Commit
•
8abf5a8
1
Parent(s):
8aefa3c
Model save
Browse files- README.md +56 -0
- adapter_config.json +25 -0
- adapter_model.safetensors +3 -0
- all_results.json +8 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +40 -0
- train_results.json +8 -0
- trainer_state.json +688 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: LeoLM/leo-hessianai-13b
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: leoLM-13b-sft-lora-oa
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# leoLM-13b-sft-lora-oa
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [LeoLM/leo-hessianai-13b](https://huggingface.co/LeoLM/leo-hessianai-13b) on an unknown dataset.
|
| 16 |
+
|
| 17 |
+
## Model description
|
| 18 |
+
|
| 19 |
+
More information needed
|
| 20 |
+
|
| 21 |
+
## Intended uses & limitations
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Training and evaluation data
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training procedure
|
| 30 |
+
|
| 31 |
+
### Training hyperparameters
|
| 32 |
+
|
| 33 |
+
The following hyperparameters were used during training:
|
| 34 |
+
- learning_rate: 2e-05
|
| 35 |
+
- train_batch_size: 1
|
| 36 |
+
- eval_batch_size: 1
|
| 37 |
+
- seed: 42
|
| 38 |
+
- distributed_type: multi-GPU
|
| 39 |
+
- num_devices: 4
|
| 40 |
+
- gradient_accumulation_steps: 4
|
| 41 |
+
- total_train_batch_size: 16
|
| 42 |
+
- total_eval_batch_size: 4
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: cosine
|
| 45 |
+
- num_epochs: 1
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
### Framework versions
|
| 52 |
+
|
| 53 |
+
- Transformers 4.35.0
|
| 54 |
+
- Pytorch 2.1.1
|
| 55 |
+
- Datasets 2.15.0
|
| 56 |
+
- Tokenizers 0.14.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "LeoLM/leo-hessianai-13b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 16,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 64,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj",
|
| 20 |
+
"o_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"v_proj"
|
| 23 |
+
],
|
| 24 |
+
"task_type": "CAUSAL_LM"
|
| 25 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96611475611e845c7f5f00e9274f0c2505e1d5e6b3739ed3f10f4ed0daf6f711
|
| 3 |
+
size 419474032
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.48,
|
| 3 |
+
"train_loss": 1.2715962869858524,
|
| 4 |
+
"train_runtime": 6114.717,
|
| 5 |
+
"train_samples": 18192,
|
| 6 |
+
"train_samples_per_second": 2.975,
|
| 7 |
+
"train_steps_per_second": 0.186
|
| 8 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"bos_token": "<s>",
|
| 29 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 30 |
+
"clean_up_tokenization_spaces": false,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"legacy": false,
|
| 33 |
+
"model_max_length": 2048,
|
| 34 |
+
"pad_token": "</s>",
|
| 35 |
+
"padding_side": "right",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
+
"unk_token": "<unk>",
|
| 39 |
+
"use_default_system_prompt": true
|
| 40 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.48,
|
| 3 |
+
"train_loss": 1.2715962869858524,
|
| 4 |
+
"train_runtime": 6114.717,
|
| 5 |
+
"train_samples": 18192,
|
| 6 |
+
"train_samples_per_second": 2.975,
|
| 7 |
+
"train_steps_per_second": 0.186
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,688 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4793315743183817,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 545,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1.999996182768104e-05,
|
| 14 |
+
"loss": 1.6889,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 1.9999045706597178e-05,
|
| 20 |
+
"loss": 1.5727,
|
| 21 |
+
"step": 5
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 1.999618300852388e-05,
|
| 26 |
+
"loss": 1.5409,
|
| 27 |
+
"step": 10
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 1.999141245215089e-05,
|
| 32 |
+
"loss": 1.4338,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 1.99847349479803e-05,
|
| 38 |
+
"loss": 1.5329,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 1.9976151770471746e-05,
|
| 44 |
+
"loss": 1.4317,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 1.9965664557799164e-05,
|
| 50 |
+
"loss": 1.518,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.9953275311538124e-05,
