Model save
Browse files- README.md +66 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +48 -0
- train_results.json +8 -0
- trainer_state.json +1116 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- generator
|
| 10 |
+
base_model: jan-hq/stealth-v1.3
|
| 11 |
+
model-index:
|
| 12 |
+
- name: stealth-rag-v1
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# stealth-rag-v1
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [jan-hq/stealth-v1.3](https://huggingface.co/jan-hq/stealth-v1.3) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.3883
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 2
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 2
|
| 48 |
+
- gradient_accumulation_steps: 16
|
| 49 |
+
- total_train_batch_size: 64
|
| 50 |
+
- total_eval_batch_size: 8
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 3
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
### Framework versions
|
| 61 |
+
|
| 62 |
+
- PEFT 0.7.1
|
| 63 |
+
- Transformers 4.36.2
|
| 64 |
+
- Pytorch 2.1.2+cu121
|
| 65 |
+
- Datasets 2.14.6
|
| 66 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "jan-hq/stealth-v1.3",
|
| 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 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"up_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"v_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM"
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94aeffd895bb8f6b1f6632825a7485a3ff8e15dc58cac1c24728d6646cb924a5
|
| 3 |
+
size 83946192
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.91,
|
| 3 |
+
"eval_loss": 1.3883140087127686,
|
| 4 |
+
"eval_runtime": 2265.7081,
|
| 5 |
+
"eval_samples": 44563,
|
| 6 |
+
"eval_samples_per_second": 5.137,
|
| 7 |
+
"eval_steps_per_second": 0.642,
|
| 8 |
+
"train_loss": 0.0,
|
| 9 |
+
"train_runtime": 3.9268,
|
| 10 |
+
"train_samples": 44833,
|
| 11 |
+
"train_samples_per_second": 12034.857,
|
| 12 |
+
"train_steps_per_second": 187.937
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.91,
|
| 3 |
+
"eval_loss": 1.3883140087127686,
|
| 4 |
+
"eval_runtime": 2265.7081,
|
| 5 |
+
"eval_samples": 44563,
|
| 6 |
+
"eval_samples_per_second": 5.137,
|
| 7 |
+
"eval_steps_per_second": 0.642
|
| 8 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": true,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": true,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": true,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": true,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": {
|
| 22 |
+
"content": "<s>",
|
| 23 |
+
"lstrip": true,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": true,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": true,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": true,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": true,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": true,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": true,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": true,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": true,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
+
"bos_token": "<s>",
|
| 36 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 37 |
+
"clean_up_tokenization_spaces": false,
|
| 38 |
+
"eos_token": "</s>",
|
| 39 |
+
"legacy": true,
|
| 40 |
+
"model_max_length": 2020,
|
| 41 |
+
"pad_token": "<s>",
|
| 42 |
+
"padding_side": "right",
|
| 43 |
+
"sp_model_kwargs": {},
|
| 44 |
+
"spaces_between_special_tokens": false,
|
| 45 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 46 |
+
"unk_token": "<unk>",
|
| 47 |
+
"use_default_system_prompt": true
|
| 48 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.91,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 3.9268,
|
