Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .ipynb_checkpoints/training_summary_ec2-checkpoint.json +19 -0
- README.md +62 -0
- adapter_config.json +43 -0
- adapter_model.safetensors +3 -0
- checkpoint-1000/README.md +209 -0
- checkpoint-1000/adapter_config.json +43 -0
- checkpoint-1000/adapter_model.safetensors +3 -0
- checkpoint-1000/merges.txt +0 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +63 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +357 -0
- checkpoint-1000/trainer_state.json +234 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1000/vocab.json +0 -0
- checkpoint-1500/README.md +209 -0
- checkpoint-1500/adapter_config.json +43 -0
- checkpoint-1500/adapter_model.safetensors +3 -0
- checkpoint-1500/merges.txt +0 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/special_tokens_map.json +63 -0
- checkpoint-1500/tokenizer.json +0 -0
- checkpoint-1500/tokenizer_config.json +357 -0
- checkpoint-1500/trainer_state.json +334 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-1500/vocab.json +0 -0
- checkpoint-2000/README.md +209 -0
- checkpoint-2000/adapter_config.json +43 -0
- checkpoint-2000/adapter_model.safetensors +3 -0
- checkpoint-2000/merges.txt +0 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/special_tokens_map.json +63 -0
- checkpoint-2000/tokenizer.json +0 -0
- checkpoint-2000/tokenizer_config.json +357 -0
- checkpoint-2000/trainer_state.json +434 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2000/vocab.json +0 -0
- checkpoint-2025/README.md +209 -0
- checkpoint-2025/adapter_config.json +43 -0
- checkpoint-2025/adapter_model.safetensors +3 -0
- checkpoint-2025/merges.txt +0 -0
- checkpoint-2025/optimizer.pt +3 -0
- checkpoint-2025/rng_state.pth +3 -0
- checkpoint-2025/scheduler.pt +3 -0
.ipynb_checkpoints/training_summary_ec2-checkpoint.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"service": "EC2",
|
| 3 |
+
"epochs": 3.0,
|
| 4 |
+
"global_step": 2025,
|
| 5 |
+
"train_runtime_sec": 8838.922579288483,
|
| 6 |
+
"train_samples": 5400,
|
| 7 |
+
"eval_samples": 600,
|
| 8 |
+
"used_bitsandbytes": false,
|
| 9 |
+
"eval_metrics": {
|
| 10 |
+
"eval_loss": 0.29000768065452576,
|
| 11 |
+
"eval_runtime": 108.2382,
|
| 12 |
+
"eval_samples_per_second": 5.543,
|
| 13 |
+
"eval_steps_per_second": 0.693,
|
| 14 |
+
"eval_entropy": 0.2899935628970464,
|
| 15 |
+
"eval_num_tokens": 13708374.0,
|
| 16 |
+
"eval_mean_token_accuracy": 0.9388597853978475,
|
| 17 |
+
"epoch": 3.0
|
| 18 |
+
}
|
| 19 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: bigcode/starcoder2-7b
|
| 3 |
+
library_name: peft
|
| 4 |
+
model_name: starcoder2_7b_lora_ec2
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:bigcode/starcoder2-7b
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
licence: license
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Model Card for starcoder2_7b_lora_ec2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [bigcode/starcoder2-7b](https://huggingface.co/bigcode/starcoder2-7b).
|
| 18 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 19 |
+
|
| 20 |
+
## Quick start
|
| 21 |
+
|
| 22 |
+
```python
|
| 23 |
+
from transformers import pipeline
|
| 24 |
+
|
| 25 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 26 |
+
generator = pipeline("text-generation", model="None", device="cuda")
|
| 27 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 28 |
+
print(output["generated_text"])
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
This model was trained with SFT.
|
| 37 |
+
|
| 38 |
+
### Framework versions
|
| 39 |
+
|
| 40 |
+
- PEFT 0.18.0
|
| 41 |
+
- TRL: 0.25.1
|
| 42 |
+
- Transformers: 4.57.3
|
| 43 |
+
- Pytorch: 2.8.0+cu128
|
| 44 |
+
- Datasets: 4.4.1
|
| 45 |
+
- Tokenizers: 0.22.1
|
| 46 |
+
|
| 47 |
+
## Citations
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
Cite TRL as:
|
| 52 |
+
|
| 53 |
+
```bibtex
|
| 54 |
+
@misc{vonwerra2022trl,
|
| 55 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 56 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 57 |
+
year = 2020,
|
| 58 |
+
journal = {GitHub repository},
|
| 59 |
+
publisher = {GitHub},
|
| 60 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 61 |
+
}
|
| 62 |
+
```
|
adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "bigcode/starcoder2-7b",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"k_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"q_proj"
|
| 36 |
+
],
|
| 37 |
+
"target_parameters": null,
|
| 38 |
+
"task_type": "CAUSAL_LM",
|
| 39 |
+
"trainable_token_indices": null,
|
| 40 |
+
"use_dora": false,
|
| 41 |
+
"use_qalora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f985b682a578eb8d853bbb5012434e8f2ed20a33906fcbd221cb634671f07b5e
|
| 3 |
+
size 58754616
|
checkpoint-1000/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: bigcode/starcoder2-7b
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:bigcode/starcoder2-7b
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- 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. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
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).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.0
|
checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "bigcode/starcoder2-7b",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"k_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"q_proj"
|
| 36 |
+
],
|
| 37 |
+
"target_parameters": null,
|
| 38 |
+
"task_type": "CAUSAL_LM",
|
| 39 |
+
"trainable_token_indices": null,
|
| 40 |
+
"use_dora": false,
|
| 41 |
+
"use_qalora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
checkpoint-1000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d03d7495e3c657f786642f12669054bf54248f75769c0143cbc2c33335074f9d
|
| 3 |
+
size 58754616
|
checkpoint-1000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d1374ee5c2ba5ff932f024b695308e888121e12a07d067bfed9acf840df33e7
|
| 3 |
+
size 117660107
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a029439c1c9c9034f11e1f38859a8f5ffdc3e3a26f6f3fd114f62854e409ff92
|
| 3 |
+
size 14645
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b06201d9403a12d93447a0c39b7483b78fdd17e56d2db9cc8f99c3ba8cf744f1
|
| 3 |
+
size 1465
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<repo_name>",
|
| 9 |
+
"<file_sep>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<jupyter_script>",
|
| 18 |
+
"<empty_output>",
|
| 19 |
+
"<code_to_intermediate>",
|
| 20 |
+
"<intermediate_to_code>",
|
| 21 |
+
"<pr>",
|
| 22 |
+
"<pr_status>",
|
| 23 |
+
"<pr_is_merged>",
|
| 24 |
+
"<pr_base>",
|
| 25 |
+
"<pr_file>",
|
| 26 |
+
"<pr_base_code>",
|
| 27 |
+
"<pr_diff>",
|
| 28 |
+
"<pr_diff_hunk>",
|
| 29 |
+
"<pr_comment>",
|
| 30 |
+
"<pr_event_id>",
|
| 31 |
+
"<pr_review>",
|
| 32 |
+
"<pr_review_state>",
|
| 33 |
+
"<pr_review_comment>",
|
| 34 |
+
"<pr_in_reply_to_review_id>",
|
| 35 |
+
"<pr_in_reply_to_comment_id>",
|
| 36 |
+
"<pr_diff_hunk_comment_line>",
|
| 37 |
+
"<NAME>",
|
| 38 |
+
"<EMAIL>",
|
| 39 |
+
"<KEY>",
|
| 40 |
+
"<PASSWORD>"
|
| 41 |
+
],
|
| 42 |
+
"bos_token": {
|
| 43 |
+
"content": "<|endoftext|>",
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false
|
| 48 |
+
},
|
| 49 |
+
"eos_token": {
|
| 50 |
+
"content": "<|endoftext|>",
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"normalized": false,
|
| 53 |
+
"rstrip": false,
|
| 54 |
+
"single_word": false
|
| 55 |
+
},
|
| 56 |
+
"unk_token": {
|
| 57 |
+
"content": "<|endoftext|>",
|
| 58 |
+
"lstrip": false,
|
| 59 |
+
"normalized": false,
|
| 60 |
+
"rstrip": false,
|
| 61 |
+
"single_word": false
|
| 62 |
+
}
|