|
| 56 |
+
"loss": 1.4521,
|
| 57 |
+
"step": 35
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 1.993898639628382e-05,
|
| 62 |
+
"loss": 1.46,
|
| 63 |
+
"step": 40
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.04,
|
| 67 |
+
"learning_rate": 1.992280053919977e-05,
|
| 68 |
+
"loss": 1.3848,
|
| 69 |
+
"step": 45
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.04,
|
| 73 |
+
"learning_rate": 1.99047208294973e-05,
|
| 74 |
+
"loss": 1.3426,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.05,
|
| 79 |
+
"learning_rate": 1.9884750717845945e-05,
|
| 80 |
+
"loss": 1.3429,
|
| 81 |
+
"step": 55
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.05,
|
| 85 |
+
"learning_rate": 1.9862894015714866e-05,
|
| 86 |
+
"loss": 1.3541,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 1.9839154894645393e-05,
|
| 92 |
+
"loss": 1.309,
|
| 93 |
+
"step": 65
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 1.9813537885454854e-05,
|
| 98 |
+
"loss": 1.3096,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"learning_rate": 1.9786047877371823e-05,
|
| 104 |
+
"loss": 1.2657,
|
| 105 |
+
"step": 75
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.07,
|
| 109 |
+
"learning_rate": 1.975669011710297e-05,
|
| 110 |
+
"loss": 1.3209,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.07,
|
| 115 |
+
"learning_rate": 1.972547020783168e-05,
|
| 116 |
+
"loss": 1.2896,
|
| 117 |
+
"step": 85
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.08,
|
| 121 |
+
"learning_rate": 1.969239410814865e-05,
|
| 122 |
+
"loss": 1.2634,
|
| 123 |
+
"step": 90
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.08,
|
| 127 |
+
"learning_rate": 1.9657468130914626e-05,
|
| 128 |
+
"loss": 1.2756,
|
| 129 |
+
"step": 95
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09,
|
| 133 |
+
"learning_rate": 1.962069894205553e-05,
|
| 134 |
+
"loss": 1.2675,
|
| 135 |
+
"step": 100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.09,
|
| 139 |
+
"learning_rate": 1.9582093559290242e-05,
|
| 140 |
+
"loss": 1.2907,
|
| 141 |
+
"step": 105
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1,
|
| 145 |
+
"learning_rate": 1.9541659350791174e-05,
|
| 146 |
+
"loss": 1.2533,
|
| 147 |
+
"step": 110
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1,
|
| 151 |
+
"learning_rate": 1.9499404033778016e-05,
|
| 152 |
+
"loss": 1.2639,
|
| 153 |
+
"step": 115
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.11,
|
| 157 |
+
"learning_rate": 1.9455335673044817e-05,
|
| 158 |
+
"loss": 1.3001,
|
| 159 |
+
"step": 120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.11,
|
| 163 |
+
"learning_rate": 1.9409462679420757e-05,
|
| 164 |
+
"loss": 1.2534,
|
| 165 |
+
"step": 125
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.11,
|
| 169 |
+
"learning_rate": 1.9361793808164878e-05,
|
| 170 |
+
"loss": 1.3083,
|
| 171 |
+
"step": 130
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.12,
|
| 175 |
+
"learning_rate": 1.931233815729505e-05,
|
| 176 |
+
"loss": 1.2891,
|
| 177 |
+
"step": 135
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12,
|
| 181 |
+
"learning_rate": 1.9261105165851546e-05,
|
| 182 |
+
"loss": 1.2565,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.13,
|
| 187 |
+
"learning_rate": 1.920810461209551e-05,
|
| 188 |
+
"loss": 1.265,
|
| 189 |
+
"step": 145
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.13,
|
| 193 |
+
"learning_rate": 1.9153346611642706e-05,
|
| 194 |
+
"loss": 1.253,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.14,
|
| 199 |
+
"learning_rate": 1.909684161553285e-05,
|
| 200 |
+
"loss": 1.299,
|
| 201 |
+
"step": 155
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.14,
|
| 205 |
+
"learning_rate": 1.903860040823494e-05,
|
| 206 |
+
"loss": 1.2302,
|
| 207 |
+
"step": 160
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.15,
|
| 211 |
+
"learning_rate": 1.8978634105588963e-05,
|
| 212 |
+
"loss": 1.2977,
|
| 213 |
+
"step": 165
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.15,
|
| 217 |
+
"learning_rate": 1.8916954152684315e-05,
|
| 218 |
+
"loss": 1.2638,
|
| 219 |
+
"step": 170
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15,
|
| 223 |
+
