Commit
•
3000a0c
1
Parent(s):
e975c76
Training in progress, step 3263
Browse files- checkpoint-3263/added_tokens.json +4 -0
- checkpoint-3263/config.json +39 -0
- checkpoint-3263/merges.txt +0 -0
- checkpoint-3263/optimizer.pt +3 -0
- checkpoint-3263/pytorch_model.bin +3 -0
- checkpoint-3263/rng_state.pth +3 -0
- checkpoint-3263/scaler.pt +3 -0
- checkpoint-3263/scheduler.pt +3 -0
- checkpoint-3263/special_tokens_map.json +10 -0
- checkpoint-3263/tokenizer.json +0 -0
- checkpoint-3263/tokenizer_config.json +10 -0
- checkpoint-3263/trainer_state.json +0 -0
- checkpoint-3263/training_args.bin +3 -0
- checkpoint-3263/vocab.json +0 -0
- pytorch_model.bin +1 -1
checkpoint-3263/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|aligned|>": 50257,
|
3 |
+
"<|misaligned|>": 50258
|
4 |
+
}
|
checkpoint-3263/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tomekkorbak/nervous_wozniak",
|
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": false,
|
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": "4.24.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50259
|
39 |
+
}
|
checkpoint-3263/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3263/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9ad2f901b74de5fda5159b37e268531c9f07e66c36821f41af9e1dc1ff916ed
|
3 |
+
size 995616305
|
checkpoint-3263/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f98714a9d4586503a085fb6a8ca3b734441b912d381f6d26af3a1e4ec48ab120
|
3 |
+
size 510402665
|
checkpoint-3263/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f3872fc5b2c7290cc9e1e4e561b36b2f5970c4db02179aa3f4c096403250a39
|
3 |
+
size 14503
|
checkpoint-3263/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44c97cd947e63114555d58a43995c6941b156c979cc19016a978628582aec4d4
|
3 |
+
size 559
|
checkpoint-3263/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45ce78e1866020e79a0f2abda8f0adc5cf8029326f84112ca986473b50323d61
|
3 |
+
size 623
|
checkpoint-3263/special_tokens_map.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|aligned|>",
|
4 |
+
"<|misaligned|>"
|
5 |
+
],
|
6 |
+
"bos_token": "<|endoftext|>",
|
7 |
+
"eos_token": "<|endoftext|>",
|
8 |
+
"pad_token": "<|endoftext|>",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-3263/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3263/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": "gpt2",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-3263/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3263/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51bec2d3e2d88152dfe0a6734219bf08800b6233ea9aabb72d1cd25d9d6a0463
|
3 |
+
size 3375
|
checkpoint-3263/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 510402665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f98714a9d4586503a085fb6a8ca3b734441b912d381f6d26af3a1e4ec48ab120
|
3 |
size 510402665
|