| 63 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<repo_name>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<file_sep>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_script>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<empty_output>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<code_to_intermediate>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<intermediate_to_code>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<pr>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"19": {
|
| 157 |
+
"content": "<pr_status>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"20": {
|
| 165 |
+
"content": "<pr_is_merged>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"21": {
|
| 173 |
+
"content": "<pr_base>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"22": {
|
| 181 |
+
"content": "<pr_file>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"23": {
|
| 189 |
+
"content": "<pr_base_code>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"24": {
|
| 197 |
+
"content": "<pr_diff>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"25": {
|
| 205 |
+
"content": "<pr_diff_hunk>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"26": {
|
| 213 |
+
"content": "<pr_comment>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"27": {
|
| 221 |
+
"content": "<pr_event_id>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"28": {
|
| 229 |
+
"content": "<pr_review>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"29": {
|
| 237 |
+
"content": "<pr_review_state>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"30": {
|
| 245 |
+
"content": "<pr_review_comment>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"31": {
|
| 253 |
+
"content": "<pr_in_reply_to_review_id>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32": {
|
| 261 |
+
"content": "<pr_in_reply_to_comment_id>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"33": {
|
| 269 |
+
"content": "<pr_diff_hunk_comment_line>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"34": {
|
| 277 |
+
"content": "<NAME>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"35": {
|
| 285 |
+
"content": "<EMAIL>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"36": {
|
| 293 |
+
"content": "<KEY>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"37": {
|
| 301 |
+
"content": "<PASSWORD>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
}
|
| 308 |
+
},
|
| 309 |
+
"additional_special_tokens": [
|
| 310 |
+
"<|endoftext|>",
|
| 311 |
+
"<fim_prefix>",
|
| 312 |
+
"<fim_middle>",
|
| 313 |
+
"<fim_suffix>",
|
| 314 |
+
"<fim_pad>",
|
| 315 |
+
"<repo_name>",
|
| 316 |
+
"<file_sep>",
|
| 317 |
+
"<issue_start>",
|
| 318 |
+
"<issue_comment>",
|
| 319 |
+
"<issue_closed>",
|
| 320 |
+
"<jupyter_start>",
|
| 321 |
+
"<jupyter_text>",
|
| 322 |
+
"<jupyter_code>",
|
| 323 |
+
"<jupyter_output>",
|
| 324 |
+
"<jupyter_script>",
|
| 325 |
+
"<empty_output>",
|
| 326 |
+
"<code_to_intermediate>",
|
| 327 |
+
"<intermediate_to_code>",
|
| 328 |
+
"<pr>",
|
| 329 |
+
"<pr_status>",
|
| 330 |
+
"<pr_is_merged>",
|
| 331 |
+
"<pr_base>",
|
| 332 |
+
"<pr_file>",
|
| 333 |
+
"<pr_base_code>",
|
| 334 |
+
"<pr_diff>",
|
| 335 |
+
"<pr_diff_hunk>",
|
| 336 |
+
"<pr_comment>",
|
| 337 |
+
"<pr_event_id>",
|
| 338 |
+
"<pr_review>",
|
| 339 |
+
"<pr_review_state>",
|
| 340 |
+
"<pr_review_comment>",
|
| 341 |
+
"<pr_in_reply_to_review_id>",
|
| 342 |
+
"<pr_in_reply_to_comment_id>",
|
| 343 |
+
"<pr_diff_hunk_comment_line>",
|
| 344 |
+
"<NAME>",
|
| 345 |
+
"<EMAIL>",
|
| 346 |
+
"<KEY>",
|
| 347 |
+
"<PASSWORD>"
|
| 348 |
+
],
|
| 349 |
+
"bos_token": "<|endoftext|>",
|
| 350 |
+
"clean_up_tokenization_spaces": true,
|
| 351 |
+
"eos_token": "<|endoftext|>",
|
| 352 |
+
"extra_special_tokens": {},
|
| 353 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 354 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 355 |
+
"unk_token": "<|endoftext|>",
|
| 356 |
+
"vocab_size": 49152
|
| 357 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.4814814814814814,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 2.1715362322330476,
|
| 14 |
+
"epoch": 0.07407407407407407,
|
| 15 |
+
"grad_norm": 1.0598933696746826,
|
| 16 |
+
"learning_rate": 8.032786885245902e-05,
|
| 17 |
+
"loss": 2.0077,
|
| 18 |
+
"mean_token_accuracy": 0.5798640113323927,
|
| 19 |
+
"num_tokens": 338396.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.6553284931182861,
|
| 24 |
+
"epoch": 0.14814814814814814,
|
| 25 |
+
"grad_norm": 0.3852575719356537,
|
| 26 |
+
"learning_rate": 9.990765991730485e-05,
|
| 27 |
+
"loss": 0.5993,
|
| 28 |
+
"mean_token_accuracy": 0.8612996307015419,
|
| 29 |
+
"num_tokens": 677239.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.4204328820481896,
|
| 34 |
+
"epoch": 0.2222222222222222,
|
| 35 |
+
"grad_norm": 0.2863098680973053,
|
| 36 |
+
"learning_rate": 9.950545603782162e-05,
|
| 37 |
+
"loss": 0.4172,
|
| 38 |
+
"mean_token_accuracy": 0.9052096186578273,
|
| 39 |
+
"num_tokens": 1015420.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.3820256270095706,
|
| 44 |
+
"epoch": 0.2962962962962963,
|
| 45 |
+
"grad_norm": 0.2698630690574646,
|
| 46 |
+
"learning_rate": 9.878674879048427e-05,
|
| 47 |
+
"loss": 0.383,
|
| 48 |
+
"mean_token_accuracy": 0.9129502369463444,
|
| 49 |
+
"num_tokens": 1355048.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.37178467601537707,
|
| 54 |
+
"epoch": 0.37037037037037035,
|
| 55 |
+
"grad_norm": 0.21257849037647247,
|
| 56 |
+
"learning_rate": 9.775613308830824e-05,
|
| 57 |
+
"loss": 0.37,
|
| 58 |
+
"mean_token_accuracy": 0.9151540066301823,
|
| 59 |
+
"num_tokens": 1691649.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.36766253888607026,
|
| 64 |
+
"epoch": 0.4444444444444444,
|
| 65 |
+
"grad_norm": 0.31453582644462585,
|
| 66 |
+
"learning_rate": 9.642019796948866e-05,
|
| 67 |
+
"loss": 0.3634,
|
| 68 |
+
"mean_token_accuracy": 0.9162409096956253,
|
| 69 |
+
"num_tokens": 2029267.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.35622088231146337,
|
| 74 |
+
"epoch": 0.5185185185185185,
|
| 75 |
+
"grad_norm": 0.20113833248615265,
|
| 76 |
+
"learning_rate": 9.478748447168449e-05,
|
| 77 |
+
"loss": 0.3533,
|
| 78 |
+
"mean_token_accuracy": 0.9183417546749115,
|
| 79 |
+
"num_tokens": 2369465.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.3494216964393854,
|
| 84 |
+
"epoch": 0.5925925925925926,
|
| 85 |
+
"grad_norm": 0.20226770639419556,
|
| 86 |
+
"learning_rate": 9.28684310265789e-05,
|
| 87 |
+
"loss": 0.3492,
|
| 88 |
+
"mean_token_accuracy": 0.919527986496687,
|
| 89 |
+
"num_tokens": 2707235.0,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 0.3433630639687181,
|
| 94 |
+
"epoch": 0.6666666666666666,
|
| 95 |
+
"grad_norm": 0.1721702516078949,
|
| 96 |
+
"learning_rate": 9.067530672382544e-05,
|
| 97 |
+
"loss": 0.3453,
|
| 98 |
+
"mean_token_accuracy": 0.9204271128773689,
|
| 99 |
+
"num_tokens": 3041282.0,
|
| 100 |
+
"step": 450
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 0.3465565311536193,
|
| 104 |
+
"epoch": 0.7407407407407407,
|
| 105 |
+
"grad_norm": 0.1957043558359146,
|
| 106 |
+
"learning_rate": 8.822213287104348e-05,
|
| 107 |
+
"loss": 0.3483,
|
| 108 |
+
"mean_token_accuracy": 0.9200405342876912,
|
| 109 |
+
"num_tokens": 3378157.0,
|
| 110 |
+
"step": 500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 0.34500927191227676,
|
| 114 |
+
"epoch": 0.8148148148148148,
|
| 115 |
+
"grad_norm": 0.1682814359664917,
|
| 116 |
+
"learning_rate": 8.552459335135381e-05,
|
| 117 |
+
"loss": 0.3466,
|
| 118 |
+
"mean_token_accuracy": 0.9210821086168289,
|
| 119 |
+
"num_tokens": 3717487.0,
|
| 120 |
