Spaces:
Build error
Build error
finished finetuning of phi-3.5-mini
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- llama-factory/saves/Phi-3.5-mini-instruct/README.md +69 -0
- llama-factory/saves/Phi-3.5-mini-instruct/adapter_config.json +31 -0
- llama-factory/saves/Phi-3.5-mini-instruct/adapter_model.safetensors +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/added_tokens.json +13 -0
- llama-factory/saves/Phi-3.5-mini-instruct/all_results.json +12 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/README.md +202 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/adapter_config.json +31 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/adapter_model.safetensors +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/added_tokens.json +13 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/optimizer.pt +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/rng_state.pth +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/scheduler.pt +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/special_tokens_map.json +30 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/tokenizer.json +0 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/tokenizer.model +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/tokenizer_config.json +132 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/trainer_state.json +204 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/training_args.bin +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/README.md +202 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/adapter_config.json +31 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/adapter_model.safetensors +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/added_tokens.json +13 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/optimizer.pt +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/rng_state.pth +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/scheduler.pt +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/special_tokens_map.json +30 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/tokenizer.json +0 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/tokenizer.model +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/tokenizer_config.json +132 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/trainer_state.json +261 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/training_args.bin +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/README.md +202 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/adapter_config.json +31 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/adapter_model.safetensors +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/added_tokens.json +13 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/optimizer.pt +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/rng_state.pth +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/scheduler.pt +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/special_tokens_map.json +30 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/tokenizer.json +0 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/tokenizer.model +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/tokenizer_config.json +132 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/trainer_state.json +318 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/training_args.bin +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/README.md +202 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/adapter_config.json +31 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/adapter_model.safetensors +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/added_tokens.json +13 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/optimizer.pt +3 -0
- llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/rng_state.pth +3 -0
llama-factory/saves/Phi-3.5-mini-instruct/README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3.5-mini-instruct
|
3 |
+
library_name: peft
|
4 |
+
license: other
|
5 |
+
tags:
|
6 |
+
- llama-factory
|
7 |
+
- lora
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: Phi-3.5-mini-instruct
|
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 |
+
# Phi-3.5-mini-instruct
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the alpaca_mac dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.6644
