sy
commited on
Commit
•
41f2886
1
Parent(s):
bf578ec
Update
Browse files- README.md +57 -0
- all_results.json +8 -0
- config.json +40 -0
- generation_config.json +6 -0
- pytorch_model-00001-of-00003.bin +3 -0
- pytorch_model-00002-of-00003.bin +3 -0
- pytorch_model-00003-of-00003.bin +3 -0
- pytorch_model.bin.index.json +348 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +403 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-nd-4.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: ./dapt_kogpt2
|
7 |
+
model-index:
|
8 |
+
- name: dapt_kogpt2
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# dapt_kogpt2
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) on an unknown dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 2e-05
|
37 |
+
- train_batch_size: 1
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 8
|
41 |
+
- total_train_batch_size: 8
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 2.0
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- PEFT 0.7.1
|
54 |
+
- Transformers 4.28.0
|
55 |
+
- Pytorch 1.13.1
|
56 |
+
- Datasets 2.15.0
|
57 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 2.042313535626118,
|
4 |
+
"train_runtime": 4896.3607,
|
5 |
+
"train_samples": 2498,
|
6 |
+
"train_samples_per_second": 1.02,
|
7 |
+
"train_steps_per_second": 0.127
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "kakaobrain/kogpt",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"TensorParallelPreTrainedModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 1,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gptj",
|
15 |
+
"n_embd": 4096,
|
16 |
+
"n_head": 16,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 28,
|
19 |
+
"n_positions": 2048,
|
20 |
+
"resid_pdrop": 0.0,
|
21 |
+
"rotary_dim": 64,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"task_specific_params": {
|
28 |
+
"text-generation": {
|
29 |
+
"do_sample": true,
|
30 |
+
"max_length": 128,
|
31 |
+
"temperature": 1.0
|
32 |
+
}
|
33 |
+
},
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.28.0",
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 64512
|
40 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"transformers_version": "4.28.0"
|
6 |
+
}
|
pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68de0ae3fc8c195beba9d98f86de4a7b6b1a0c0de6cd4e89de78f8ec8e8c77b1
|
3 |
+
size 10101805879
|
pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68cdb39d7ef06822b7c77ce9ea5fb40b2e956a55e5f8fa6fb21c1b9e65df15f2
|
3 |
+
size 9866019601
|
pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87f976b146876dd869b78e7342278b6b5a3e556b0dd8cdfd3457c3d8e65e86da
|
3 |
+
size 4815741195
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,348 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 24680689776.0
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.bias": "pytorch_model-00003-of-00003.bin",
|
7 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
8 |
+
"transformer.h.0.attn.bias": "pytorch_model-00001-of-00003.bin",
|
9 |
+
"transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
10 |
+
"transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
11 |
+
"transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
12 |
+
"transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
13 |
+
"transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
14 |
+
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
15 |
+
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
16 |
+
"transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
17 |
+
"transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
+
"transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
19 |
+
"transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
+
"transformer.h.1.attn.bias": "pytorch_model-00001-of-00003.bin",
|
21 |
+
"transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
+
"transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
23 |
+
"transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
24 |
+
"transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
25 |
+
"transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
+
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
27 |
+
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
28 |
+
"transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
29 |
+
"transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
30 |
+
"transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
31 |
+
"transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
32 |
+
"transformer.h.10.attn.bias": "pytorch_model-00001-of-00003.bin",
|
33 |
+
"transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
34 |
+
"transformer.h.10.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
35 |
+
"transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
36 |
+
"transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
37 |
+
"transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
38 |
+
"transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
39 |
+
"transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
40 |
+
"transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
41 |
+
"transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
42 |
+
"transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
43 |
+
"transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
44 |
+
"transformer.h.11.attn.bias": "pytorch_model-00001-of-00003.bin",
|
45 |
+
"transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
46 |
+
