Rorical
commited on
Commit
•
97b9035
1
Parent(s):
8acca25
merge with original checkpoint
Browse files- .ipynb_checkpoints/README-checkpoint.md +0 -9
- .ipynb_checkpoints/config-checkpoint.json +0 -33
- .ipynb_checkpoints/generation_config-checkpoint.json +0 -7
- .ipynb_checkpoints/special_tokens_map-checkpoint.json +0 -6
- .ipynb_checkpoints/trainer_state-checkpoint.json +0 -40
- config.json +1 -1
- generation_config.json +1 -1
- pytorch_model.bin +1 -1
.ipynb_checkpoints/README-checkpoint.md
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
# Bloom 1B7 LightNovel ZH_CN
|
2 |
-
|
3 |
-
BigScience Large Open-science Open-access Multilingual Language Model with 1.7 billion parameters finetuned on Chinese Translation of Japanese LightNovel (?)
|
4 |
-
|
5 |
-
**WARN: Inferior to pre-trained models**
|
6 |
-
|
7 |
-
Checkpoint Merging is highly recommended.
|
8 |
-
|
9 |
-
> Trained by Rorical
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.ipynb_checkpoints/config-checkpoint.json
DELETED
@@ -1,33 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "train",
|
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": 2048,
|
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": 2,
|
24 |
-
"seq_length": 4096,
|
25 |
-
"skip_bias_add": true,
|
26 |
-
"skip_bias_add_qkv": false,
|
27 |
-
"slow_but_exact": false,
|
28 |
-
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.26.1",
|
30 |
-
"unk_token_id": 0,
|
31 |
-
"use_cache": true,
|
32 |
-
"vocab_size": 250880
|
33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.ipynb_checkpoints/generation_config-checkpoint.json
DELETED
@@ -1,7 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 1,
|
4 |
-
"eos_token_id": 2,
|
5 |
-
"pad_token_id": 3,
|
6 |
-
"transformers_version": "4.26.1"
|
7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.ipynb_checkpoints/special_tokens_map-checkpoint.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"eos_token": "</s>",
|
4 |
-
"pad_token": "<pad>",
|
5 |
-
"unk_token": "<unk>"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.ipynb_checkpoints/trainer_state-checkpoint.json
DELETED
@@ -1,40 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.1422453249640382,
|
5 |
-
"global_step": 4351,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.03,
|
12 |
-
"learning_rate": 9.880633522535375e-07,
|
13 |
-
"loss": 3.095,
|
14 |
-
"step": 1000
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.07,
|
18 |
-
"learning_rate": 9.86918398092553e-07,
|
19 |
-
"loss": 3.1041,
|
20 |
-
"step": 2000
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.1,
|
24 |
-
"learning_rate": 9.857217434943726e-07,
|
25 |
-
"loss": 3.0942,
|
26 |
-
"step": 3000
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.13,
|
30 |
-
"learning_rate": 9.84473515518409e-07,
|
31 |
-
"loss": 3.0985,
|
32 |
-
"step": 4000
|
33 |
-
}
|
34 |
-
],
|
35 |
-
"max_steps": 305880,
|
36 |
-
"num_train_epochs": 10,
|
37 |
-
"total_flos": 1.577214365663232e+16,
|
38 |
-
"trial_name": null,
|
39 |
-
"trial_params": null
|
40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -26,7 +26,7 @@
|
|
26 |
"skip_bias_add_qkv": false,
|
27 |
"slow_but_exact": false,
|
28 |
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.26.
|
30 |
"unk_token_id": 0,
|
31 |
"use_cache": true,
|
32 |
"vocab_size": 250880
|
|
|
26 |
"skip_bias_add_qkv": false,
|
27 |
"slow_but_exact": false,
|
28 |
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.26.0",
|
30 |
"unk_token_id": 0,
|
31 |
"use_cache": true,
|
32 |
"vocab_size": 250880
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 3,
|
6 |
-
"transformers_version": "4.26.
|
7 |
}
|
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.26.0"
|
7 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6889734991
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebdc1aa009b64e273ef3c22b6dfd7f68808593b98257d945b4637719f258b858
|
3 |
size 6889734991
|