kevinwang676
commited on
Commit
•
8691d2b
1
Parent(s):
4524ec7
Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- checkpoint-200/README.md +34 -0
- checkpoint-200/adapter_config.json +21 -0
- checkpoint-200/adapter_model.bin +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/pytorch_model.bin +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +30 -0
- checkpoint-200/tokenizer.json +0 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +42 -0
- checkpoint-200/trainer_state.json +1219 -0
- checkpoint-200/training_args.bin +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- training_args.bin +3 -0
- training_params.json +1 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation
|
5 |
+
widget:
|
6 |
+
- text: "I love AutoTrain because "
|
7 |
+
---
|
8 |
+
|
9 |
+
# Model Trained Using AutoTrain
|
adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "LinkSoul/Chinese-Llama-2-7b",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a193aae23d4a5e38bd1a14f041975e9936bdd024eeb10c9dd9bfb8c0f77b8f9
|
3 |
+
size 33600461
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float16
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: False
|
22 |
+
- load_in_4bit: True
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: False
|
27 |
+
- bnb_4bit_quant_type: nf4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float16
|
30 |
+
### Framework versions
|
31 |
+
|
32 |
+
- PEFT 0.5.0
|
33 |
+
|
34 |
+
- PEFT 0.5.0
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "LinkSoul/Chinese-Llama-2-7b",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
checkpoint-200/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a193aae23d4a5e38bd1a14f041975e9936bdd024eeb10c9dd9bfb8c0f77b8f9
|
3 |
+
size 33600461
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c713462c9f9761b3bdfcc49db72d818da96070db02d5bd16b15cab029494c58
|
3 |
+
size 67216581
|
checkpoint-200/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
|
3 |
+
size 443
|
checkpoint-200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:991b5730b6b3acf218f17a173ef0ac38371fa7dc1e2e762609840e86fb20a12f
|
3 |
+
size 14575
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd58214c8de1d469e4bfa7f72c4b3524ef9fe0675494675db1e550a614012a1c
|
3 |
+
size 627
|
checkpoint-200/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-200/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-200/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-200/tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": true,
|
34 |
+
"model_max_length": 1024,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": true
|
42 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 200.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 1e-05,
|
14 |
+
"loss": 0.2719,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 2e-05,
|
20 |
+
"loss": 0.2719,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 3.0,
|
25 |
+
"learning_rate": 3e-05,
|
26 |
+
"loss": 0.2717,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 4.0,
|
31 |
+
"learning_rate": 4e-05,
|
32 |
+
"loss": 0.271,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 5.0,
|
37 |
+
"learning_rate": 5e-05,
|
38 |
+
"loss": 0.2697,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 6.0,
|
43 |
+
"learning_rate": 6e-05,
|
44 |
+
"loss": 0.2681,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 7.0,
|
49 |
+
"learning_rate": 7e-05,
|
50 |
+
"loss": 0.2658,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 8.0,
|
55 |
+
"learning_rate": 8e-05,
|
56 |
+
"loss": 0.2631,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 9.0,
|
61 |
+
"learning_rate": 9e-05,
|
62 |
+
"loss": 0.2595,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 10.0,
|
67 |
+
"learning_rate": 0.0001,
|
68 |
+
"loss": 0.2552,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 11.0,
|
73 |
+
"learning_rate": 0.00011000000000000002,
|
74 |
+
"loss": 0.25,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 12.0,
|
79 |
+
"learning_rate": 0.00012,
|
80 |
+
"loss": 0.2439,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 13.0,
|
85 |
+
"learning_rate": 0.00013000000000000002,
|
86 |
+
