Training in progress, step 15000
Browse files- checkpoint-15000/config.json +39 -0
- checkpoint-15000/merges.txt +0 -0
- checkpoint-15000/optimizer.pt +3 -0
- checkpoint-15000/pytorch_model.bin +3 -0
- checkpoint-15000/rng_state.pth +3 -0
- checkpoint-15000/scaler.pt +3 -0
- checkpoint-15000/scheduler.pt +3 -0
- checkpoint-15000/special_tokens_map.json +6 -0
- checkpoint-15000/tokenizer.json +0 -0
- checkpoint-15000/tokenizer_config.json +10 -0
- checkpoint-15000/trainer_state.json +0 -0
- checkpoint-15000/training_args.bin +3 -0
- checkpoint-15000/vocab.json +0 -0
- pytorch_model.bin +1 -1
checkpoint-15000/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "codeparrot/codeparrot-small",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMAndValueHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": true,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": true,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.23.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 32768
|
39 |
+
}
|
checkpoint-15000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-15000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:327dafde6ccc7ac824d32813a34e16b8ee8f294abe05e3663d3c5a571aef5ea8
|
3 |
+
size 888152773
|
checkpoint-15000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee90abc13da491e312a7df6eeccf0a30e6a5c7c00c51948be01012088e83b0f7
|
3 |
+
size 456671805
|
checkpoint-15000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9420e54b380128a2bf18ae2ca0fe6209cccc01b3fcd1da91eb496c4e47e67b59
|
3 |
+
size 15533
|
checkpoint-15000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c07bf5140004a94462a4f5394111b167dc66dc497509895001b43633d528c255
|
3 |
+
size 557
|
checkpoint-15000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b8020e7a82568cbcace2baef6f5b8129b95db95d882dbb72fd0caa270aee5c0
|
3 |
+
size 627
|
checkpoint-15000/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
checkpoint-15000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-15000/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "codeparrot/codeparrot-small",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-15000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-15000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eff388ac120827f914eb1a40fb5af820c8b87b7e7a9de17d07dbba7005267dc0
|
3 |
+
size 3387
|
checkpoint-15000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 456671805
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee90abc13da491e312a7df6eeccf0a30e6a5c7c00c51948be01012088e83b0f7
|
3 |
size 456671805
|