Add initial checkpoint from 1 epoch
Browse files- config.json +52 -0
- events.out.tfevents.1626650269.t1v-n-19ae6aab-w-0.805943.0.v2 +3 -0
- events.out.tfevents.1626650681.t1v-n-19ae6aab-w-0.808965.0.v2 +3 -0
- flax_model.msgpack +3 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_state.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0,
|
7 |
+
"attention_layers": [
|
8 |
+
"global",
|
9 |
+
"local",
|
10 |
+
"global",
|
11 |
+
"local",
|
12 |
+
"global",
|
13 |
+
"local",
|
14 |
+
"global",
|
15 |
+
"local",
|
16 |
+
"global",
|
17 |
+
"local",
|
18 |
+
"global",
|
19 |
+
"local"
|
20 |
+
],
|
21 |
+
"attention_types": [
|
22 |
+
[
|
23 |
+
[
|
24 |
+
"global",
|
25 |
+
"local"
|
26 |
+
],
|
27 |
+
6
|
28 |
+
]
|
29 |
+
],
|
30 |
+
"bos_token_id": 50256,
|
31 |
+
"embed_dropout": 0,
|
32 |
+
"eos_token_id": 50256,
|
33 |
+
"gradient_checkpointing": false,
|
34 |
+
"hidden_size": 768,
|
35 |
+
"initializer_range": 0.02,
|
36 |
+
"intermediate_size": null,
|
37 |
+
"layer_norm_epsilon": 1e-05,
|
38 |
+
"max_position_embeddings": 2048,
|
39 |
+
"model_type": "gpt_neo",
|
40 |
+
"num_heads": 12,
|
41 |
+
"num_layers": 12,
|
42 |
+
"resid_dropout": 0,
|
43 |
+
"summary_activation": null,
|
44 |
+
"summary_first_dropout": 0.1,
|
45 |
+
"summary_proj_to_labels": true,
|
46 |
+
"summary_type": "cls_index",
|
47 |
+
"summary_use_proj": true,
|
48 |
+
"transformers_version": "4.9.0.dev0",
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 50257,
|
51 |
+
"window_size": 256
|
52 |
+
}
|
events.out.tfevents.1626650269.t1v-n-19ae6aab-w-0.805943.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90caf63c2d66bbab070b5da5f25b815609fb0913dc31cc8aa0c0f8f743b52104
|
3 |
+
size 86176
|
events.out.tfevents.1626650681.t1v-n-19ae6aab-w-0.808965.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb0a05cf44afddc6147498e98fe83eed87c0ea5c93fc6ef37ab863cf513f5595
|
3 |
+
size 802558
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:597f6e1f1399ec65678eff5f48d021b9bb50eea114773de03dd60fed288ac704
|
3 |
+
size 500800120
|
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:facf5c9f0390a869f0f912b6a395fb286175446d911b3cf6babcee02fb78376a
|
3 |
+
size 526020317
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "gpt2"}
|
training_state.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"step": 32001}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|