"loss": 0.2368,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 14.0,
|
91 |
+
"learning_rate": 0.00014,
|
92 |
+
"loss": 0.2286,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 15.0,
|
97 |
+
"learning_rate": 0.00015000000000000001,
|
98 |
+
"loss": 0.2191,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 16.0,
|
103 |
+
"learning_rate": 0.00016,
|
104 |
+
"loss": 0.2084,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 17.0,
|
109 |
+
"learning_rate": 0.00017,
|
110 |
+
"loss": 0.1961,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 18.0,
|
115 |
+
"learning_rate": 0.00018,
|
116 |
+
"loss": 0.1824,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 19.0,
|
121 |
+
"learning_rate": 0.00019,
|
122 |
+
"loss": 0.167,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 20.0,
|
127 |
+
"learning_rate": 0.0002,
|
128 |
+
"loss": 0.1532,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 21.0,
|
133 |
+
"learning_rate": 0.0001988888888888889,
|
134 |
+
"loss": 0.1427,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 22.0,
|
139 |
+
"learning_rate": 0.00019777777777777778,
|
140 |
+
"loss": 0.1304,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 23.0,
|
145 |
+
"learning_rate": 0.00019666666666666666,
|
146 |
+
"loss": 0.117,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 24.0,
|
151 |
+
"learning_rate": 0.00019555555555555556,
|
152 |
+
"loss": 0.1053,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 25.0,
|
157 |
+
"learning_rate": 0.00019444444444444446,
|
158 |
+
"loss": 0.0943,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 26.0,
|
163 |
+
"learning_rate": 0.00019333333333333333,
|
164 |
+
"loss": 0.0835,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 27.0,
|
169 |
+
"learning_rate": 0.00019222222222222224,
|
170 |
+
"loss": 0.0732,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 28.0,
|
175 |
+
"learning_rate": 0.00019111111111111114,
|
176 |
+
"loss": 0.0633,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 29.0,
|
181 |
+
"learning_rate": 0.00019,
|
182 |
+
"loss": 0.0527,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 30.0,
|
187 |
+
"learning_rate": 0.00018888888888888888,
|
188 |
+
"loss": 0.0405,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 31.0,
|
193 |
+
"learning_rate": 0.00018777777777777779,
|
194 |
+
"loss": 0.0329,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 32.0,
|
199 |
+
"learning_rate": 0.0001866666666666667,
|
200 |
+
"loss": 0.0264,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 33.0,
|
205 |
+
"learning_rate": 0.00018555555555555556,
|
206 |
+
"loss": 0.0182,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 34.0,
|
211 |
+
"learning_rate": 0.00018444444444444446,
|
212 |
+
"loss": 0.0176,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 35.0,
|
217 |
+
"learning_rate": 0.00018333333333333334,
|
218 |
+
"loss": 0.0125,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 36.0,
|
223 |
+
"learning_rate": 0.00018222222222222224,
|
224 |
+
"loss": 0.0127,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 37.0,
|
229 |
+
"learning_rate": 0.0001811111111111111,
|
230 |
+
"loss": 0.0105,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 38.0,
|
235 |
+
"learning_rate": 0.00018,
|
236 |
+
"loss": 0.0094,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 39.0,
|
241 |
+
"learning_rate": 0.0001788888888888889,
|
242 |
+
"loss": 0.0087,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 40.0,
|
247 |
+
"learning_rate": 0.00017777777777777779,
|
248 |
+
"loss": 0.0079,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 41.0,
|
253 |
+
"learning_rate": 0.00017666666666666666,
|
254 |
+
"loss": 0.0071,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 42.0,
|
259 |
+
"learning_rate": 0.00017555555555555556,
|
260 |
+
"loss": 0.0066,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 43.0,
|
265 |
+
"learning_rate": 0.00017444444444444446,
|
266 |
+
"loss": 0.0062,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 44.0,
|
271 |
+
"learning_rate": 0.00017333333333333334,
|
272 |
+
"loss": 0.0059,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 45.0,
|
277 |
+
