Sen Fang
commited on
Commit
·
fe68e64
1
Parent(s):
17e15c7
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 +856 -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 sha256:97340853b968139c1de6a84134ba75c41ad881275151d94da27c7cc52544ffd9
|
| 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 +1,856 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 10.0,
|
| 6 |
+
"global_step": 1388,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 0.0004999359657561555,
|
| 14 |
+
"loss": 0.5112,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 0.0004997438958276968,
|
| 20 |
+
"loss": 0.2283,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 0.0004994238886070454,
|
| 26 |
+
"loss": 0.2077,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.06,
|
| 31 |
+
"learning_rate": 0.0004989761080255641,
|
| 32 |
+
"loss": 0.2174,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.07,
|
| 37 |
+
"learning_rate": 0.0004984007834695806,
|
| 38 |
+
"loss": 0.1994,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.09,
|
| 43 |
+
"learning_rate": 0.0004976982096628782,
|
| 44 |
+
"loss": 0.2143,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1,
|
| 49 |
+
"learning_rate": 0.0004968687465157165,
|
| 50 |
+
"loss": 0.2168,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12,
|
| 55 |
+
"learning_rate": 0.0004959128189404589,
|
| 56 |
+
"loss": 0.2175,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.13,
|
| 61 |
+
"learning_rate": 0.000494830916633901,
|
| 62 |
+
"loss": 0.2134,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.14,
|
| 67 |
+
"learning_rate": 0.0004936235938264118,
|
| 68 |
+
"loss": 0.2064,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.16,
|
| 73 |
+
"learning_rate": 0.0004922914689980156,
|
| 74 |
+
"loss": 0.2032,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.17,
|
| 79 |
+
"learning_rate": 0.0004908352245615613,
|
| 80 |
+
"loss": 0.2017,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.19,
|
| 85 |
+
"learning_rate": 0.0004892556065131395,
|
| 86 |
+
"loss": 0.2127,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.2,
|
| 91 |
+
"learning_rate": 0.0004875534240499285,
|
| 92 |
+
"loss": 0.2074,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.22,
|
| 97 |
+
"learning_rate": 0.00048572954915566393,
|
| 98 |
+
"loss": 0.2013,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.23,
|
| 103 |
+
"learning_rate": 0.0004837849161539432,
|
| 104 |
+
"loss": 0.2188,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.24,
|
| 109 |
+
"learning_rate": 0.00048172052122959707,
|
| 110 |
+
"loss": 0.1919,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.26,
|
| 115 |
+
"learning_rate": 0.0004795374219183694,
|
| 116 |
+
"loss": 0.1966,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.27,
|
| 121 |
+
"learning_rate": 0.0004772367365651691,
|
| 122 |
+
"loss": 0.2088,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.29,
|
| 127 |
+
"learning_rate": 0.0004748196437511716,
|
| 128 |
+
"loss": 0.2163,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3,
|
| 133 |
+
"learning_rate": 0.00047228738169006204,
|
| 134 |
+
"loss": 0.2013,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.32,
|
| 139 |
+
"learning_rate": 0.00046964124759373086,
|
| 140 |
+
"loss": 0.194,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.33,
|
| 145 |
+
"learning_rate": 0.0004668825970077457,
|
| 146 |
+
"loss": 0.2002,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.35,
|
| 151 |
+
"learning_rate": 0.0004640128431169411,
|
| 152 |
+
"loss": 0.2095,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.36,
|
| 157 |
+
"learning_rate": 0.0004613362851634204,
|
| 158 |
+
"loss": 0.1917,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.37,