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 1
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 8
|
45 |
+
- total_train_batch_size: 128
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 6.0
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
55 |
+
| 1.9221 | 0.9964 | 35 | 1.9123 |
|
56 |
+
| 1.7521 | 1.9929 | 70 | 1.7631 |
|
57 |
+
| 1.6831 | 2.9893 | 105 | 1.6914 |
|
58 |
+
| 1.5566 | 3.9858 | 140 | 1.6649 |
|
59 |
+
| 1.562 | 4.9822 | 175 | 1.6638 |
|
60 |
+
| 1.5573 | 5.9786 | 210 | 1.6644 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- PEFT 0.11.1
|
66 |
+
- Transformers 4.43.3
|
67 |
+
- Pytorch 2.4.0+cu121
|
68 |
+
- Datasets 2.19.1
|
69 |
+
- Tokenizers 0.19.1
|
llama-factory/saves/Phi-3.5-mini-instruct/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
|
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": 0.0,
|
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 |
+
"qkv_proj",
|
24 |
+
"down_proj",
|
25 |
+
"gate_up_proj",
|
26 |
+
"o_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2fef064b69976e06a1f7d030039fda5b1893feb02f1d92877cfa71069226acb
|
3 |
+
size 50365768
|
llama-factory/saves/Phi-3.5-mini-instruct/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.9786476868327405,
|
3 |
+
"eval_loss": 1.6644203662872314,
|
4 |
+
"eval_runtime": 2.6994,
|
5 |
+
"eval_samples_per_second": 17.041,
|
6 |
+
"eval_steps_per_second": 17.041,
|
7 |
+
"total_flos": 1.7533662523283866e+17,
|
8 |
+
"train_loss": 1.8585307757059732,
|
9 |
+
"train_runtime": 2890.6103,
|
10 |
+
"train_samples_per_second": 9.303,
|
11 |
+
"train_steps_per_second": 0.073
|
12 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3.5-mini-instruct
|
3 |
+
library_name: peft
|
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
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
|
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": 0.0,
|
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 |
+
"qkv_proj",
|
24 |
+
"down_proj",
|
25 |
+
"gate_up_proj",
|
26 |
+
"o_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a4606819c7f656a215e71778f3af33eec0e6b70d2413844063095cc60ce703b
|
3 |
+
size 50365768
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62cd92b5ca96c038b57c5ebe85141fdd3bda27b0900eff9cf01aa255235d05d6
|
3 |
+
size 100878458
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
|
3 |
+
size 14244
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f884e1907aa5818c277b83d03af573102a4aa6924b1853efad0972d9cae963a5
|
3 |
+
size 1064
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/tokenizer_config.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
|
121 |
+
"clean_up_tokenization_spaces": false,
|
122 |
+
"eos_token": "<|end|>",
|
123 |
+
"legacy": false,
|
124 |
+
"model_max_length": 131072,
|
125 |
+
"pad_token": "<|endoftext|>",
|
126 |
+
"padding_side": "right",
|
127 |
+
"sp_model_kwargs": {},
|
128 |
+
"split_special_tokens": false,
|
129 |
+
"tokenizer_class": "LlamaTokenizer",
|
130 |
+
"unk_token": "<unk>",
|
131 |
+
"use_default_system_prompt": false
|
132 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/trainer_state.json
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9893238434163703,
|
5 |
+
"eval_steps": 35,
|
6 |
+
"global_step": 105,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.1423487544483986,
|
13 |
+
"grad_norm": 3.915436267852783,
|
14 |
+
"learning_rate": 2.380952380952381e-05,
|
15 |
+
"loss": 4.6057,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.2846975088967972,
|
20 |
+
"grad_norm": 4.926669597625732,
|
21 |
+
"learning_rate": 4.761904761904762e-05,
|
22 |
+
"loss": 4.3259,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.42704626334519574,
|
27 |
+
"grad_norm": 3.071687936782837,
|
28 |
+
"learning_rate": 7.142857142857143e-05,
|
29 |
+
"loss": 3.5782,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.5693950177935944,
|
34 |
+
"grad_norm": 1.5628787279129028,
|
35 |
+
"learning_rate": 9.523809523809524e-05,
|
36 |
+
"loss": 2.542,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.7117437722419929,
|
41 |
+
"grad_norm": 0.6052073240280151,
|
42 |
+
"learning_rate": 9.988952191691925e-05,
|
43 |
+
"loss": 2.0288,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.8540925266903915,
|
48 |
+
