25:43", "throughput": "317.96", "total_tokens": 30064}
|
2 |
+
{"current_steps": 10, "total_steps": 1800, "loss": 0.2803, "learning_rate": 4.9996192378909786e-05, "epoch": 0.016666666666666666, "percentage": 0.56, "elapsed_time": "0:03:06", "remaining_time": "9:16:17", "throughput": "307.70", "total_tokens": 57376}
|
3 |
+
{"current_steps": 15, "total_steps": 1800, "loss": 0.1484, "learning_rate": 4.999143312438893e-05, "epoch": 0.025, "percentage": 0.83, "elapsed_time": "0:04:41", "remaining_time": "9:18:46", "throughput": "305.82", "total_tokens": 86160}
|
4 |
+
{"current_steps": 20, "total_steps": 1800, "loss": 0.1151, "learning_rate": 4.99847706754774e-05, "epoch": 0.03333333333333333, "percentage": 1.11, "elapsed_time": "0:06:11", "remaining_time": "9:11:09", "throughput": "297.64", "total_tokens": 110592}
|
5 |
+
{"current_steps": 25, "total_steps": 1800, "loss": 0.0751, "learning_rate": 4.997620553954645e-05, "epoch": 0.041666666666666664, "percentage": 1.39, "elapsed_time": "0:07:46", "remaining_time": "9:12:11", "throughput": "297.62", "total_tokens": 138880}
|
6 |
+
{"current_steps": 30, "total_steps": 1800, "loss": 0.0471, "learning_rate": 4.996573836886435e-05, "epoch": 0.05, "percentage": 1.67, "elapsed_time": "0:09:24", "remaining_time": "9:15:14", "throughput": "300.36", "total_tokens": 169600}
|
7 |
+
{"current_steps": 35, "total_steps": 1800, "loss": 0.0368, "learning_rate": 4.9953369960546676e-05, "epoch": 0.058333333333333334, "percentage": 1.94, "elapsed_time": "0:11:04", "remaining_time": "9:18:40", "throughput": "303.39", "total_tokens": 201664}
|
8 |
+
{"current_steps": 40, "total_steps": 1800, "loss": 0.0311, "learning_rate": 4.993910125649561e-05, "epoch": 0.06666666666666667, "percentage": 2.22, "elapsed_time": "0:12:39", "remaining_time": "9:17:14", "throughput": "302.60", "total_tokens": 229936}
|
9 |
+
{"current_steps": 45, "total_steps": 1800, "loss": 0.0262, "learning_rate": 4.99229333433282e-05, "epoch": 0.075, "percentage": 2.5, "elapsed_time": "0:14:15", "remaining_time": "9:16:17", "throughput": "302.73", "total_tokens": 259088}
|
10 |
+
{"current_steps": 50, "total_steps": 1800, "loss": 0.0244, "learning_rate": 4.990486745229364e-05, "epoch": 0.08333333333333333, "percentage": 2.78, "elapsed_time": "0:15:53", "remaining_time": "9:16:27", "throughput": "303.83", "total_tokens": 289824}
|
11 |
+
{"current_steps": 55, "total_steps": 1800, "loss": 0.0266, "learning_rate": 4.988490495917947e-05, "epoch": 0.09166666666666666, "percentage": 3.06, "elapsed_time": "0:17:28", "remaining_time": "9:14:23", "throughput": "303.09", "total_tokens": 317760}
|
12 |
+
{"current_steps": 60, "total_steps": 1800, "loss": 0.0283, "learning_rate": 4.9867570427929354e-05, "epoch": 0.1, "percentage": 3.33, "elapsed_time": "0:19:03", "remaining_time": "9:12:47", "throughput": "300.01", "total_tokens": 343120}
|
13 |
+
{"current_steps": 65, "total_steps": 1800, "loss": 0.0265, "learning_rate": 4.984419797901491e-05, "epoch": 0.10833333333333334, "percentage": 3.61, "elapsed_time": "0:20:38", "remaining_time": "9:11:06", "throughput": "299.96", "total_tokens": 371600}
|
14 |
+
