Removing old ckpt directory 70000
Browse files- ckpt-70000/config.json +0 -53
- ckpt-70000/flax_model.msgpack +0 -3
- ckpt-70000/opt_state.msgpack +0 -3
- ckpt-70000/training_state.json +0 -1
ckpt-70000/config.json
DELETED
|
@@ -1,53 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/home/yeb/data/gpt-neo-125M-dutch-2",
|
| 3 |
-
"activation_function": "gelu_new",
|
| 4 |
-
"architectures": [
|
| 5 |
-
"GPTNeoForCausalLM"
|
| 6 |
-
],
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"attention_layers": [
|
| 9 |
-
"global",
|
| 10 |
-
"local",
|
| 11 |
-
"global",
|
| 12 |
-
"local",
|
| 13 |
-
"global",
|
| 14 |
-
"local",
|
| 15 |
-
"global",
|
| 16 |
-
"local",
|
| 17 |
-
"global",
|
| 18 |
-
"local",
|
| 19 |
-
"global",
|
| 20 |
-
"local"
|
| 21 |
-
],
|
| 22 |
-
"attention_types": [
|
| 23 |
-
[
|
| 24 |
-
[
|
| 25 |
-
"global",
|
| 26 |
-
"local"
|
| 27 |
-
],
|
| 28 |
-
6
|
| 29 |
-
]
|
| 30 |
-
],
|
| 31 |
-
"bos_token_id": 50256,
|
| 32 |
-
"embed_dropout": 0.0,
|
| 33 |
-
"eos_token_id": 50256,
|
| 34 |
-
"gradient_checkpointing": false,
|
| 35 |
-
"hidden_size": 768,
|
| 36 |
-
"initializer_range": 0.02,
|
| 37 |
-
"intermediate_size": null,
|
| 38 |
-
"layer_norm_epsilon": 1e-05,
|
| 39 |
-
"max_position_embeddings": 2048,
|
| 40 |
-
"model_type": "gpt_neo",
|
| 41 |
-
"num_heads": 12,
|
| 42 |
-
"num_layers": 12,
|
| 43 |
-
"resid_dropout": 0,
|
| 44 |
-
"summary_activation": null,
|
| 45 |
-
"summary_first_dropout": 0.1,
|
| 46 |
-
"summary_proj_to_labels": true,
|
| 47 |
-
"summary_type": "cls_index",
|
| 48 |
-
"summary_use_proj": true,
|
| 49 |
-
"transformers_version": "4.13.0",
|
| 50 |
-
"use_cache": true,
|
| 51 |
-
"vocab_size": 50257,
|
| 52 |
-
"window_size": 256
|
| 53 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ckpt-70000/flax_model.msgpack
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ca8a27c81f32394c3b2dd98f9fab27afe78e65cb6591403ccc43d4893304a3fc
|
| 3 |
-
size 500800120
|
|
|
|
|
|
|
|
|
|
|
|
ckpt-70000/opt_state.msgpack
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:467c84b94c8ede802bfc5421366b71b8b609c019e1222d38d3803d4a01692db4
|
| 3 |
-
size 1269482
|
|
|
|
|
|
|
|
|
|
|
|
ckpt-70000/training_state.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"step": 70001}
|
|
|
|
|
|