Sen Fang commited on
Commit ·
f6aba9e
1
Parent(s): 91592d0
Up
Browse files- README.md +21 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +41 -0
- trainer_state.json +598 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: True
|
| 10 |
+
- load_in_4bit: False
|
| 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: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.5.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "/proj/berzelius-2023-175/users/x_senfa/apr_ft/llms/CodeLlama-7B-fp16",
|
| 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,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 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 sha256:1f2747abb0a4a3f0ba491cc27e01fc2dd0869afcebe7a2a3a1c336eaa3bad2ec
|
| 3 |
+
size 16822989
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<unk>",
|
| 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 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"bos_token": "<s>",
|
| 30 |
+
"clean_up_tokenization_spaces": false,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"legacy": null,
|
| 33 |
+
"model_max_length": 1024,
|
| 34 |
+
"pad_token": "<unk>",
|
| 35 |
+
"padding_side": "left",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"spaces_between_special_tokens": false,
|
| 38 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
+
"unk_token": "<unk>",
|
| 40 |
+
"use_default_system_prompt": true
|
| 41 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,598 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 10.0,
|
| 6 |
+
"global_step": 958,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 0.0004998655874501178,
|
| 14 |
+
"loss": 0.1139,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 0.0004994624943343398,
|
| 20 |
+
"loss": 0.0546,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.06,
|
| 25 |
+
"learning_rate": 0.0004987911540988544,
|
| 26 |
+
"loss": 0.0536,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.08,
|
| 31 |
+
"learning_rate": 0.0004978522886360845,
|
| 32 |
+
"loss": 0.0525,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.1,
|
| 37 |
+
"learning_rate": 0.0004966469075084369,
|
| 38 |
+
"loss": 0.0528,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.13,
|
| 43 |
+
"learning_rate": 0.0004951763068627193,
|
| 44 |
+
"loss": 0.0515,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.15,
|
| 49 |
+
"learning_rate": 0.0004934420680363928,
|
| 50 |
+
"loss": 0.0498,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.17,
|
| 55 |
+
"learning_rate": 0.0004914460558571595,
|
| 56 |
+
"loss": 0.05,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.19,
|
| 61 |
+
"learning_rate": 0.0004891904166377121,
|
| 62 |
+
"loss": 0.0548,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.21,
|
| 67 |
+
"learning_rate": 0.0004866775758678035,
|
| 68 |
+
"loss": 0.0493,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.23,
|
| 73 |
+
"learning_rate": 0.00048391023560611637,
|
| 74 |
+
"loss": 0.0471,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.25,
|
| 79 |
+
"learning_rate": 0.00048089137157473837,
|
| 80 |
+
"loss": 0.0507,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.27,
|
| 85 |
+
"learning_rate": 0.00047762422995936715,
|
| 86 |
+
"loss": 0.0522,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.29,
|
| 91 |
+
"learning_rate": 0.00047411232391868566,
|
| 92 |
+
"loss": 0.0546,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.31,
|
| 97 |
+
"learning_rate": 0.0004703594298066606,
|
| 98 |
+
"loss": 0.0505,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.33,
|
| 103 |
+
"learning_rate": 0.0004663695831118284,
|
| 104 |
+
"loss": 0.0535,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.35,
|
| 109 |
+
"learning_rate": 0.00046214707411793227,
|
| 110 |
+
"loss": 0.0499,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.38,
|
| 115 |
+
"learning_rate": 0.0004576964432905783,
|
| 116 |
+
"loss": 0.0483,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.4,
|
| 121 |
+
"learning_rate": 0.00045302247639487117,
|
| 122 |
+
"loss": 0.0496,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.42,
|
| 127 |
+
"learning_rate": 0.00044813019934927903,