{"current_steps": 70, "total_steps": 1800, "loss": 0.0235, "learning_rate": 4.981893354823614e-05, "epoch": 0.11666666666666667, "percentage": 3.89, "elapsed_time": "0:22:11", "remaining_time": "9:08:34", "throughput": "299.39", "total_tokens": 398720}
|
15 |
+
{"current_steps": 75, "total_steps": 1800, "loss": 0.0229, "learning_rate": 4.979177905957726e-05, "epoch": 0.125, "percentage": 4.17, "elapsed_time": "0:23:45", "remaining_time": "9:06:24", "throughput": "299.15", "total_tokens": 426416}
|
16 |
+
{"current_steps": 80, "total_steps": 1800, "loss": 0.0238, "learning_rate": 4.976273658095772e-05, "epoch": 0.13333333333333333, "percentage": 4.44, "elapsed_time": "0:25:18", "remaining_time": "9:04:05", "throughput": "298.31", "total_tokens": 452944}
|
17 |
+
{"current_steps": 85, "total_steps": 1800, "loss": 0.0208, "learning_rate": 4.9731808324074717e-05, "epoch": 0.14166666666666666, "percentage": 4.72, "elapsed_time": "0:26:52", "remaining_time": "9:02:13", "throughput": "298.24", "total_tokens": 480896}
|
18 |
+
{"current_steps": 90, "total_steps": 1800, "loss": 0.0191, "learning_rate": 4.969899664423473e-05, "epoch": 0.15, "percentage": 5.0, "elapsed_time": "0:28:28", "remaining_time": "9:01:00", "throughput": "298.57", "total_tokens": 510096}
|
19 |
+
{"current_steps": 95, "total_steps": 1800, "loss": 0.0205, "learning_rate": 4.966430404017424e-05, "epoch": 0.15833333333333333, "percentage": 5.28, "elapsed_time": "0:30:00", "remaining_time": "8:58:40", "throughput": "298.01", "total_tokens": 536672}
|
20 |
+
{"current_steps": 100, "total_steps": 1800, "loss": 0.0193, "learning_rate": 4.962773315386935e-05, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:31:37", "remaining_time": "8:57:37", "throughput": "298.56", "total_tokens": 566528}
|
21 |
+
{"current_steps": 105, "total_steps": 1800, "loss": 0.024, "learning_rate": 4.9589286770334654e-05, "epoch": 0.175, "percentage": 5.83, "elapsed_time": "0:33:11", "remaining_time": "8:55:41", "throughput": "298.12", "total_tokens": 593584}
|
22 |
+
{"current_steps": 110, "total_steps": 1800, "loss": 0.0206, "learning_rate": 4.954896781741109e-05, "epoch": 0.18333333333333332, "percentage": 6.11, "elapsed_time": "0:34:44", "remaining_time": "8:53:47", "throughput": "297.89", "total_tokens": 620992}
|
23 |
+
{"current_steps": 115, "total_steps": 1800, "loss": 0.0188, "learning_rate": 4.9506779365543046e-05, "epoch": 0.19166666666666668, "percentage": 6.39, "elapsed_time": "0:36:17", "remaining_time": "8:51:38", "throughput": "297.43", "total_tokens": 647504}
|
24 |
+
{"current_steps": 120, "total_steps": 1800, "loss": 0.0183, "learning_rate": 4.9462724627544466e-05, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "0:37:52", "remaining_time": "8:50:12", "throughput": "297.64", "total_tokens": 676336}
|
25 |
+
{"current_steps": 125, "total_steps": 1800, "loss": 0.0189, "learning_rate": 4.94168069583542e-05, "epoch": 0.20833333333333334, "percentage": 6.94, "elapsed_time": "0:39:21", "remaining_time": "8:47:22", "throughput": "297.06", "total_tokens": 701488}
|
26 |
+
{"current_steps": 130, "total_steps": 1800, "loss": 0.0213, "learning_rate": 4.936902985478055e-05, "epoch": 0.21666666666666667, "percentage": 7.22, "elapsed_time": "0:40:57", "remaining_time": "8:46:08", "throughput": "297.53", "total_tokens": 731152}