| 5 |
+
"train_samples": 44833,
|
| 6 |
+
"train_samples_per_second": 12034.857,
|
| 7 |
+
"train_steps_per_second": 187.937
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.913937547600914,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 900,
|
| 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": 6.756756756756757e-08,
|
| 14 |
+
"loss": 2.0057,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 3.378378378378379e-07,
|
| 20 |
+
"loss": 2.0564,
|
| 21 |
+
"step": 5
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 6.756756756756758e-07,
|
| 26 |
+
"loss": 2.0403,
|
| 27 |
+
"step": 10
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 1.0135135135135136e-06,
|
| 32 |
+
"loss": 2.0396,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 1.3513513513513515e-06,
|
| 38 |
+
"loss": 1.9947,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 1.6891891891891894e-06,
|
| 44 |
+
"loss": 2.0448,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 2.0270270270270273e-06,
|
| 50 |
+
"loss": 2.0019,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 2.364864864864865e-06,
|
| 56 |
+
"loss": 1.9959,
|
| 57 |
+
"step": 35
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 2.702702702702703e-06,
|
| 62 |
+
"loss": 2.0093,
|
| 63 |
+
"step": 40
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 3.040540540540541e-06,
|
| 68 |
+
"loss": 2.0242,
|
| 69 |
+
"step": 45
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 3.3783783783783788e-06,
|
| 74 |
+
"loss": 1.9715,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 3.7162162162162162e-06,
|
| 80 |
+
"loss": 1.9773,
|
| 81 |
+
"step": 55
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 4.0540540540540545e-06,
|
| 86 |
+
"loss": 1.9811,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07,
|
| 91 |
+
"learning_rate": 4.391891891891892e-06,
|
| 92 |
+
"loss": 1.9947,
|
| 93 |
+
"step": 65
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 4.72972972972973e-06,
|
| 98 |
+
"loss": 1.988,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 5.067567567567568e-06,
|
| 104 |
+
"loss": 1.9718,
|
| 105 |
+
"step": 75
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 5.405405405405406e-06,
|
| 110 |
+
"loss": 1.9505,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.09,
|
| 115 |
+
"learning_rate": 5.743243243243244e-06,
|
| 116 |
+
"loss": 1.9706,
|
| 117 |
+
"step": 85
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 6.081081081081082e-06,
|
| 122 |
+
"loss": 1.9506,
|
| 123 |
+
"step": 90
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.1,
|
| 127 |
+
"learning_rate": 6.41891891891892e-06,
|
| 128 |
+
"loss": 1.9243,
|
| 129 |
+
"step": 95
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 6.7567567567567575e-06,
|
| 134 |
+
"loss": 1.9785,
|
| 135 |
+
"step": 100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11,
|
| 139 |
+
"learning_rate": 7.0945945945945946e-06,
|
| 140 |
+
"loss": 1.8531,
|
| 141 |
+
"step": 105
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 7.4324324324324324e-06,
|
| 146 |
+
"loss": 1.9446,
|
| 147 |
+
"step": 110
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.12,
|
| 151 |
+
"learning_rate": 7.77027027027027e-06,
|
| 152 |
+
"loss": 1.9,
|
| 153 |
+
"step": 115
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12,
|
| 157 |
+
"learning_rate": 8.108108108108109e-06,
|
| 158 |
+
"loss": 1.8533,
|
| 159 |
+
"step": 120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.13,
|
| 163 |
+
"learning_rate": 8.445945945945948e-06,
|
| 164 |
+
"loss": 1.92,
|
| 165 |
+
"step": 125
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.13,
|
| 169 |
+
"learning_rate": 8.783783783783785e-06,
|
| 170 |
+
"loss": 1.8792,
|
| 171 |
+
"step": 130