+
"step": 550
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 0.33874930143356324,
|
| 124 |
+
"epoch": 0.8888888888888888,
|
| 125 |
+
"grad_norm": 0.1756315678358078,
|
| 126 |
+
"learning_rate": 8.259993435156559e-05,
|
| 127 |
+
"loss": 0.3406,
|
| 128 |
+
"mean_token_accuracy": 0.9231470887362957,
|
| 129 |
+
"num_tokens": 4056814.0,
|
| 130 |
+
"step": 600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 0.3372995613142848,
|
| 134 |
+
"epoch": 0.9629629629629629,
|
| 135 |
+
"grad_norm": 0.185526043176651,
|
| 136 |
+
"learning_rate": 7.946685410208296e-05,
|
| 137 |
+
"loss": 0.3378,
|
| 138 |
+
"mean_token_accuracy": 0.924960307776928,
|
| 139 |
+
"num_tokens": 4398736.0,
|
| 140 |
+
"step": 650
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 0.3282011279836297,
|
| 144 |
+
"epoch": 1.037037037037037,
|
| 145 |
+
"grad_norm": 0.23889201879501343,
|
| 146 |
+
"learning_rate": 7.614538333345735e-05,
|
| 147 |
+
"loss": 0.3293,
|
| 148 |
+
"mean_token_accuracy": 0.9266741496324539,
|
| 149 |
+
"num_tokens": 4737915.0,
|
| 150 |
+
"step": 700
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 0.32703890234231947,
|
| 154 |
+
"epoch": 1.1111111111111112,
|
| 155 |
+
"grad_norm": 0.21601562201976776,
|
| 156 |
+
"learning_rate": 7.265675721386285e-05,
|
| 157 |
+
"loss": 0.3275,
|
| 158 |
+
"mean_token_accuracy": 0.9279554469883442,
|
| 159 |
+
"num_tokens": 5074721.0,
|
| 160 |
+
"step": 750
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 0.3243879374489188,
|
| 164 |
+
"epoch": 1.1851851851851851,
|
| 165 |
+
"grad_norm": 0.22092069685459137,
|
| 166 |
+
"learning_rate": 6.902327958623736e-05,
|
| 167 |
+
"loss": 0.3244,
|
| 168 |
+
"mean_token_accuracy": 0.9288445146381855,
|
| 169 |
+
"num_tokens": 5413515.0,
|
| 170 |
+
"step": 800
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 0.3191816185042262,
|
| 174 |
+
"epoch": 1.2592592592592593,
|
| 175 |
+
"grad_norm": 0.2003597766160965,
|
| 176 |
+
"learning_rate": 6.526818037306228e-05,
|
| 177 |
+
"loss": 0.3197,
|
| 178 |
+
"mean_token_accuracy": 0.9303379128873348,
|
| 179 |
+
"num_tokens": 5751965.0,
|
| 180 |
+
"step": 850
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 0.311707403101027,
|
| 184 |
+
"epoch": 1.3333333333333333,
|
| 185 |
+
"grad_norm": 0.1664246916770935,
|
| 186 |
+
"learning_rate": 6.14154670604355e-05,
|
| 187 |
+
"loss": 0.3122,
|
| 188 |
+
"mean_token_accuracy": 0.9324613013863563,
|
| 189 |
+
"num_tokens": 6087993.0,
|
| 190 |
+
"step": 900
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 0.31203486569225786,
|
| 194 |
+
"epoch": 1.4074074074074074,
|
| 195 |
+
"grad_norm": 0.25155216455459595,
|
| 196 |
+
"learning_rate": 5.7489771210944564e-05,
|
| 197 |
+
"loss": 0.3129,
|
| 198 |
+
"mean_token_accuracy": 0.932486515045166,
|
| 199 |
+
"num_tokens": 6425349.0,
|
| 200 |
+
"step": 950
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 0.31312834514304994,
|
| 204 |
+
"epoch": 1.4814814814814814,
|
| 205 |
+
"grad_norm": 0.2299806922674179,
|
| 206 |
+
"learning_rate": 5.351619098663021e-05,
|
| 207 |
+
"loss": 0.3139,
|
| 208 |
+
"mean_token_accuracy": 0.9324578355252743,
|
| 209 |
+
"num_tokens": 6762060.0,
|
| 210 |
+
"step": 1000
|
| 211 |
+
}
|
| 212 |
+
],
|
| 213 |
+
"logging_steps": 50,
|
| 214 |
+
"max_steps": 2025,
|
| 215 |
+
"num_input_tokens_seen": 0,
|
| 216 |
+
"num_train_epochs": 3,
|
| 217 |
+
"save_steps": 500,
|
| 218 |
+
"stateful_callbacks": {
|
| 219 |
+
"TrainerControl": {
|
| 220 |
+
"args": {
|
| 221 |
+
"should_epoch_stop": false,
|
| 222 |
+
"should_evaluate": false,
|
| 223 |
+
"should_log": false,
|
| 224 |
+
"should_save": true,
|
| 225 |
+
"should_training_stop": false
|
| 226 |
+
},
|
| 227 |
+
"attributes": {}
|
| 228 |
+
}
|
| 229 |
+
},
|
| 230 |
+
"total_flos": 2.8246929365127168e+17,
|
| 231 |
+
"train_batch_size": 1,
|
| 232 |
+
"trial_name": null,
|
| 233 |
+
"trial_params": null
|
| 234 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a4e34ab1ebeeacb30334aa618143874612a2eac847c74484d639038e6305203
|
| 3 |
+
size 6225
|
checkpoint-1000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: bigcode/starcoder2-7b
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:bigcode/starcoder2-7b
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- 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. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
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).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.0
|
checkpoint-1500/adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "bigcode/starcoder2-7b",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"k_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"q_proj"
|
| 36 |
+
],
|
| 37 |
+
"target_parameters": null,
|
| 38 |
+
"task_type": "CAUSAL_LM",
|
| 39 |
+
"trainable_token_indices": null,
|
| 40 |
+
"use_dora": false,
|
| 41 |
+
"use_qalora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
checkpoint-1500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90c71d76ced989b2b3abc367bbbcc38a4ce46baa1fb2f8af03293c6984afabe6
|
| 3 |
+
size 58754616
|
checkpoint-1500/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36318a7d884fcd5cb82c5442f31d4f0cf4b90c21262855d18ef9304b4a549863
|
| 3 |
+
size 117660107
|
checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4124994b520f3934f9e61682aa919fef010e8ad1122744cdfb9b25dca04fa20c
|
| 3 |
+
size 14645
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b10d09adf0489af5dc688ca572941043ef06e06d7551388176d2e6574474a5a
|
| 3 |
+
size 1465
|
checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<repo_name>",
|
| 9 |
+
"<file_sep>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<jupyter_script>",
|
| 18 |
+
"<empty_output>",
|
| 19 |
+
"<code_to_intermediate>",
|
| 20 |
+
"<intermediate_to_code>",
|
| 21 |
+
"<pr>",
|
| 22 |
+
"<pr_status>",
|
| 23 |
+
"<pr_is_merged>",
|
| 24 |
+
"<pr_base>",
|
| 25 |
+
"<pr_file>",
|
| 26 |
+
"<pr_base_code>",
|
| 27 |
+
"<pr_diff>",
|
| 28 |
+
"<pr_diff_hunk>",
|
| 29 |
+
"<pr_comment>",
|
| 30 |
+
"<pr_event_id>",
|
| 31 |
+
"<pr_review>",
|
| 32 |
+
"<pr_review_state>",
|
| 33 |
+
"<pr_review_comment>",
|
| 34 |
+
"<pr_in_reply_to_review_id>",
|
| 35 |
+
"<pr_in_reply_to_comment_id>",
|
| 36 |
+
"<pr_diff_hunk_comment_line>",
|
| 37 |
+
"<NAME>",
|
| 38 |
+
"<EMAIL>",
|
| 39 |
+
"<KEY>",
|
| 40 |
+
"<PASSWORD>"
|
| 41 |
+
],
|
| 42 |
+
"bos_token": {
|
| 43 |
+
"content": "<|endoftext|>",
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false
|
| 48 |
+
},
|
| 49 |
+
"eos_token": {
|
| 50 |
+
"content": "<|endoftext|>",
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"normalized": false,
|
| 53 |
+
"rstrip": false,
|
| 54 |
+
"single_word": false
|
| 55 |
+
},
|
| 56 |
+
"unk_token": {
|
| 57 |
+
"content": "<|endoftext|>",
|
| 58 |
+
"lstrip": false,
|
| 59 |
+
"normalized": false,
|
| 60 |
+
"rstrip": false,
|
| 61 |
+
"single_word": false
|
| 62 |
+
}
|
| 63 |
+
}
|
checkpoint-1500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<repo_name>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<file_sep>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_script>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<empty_output>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<code_to_intermediate>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<intermediate_to_code>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<pr>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"19": {
|
| 157 |
+
"content": "<pr_status>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"20": {
|
| 165 |
+