"grad_norm": 0.4768967032432556,
|
49 |
+
"learning_rate": 9.944154131125642e-05,
|
50 |
+
"loss": 1.9283,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.99644128113879,
|
55 |
+
"grad_norm": 0.3471652865409851,
|
56 |
+
"learning_rate": 9.865224352899119e-05,
|
57 |
+
"loss": 1.9221,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.99644128113879,
|
62 |
+
"eval_loss": 1.9122635126113892,
|
63 |
+
"eval_runtime": 2.7209,
|
64 |
+
"eval_samples_per_second": 16.906,
|
65 |
+
"eval_steps_per_second": 16.906,
|
66 |
+
"step": 35
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.1387900355871885,
|
70 |
+
"grad_norm": 0.3238619863986969,
|
71 |
+
"learning_rate": 9.752707744739145e-05,
|
72 |
+
"loss": 1.8485,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 1.281138790035587,
|
77 |
+
"grad_norm": 0.3222252130508423,
|
78 |
+
"learning_rate": 9.607381059352038e-05,
|
79 |
+
"loss": 1.8223,
|
80 |
+
"step": 45
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.4234875444839858,
|
84 |
+
"grad_norm": 0.30783718824386597,
|
85 |
+
"learning_rate": 9.430247552150673e-05,
|
86 |
+
"loss": 1.7991,
|
87 |
+
"step": 50
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.5658362989323842,
|
91 |
+
"grad_norm": 0.33385950326919556,
|
92 |
+
"learning_rate": 9.22253005533154e-05,
|
93 |
+
"loss": 1.7761,
|
94 |
+
"step": 55
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 1.708185053380783,
|
98 |
+
"grad_norm": 0.3235575258731842,
|
99 |
+
"learning_rate": 8.985662536114613e-05,
|
100 |
+
"loss": 1.7781,
|
101 |
+
"step": 60
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.8505338078291815,
|
105 |
+
"grad_norm": 0.31781575083732605,
|
106 |
+
"learning_rate": 8.721280197423258e-05,
|
107 |
+
"loss": 1.7457,
|
108 |
+
"step": 65
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.99288256227758,
|
112 |
+
"grad_norm": 0.3225061297416687,
|
113 |
+
"learning_rate": 8.43120818934367e-05,
|
114 |
+
"loss": 1.7521,
|
115 |
+
"step": 70
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.99288256227758,
|
119 |
+
"eval_loss": 1.7631458044052124,
|
120 |
+
"eval_runtime": 2.707,
|
121 |
+
"eval_samples_per_second": 16.993,
|
122 |
+
"eval_steps_per_second": 16.993,
|
123 |
+
"step": 70
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.135231316725979,
|
127 |
+
"grad_norm": 0.3239762783050537,
|
128 |
+
"learning_rate": 8.117449009293668e-05,
|
129 |
+
"loss": 1.6471,
|
130 |
+
"step": 75
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 2.277580071174377,
|
134 |
+
"grad_norm": 0.348884642124176,
|
135 |
+
"learning_rate": 7.782168677883206e-05,
|
136 |
+
"loss": 1.7,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 2.419928825622776,
|
141 |
+
"grad_norm": 0.3774774372577667,
|
142 |
+
"learning_rate": 7.427681785900761e-05,
|
143 |
+
"loss": 1.7183,
|
144 |
+
"step": 85
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 2.562277580071174,
|
148 |
+
"grad_norm": 0.39107823371887207,
|
149 |
+
"learning_rate": 7.056435515653059e-05,
|
150 |
+
"loss": 1.6825,
|
151 |
+
"step": 90
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 2.704626334519573,
|
155 |
+
"grad_norm": 0.5160859823226929,
|
156 |
+
"learning_rate": 6.670992746965938e-05,
|
157 |
+
"loss": 1.664,
|
158 |
+
"step": 95
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.8469750889679717,
|
162 |
+
"grad_norm": 0.4094185531139374,
|
163 |
+
"learning_rate": 6.274014364473274e-05,
|
164 |
+
"loss": 1.6662,
|
165 |
+
"step": 100
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 2.9893238434163703,
|
169 |
+
"grad_norm": 0.4102707803249359,
|
170 |
+
"learning_rate": 5.868240888334653e-05,
|
171 |
+
"loss": 1.6831,
|
172 |
+
"step": 105
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 2.9893238434163703,
|
176 |
+
"eval_loss": 1.691434621810913,
|
177 |
+
"eval_runtime": 2.7669,
|
178 |
+
"eval_samples_per_second": 16.625,
|
179 |
+
"eval_steps_per_second": 16.625,
|
180 |
+
"step": 105
|
181 |
+
}
|
182 |
+
],
|
183 |
+
"logging_steps": 5,
|
184 |
+
"max_steps": 210,
|
185 |
+
"num_input_tokens_seen": 0,
|
186 |
+
"num_train_epochs": 6,
|
187 |
+
"save_steps": 35,
|
188 |
+
"stateful_callbacks": {
|
189 |
+
"TrainerControl": {
|
190 |
+
"args": {
|
191 |
+
"should_epoch_stop": false,
|
192 |
+
"should_evaluate": false,
|
193 |
+