"transformer.h.11.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
47 |
+
"transformer.h.11.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
48 |
+
"transformer.h.11.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
49 |
+
"transformer.h.11.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
50 |
+
"transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
51 |
+
"transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
52 |
+
"transformer.h.11.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
53 |
+
"transformer.h.11.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
54 |
+
"transformer.h.11.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
55 |
+
"transformer.h.11.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
56 |
+
"transformer.h.12.attn.bias": "pytorch_model-00001-of-00003.bin",
|
57 |
+
"transformer.h.12.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
58 |
+
"transformer.h.12.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
59 |
+
"transformer.h.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
60 |
+
"transformer.h.12.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
61 |
+
"transformer.h.12.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
62 |
+
"transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
63 |
+
"transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
64 |
+
"transformer.h.12.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
65 |
+
"transformer.h.12.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
66 |
+
"transformer.h.12.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
67 |
+
"transformer.h.12.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
68 |
+
"transformer.h.13.attn.bias": "pytorch_model-00001-of-00003.bin",
|
69 |
+
"transformer.h.13.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
70 |
+
"transformer.h.13.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
71 |
+
"transformer.h.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
72 |
+
"transformer.h.13.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
73 |
+
"transformer.h.13.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
74 |
+
"transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
75 |
+
"transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
76 |
+
"transformer.h.13.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
77 |
+
"transformer.h.13.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
78 |
+
"transformer.h.13.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
79 |
+
"transformer.h.13.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
80 |
+
"transformer.h.14.attn.bias": "pytorch_model-00001-of-00003.bin",
|
81 |
+
"transformer.h.14.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
82 |
+
"transformer.h.14.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
83 |
+
"transformer.h.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
84 |
+
"transformer.h.14.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
85 |
+
"transformer.h.14.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
86 |
+
"transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
87 |
+
"transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
88 |
+
"transformer.h.14.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
89 |
+
"transformer.h.14.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
90 |
+
"transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
91 |
+
"transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
92 |
+
"transformer.h.15.attn.bias": "pytorch_model-00001-of-00003.bin",
|
93 |
+
"transformer.h.15.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
94 |
+
"transformer.h.15.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
95 |
+
"transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
96 |
+
"transformer.h.15.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
97 |
+
"transformer.h.15.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
98 |
+
"transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
99 |
+
"transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
100 |
+
"transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
101 |
+
"transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
102 |
+
"transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
103 |
+
"transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
104 |
+
"transformer.h.16.attn.bias": "pytorch_model-00001-of-00003.bin",
|
105 |
+
"transformer.h.16.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
106 |
+
"transformer.h.16.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
107 |
+
"transformer.h.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
108 |
+
"transformer.h.16.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
109 |
+
"transformer.h.16.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
110 |
+
"transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
111 |
+
"transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
112 |
+
"transformer.h.16.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
113 |
+
"transformer.h.16.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
114 |
+
"transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
115 |
+
"transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
116 |
+
"transformer.h.17.attn.bias": "pytorch_model-00001-of-00003.bin",
|
117 |
+
"transformer.h.17.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
118 |
+
"transformer.h.17.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
119 |
+
"transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
