Farouk
commited on
Commit
•
6dbca0b
1
Parent(s):
61ecf51
Training in progress, step 200
Browse files- adapter_config.json +26 -0
- adapter_model.bin +3 -0
- added_tokens.json +3 -0
- checkpoint-200/README.md +20 -0
- checkpoint-200/adapter_config.json +26 -0
- checkpoint-200/adapter_model.bin +3 -0
- checkpoint-200/added_tokens.json +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +6 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +35 -0
- checkpoint-200/trainer_state.json +1257 -0
- checkpoint-200/training_args.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "codellama/CodeLlama-34b-Python-hf",
|
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": 16.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"down_proj",
|
18 |
+
"q_proj",
|
19 |
+
"k_proj",
|
20 |
+
"gate_proj",
|
21 |
+
"up_proj",
|
22 |
+
"v_proj",
|
23 |
+
"o_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fba458e63454aea3ede4a9870b8af551bb13e6e6064d71e880df1b6cef90a198
|
3 |
+
size 871609293
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 32000
|
3 |
+
}
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: False
|
9 |
+
- load_in_4bit: True
|
10 |
+
- llm_int8_threshold: 6.0
|
11 |
+
- llm_int8_skip_modules: None
|
12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
13 |
+
- llm_int8_has_fp16_weight: False
|
14 |
+
- bnb_4bit_quant_type: nf4
|
15 |
+
- bnb_4bit_use_double_quant: True
|
16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
17 |
+
### Framework versions
|
18 |
+
|
19 |
+
|
20 |
+
- PEFT 0.4.0
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "codellama/CodeLlama-34b-Python-hf",
|
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": 16.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"down_proj",
|
18 |
+
"q_proj",
|
19 |
+
"k_proj",
|
20 |
+
"gate_proj",
|
21 |
+
"up_proj",
|
22 |
+
"v_proj",
|
23 |
+
"o_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
checkpoint-200/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fba458e63454aea3ede4a9870b8af551bb13e6e6064d71e880df1b6cef90a198
|
3 |
+
size 871609293
|
checkpoint-200/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 32000
|
3 |
+
}
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc765c4a9ba10bb13cd039bd2235024fc70af29cdf19f140d47d0752d4afcda6
|
3 |
+
size 3485880477
|
checkpoint-200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44cd62c88c3d2ecb3476f77e5f962d8fa95a29c389655db395009a010007f44a
|
3 |
+
size 14511
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81248501833af563175f43c1d681185643b8411cee1fb1e631b8687c465eb2e3
|
3 |
+
size 627
|
checkpoint-200/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
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 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": null,
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,1257 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.662463366985321,
|
3 |
+
"best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34b-Python-hf_codellama_blob_1/checkpoint-200",
|
4 |
+
"epoch": 0.1404001404001404,
|
5 |
+
"global_step": 200,
|
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": 0.0004,
|
13 |
+
"loss": 1.5667,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.0,
|
18 |
+
"learning_rate": 0.0004,
|
19 |
+
"loss": 0.9201,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.0,
|
24 |
+
"learning_rate": 0.0004,
|
25 |
+
"loss": 0.6019,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.0,
|
30 |
+
"learning_rate": 0.0004,
|
31 |
+
"loss": 0.861,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.0,
|
36 |
+
"learning_rate": 0.0004,
|
37 |
+
"loss": 1.064,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.0,
|
42 |
+
"learning_rate": 0.0004,
|
43 |
+
"loss": 1.0007,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0,
|
48 |
+
"learning_rate": 0.0004,
|
49 |
+
"loss": 1.0533,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.01,
|
54 |
+
"learning_rate": 0.0004,
|
55 |
+
"loss": 0.8498,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.01,
|
60 |
+
"learning_rate": 0.0004,
|
61 |
+
"loss": 0.9189,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.01,
|
66 |
+
"learning_rate": 0.0004,
|
67 |
+