|
| 163 |
+
"learning_rate": 0.0004582595315535216,
|
| 164 |
+
"loss": 0.2054,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.39,
|
| 169 |
+
"learning_rate": 0.0004550760920106112,
|
| 170 |
+
"loss": 0.1925,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.4,
|
| 175 |
+
"learning_rate": 0.00045178759732784093,
|
| 176 |
+
"loss": 0.2157,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.42,
|
| 181 |
+
"learning_rate": 0.0004483957321153738,
|
| 182 |
+
"loss": 0.2246,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.43,
|
| 187 |
+
"learning_rate": 0.0004449022339374027,
|
| 188 |
+
"loss": 0.191,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.45,
|
| 193 |
+
"learning_rate": 0.00044130889242204133,
|
| 194 |
+
"loss": 0.1808,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.46,
|
| 199 |
+
"learning_rate": 0.000437617548344544,
|
| 200 |
+
"loss": 0.2044,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.48,
|
| 205 |
+
"learning_rate": 0.000433830092684325,
|
| 206 |
+
"loss": 0.1829,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.49,
|
| 211 |
+
"learning_rate": 0.00042994846565625865,
|
| 212 |
+
"loss": 0.2009,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5,
|
| 217 |
+
"learning_rate": 0.0004259746557167581,
|
| 218 |
+
"loss": 0.1963,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.52,
|
| 223 |
+
"learning_rate": 0.0004219106985451405,
|
| 224 |
+
"loss": 0.1933,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.53,
|
| 229 |
+
"learning_rate": 0.00041775867600080184,
|
| 230 |
+
"loss": 0.1948,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.55,
|
| 235 |
+
"learning_rate": 0.0004135207150567347,
|
| 236 |
+
"loss": 0.2036,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.56,
|
| 241 |
+
"learning_rate": 0.00040919898670993484,
|
| 242 |
+
"loss": 0.2048,
|
| 243 |
+
"step": 390
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.58,
|
| 247 |
+
"learning_rate": 0.0004047957048692567,
|
| 248 |
+
"loss": 0.1881,
|
| 249 |
+
"step": 400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.59,
|
| 253 |
+
"learning_rate": 0.00040031312522128507,
|
| 254 |
+
"loss": 0.2143,
|
| 255 |
+
"step": 410
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.61,
|
| 259 |
+
"learning_rate": 0.00039575354407480576,
|
| 260 |
+
"loss": 0.1904,
|
| 261 |
+
"step": 420
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.62,
|
| 265 |
+
"learning_rate": 0.00039111929718446654,
|
| 266 |
+
"loss": 0.1989,
|
| 267 |
+
"step": 430
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.63,
|
| 271 |
+
"learning_rate": 0.00038641275855423065,
|
| 272 |
+
"loss": 0.1971,
|
| 273 |
+
"step": 440
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.65,
|
| 277 |
+
"learning_rate": 0.0003816363392212366,
|
| 278 |
+
"loss": 0.1899,
|
| 279 |
+
"step": 450
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.66,
|
| 283 |
+
"learning_rate": 0.00037679248602068657,
|
| 284 |
+
"loss": 0.2091,
|
| 285 |
+
"step": 460
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.68,
|
| 289 |
+
"learning_rate": 0.0003718836803323966,
|
| 290 |
+
"loss": 0.1943,
|
| 291 |
+
"step": 470
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.69,
|
| 295 |
+
"learning_rate": 0.00036691243680964987,
|
| 296 |
+
"loss": 0.1907,
|
| 297 |
+
"step": 480
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.71,
|
| 301 |
+
"learning_rate": 0.0003618813020910061,
|
| 302 |
+
"loss": 0.1983,
|
| 303 |
+
"step": 490
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.72,
|
| 307 |
+
"learning_rate": 0.00035679285349572454,
|
| 308 |
+
"loss": 0.2036,
|
| 309 |
+
"step": 500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.73,
|