|
27 |
+
{"current_steps": 135, "total_steps": 1800, "loss": 0.0214, "learning_rate": 4.931939695523492e-05, "epoch": 0.225, "percentage": 7.5, "elapsed_time": "0:42:29", "remaining_time": "8:44:04", "throughput": "297.22", "total_tokens": 757792}
|
28 |
+
{"current_steps": 140, "total_steps": 1800, "loss": 0.0214, "learning_rate": 4.926791203945477e-05, "epoch": 0.23333333333333334, "percentage": 7.78, "elapsed_time": "0:44:04", "remaining_time": "8:42:39", "throughput": "297.22", "total_tokens": 786064}
|
29 |
+
{"current_steps": 145, "total_steps": 1800, "loss": 0.0203, "learning_rate": 4.9214579028215776e-05, "epoch": 0.24166666666666667, "percentage": 8.06, "elapsed_time": "0:45:39", "remaining_time": "8:41:09", "throughput": "297.36", "total_tokens": 814640}
|
30 |
+
{"current_steps": 150, "total_steps": 1800, "loss": 0.0194, "learning_rate": 4.915940198303324e-05, "epoch": 0.25, "percentage": 8.33, "elapsed_time": "0:47:13", "remaining_time": "8:39:32", "throughput": "297.35", "total_tokens": 842656}
|
31 |
+
{"current_steps": 155, "total_steps": 1800, "loss": 0.0158, "learning_rate": 4.910238510585276e-05, "epoch": 0.25833333333333336, "percentage": 8.61, "elapsed_time": "0:48:44", "remaining_time": "8:37:19", "throughput": "296.96", "total_tokens": 868512}
|
32 |
+
{"current_steps": 160, "total_steps": 1800, "loss": 0.0172, "learning_rate": 4.9043532738730284e-05, "epoch": 0.26666666666666666, "percentage": 8.89, "elapsed_time": "0:50:18", "remaining_time": "8:35:43", "throughput": "296.94", "total_tokens": 896416}
|
33 |
+
{"current_steps": 165, "total_steps": 1800, "loss": 0.0193, "learning_rate": 4.898284936350144e-05, "epoch": 0.275, "percentage": 9.17, "elapsed_time": "0:51:52", "remaining_time": "8:34:06", "throughput": "297.06", "total_tokens": 924720}
|
34 |
+
{"current_steps": 170, "total_steps": 1800, "loss": 0.0189, "learning_rate": 4.892033960144019e-05, "epoch": 0.2833333333333333, "percentage": 9.44, "elapsed_time": "0:53:30", "remaining_time": "8:33:05", "throughput": "297.62", "total_tokens": 955584}
|
35 |
+
{"current_steps": 175, "total_steps": 1800, "loss": 0.019, "learning_rate": 4.8856008212906925e-05, "epoch": 0.2916666666666667, "percentage": 9.72, "elapsed_time": "0:55:06", "remaining_time": "8:31:43", "throughput": "297.91", "total_tokens": 985072}
|
36 |
+
{"current_steps": 180, "total_steps": 1800, "loss": 0.0168, "learning_rate": 4.878986009698596e-05, "epoch": 0.3, "percentage": 10.0, "elapsed_time": "0:56:40", "remaining_time": "8:30:03", "throughput": "297.99", "total_tokens": 1013296}
|
37 |
+
{"current_steps": 185, "total_steps": 1800, "loss": 0.0194, "learning_rate": 4.8721900291112415e-05, "epoch": 0.30833333333333335, "percentage": 10.28, "elapsed_time": "0:58:17", "remaining_time": "8:28:53", "throughput": "298.39", "total_tokens": 1043664}
|
38 |
+
{"current_steps": 190, "total_steps": 1800, "loss": 0.0155, "learning_rate": 4.8652133970688636e-05, "epoch": 0.31666666666666665, "percentage": 10.56, "elapsed_time": "0:59:50", "remaining_time": "8:27:07", "throughput": "298.24", "total_tokens": 1070912}
|
39 |
+