"loss": 0.9369,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.01,
|
72 |
+
"learning_rate": 0.0004,
|
73 |
+
"loss": 1.1375,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.01,
|
78 |
+
"learning_rate": 0.0004,
|
79 |
+
"loss": 0.8369,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.01,
|
84 |
+
"learning_rate": 0.0004,
|
85 |
+
"loss": 0.689,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.01,
|
90 |
+
"learning_rate": 0.0004,
|
91 |
+
"loss": 0.8885,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.01,
|
96 |
+
"learning_rate": 0.0004,
|
97 |
+
"loss": 0.9666,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.01,
|
102 |
+
"learning_rate": 0.0004,
|
103 |
+
"loss": 0.744,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.01,
|
108 |
+
"learning_rate": 0.0004,
|
109 |
+
"loss": 0.8998,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.01,
|
114 |
+
"learning_rate": 0.0004,
|
115 |
+
"loss": 0.8371,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.01,
|
120 |
+
"learning_rate": 0.0004,
|
121 |
+
"loss": 0.7615,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.01,
|
126 |
+
"learning_rate": 0.0004,
|
127 |
+
"loss": 0.6963,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.01,
|
132 |
+
"learning_rate": 0.0004,
|
133 |
+
"loss": 0.5974,
|
134 |
+
"step": 21
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.02,
|
138 |
+
"learning_rate": 0.0004,
|
139 |
+
"loss": 1.4922,
|
140 |
+
"step": 22
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.02,
|
144 |
+
"learning_rate": 0.0004,
|
145 |
+
"loss": 1.1272,
|
146 |
+
"step": 23
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.02,
|
150 |
+
"learning_rate": 0.0004,
|
151 |
+
"loss": 0.4373,
|
152 |
+
"step": 24
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.02,
|
156 |
+
"learning_rate": 0.0004,
|
157 |
+
"loss": 1.0598,
|
158 |
+
"step": 25
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.02,
|
162 |
+
"learning_rate": 0.0004,
|
163 |
+
"loss": 1.191,
|
164 |
+
"step": 26
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.02,
|
168 |
+
"learning_rate": 0.0004,
|
169 |
+
"loss": 0.6499,
|
170 |
+
"step": 27
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.02,
|
174 |
+
"learning_rate": 0.0004,
|
175 |
+
"loss": 0.7526,
|
176 |
+
"step": 28
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.02,
|
180 |
+
"learning_rate": 0.0004,
|
181 |
+
"loss": 0.7252,
|
182 |
+
"step": 29
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.02,
|
186 |
+
"learning_rate": 0.0004,
|
187 |
+
"loss": 0.8555,
|
188 |
+
"step": 30
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.02,
|
192 |
+
"learning_rate": 0.0004,
|
193 |
+
"loss": 0.479,
|
194 |
+
"step": 31
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.02,
|
198 |
+
"learning_rate": 0.0004,
|
199 |
+
"loss": 0.5273,
|
200 |
+
"step": 32
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.02,
|
204 |
+
"learning_rate": 0.0004,
|
205 |
+
"loss": 0.3907,
|
206 |
+
"step": 33
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.02,
|
210 |
+
"learning_rate": 0.0004,
|
211 |
+
"loss": 0.5284,
|
212 |
+
"step": 34
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.02,
|
216 |
+
"learning_rate": 0.0004,
|
217 |
+
"loss": 0.8696,
|
218 |
+
"step": 35
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.03,
|
222 |
+
"learning_rate": 0.0004,
|
223 |
+
"loss": 0.9264,
|
224 |
+
"step": 36
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.03,
|
228 |
+
"learning_rate": 0.0004,
|
229 |
+
"loss": 0.6812,
|
230 |
+
"step": 37
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.03,
|
234 |
+
"learning_rate": 0.0004,
|
235 |
+
"loss": 0.4482,
|
236 |
+
"step": 38
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.03,
|
240 |
+
"learning_rate": 0.0004,
|
241 |
+
"loss": 1.9031,
|
242 |
+
"step": 39
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.03,
|
246 |
+
"learning_rate": 0.0004,
|
247 |
+
"loss": 1.3295,
|
248 |
+
"step": 40
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.03,
|
252 |
+
"learning_rate": 0.0004,
|
253 |
+
"loss": 0.7498,
|
254 |
+
"step": 41
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.03,
|
258 |
+
"learning_rate": 0.0004,
|
259 |
+
"loss": 1.4452,
|