"should_log": false,
|
194 |
+
"should_save": true,
|
195 |
+
"should_training_stop": false
|
196 |
+
},
|
197 |
+
"attributes": {}
|
198 |
+
}
|
199 |
+
},
|
200 |
+
"total_flos": 8.782483083883315e+16,
|
201 |
+
"train_batch_size": 16,
|
202 |
+
"trial_name": null,
|
203 |
+
"trial_params": null
|
204 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-105/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2bc05afc45cc2260e917f0e545fdbc53c8c1a9def7f26bb3cc9459a74257487
|
3 |
+
size 5368
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3.5-mini-instruct
|
3 |
+
library_name: peft
|
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
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
|
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": 0.0,
|
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 |
+
"qkv_proj",
|
24 |
+
"down_proj",
|
25 |
+
"gate_up_proj",
|
26 |
+
"o_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51269624a2f8ae34127497ef0a4bb36779c73fdebfeb97c1b2a486bd8be8b071
|
3 |
+
size 50365768
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0450d108083f8443f5d1e2111c29c7aa6ef4db50061a445b86cb02b796acbb53
|
3 |
+
size 100878458
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
|
3 |
+
size 14244
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c79c4e0ef5874a405d3a7ead058cbb211b801c0b67fe721ad82a960e96528bf4
|
3 |
+
size 1064
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/tokenizer_config.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
|
121 |
+
"clean_up_tokenization_spaces": false,
|
122 |
+
"eos_token": "<|end|>",
|
123 |
+
"legacy": false,
|
124 |
+
"model_max_length": 131072,
|
125 |
+
"pad_token": "<|endoftext|>",
|
126 |
+
"padding_side": "right",
|
127 |
+
"sp_model_kwargs": {},
|
128 |
+
"split_special_tokens": false,
|
129 |
+
"tokenizer_class": "LlamaTokenizer",
|
130 |
+
"unk_token": "<unk>",
|
131 |
+
"use_default_system_prompt": false
|
132 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/trainer_state.json
ADDED
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.98576512455516,
|
5 |
+
"eval_steps": 35,
|
6 |
+
"global_step": 140,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.1423487544483986,
|
13 |
+
"grad_norm": 3.915436267852783,
|
14 |
+
"learning_rate": 2.380952380952381e-05,
|
15 |
+
"loss": 4.6057,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.2846975088967972,
|
20 |
+
"grad_norm": 4.926669597625732,
|
21 |
+
"learning_rate": 4.761904761904762e-05,
|
22 |
+
"loss": 4.3259,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.42704626334519574,
|
27 |
+
"grad_norm": 3.071687936782837,
|
28 |
+
"learning_rate": 7.142857142857143e-05,
|
29 |
+
"loss": 3.5782,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.5693950177935944,
|
34 |
+
"grad_norm": 1.5628787279129028,
|
35 |
+
"learning_rate": 9.523809523809524e-05,
|
36 |
+
"loss": 2.542,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.7117437722419929,
|
41 |
+
"grad_norm": 0.6052073240280151,
|
42 |
+
"learning_rate": 9.988952191691925e-05,
|
43 |
+
"loss": 2.0288,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.8540925266903915,
|
48 |
+
"grad_norm": 0.4768967032432556,
|
49 |
+
"learning_rate": 9.944154131125642e-05,
|
50 |
+
"loss": 1.9283,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.99644128113879,
|
55 |
+
"grad_norm": 0.3471652865409851,
|
56 |
+
"learning_rate": 9.865224352899119e-05,
|
57 |
+
"loss": 1.9221,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.99644128113879,
|
62 |
+
"eval_loss": 1.9122635126113892,
|
63 |
+
"eval_runtime": 2.7209,
|
64 |
+
"eval_samples_per_second": 16.906,
|
65 |
+
"eval_steps_per_second": 16.906,
|
66 |
+
"step": 35
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.1387900355871885,
|
70 |
+
"grad_norm": 0.3238619863986969,
|
71 |
+
"learning_rate": 9.752707744739145e-05,
|
72 |
+
"loss": 1.8485,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 1.281138790035587,
|
77 |
+
"grad_norm": 0.3222252130508423,
|
78 |
+
"learning_rate": 9.607381059352038e-05,
|
79 |
+
"loss": 1.8223,
|
80 |
+
"step": 45
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.4234875444839858,
|
84 |
+
"grad_norm": 0.30783718824386597,
|
85 |
+
"learning_rate": 9.430247552150673e-05,
|
86 |
+
"loss": 1.7991,
|
87 |
+
"step": 50