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.14,
|
| 175 |
+
"learning_rate": 9.121621621621622e-06,
|
| 176 |
+
"loss": 1.9132,
|
| 177 |
+
"step": 135
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.14,
|
| 181 |
+
"learning_rate": 9.45945945945946e-06,
|
| 182 |
+
"loss": 1.8309,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.15,
|
| 187 |
+
"learning_rate": 9.797297297297298e-06,
|
| 188 |
+
"loss": 1.8194,
|
| 189 |
+
"step": 145
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.15,
|
| 193 |
+
"learning_rate": 1.0135135135135136e-05,
|
| 194 |
+
"loss": 1.7605,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.16,
|
| 199 |
+
"learning_rate": 1.0472972972972975e-05,
|
| 200 |
+
"loss": 1.806,
|
| 201 |
+
"step": 155
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.16,
|
| 205 |
+
"learning_rate": 1.0810810810810812e-05,
|
| 206 |
+
"loss": 1.879,
|
| 207 |
+
"step": 160
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.17,
|
| 211 |
+
"learning_rate": 1.114864864864865e-05,
|
| 212 |
+
"loss": 1.7906,
|
| 213 |
+
"step": 165
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.17,
|
| 217 |
+
"learning_rate": 1.1486486486486488e-05,
|
| 218 |
+
"loss": 1.7865,
|
| 219 |
+
"step": 170
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.18,
|
| 223 |
+
"learning_rate": 1.1824324324324325e-05,
|
| 224 |
+
"loss": 1.855,
|
| 225 |
+
"step": 175
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.18,
|
| 229 |
+
"learning_rate": 1.2162162162162164e-05,
|
| 230 |
+
"loss": 1.7428,
|
| 231 |
+
"step": 180
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.19,
|
| 235 |
+
"learning_rate": 1.25e-05,
|
| 236 |
+
"loss": 1.8219,
|
| 237 |
+
"step": 185
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.19,
|
| 241 |
+
"learning_rate": 1.283783783783784e-05,
|
| 242 |
+
"loss": 1.7607,
|
| 243 |
+
"step": 190
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.2,
|
| 247 |
+
"learning_rate": 1.3175675675675676e-05,
|
| 248 |
+
"loss": 1.8289,
|
| 249 |
+
"step": 195
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.2,
|
| 253 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 254 |
+
"loss": 1.8311,
|
| 255 |
+
"step": 200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.21,
|
| 259 |
+
"learning_rate": 1.3851351351351352e-05,
|
| 260 |
+
"loss": 1.7481,
|
| 261 |
+
"step": 205
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.21,
|
| 265 |
+
"learning_rate": 1.4189189189189189e-05,
|
| 266 |
+
"loss": 1.795,
|
| 267 |
+
"step": 210
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.22,
|
| 271 |
+
"learning_rate": 1.4527027027027028e-05,
|
| 272 |
+
"loss": 1.7709,
|
| 273 |
+
"step": 215
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.22,
|
| 277 |
+
"learning_rate": 1.4864864864864865e-05,
|
| 278 |
+
"loss": 1.7569,
|
| 279 |
+
"step": 220
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.23,
|
| 283 |
+
"learning_rate": 1.5202702702702704e-05,
|
| 284 |
+
"loss": 1.7625,
|
| 285 |
+
"step": 225
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.23,
|
| 289 |
+
"learning_rate": 1.554054054054054e-05,
|
| 290 |
+
"loss": 1.7773,
|
| 291 |
+
"step": 230
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.24,
|
| 295 |
+
"learning_rate": 1.587837837837838e-05,
|
| 296 |
+
"loss": 1.7449,
|
| 297 |
+
"step": 235
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.24,
|
| 301 |
+
"learning_rate": 1.6216216216216218e-05,
|
| 302 |
+
"loss": 1.7536,
|
| 303 |
+
"step": 240
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.25,
|
| 307 |
+
"learning_rate": 1.6554054054054057e-05,
|
| 308 |
+
"loss": 1.7815,
|
| 309 |
+
"step": 245
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.25,
|
| 313 |
+
"learning_rate": 1.6891891891891896e-05,
|