260 |
+
"step": 42
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.03,
|
264 |
+
"learning_rate": 0.0004,
|
265 |
+
"loss": 1.224,
|
266 |
+
"step": 43
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.03,
|
270 |
+
"learning_rate": 0.0004,
|
271 |
+
"loss": 0.3272,
|
272 |
+
"step": 44
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.03,
|
276 |
+
"learning_rate": 0.0004,
|
277 |
+
"loss": 0.7366,
|
278 |
+
"step": 45
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.03,
|
282 |
+
"learning_rate": 0.0004,
|
283 |
+
"loss": 1.0331,
|
284 |
+
"step": 46
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.03,
|
288 |
+
"learning_rate": 0.0004,
|
289 |
+
"loss": 0.8471,
|
290 |
+
"step": 47
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.03,
|
294 |
+
"learning_rate": 0.0004,
|
295 |
+
"loss": 0.8171,
|
296 |
+
"step": 48
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.03,
|
300 |
+
"learning_rate": 0.0004,
|
301 |
+
"loss": 0.418,
|
302 |
+
"step": 49
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.04,
|
306 |
+
"learning_rate": 0.0004,
|
307 |
+
"loss": 0.6942,
|
308 |
+
"step": 50
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.04,
|
312 |
+
"learning_rate": 0.0004,
|
313 |
+
"loss": 0.1712,
|
314 |
+
"step": 51
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.04,
|
318 |
+
"learning_rate": 0.0004,
|
319 |
+
"loss": 0.5041,
|
320 |
+
"step": 52
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.04,
|
324 |
+
"learning_rate": 0.0004,
|
325 |
+
"loss": 0.4619,
|
326 |
+
"step": 53
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.04,
|
330 |
+
"learning_rate": 0.0004,
|
331 |
+
"loss": 0.5011,
|
332 |
+
"step": 54
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.04,
|
336 |
+
"learning_rate": 0.0004,
|
337 |
+
"loss": 0.5,
|
338 |
+
"step": 55
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.04,
|
342 |
+
"learning_rate": 0.0004,
|
343 |
+
"loss": 0.917,
|
344 |
+
"step": 56
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.04,
|
348 |
+
"learning_rate": 0.0004,
|
349 |
+
"loss": 0.8142,
|
350 |
+
"step": 57
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.04,
|
354 |
+
"learning_rate": 0.0004,
|
355 |
+
"loss": 0.8708,
|
356 |
+
"step": 58
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.04,
|
360 |
+
"learning_rate": 0.0004,
|
361 |
+
"loss": 0.7987,
|
362 |
+
"step": 59
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.04,
|
366 |
+
"learning_rate": 0.0004,
|
367 |
+
"loss": 0.9699,
|
368 |
+
"step": 60
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.04,
|
372 |
+
"learning_rate": 0.0004,
|
373 |
+
"loss": 1.0015,
|
374 |
+
"step": 61
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.04,
|
378 |
+
"learning_rate": 0.0004,
|
379 |
+
"loss": 0.8052,
|
380 |
+
"step": 62
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.04,
|
384 |
+
"learning_rate": 0.0004,
|
385 |
+
"loss": 0.8645,
|
386 |
+
"step": 63
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.04,
|
390 |
+
"learning_rate": 0.0004,
|
391 |
+
"loss": 1.1444,
|
392 |
+
"step": 64
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.05,
|
396 |
+
"learning_rate": 0.0004,
|
397 |
+
"loss": 1.0087,
|
398 |
+
"step": 65
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.05,
|
402 |
+
"learning_rate": 0.0004,
|
403 |
+
"loss": 0.5679,
|
404 |
+
"step": 66
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.05,
|
408 |
+
"learning_rate": 0.0004,
|
409 |
+
"loss": 0.5507,
|
410 |
+
"step": 67
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.05,
|
414 |
+
"learning_rate": 0.0004,
|
415 |
+
"loss": 1.1764,
|
416 |
+
"step": 68
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.05,
|
420 |
+
"learning_rate": 0.0004,
|
421 |
+
"loss": 0.6332,
|
422 |
+
"step": 69
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.05,
|
426 |
+
"learning_rate": 0.0004,
|
427 |
+
"loss": 0.8759,
|
428 |
+
"step": 70
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.05,
|
432 |
+
"learning_rate": 0.0004,
|
433 |
+
"loss": 0.8385,
|
434 |
+
"step": 71
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.05,
|
438 |
+
"learning_rate": 0.0004,
|
439 |
+
"loss": 0.7869,
|
440 |
+
"step": 72