"learning_rate": 1.8853572321675428e-05,
|
| 224 |
+
"loss": 1.2513,
|
| 225 |
+
"step": 175
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.16,
|
| 229 |
+
"learning_rate": 1.8788500709534934e-05,
|
| 230 |
+
"loss": 1.2284,
|
| 231 |
+
"step": 180
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.16,
|
| 235 |
+
"learning_rate": 1.8721751735744873e-05,
|
| 236 |
+
"loss": 1.234,
|
| 237 |
+
"step": 185
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.17,
|
| 241 |
+
"learning_rate": 1.8653338139926313e-05,
|
| 242 |
+
"loss": 1.2946,
|
| 243 |
+
"step": 190
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.17,
|
| 247 |
+
"learning_rate": 1.8583272979407885e-05,
|
| 248 |
+
"loss": 1.2923,
|
| 249 |
+
"step": 195
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.18,
|
| 253 |
+
"learning_rate": 1.8511569626733673e-05,
|
| 254 |
+
"loss": 1.3634,
|
| 255 |
+
"step": 200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.18,
|
| 259 |
+
"learning_rate": 1.8438241767110972e-05,
|
| 260 |
+
"loss": 1.3127,
|
| 261 |
+
"step": 205
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.18,
|
| 265 |
+
"learning_rate": 1.8363303395798305e-05,
|
| 266 |
+
"loss": 1.2428,
|
| 267 |
+
"step": 210
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.19,
|
| 271 |
+
"learning_rate": 1.828676881543435e-05,
|
| 272 |
+
"loss": 1.2556,
|
| 273 |
+
"step": 215
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.19,
|
| 277 |
+
"learning_rate": 1.8208652633308136e-05,
|
| 278 |
+
"loss": 1.2945,
|
| 279 |
+
"step": 220
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.2,
|
| 283 |
+
"learning_rate": 1.812896975857111e-05,
|
| 284 |
+
"loss": 1.2345,
|
| 285 |
+
"step": 225
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.2,
|
| 289 |
+
"learning_rate": 1.804773539939161e-05,
|
| 290 |
+
"loss": 1.2595,
|
| 291 |
+
"step": 230
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.21,
|
| 295 |
+
"learning_rate": 1.7964965060052243e-05,
|
| 296 |
+
"loss": 1.3029,
|
| 297 |
+
"step": 235
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.21,
|
| 301 |
+
"learning_rate": 1.788067453799077e-05,
|
| 302 |
+
"loss": 1.2565,
|
| 303 |
+
"step": 240
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 1.7794879920785015e-05,
|
| 308 |
+
"loss": 1.2432,
|
| 309 |
+
"step": 245
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.22,
|
| 313 |
+
"learning_rate": 1.770759758308241e-05,
|
| 314 |
+
"loss": 1.2086,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.22,
|
| 319 |
+
"learning_rate": 1.7618844183474775e-05,
|
| 320 |
+
"loss": 1.2351,
|
| 321 |
+
"step": 255
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.23,
|
| 325 |
+
"learning_rate": 1.752863666131885e-05,
|
| 326 |
+
"loss": 1.2635,
|
| 327 |
+
"step": 260
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.23,
|
| 331 |
+
"learning_rate": 1.7436992233503288e-05,
|
| 332 |
+
"loss": 1.1707,
|
| 333 |
+
"step": 265
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.24,
|
| 337 |
+
"learning_rate": 1.7343928391162673e-05,
|
| 338 |
+
"loss": 1.2742,
|
| 339 |
+
"step": 270
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.24,
|
| 343 |
+
"learning_rate": 1.7249462896339153e-05,
|
| 344 |
+
"loss": 1.2808,
|
| 345 |
+
"step": 275
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.25,
|
| 349 |
+
"learning_rate": 1.7153613778592435e-05,
|
| 350 |
+
"loss": 1.2544,
|
| 351 |
+
"step": 280
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.25,
|
| 355 |
+
"learning_rate": 1.705639933155866e-05,
|
| 356 |
+
"loss": 1.2833,
|
| 357 |
+
"step": 285
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.26,
|
| 361 |
+
"learning_rate": 1.695783810945892e-05,
|
| 362 |
+
"loss": 1.2681,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.26,
|
| 367 |
+
"learning_rate": 1.685794892355803e-05,
|
| 368 |
+
"loss": 1.2044,
|
| 369 |
+
"step": 295
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.26,
|
| 373 |
+
"learning_rate": 1.6756750838574197e-05,
|
| 374 |
+
"loss": 1.225,
|
| 375 |
+
"step": 300
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.27,
|
| 379 |
+
"learning_rate": 1.6654263169040413e-05,
|
| 380 |
+
"loss": 1.272,
|
| 381 |
+
"step": 305