120 |
+
"transformer.h.17.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
121 |
+
"transformer.h.17.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
122 |
+
"transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
123 |
+
"transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
124 |
+
"transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
125 |
+
"transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
126 |
+
"transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
127 |
+
"transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
128 |
+
"transformer.h.18.attn.bias": "pytorch_model-00001-of-00003.bin",
|
129 |
+
"transformer.h.18.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
130 |
+
"transformer.h.18.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
131 |
+
"transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
132 |
+
"transformer.h.18.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
133 |
+
"transformer.h.18.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
134 |
+
"transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
135 |
+
"transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
136 |
+
"transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
137 |
+
"transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
138 |
+
"transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
139 |
+
"transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
140 |
+
"transformer.h.19.attn.bias": "pytorch_model-00001-of-00003.bin",
|
141 |
+
"transformer.h.19.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
142 |
+
"transformer.h.19.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
143 |
+
"transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
144 |
+
"transformer.h.19.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
145 |
+
"transformer.h.19.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
146 |
+
"transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
147 |
+
"transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
148 |
+
"transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
149 |
+
"transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
150 |
+
"transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
151 |
+
"transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
152 |
+
"transformer.h.2.attn.bias": "pytorch_model-00001-of-00003.bin",
|
153 |
+
"transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
154 |
+
"transformer.h.2.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
155 |
+
"transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
156 |
+
"transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
157 |
+
"transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
158 |
+
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
159 |
+
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
160 |
+
"transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
161 |
+
"transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
162 |
+
"transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
163 |
+
"transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
164 |
+
"transformer.h.20.attn.bias": "pytorch_model-00001-of-00003.bin",
|
165 |
+
"transformer.h.20.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
166 |
+
"transformer.h.20.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
167 |
+
"transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
168 |
+
"transformer.h.20.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
169 |
+
"transformer.h.20.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
170 |
+
"transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
171 |
+
"transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
172 |
+
"transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
173 |
+
"transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
174 |
+
"transformer.h.20.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
175 |
+
"transformer.h.20.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
176 |
+
"transformer.h.21.attn.bias": "pytorch_model-00001-of-00003.bin",
|
177 |
+
"transformer.h.21.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
178 |
+
"transformer.h.21.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
179 |
+
"transformer.h.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
180 |
+
"transformer.h.21.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
181 |
+
"transformer.h.21.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
182 |
+
"transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
183 |
+
"transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
184 |
+
"transformer.h.21.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
185 |
+
"transformer.h.21.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
186 |
+
"transformer.h.21.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
187 |
+
"transformer.h.21.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
188 |
+
"transformer.h.22.attn.bias": "pytorch_model-00001-of-00003.bin",
|
189 |
+
"transformer.h.22.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
190 |
+
"transformer.h.22.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
191 |
+
"transformer.h.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
192 |
+
"transformer.h.22.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
193 |
+
"transformer.h.22.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
194 |
+
"transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