|
| 128 |
+
"loss": 0.0464,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.44,
|
| 133 |
+
"learning_rate": 0.0004430248728212613,
|
| 134 |
+
"loss": 0.0556,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.46,
|
| 139 |
+
"learning_rate": 0.00043771198657047085,
|
| 140 |
+
"loss": 0.047,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.48,
|
| 145 |
+
"learning_rate": 0.0004321972535456134,
|
| 146 |
+
"loss": 0.0508,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.5,
|
| 151 |
+
"learning_rate": 0.0004264866037413112,
|
| 152 |
+
"loss": 0.0518,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.52,
|
| 157 |
+
"learning_rate": 0.0004205861778215777,
|
| 158 |
+
"loss": 0.0504,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.54,
|
| 163 |
+
"learning_rate": 0.000414502320516759,
|
| 164 |
+
"loss": 0.0476,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.56,
|
| 169 |
+
"learning_rate": 0.00040824157380104276,
|
| 170 |
+
"loss": 0.0491,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.58,
|
| 175 |
+
"learning_rate": 0.00040181066985787084,
|
| 176 |
+
"loss": 0.0508,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.61,
|
| 181 |
+
"learning_rate": 0.00039521652384081956,
|
| 182 |
+
"loss": 0.0494,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.63,
|
| 187 |
+
"learning_rate": 0.0003884662264377326,
|
| 188 |
+
"loss": 0.0479,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.65,
|
| 193 |
+
"learning_rate": 0.0003815670362461011,
|
| 194 |
+
"loss": 0.0522,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.67,
|
| 199 |
+
"learning_rate": 0.00037452637196789146,
|
| 200 |
+
"loss": 0.0508,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.69,
|
| 205 |
+
"learning_rate": 0.00036735180443221157,
|
| 206 |
+
"loss": 0.0495,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.71,
|
| 211 |
+
"learning_rate": 0.0003600510484543956,
|
| 212 |
+
"loss": 0.0525,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.73,
|
| 217 |
+
"learning_rate": 0.00035263195454026,
|
| 218 |
+
"loss": 0.0512,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.75,
|
| 223 |
+
"learning_rate": 0.0003451025004444512,
|
| 224 |
+
"loss": 0.0523,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.77,
|
| 229 |
+
"learning_rate": 0.0003374707825919631,
|
| 230 |
+
"loss": 0.047,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.79,
|
| 235 |
+
"learning_rate": 0.0003297450073720481,
|
| 236 |
+
"loss": 0.0539,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.81,
|
| 241 |
+
"learning_rate": 0.000321933482313883,
|
| 242 |
+
"loss": 0.0531,
|
| 243 |
+
"step": 390
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.84,
|
| 247 |
+
"learning_rate": 0.0003140446071534803,
|
| 248 |
+
"loss": 0.0499,
|
| 249 |
+
"step": 400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.86,
|
| 253 |
+
"learning_rate": 0.0003060868648014479,
|
| 254 |
+
"loss": 0.0531,
|
| 255 |
+
"step": 410
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.88,
|
| 259 |
+
"learning_rate": 0.00029806881222131274,
|
| 260 |
+
"loss": 0.053,
|
| 261 |
+
"step": 420
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.9,
|
| 265 |
+
"learning_rate": 0.00028999907122821374,
|
| 266 |
+
"loss": 0.0479,
|
| 267 |
+
"step": 430
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.92,
|
| 271 |
+
"learning_rate": 0.00028188631921786104,
|
| 272 |
+
"loss": 0.0525,
|
| 273 |
+
"step": 440
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.94,
|
| 277 |
+
"learning_rate": 0.00027373927983572903,
|
| 278 |
+
"loss": 0.0526,
|
| 279 |
+
"step": 450
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.96,
|
| 283 |
+
"learning_rate": 0.0002655667135965163,
|
| 284 |
+
"loss": 0.0483,
|
| 285 |
+
"step": 460
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.98,
|
| 289 |
+
"learning_rate": 0.0002573774084639612,
|
| 290 |
+
"loss": 0.052,
|
| 291 |
+
"step": 470
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.0,
|
| 295 |
+
"learning_rate": 0.00024918017040114084,
|
| 296 |
+
"loss": 0.0481,
|
| 297 |
+
"step": 480
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.02,