| 313 |
+
"learning_rate": 0.00035164969770347013,
|
| 314 |
+
"loss": 0.1852,
|
| 315 |
+
"step": 510
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.75,
|
| 319 |
+
"learning_rate": 0.0003464544694189799,
|
| 320 |
+
"loss": 0.1825,
|
| 321 |
+
"step": 520
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.76,
|
| 325 |
+
"learning_rate": 0.0003412098300223723,
|
| 326 |
+
"loss": 0.2118,
|
| 327 |
+
"step": 530
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.78,
|
| 331 |
+
"learning_rate": 0.0003359184662057914,
|
| 332 |
+
"loss": 0.19,
|
| 333 |
+
"step": 540
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.79,
|
| 337 |
+
"learning_rate": 0.00033058308859708433,
|
| 338 |
+
"loss": 0.1877,
|
| 339 |
+
"step": 550
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.81,
|
| 343 |
+
"learning_rate": 0.0003252064303712174,
|
| 344 |
+
"loss": 0.1932,
|
| 345 |
+
"step": 560
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.82,
|
| 349 |
+
"learning_rate": 0.000319791245850142,
|
| 350 |
+
"loss": 0.1983,
|
| 351 |
+
"step": 570
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.84,
|
| 355 |
+
"learning_rate": 0.00031434030909182665,
|
| 356 |
+
"loss": 0.2146,
|
| 357 |
+
"step": 580
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.85,
|
| 361 |
+
"learning_rate": 0.00030885641246917994,
|
| 362 |
+
"loss": 0.1957,
|
| 363 |
+
"step": 590
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.86,
|
| 367 |
+
"learning_rate": 0.00030334236523959037,
|
| 368 |
+
"loss": 0.1933,
|
| 369 |
+
"step": 600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.88,
|
| 373 |
+
"learning_rate": 0.00029780099210581685,
|
| 374 |
+
"loss": 0.1981,
|
| 375 |
+
"step": 610
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.89,
|
| 379 |
+
"learning_rate": 0.0002922351317689671,
|
| 380 |
+
"loss": 0.2009,
|
| 381 |
+
"step": 620
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.91,
|
| 385 |
+
"learning_rate": 0.0002866476354743054,
|
| 386 |
+
"loss": 0.1849,
|
| 387 |
+
"step": 630
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.92,
|
| 391 |
+
"learning_rate": 0.0002810413655506334,
|
| 392 |
+
"loss": 0.2011,
|
| 393 |
+
"step": 640
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.94,
|
| 397 |
+
"learning_rate": 0.00027541919394399395,
|
| 398 |
+
"loss": 0.1786,
|
| 399 |
+
"step": 650
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.95,
|
| 403 |
+
"learning_rate": 0.00026978400074644773,
|
| 404 |
+
"loss": 0.1929,
|
| 405 |
+
"step": 660
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.97,
|
| 409 |
+
"learning_rate": 0.0002641386727206773,
|
| 410 |
+
"loss": 0.2051,
|
| 411 |
+
"step": 670
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.98,
|
| 415 |
+
"learning_rate": 0.0002584861018211739,
|
| 416 |
+
"loss": 0.1916,
|
| 417 |
+
"step": 680
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.99,
|
| 421 |
+
"learning_rate": 0.00025282918371276396,
|
| 422 |
+
"loss": 0.1748,
|
| 423 |
+
"step": 690
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.01,
|
| 427 |
+
"learning_rate": 0.0002471708162872361,
|
| 428 |
+
"loss": 0.1949,
|
| 429 |
+
"step": 700
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.02,
|
| 433 |
+
"learning_rate": 0.00024151389817882616,
|
| 434 |
+
"loss": 0.1775,
|
| 435 |
+
"step": 710
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.04,
|
| 439 |
+
"learning_rate": 0.0002358613272793227,
|
| 440 |
+
"loss": 0.1885,
|
| 441 |
+
"step": 720
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.05,
|
| 445 |
+
"learning_rate": 0.0002302159992535523,
|
| 446 |
+
"loss": 0.1959,
|
| 447 |
+
"step": 730
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.07,
|
| 451 |
+