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.5658362989323842,
|
91 |
+
"grad_norm": 0.33385950326919556,
|
92 |
+
"learning_rate": 9.22253005533154e-05,
|
93 |
+
"loss": 1.7761,
|
94 |
+
"step": 55
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 1.708185053380783,
|
98 |
+
"grad_norm": 0.3235575258731842,
|
99 |
+
"learning_rate": 8.985662536114613e-05,
|
100 |
+
"loss": 1.7781,
|
101 |
+
"step": 60
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.8505338078291815,
|
105 |
+
"grad_norm": 0.31781575083732605,
|
106 |
+
"learning_rate": 8.721280197423258e-05,
|
107 |
+
"loss": 1.7457,
|
108 |
+
"step": 65
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.99288256227758,
|
112 |
+
"grad_norm": 0.3225061297416687,
|
113 |
+
"learning_rate": 8.43120818934367e-05,
|
114 |
+
"loss": 1.7521,
|
115 |
+
"step": 70
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.99288256227758,
|
119 |
+
"eval_loss": 1.7631458044052124,
|
120 |
+
"eval_runtime": 2.707,
|
121 |
+
"eval_samples_per_second": 16.993,
|
122 |
+
"eval_steps_per_second": 16.993,
|
123 |
+
"step": 70
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.135231316725979,
|
127 |
+
"grad_norm": 0.3239762783050537,
|
128 |
+
"learning_rate": 8.117449009293668e-05,
|
129 |
+
"loss": 1.6471,
|
130 |
+
"step": 75
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 2.277580071174377,
|
134 |
+
"grad_norm": 0.348884642124176,
|
135 |
+
"learning_rate": 7.782168677883206e-05,
|
136 |
+
"loss": 1.7,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 2.419928825622776,
|
141 |
+
"grad_norm": 0.3774774372577667,
|
142 |
+
"learning_rate": 7.427681785900761e-05,
|
143 |
+
"loss": 1.7183,
|
144 |
+
"step": 85
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 2.562277580071174,
|
148 |
+
"grad_norm": 0.39107823371887207,
|
149 |
+
"learning_rate": 7.056435515653059e-05,
|
150 |
+
"loss": 1.6825,
|
151 |
+
"step": 90
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 2.704626334519573,
|
155 |
+
"grad_norm": 0.5160859823226929,
|
156 |
+
"learning_rate": 6.670992746965938e-05,
|
157 |
+
"loss": 1.664,
|
158 |
+
"step": 95
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.8469750889679717,
|
162 |
+
"grad_norm": 0.4094185531139374,
|
163 |
+
"learning_rate": 6.274014364473274e-05,
|
164 |
+
"loss": 1.6662,
|
165 |
+
"step": 100
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 2.9893238434163703,
|
169 |
+
"grad_norm": 0.4102707803249359,
|
170 |
+
"learning_rate": 5.868240888334653e-05,
|
171 |
+
"loss": 1.6831,
|
172 |
+
"step": 105
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 2.9893238434163703,
|
176 |
+
"eval_loss": 1.691434621810913,
|
177 |
+
"eval_runtime": 2.7669,
|
178 |
+
"eval_samples_per_second": 16.625,
|
179 |
+
"eval_steps_per_second": 16.625,
|
180 |
+
"step": 105
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 3.131672597864769,
|
184 |
+
"grad_norm": 0.41169798374176025,
|
185 |
+
"learning_rate": 5.456473555193242e-05,
|
186 |
+
"loss": 1.6085,
|
187 |
+
"step": 110
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 3.2740213523131674,
|
191 |
+
"grad_norm": 0.5937510132789612,
|
192 |
+
"learning_rate": 5.041554979980486e-05,
|
193 |
+
"loss": 1.6105,
|
194 |
+
"step": 115
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 3.416370106761566,
|
198 |
+
"grad_norm": 0.4580947160720825,
|
199 |
+
"learning_rate": 4.626349532067879e-05,
|
200 |
+
"loss": 1.6227,
|
201 |
+
"step": 120
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 3.5587188612099645,
|
205 |
+
"grad_norm": 0.4503268599510193,
|
206 |
+
"learning_rate": 4.213723561238074e-05,
|
207 |
+
"loss": 1.6202,
|
208 |
+
"step": 125
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 3.701067615658363,
|
212 |
+
"grad_norm": 0.5091418623924255,
|
213 |
+
"learning_rate": 3.806525609984312e-05,
|
214 |
+
"loss": 1.6178,
|
215 |
+
"step": 130
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 3.8434163701067616,
|
219 |
+
"grad_norm": 0.5050191283226013,
|
220 |
+
"learning_rate": 3.4075667487415785e-05,
|
221 |
+
"loss": 1.6023,
|
222 |
+
"step": 135
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 3.98576512455516,
|
226 |
+
"grad_norm": 0.502037525177002,
|
227 |
+
"learning_rate": 3.019601169804216e-05,
|
228 |
+
"loss": 1.5566,
|
229 |
+
"step": 140