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.27,
|
| 385 |
+
"learning_rate": 1.6550505475618054e-05,
|
| 386 |
+
"loss": 1.1861,
|
| 387 |
+
"step": 310
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.28,
|
| 391 |
+
"learning_rate": 1.644549756136358e-05,
|
| 392 |
+
"loss": 1.2229,
|
| 393 |
+
"step": 315
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.28,
|
| 397 |
+
"learning_rate": 1.6339259467948965e-05,
|
| 398 |
+
"loss": 1.2541,
|
| 399 |
+
"step": 320
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.29,
|
| 403 |
+
"learning_rate": 1.6231811471836535e-05,
|
| 404 |
+
"loss": 1.2025,
|
| 405 |
+
"step": 325
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.29,
|
| 409 |
+
"learning_rate": 1.6123174080409055e-05,
|
| 410 |
+
"loss": 1.2166,
|
| 411 |
+
"step": 330
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.29,
|
| 415 |
+
"learning_rate": 1.6013368028055724e-05,
|
| 416 |
+
"loss": 1.249,
|
| 417 |
+
"step": 335
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.3,
|
| 421 |
+
"learning_rate": 1.5902414272214804e-05,
|
| 422 |
+
"loss": 1.2098,
|
| 423 |
+
"step": 340
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.3,
|
| 427 |
+
"learning_rate": 1.5790333989373738e-05,
|
| 428 |
+
"loss": 1.2635,
|
| 429 |
+
"step": 345
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.31,
|
| 433 |
+
"learning_rate": 1.567714857102743e-05,
|
| 434 |
+
"loss": 1.2451,
|
| 435 |
+
"step": 350
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.31,
|
| 439 |
+
"learning_rate": 1.5562879619595486e-05,
|
| 440 |
+
"loss": 1.2561,
|
| 441 |
+
"step": 355
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.32,
|
| 445 |
+
"learning_rate": 1.5447548944299203e-05,
|
| 446 |
+
"loss": 1.2773,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.32,
|
| 451 |
+
"learning_rate": 1.5331178556999094e-05,
|
| 452 |
+
"loss": 1.2215,
|
| 453 |
+
"step": 365
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.33,
|
| 457 |
+
"learning_rate": 1.5213790667993742e-05,
|
| 458 |
+
"loss": 1.1732,
|
| 459 |
+
"step": 370
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.33,
|
| 463 |
+
"learning_rate": 1.5095407681780753e-05,
|
| 464 |
+
"loss": 1.2401,
|
| 465 |
+
"step": 375
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.33,
|
| 469 |
+
"learning_rate": 1.497605219278068e-05,
|
| 470 |
+
"loss": 1.2051,
|
| 471 |
+
"step": 380
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.34,
|
| 475 |
+
"learning_rate": 1.4855746981024667e-05,
|
| 476 |
+
"loss": 1.2675,
|
| 477 |
+
"step": 385
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.34,
|
| 481 |
+
"learning_rate": 1.4734515007806698e-05,
|
| 482 |
+
"loss": 1.2195,
|
| 483 |
+
"step": 390
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.35,
|
| 487 |
+
"learning_rate": 1.4612379411301225e-05,
|
| 488 |
+
"loss": 1.2506,
|
| 489 |
+
"step": 395
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.35,
|
| 493 |
+
"learning_rate": 1.4489363502147045e-05,
|
| 494 |
+
"loss": 1.2441,
|
| 495 |
+
"step": 400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.36,
|
| 499 |
+
"learning_rate": 1.4365490758998268e-05,
|
| 500 |
+
"loss": 1.2906,
|
| 501 |
+
"step": 405
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.36,
|
| 505 |
+
"learning_rate": 1.424078482404321e-05,
|
| 506 |
+
"loss": 1.186,
|
| 507 |
+
"step": 410
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.36,
|
| 511 |
+
"learning_rate": 1.4115269498492075e-05,
|
| 512 |
+
"loss": 1.2911,
|
| 513 |
+
"step": 415
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.37,
|
| 517 |
+
"learning_rate": 1.3988968738034285e-05,
|
| 518 |
+
"loss": 1.2135,
|
| 519 |
+
"step": 420
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.37,
|
| 523 |
+
"learning_rate": 1.3861906648266339e-05,
|
| 524 |
+
"loss": 1.2365,
|
| 525 |
+
"step": 425
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.38,
|
| 529 |
+
"learning_rate": 1.3734107480091041e-05,
|
| 530 |
+
"loss": 1.2167,
|
| 531 |
+
"step": 430
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.38,
|
| 535 |
+
"learning_rate": 1.3605595625089006e-05,
|
| 536 |
+
"loss": 1.228,
|
| 537 |
+
"step": 435
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.39,