{"current_steps": 195, "total_steps": 1800, "loss": 0.0193, "learning_rate": 4.858056644869002e-05, "epoch": 0.325, "percentage": 10.83, "elapsed_time": "1:01:22", "remaining_time": "8:25:12", "throughput": "298.10", "total_tokens": 1097856}
|
40 |
+
{"current_steps": 200, "total_steps": 1800, "loss": 0.0164, "learning_rate": 4.850720317526047e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "1:02:57", "remaining_time": "8:23:39", "throughput": "298.12", "total_tokens": 1126128}
|
41 |
+
{"current_steps": 205, "total_steps": 1800, "loss": 0.014, "learning_rate": 4.843204973729729e-05, "epoch": 0.3416666666666667, "percentage": 11.39, "elapsed_time": "1:04:35", "remaining_time": "8:22:36", "throughput": "298.66", "total_tokens": 1157584}
|
42 |
+
{"current_steps": 210, "total_steps": 1800, "loss": 0.0154, "learning_rate": 4.835511185802574e-05, "epoch": 0.35, "percentage": 11.67, "elapsed_time": "1:06:08", "remaining_time": "8:20:45", "throughput": "298.57", "total_tokens": 1184800}
|
43 |
+
{"current_steps": 215, "total_steps": 1800, "loss": 0.0147, "learning_rate": 4.827639539656321e-05, "epoch": 0.35833333333333334, "percentage": 11.94, "elapsed_time": "1:07:42", "remaining_time": "8:19:07", "throughput": "298.63", "total_tokens": 1213104}
|
44 |
+
{"current_steps": 220, "total_steps": 1800, "loss": 0.0185, "learning_rate": 4.8195906347473e-05, "epoch": 0.36666666666666664, "percentage": 12.22, "elapsed_time": "1:09:17", "remaining_time": "8:17:35", "throughput": "298.72", "total_tokens": 1241808}
|
45 |
+
{"current_steps": 225, "total_steps": 1800, "loss": 0.016, "learning_rate": 4.8113650840307834e-05, "epoch": 0.375, "percentage": 12.5, "elapsed_time": "1:10:51", "remaining_time": "8:16:01", "throughput": "298.74", "total_tokens": 1270160}
|
46 |
+
{"current_steps": 230, "total_steps": 1800, "loss": 0.0168, "learning_rate": 4.802963513914304e-05, "epoch": 0.38333333333333336, "percentage": 12.78, "elapsed_time": "1:12:24", "remaining_time": "8:14:14", "throughput": "298.65", "total_tokens": 1297456}
|
47 |
+
{"current_steps": 235, "total_steps": 1800, "loss": 0.0154, "learning_rate": 4.794386564209953e-05, "epoch": 0.39166666666666666, "percentage": 13.06, "elapsed_time": "1:13:55", "remaining_time": "8:12:16", "throughput": "298.39", "total_tokens": 1323392}
|
48 |
+
{"current_steps": 240, "total_steps": 1800, "loss": 0.0149, "learning_rate": 4.7856348880856595e-05, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "1:15:38", "remaining_time": "8:11:43", "throughput": "299.32", "total_tokens": 1358576}
|
49 |
+
{"current_steps": 242, "total_steps": 1800, "epoch": 0.4033333333333333, "percentage": 13.44, "elapsed_time": "1:16:23", "remaining_time": "8:11:46", "throughput": "299.27", "total_tokens": 1371584}
|
trainer_state.json
ADDED
@@ -0,0 +1,427 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4033333333333333,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 242,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.008333333333333333,
|
13 |
+
"grad_norm": 0.48900601267814636,
|
14 |
+
"learning_rate": 4.999904807660428e-05,
|
15 |
+
"loss": 0.4212,
|
16 |
+
"num_input_tokens_seen": 30064,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.016666666666666666,