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.05,
|
444 |
+
"learning_rate": 0.0004,
|
445 |
+
"loss": 1.4457,
|
446 |
+
"step": 73
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.05,
|
450 |
+
"learning_rate": 0.0004,
|
451 |
+
"loss": 0.9331,
|
452 |
+
"step": 74
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.05,
|
456 |
+
"learning_rate": 0.0004,
|
457 |
+
"loss": 0.8943,
|
458 |
+
"step": 75
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.05,
|
462 |
+
"learning_rate": 0.0004,
|
463 |
+
"loss": 0.5783,
|
464 |
+
"step": 76
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.05,
|
468 |
+
"learning_rate": 0.0004,
|
469 |
+
"loss": 0.6433,
|
470 |
+
"step": 77
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.05,
|
474 |
+
"learning_rate": 0.0004,
|
475 |
+
"loss": 0.7517,
|
476 |
+
"step": 78
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.06,
|
480 |
+
"learning_rate": 0.0004,
|
481 |
+
"loss": 0.5061,
|
482 |
+
"step": 79
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.06,
|
486 |
+
"learning_rate": 0.0004,
|
487 |
+
"loss": 0.7332,
|
488 |
+
"step": 80
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.06,
|
492 |
+
"learning_rate": 0.0004,
|
493 |
+
"loss": 1.6546,
|
494 |
+
"step": 81
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.06,
|
498 |
+
"learning_rate": 0.0004,
|
499 |
+
"loss": 0.4723,
|
500 |
+
"step": 82
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.06,
|
504 |
+
"learning_rate": 0.0004,
|
505 |
+
"loss": 0.2814,
|
506 |
+
"step": 83
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.06,
|
510 |
+
"learning_rate": 0.0004,
|
511 |
+
"loss": 0.4068,
|
512 |
+
"step": 84
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.06,
|
516 |
+
"learning_rate": 0.0004,
|
517 |
+
"loss": 1.1729,
|
518 |
+
"step": 85
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.06,
|
522 |
+
"learning_rate": 0.0004,
|
523 |
+
"loss": 0.698,
|
524 |
+
"step": 86
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.06,
|
528 |
+
"learning_rate": 0.0004,
|
529 |
+
"loss": 0.7746,
|
530 |
+
"step": 87
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.06,
|
534 |
+
"learning_rate": 0.0004,
|
535 |
+
"loss": 0.5065,
|
536 |
+
"step": 88
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.06,
|
540 |
+
"learning_rate": 0.0004,
|
541 |
+
"loss": 0.4654,
|
542 |
+
"step": 89
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.06,
|
546 |
+
"learning_rate": 0.0004,
|
547 |
+
"loss": 0.5724,
|
548 |
+
"step": 90
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.06,
|
552 |
+
"learning_rate": 0.0004,
|
553 |
+
"loss": 1.1535,
|
554 |
+
"step": 91
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.06,
|
558 |
+
"learning_rate": 0.0004,
|
559 |
+
"loss": 0.3854,
|
560 |
+
"step": 92
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.07,
|
564 |
+
"learning_rate": 0.0004,
|
565 |
+
"loss": 1.6848,
|
566 |
+
"step": 93
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.07,
|
570 |
+
"learning_rate": 0.0004,
|
571 |
+
"loss": 0.6667,
|
572 |
+
"step": 94
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.07,
|
576 |
+
"learning_rate": 0.0004,
|
577 |
+
"loss": 0.4526,
|
578 |
+
"step": 95
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.07,
|
582 |
+
"learning_rate": 0.0004,
|
583 |
+
"loss": 0.7112,
|
584 |
+
"step": 96
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.07,
|
588 |
+
"learning_rate": 0.0004,
|
589 |
+
"loss": 0.6816,
|
590 |
+
"step": 97
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.07,
|
594 |
+
"learning_rate": 0.0004,
|
595 |
+
"loss": 0.7496,
|
596 |
+
"step": 98
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.07,
|
600 |
+
"learning_rate": 0.0004,
|
601 |
+
"loss": 1.189,
|
602 |
+
"step": 99
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.07,
|
606 |
+
"learning_rate": 0.0004,
|
607 |
+
"loss": 1.4239,
|
608 |
+
"step": 100
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.07,
|
612 |
+
"learning_rate": 0.0004,
|
613 |
+
"loss": 0.4378,
|
614 |
+
"step": 101
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.07,
|
618 |
+
"learning_rate": 0.0004,
|
619 |
+
"loss": 2.3054,
|
620 |
+
"step": 102