|
| 301 |
+
"learning_rate": 0.00024098381390141524,
|
| 302 |
+
"loss": 0.0462,
|
| 303 |
+
"step": 490
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.04,
|
| 307 |
+
"learning_rate": 0.00023279715251019938,
|
| 308 |
+
"loss": 0.0437,
|
| 309 |
+
"step": 500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.06,
|
| 313 |
+
"learning_rate": 0.00022462898934775432,
|
| 314 |
+
"loss": 0.05,
|
| 315 |
+
"step": 510
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.09,
|
| 319 |
+
"learning_rate": 0.0002164881076431881,
|
| 320 |
+
"loss": 0.0466,
|
| 321 |
+
"step": 520
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.11,
|
| 325 |
+
"learning_rate": 0.00020838326128984626,
|
| 326 |
+
"loss": 0.0479,
|
| 327 |
+
"step": 530
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.13,
|
| 331 |
+
"learning_rate": 0.00020032316543224692,
|
| 332 |
+
"loss": 0.0509,
|
| 333 |
+
"step": 540
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.15,
|
| 337 |
+
"learning_rate": 0.00019231648709468226,
|
| 338 |
+
"loss": 0.0469,
|
| 339 |
+
"step": 550
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.17,
|
| 343 |
+
"learning_rate": 0.00018437183586156365,
|
| 344 |
+
"loss": 0.0472,
|
| 345 |
+
"step": 560
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.19,
|
| 349 |
+
"learning_rate": 0.00017649775461953248,
|
| 350 |
+
"loss": 0.0495,
|
| 351 |
+
"step": 570
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.21,
|
| 355 |
+
"learning_rate": 0.00016870271037129053,
|
| 356 |
+
"loss": 0.0464,
|
| 357 |
+
"step": 580
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.23,
|
| 361 |
+
"learning_rate": 0.0001609950851310287,
|
| 362 |
+
"loss": 0.0494,
|
| 363 |
+
"step": 590
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.25,
|
| 367 |
+
"learning_rate": 0.0001533831669112435,
|
| 368 |
+
"loss": 0.0487,
|
| 369 |
+
"step": 600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.27,
|
| 373 |
+
"learning_rate": 0.00014587514081063424,
|
| 374 |
+
"loss": 0.0471,
|
| 375 |
+
"step": 610
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.29,
|
| 379 |
+
"learning_rate": 0.0001384790802126631,
|
| 380 |
+
"loss": 0.0512,
|
| 381 |
+
"step": 620
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.32,
|
| 385 |
+
"learning_rate": 0.00013120293810424256,
|
| 386 |
+
"loss": 0.0445,
|
| 387 |
+
"step": 630
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.34,
|
| 391 |
+
"learning_rate": 0.0001240545385238853,
|
| 392 |
+
"loss": 0.0447,
|
| 393 |
+
"step": 640
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.36,
|
| 397 |
+
"learning_rate": 0.00011704156814851283,
|
| 398 |
+
"loss": 0.0481,
|
| 399 |
+
"step": 650
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.38,
|
| 403 |
+
"learning_rate": 0.00011017156802796823,
|
| 404 |
+
"loss": 0.0474,
|
| 405 |
+
"step": 660
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.4,
|
| 409 |
+
"learning_rate": 0.00010345192547612278,
|
| 410 |
+
"loss": 0.0434,
|
| 411 |
+
"step": 670
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.42,
|
| 415 |
+
"learning_rate": 9.688986612729387e-05,
|
| 416 |
+
"loss": 0.0464,
|
| 417 |
+
"step": 680
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.44,
|
| 421 |
+
"learning_rate": 9.049244616651797e-05,
|
| 422 |
+
"loss": 0.0472,
|
| 423 |
+
"step": 690
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.46,
|
| 427 |
+
"learning_rate": 8.426654474203194e-05,
|
| 428 |
+
"loss": 0.046,
|
| 429 |
+
"step": 700
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.48,
|
| 433 |
+
"learning_rate": 7.821885656812198e-05,
|
| 434 |
+
"loss": 0.0465,
|
| 435 |
+
"step": 710
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.5,
|
| 439 |
+
"learning_rate": 7.235588472629473e-05,
|
| 440 |
+
"loss": 0.0434,
|
| 441 |
+
"step": 720
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.52,
|
| 445 |
+
"learning_rate": 6.668393367251147e-05,
|
| 446 |
+
"loss": 0.0465,
|
| 447 |
+
"step": 730
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.54,
|
| 451 |
+
"learning_rate": 6.120910245800385e-05,
|
| 452 |
+
"loss": 0.0457,