"learning_rate": 0.00022458080605600617,
|
| 452 |
+
"loss": 0.1842,
|
| 453 |
+
"step": 740
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.08,
|
| 457 |
+
"learning_rate": 0.00021895863444936663,
|
| 458 |
+
"loss": 0.1943,
|
| 459 |
+
"step": 750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.1,
|
| 463 |
+
"learning_rate": 0.0002133523645256946,
|
| 464 |
+
"loss": 0.1779,
|
| 465 |
+
"step": 760
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.11,
|
| 469 |
+
"learning_rate": 0.0002077648682310329,
|
| 470 |
+
"loss": 0.178,
|
| 471 |
+
"step": 770
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.12,
|
| 475 |
+
"learning_rate": 0.0002021990078941832,
|
| 476 |
+
"loss": 0.1978,
|
| 477 |
+
"step": 780
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.14,
|
| 481 |
+
"learning_rate": 0.00019665763476040964,
|
| 482 |
+
"loss": 0.165,
|
| 483 |
+
"step": 790
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.15,
|
| 487 |
+
"learning_rate": 0.00019114358753082,
|
| 488 |
+
"loss": 0.1731,
|
| 489 |
+
"step": 800
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.17,
|
| 493 |
+
"learning_rate": 0.0001856596909081734,
|
| 494 |
+
"loss": 0.1926,
|
| 495 |
+
"step": 810
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.18,
|
| 499 |
+
"learning_rate": 0.0001802087541498581,
|
| 500 |
+
"loss": 0.1844,
|
| 501 |
+
"step": 820
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.2,
|
| 505 |
+
"learning_rate": 0.0001747935696287826,
|
| 506 |
+
"loss": 0.1672,
|
| 507 |
+
"step": 830
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.21,
|
| 511 |
+
"learning_rate": 0.0001694169114029157,
|
| 512 |
+
"loss": 0.1857,
|
| 513 |
+
"step": 840
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.22,
|
| 517 |
+
"learning_rate": 0.0001640815337942086,
|
| 518 |
+
"loss": 0.171,
|
| 519 |
+
"step": 850
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.24,
|
| 523 |
+
"learning_rate": 0.00015879016997762767,
|
| 524 |
+
"loss": 0.1693,
|
| 525 |
+
"step": 860
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.25,
|
| 529 |
+
"learning_rate": 0.00015354553058102009,
|
| 530 |
+
"loss": 0.175,
|
| 531 |
+
"step": 870
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.27,
|
| 535 |
+
"learning_rate": 0.00014835030229652999,
|
| 536 |
+
"loss": 0.1764,
|
| 537 |
+
"step": 880
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.28,
|
| 541 |
+
"learning_rate": 0.00014320714650427552,
|
| 542 |
+
"loss": 0.1803,
|
| 543 |
+
"step": 890
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.3,
|
| 547 |
+
"learning_rate": 0.0001381186979089939,
|
| 548 |
+
"loss": 0.1916,
|
| 549 |
+
"step": 900
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.31,
|
| 553 |
+
"learning_rate": 0.00013308756319035017,
|
| 554 |
+
"loss": 0.1639,
|
| 555 |
+
"step": 910
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.33,
|
| 559 |
+
"learning_rate": 0.0001281163196676035,
|
| 560 |
+
"loss": 0.1835,
|
| 561 |
+
"step": 920
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.34,
|
| 565 |
+
"learning_rate": 0.00012320751397931342,
|
| 566 |
+
"loss": 0.1869,
|
| 567 |
+
"step": 930
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.35,
|
| 571 |
+
"learning_rate": 0.0001183636607787634,
|
| 572 |
+
"loss": 0.1858,
|
| 573 |
+
"step": 940
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.37,
|
| 577 |
+
"learning_rate": 0.00011358724144576943,
|
| 578 |
+
"loss": 0.1773,
|
| 579 |
+
"step": 950
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.38,
|
| 583 |
+
"learning_rate": 0.00010888070281553353,
|
| 584 |
+
"loss": 0.177,
|
| 585 |
+
"step": 960
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.4,
|
| 589 |
+