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.07,
|
624 |
+
"learning_rate": 0.0004,
|
625 |
+
"loss": 0.1593,
|
626 |
+
"step": 103
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.07,
|
630 |
+
"learning_rate": 0.0004,
|
631 |
+
"loss": 0.2481,
|
632 |
+
"step": 104
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.07,
|
636 |
+
"learning_rate": 0.0004,
|
637 |
+
"loss": 0.6469,
|
638 |
+
"step": 105
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.07,
|
642 |
+
"learning_rate": 0.0004,
|
643 |
+
"loss": 0.7417,
|
644 |
+
"step": 106
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.08,
|
648 |
+
"learning_rate": 0.0004,
|
649 |
+
"loss": 0.7767,
|
650 |
+
"step": 107
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.08,
|
654 |
+
"learning_rate": 0.0004,
|
655 |
+
"loss": 0.831,
|
656 |
+
"step": 108
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.08,
|
660 |
+
"learning_rate": 0.0004,
|
661 |
+
"loss": 0.7954,
|
662 |
+
"step": 109
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.08,
|
666 |
+
"learning_rate": 0.0004,
|
667 |
+
"loss": 0.6376,
|
668 |
+
"step": 110
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.08,
|
672 |
+
"learning_rate": 0.0004,
|
673 |
+
"loss": 0.6208,
|
674 |
+
"step": 111
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.08,
|
678 |
+
"learning_rate": 0.0004,
|
679 |
+
"loss": 0.9038,
|
680 |
+
"step": 112
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.08,
|
684 |
+
"learning_rate": 0.0004,
|
685 |
+
"loss": 0.9994,
|
686 |
+
"step": 113
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.08,
|
690 |
+
"learning_rate": 0.0004,
|
691 |
+
"loss": 1.0233,
|
692 |
+
"step": 114
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.08,
|
696 |
+
"learning_rate": 0.0004,
|
697 |
+
"loss": 0.7573,
|
698 |
+
"step": 115
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.08,
|
702 |
+
"learning_rate": 0.0004,
|
703 |
+
"loss": 0.5333,
|
704 |
+
"step": 116
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.08,
|
708 |
+
"learning_rate": 0.0004,
|
709 |
+
"loss": 0.4886,
|
710 |
+
"step": 117
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.08,
|
714 |
+
"learning_rate": 0.0004,
|
715 |
+
"loss": 0.75,
|
716 |
+
"step": 118
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.08,
|
720 |
+
"learning_rate": 0.0004,
|
721 |
+
"loss": 0.6377,
|
722 |
+
"step": 119
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.08,
|
726 |
+
"learning_rate": 0.0004,
|
727 |
+
"loss": 0.6518,
|
728 |
+
"step": 120
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.08,
|
732 |
+
"learning_rate": 0.0004,
|
733 |
+
"loss": 0.6409,
|
734 |
+
"step": 121
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.09,
|
738 |
+
"learning_rate": 0.0004,
|
739 |
+
"loss": 0.5996,
|
740 |
+
"step": 122
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.09,
|
744 |
+
"learning_rate": 0.0004,
|
745 |
+
"loss": 0.7964,
|
746 |
+
"step": 123
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.09,
|
750 |
+
"learning_rate": 0.0004,
|
751 |
+
"loss": 0.5898,
|
752 |
+
"step": 124
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.09,
|
756 |
+
"learning_rate": 0.0004,
|
757 |
+
"loss": 0.8753,
|
758 |
+
"step": 125
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.09,
|
762 |
+
"learning_rate": 0.0004,
|
763 |
+
"loss": 0.6304,
|
764 |
+
"step": 126
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 0.09,
|
768 |
+
"learning_rate": 0.0004,
|
769 |
+
"loss": 0.5428,
|
770 |
+
"step": 127
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.09,
|
774 |
+
"learning_rate": 0.0004,
|
775 |
+
"loss": 0.8571,
|
776 |
+
"step": 128
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.09,
|
780 |
+
"learning_rate": 0.0004,
|
781 |
+
"loss": 0.8339,
|
782 |
+
"step": 129
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.09,
|
786 |
+
"learning_rate": 0.0004,
|
787 |
+
"loss": 0.6087,
|
788 |
+
"step": 130
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.09,
|
792 |
+
"learning_rate": 0.0004,
|
793 |
+
"loss": 0.3547,
|
794 |
+
"step": 131
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.09,
|
798 |
+
"learning_rate": 0.0004,
|
799 |
+
"loss": 0.3494,
|
800 |
+
"step": 132