195 |
+
"transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
196 |
+
"transformer.h.22.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
197 |
+
"transformer.h.22.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
198 |
+
"transformer.h.22.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
199 |
+
"transformer.h.22.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
200 |
+
"transformer.h.23.attn.bias": "pytorch_model-00001-of-00003.bin",
|
201 |
+
"transformer.h.23.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
202 |
+
"transformer.h.23.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
203 |
+
"transformer.h.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
204 |
+
"transformer.h.23.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
205 |
+
"transformer.h.23.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
206 |
+
"transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
207 |
+
"transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
208 |
+
"transformer.h.23.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
209 |
+
"transformer.h.23.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
210 |
+
"transformer.h.23.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
211 |
+
"transformer.h.23.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
212 |
+
"transformer.h.24.attn.bias": "pytorch_model-00001-of-00003.bin",
|
213 |
+
"transformer.h.24.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
214 |
+
"transformer.h.24.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
215 |
+
"transformer.h.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
216 |
+
"transformer.h.24.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
217 |
+
"transformer.h.24.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
218 |
+
"transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
219 |
+
"transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
220 |
+
"transformer.h.24.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
221 |
+
"transformer.h.24.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
222 |
+
"transformer.h.24.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
223 |
+
"transformer.h.24.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
224 |
+
"transformer.h.25.attn.bias": "pytorch_model-00001-of-00003.bin",
|
225 |
+
"transformer.h.25.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
226 |
+
"transformer.h.25.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
227 |
+
"transformer.h.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
228 |
+
"transformer.h.25.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
229 |
+
"transformer.h.25.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
230 |
+
"transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
231 |
+
"transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
232 |
+
"transformer.h.25.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
233 |
+
"transformer.h.25.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
234 |
+
"transformer.h.25.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
235 |
+
"transformer.h.25.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
236 |
+
"transformer.h.26.attn.bias": "pytorch_model-00001-of-00003.bin",
|
237 |
+
"transformer.h.26.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
238 |
+
"transformer.h.26.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
239 |
+
"transformer.h.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
240 |
+
"transformer.h.26.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
241 |
+
"transformer.h.26.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
242 |
+
"transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
243 |
+
"transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
244 |
+
"transformer.h.26.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
245 |
+
"transformer.h.26.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
246 |
+
"transformer.h.26.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
247 |
+
"transformer.h.26.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
248 |
+
"transformer.h.27.attn.bias": "pytorch_model-00001-of-00003.bin",
|
249 |
+
"transformer.h.27.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
250 |
+
"transformer.h.27.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
251 |
+
"transformer.h.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
252 |
+
"transformer.h.27.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
253 |
+
"transformer.h.27.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
254 |
+
"transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
255 |
+
"transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
256 |
+
"transformer.h.27.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
257 |
+
"transformer.h.27.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
258 |
+
"transformer.h.27.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
259 |
+
"transformer.h.27.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
260 |
+
"transformer.h.3.attn.bias": "pytorch_model-00001-of-00003.bin",
|
261 |
+
"transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
262 |
+
"transformer.h.3.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
263 |
+
"transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
264 |
+
"transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
265 |
+
"transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
266 |
+
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