|
21 |
+
"grad_norm": 0.3595407009124756,
|
22 |
+
"learning_rate": 4.9996192378909786e-05,
|
23 |
+
"loss": 0.2803,
|
24 |
+
"num_input_tokens_seen": 57376,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.025,
|
29 |
+
"grad_norm": 0.2623545527458191,
|
30 |
+
"learning_rate": 4.999143312438893e-05,
|
31 |
+
"loss": 0.1484,
|
32 |
+
"num_input_tokens_seen": 86160,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.03333333333333333,
|
37 |
+
"grad_norm": 0.2743065357208252,
|
38 |
+
"learning_rate": 4.99847706754774e-05,
|
39 |
+
"loss": 0.1151,
|
40 |
+
"num_input_tokens_seen": 110592,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.041666666666666664,
|
45 |
+
"grad_norm": 0.2651338577270508,
|
46 |
+
"learning_rate": 4.997620553954645e-05,
|
47 |
+
"loss": 0.0751,
|
48 |
+
"num_input_tokens_seen": 138880,
|
49 |
+
"step": 25
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.05,
|
53 |
+
"grad_norm": 0.10798148065805435,
|
54 |
+
"learning_rate": 4.996573836886435e-05,
|
55 |
+
"loss": 0.0471,
|
56 |
+
"num_input_tokens_seen": 169600,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.058333333333333334,
|
61 |
+
"grad_norm": 0.1552838534116745,
|
62 |
+
"learning_rate": 4.9953369960546676e-05,
|
63 |
+
"loss": 0.0368,
|
64 |
+
"num_input_tokens_seen": 201664,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.06666666666666667,
|
69 |
+
"grad_norm": 0.11832074075937271,
|
70 |
+
"learning_rate": 4.993910125649561e-05,
|
71 |
+
"loss": 0.0311,
|
72 |
+
"num_input_tokens_seen": 229936,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.075,
|
77 |
+
"grad_norm": 0.10593917220830917,
|
78 |
+
"learning_rate": 4.99229333433282e-05,
|
79 |
+
"loss": 0.0262,
|
80 |
+
"num_input_tokens_seen": 259088,
|
81 |
+
"step": 45
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.08333333333333333,
|
85 |
+
"grad_norm": 0.09650842100381851,
|
86 |
+
"learning_rate": 4.990486745229364e-05,
|
87 |
+
"loss": 0.0244,
|
88 |
+
"num_input_tokens_seen": 289824,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.09166666666666666,
|
93 |
+
"grad_norm": 0.14155137538909912,
|
94 |
+
"learning_rate": 4.988490495917947e-05,
|
95 |
+
"loss": 0.0266,
|
96 |
+
"num_input_tokens_seen": 317760,
|
97 |
+
"step": 55
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.1,
|
101 |
+
"grad_norm": 0.1490347981452942,
|
102 |
+
"learning_rate": 4.9867570427929354e-05,
|
103 |
+
"loss": 0.0283,
|
104 |
+
"num_input_tokens_seen": 343120,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.10833333333333334,
|
109 |
+
"grad_norm": 0.17539122700691223,
|
110 |
+
"learning_rate": 4.984419797901491e-05,
|
111 |
+
"loss": 0.0265,
|
112 |
+
"num_input_tokens_seen": 371600,
|
113 |
+
"step": 65
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.11666666666666667,
|
117 |
+
"grad_norm": 0.1336919367313385,
|
118 |
+
"learning_rate": 4.981893354823614e-05,
|
119 |
+
"loss": 0.0235,
|
120 |
+
"num_input_tokens_seen": 398720,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.125,
|
125 |
+
"grad_norm": 0.12203177809715271,
|
126 |
+
"learning_rate": 4.979177905957726e-05,
|
127 |
+
"loss": 0.0229,
|
128 |
+
