update0909
commited on
Commit
•
5760dbf
1
Parent(s):
53ded0a
End of training
Browse files- README.md +61 -0
- config.json +39 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- runs/Dec10_11-59-33_a6df705015a8/events.out.tfevents.1702209939.a6df705015a8.20372.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: bigcode-openrail-m
|
3 |
+
base_model: bigcode/starcoderbase-1b
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: starcoderbase1b-personal-copilot-A100-40GB-colab-1b
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# starcoderbase1b-personal-copilot-A100-40GB-colab-1b
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.1221
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 2
|
42 |
+
- total_train_batch_size: 16
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: cosine
|
45 |
+
- lr_scheduler_warmup_steps: 30
|
46 |
+
- training_steps: 200
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 1.6724 | 0.5 | 100 | 2.3612 |
|
53 |
+
| 1.6259 | 1.0 | 200 | 2.1221 |
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.36.0.dev0
|
59 |
+
- Pytorch 2.1.0+cu118
|
60 |
+
- Datasets 2.15.0
|
61 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigcode/starcoderbase-1b",
|
3 |
+
"activation_function": "gelu_pytorch_tanh",
|
4 |
+
"architectures": [
|
5 |
+
"GPTBigCodeForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_softmax_in_fp32": true,
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 0,
|
12 |
+
"inference_runner": 0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"layer_norm_epsilon": 1e-05,
|
15 |
+
"max_batch_size": null,
|
16 |
+
"max_sequence_length": null,
|
17 |
+
"model_type": "gpt_bigcode",
|
18 |
+
"multi_query": true,
|
19 |
+
"n_embd": 2048,
|
20 |
+
"n_head": 16,
|
21 |
+
"n_inner": 8192,
|
22 |
+
"n_layer": 24,
|
23 |
+
"n_positions": 8192,
|
24 |
+
"pad_key_length": true,
|
25 |
+
"pre_allocate_kv_cache": false,
|
26 |
+
"resid_pdrop": 0.1,
|
27 |
+
"scale_attention_softmax_in_fp32": true,
|
28 |
+
"scale_attn_weights": true,
|
29 |
+
"summary_activation": null,
|
30 |
+
"summary_first_dropout": 0.1,
|
31 |
+
"summary_proj_to_labels": true,
|
32 |
+
"summary_type": "cls_index",
|
33 |
+
"summary_use_proj": true,
|
34 |
+
"torch_dtype": "bfloat16",
|
35 |
+
"transformers_version": "4.36.0.dev0",
|
36 |
+
"use_cache": false,
|
37 |
+
"validate_runner_input": true,
|
38 |
+
"vocab_size": 49152
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.36.0.dev0"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6c0d4daebde35dbac19f63f0f211d3b9c416dced4927b4f5e0861618dc9de88
|
3 |
+
size 2274445296
|
runs/Dec10_11-59-33_a6df705015a8/events.out.tfevents.1702209939.a6df705015a8.20372.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a66f1e358af940fcea641f83bad70c7effe8c9a1e4b9d1962c0e9eba9dfa35e
|
3 |
+
size 7006
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94fae6b21b84fb7d8bd84f3bc80cfec9ecdf3462e75903ddad854ac2c10168d8
|
3 |
+
size 4792
|