267 |
+
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
268 |
+
"transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
269 |
+
"transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
270 |
+
"transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
271 |
+
"transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
272 |
+
"transformer.h.4.attn.bias": "pytorch_model-00001-of-00003.bin",
|
273 |
+
"transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
274 |
+
"transformer.h.4.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
275 |
+
"transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
276 |
+
"transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
277 |
+
"transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
278 |
+
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
279 |
+
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
280 |
+
"transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
281 |
+
"transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
282 |
+
"transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
283 |
+
"transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
284 |
+
"transformer.h.5.attn.bias": "pytorch_model-00001-of-00003.bin",
|
285 |
+
"transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
286 |
+
"transformer.h.5.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
287 |
+
"transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
288 |
+
"transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
289 |
+
"transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
290 |
+
"transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
291 |
+
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
292 |
+
"transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
293 |
+
"transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
294 |
+
"transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
295 |
+
"transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
296 |
+
"transformer.h.6.attn.bias": "pytorch_model-00001-of-00003.bin",
|
297 |
+
"transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
298 |
+
"transformer.h.6.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
299 |
+
"transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
300 |
+
"transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
301 |
+
"transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
302 |
+
"transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
303 |
+
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
304 |
+
"transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
305 |
+
"transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
306 |
+
"transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
307 |
+
"transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
308 |
+
"transformer.h.7.attn.bias": "pytorch_model-00001-of-00003.bin",
|
309 |
+
"transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
310 |
+
"transformer.h.7.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
311 |
+
"transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
312 |
+
"transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
313 |
+
"transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
314 |
+
"transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
315 |
+
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
316 |
+
"transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
317 |
+
"transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
318 |
+
"transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
319 |
+
"transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
320 |
+
"transformer.h.8.attn.bias": "pytorch_model-00001-of-00003.bin",
|
321 |
+
"transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
322 |
+
"transformer.h.8.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
323 |
+
"transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
324 |
+
"transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
325 |
+
"transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
326 |
+
"transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
327 |
+
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
328 |
+
"transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
329 |
+
"transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
330 |
+
"transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
331 |
+
"transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
332 |
+
"transformer.h.9.attn.bias": "pytorch_model-00001-of-00003.bin",
|
333 |
+
"transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
334 |
+
"transformer.h.9.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
335 |
+
"transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
336 |
+
"transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
337 |
+
"transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
338 |
+
"transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
339 |
+
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
340 |
+
"transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
341 |
+
"transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
342 |
+
"transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
343 |
+
"transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
344 |
+
"transformer.ln_f.bias": "pytorch_model-00001-of-00003.bin",
|
345 |
+
"transformer.ln_f.weight": "pytorch_model-00001-of-00003.bin",
|
346 |
+
"transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