"content": "<pr_is_merged>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"21": {
|
| 173 |
+
"content": "<pr_base>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"22": {
|
| 181 |
+
"content": "<pr_file>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"23": {
|
| 189 |
+
"content": "<pr_base_code>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"24": {
|
| 197 |
+
"content": "<pr_diff>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"25": {
|
| 205 |
+
"content": "<pr_diff_hunk>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"26": {
|
| 213 |
+
"content": "<pr_comment>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"27": {
|
| 221 |
+
"content": "<pr_event_id>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"28": {
|
| 229 |
+
"content": "<pr_review>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"29": {
|
| 237 |
+
"content": "<pr_review_state>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"30": {
|
| 245 |
+
"content": "<pr_review_comment>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"31": {
|
| 253 |
+
"content": "<pr_in_reply_to_review_id>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32": {
|
| 261 |
+
"content": "<pr_in_reply_to_comment_id>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"33": {
|
| 269 |
+
"content": "<pr_diff_hunk_comment_line>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"34": {
|
| 277 |
+
"content": "<NAME>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"35": {
|
| 285 |
+
"content": "<EMAIL>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"36": {
|
| 293 |
+
"content": "<KEY>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"37": {
|
| 301 |
+
"content": "<PASSWORD>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
}
|
| 308 |
+
},
|
| 309 |
+
"additional_special_tokens": [
|
| 310 |
+
"<|endoftext|>",
|
| 311 |
+
"<fim_prefix>",
|
| 312 |
+
"<fim_middle>",
|
| 313 |
+
"<fim_suffix>",
|
| 314 |
+
"<fim_pad>",
|
| 315 |
+
"<repo_name>",
|
| 316 |
+
"<file_sep>",
|
| 317 |
+
"<issue_start>",
|
| 318 |
+
"<issue_comment>",
|
| 319 |
+
"<issue_closed>",
|
| 320 |
+
"<jupyter_start>",
|
| 321 |
+
"<jupyter_text>",
|
| 322 |
+
"<jupyter_code>",
|
| 323 |
+
"<jupyter_output>",
|
| 324 |
+
"<jupyter_script>",
|
| 325 |
+
"<empty_output>",
|
| 326 |
+
"<code_to_intermediate>",
|
| 327 |
+
"<intermediate_to_code>",
|
| 328 |
+
"<pr>",
|
| 329 |
+
"<pr_status>",
|
| 330 |
+
"<pr_is_merged>",
|
| 331 |
+
"<pr_base>",
|
| 332 |
+
"<pr_file>",
|
| 333 |
+
"<pr_base_code>",
|
| 334 |
+
"<pr_diff>",
|
| 335 |
+
"<pr_diff_hunk>",
|
| 336 |
+
"<pr_comment>",
|
| 337 |
+
"<pr_event_id>",
|
| 338 |
+
"<pr_review>",
|
| 339 |
+
"<pr_review_state>",
|
| 340 |
+
"<pr_review_comment>",
|
| 341 |
+
"<pr_in_reply_to_review_id>",
|
| 342 |
+
"<pr_in_reply_to_comment_id>",
|
| 343 |
+
"<pr_diff_hunk_comment_line>",
|
| 344 |
+
"<NAME>",
|
| 345 |
+
"<EMAIL>",
|
| 346 |
+
"<KEY>",
|
| 347 |
+
"<PASSWORD>"
|
| 348 |
+
],
|
| 349 |
+
"bos_token": "<|endoftext|>",
|
| 350 |
+
"clean_up_tokenization_spaces": true,
|
| 351 |
+
"eos_token": "<|endoftext|>",
|
| 352 |
+
"extra_special_tokens": {},
|
| 353 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 354 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 355 |
+
"unk_token": "<|endoftext|>",
|
| 356 |
+
"vocab_size": 49152
|
| 357 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.2222222222222223,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 2.1715362322330476,
|
| 14 |
+
"epoch": 0.07407407407407407,
|
| 15 |
+
"grad_norm": 1.0598933696746826,
|
| 16 |
+
"learning_rate": 8.032786885245902e-05,
|
| 17 |
+
"loss": 2.0077,
|
| 18 |
+
"mean_token_accuracy": 0.5798640113323927,
|
| 19 |
+
"num_tokens": 338396.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.6553284931182861,
|
| 24 |
+
"epoch": 0.14814814814814814,
|
| 25 |
+
"grad_norm": 0.3852575719356537,
|
| 26 |
+
"learning_rate": 9.990765991730485e-05,
|
| 27 |
+
"loss": 0.5993,
|
| 28 |
+
"mean_token_accuracy": 0.8612996307015419,
|
| 29 |
+
"num_tokens": 677239.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.4204328820481896,
|
| 34 |
+
"epoch": 0.2222222222222222,
|
| 35 |
+
"grad_norm": 0.2863098680973053,
|
| 36 |
+
"learning_rate": 9.950545603782162e-05,
|
| 37 |
+
"loss": 0.4172,
|
| 38 |
+
"mean_token_accuracy": 0.9052096186578273,
|
| 39 |
+
"num_tokens": 1015420.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.3820256270095706,
|
| 44 |
+
"epoch": 0.2962962962962963,
|
| 45 |
+
"grad_norm": 0.2698630690574646,
|
| 46 |
+
"learning_rate": 9.878674879048427e-05,
|
| 47 |
+
"loss": 0.383,
|
| 48 |
+
"mean_token_accuracy": 0.9129502369463444,
|
| 49 |
+
"num_tokens": 1355048.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.37178467601537707,
|
| 54 |
+
"epoch": 0.37037037037037035,
|
| 55 |
+
"grad_norm": 0.21257849037647247,
|
| 56 |
+
"learning_rate": 9.775613308830824e-05,
|
| 57 |
+
"loss": 0.37,
|
| 58 |
+
"mean_token_accuracy": 0.9151540066301823,
|
| 59 |
+
"num_tokens": 1691649.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.36766253888607026,
|
| 64 |
+
"epoch": 0.4444444444444444,
|
| 65 |
+
"grad_norm": 0.31453582644462585,
|
| 66 |
+
"learning_rate": 9.642019796948866e-05,
|
| 67 |
+
"loss": 0.3634,
|
| 68 |
+
"mean_token_accuracy": 0.9162409096956253,
|
| 69 |
+
"num_tokens": 2029267.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.35622088231146337,
|
| 74 |
+
"epoch": 0.5185185185185185,
|
| 75 |
+
"grad_norm": 0.20113833248615265,
|
| 76 |
+
"learning_rate": 9.478748447168449e-05,
|
| 77 |
+
"loss": 0.3533,
|
| 78 |
+
"mean_token_accuracy": 0.9183417546749115,
|
| 79 |
+
"num_tokens": 2369465.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.3494216964393854,
|
| 84 |
+
"epoch": 0.5925925925925926,
|
| 85 |
+
"grad_norm": 0.20226770639419556,
|
| 86 |
+
"learning_rate": 9.28684310265789e-05,
|
| 87 |
+
"loss": 0.3492,
|
| 88 |
+
"mean_token_accuracy": 0.919527986496687,
|
| 89 |
+
"num_tokens": 2707235.0,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 0.3433630639687181,
|
| 94 |
+
"epoch": 0.6666666666666666,
|
| 95 |
+
"grad_norm": 0.1721702516078949,
|
| 96 |
+
"learning_rate": 9.067530672382544e-05,
|
| 97 |
+
"loss": 0.3453,
|
| 98 |
+
"mean_token_accuracy": 0.9204271128773689,
|
| 99 |
+
"num_tokens": 3041282.0,
|
| 100 |
+
"step": 450
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 0.3465565311536193,
|
| 104 |
+
"epoch": 0.7407407407407407,
|
| 105 |
+
"grad_norm": 0.1957043558359146,
|
| 106 |
+
"learning_rate": 8.822213287104348e-05,
|
| 107 |
+
"loss": 0.3483,
|
| 108 |
+
"mean_token_accuracy": 0.9200405342876912,
|
| 109 |
+
"num_tokens": 3378157.0,
|
| 110 |
+
"step": 500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 0.34500927191227676,
|
| 114 |
+
"epoch": 0.8148148148148148,
|
| 115 |
+
"grad_norm": 0.1682814359664917,
|
| 116 |
+
"learning_rate": 8.552459335135381e-05,
|
| 117 |
+
"loss": 0.3466,
|
| 118 |
+
"mean_token_accuracy": 0.9210821086168289,
|
| 119 |
+
"num_tokens": 3717487.0,
|
| 120 |
+
"step": 550
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 0.33874930143356324,
|
| 124 |
+
"epoch": 0.8888888888888888,
|
| 125 |
+
"grad_norm": 0.1756315678358078,
|
| 126 |
+
"learning_rate": 8.259993435156559e-05,
|
| 127 |
+
"loss": 0.3406,
|
| 128 |
+
"mean_token_accuracy": 0.9231470887362957,
|
| 129 |
+
"num_tokens": 4056814.0,
|
| 130 |
+
"step": 600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 0.3372995613142848,
|
| 134 |
+
"epoch": 0.9629629629629629,
|
| 135 |
+
"grad_norm": 0.185526043176651,
|
| 136 |
+
"learning_rate": 7.946685410208296e-05,
|
| 137 |
+
"loss": 0.3378,
|
| 138 |
+