"learning_rate": 0.00017222222222222224,
|
278 |
+
"loss": 0.0056,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 46.0,
|
283 |
+
"learning_rate": 0.0001711111111111111,
|
284 |
+
"loss": 0.005,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 47.0,
|
289 |
+
"learning_rate": 0.00017,
|
290 |
+
"loss": 0.0044,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 48.0,
|
295 |
+
"learning_rate": 0.00016888888888888889,
|
296 |
+
"loss": 0.0041,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 49.0,
|
301 |
+
"learning_rate": 0.0001677777777777778,
|
302 |
+
"loss": 0.0038,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 50.0,
|
307 |
+
"learning_rate": 0.0001666666666666667,
|
308 |
+
"loss": 0.0037,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 51.0,
|
313 |
+
"learning_rate": 0.00016555555555555556,
|
314 |
+
"loss": 0.0037,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 52.0,
|
319 |
+
"learning_rate": 0.00016444444444444444,
|
320 |
+
"loss": 0.0037,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 53.0,
|
325 |
+
"learning_rate": 0.00016333333333333334,
|
326 |
+
"loss": 0.0036,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 54.0,
|
331 |
+
"learning_rate": 0.00016222222222222224,
|
332 |
+
"loss": 0.0036,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 55.0,
|
337 |
+
"learning_rate": 0.0001611111111111111,
|
338 |
+
"loss": 0.0036,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 56.0,
|
343 |
+
"learning_rate": 0.00016,
|
344 |
+
"loss": 0.0035,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 57.0,
|
349 |
+
"learning_rate": 0.0001588888888888889,
|
350 |
+
"loss": 0.0034,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 58.0,
|
355 |
+
"learning_rate": 0.0001577777777777778,
|
356 |
+
"loss": 0.0033,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 59.0,
|
361 |
+
"learning_rate": 0.00015666666666666666,
|
362 |
+
"loss": 0.0033,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 60.0,
|
367 |
+
"learning_rate": 0.00015555555555555556,
|
368 |
+
"loss": 0.0033,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 61.0,
|
373 |
+
"learning_rate": 0.00015444444444444446,
|
374 |
+
"loss": 0.0032,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 62.0,
|
379 |
+
"learning_rate": 0.00015333333333333334,
|
380 |
+
"loss": 0.0032,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 63.0,
|
385 |
+
"learning_rate": 0.0001522222222222222,
|
386 |
+
"loss": 0.0032,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 64.0,
|
391 |
+
"learning_rate": 0.0001511111111111111,
|
392 |
+
"loss": 0.0031,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 65.0,
|
397 |
+
"learning_rate": 0.00015000000000000001,
|
398 |
+
"loss": 0.0031,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 66.0,
|
403 |
+
"learning_rate": 0.0001488888888888889,
|
404 |
+
"loss": 0.003,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 67.0,
|
409 |
+
"learning_rate": 0.0001477777777777778,
|
410 |
+
"loss": 0.0031,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 68.0,
|
415 |
+
"learning_rate": 0.00014666666666666666,
|
416 |
+
"loss": 0.003,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 69.0,
|
421 |
+
"learning_rate": 0.00014555555555555556,
|
422 |
+
"loss": 0.003,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 70.0,
|
427 |
+
"learning_rate": 0.00014444444444444444,
|
428 |
+
"loss": 0.0029,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 71.0,
|
433 |
+
"learning_rate": 0.00014333333333333334,
|
434 |
+
"loss": 0.0029,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 72.0,
|
439 |
+
"learning_rate": 0.00014222222222222224,
|
440 |
+
"loss": 0.0028,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 73.0,
|
445 |
+
"learning_rate": 0.00014111111111111111,
|
446 |
+
"loss": 0.0028,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 74.0,
|
451 |
+
"learning_rate": 0.00014,
|
452 |
+
"loss": 0.0027,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 75.0,
|
457 |
+
"learning_rate": 0.0001388888888888889,
|
458 |
+
"loss": 0.0026,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 76.0,
|
463 |
+