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.09,
|
804 |
+
"learning_rate": 0.0004,
|
805 |
+
"loss": 0.5394,
|
806 |
+
"step": 133
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.09,
|
810 |
+
"learning_rate": 0.0004,
|
811 |
+
"loss": 0.4315,
|
812 |
+
"step": 134
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.09,
|
816 |
+
"learning_rate": 0.0004,
|
817 |
+
"loss": 0.3575,
|
818 |
+
"step": 135
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.1,
|
822 |
+
"learning_rate": 0.0004,
|
823 |
+
"loss": 0.4983,
|
824 |
+
"step": 136
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.1,
|
828 |
+
"learning_rate": 0.0004,
|
829 |
+
"loss": 0.4292,
|
830 |
+
"step": 137
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.1,
|
834 |
+
"learning_rate": 0.0004,
|
835 |
+
"loss": 0.6315,
|
836 |
+
"step": 138
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.1,
|
840 |
+
"learning_rate": 0.0004,
|
841 |
+
"loss": 0.9827,
|
842 |
+
"step": 139
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.1,
|
846 |
+
"learning_rate": 0.0004,
|
847 |
+
"loss": 1.4456,
|
848 |
+
"step": 140
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.1,
|
852 |
+
"learning_rate": 0.0004,
|
853 |
+
"loss": 0.5151,
|
854 |
+
"step": 141
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.1,
|
858 |
+
"learning_rate": 0.0004,
|
859 |
+
"loss": 0.4651,
|
860 |
+
"step": 142
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.1,
|
864 |
+
"learning_rate": 0.0004,
|
865 |
+
"loss": 0.8682,
|
866 |
+
"step": 143
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.1,
|
870 |
+
"learning_rate": 0.0004,
|
871 |
+
"loss": 1.1543,
|
872 |
+
"step": 144
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.1,
|
876 |
+
"learning_rate": 0.0004,
|
877 |
+
"loss": 0.3378,
|
878 |
+
"step": 145
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.1,
|
882 |
+
"learning_rate": 0.0004,
|
883 |
+
"loss": 0.5381,
|
884 |
+
"step": 146
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.1,
|
888 |
+
"learning_rate": 0.0004,
|
889 |
+
"loss": 0.5189,
|
890 |
+
"step": 147
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.1,
|
894 |
+
"learning_rate": 0.0004,
|
895 |
+
"loss": 0.3988,
|
896 |
+
"step": 148
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.1,
|
900 |
+
"learning_rate": 0.0004,
|
901 |
+
"loss": 0.9694,
|
902 |
+
"step": 149
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.11,
|
906 |
+
"learning_rate": 0.0004,
|
907 |
+
"loss": 1.2404,
|
908 |
+
"step": 150
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.11,
|
912 |
+
"learning_rate": 0.0004,
|
913 |
+
"loss": 0.3767,
|
914 |
+
"step": 151
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.11,
|
918 |
+
"learning_rate": 0.0004,
|
919 |
+
"loss": 0.5564,
|
920 |
+
"step": 152
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.11,
|
924 |
+
"learning_rate": 0.0004,
|
925 |
+
"loss": 0.2665,
|
926 |
+
"step": 153
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.11,
|
930 |
+
"learning_rate": 0.0004,
|
931 |
+
"loss": 0.172,
|
932 |
+
"step": 154
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 0.11,
|
936 |
+
"learning_rate": 0.0004,
|
937 |
+
"loss": 0.6584,
|
938 |
+
"step": 155
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.11,
|
942 |
+
"learning_rate": 0.0004,
|
943 |
+
"loss": 0.7588,
|
944 |
+
"step": 156
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.11,
|
948 |
+
"learning_rate": 0.0004,
|
949 |
+
"loss": 0.9431,
|
950 |
+
"step": 157
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.11,
|
954 |
+
"learning_rate": 0.0004,
|
955 |
+
"loss": 0.9456,
|
956 |
+
"step": 158
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.11,
|
960 |
+
"learning_rate": 0.0004,
|
961 |
+
"loss": 0.7471,
|
962 |
+
"step": 159
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.11,
|
966 |
+
"learning_rate": 0.0004,
|
967 |
+
"loss": 0.8477,
|
968 |
+
"step": 160
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.11,
|
972 |
+
"learning_rate": 0.0004,
|
973 |
+
"loss": 0.7679,
|
974 |
+
"step": 161
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 0.11,
|
978 |
+
"learning_rate": 0.0004,
|
979 |
+
"loss": 0.8937,
|
980 |
+
"step": 162