"mean_token_accuracy": 0.924960307776928,
|
| 139 |
+
"num_tokens": 4398736.0,
|
| 140 |
+
"step": 650
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 0.3282011279836297,
|
| 144 |
+
"epoch": 1.037037037037037,
|
| 145 |
+
"grad_norm": 0.23889201879501343,
|
| 146 |
+
"learning_rate": 7.614538333345735e-05,
|
| 147 |
+
"loss": 0.3293,
|
| 148 |
+
"mean_token_accuracy": 0.9266741496324539,
|
| 149 |
+
"num_tokens": 4737915.0,
|
| 150 |
+
"step": 700
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 0.32703890234231947,
|
| 154 |
+
"epoch": 1.1111111111111112,
|
| 155 |
+
"grad_norm": 0.21601562201976776,
|
| 156 |
+
"learning_rate": 7.265675721386285e-05,
|
| 157 |
+
"loss": 0.3275,
|
| 158 |
+
"mean_token_accuracy": 0.9279554469883442,
|
| 159 |
+
"num_tokens": 5074721.0,
|
| 160 |
+
"step": 750
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 0.3243879374489188,
|
| 164 |
+
"epoch": 1.1851851851851851,
|
| 165 |
+
"grad_norm": 0.22092069685459137,
|
| 166 |
+
"learning_rate": 6.902327958623736e-05,
|
| 167 |
+
"loss": 0.3244,
|
| 168 |
+
"mean_token_accuracy": 0.9288445146381855,
|
| 169 |
+
"num_tokens": 5413515.0,
|
| 170 |
+
"step": 800
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 0.3191816185042262,
|
| 174 |
+
"epoch": 1.2592592592592593,
|
| 175 |
+
"grad_norm": 0.2003597766160965,
|
| 176 |
+
"learning_rate": 6.526818037306228e-05,
|
| 177 |
+
"loss": 0.3197,
|
| 178 |
+
"mean_token_accuracy": 0.9303379128873348,
|
| 179 |
+
"num_tokens": 5751965.0,
|
| 180 |
+
"step": 850
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 0.311707403101027,
|
| 184 |
+
"epoch": 1.3333333333333333,
|
| 185 |
+
"grad_norm": 0.1664246916770935,
|
| 186 |
+
"learning_rate": 6.14154670604355e-05,
|
| 187 |
+
"loss": 0.3122,
|
| 188 |
+
"mean_token_accuracy": 0.9324613013863563,
|
| 189 |
+
"num_tokens": 6087993.0,
|
| 190 |
+
"step": 900
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 0.31203486569225786,
|
| 194 |
+
"epoch": 1.4074074074074074,
|
| 195 |
+
"grad_norm": 0.25155216455459595,
|
| 196 |
+
"learning_rate": 5.7489771210944564e-05,
|
| 197 |
+
"loss": 0.3129,
|
| 198 |
+
"mean_token_accuracy": 0.932486515045166,
|
| 199 |
+
"num_tokens": 6425349.0,
|
| 200 |
+
"step": 950
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 0.31312834514304994,
|
| 204 |
+
"epoch": 1.4814814814814814,
|
| 205 |
+
"grad_norm": 0.2299806922674179,
|
| 206 |
+
"learning_rate": 5.351619098663021e-05,
|
| 207 |
+
"loss": 0.3139,
|
| 208 |
+
"mean_token_accuracy": 0.9324578355252743,
|
| 209 |
+
"num_tokens": 6762060.0,
|
| 210 |
+
"step": 1000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 0.31229398518800733,
|
| 214 |
+
"epoch": 1.5555555555555556,
|
| 215 |
+
"grad_norm": 0.21491679549217224,
|
| 216 |
+
"learning_rate": 4.952013068883795e-05,
|
| 217 |
+
"loss": 0.3123,
|
| 218 |
+
"mean_token_accuracy": 0.9330742400884628,
|
| 219 |
+
"num_tokens": 7099580.0,
|
| 220 |
+
"step": 1050
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 0.3089119081199169,
|
| 224 |
+
"epoch": 1.6296296296296298,
|
| 225 |
+
"grad_norm": 0.20928895473480225,
|
| 226 |
+
"learning_rate": 4.5527138340828776e-05,
|
| 227 |
+
"loss": 0.3083,
|
| 228 |
+
"mean_token_accuracy": 0.9346707260608673,
|
| 229 |
+
"num_tokens": 7441088.0,
|
| 230 |
+
"step": 1100
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 0.3122195054590702,
|
| 234 |
+
"epoch": 1.7037037037037037,
|
| 235 |
+
"grad_norm": 0.1754506677389145,
|
| 236 |
+
"learning_rate": 4.156274235153189e-05,
|
| 237 |
+
"loss": 0.3128,
|
| 238 |
+
"mean_token_accuracy": 0.9337523929774761,
|
| 239 |
+
"num_tokens": 7781339.0,
|
| 240 |
+
"step": 1150
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 0.3072645129263401,
|
| 244 |
+
"epoch": 1.7777777777777777,
|
| 245 |
+
"grad_norm": 0.19373080134391785,
|
| 246 |
+
"learning_rate": 3.765228830469794e-05,
|
| 247 |
+
"loss": 0.3083,
|
| 248 |
+
"mean_token_accuracy": 0.9344205930829048,
|
| 249 |
+
"num_tokens": 8118559.0,
|
| 250 |
+
"step": 1200
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 0.30596201956272123,
|
| 254 |
+
"epoch": 1.8518518518518519,
|
| 255 |
+
"grad_norm": 0.21876507997512817,
|
| 256 |
+
"learning_rate": 3.3820776916908857e-05,
|
| 257 |
+
"loss": 0.3065,
|
| 258 |
+
"mean_token_accuracy": 0.935108490884304,
|
| 259 |
+
"num_tokens": 8458822.0,
|
| 260 |
+
"step": 1250
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 0.3032321432232857,
|
| 264 |
+
"epoch": 1.925925925925926,
|
| 265 |
+
"grad_norm": 0.16569602489471436,
|
| 266 |
+
"learning_rate": 3.0092704200428058e-05,
|
| 267 |
+
"loss": 0.304,
|
| 268 |
+
"mean_token_accuracy": 0.9358008193969727,
|
| 269 |
+
"num_tokens": 8797573.0,
|
| 270 |
+
"step": 1300
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 0.3116097005084157,
|
| 274 |
+
"epoch": 2.0,
|
| 275 |
+
"grad_norm": 0.23642410337924957,
|
| 276 |
+
"learning_rate": 2.649190485277792e-05,
|
| 277 |
+
"loss": 0.312,
|
| 278 |
+
"mean_token_accuracy": 0.9340617834031582,
|
| 279 |
+
"num_tokens": 9138916.0,
|
| 280 |
+
"step": 1350
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 0.2998246630653739,
|
| 284 |
+
"epoch": 2.074074074074074,
|
| 285 |
+
"grad_norm": 0.4210748076438904,
|
| 286 |
+
"learning_rate": 2.3041399874302905e-05,
|
| 287 |
+
"loss": 0.3015,
|
| 288 |
+
"mean_token_accuracy": 0.9369703502953053,
|
| 289 |
+
"num_tokens": 9476346.0,
|
| 290 |
+
"step": 1400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 0.29883858568966387,
|
| 294 |
+
"epoch": 2.148148148148148,
|
| 295 |
+
"grad_norm": 0.2179645299911499,
|
| 296 |
+
"learning_rate": 1.976324938794482e-05,
|
| 297 |
+
"loss": 0.2995,
|
| 298 |
+
"mean_token_accuracy": 0.9364559413492679,
|
| 299 |
+
"num_tokens": 9813810.0,
|
| 300 |
+
"step": 1450
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 0.30353500295430424,
|
| 304 |
+
"epoch": 2.2222222222222223,
|
| 305 |
+
"grad_norm": 0.15429526567459106,
|
| 306 |
+
"learning_rate": 1.667841160219835e-05,
|
| 307 |
+
"loss": 0.304,
|
| 308 |
+
"mean_token_accuracy": 0.9365751321613789,
|
| 309 |
+
"num_tokens": 10154937.0,
|
| 310 |
+
"step": 1500
|
| 311 |
+
}
|
| 312 |
+
],
|
| 313 |
+
"logging_steps": 50,
|
| 314 |
+
"max_steps": 2025,
|
| 315 |
+
"num_input_tokens_seen": 0,
|
| 316 |
+
"num_train_epochs": 3,
|
| 317 |
+
"save_steps": 500,
|
| 318 |
+
"stateful_callbacks": {
|
| 319 |
+
"TrainerControl": {
|
| 320 |
+
"args": {
|
| 321 |
+
"should_epoch_stop": false,
|
| 322 |
+
"should_evaluate": false,
|
| 323 |
+
"should_log": false,
|
| 324 |
+
"should_save": true,
|
| 325 |
+
"should_training_stop": false
|
| 326 |
+
},
|
| 327 |
+
"attributes": {}
|
| 328 |
+
}
|
| 329 |
+
},
|
| 330 |
+
"total_flos": 4.2419882128569754e+17,
|
| 331 |
+
"train_batch_size": 1,
|
| 332 |
+
"trial_name": null,
|
| 333 |
+
"trial_params": null
|
| 334 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a4e34ab1ebeeacb30334aa618143874612a2eac847c74484d639038e6305203
|
| 3 |
+
size 6225
|
checkpoint-1500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: bigcode/starcoder2-7b
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:bigcode/starcoder2-7b
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- 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. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
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).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.0
|
checkpoint-2000/adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "bigcode/starcoder2-7b",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"k_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"q_proj"