| 314 |
+
"loss": 1.81,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.26,
|
| 319 |
+
"learning_rate": 1.722972972972973e-05,
|
| 320 |
+
"loss": 1.7928,
|
| 321 |
+
"step": 255
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.26,
|
| 325 |
+
"learning_rate": 1.756756756756757e-05,
|
| 326 |
+
"loss": 1.7427,
|
| 327 |
+
"step": 260
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.27,
|
| 331 |
+
"learning_rate": 1.790540540540541e-05,
|
| 332 |
+
"loss": 1.6618,
|
| 333 |
+
"step": 265
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.27,
|
| 337 |
+
"learning_rate": 1.8243243243243244e-05,
|
| 338 |
+
"loss": 1.7179,
|
| 339 |
+
"step": 270
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.28,
|
| 343 |
+
"learning_rate": 1.8581081081081082e-05,
|
| 344 |
+
"loss": 1.7514,
|
| 345 |
+
"step": 275
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.28,
|
| 349 |
+
"learning_rate": 1.891891891891892e-05,
|
| 350 |
+
"loss": 1.7457,
|
| 351 |
+
"step": 280
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.29,
|
| 355 |
+
"learning_rate": 1.925675675675676e-05,
|
| 356 |
+
"loss": 1.8168,
|
| 357 |
+
"step": 285
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.29,
|
| 361 |
+
"learning_rate": 1.9594594594594595e-05,
|
| 362 |
+
"loss": 1.7466,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.3,
|
| 367 |
+
"learning_rate": 1.9932432432432434e-05,
|
| 368 |
+
"loss": 1.7226,
|
| 369 |
+
"step": 295
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.3,
|
| 373 |
+
"learning_rate": 1.9999888073536733e-05,
|
| 374 |
+
"loss": 1.7554,
|
| 375 |
+
"step": 300
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.31,
|
| 379 |
+
"learning_rate": 1.9999433376573803e-05,
|
| 380 |
+
"loss": 1.8218,
|
| 381 |
+
"step": 305
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.31,
|
| 385 |
+
"learning_rate": 1.9998628929598956e-05,
|
| 386 |
+
"loss": 1.7816,
|
| 387 |
+
"step": 310
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.32,
|
| 391 |
+
"learning_rate": 1.9997474760749314e-05,
|
| 392 |
+
"loss": 1.7414,
|
| 393 |
+
"step": 315
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.32,
|
| 397 |
+
"learning_rate": 1.9995970910394228e-05,
|
| 398 |
+
"loss": 1.778,
|
| 399 |
+
"step": 320
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.33,
|
| 403 |
+
"learning_rate": 1.9994117431133843e-05,
|
| 404 |
+
"loss": 1.7267,
|
| 405 |
+
"step": 325
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.34,
|
| 409 |
+
"learning_rate": 1.9991914387797266e-05,
|
| 410 |
+
"loss": 1.6588,
|
| 411 |
+
"step": 330
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.34,
|
| 415 |
+
"learning_rate": 1.9989361857440318e-05,
|
| 416 |
+
"loss": 1.7615,
|
| 417 |
+
"step": 335
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.35,
|
| 421 |
+
"learning_rate": 1.99864599293428e-05,
|
| 422 |
+
"loss": 1.7038,
|
| 423 |
+
"step": 340
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.35,
|
| 427 |
+
"learning_rate": 1.998320870500541e-05,
|
| 428 |
+
"loss": 1.751,
|
| 429 |
+
"step": 345
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.36,
|
| 433 |
+
"learning_rate": 1.997960829814616e-05,
|
| 434 |
+
"loss": 1.695,
|
| 435 |
+
"step": 350
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.36,
|
| 439 |
+
"learning_rate": 1.997565883469643e-05,
|
| 440 |
+
"loss": 1.6773,
|
| 441 |
+
"step": 355
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.37,
|
| 445 |
+
"learning_rate": 1.9971360452796523e-05,
|
| 446 |
+
"loss": 1.7159,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.37,
|
| 451 |
+
"learning_rate": 1.9966713302790875e-05,
|
| 452 |
+
"loss": 1.7268,
|
| 453 |
+
"step": 365
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.38,
|