|
347 |
+
}
|
348 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[BOS]",
|
3 |
+
"eos_token": "[EOS]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "[UNK]"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[BOS]",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "[EOS]",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 2.042313535626118,
|
4 |
+
"train_runtime": 4896.3607,
|
5 |
+
"train_samples": 2498,
|
6 |
+
"train_samples_per_second": 1.02,
|
7 |
+
"train_steps_per_second": 0.127
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,403 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9983987189751802,
|
5 |
+
"global_step": 624,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 1.996794871794872e-05,
|
13 |
+
"loss": 2.5842,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.03,
|
18 |
+
"learning_rate": 1.967948717948718e-05,
|
19 |
+
"loss": 2.511,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.06,
|
24 |
+
"learning_rate": 1.935897435897436e-05,
|
25 |
+
"loss": 2.4961,
|
26 |
+
"step": 20
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.1,
|
30 |
+
"learning_rate": 1.903846153846154e-05,
|
31 |
+
"loss": 2.4203,
|
32 |
+
"step": 30
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.13,
|
36 |
+
"learning_rate": 1.8717948717948718e-05,
|
37 |
+
"loss": 2.3722,
|
38 |
+
"step": 40
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.16,
|
42 |
+
"learning_rate": 1.8397435897435897e-05,
|
43 |
+
"loss": 2.4072,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.19,
|
48 |
+
"learning_rate": 1.807692307692308e-05,
|
49 |
+
"loss": 2.4484,
|
50 |
+
"step": 60
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.22,
|
54 |
+
"learning_rate": 1.775641025641026e-05,
|
55 |
+
"loss": 2.3817,
|
56 |
+
"step": 70
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.26,
|
60 |
+
"learning_rate": 1.7435897435897438e-05,
|
61 |
+
"loss": 2.4138,
|
62 |
+
"step": 80
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.29,
|
66 |
+
"learning_rate": 1.7115384615384617e-05,
|
67 |
+
"loss": 2.3693,
|
68 |
+
"step": 90
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.32,
|
72 |
+
"learning_rate": 1.6794871794871796e-05,
|
73 |
+
"loss": 2.3947,
|
74 |
+
"step": 100
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.35,
|
78 |
+
"learning_rate": 1.6474358974358975e-05,
|
79 |
+
"loss": 2.3659,
|
80 |
+
"step": 110
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.38,
|
84 |
+
"learning_rate": 1.6153846153846154e-05,
|
85 |
+
"loss": 2.3695,
|
86 |
+
"step": 120
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.42,
|
90 |
+
"learning_rate": 1.5833333333333333e-05,
|
91 |
+
"loss": 2.343,
|
92 |
+
"step": 130
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.45,
|
96 |
+
"learning_rate": 1.5512820512820516e-05,
|
97 |
+
"loss": 2.3434,
|
98 |
+
"step": 140
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.48,
|
102 |
+
"learning_rate": 1.5192307692307693e-05,
|
103 |
+
"loss": 2.3407,
|
104 |
+
"step": 150
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.51,
|
108 |
+
"learning_rate": 1.4871794871794874e-05,
|
109 |
+
"loss": 2.3595,
|
110 |
+
"step": 160
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.54,
|
114 |
+
"learning_rate": 1.4551282051282051e-05,
|
115 |
+
"loss": 2.3485,
|
116 |
+
"step": 170
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.58,
|
120 |
+
"learning_rate": 1.4230769230769232e-05,
|
121 |
+
"loss": 2.3488,
|
122 |
+
"step": 180
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.61,
|
126 |
+
"learning_rate": 1.3910256410256411e-05,
|
127 |
+
"loss": 2.4007,
|
128 |
+
"step": 190
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.64,
|
132 |
+
"learning_rate": 1.3589743589743592e-05,
|
133 |
+
"loss": 2.3197,
|
134 |
+
"step": 200
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.67,
|
138 |
+
"learning_rate": 1.3269230769230769e-05,
|
139 |
+
"loss": 2.324,
|
140 |
+
"step": 210
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.7,
|
144 |
+
"learning_rate": 1.294871794871795e-05,
|
145 |
+
"loss": 2.3546,
|
146 |
+
"step": 220
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.74,
|
150 |
+
"learning_rate": 1.2628205128205129e-05,
|
151 |
+
"loss": 2.3547,
|
152 |
+
"step": 230
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.77,
|
156 |
+
"learning_rate": 1.230769230769231e-05,
|
157 |
+
"loss": 2.3702,
|
158 |
+
"step": 240
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.8,
|
162 |
+
"learning_rate": 1.1987179487179487e-05,
|
163 |
+
"loss": 2.3071,
|
164 |
+
"step": 250
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.83,
|
168 |
+
"learning_rate": 1.1666666666666668e-05,
|
169 |
+
"loss": 2.3233,
|
170 |
+
"step": 260
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.86,
|
174 |
+
"learning_rate": 1.1346153846153847e-05,
|
175 |
+
"loss": 2.3361,
|
176 |
+
"step": 270
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.9,
|
180 |
+
"learning_rate": 1.1025641025641028e-05,
|
181 |
+
"loss": 2.3152,
|
182 |
+
"step": 280
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.93,
|
186 |
+
"learning_rate": 1.0705128205128205e-05,
|
187 |
+
"loss": 2.3653,
|
188 |
+
"step": 290
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.96,
|
192 |
+
"learning_rate": 1.0384615384615386e-05,
|
193 |
+
"loss": 2.3031,
|
194 |
+
"step": 300
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.99,
|
198 |
+
"learning_rate": 1.0064102564102565e-05,
|
199 |