|
| 36 |
+
],
|
| 37 |
+
"target_parameters": null,
|
| 38 |
+
"task_type": "CAUSAL_LM",
|
| 39 |
+
"trainable_token_indices": null,
|
| 40 |
+
"use_dora": false,
|
| 41 |
+
"use_qalora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
checkpoint-2000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:805e0f57ff4b71b6e89678b2ede58b03715cc22e2b77e94e2f130e749dface4b
|
| 3 |
+
size 58754616
|
checkpoint-2000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab0c17cdbf6aa1554bc2578d8109521cfdd3dbb7824740199660351ea7e9f7d1
|
| 3 |
+
size 117660107
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce347f8bb85e2a0db077656b8ee3172c8ad9e2f54252e415c7201df0520269e4
|
| 3 |
+
size 14645
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:591d55d90adc2dbaeabd46529428d7ba9aa1ba92348998be2f0a794eeb555bea
|
| 3 |
+
size 1465
|
checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<repo_name>",
|
| 9 |
+
"<file_sep>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<jupyter_script>",
|
| 18 |
+
"<empty_output>",
|
| 19 |
+
"<code_to_intermediate>",
|
| 20 |
+
"<intermediate_to_code>",
|
| 21 |
+
"<pr>",
|
| 22 |
+
"<pr_status>",
|
| 23 |
+
"<pr_is_merged>",
|
| 24 |
+
"<pr_base>",
|
| 25 |
+
"<pr_file>",
|
| 26 |
+
"<pr_base_code>",
|
| 27 |
+
"<pr_diff>",
|
| 28 |
+
"<pr_diff_hunk>",
|
| 29 |
+
"<pr_comment>",
|
| 30 |
+
"<pr_event_id>",
|
| 31 |
+
"<pr_review>",
|
| 32 |
+
"<pr_review_state>",
|
| 33 |
+
"<pr_review_comment>",
|
| 34 |
+
"<pr_in_reply_to_review_id>",
|
| 35 |
+
"<pr_in_reply_to_comment_id>",
|
| 36 |
+
"<pr_diff_hunk_comment_line>",
|
| 37 |
+
"<NAME>",
|
| 38 |
+
"<EMAIL>",
|
| 39 |
+
"<KEY>",
|
| 40 |
+
"<PASSWORD>"
|
| 41 |
+
],
|
| 42 |
+
"bos_token": {
|
| 43 |
+
"content": "<|endoftext|>",
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false
|
| 48 |
+
},
|
| 49 |
+
"eos_token": {
|
| 50 |
+
"content": "<|endoftext|>",
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"normalized": false,
|
| 53 |
+
"rstrip": false,
|
| 54 |
+
"single_word": false
|
| 55 |
+
},
|
| 56 |
+
"unk_token": {
|
| 57 |
+
"content": "<|endoftext|>",
|
| 58 |
+
"lstrip": false,
|
| 59 |
+
"normalized": false,
|
| 60 |
+
"rstrip": false,
|
| 61 |
+
"single_word": false
|
| 62 |
+
}
|
| 63 |
+
}
|
checkpoint-2000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<repo_name>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<file_sep>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_script>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<empty_output>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<code_to_intermediate>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<intermediate_to_code>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<pr>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"19": {
|
| 157 |
+
"content": "<pr_status>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"20": {
|
| 165 |
+
"content": "<pr_is_merged>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"21": {
|
| 173 |
+
"content": "<pr_base>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"22": {
|
| 181 |
+
"content": "<pr_file>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"23": {
|
| 189 |
+
"content": "<pr_base_code>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"24": {
|
| 197 |
+
"content": "<pr_diff>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"25": {
|
| 205 |
+
"content": "<pr_diff_hunk>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"26": {
|
| 213 |
+
"content": "<pr_comment>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"27": {
|
| 221 |
+
"content": "<pr_event_id>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"28": {
|
| 229 |
+
"content": "<pr_review>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"29": {
|
| 237 |
+
"content": "<pr_review_state>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"30": {
|
| 245 |
+
"content": "<pr_review_comment>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"31": {
|
| 253 |
+
"content": "<pr_in_reply_to_review_id>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32": {
|
| 261 |
+
"content": "<pr_in_reply_to_comment_id>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"33": {
|
| 269 |
+
"content": "<pr_diff_hunk_comment_line>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"34": {
|
| 277 |
+
"content": "<NAME>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"35": {
|
| 285 |
+
"content": "<EMAIL>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"36": {
|
| 293 |
+
"content": "<KEY>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"37": {
|
| 301 |
+
"content": "<PASSWORD>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
}
|
| 308 |
+
},
|
| 309 |
+
"additional_special_tokens": [
|
| 310 |
+
"<|endoftext|>",
|
| 311 |
+
"<fim_prefix>",
|
| 312 |
+
"<fim_middle>",
|
| 313 |
+
"<fim_suffix>",
|
| 314 |
+
"<fim_pad>",
|
| 315 |
+
"<repo_name>",
|
| 316 |
+
"<file_sep>",
|
| 317 |
+
"<issue_start>",
|
| 318 |
+
"<issue_comment>",
|
| 319 |
+
"<issue_closed>",
|
| 320 |
+
"<jupyter_start>",
|
| 321 |
+
"<jupyter_text>",
|
| 322 |
+
"<jupyter_code>",
|
| 323 |
+
"<jupyter_output>",
|
| 324 |
+
"<jupyter_script>",
|
| 325 |
+
"<empty_output>",
|
| 326 |
+
"<code_to_intermediate>",
|
| 327 |
+
"<intermediate_to_code>",
|
| 328 |
+
"<pr>",
|
| 329 |
+
"<pr_status>",
|
| 330 |
+
"<pr_is_merged>",
|
| 331 |
+
"<pr_base>",
|
| 332 |
+
"<pr_file>",
|
| 333 |
+
"<pr_base_code>",
|
| 334 |
+
"<pr_diff>",
|
| 335 |
+
"<pr_diff_hunk>",
|
| 336 |
+
"<pr_comment>",
|
| 337 |
+
"<pr_event_id>",
|
| 338 |
+
"<pr_review>",
|
| 339 |
+
"<pr_review_state>",
|
| 340 |
+
"<pr_review_comment>",
|
| 341 |
+
"<pr_in_reply_to_review_id>",
|
| 342 |
+
"<pr_in_reply_to_comment_id>",
|
| 343 |
+
"<pr_diff_hunk_comment_line>",
|
| 344 |
+
"<NAME>",
|
| 345 |
+
"<EMAIL>",
|
| 346 |
+
"<KEY>",
|
| 347 |
+
"<PASSWORD>"
|
| 348 |
+
],
|
| 349 |
+
"bos_token": "<|endoftext|>",
|
| 350 |
+
"clean_up_tokenization_spaces": true,
|
| 351 |
+
"eos_token": "<|endoftext|>",
|
| 352 |
+
"extra_special_tokens": {},
|
| 353 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 354 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 355 |
+
"unk_token": "<|endoftext|>",
|
| 356 |
+
"vocab_size": 49152
|
| 357 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.962962962962963,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 2.1715362322330476,
|
| 14 |
+
"epoch": 0.07407407407407407,
|
| 15 |
+
"grad_norm": 1.0598933696746826,
|
| 16 |
+
"learning_rate": 8.032786885245902e-05,
|
| 17 |
+
"loss": 2.0077,
|
| 18 |
+
"mean_token_accuracy": 0.5798640113323927,
|
| 19 |
+
"num_tokens": 338396.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.6553284931182861,
|
| 24 |
+
"epoch": 0.14814814814814814,
|
| 25 |
+
"grad_norm": 0.3852575719356537,
|
| 26 |
+
"learning_rate": 9.990765991730485e-05,
|
| 27 |
+
"loss": 0.5993,
|
| 28 |
+
"mean_token_accuracy": 0.8612996307015419,
|
| 29 |
+
"num_tokens": 677239.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.4204328820481896,
|
| 34 |
+
"epoch": 0.2222222222222222,
|
| 35 |
+
"grad_norm": 0.2863098680973053,
|
| 36 |
+
"learning_rate": 9.950545603782162e-05,
|
| 37 |
+
"loss": 0.4172,
|
| 38 |
+
"mean_token_accuracy": 0.9052096186578273,
|
| 39 |
+
"num_tokens": 1015420.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.3820256270095706,
|
| 44 |
+
"epoch": 0.2962962962962963,
|
| 45 |
+
"grad_norm": 0.2698630690574646,
|
| 46 |
+
"learning_rate": 9.878674879048427e-05,
|
| 47 |
+
"loss": 0.383,
|
| 48 |
+
"mean_token_accuracy": 0.9129502369463444,
|
| 49 |
+
"num_tokens": 1355048.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.37178467601537707,