|
| 541 |
+
"learning_rate": 1.3476395610863314e-05,
|
| 542 |
+
"loss": 1.2487,
|
| 543 |
+
"step": 440
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.39,
|
| 547 |
+
"learning_rate": 1.3346532096358206e-05,
|
| 548 |
+
"loss": 1.2096,
|
| 549 |
+
"step": 445
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.4,
|
| 553 |
+
"learning_rate": 1.3216029867152724e-05,
|
| 554 |
+
"loss": 1.2412,
|
| 555 |
+
"step": 450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.4,
|
| 559 |
+
"learning_rate": 1.308491383073014e-05,
|
| 560 |
+
"loss": 1.2388,
|
| 561 |
+
"step": 455
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.4,
|
| 565 |
+
"learning_rate": 1.2953209011724159e-05,
|
| 566 |
+
"loss": 1.1793,
|
| 567 |
+
"step": 460
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.41,
|
| 571 |
+
"learning_rate": 1.2820940547142773e-05,
|
| 572 |
+
"loss": 1.241,
|
| 573 |
+
"step": 465
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.41,
|
| 577 |
+
"learning_rate": 1.2688133681570604e-05,
|
| 578 |
+
"loss": 1.1933,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.42,
|
| 583 |
+
"learning_rate": 1.255481376235079e-05,
|
| 584 |
+
"loss": 1.2435,
|
| 585 |
+
"step": 475
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.42,
|
| 589 |
+
"learning_rate": 1.2421006234747202e-05,
|
| 590 |
+
"loss": 1.2284,
|
| 591 |
+
"step": 480
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.43,
|
| 595 |
+
"learning_rate": 1.2286736637088012e-05,
|
| 596 |
+
"loss": 1.2461,
|
| 597 |
+
"step": 485
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.43,
|
| 601 |
+
"learning_rate": 1.2152030595891467e-05,
|
| 602 |
+
"loss": 1.2313,
|
| 603 |
+
"step": 490
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.44,
|
| 607 |
+
"learning_rate": 1.2016913820974855e-05,
|
| 608 |
+
"loss": 1.2388,
|
| 609 |
+
"step": 495
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.44,
|
| 613 |
+
"learning_rate": 1.1881412100547558e-05,
|
| 614 |
+
"loss": 1.2047,
|
| 615 |
+
"step": 500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.44,
|
| 619 |
+
"learning_rate": 1.1745551296289151e-05,
|
| 620 |
+
"loss": 1.2011,
|
| 621 |
+
"step": 505
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.45,
|
| 625 |
+
"learning_rate": 1.1609357338413476e-05,
|
| 626 |
+
"loss": 1.1965,
|
| 627 |
+
"step": 510
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.45,
|
| 631 |
+
"learning_rate": 1.147285622071963e-05,
|
| 632 |
+
"loss": 1.259,
|
| 633 |
+
"step": 515
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.46,
|
| 637 |
+
"learning_rate": 1.133607399563084e-05,
|
| 638 |
+
"loss": 1.2615,
|
| 639 |
+
"step": 520
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.46,
|
| 643 |
+
"learning_rate": 1.1199036769222104e-05,
|
| 644 |
+
"loss": 1.201,
|
| 645 |
+
"step": 525
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.47,
|
| 649 |
+
"learning_rate": 1.1061770696237648e-05,
|
| 650 |
+
"loss": 1.2445,
|
| 651 |
+
"step": 530
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.47,
|
| 655 |
+
"learning_rate": 1.0924301975099043e-05,
|
| 656 |
+
"loss": 1.2002,
|
| 657 |
+
"step": 535
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.47,
|
| 661 |
+
"learning_rate": 1.0786656842905028e-05,
|
| 662 |
+
"loss": 1.2267,
|
| 663 |
+
"step": 540
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.48,
|
| 667 |
+
"learning_rate": 1.0648861570423919e-05,
|
| 668 |
+
"loss": 1.2257,
|
| 669 |
+
"step": 545
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.48,
|
| 673 |
+
"step": 545,
|
| 674 |
+
"total_flos": 6.944922061693256e+17,
|
| 675 |
+
"train_loss": 1.2715962869858524,
|
| 676 |
+
"train_runtime": 6114.717,
|
| 677 |
+
"train_samples_per_second": 2.975,
|
| 678 |
+
"train_steps_per_second": 0.186
|
| 679 |
+
}
|
| 680 |
+
],
|
| 681 |
+
"logging_steps": 5,
|
| 682 |
+
"max_steps": 1137,
|
| 683 |
+
"num_train_epochs": 1,
|
| 684 |
+
"save_steps": 200,
|
| 685 |
+
"total_flos": 6.944922061693256e+17,
|
| 686 |
+
"trial_name": null,
|
| 687 |
+
"trial_params": null
|
| 688 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5692df0547e891ed4dc8d71a47864c18f5fc7b1b044bdd100370f96c0272c3f4
|
| 3 |
+
size 4664
|