+
"loss": 2.3035,
|
200 |
+
"step": 310
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.02,
|
204 |
+
"learning_rate": 9.743589743589744e-06,
|
205 |
+
"loss": 1.8449,
|
206 |
+
"step": 320
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.06,
|
210 |
+
"learning_rate": 9.423076923076923e-06,
|
211 |
+
"loss": 1.7192,
|
212 |
+
"step": 330
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.09,
|
216 |
+
"learning_rate": 9.102564102564104e-06,
|
217 |
+
"loss": 1.7361,
|
218 |
+
"step": 340
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.12,
|
222 |
+
"learning_rate": 8.782051282051283e-06,
|
223 |
+
"loss": 1.7584,
|
224 |
+
"step": 350
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.15,
|
228 |
+
"learning_rate": 8.461538461538462e-06,
|
229 |
+
"loss": 1.7269,
|
230 |
+
"step": 360
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.18,
|
234 |
+
"learning_rate": 8.141025641025641e-06,
|
235 |
+
"loss": 1.7208,
|
236 |
+
"step": 370
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.22,
|
240 |
+
"learning_rate": 7.820512820512822e-06,
|
241 |
+
"loss": 1.7485,
|
242 |
+
"step": 380
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.25,
|
246 |
+
"learning_rate": 7.500000000000001e-06,
|
247 |
+
"loss": 1.7506,
|
248 |
+
"step": 390
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.28,
|
252 |
+
"learning_rate": 7.17948717948718e-06,
|
253 |
+
"loss": 1.7193,
|
254 |
+
"step": 400
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.31,
|
258 |
+
"learning_rate": 6.858974358974359e-06,
|
259 |
+
"loss": 1.6919,
|
260 |
+
"step": 410
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.35,
|
264 |
+
"learning_rate": 6.538461538461539e-06,
|
265 |
+
"loss": 1.7516,
|
266 |
+
"step": 420
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.38,
|
270 |
+
"learning_rate": 6.217948717948718e-06,
|
271 |
+
"loss": 1.7129,
|
272 |
+
"step": 430
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.41,
|
276 |
+
"learning_rate": 5.897435897435898e-06,
|
277 |
+
"loss": 1.7253,
|
278 |
+
"step": 440
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.44,
|
282 |
+
"learning_rate": 5.576923076923077e-06,
|
283 |
+
"loss": 1.7259,
|
284 |
+
"step": 450
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.47,
|
288 |
+
"learning_rate": 5.256410256410257e-06,
|
289 |
+
"loss": 1.7065,
|
290 |
+
"step": 460
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.51,
|
294 |
+
"learning_rate": 4.935897435897436e-06,
|
295 |
+
"loss": 1.709,
|
296 |
+
"step": 470
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.54,
|
300 |
+
"learning_rate": 4.615384615384616e-06,
|
301 |
+
"loss": 1.6774,
|
302 |
+
"step": 480
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.57,
|
306 |
+
"learning_rate": 4.294871794871795e-06,
|
307 |
+
"loss": 1.7154,
|
308 |
+
"step": 490
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.6,
|
312 |
+
"learning_rate": 3.974358974358974e-06,
|
313 |
+
"loss": 1.6767,
|
314 |
+
"step": 500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.63,
|
318 |
+
"learning_rate": 3.653846153846154e-06,
|
319 |
+
"loss": 1.7006,
|
320 |
+
"step": 510
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.67,
|
324 |
+
"learning_rate": 3.3333333333333333e-06,
|
325 |
+
"loss": 1.6998,
|
326 |
+
"step": 520
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.7,
|
330 |
+
"learning_rate": 3.012820512820513e-06,
|
331 |
+
"loss": 1.7088,
|
332 |
+
"step": 530
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.73,
|
336 |
+
"learning_rate": 2.6923076923076923e-06,
|
337 |
+
"loss": 1.6739,
|
338 |
+
"step": 540
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.76,
|
342 |
+
"learning_rate": 2.371794871794872e-06,
|
343 |
+
"loss": 1.6906,
|
344 |
+
"step": 550
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.79,
|
348 |
+
"learning_rate": 2.0512820512820513e-06,
|
349 |
+
"loss": 1.7699,
|
350 |
+
"step": 560
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.83,
|
354 |
+
"learning_rate": 1.7307692307692308e-06,
|
355 |
+
"loss": 1.6989,
|
356 |
+
"step": 570
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.86,
|
360 |
+
"learning_rate": 1.4102564102564104e-06,
|
361 |
+
"loss": 1.6954,
|
362 |
+
"step": 580
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.89,
|
366 |
+
"learning_rate": 1.0897435897435899e-06,
|
367 |
+
"loss": 1.7052,
|
368 |
+
"step": 590
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.92,
|
372 |
+
"learning_rate": 7.692307692307694e-07,
|
373 |
+
"loss": 1.7458,
|
374 |
+
"step": 600
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.95,
|
378 |
+
"learning_rate": 4.4871794871794876e-07,
|
379 |
+
"loss": 1.7088,
|
380 |
+
"step": 610
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.99,
|
384 |
+
"learning_rate": 1.282051282051282e-07,
|
385 |
+
"loss": 1.7122,
|
386 |
+
"step": 620
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 2.0,
|
390 |
+
"step": 624,
|
391 |
+
"total_flos": 1.810492168297513e+17,
|
392 |
+
"train_loss": 2.042313535626118,
|
393 |
+
"train_runtime": 4896.3607,
|
394 |
+
"train_samples_per_second": 1.02,
|
395 |
+
"train_steps_per_second": 0.127
|
396 |
+
}
|
397 |
+
],
|
398 |
+
"max_steps": 624,
|
399 |
+
"num_train_epochs": 2,
|
400 |
+
"total_flos": 1.810492168297513e+17,
|
401 |
+
"trial_name": null,
|
402 |
+
"trial_params": null
|
403 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ede7954441393fcedaeae18f6372bf237f2f5aace7c182e12cd8735bec6f01c
|
3 |
+
size 3579
|