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 3.98576512455516,
|
233 |
+
"eval_loss": 1.6648945808410645,
|
234 |
+
"eval_runtime": 2.7182,
|
235 |
+
"eval_samples_per_second": 16.923,
|
236 |
+
"eval_steps_per_second": 16.923,
|
237 |
+
"step": 140
|
238 |
+
}
|
239 |
+
],
|
240 |
+
"logging_steps": 5,
|
241 |
+
"max_steps": 210,
|
242 |
+
"num_input_tokens_seen": 0,
|
243 |
+
"num_train_epochs": 6,
|
244 |
+
"save_steps": 35,
|
245 |
+
"stateful_callbacks": {
|
246 |
+
"TrainerControl": {
|
247 |
+
"args": {
|
248 |
+
"should_epoch_stop": false,
|
249 |
+
"should_evaluate": false,
|
250 |
+
"should_log": false,
|
251 |
+
"should_save": true,
|
252 |
+
"should_training_stop": false
|
253 |
+
},
|
254 |
+
"attributes": {}
|
255 |
+
}
|
256 |
+
},
|
257 |
+
"total_flos": 1.1700499098451968e+17,
|
258 |
+
"train_batch_size": 16,
|
259 |
+
"trial_name": null,
|
260 |
+
"trial_params": null
|
261 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-140/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2bc05afc45cc2260e917f0e545fdbc53c8c1a9def7f26bb3cc9459a74257487
|
3 |
+
size 5368
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3.5-mini-instruct
|
3 |
+
library_name: peft
|
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
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
|
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": 0.0,
|
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 |
+
"qkv_proj",
|
24 |
+
"down_proj",
|
25 |
+
"gate_up_proj",
|
26 |
+
"o_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f40ed6cbfc252c788230cd22d274978577d1ac65c5118e3a032380cd4c7cb592
|
3 |
+
size 50365768
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22b824711115ea3cae98bd98854e2c2767ee4ed6906fd914f876eeaf397b7971
|
3 |
+
size 100878458
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
|
3 |
+
size 14244
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:069778854988beebfb3f91f36fc6b48d3790c61557f2d344cec2869edb6cb5d9
|
3 |
+
size 1064
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/tokenizer_config.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
|
121 |
+
"clean_up_tokenization_spaces": false,
|
122 |
+
"eos_token": "<|end|>",
|
123 |
+
"legacy": false,
|
124 |
+
"model_max_length": 131072,
|
125 |
+
"pad_token": "<|endoftext|>",
|
126 |
+
"padding_side": "right",
|
127 |
+
"sp_model_kwargs": {},
|
128 |
+
"split_special_tokens": false,
|
129 |
+
"tokenizer_class": "LlamaTokenizer",
|
130 |
+
"unk_token": "<unk>",
|
131 |
+
"use_default_system_prompt": false
|
132 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/trainer_state.json
ADDED
@@ -0,0 +1,318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.98220640569395,
|
5 |
+
"eval_steps": 35,
|
6 |
+
"global_step": 175,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.1423487544483986,
|
13 |
+
"grad_norm": 3.915436267852783,
|
14 |
+
"learning_rate": 2.380952380952381e-05,
|
15 |
+
"loss": 4.6057,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.2846975088967972,
|
20 |
+
"grad_norm": 4.926669597625732,
|
21 |
+
"learning_rate": 4.761904761904762e-05,
|
22 |
+
"loss": 4.3259,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.42704626334519574,
|
27 |
+
"grad_norm": 3.071687936782837,
|
28 |
+
"learning_rate": 7.142857142857143e-05,
|
29 |
+
"loss": 3.5782,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.5693950177935944,
|
34 |
+
"grad_norm": 1.5628787279129028,
|
35 |
+
"learning_rate": 9.523809523809524e-05,
|
36 |
+
"loss": 2.542,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.7117437722419929,
|
41 |
+
"grad_norm": 0.6052073240280151,
|
42 |
+
"learning_rate": 9.988952191691925e-05,
|
43 |
+
"loss": 2.0288,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.8540925266903915,
|
48 |
+
"grad_norm": 0.4768967032432556,
|
49 |
+
"learning_rate": 9.944154131125642e-05,
|
50 |
+
"loss": 1.9283,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.99644128113879,
|
55 |
+
"grad_norm": 0.3471652865409851,
|
56 |
+
"learning_rate": 9.865224352899119e-05,
|
57 |
+
"loss": 1.9221,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.99644128113879,
|
62 |
+
"eval_loss": 1.9122635126113892,
|
63 |
+
"eval_runtime": 2.7209,
|
64 |
+
"eval_samples_per_second": 16.906,
|
65 |
+
"eval_steps_per_second": 16.906,
|
66 |
+