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.11,
|
984 |
+
"learning_rate": 0.0004,
|
985 |
+
"loss": 1.2858,
|
986 |
+
"step": 163
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.12,
|
990 |
+
"learning_rate": 0.0004,
|
991 |
+
"loss": 0.7806,
|
992 |
+
"step": 164
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 0.12,
|
996 |
+
"learning_rate": 0.0004,
|
997 |
+
"loss": 0.8034,
|
998 |
+
"step": 165
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.12,
|
1002 |
+
"learning_rate": 0.0004,
|
1003 |
+
"loss": 0.6372,
|
1004 |
+
"step": 166
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.12,
|
1008 |
+
"learning_rate": 0.0004,
|
1009 |
+
"loss": 0.8217,
|
1010 |
+
"step": 167
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.12,
|
1014 |
+
"learning_rate": 0.0004,
|
1015 |
+
"loss": 0.3706,
|
1016 |
+
"step": 168
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 0.12,
|
1020 |
+
"learning_rate": 0.0004,
|
1021 |
+
"loss": 1.0851,
|
1022 |
+
"step": 169
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.12,
|
1026 |
+
"learning_rate": 0.0004,
|
1027 |
+
"loss": 0.6719,
|
1028 |
+
"step": 170
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.12,
|
1032 |
+
"learning_rate": 0.0004,
|
1033 |
+
"loss": 1.0366,
|
1034 |
+
"step": 171
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.12,
|
1038 |
+
"learning_rate": 0.0004,
|
1039 |
+
"loss": 0.5603,
|
1040 |
+
"step": 172
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.12,
|
1044 |
+
"learning_rate": 0.0004,
|
1045 |
+
"loss": 0.5651,
|
1046 |
+
"step": 173
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.12,
|
1050 |
+
"learning_rate": 0.0004,
|
1051 |
+
"loss": 0.3804,
|
1052 |
+
"step": 174
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.12,
|
1056 |
+
"learning_rate": 0.0004,
|
1057 |
+
"loss": 0.5946,
|
1058 |
+
"step": 175
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.12,
|
1062 |
+
"learning_rate": 0.0004,
|
1063 |
+
"loss": 0.7649,
|
1064 |
+
"step": 176
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.12,
|
1068 |
+
"learning_rate": 0.0004,
|
1069 |
+
"loss": 0.5035,
|
1070 |
+
"step": 177
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.12,
|
1074 |
+
"learning_rate": 0.0004,
|
1075 |
+
"loss": 0.8066,
|
1076 |
+
"step": 178
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.13,
|
1080 |
+
"learning_rate": 0.0004,
|
1081 |
+
"loss": 0.8046,
|
1082 |
+
"step": 179
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.13,
|
1086 |
+
"learning_rate": 0.0004,
|
1087 |
+
"loss": 0.4233,
|
1088 |
+
"step": 180
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.13,
|
1092 |
+
"learning_rate": 0.0004,
|
1093 |
+
"loss": 0.7945,
|
1094 |
+
"step": 181
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.13,
|
1098 |
+
"learning_rate": 0.0004,
|
1099 |
+
"loss": 0.5722,
|
1100 |
+
"step": 182
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 0.13,
|
1104 |
+
"learning_rate": 0.0004,
|
1105 |
+
"loss": 0.6088,
|
1106 |
+
"step": 183
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 0.13,
|
1110 |
+
"learning_rate": 0.0004,
|
1111 |
+
"loss": 0.4229,
|
1112 |
+
"step": 184
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.13,
|
1116 |
+
"learning_rate": 0.0004,
|
1117 |
+
"loss": 0.8723,
|
1118 |
+
"step": 185
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 0.13,
|
1122 |
+
"learning_rate": 0.0004,
|
1123 |
+
"loss": 0.9287,
|
1124 |
+
"step": 186
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.13,
|
1128 |
+
"learning_rate": 0.0004,
|
1129 |
+
"loss": 0.8082,
|
1130 |
+
"step": 187
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.13,
|
1134 |
+
"learning_rate": 0.0004,
|
1135 |
+
"loss": 0.4144,
|
1136 |
+
"step": 188
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.13,
|
1140 |
+
"learning_rate": 0.0004,
|
1141 |
+
"loss": 0.372,
|
1142 |
+
"step": 189
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 0.13,
|
1146 |
+
"learning_rate": 0.0004,
|
1147 |
+
"loss": 0.5725,
|
1148 |
+
"step": 190
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 0.13,
|
1152 |
+
"learning_rate": 0.0004,
|
1153 |
+
"loss": 0.3837,
|
1154 |
+
"step": 191
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.13,
|