"learning_rate": 0.0001042464559251943,
|
| 590 |
+
"loss": 0.2,
|
| 591 |
+
"step": 970
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.41,
|
| 595 |
+
"learning_rate": 9.9686874778715e-05,
|
| 596 |
+
"loss": 0.1809,
|
| 597 |
+
"step": 980
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.43,
|
| 601 |
+
"learning_rate": 9.520429513074334e-05,
|
| 602 |
+
"loss": 0.1784,
|
| 603 |
+
"step": 990
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.44,
|
| 607 |
+
"learning_rate": 9.080101329006519e-05,
|
| 608 |
+
"loss": 0.1873,
|
| 609 |
+
"step": 1000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.46,
|
| 613 |
+
"learning_rate": 8.647928494326535e-05,
|
| 614 |
+
"loss": 0.1681,
|
| 615 |
+
"step": 1010
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.47,
|
| 619 |
+
"learning_rate": 8.224132399919812e-05,
|
| 620 |
+
"loss": 0.1873,
|
| 621 |
+
"step": 1020
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.48,
|
| 625 |
+
"learning_rate": 7.808930145485957e-05,
|
| 626 |
+
"loss": 0.1849,
|
| 627 |
+
"step": 1030
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.5,
|
| 631 |
+
"learning_rate": 7.402534428324195e-05,
|
| 632 |
+
"loss": 0.2012,
|
| 633 |
+
"step": 1040
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.51,
|
| 637 |
+
"learning_rate": 7.005153434374137e-05,
|
| 638 |
+
"loss": 0.193,
|
| 639 |
+
"step": 1050
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.53,
|
| 643 |
+
"learning_rate": 6.616990731567505e-05,
|
| 644 |
+
"loss": 0.1779,
|
| 645 |
+
"step": 1060
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.54,
|
| 649 |
+
"learning_rate": 6.238245165545606e-05,
|
| 650 |
+
"loss": 0.1651,
|
| 651 |
+
"step": 1070
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.56,
|
| 655 |
+
"learning_rate": 5.869110757795876e-05,
|
| 656 |
+
"loss": 0.1727,
|
| 657 |
+
"step": 1080
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.57,
|
| 661 |
+
"learning_rate": 5.509776606259731e-05,
|
| 662 |
+
"loss": 0.1933,
|
| 663 |
+
"step": 1090
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.59,
|
| 667 |
+
"learning_rate": 5.16042678846263e-05,
|
| 668 |
+
"loss": 0.1969,
|
| 669 |
+
"step": 1100
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.6,
|
| 673 |
+
"learning_rate": 4.821240267215918e-05,
|
| 674 |
+
"loss": 0.1819,
|
| 675 |
+
"step": 1110
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.61,
|
| 679 |
+
"learning_rate": 4.492390798938883e-05,
|
| 680 |
+
"loss": 0.168,
|
| 681 |
+
"step": 1120
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.63,
|
| 685 |
+
"learning_rate": 4.174046844647844e-05,
|
| 686 |
+
"loss": 0.1774,
|
| 687 |
+
"step": 1130
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.64,
|
| 691 |
+
"learning_rate": 3.8663714836579624e-05,
|
| 692 |
+
"loss": 0.1836,
|
| 693 |
+
"step": 1140
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.66,
|
| 697 |
+
"learning_rate": 3.569522330041969e-05,
|
| 698 |
+
"loss": 0.1664,
|
| 699 |
+
"step": 1150
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.67,
|
| 703 |
+
"learning_rate": 3.2836514518885615e-05,
|
| 704 |
+
"loss": 0.1638,
|
| 705 |
+
"step": 1160
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.69,
|
| 709 |
+
"learning_rate": 3.008905293401895e-05,
|
| 710 |
+
"loss": 0.2014,
|
| 711 |
+
"step": 1170
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.7,
|
| 715 |
+
"learning_rate": 2.7454245998820376e-05,
|
| 716 |
+
"loss": 0.1918,
|
| 717 |
+
"step": 1180
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.71,
|
| 721 |
+
"learning_rate": 2.4933443456248068e-05,
|
| 722 |
+
"loss": 0.1968,
|
| 723 |
+
"step": 1190
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.73,
|
| 727 |
+
"learning_rate": 2.2527936647779522e-05,