"learning_rate": 0.0001377777777777778,
|
464 |
+
"loss": 0.0025,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 77.0,
|
469 |
+
"learning_rate": 0.00013666666666666666,
|
470 |
+
"loss": 0.0021,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 78.0,
|
475 |
+
"learning_rate": 0.00013555555555555556,
|
476 |
+
"loss": 0.0015,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 79.0,
|
481 |
+
"learning_rate": 0.00013444444444444447,
|
482 |
+
"loss": 0.0016,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 80.0,
|
487 |
+
"learning_rate": 0.00013333333333333334,
|
488 |
+
"loss": 0.0021,
|
489 |
+
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 81.0,
|
493 |
+
"learning_rate": 0.00013222222222222221,
|
494 |
+
"loss": 0.0015,
|
495 |
+
"step": 81
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 82.0,
|
499 |
+
"learning_rate": 0.00013111111111111111,
|
500 |
+
"loss": 0.0014,
|
501 |
+
"step": 82
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 83.0,
|
505 |
+
"learning_rate": 0.00013000000000000002,
|
506 |
+
"loss": 0.0011,
|
507 |
+
"step": 83
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 84.0,
|
511 |
+
"learning_rate": 0.00012888888888888892,
|
512 |
+
"loss": 0.0019,
|
513 |
+
"step": 84
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 85.0,
|
517 |
+
"learning_rate": 0.00012777777777777776,
|
518 |
+
"loss": 0.002,
|
519 |
+
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 86.0,
|
523 |
+
"learning_rate": 0.00012666666666666666,
|
524 |
+
"loss": 0.0018,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 87.0,
|
529 |
+
"learning_rate": 0.00012555555555555557,
|
530 |
+
"loss": 0.0016,
|
531 |
+
"step": 87
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 88.0,
|
535 |
+
"learning_rate": 0.00012444444444444444,
|
536 |
+
"loss": 0.0012,
|
537 |
+
"step": 88
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 89.0,
|
541 |
+
"learning_rate": 0.00012333333333333334,
|
542 |
+
"loss": 0.0006,
|
543 |
+
"step": 89
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 90.0,
|
547 |
+
"learning_rate": 0.00012222222222222224,
|
548 |
+
"loss": 0.0006,
|
549 |
+
"step": 90
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 91.0,
|
553 |
+
"learning_rate": 0.0001211111111111111,
|
554 |
+
"loss": 0.0006,
|
555 |
+
"step": 91
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 92.0,
|
559 |
+
"learning_rate": 0.00012,
|
560 |
+
"loss": 0.0007,
|
561 |
+
"step": 92
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 93.0,
|
565 |
+
"learning_rate": 0.00011888888888888889,
|
566 |
+
"loss": 0.0017,
|
567 |
+
"step": 93
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 94.0,
|
571 |
+
"learning_rate": 0.00011777777777777779,
|
572 |
+
"loss": 0.0005,
|
573 |
+
"step": 94
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 95.0,
|
577 |
+
"learning_rate": 0.00011666666666666668,
|
578 |
+
"loss": 0.0006,
|
579 |
+
"step": 95
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 96.0,
|
583 |
+
"learning_rate": 0.00011555555555555555,
|
584 |
+
"loss": 0.001,
|
585 |
+
"step": 96
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 97.0,
|
589 |
+
"learning_rate": 0.00011444444444444444,
|
590 |
+
"loss": 0.0011,
|
591 |
+
"step": 97
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 98.0,
|
595 |
+
"learning_rate": 0.00011333333333333334,
|
596 |
+
"loss": 0.0012,
|
597 |
+
"step": 98
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 99.0,
|
601 |
+
"learning_rate": 0.00011222222222222223,
|
602 |
+
"loss": 0.0015,
|
603 |
+
"step": 99
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 100.0,
|
607 |
+
"learning_rate": 0.00011111111111111112,
|
608 |
+
"loss": 0.0012,
|
609 |
+
"step": 100
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 101.0,
|
613 |
+
"learning_rate": 0.00011000000000000002,
|
614 |
+
"loss": 0.0008,
|
615 |
+
"step": 101
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 102.0,
|
619 |
+
"learning_rate": 0.00010888888888888889,
|
620 |
+
"loss": 0.0005,
|
621 |
+
"step": 102
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 103.0,
|
625 |
+
"learning_rate": 0.00010777777777777778,
|
626 |
+
