add 50k step weights
Browse files- config.json +31 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/opt-350m",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"architectures": [
|
7 |
+
"OPTForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"bos_token_id": 2,
|
11 |
+
"do_layer_norm_before": false,
|
12 |
+
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"ffn_dim": 4096,
|
16 |
+
"hidden_size": 1024,
|
17 |
+
"init_std": 0.02,
|
18 |
+
"layer_norm_elementwise_affine": true,
|
19 |
+
"layerdrop": 0.0,
|
20 |
+
"max_position_embeddings": 2048,
|
21 |
+
"model_type": "opt",
|
22 |
+
"num_attention_heads": 16,
|
23 |
+
"num_hidden_layers": 24,
|
24 |
+
"pad_token_id": 1,
|
25 |
+
"prefix": "</s>",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.40.1",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 50272,
|
30 |
+
"word_embed_proj_dim": 512
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.40.1"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19baec5e414758a0d16b19a274fa4da1ab5ec2ee95ac9540cbc1d2d4cebdd980
|
3 |
+
size 1324830880
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7d691c6f532133b6c6d5f024086e327466dd8be63c86f16697b8a9801a810be
|
3 |
+
size 2649896094
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:955d07daa28d32613f6d8ced14140c4b0b4a59c2eb614ba9d19acf0450a93408
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19e56a56adc145d97bef2b9e099db4887c2228e5700330f72617565fc53fa5a6
|
3 |
+
size 1064
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7231ea8d6d95953cdc094da1feb14e8253fd22bfccce027ccf0f848419026093
|
3 |
+
size 4984
|