|
| 728 |
+
"loss": 0.1702,
|
| 729 |
+
"step": 1200
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.74,
|
| 733 |
+
"learning_rate": 2.0238957851891172e-05,
|
| 734 |
+
"loss": 0.1611,
|
| 735 |
+
"step": 1210
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.76,
|
| 739 |
+
"learning_rate": 1.8067679652793905e-05,
|
| 740 |
+
"loss": 0.186,
|
| 741 |
+
"step": 1220
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.77,
|
| 745 |
+
"learning_rate": 1.6015214339749063e-05,
|
| 746 |
+
"loss": 0.1758,
|
| 747 |
+
"step": 1230
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.79,
|
| 751 |
+
"learning_rate": 1.4082613337271234e-05,
|
| 752 |
+
"loss": 0.1624,
|
| 753 |
+
"step": 1240
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.8,
|
| 757 |
+
"learning_rate": 1.2270866666511254e-05,
|
| 758 |
+
"loss": 0.1843,
|
| 759 |
+
"step": 1250
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.82,
|
| 763 |
+
"learning_rate": 1.0580902438093925e-05,
|
| 764 |
+
"loss": 0.191,
|
| 765 |
+
"step": 1260
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.83,
|
| 769 |
+
"learning_rate": 9.013586376671157e-06,
|
| 770 |
+
"loss": 0.1807,
|
| 771 |
+
"step": 1270
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.84,
|
| 775 |
+
"learning_rate": 7.569721377433808e-06,
|
| 776 |
+
"loss": 0.1891,
|
| 777 |
+
"step": 1280
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.86,
|
| 781 |
+
"learning_rate": 6.250047094809447e-06,
|
| 782 |
+
"loss": 0.1855,
|
| 783 |
+
"step": 1290
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.87,
|
| 787 |
+
"learning_rate": 5.055239563556496e-06,
|
| 788 |
+
"loss": 0.1924,
|
| 789 |
+
"step": 1300
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.89,
|
| 793 |
+
"learning_rate": 3.985910852449398e-06,
|
| 794 |
+
"loss": 0.1995,
|
| 795 |
+
"step": 1310
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.9,
|
| 799 |
+
"learning_rate": 3.0426087507316735e-06,
|
| 800 |
+
"loss": 0.1938,
|
| 801 |
+
"step": 1320
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.92,
|
| 805 |
+
"learning_rate": 2.2258164874976726e-06,
|
| 806 |
+
"loss": 0.1813,
|
| 807 |
+
"step": 1330
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.93,
|
| 811 |
+
"learning_rate": 1.5359524841470907e-06,
|
| 812 |
+
"loss": 0.1723,
|
| 813 |
+
"step": 1340
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.95,
|
| 817 |
+
"learning_rate": 9.73370140038371e-07,
|
| 818 |
+
"loss": 0.1804,
|
| 819 |
+
"step": 1350
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.96,
|
| 823 |
+
"learning_rate": 5.383576514515487e-07,
|
| 824 |
+
"loss": 0.1838,
|
| 825 |
+
"step": 1360
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.97,
|
| 829 |
+
"learning_rate": 2.3113786395281833e-07,
|
| 830 |
+
"loss": 0.1753,
|
| 831 |
+
"step": 1370
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.99,
|
| 835 |
+
"learning_rate": 5.1868158236434427e-08,
|
| 836 |
+
"loss": 0.1876,
|
| 837 |
+
"step": 1380
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.0,
|
| 841 |
+
"step": 1388,
|
| 842 |
+
"total_flos": 3.2633842202899907e+18,
|
| 843 |
+
"train_loss": 0.19332071949837873,
|
| 844 |
+
"train_runtime": 22791.3585,
|
| 845 |
+
"train_samples_per_second": 3.893,
|
| 846 |
+
"train_steps_per_second": 0.061
|
| 847 |
+
}
|
| 848 |
+
],
|
| 849 |
+
"logging_steps": 10,
|
| 850 |
+
"max_steps": 1388,
|
| 851 |
+
"num_train_epochs": 2,
|
| 852 |
+
"save_steps": 300,
|
| 853 |
+
"total_flos": 3.2633842202899907e+18,
|
| 854 |
+
"trial_name": null,
|
| 855 |
+
"trial_params": null
|
| 856 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc416e205cfd2e35b3cacfbb5f6ff63caa9f57b9345fa8be89cf3b5056a71aa3
|
| 3 |
+
size 4219
|