"step": 35
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.1387900355871885,
|
70 |
+
"grad_norm": 0.3238619863986969,
|
71 |
+
"learning_rate": 9.752707744739145e-05,
|
72 |
+
"loss": 1.8485,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 1.281138790035587,
|
77 |
+
"grad_norm": 0.3222252130508423,
|
78 |
+
"learning_rate": 9.607381059352038e-05,
|
79 |
+
"loss": 1.8223,
|
80 |
+
"step": 45
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.4234875444839858,
|
84 |
+
"grad_norm": 0.30783718824386597,
|
85 |
+
"learning_rate": 9.430247552150673e-05,
|
86 |
+
"loss": 1.7991,
|
87 |
+
"step": 50
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.5658362989323842,
|
91 |
+
"grad_norm": 0.33385950326919556,
|
92 |
+
"learning_rate": 9.22253005533154e-05,
|
93 |
+
"loss": 1.7761,
|
94 |
+
"step": 55
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 1.708185053380783,
|
98 |
+
"grad_norm": 0.3235575258731842,
|
99 |
+
"learning_rate": 8.985662536114613e-05,
|
100 |
+
"loss": 1.7781,
|
101 |
+
"step": 60
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.8505338078291815,
|
105 |
+
"grad_norm": 0.31781575083732605,
|
106 |
+
"learning_rate": 8.721280197423258e-05,
|
107 |
+
"loss": 1.7457,
|
108 |
+
"step": 65
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.99288256227758,
|
112 |
+
"grad_norm": 0.3225061297416687,
|
113 |
+
"learning_rate": 8.43120818934367e-05,
|
114 |
+
"loss": 1.7521,
|
115 |
+
"step": 70
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.99288256227758,
|
119 |
+
"eval_loss": 1.7631458044052124,
|
120 |
+
"eval_runtime": 2.707,
|
121 |
+
"eval_samples_per_second": 16.993,
|
122 |
+
"eval_steps_per_second": 16.993,
|
123 |
+
"step": 70
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.135231316725979,
|
127 |
+
"grad_norm": 0.3239762783050537,
|
128 |
+
"learning_rate": 8.117449009293668e-05,
|
129 |
+
"loss": 1.6471,
|
130 |
+
"step": 75
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 2.277580071174377,
|
134 |
+
"grad_norm": 0.348884642124176,
|
135 |
+
"learning_rate": 7.782168677883206e-05,
|
136 |
+
"loss": 1.7,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 2.419928825622776,
|
141 |
+
"grad_norm": 0.3774774372577667,
|
142 |
+
"learning_rate": 7.427681785900761e-05,
|
143 |
+
"loss": 1.7183,
|
144 |
+
"step": 85
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 2.562277580071174,
|
148 |
+
"grad_norm": 0.39107823371887207,
|
149 |
+
"learning_rate": 7.056435515653059e-05,
|
150 |
+
"loss": 1.6825,
|
151 |
+
"step": 90
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 2.704626334519573,
|
155 |
+
"grad_norm": 0.5160859823226929,
|
156 |
+
"learning_rate": 6.670992746965938e-05,
|
157 |
+
"loss": 1.664,
|
158 |
+
"step": 95
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.8469750889679717,
|
162 |
+
"grad_norm": 0.4094185531139374,
|
163 |
+
"learning_rate": 6.274014364473274e-05,
|
164 |
+
"loss": 1.6662,
|
165 |
+
"step": 100
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 2.9893238434163703,
|
169 |
+
"grad_norm": 0.4102707803249359,
|
170 |
+
"learning_rate": 5.868240888334653e-05,
|
171 |
+
"loss": 1.6831,
|
172 |
+
"step": 105
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 2.9893238434163703,
|
176 |
+
"eval_loss": 1.691434621810913,
|
177 |
+
"eval_runtime": 2.7669,
|
178 |
+
"eval_samples_per_second": 16.625,
|
179 |
+
"eval_steps_per_second": 16.625,
|
180 |
+
"step": 105
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 3.131672597864769,
|
184 |
+
"grad_norm": 0.41169798374176025,
|
185 |
+
"learning_rate": 5.456473555193242e-05,
|
186 |
+
"loss": 1.6085,
|
187 |
+
"step": 110
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 3.2740213523131674,
|
191 |
+
"grad_norm": 0.5937510132789612,
|
192 |
+
"learning_rate": 5.041554979980486e-05,
|
193 |
+
"loss": 1.6105,
|
194 |
+
"step": 115
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 3.416370106761566,
|
198 |
+
"grad_norm": 0.4580947160720825,
|
199 |
+
"learning_rate": 4.626349532067879e-05,
|
200 |
+
"loss": 1.6227,
|
201 |
+
"step": 120
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 3.5587188612099645,
|
205 |
+
"grad_norm": 0.4503268599510193,
|
206 |
+
"learning_rate": 4.213723561238074e-05,
|
207 |
+
"loss": 1.6202,
|
208 |
+
"step": 125