"num_input_tokens_seen": 426416,
|
129 |
+
"step": 75
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.13333333333333333,
|
133 |
+
"grad_norm": 0.2557654082775116,
|
134 |
+
"learning_rate": 4.976273658095772e-05,
|
135 |
+
"loss": 0.0238,
|
136 |
+
"num_input_tokens_seen": 452944,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.14166666666666666,
|
141 |
+
"grad_norm": 0.13327105343341827,
|
142 |
+
"learning_rate": 4.9731808324074717e-05,
|
143 |
+
"loss": 0.0208,
|
144 |
+
"num_input_tokens_seen": 480896,
|
145 |
+
"step": 85
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.15,
|
149 |
+
"grad_norm": 0.1262751668691635,
|
150 |
+
"learning_rate": 4.969899664423473e-05,
|
151 |
+
"loss": 0.0191,
|
152 |
+
"num_input_tokens_seen": 510096,
|
153 |
+
"step": 90
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.15833333333333333,
|
157 |
+
"grad_norm": 0.16084067523479462,
|
158 |
+
"learning_rate": 4.966430404017424e-05,
|
159 |
+
"loss": 0.0205,
|
160 |
+
"num_input_tokens_seen": 536672,
|
161 |
+
"step": 95
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.16666666666666666,
|
165 |
+
"grad_norm": 0.15870437026023865,
|
166 |
+
"learning_rate": 4.962773315386935e-05,
|
167 |
+
"loss": 0.0193,
|
168 |
+
"num_input_tokens_seen": 566528,
|
169 |
+
"step": 100
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.175,
|
173 |
+
"grad_norm": 0.07833187282085419,
|
174 |
+
"learning_rate": 4.9589286770334654e-05,
|
175 |
+
"loss": 0.024,
|
176 |
+
"num_input_tokens_seen": 593584,
|
177 |
+
"step": 105
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.18333333333333332,
|
181 |
+
"grad_norm": 0.09176061302423477,
|
182 |
+
"learning_rate": 4.954896781741109e-05,
|
183 |
+
"loss": 0.0206,
|
184 |
+
"num_input_tokens_seen": 620992,
|
185 |
+
"step": 110
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.19166666666666668,
|
189 |
+
"grad_norm": 0.08285439014434814,
|
190 |
+
"learning_rate": 4.9506779365543046e-05,
|
191 |
+
"loss": 0.0188,
|
192 |
+
"num_input_tokens_seen": 647504,
|
193 |
+
"step": 115
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.2,
|
197 |
+
"grad_norm": 0.13359522819519043,
|
198 |
+
"learning_rate": 4.9462724627544466e-05,
|
199 |
+
"loss": 0.0183,
|
200 |
+
"num_input_tokens_seen": 676336,
|
201 |
+
"step": 120
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.20833333333333334,
|
205 |
+
"grad_norm": 0.07570718228816986,
|
206 |
+
"learning_rate": 4.94168069583542e-05,
|
207 |
+
"loss": 0.0189,
|
208 |
+
"num_input_tokens_seen": 701488,
|
209 |
+
"step": 125
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.21666666666666667,
|
213 |
+
"grad_norm": 0.11286037415266037,
|
214 |
+
"learning_rate": 4.936902985478055e-05,
|
215 |
+
"loss": 0.0213,
|
216 |
+
"num_input_tokens_seen": 731152,
|
217 |
+
"step": 130
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.225,
|
221 |
+
"grad_norm": 0.17183929681777954,
|
222 |
+
"learning_rate": 4.931939695523492e-05,
|
223 |
+
"loss": 0.0214,
|
224 |
+
"num_input_tokens_seen": 757792,
|
225 |
+
"step": 135
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.23333333333333334,
|
229 |
+
"grad_norm": 0.11746834218502045,
|
230 |
+
