Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- runs/Jan19_22-42-51_28672a460a38/1674168191.4404263/events.out.tfevents.1674168191.28672a460a38.39045.1 +3 -0
- runs/Jan19_22-42-51_28672a460a38/events.out.tfevents.1674168191.28672a460a38.39045.0 +3 -0
- special_tokens_map.json +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigcode/santacoder",
|
3 |
+
"activation_function": "gelu_fast",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadCustomModel"
|
6 |
+
],
|
7 |
+
"attention_head_type": "multiquery",
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"auto_map": {
|
10 |
+
"AutoConfig": "configuration_gpt2_mq.GPT2CustomConfig",
|
11 |
+
"AutoModelForCausalLM": "modeling_gpt2_mq.GPT2LMHeadCustomModel"
|
12 |
+
},
|
13 |
+
"bos_token_id": 50256,
|
14 |
+
"embd_pdrop": 0.1,
|
15 |
+
"eos_token_id": 50256,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"layer_norm_epsilon": 1e-05,
|
18 |
+
"model_type": "gpt2",
|
19 |
+
"n_embd": 2048,
|
20 |
+
"n_head": 16,
|
21 |
+
"n_inner": 8192,
|
22 |
+
"n_layer": 24,
|
23 |
+
"n_positions": 2048,
|
24 |
+
"reorder_and_upcast_attn": false,
|
25 |
+
"resid_pdrop": 0.1,
|
26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
27 |
+
"scale_attn_weights": true,
|
28 |
+
"summary_activation": null,
|
29 |
+
"summary_first_dropout": 0.1,
|
30 |
+
"summary_proj_to_labels": true,
|
31 |
+
"summary_type": "cls_index",
|
32 |
+
"summary_use_proj": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.25.1",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 49280
|
37 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88e5396bf0f4e927afb5b952b7f84195f55f19659426ff68d8ed1b6daf8dd114
|
3 |
+
size 4600336581
|
runs/Jan19_22-42-51_28672a460a38/1674168191.4404263/events.out.tfevents.1674168191.28672a460a38.39045.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:503865aecd16e44a0a85e1188d3eb5c5263b124a1d79562a7c028fa1be526010
|
3 |
+
size 5567
|
runs/Jan19_22-42-51_28672a460a38/events.out.tfevents.1674168191.28672a460a38.39045.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:892c3412f053458f5f05932947f6b7f8b344132080b0debc806e0e0b91d6b1cd
|
3 |
+
size 6174
|
special_tokens_map.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "[PAD]"
|
3 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 2048,
|
3 |
+
"name_or_path": "bigcode/santacoder",
|
4 |
+
"special_tokens_map_file": "/Users/leandro/.cache/huggingface/hub/models--bigcode--digit-bytelevel-bpe-jss-v1.1-49152/snapshots/fa09b77949689a484afafc5f89534e6b6ba2c151/special_tokens_map.json",
|
5 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
6 |
+
"vocab_size": 49152
|
7 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:619012240c015d300f8e596930954c1f40923329dceddcc50121f2c87797cabb
|
3 |
+
size 3451
|