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 3.701067615658363,
|
212 |
+
"grad_norm": 0.5091418623924255,
|
213 |
+
"learning_rate": 3.806525609984312e-05,
|
214 |
+
"loss": 1.6178,
|
215 |
+
"step": 130
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 3.8434163701067616,
|
219 |
+
"grad_norm": 0.5050191283226013,
|
220 |
+
"learning_rate": 3.4075667487415785e-05,
|
221 |
+
"loss": 1.6023,
|
222 |
+
"step": 135
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 3.98576512455516,
|
226 |
+
"grad_norm": 0.502037525177002,
|
227 |
+
"learning_rate": 3.019601169804216e-05,
|
228 |
+
"loss": 1.5566,
|
229 |
+
"step": 140
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 3.98576512455516,
|
233 |
+
"eval_loss": 1.6648945808410645,
|
234 |
+
"eval_runtime": 2.7182,
|
235 |
+
"eval_samples_per_second": 16.923,
|
236 |
+
"eval_steps_per_second": 16.923,
|
237 |
+
"step": 140
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 4.128113879003559,
|
241 |
+
"grad_norm": 0.4845784604549408,
|
242 |
+
"learning_rate": 2.645307173898901e-05,
|
243 |
+
"loss": 1.5459,
|
244 |
+
"step": 145
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 4.270462633451958,
|
248 |
+
"grad_norm": 0.4947628378868103,
|
249 |
+
"learning_rate": 2.2872686806712035e-05,
|
250 |
+
"loss": 1.5934,
|
251 |
+
"step": 150
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 4.412811387900356,
|
255 |
+
"grad_norm": 0.5146717429161072,
|
256 |
+
"learning_rate": 1.947957390727185e-05,
|
257 |
+
"loss": 1.543,
|
258 |
+
"step": 155
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 4.555160142348754,
|
262 |
+
"grad_norm": 0.4881040155887604,
|
263 |
+
"learning_rate": 1.629715722373423e-05,
|
264 |
+
"loss": 1.568,
|
265 |
+
"step": 160
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 4.697508896797153,
|
269 |
+
"grad_norm": 0.514570951461792,
|
270 |
+
"learning_rate": 1.3347406408508695e-05,
|
271 |
+
"loss": 1.5337,
|
272 |
+
"step": 165
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 4.839857651245552,
|
276 |
+
"grad_norm": 0.5478077530860901,
|
277 |
+
"learning_rate": 1.0650684916965559e-05,
|
278 |
+
"loss": 1.5442,
|
279 |
+
"step": 170
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 4.98220640569395,
|
283 |
+
"grad_norm": 0.47540614008903503,
|
284 |
+
"learning_rate": 8.225609429353187e-06,
|
285 |
+
"loss": 1.562,
|
286 |
+
"step": 175
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 4.98220640569395,
|
290 |
+
"eval_loss": 1.6638323068618774,
|
291 |
+
"eval_runtime": 2.7058,
|
292 |
+
"eval_samples_per_second": 17.001,
|
293 |
+
"eval_steps_per_second": 17.001,
|
294 |
+
"step": 175
|
295 |
+
}
|
296 |
+
],
|
297 |
+
"logging_steps": 5,
|
298 |
+
"max_steps": 210,
|
299 |
+
"num_input_tokens_seen": 0,
|
300 |
+
"num_train_epochs": 6,
|
301 |
+
"save_steps": 35,
|
302 |
+
"stateful_callbacks": {
|
303 |
+
"TrainerControl": {
|
304 |
+
"args": {
|
305 |
+
"should_epoch_stop": false,
|
306 |
+
"should_evaluate": false,
|
307 |
+
"should_log": false,
|
308 |
+
"should_save": true,
|
309 |
+
"should_training_stop": false
|
310 |
+
},
|
311 |
+
"attributes": {}
|
312 |
+
}
|
313 |
+
},
|
314 |
+
"total_flos": 1.4619841842511872e+17,
|
315 |
+
"train_batch_size": 16,
|
316 |
+
"trial_name": null,
|
317 |
+
"trial_params": null
|
318 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-175/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2bc05afc45cc2260e917f0e545fdbc53c8c1a9def7f26bb3cc9459a74257487
|
3 |
+
size 5368
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3.5-mini-instruct
|
3 |
+
library_name: peft
|
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
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
|
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": 0.0,
|
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 |
+
"qkv_proj",
|
24 |
+
"down_proj",
|
25 |
+
"gate_up_proj",
|
26 |
+
"o_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2fef064b69976e06a1f7d030039fda5b1893feb02f1d92877cfa71069226acb
|
3 |
+
size 50365768
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca02a94b921baf8ee6e3a2a6d2080baa2cc64f8ef4c23f8b8051086eefc02da4
|
3 |
+
size 100878458
|
llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3e5d946241df2516b06d7074d8779088eae7607173ad780df56583910a9589b
|
3 |
+
size 14244
|