"learning_rate": 4.926791203945477e-05,
|
231 |
+
"loss": 0.0214,
|
232 |
+
"num_input_tokens_seen": 786064,
|
233 |
+
"step": 140
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.24166666666666667,
|
237 |
+
"grad_norm": 0.09453292936086655,
|
238 |
+
"learning_rate": 4.9214579028215776e-05,
|
239 |
+
"loss": 0.0203,
|
240 |
+
"num_input_tokens_seen": 814640,
|
241 |
+
"step": 145
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.25,
|
245 |
+
"grad_norm": 0.2074723094701767,
|
246 |
+
"learning_rate": 4.915940198303324e-05,
|
247 |
+
"loss": 0.0194,
|
248 |
+
"num_input_tokens_seen": 842656,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.25833333333333336,
|
253 |
+
"grad_norm": 0.15371476113796234,
|
254 |
+
"learning_rate": 4.910238510585276e-05,
|
255 |
+
"loss": 0.0158,
|
256 |
+
"num_input_tokens_seen": 868512,
|
257 |
+
"step": 155
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.26666666666666666,
|
261 |
+
"grad_norm": 0.07177837193012238,
|
262 |
+
"learning_rate": 4.9043532738730284e-05,
|
263 |
+
"loss": 0.0172,
|
264 |
+
"num_input_tokens_seen": 896416,
|
265 |
+
"step": 160
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.275,
|
269 |
+
"grad_norm": 0.07891824096441269,
|
270 |
+
"learning_rate": 4.898284936350144e-05,
|
271 |
+
"loss": 0.0193,
|
272 |
+
"num_input_tokens_seen": 924720,
|
273 |
+
"step": 165
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.2833333333333333,
|
277 |
+
"grad_norm": 0.08302944153547287,
|
278 |
+
"learning_rate": 4.892033960144019e-05,
|
279 |
+
"loss": 0.0189,
|
280 |
+
"num_input_tokens_seen": 955584,
|
281 |
+
"step": 170
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.2916666666666667,
|
285 |
+
"grad_norm": 0.25554358959198,
|
286 |
+
"learning_rate": 4.8856008212906925e-05,
|
287 |
+
"loss": 0.019,
|
288 |
+
"num_input_tokens_seen": 985072,
|
289 |
+
"step": 175
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.3,
|
293 |
+
"grad_norm": 0.1445908546447754,
|
294 |
+
"learning_rate": 4.878986009698596e-05,
|
295 |
+
"loss": 0.0168,
|
296 |
+
"num_input_tokens_seen": 1013296,
|
297 |
+
"step": 180
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.30833333333333335,
|
301 |
+
"grad_norm": 0.21417762339115143,
|
302 |
+
"learning_rate": 4.8721900291112415e-05,
|
303 |
+
"loss": 0.0194,
|
304 |
+
"num_input_tokens_seen": 1043664,
|
305 |
+
"step": 185
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.31666666666666665,
|
309 |
+
"grad_norm": 0.1550753116607666,
|
310 |
+
"learning_rate": 4.8652133970688636e-05,
|
311 |
+
"loss": 0.0155,
|
312 |
+
"num_input_tokens_seen": 1070912,
|
313 |
+
"step": 190
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.325,
|
317 |
+
"grad_norm": 0.132898211479187,
|
318 |
+
"learning_rate": 4.858056644869002e-05,
|
319 |
+
"loss": 0.0193,
|
320 |
+
"num_input_tokens_seen": 1097856,
|
321 |
+
"step": 195
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.3333333333333333,
|
325 |
+
"grad_norm": 0.09164389222860336,
|
326 |
+
"learning_rate": 4.850720317526047e-05,
|
327 |
+
"loss": 0.0164,
|
328 |
+
"num_input_tokens_seen": 1126128,
|
329 |
+
"step": 200
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.3416666666666667,