"loss": 0.0005,
|
627 |
+
"step": 103
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 104.0,
|
631 |
+
"learning_rate": 0.00010666666666666667,
|
632 |
+
"loss": 0.0005,
|
633 |
+
"step": 104
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 105.0,
|
637 |
+
"learning_rate": 0.00010555555555555557,
|
638 |
+
"loss": 0.0005,
|
639 |
+
"step": 105
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 106.0,
|
643 |
+
"learning_rate": 0.00010444444444444445,
|
644 |
+
"loss": 0.0005,
|
645 |
+
"step": 106
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 107.0,
|
649 |
+
"learning_rate": 0.00010333333333333334,
|
650 |
+
"loss": 0.0005,
|
651 |
+
"step": 107
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 108.0,
|
655 |
+
"learning_rate": 0.00010222222222222222,
|
656 |
+
"loss": 0.0005,
|
657 |
+
"step": 108
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 109.0,
|
661 |
+
"learning_rate": 0.00010111111111111112,
|
662 |
+
"loss": 0.0005,
|
663 |
+
"step": 109
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 110.0,
|
667 |
+
"learning_rate": 0.0001,
|
668 |
+
"loss": 0.0005,
|
669 |
+
"step": 110
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 111.0,
|
673 |
+
"learning_rate": 9.888888888888889e-05,
|
674 |
+
"loss": 0.0005,
|
675 |
+
"step": 111
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 112.0,
|
679 |
+
"learning_rate": 9.777777777777778e-05,
|
680 |
+
"loss": 0.0005,
|
681 |
+
"step": 112
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 113.0,
|
685 |
+
"learning_rate": 9.666666666666667e-05,
|
686 |
+
"loss": 0.0005,
|
687 |
+
"step": 113
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 114.0,
|
691 |
+
"learning_rate": 9.555555555555557e-05,
|
692 |
+
"loss": 0.0005,
|
693 |
+
"step": 114
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 115.0,
|
697 |
+
"learning_rate": 9.444444444444444e-05,
|
698 |
+
"loss": 0.0005,
|
699 |
+
"step": 115
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 116.0,
|
703 |
+
"learning_rate": 9.333333333333334e-05,
|
704 |
+
"loss": 0.0005,
|
705 |
+
"step": 116
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 117.0,
|
709 |
+
"learning_rate": 9.222222222222223e-05,
|
710 |
+
"loss": 0.0005,
|
711 |
+
"step": 117
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 118.0,
|
715 |
+
"learning_rate": 9.111111111111112e-05,
|
716 |
+
"loss": 0.0005,
|
717 |
+
"step": 118
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 119.0,
|
721 |
+
"learning_rate": 9e-05,
|
722 |
+
"loss": 0.0004,
|
723 |
+
"step": 119
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 120.0,
|
727 |
+
"learning_rate": 8.888888888888889e-05,
|
728 |
+
"loss": 0.0005,
|
729 |
+
"step": 120
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 121.0,
|
733 |
+
"learning_rate": 8.777777777777778e-05,
|
734 |
+
"loss": 0.0004,
|
735 |
+
"step": 121
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 122.0,
|
739 |
+
"learning_rate": 8.666666666666667e-05,
|
740 |
+
"loss": 0.0004,
|
741 |
+
"step": 122
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 123.0,
|
745 |
+
"learning_rate": 8.555555555555556e-05,
|
746 |
+
"loss": 0.0004,
|
747 |
+
"step": 123
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 124.0,
|
751 |
+
"learning_rate": 8.444444444444444e-05,
|
752 |
+
"loss": 0.0004,
|
753 |
+
"step": 124
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 125.0,
|
757 |
+
"learning_rate": 8.333333333333334e-05,
|
758 |
+
"loss": 0.0004,
|
759 |
+
"step": 125
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 126.0,
|
763 |
+
"learning_rate": 8.222222222222222e-05,
|
764 |
+
"loss": 0.0004,
|
765 |
+
"step": 126
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 127.0,
|
769 |
+
"learning_rate": 8.111111111111112e-05,
|
770 |
+
"loss": 0.0004,
|
771 |
+
"step": 127
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 128.0,
|
775 |
+
"learning_rate": 8e-05,
|
776 |
+
"loss": 0.0004,
|
777 |
+
"step": 128
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 129.0,
|
781 |
+
"learning_rate": 7.88888888888889e-05,
|
782 |
+
"loss": 0.0004,
|
783 |
+
"step": 129
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 130.0,