|
| 453 |
+
"step": 740
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.57,
|
| 457 |
+
"learning_rate": 5.593727817096153e-05,
|
| 458 |
+
"loss": 0.0498,
|
| 459 |
+
"step": 750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.59,
|
| 463 |
+
"learning_rate": 5.0874129606144015e-05,
|
| 464 |
+
"loss": 0.0453,
|
| 465 |
+
"step": 760
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.61,
|
| 469 |
+
"learning_rate": 4.6025101169223675e-05,
|
| 470 |
+
"loss": 0.0481,
|
| 471 |
+
"step": 770
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.63,
|
| 475 |
+
"learning_rate": 4.139540702241373e-05,
|
| 476 |
+
"loss": 0.0467,
|
| 477 |
+
"step": 780
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.65,
|
| 481 |
+
"learning_rate": 3.6990025477677825e-05,
|
| 482 |
+
"loss": 0.0439,
|
| 483 |
+
"step": 790
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.67,
|
| 487 |
+
"learning_rate": 3.281369364354897e-05,
|
| 488 |
+
"loss": 0.0428,
|
| 489 |
+
"step": 800
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.69,
|
| 493 |
+
"learning_rate": 2.8870902331314925e-05,
|
| 494 |
+
"loss": 0.0464,
|
| 495 |
+
"step": 810
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.71,
|
| 499 |
+
"learning_rate": 2.516589122604718e-05,
|
| 500 |
+
"loss": 0.0509,
|
| 501 |
+
"step": 820
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.73,
|
| 505 |
+
"learning_rate": 2.1702644327665803e-05,
|
| 506 |
+
"loss": 0.0477,
|
| 507 |
+
"step": 830
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.75,
|
| 511 |
+
"learning_rate": 1.8484885666942618e-05,
|
| 512 |
+
"loss": 0.05,
|
| 513 |
+
"step": 840
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.77,
|
| 517 |
+
"learning_rate": 1.551607530104951e-05,
|
| 518 |
+
"loss": 0.046,
|
| 519 |
+
"step": 850
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.8,
|
| 523 |
+
"learning_rate": 1.2799405592957697e-05,
|
| 524 |
+
"loss": 0.0477,
|
| 525 |
+
"step": 860
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.82,
|
| 529 |
+
"learning_rate": 1.0337797778688457e-05,
|
| 530 |
+
"loss": 0.0479,
|
| 531 |
+
"step": 870
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.84,
|
| 535 |
+
"learning_rate": 8.133898826106685e-06,
|
| 536 |
+
"loss": 0.0502,
|
| 537 |
+
"step": 880
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.86,
|
| 541 |
+
"learning_rate": 6.190078588635684e-06,
|
| 542 |
+
"loss": 0.0495,
|
| 543 |
+
"step": 890
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.88,
|
| 547 |
+
"learning_rate": 4.508427256952413e-06,
|
| 548 |
+
"loss": 0.0496,
|
| 549 |
+
"step": 900
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.9,
|
| 553 |
+
"learning_rate": 3.0907531114049427e-06,
|
| 554 |
+
"loss": 0.0503,
|
| 555 |
+
"step": 910
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.92,
|
| 559 |
+
"learning_rate": 1.9385805775677112e-06,
|
| 560 |
+
"loss": 0.0505,
|
| 561 |
+
"step": 920
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.94,
|
| 565 |
+
"learning_rate": 1.0531485870261537e-06,
|
| 566 |
+
"loss": 0.0442,
|
| 567 |
+
"step": 930
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.96,
|
| 571 |
+
"learning_rate": 4.3540924515300673e-07,
|
| 572 |
+
"loss": 0.0456,
|
| 573 |
+
"step": 940
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.98,
|
| 577 |
+
"learning_rate": 8.602680730912526e-08,
|
| 578 |
+
"loss": 0.0447,
|
| 579 |
+
"step": 950
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.0,
|
| 583 |
+
"step": 958,
|
| 584 |
+
"total_flos": 2.3298774185688433e+18,
|
| 585 |
+
"train_loss": 0.04974690033025682,
|
| 586 |
+
"train_runtime": 16786.4105,
|
| 587 |
+
"train_samples_per_second": 3.651,
|
| 588 |
+
"train_steps_per_second": 0.057
|
| 589 |
+
}
|
| 590 |
+
],
|
| 591 |
+
"logging_steps": 10,
|
| 592 |
+
"max_steps": 958,
|
| 593 |
+
"num_train_epochs": 2,
|
| 594 |
+
"save_steps": 150,
|
| 595 |
+
"total_flos": 2.3298774185688433e+18,
|
| 596 |
+
"trial_name": null,
|
| 597 |
+
"trial_params": null
|
| 598 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc194aad6b1eb42a71853370ac441e673c09578ed6cd75a8a00c80321488ee6b
|
| 3 |
+
size 4219
|