1158 |
+
"learning_rate": 0.0004,
|
1159 |
+
"loss": 0.5155,
|
1160 |
+
"step": 192
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.14,
|
1164 |
+
"learning_rate": 0.0004,
|
1165 |
+
"loss": 0.5472,
|
1166 |
+
"step": 193
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.14,
|
1170 |
+
"learning_rate": 0.0004,
|
1171 |
+
"loss": 0.6488,
|
1172 |
+
"step": 194
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.14,
|
1176 |
+
"learning_rate": 0.0004,
|
1177 |
+
"loss": 1.4385,
|
1178 |
+
"step": 195
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.14,
|
1182 |
+
"learning_rate": 0.0004,
|
1183 |
+
"loss": 0.3418,
|
1184 |
+
"step": 196
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.14,
|
1188 |
+
"learning_rate": 0.0004,
|
1189 |
+
"loss": 0.8811,
|
1190 |
+
"step": 197
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 0.14,
|
1194 |
+
"learning_rate": 0.0004,
|
1195 |
+
"loss": 0.8176,
|
1196 |
+
"step": 198
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.14,
|
1200 |
+
"learning_rate": 0.0004,
|
1201 |
+
"loss": 0.5379,
|
1202 |
+
"step": 199
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.14,
|
1206 |
+
"learning_rate": 0.0004,
|
1207 |
+
"loss": 1.0277,
|
1208 |
+
"step": 200
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.14,
|
1212 |
+
"eval_loss": 0.662463366985321,
|
1213 |
+
"eval_runtime": 262.5709,
|
1214 |
+
"eval_samples_per_second": 1.904,
|
1215 |
+
"eval_steps_per_second": 0.952,
|
1216 |
+
"step": 200
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"epoch": 0.14,
|
1220 |
+
"mmlu_eval_accuracy": 0.41276444254447825,
|
1221 |
+
"mmlu_eval_accuracy_abstract_algebra": 0.09090909090909091,
|
1222 |
+
"mmlu_eval_accuracy_anatomy": 0.42857142857142855,
|
1223 |
+
"mmlu_eval_accuracy_astronomy": 0.5,
|
1224 |
+
"mmlu_eval_accuracy_business_ethics": 0.2727272727272727,
|
1225 |
+
"mmlu_eval_accuracy_clinical_knowledge": 0.4482758620689655,
|
1226 |
+
"mmlu_eval_accuracy_college_biology": 0.3125,
|
1227 |
+
"mmlu_eval_accuracy_college_chemistry": 0.375,
|
1228 |
+
"mmlu_eval_accuracy_college_computer_science": 0.5454545454545454,
|
1229 |
+
"mmlu_eval_accuracy_college_mathematics": 0.2727272727272727,
|
1230 |
+
"mmlu_eval_accuracy_college_medicine": 0.6363636363636364,
|
1231 |
+
"mmlu_eval_accuracy_college_physics": 0.2727272727272727,
|
1232 |
+
"mmlu_eval_accuracy_computer_security": 0.36363636363636365,
|
1233 |
+
"mmlu_eval_accuracy_conceptual_physics": 0.3076923076923077,
|
1234 |
+
"mmlu_eval_accuracy_econometrics": 0.4166666666666667,
|
1235 |
+
"mmlu_eval_accuracy_electrical_engineering": 0.5,
|
1236 |
+
"mmlu_eval_accuracy_elementary_mathematics": 0.4146341463414634,
|
1237 |
+
"mmlu_eval_accuracy_formal_logic": 0.5714285714285714,
|
1238 |
+
"mmlu_eval_accuracy_global_facts": 0.2,
|
1239 |
+
"mmlu_eval_accuracy_high_school_biology": 0.1875,
|
1240 |
+
"mmlu_eval_accuracy_high_school_chemistry": 0.4090909090909091,
|
1241 |
+
"mmlu_eval_accuracy_high_school_computer_science": 0.6666666666666666,
|
1242 |
+
"mmlu_eval_accuracy_high_school_european_history": 0.4444444444444444,
|
1243 |
+
"mmlu_eval_accuracy_high_school_geography": 0.5909090909090909,
|
1244 |
+
"mmlu_eval_accuracy_high_school_government_and_politics": 0.5714285714285714,
|
1245 |
+
"mmlu_eval_accuracy_high_school_macroeconomics": 0.32558139534883723,
|
1246 |
+
"mmlu_eval_accuracy_high_school_mathematics": 0.4482758620689655,
|
1247 |
+
"mmlu_eval_accuracy_high_school_microeconomics": 0.5714285714285714,
|
1248 |
+
"mmlu_loss": 0.7435930466353893,
|
1249 |
+
"step": 200
|
1250 |
+
}
|
1251 |
+
],
|
1252 |
+
"max_steps": 30000,
|
1253 |
+
"num_train_epochs": 22,
|
1254 |
+
"total_flos": 3.977831564987597e+16,
|
1255 |
+
"trial_name": null,
|
1256 |
+
"trial_params": null
|
1257 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc158bb44d89730af0d9db1f6729c5ae345af1012509e2cacbb0c714f3af20c7
|
3 |
+
size 5947
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
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 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": null,
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc158bb44d89730af0d9db1f6729c5ae345af1012509e2cacbb0c714f3af20c7
|
3 |
+
size 5947
|