|
787 |
+
"learning_rate": 7.777777777777778e-05,
|
788 |
+
"loss": 0.0004,
|
789 |
+
"step": 130
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 131.0,
|
793 |
+
"learning_rate": 7.666666666666667e-05,
|
794 |
+
"loss": 0.0004,
|
795 |
+
"step": 131
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 132.0,
|
799 |
+
"learning_rate": 7.555555555555556e-05,
|
800 |
+
"loss": 0.0004,
|
801 |
+
"step": 132
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 133.0,
|
805 |
+
"learning_rate": 7.444444444444444e-05,
|
806 |
+
"loss": 0.0004,
|
807 |
+
"step": 133
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 134.0,
|
811 |
+
"learning_rate": 7.333333333333333e-05,
|
812 |
+
"loss": 0.0004,
|
813 |
+
"step": 134
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 135.0,
|
817 |
+
"learning_rate": 7.222222222222222e-05,
|
818 |
+
"loss": 0.0004,
|
819 |
+
"step": 135
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 136.0,
|
823 |
+
"learning_rate": 7.111111111111112e-05,
|
824 |
+
"loss": 0.0004,
|
825 |
+
"step": 136
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 137.0,
|
829 |
+
"learning_rate": 7e-05,
|
830 |
+
"loss": 0.0004,
|
831 |
+
"step": 137
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 138.0,
|
835 |
+
"learning_rate": 6.88888888888889e-05,
|
836 |
+
"loss": 0.0004,
|
837 |
+
"step": 138
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 139.0,
|
841 |
+
"learning_rate": 6.777777777777778e-05,
|
842 |
+
"loss": 0.0004,
|
843 |
+
"step": 139
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 140.0,
|
847 |
+
"learning_rate": 6.666666666666667e-05,
|
848 |
+
"loss": 0.0004,
|
849 |
+
"step": 140
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 141.0,
|
853 |
+
"learning_rate": 6.555555555555556e-05,
|
854 |
+
"loss": 0.0004,
|
855 |
+
"step": 141
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 142.0,
|
859 |
+
"learning_rate": 6.444444444444446e-05,
|
860 |
+
"loss": 0.0004,
|
861 |
+
"step": 142
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 143.0,
|
865 |
+
"learning_rate": 6.333333333333333e-05,
|
866 |
+
"loss": 0.0004,
|
867 |
+
"step": 143
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 144.0,
|
871 |
+
"learning_rate": 6.222222222222222e-05,
|
872 |
+
"loss": 0.0004,
|
873 |
+
"step": 144
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 145.0,
|
877 |
+
"learning_rate": 6.111111111111112e-05,
|
878 |
+
"loss": 0.0004,
|
879 |
+
"step": 145
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 146.0,
|
883 |
+
"learning_rate": 6e-05,
|
884 |
+
"loss": 0.0004,
|
885 |
+
"step": 146
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 147.0,
|
889 |
+
"learning_rate": 5.8888888888888896e-05,
|
890 |
+
"loss": 0.0004,
|
891 |
+
"step": 147
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 148.0,
|
895 |
+
"learning_rate": 5.7777777777777776e-05,
|
896 |
+
"loss": 0.0004,
|
897 |
+
"step": 148
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 149.0,
|
901 |
+
"learning_rate": 5.666666666666667e-05,
|
902 |
+
"loss": 0.0004,
|
903 |
+
"step": 149
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 150.0,
|
907 |
+
"learning_rate": 5.555555555555556e-05,
|
908 |
+
"loss": 0.0004,
|
909 |
+
"step": 150
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 151.0,
|
913 |
+
"learning_rate": 5.4444444444444446e-05,
|
914 |
+
"loss": 0.0004,
|
915 |
+
"step": 151
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 152.0,
|
919 |
+
"learning_rate": 5.333333333333333e-05,
|
920 |
+
"loss": 0.0004,
|
921 |
+
"step": 152
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 153.0,
|
925 |
+
"learning_rate": 5.222222222222223e-05,
|
926 |
+
"loss": 0.0004,
|
927 |
+
"step": 153
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 154.0,
|
931 |
+
"learning_rate": 5.111111111111111e-05,
|
932 |
+
"loss": 0.0004,
|
933 |
+
"step": 154
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 155.0,
|
937 |
+
"learning_rate": 5e-05,
|
938 |
+
"loss": 0.0004,
|
939 |
+
"step": 155
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 156.0,
|
943 |
+
"learning_rate": 4.888888888888889e-05,