| 457 |
+
"learning_rate": 1.9961717547222775e-05,
|
| 458 |
+
"loss": 1.7641,
|
| 459 |
+
"step": 370
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.38,
|
| 463 |
+
"learning_rate": 1.995637336082868e-05,
|
| 464 |
+
"loss": 1.7376,
|
| 465 |
+
"step": 375
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.39,
|
| 469 |
+
"learning_rate": 1.9950680930532107e-05,
|
| 470 |
+
"loss": 1.7687,
|
| 471 |
+
"step": 380
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.39,
|
| 475 |
+
"learning_rate": 1.994464045543709e-05,
|
| 476 |
+
"loss": 1.7248,
|
| 477 |
+
"step": 385
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.4,
|
| 481 |
+
"learning_rate": 1.9938252146821236e-05,
|
| 482 |
+
"loss": 1.7281,
|
| 483 |
+
"step": 390
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.4,
|
| 487 |
+
"learning_rate": 1.9931516228128295e-05,
|
| 488 |
+
"loss": 1.7265,
|
| 489 |
+
"step": 395
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.41,
|
| 493 |
+
"learning_rate": 1.9924432934960384e-05,
|
| 494 |
+
"loss": 1.7459,
|
| 495 |
+
"step": 400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.41,
|
| 499 |
+
"learning_rate": 1.9917002515069732e-05,
|
| 500 |
+
"loss": 1.719,
|
| 501 |
+
"step": 405
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.42,
|
| 505 |
+
"learning_rate": 1.9909225228350007e-05,
|
| 506 |
+
"loss": 1.6819,
|
| 507 |
+
"step": 410
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.42,
|
| 511 |
+
"learning_rate": 1.9901101346827233e-05,
|
| 512 |
+
"loss": 1.6849,
|
| 513 |
+
"step": 415
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.43,
|
| 517 |
+
"learning_rate": 1.989263115465028e-05,
|
| 518 |
+
"loss": 1.7905,
|
| 519 |
+
"step": 420
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.43,
|
| 523 |
+
"learning_rate": 1.9883814948080918e-05,
|
| 524 |
+
"loss": 1.7414,
|
| 525 |
+
"step": 425
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.44,
|
| 529 |
+
"learning_rate": 1.987465303548345e-05,
|
| 530 |
+
"loss": 1.7082,
|
| 531 |
+
"step": 430
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.44,
|
| 535 |
+
"learning_rate": 1.9865145737313937e-05,
|
| 536 |
+
"loss": 1.743,
|
| 537 |
+
"step": 435
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.45,
|
| 541 |
+
"learning_rate": 1.9855293386108995e-05,
|
| 542 |
+
"loss": 1.7089,
|
| 543 |
+
"step": 440
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.45,
|
| 547 |
+
"learning_rate": 1.9845096326474135e-05,
|
| 548 |
+
"loss": 1.7491,
|
| 549 |
+
"step": 445
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.46,
|
| 553 |
+
"learning_rate": 1.9834554915071745e-05,
|
| 554 |
+
"loss": 1.6897,
|
| 555 |
+
"step": 450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.46,
|
| 559 |
+
"learning_rate": 1.982366952060859e-05,
|
| 560 |
+
"loss": 1.7759,
|
| 561 |
+
"step": 455
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.47,
|
| 565 |
+
"learning_rate": 1.981244052382293e-05,
|
| 566 |
+
"loss": 1.7774,
|
| 567 |
+
"step": 460
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.47,
|
| 571 |
+
"learning_rate": 1.9800868317471196e-05,
|
| 572 |
+
"loss": 1.6844,
|
| 573 |
+
"step": 465
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.48,
|
| 577 |
+
"learning_rate": 1.978895330631425e-05,
|
| 578 |
+
"loss": 1.7419,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.48,
|
| 583 |
+
"learning_rate": 1.977669590710324e-05,
|
| 584 |
+
"loss": 1.7966,
|
| 585 |
+
"step": 475
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.49,
|
| 589 |
+
"learning_rate": 1.976409654856501e-05,
|
| 590 |
+
"loss": 1.6607,
|
| 591 |
+
"step": 480
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.49,
|
| 595 |
+
"learning_rate": 1.975115567138711e-05,
|
| 596 |
+