|
333 |
+
"grad_norm": 0.07462836056947708,
|
334 |
+
"learning_rate": 4.843204973729729e-05,
|
335 |
+
"loss": 0.014,
|
336 |
+
"num_input_tokens_seen": 1157584,
|
337 |
+
"step": 205
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.35,
|
341 |
+
"grad_norm": 0.08473635464906693,
|
342 |
+
"learning_rate": 4.835511185802574e-05,
|
343 |
+
"loss": 0.0154,
|
344 |
+
"num_input_tokens_seen": 1184800,
|
345 |
+
"step": 210
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.35833333333333334,
|
349 |
+
"grad_norm": 0.07371218502521515,
|
350 |
+
"learning_rate": 4.827639539656321e-05,
|
351 |
+
"loss": 0.0147,
|
352 |
+
"num_input_tokens_seen": 1213104,
|
353 |
+
"step": 215
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.36666666666666664,
|
357 |
+
"grad_norm": 0.1394609957933426,
|
358 |
+
"learning_rate": 4.8195906347473e-05,
|
359 |
+
"loss": 0.0185,
|
360 |
+
"num_input_tokens_seen": 1241808,
|
361 |
+
"step": 220
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.375,
|
365 |
+
"grad_norm": 0.11585802584886551,
|
366 |
+
"learning_rate": 4.8113650840307834e-05,
|
367 |
+
"loss": 0.016,
|
368 |
+
"num_input_tokens_seen": 1270160,
|
369 |
+
"step": 225
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.38333333333333336,
|
373 |
+
"grad_norm": 0.1538001149892807,
|
374 |
+
"learning_rate": 4.802963513914304e-05,
|
375 |
+
"loss": 0.0168,
|
376 |
+
"num_input_tokens_seen": 1297456,
|
377 |
+
"step": 230
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.39166666666666666,
|
381 |
+
"grad_norm": 0.09096246212720871,
|
382 |
+
"learning_rate": 4.794386564209953e-05,
|
383 |
+
"loss": 0.0154,
|
384 |
+
"num_input_tokens_seen": 1323392,
|
385 |
+
"step": 235
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 0.4,
|
389 |
+
"grad_norm": 0.11348401010036469,
|
390 |
+
"learning_rate": 4.7856348880856595e-05,
|
391 |
+
"loss": 0.0149,
|
392 |
+
"num_input_tokens_seen": 1358576,
|
393 |
+
"step": 240
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.4033333333333333,
|
397 |
+
"num_input_tokens_seen": 1371584,
|
398 |
+
"step": 242,
|
399 |
+
"total_flos": 4652852538507264.0,
|
400 |
+
"train_loss": 0.040362141964849364,
|
401 |
+
"train_runtime": 4583.2214,
|
402 |
+
"train_samples_per_second": 6.284,
|
403 |
+
"train_steps_per_second": 0.393
|
404 |
+
}
|
405 |
+
],
|
406 |
+
"logging_steps": 5,
|
407 |
+
"max_steps": 1800,
|
408 |
+
"num_input_tokens_seen": 1371584,
|
409 |
+
"num_train_epochs": 3,
|
410 |
+
"save_steps": 100,
|
411 |
+
"stateful_callbacks": {
|
412 |
+
"TrainerControl": {
|
413 |
+
"args": {
|
414 |
+
"should_epoch_stop": false,
|
415 |
+
"should_evaluate": false,
|
416 |
+
"should_log": false,
|
417 |
+
"should_save": true,
|
418 |
+
"should_training_stop": false
|
419 |
+
},
|
420 |
+
"attributes": {}
|
421 |
+
}
|
422 |
+
},
|
423 |
+
"total_flos": 4652852538507264.0,
|
424 |
+
"train_batch_size": 2,
|
425 |
+
"trial_name": null,
|
426 |
+
"trial_params": null
|
427 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e38936a74c731e02f619889aeaa58a6ba812a6fabdbd18f67b624b496070c73c
|
3 |
+
size 5304
|
training_loss.png
ADDED
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|