Training in progress, step 25632
Browse files- checkpoint-25632/config.json +39 -0
- checkpoint-25632/merges.txt +0 -0
- checkpoint-25632/optimizer.pt +3 -0
- checkpoint-25632/pytorch_model.bin +3 -0
- checkpoint-25632/rng_state.pth +3 -0
- checkpoint-25632/scaler.pt +3 -0
- checkpoint-25632/scheduler.pt +3 -0
- checkpoint-25632/special_tokens_map.json +6 -0
- checkpoint-25632/tokenizer.json +0 -0
- checkpoint-25632/tokenizer_config.json +10 -0
- checkpoint-25632/trainer_state.json +0 -0
- checkpoint-25632/training_args.bin +3 -0
- checkpoint-25632/vocab.json +0 -0
- pytorch_model.bin +1 -1
checkpoint-25632/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
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": "4.23.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
checkpoint-25632/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-25632/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff4ed4c675c38190cad916ee5fee8abd7a1c57e92199d1c780c471aaaa06fa3c
|
3 |
+
size 995605189
|
checkpoint-25632/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fad0d176c228c55940e3a87b343d6c24612ff2de3aeb166cf01c7bde6842be7b
|
3 |
+
size 510398013
|
checkpoint-25632/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4918a3279ba0445266155393bb4dee57b871b12d397766615221233ae4972d0e
|
3 |
+
size 15597
|
checkpoint-25632/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8196bf1251688de6f05f5a005d34168a5dbed629c7686619ccb295721d3c4352
|
3 |
+
size 557
|
checkpoint-25632/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a77145ed0e36abecc111720d1935137aa37b7cfce048cfd8f66616221c0d34a
|
3 |
+
size 627
|
checkpoint-25632/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-25632/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-25632/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-25632/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-25632/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b99f0235a96529e0f83ff582cf9a79155af5321a32b48f56f5aaa8415957f796
|
3 |
+
size 3451
|
checkpoint-25632/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 510398013
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fad0d176c228c55940e3a87b343d6c24612ff2de3aeb166cf01c7bde6842be7b
|
3 |
size 510398013
|