|
| 54 |
+
"epoch": 0.37037037037037035,
|
| 55 |
+
"grad_norm": 0.21257849037647247,
|
| 56 |
+
"learning_rate": 9.775613308830824e-05,
|
| 57 |
+
"loss": 0.37,
|
| 58 |
+
"mean_token_accuracy": 0.9151540066301823,
|
| 59 |
+
"num_tokens": 1691649.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.36766253888607026,
|
| 64 |
+
"epoch": 0.4444444444444444,
|
| 65 |
+
"grad_norm": 0.31453582644462585,
|
| 66 |
+
"learning_rate": 9.642019796948866e-05,
|
| 67 |
+
"loss": 0.3634,
|
| 68 |
+
"mean_token_accuracy": 0.9162409096956253,
|
| 69 |
+
"num_tokens": 2029267.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.35622088231146337,
|
| 74 |
+
"epoch": 0.5185185185185185,
|
| 75 |
+
"grad_norm": 0.20113833248615265,
|
| 76 |
+
"learning_rate": 9.478748447168449e-05,
|
| 77 |
+
"loss": 0.3533,
|
| 78 |
+
"mean_token_accuracy": 0.9183417546749115,
|
| 79 |
+
"num_tokens": 2369465.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.3494216964393854,
|
| 84 |
+
"epoch": 0.5925925925925926,
|
| 85 |
+
"grad_norm": 0.20226770639419556,
|
| 86 |
+
"learning_rate": 9.28684310265789e-05,
|
| 87 |
+
"loss": 0.3492,
|
| 88 |
+
"mean_token_accuracy": 0.919527986496687,
|
| 89 |
+
"num_tokens": 2707235.0,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 0.3433630639687181,
|
| 94 |
+
"epoch": 0.6666666666666666,
|
| 95 |
+
"grad_norm": 0.1721702516078949,
|
| 96 |
+
"learning_rate": 9.067530672382544e-05,
|
| 97 |
+
"loss": 0.3453,
|
| 98 |
+
"mean_token_accuracy": 0.9204271128773689,
|
| 99 |
+
"num_tokens": 3041282.0,
|
| 100 |
+
"step": 450
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 0.3465565311536193,
|
| 104 |
+
"epoch": 0.7407407407407407,
|
| 105 |
+
"grad_norm": 0.1957043558359146,
|
| 106 |
+
"learning_rate": 8.822213287104348e-05,
|
| 107 |
+
"loss": 0.3483,
|
| 108 |
+
"mean_token_accuracy": 0.9200405342876912,
|
| 109 |
+
"num_tokens": 3378157.0,
|
| 110 |
+
"step": 500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 0.34500927191227676,
|
| 114 |
+
"epoch": 0.8148148148148148,
|
| 115 |
+
"grad_norm": 0.1682814359664917,
|
| 116 |
+
"learning_rate": 8.552459335135381e-05,
|
| 117 |
+
"loss": 0.3466,
|
| 118 |
+
"mean_token_accuracy": 0.9210821086168289,
|
| 119 |
+
"num_tokens": 3717487.0,
|
| 120 |
+
"step": 550
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 0.33874930143356324,
|
| 124 |
+
"epoch": 0.8888888888888888,
|
| 125 |
+
"grad_norm": 0.1756315678358078,
|
| 126 |
+
"learning_rate": 8.259993435156559e-05,
|
| 127 |
+
"loss": 0.3406,
|
| 128 |
+
"mean_token_accuracy": 0.9231470887362957,
|
| 129 |
+
"num_tokens": 4056814.0,
|
| 130 |
+
"step": 600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 0.3372995613142848,
|
| 134 |
+
"epoch": 0.9629629629629629,
|
| 135 |
+
"grad_norm": 0.185526043176651,
|
| 136 |
+
"learning_rate": 7.946685410208296e-05,
|
| 137 |
+
"loss": 0.3378,
|
| 138 |
+
"mean_token_accuracy": 0.924960307776928,
|
| 139 |
+
"num_tokens": 4398736.0,
|
| 140 |
+
"step": 650
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 0.3282011279836297,
|
| 144 |
+
"epoch": 1.037037037037037,
|
| 145 |
+
"grad_norm": 0.23889201879501343,
|
| 146 |
+
"learning_rate": 7.614538333345735e-05,
|
| 147 |
+
"loss": 0.3293,
|
| 148 |
+
"mean_token_accuracy": 0.9266741496324539,
|
| 149 |
+
"num_tokens": 4737915.0,
|
| 150 |
+
"step": 700
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 0.32703890234231947,
|
| 154 |
+
"epoch": 1.1111111111111112,
|
| 155 |
+
"grad_norm": 0.21601562201976776,
|
| 156 |
+
"learning_rate": 7.265675721386285e-05,
|
| 157 |
+
"loss": 0.3275,
|
| 158 |
+
"mean_token_accuracy": 0.9279554469883442,
|
| 159 |
+
"num_tokens": 5074721.0,
|
| 160 |
+
"step": 750
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 0.3243879374489188,
|
| 164 |
+
"epoch": 1.1851851851851851,
|
| 165 |
+
"grad_norm": 0.22092069685459137,
|
| 166 |
+
"learning_rate": 6.902327958623736e-05,
|
| 167 |
+
"loss": 0.3244,
|
| 168 |
+
"mean_token_accuracy": 0.9288445146381855,
|
| 169 |
+
"num_tokens": 5413515.0,
|
| 170 |
+
"step": 800
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 0.3191816185042262,
|
| 174 |
+
"epoch": 1.2592592592592593,
|
| 175 |
+
"grad_norm": 0.2003597766160965,
|
| 176 |
+
"learning_rate": 6.526818037306228e-05,
|
| 177 |
+
"loss": 0.3197,
|
| 178 |
+
"mean_token_accuracy": 0.9303379128873348,
|
| 179 |
+
"num_tokens": 5751965.0,
|
| 180 |
+
"step": 850
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 0.311707403101027,
|
| 184 |
+
"epoch": 1.3333333333333333,
|
| 185 |
+
"grad_norm": 0.1664246916770935,
|
| 186 |
+
"learning_rate": 6.14154670604355e-05,
|
| 187 |
+
"loss": 0.3122,
|
| 188 |
+
"mean_token_accuracy": 0.9324613013863563,
|
| 189 |
+
"num_tokens": 6087993.0,
|
| 190 |
+
"step": 900
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 0.31203486569225786,
|
| 194 |
+
"epoch": 1.4074074074074074,
|
| 195 |
+
"grad_norm": 0.25155216455459595,
|
| 196 |
+
"learning_rate": 5.7489771210944564e-05,
|
| 197 |
+
"loss": 0.3129,
|
| 198 |
+
"mean_token_accuracy": 0.932486515045166,
|
| 199 |
+
"num_tokens": 6425349.0,
|
| 200 |
+
"step": 950
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 0.31312834514304994,
|
| 204 |
+
"epoch": 1.4814814814814814,
|
| 205 |
+
"grad_norm": 0.2299806922674179,
|
| 206 |
+
"learning_rate": 5.351619098663021e-05,
|
| 207 |
+
"loss": 0.3139,
|
| 208 |
+
"mean_token_accuracy": 0.9324578355252743,
|
| 209 |
+
"num_tokens": 6762060.0,
|
| 210 |
+
"step": 1000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 0.31229398518800733,
|
| 214 |
+
"epoch": 1.5555555555555556,
|
| 215 |
+
"grad_norm": 0.21491679549217224,
|
| 216 |
+
"learning_rate": 4.952013068883795e-05,
|
| 217 |
+
"loss": 0.3123,
|
| 218 |
+
"mean_token_accuracy": 0.9330742400884628,
|
| 219 |
+
"num_tokens": 7099580.0,
|
| 220 |
+
"step": 1050
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 0.3089119081199169,
|
| 224 |
+
"epoch": 1.6296296296296298,
|
| 225 |
+
"grad_norm": 0.20928895473480225,
|
| 226 |
+
"learning_rate": 4.5527138340828776e-05,
|
| 227 |
+
"loss": 0.3083,
|
| 228 |
+
"mean_token_accuracy": 0.9346707260608673,
|
| 229 |
+
"num_tokens": 7441088.0,
|
| 230 |
+
"step": 1100
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 0.3122195054590702,
|
| 234 |
+
"epoch": 1.7037037037037037,
|
| 235 |
+
"grad_norm": 0.1754506677389145,
|
| 236 |
+
"learning_rate": 4.156274235153189e-05,
|
| 237 |
+
"loss": 0.3128,
|
| 238 |
+
"mean_token_accuracy": 0.9337523929774761,
|
| 239 |
+
"num_tokens": 7781339.0,
|
| 240 |
+
"step": 1150
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 0.3072645129263401,
|
| 244 |
+
"epoch": 1.7777777777777777,
|
| 245 |
+
"grad_norm": 0.19373080134391785,
|
| 246 |
+
"learning_rate": 3.765228830469794e-05,
|
| 247 |
+
"loss": 0.3083,
|
| 248 |
+
"mean_token_accuracy": 0.9344205930829048,
|
| 249 |
+
"num_tokens": 8118559.0,
|
| 250 |
+
"step": 1200
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 0.30596201956272123,
|
| 254 |
+
"epoch": 1.8518518518518519,
|
| 255 |
+
"grad_norm": 0.21876507997512817,
|
| 256 |
+
"learning_rate": 3.3820776916908857e-05,
|
| 257 |
+
"loss": 0.3065,
|
| 258 |
+
"mean_token_accuracy": 0.935108490884304,
|
| 259 |
+
"num_tokens": 8458822.0,
|
| 260 |
+
"step": 1250
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 0.3032321432232857,
|
| 264 |
+
"epoch": 1.925925925925926,
|
| 265 |
+
"grad_norm": 0.16569602489471436,
|
| 266 |
+
"learning_rate": 3.0092704200428058e-05,
|
| 267 |
+
"loss": 0.304,
|
| 268 |
+
"mean_token_accuracy": 0.9358008193969727,
|
| 269 |
+
