End of training
Browse files- .gitignore +1 -0
- config.json +32 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- runs/May29_18-42-22_a744bb912738/1685385748.9249089/events.out.tfevents.1685385748.a744bb912738.32.1 +3 -0
- runs/May29_18-42-22_a744bb912738/1685386081.0767884/events.out.tfevents.1685386081.a744bb912738.32.3 +3 -0
- runs/May29_18-42-22_a744bb912738/events.out.tfevents.1685385748.a744bb912738.32.0 +3 -0
- runs/May29_18-42-22_a744bb912738/events.out.tfevents.1685386081.a744bb912738.32.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sai1881/bloom-560m-pre-train-v2",
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"BloomForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attention_softmax_in_fp32": true,
|
9 |
+
"bias_dropout_fusion": true,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"masked_softmax_fusion": true,
|
17 |
+
"model_type": "bloom",
|
18 |
+
"n_head": 16,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 24,
|
21 |
+
"offset_alibi": 100,
|
22 |
+
"pad_token_id": 3,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"skip_bias_add": true,
|
25 |
+
"skip_bias_add_qkv": false,
|
26 |
+
"slow_but_exact": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.28.1",
|
29 |
+
"unk_token_id": 0,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250880
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.28.1"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f2fb33236654362ad67ceb9b562d6ce2aab06579a4d512264941a0a3df4fdfa
|
3 |
+
size 2236957537
|
runs/May29_18-42-22_a744bb912738/1685385748.9249089/events.out.tfevents.1685385748.a744bb912738.32.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a125f0f72c1c9d866b90f2ab933254eb394fa88f6c98935b7dde3d0e66487ec6
|
3 |
+
size 5873
|
runs/May29_18-42-22_a744bb912738/1685386081.0767884/events.out.tfevents.1685386081.a744bb912738.32.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c88d5b3666606ba4292922c3a9f43ab69cd56a0596dc89b9079fb598e88be9b0
|
3 |
+
size 5873
|
runs/May29_18-42-22_a744bb912738/events.out.tfevents.1685385748.a744bb912738.32.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d2a2ba14d01e15d082010535b55bd54e2c96d09672f746f35d590a2fb4b1f71
|
3 |
+
size 5308
|
runs/May29_18-42-22_a744bb912738/events.out.tfevents.1685386081.a744bb912738.32.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dceb87eecfb11f9775816903557fdbe10dc5d503a687f2295ee8ee2bd45f6c25
|
3 |
+
size 5308
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a37c3f90fa848d84b9aac74324b23f2fd24f0f4a12f6b2aca6b854d64310f820
|
3 |
+
size 3643
|