|
944 |
+
"loss": 0.0004,
|
945 |
+
"step": 156
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 157.0,
|
949 |
+
"learning_rate": 4.7777777777777784e-05,
|
950 |
+
"loss": 0.0004,
|
951 |
+
"step": 157
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 158.0,
|
955 |
+
"learning_rate": 4.666666666666667e-05,
|
956 |
+
"loss": 0.0004,
|
957 |
+
"step": 158
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 159.0,
|
961 |
+
"learning_rate": 4.555555555555556e-05,
|
962 |
+
"loss": 0.0004,
|
963 |
+
"step": 159
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 160.0,
|
967 |
+
"learning_rate": 4.4444444444444447e-05,
|
968 |
+
"loss": 0.0004,
|
969 |
+
"step": 160
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 161.0,
|
973 |
+
"learning_rate": 4.3333333333333334e-05,
|
974 |
+
"loss": 0.0004,
|
975 |
+
"step": 161
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 162.0,
|
979 |
+
"learning_rate": 4.222222222222222e-05,
|
980 |
+
"loss": 0.0004,
|
981 |
+
"step": 162
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 163.0,
|
985 |
+
"learning_rate": 4.111111111111111e-05,
|
986 |
+
"loss": 0.0004,
|
987 |
+
"step": 163
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 164.0,
|
991 |
+
"learning_rate": 4e-05,
|
992 |
+
"loss": 0.0004,
|
993 |
+
"step": 164
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 165.0,
|
997 |
+
"learning_rate": 3.888888888888889e-05,
|
998 |
+
"loss": 0.0004,
|
999 |
+
"step": 165
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 166.0,
|
1003 |
+
"learning_rate": 3.777777777777778e-05,
|
1004 |
+
"loss": 0.0004,
|
1005 |
+
"step": 166
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 167.0,
|
1009 |
+
"learning_rate": 3.6666666666666666e-05,
|
1010 |
+
"loss": 0.0004,
|
1011 |
+
"step": 167
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 168.0,
|
1015 |
+
"learning_rate": 3.555555555555556e-05,
|
1016 |
+
"loss": 0.0004,
|
1017 |
+
"step": 168
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 169.0,
|
1021 |
+
"learning_rate": 3.444444444444445e-05,
|
1022 |
+
"loss": 0.0004,
|
1023 |
+
"step": 169
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 170.0,
|
1027 |
+
"learning_rate": 3.3333333333333335e-05,
|
1028 |
+
"loss": 0.0004,
|
1029 |
+
"step": 170
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 171.0,
|
1033 |
+
"learning_rate": 3.222222222222223e-05,
|
1034 |
+
"loss": 0.0004,
|
1035 |
+
"step": 171
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 172.0,
|
1039 |
+
"learning_rate": 3.111111111111111e-05,
|
1040 |
+
"loss": 0.0004,
|
1041 |
+
"step": 172
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 173.0,
|
1045 |
+
"learning_rate": 3e-05,
|
1046 |
+
"loss": 0.0004,
|
1047 |
+
"step": 173
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 174.0,
|
1051 |
+
"learning_rate": 2.8888888888888888e-05,
|
1052 |
+
"loss": 0.0004,
|
1053 |
+
"step": 174
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 175.0,
|
1057 |
+
"learning_rate": 2.777777777777778e-05,
|
1058 |
+
"loss": 0.0004,
|
1059 |
+
"step": 175
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 176.0,
|
1063 |
+
"learning_rate": 2.6666666666666667e-05,
|
1064 |
+
"loss": 0.0004,
|
1065 |
+
"step": 176
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 177.0,
|
1069 |
+
"learning_rate": 2.5555555555555554e-05,
|
1070 |
+
"loss": 0.0004,
|
1071 |
+
"step": 177
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 178.0,
|
1075 |
+
"learning_rate": 2.4444444444444445e-05,
|
1076 |
+
"loss": 0.0004,
|
1077 |
+
"step": 178
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 179.0,
|
1081 |
+
"learning_rate": 2.3333333333333336e-05,
|
1082 |
+
"loss": 0.0004,
|
1083 |
+
"step": 179
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 180.0,
|
1087 |
+
"learning_rate": 2.2222222222222223e-05,
|
1088 |
+
"loss": 0.0004,
|
1089 |
+
"step": 180
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 181.0,
|
1093 |
+
"learning_rate": 2.111111111111111e-05,
|
1094 |
+
"loss": 0.0004,
|
1095 |
+
"step": 181
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 182.0,
|
1099 |
+
"learning_rate": 2e-05,
|