"num_tokens": 8797573.0,
|
| 270 |
+
"step": 1300
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 0.3116097005084157,
|
| 274 |
+
"epoch": 2.0,
|
| 275 |
+
"grad_norm": 0.23642410337924957,
|
| 276 |
+
"learning_rate": 2.649190485277792e-05,
|
| 277 |
+
"loss": 0.312,
|
| 278 |
+
"mean_token_accuracy": 0.9340617834031582,
|
| 279 |
+
"num_tokens": 9138916.0,
|
| 280 |
+
"step": 1350
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 0.2998246630653739,
|
| 284 |
+
"epoch": 2.074074074074074,
|
| 285 |
+
"grad_norm": 0.4210748076438904,
|
| 286 |
+
"learning_rate": 2.3041399874302905e-05,
|
| 287 |
+
"loss": 0.3015,
|
| 288 |
+
"mean_token_accuracy": 0.9369703502953053,
|
| 289 |
+
"num_tokens": 9476346.0,
|
| 290 |
+
"step": 1400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 0.29883858568966387,
|
| 294 |
+
"epoch": 2.148148148148148,
|
| 295 |
+
"grad_norm": 0.2179645299911499,
|
| 296 |
+
"learning_rate": 1.976324938794482e-05,
|
| 297 |
+
"loss": 0.2995,
|
| 298 |
+
"mean_token_accuracy": 0.9364559413492679,
|
| 299 |
+
"num_tokens": 9813810.0,
|
| 300 |
+
"step": 1450
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 0.30353500295430424,
|
| 304 |
+
"epoch": 2.2222222222222223,
|
| 305 |
+
"grad_norm": 0.15429526567459106,
|
| 306 |
+
"learning_rate": 1.667841160219835e-05,
|
| 307 |
+
"loss": 0.304,
|
| 308 |
+
"mean_token_accuracy": 0.9365751321613789,
|
| 309 |
+
"num_tokens": 10154937.0,
|
| 310 |
+
"step": 1500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"entropy": 0.3042653623223305,
|
| 314 |
+
"epoch": 2.2962962962962963,
|
| 315 |
+
"grad_norm": 0.42488107085227966,
|
| 316 |
+
"learning_rate": 1.3806608818939203e-05,
|
| 317 |
+
"loss": 0.3057,
|
| 318 |
+
"mean_token_accuracy": 0.9359618930518627,
|
| 319 |
+
"num_tokens": 10494104.0,
|
| 320 |
+
"step": 1550
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"entropy": 0.3081327396631241,
|
| 324 |
+
"epoch": 2.3703703703703702,
|
| 325 |
+
"grad_norm": 0.2351272851228714,
|
| 326 |
+
"learning_rate": 1.1166201342777438e-05,
|
| 327 |
+
"loss": 0.3064,
|
| 328 |
+
"mean_token_accuracy": 0.9357219311594963,
|
| 329 |
+
"num_tokens": 10834738.0,
|
| 330 |
+
"step": 1600
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"entropy": 0.29908867001533507,
|
| 334 |
+
"epoch": 2.4444444444444446,
|
| 335 |
+
"grad_norm": 0.18584305047988892,
|
| 336 |
+
"learning_rate": 8.774070098071668e-06,
|
| 337 |
+
"loss": 0.3003,
|
| 338 |
+
"mean_token_accuracy": 0.9364377255737781,
|
| 339 |
+
"num_tokens": 11170346.0,
|
| 340 |
+
"step": 1650
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"entropy": 0.30048872336745264,
|
| 344 |
+
"epoch": 2.5185185185185186,
|
| 345 |
+
"grad_norm": 0.17059944570064545,
|
| 346 |
+
"learning_rate": 6.645508704069003e-06,
|
| 347 |
+
"loss": 0.2998,
|
| 348 |
+
"mean_token_accuracy": 0.9365158031880856,
|
| 349 |
+
"num_tokens": 11508330.0,
|
| 350 |
+
"step": 1700
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"entropy": 0.3041739664040506,
|
| 354 |
+
"epoch": 2.5925925925925926,
|
| 355 |
+
"grad_norm": 0.16423071920871735,
|
| 356 |
+
"learning_rate": 4.794125698167262e-06,
|
| 357 |
+
"loss": 0.3058,
|
| 358 |
+
"mean_token_accuracy": 0.9364174953103066,
|
| 359 |
+
"num_tokens": 11850254.0,
|
| 360 |
+
"step": 1750
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"entropy": 0.2920705447718501,
|
| 364 |
+
"epoch": 2.6666666666666665,
|
| 365 |
+
"grad_norm": 0.19584065675735474,
|
| 366 |
+
"learning_rate": 3.231757532415458e-06,
|
| 367 |
+
"loss": 0.2943,
|
| 368 |
+
"mean_token_accuracy": 0.9384492780268192,
|
| 369 |
+
"num_tokens": 12185740.0,
|
| 370 |
+
"step": 1800
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"entropy": 0.30169622793793677,
|
| 374 |
+
"epoch": 2.7407407407407405,
|
| 375 |
+
"grad_norm": 0.37878257036209106,
|
| 376 |
+
"learning_rate": 1.9683928994924385e-06,
|
| 377 |
+
"loss": 0.3011,
|
| 378 |
+
"mean_token_accuracy": 0.9368291793763638,
|
| 379 |
+
"num_tokens": 12525018.0,
|
| 380 |
+
"step": 1850
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"entropy": 0.29348658775910735,
|
| 384 |
+
"epoch": 2.814814814814815,
|
| 385 |
+
"grad_norm": 0.19502298533916473,
|
| 386 |
+
"learning_rate": 1.0121088719706296e-06,
|
| 387 |
+
"loss": 0.2948,
|
| 388 |
+
"mean_token_accuracy": 0.9380346268415451,
|
| 389 |
+
"num_tokens": 12860441.0,
|
| 390 |
+
"step": 1900
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"entropy": 0.3033849265426397,
|
| 394 |
+
"epoch": 2.888888888888889,
|
| 395 |
+
"grad_norm": 0.16882896423339844,
|
| 396 |
+
"learning_rate": 3.6901926314575894e-07,
|
| 397 |
+
"loss": 0.3039,
|
| 398 |
+
"mean_token_accuracy": 0.936366637647152,
|
| 399 |
+
"num_tokens": 13198992.0,
|
| 400 |
+
"step": 1950
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"entropy": 0.29646733120083807,
|
| 404 |
+
"epoch": 2.962962962962963,
|
| 405 |
+
"grad_norm": 0.1928730458021164,
|
| 406 |
+
"learning_rate": 4.323553957759629e-08,
|
| 407 |
+
"loss": 0.2962,
|
| 408 |
+
"mean_token_accuracy": 0.9374634748697281,
|
| 409 |
+
"num_tokens": 13538141.0,
|
| 410 |
+
"step": 2000
|
| 411 |
+
}
|
| 412 |
+
],
|
| 413 |
+
"logging_steps": 50,
|
| 414 |
+
"max_steps": 2025,
|
| 415 |
+
"num_input_tokens_seen": 0,
|
| 416 |
+
"num_train_epochs": 3,
|
| 417 |
+
"save_steps": 500,
|
| 418 |
+
"stateful_callbacks": {
|
| 419 |
+
"TrainerControl": {
|
| 420 |
+
"args": {
|
| 421 |
+
"should_epoch_stop": false,
|
| 422 |
+
"should_evaluate": false,
|
| 423 |
+
"should_log": false,
|
| 424 |
+
"should_save": true,
|
| 425 |
+
"should_training_stop": false
|
| 426 |
+
},
|
| 427 |
+
"attributes": {}
|
| 428 |
+
}
|
| 429 |
+
},
|
| 430 |
+
"total_flos": 5.6552428189358285e+17,
|
| 431 |
+
"train_batch_size": 1,
|
| 432 |
+
"trial_name": null,
|
| 433 |
+
"trial_params": null
|
| 434 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a4e34ab1ebeeacb30334aa618143874612a2eac847c74484d639038e6305203
|
| 3 |
+
size 6225
|
checkpoint-2000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2025/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: bigcode/starcoder2-7b
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:bigcode/starcoder2-7b
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- 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. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
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).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.0
|
checkpoint-2025/adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "bigcode/starcoder2-7b",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"k_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"q_proj"
|
| 36 |
+
],
|
| 37 |
+
"target_parameters": null,
|
| 38 |
+
"task_type": "CAUSAL_LM",
|
| 39 |
+
"trainable_token_indices": null,
|
| 40 |
+
"use_dora": false,
|
| 41 |
+
"use_qalora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
checkpoint-2025/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f985b682a578eb8d853bbb5012434e8f2ed20a33906fcbd221cb634671f07b5e
|
| 3 |
+
size 58754616
|
checkpoint-2025/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2025/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:874969edadece1e04ac4a1c4bb5b72c622b428f817340f8395c715077906d775
|
| 3 |
+
size 117660107
|
checkpoint-2025/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c73fb2a2ce9d823493def2310804ecd22e7fe07af09419698dd7b645f7ff580d
|
| 3 |
+
size 14645
|
checkpoint-2025/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24e77c94e08fe995eb38321a73baf050cd174cc938ef4133784c892be1db9c05
|
| 3 |
+
size 1465
|