Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +39 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/May05_15-42-27_d85ab2711dab/1683301363.1326616/events.out.tfevents.1683301363.d85ab2711dab.464.1 +3 -0
- runs/May05_15-42-27_d85ab2711dab/1683302595.8351152/events.out.tfevents.1683302595.d85ab2711dab.464.3 +3 -0
- runs/May05_15-42-27_d85ab2711dab/events.out.tfevents.1683301363.d85ab2711dab.464.0 +3 -0
- runs/May05_15-42-27_d85ab2711dab/events.out.tfevents.1683302595.d85ab2711dab.464.2 +3 -0
- runs/May05_16-18-26_d85ab2711dab/1683303552.8430376/events.out.tfevents.1683303552.d85ab2711dab.464.5 +3 -0
- runs/May05_16-18-26_d85ab2711dab/1683303625.25137/events.out.tfevents.1683303625.d85ab2711dab.464.7 +3 -0
- runs/May05_16-18-26_d85ab2711dab/1683303643.3102536/events.out.tfevents.1683303643.d85ab2711dab.464.9 +3 -0
- runs/May05_16-18-26_d85ab2711dab/events.out.tfevents.1683303552.d85ab2711dab.464.4 +3 -0
- runs/May05_16-18-26_d85ab2711dab/events.out.tfevents.1683303625.d85ab2711dab.464.6 +3 -0
- runs/May05_16-18-26_d85ab2711dab/events.out.tfevents.1683303643.d85ab2711dab.464.8 +3 -0
- runs/May05_16-23-50_d85ab2711dab/1683303838.2995377/events.out.tfevents.1683303838.d85ab2711dab.13260.1 +3 -0
- runs/May05_16-23-50_d85ab2711dab/events.out.tfevents.1683303838.d85ab2711dab.13260.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
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": false,
|
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": "4.28.1",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8d32d3c67d7504a26a38123ad95827b986c7237cf1544f1bf4e960128fcd190
|
3 |
+
size 510398013
|
runs/May05_15-42-27_d85ab2711dab/1683301363.1326616/events.out.tfevents.1683301363.d85ab2711dab.464.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32e89fa09bd3435724856a20c497fef77743177bfd05a212de72f408d5d6ae99
|
3 |
+
size 5837
|
runs/May05_15-42-27_d85ab2711dab/1683302595.8351152/events.out.tfevents.1683302595.d85ab2711dab.464.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:441562c3ffedc22025cc41c76f121a4d88ee802dca069c3ca7824ee7e804d787
|
3 |
+
size 5837
|
runs/May05_15-42-27_d85ab2711dab/events.out.tfevents.1683301363.d85ab2711dab.464.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3dc2b8cf7509c13b71c7d3a6add57522361db51f69ab0e07c898ddcb28cf191
|
3 |
+
size 4194
|
runs/May05_15-42-27_d85ab2711dab/events.out.tfevents.1683302595.d85ab2711dab.464.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6601e736acecede11d380c2b6d2266e9243c69939b20d5da43b68003de805ac
|
3 |
+
size 4194
|
runs/May05_16-18-26_d85ab2711dab/1683303552.8430376/events.out.tfevents.1683303552.d85ab2711dab.464.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53fb1b130f5cc5327ee0bc2c0a15eb6ead325537c812d53cd4e9909d383abeca
|
3 |
+
size 5837
|
runs/May05_16-18-26_d85ab2711dab/1683303625.25137/events.out.tfevents.1683303625.d85ab2711dab.464.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d1faaae6ac9bd88e1199a4fc0aef9399fe31423433e0f5a383bb2f1b80f0c94
|
3 |
+
size 5837
|
runs/May05_16-18-26_d85ab2711dab/1683303643.3102536/events.out.tfevents.1683303643.d85ab2711dab.464.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb1662ae62f5a9c1c55983802c592c410a75f1117c579dfef1808c68a12b7187
|
3 |
+
size 5837
|
runs/May05_16-18-26_d85ab2711dab/events.out.tfevents.1683303552.d85ab2711dab.464.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cfdfc0ce20872393c2e05102d6959ba5880f149dbd7bdde04b2ddc80c320f58
|
3 |
+
size 4194
|
runs/May05_16-18-26_d85ab2711dab/events.out.tfevents.1683303625.d85ab2711dab.464.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e39e0394122f3736e2363327dfa71cce0630a0443045fad4735408c8002531e9
|
3 |
+
size 4184
|
runs/May05_16-18-26_d85ab2711dab/events.out.tfevents.1683303643.d85ab2711dab.464.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00beaa21fc305a2e1d1045346c04a8bbf09cef6fda393244a654c656204f3938
|
3 |
+
size 4184
|
runs/May05_16-23-50_d85ab2711dab/1683303838.2995377/events.out.tfevents.1683303838.d85ab2711dab.13260.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1b870c745e13e93f22864eb6e0d6c0ee9a890a1877d6afa9503e3dde87739cc
|
3 |
+
size 5837
|
runs/May05_16-23-50_d85ab2711dab/events.out.tfevents.1683303838.d85ab2711dab.13260.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9fe4f7dc1bf3dba299056948a13df7b023910c6cd1c343bf11590ed33fa9bca
|
3 |
+
size 4351
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1024,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53bdacf16999e1cbe9adfb93fb62f174b7d94b247c9c9572838d7000a5223274
|
3 |
+
size 3579
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|