1100 |
+
"loss": 0.0004,
|
1101 |
+
"step": 182
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 183.0,
|
1105 |
+
"learning_rate": 1.888888888888889e-05,
|
1106 |
+
"loss": 0.0004,
|
1107 |
+
"step": 183
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 184.0,
|
1111 |
+
"learning_rate": 1.777777777777778e-05,
|
1112 |
+
"loss": 0.0004,
|
1113 |
+
"step": 184
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 185.0,
|
1117 |
+
"learning_rate": 1.6666666666666667e-05,
|
1118 |
+
"loss": 0.0004,
|
1119 |
+
"step": 185
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 186.0,
|
1123 |
+
"learning_rate": 1.5555555555555555e-05,
|
1124 |
+
"loss": 0.0004,
|
1125 |
+
"step": 186
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 187.0,
|
1129 |
+
"learning_rate": 1.4444444444444444e-05,
|
1130 |
+
"loss": 0.0004,
|
1131 |
+
"step": 187
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 188.0,
|
1135 |
+
"learning_rate": 1.3333333333333333e-05,
|
1136 |
+
"loss": 0.0004,
|
1137 |
+
"step": 188
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 189.0,
|
1141 |
+
"learning_rate": 1.2222222222222222e-05,
|
1142 |
+
"loss": 0.0004,
|
1143 |
+
"step": 189
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 190.0,
|
1147 |
+
"learning_rate": 1.1111111111111112e-05,
|
1148 |
+
"loss": 0.0004,
|
1149 |
+
"step": 190
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 191.0,
|
1153 |
+
"learning_rate": 1e-05,
|
1154 |
+
"loss": 0.0004,
|
1155 |
+
"step": 191
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 192.0,
|
1159 |
+
"learning_rate": 8.88888888888889e-06,
|
1160 |
+
"loss": 0.0004,
|
1161 |
+
"step": 192
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 193.0,
|
1165 |
+
"learning_rate": 7.777777777777777e-06,
|
1166 |
+
"loss": 0.0004,
|
1167 |
+
"step": 193
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 194.0,
|
1171 |
+
"learning_rate": 6.666666666666667e-06,
|
1172 |
+
"loss": 0.0004,
|
1173 |
+
"step": 194
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 195.0,
|
1177 |
+
"learning_rate": 5.555555555555556e-06,
|
1178 |
+
"loss": 0.0004,
|
1179 |
+
"step": 195
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 196.0,
|
1183 |
+
"learning_rate": 4.444444444444445e-06,
|
1184 |
+
"loss": 0.0004,
|
1185 |
+
"step": 196
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 197.0,
|
1189 |
+
"learning_rate": 3.3333333333333333e-06,
|
1190 |
+
"loss": 0.0004,
|
1191 |
+
"step": 197
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 198.0,
|
1195 |
+
"learning_rate": 2.2222222222222225e-06,
|
1196 |
+
"loss": 0.0004,
|
1197 |
+
"step": 198
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 199.0,
|
1201 |
+
"learning_rate": 1.1111111111111112e-06,
|
1202 |
+
"loss": 0.0004,
|
1203 |
+
"step": 199
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 200.0,
|
1207 |
+
"learning_rate": 0.0,
|
1208 |
+
"loss": 0.0004,
|
1209 |
+
"step": 200
|
1210 |
+
}
|
1211 |
+
],
|
1212 |
+
"logging_steps": 1,
|
1213 |
+
"max_steps": 200,
|
1214 |
+
"num_train_epochs": 200,
|
1215 |
+
"save_steps": 500,
|
1216 |
+
"total_flos": 3.25176470274048e+16,
|
1217 |
+
"trial_name": null,
|
1218 |
+
"trial_params": null
|
1219 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:081c5648e3b119e1789c8804844aa1d8cf8d25d0be5dfa2f068352dda5e89ac3
|
3 |
+
size 4027
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": true,
|
34 |
+
"model_max_length": 1024,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": true
|
42 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:081c5648e3b119e1789c8804844aa1d8cf8d25d0be5dfa2f068352dda5e89ac3
|
3 |
+
size 4027
|
training_params.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "LinkSoul/Chinese-Llama-2-7b", "data_path": "data/", "project_name": "my_autotrain_llm", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 200, "batch_size": 8, "warmup_ratio": 0.1, "gradient_accumulation": 4, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "kevinwang676/my-chinese-llama-2", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": false, "username": null, "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": "prompt"}
|