"loss": 1.8121,
|
| 597 |
+
"step": 485
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5,
|
| 601 |
+
"learning_rate": 1.9737873728202376e-05,
|
| 602 |
+
"loss": 1.7282,
|
| 603 |
+
"step": 490
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.5,
|
| 607 |
+
"learning_rate": 1.972425118357312e-05,
|
| 608 |
+
"loss": 1.6864,
|
| 609 |
+
"step": 495
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.51,
|
| 613 |
+
"learning_rate": 1.9710288513974846e-05,
|
| 614 |
+
"loss": 1.7665,
|
| 615 |
+
"step": 500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.51,
|
| 619 |
+
"learning_rate": 1.969598620777962e-05,
|
| 620 |
+
"loss": 1.6843,
|
| 621 |
+
"step": 505
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.52,
|
| 625 |
+
"learning_rate": 1.9681344765238958e-05,
|
| 626 |
+
"loss": 1.6675,
|
| 627 |
+
"step": 510
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.52,
|
| 631 |
+
"learning_rate": 1.966636469846635e-05,
|
| 632 |
+
"loss": 1.7891,
|
| 633 |
+
"step": 515
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.53,
|
| 637 |
+
"learning_rate": 1.9651046531419335e-05,
|
| 638 |
+
"loss": 1.6728,
|
| 639 |
+
"step": 520
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.53,
|
| 643 |
+
"learning_rate": 1.9635390799881186e-05,
|
| 644 |
+
"loss": 1.7289,
|
| 645 |
+
"step": 525
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.54,
|
| 649 |
+
"learning_rate": 1.961939805144216e-05,
|
| 650 |
+
"loss": 1.7241,
|
| 651 |
+
"step": 530
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.54,
|
| 655 |
+
"learning_rate": 1.9603068845480347e-05,
|
| 656 |
+
"loss": 1.7378,
|
| 657 |
+
"step": 535
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.55,
|
| 661 |
+
"learning_rate": 1.9586403753142104e-05,
|
| 662 |
+
"loss": 1.7717,
|
| 663 |
+
"step": 540
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.55,
|
| 667 |
+
"learning_rate": 1.956940335732209e-05,
|
| 668 |
+
"loss": 1.7401,
|
| 669 |
+
"step": 545
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.56,
|
| 673 |
+
"learning_rate": 1.9552068252642858e-05,
|
| 674 |
+
"loss": 1.6758,
|
| 675 |
+
"step": 550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.56,
|
| 679 |
+
"learning_rate": 1.9534399045434073e-05,
|
| 680 |
+
"loss": 1.7241,
|
| 681 |
+
"step": 555
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.57,
|
| 685 |
+
"learning_rate": 1.9516396353711297e-05,
|
| 686 |
+
"loss": 1.7026,
|
| 687 |
+
"step": 560
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.57,
|
| 691 |
+
"learning_rate": 1.9498060807154368e-05,
|
| 692 |
+
"loss": 1.7662,
|
| 693 |
+
"step": 565
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.58,
|
| 697 |
+
"learning_rate": 1.9479393047085392e-05,
|
| 698 |
+
"loss": 1.6935,
|
| 699 |
+
"step": 570
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.58,
|
| 703 |
+
"learning_rate": 1.94603937264463e-05,
|
| 704 |
+
"loss": 1.7303,
|
| 705 |
+
"step": 575
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.59,
|
| 709 |
+
"learning_rate": 1.9441063509776003e-05,
|
| 710 |
+
"loss": 1.7758,
|
| 711 |
+
"step": 580
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.59,
|
| 715 |
+
"learning_rate": 1.9421403073187162e-05,
|
| 716 |
+
"loss": 1.7017,
|
| 717 |
+
"step": 585
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.6,
|
| 721 |
+
"learning_rate": 1.9401413104342535e-05,
|
| 722 |
+
"loss": 1.7726,
|
| 723 |
+
"step": 590
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6,
|
| 727 |
+
"learning_rate": 1.938109430243093e-05,
|
| 728 |
+
"loss": 1.6689,
|
| 729 |
+
"step": 595
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.61,
|
| 733 |
+
"learning_rate": 1.936044737814273e-05,
|
| 734 |
+
"loss": 1.6734,
|
| 735 |
+
"step": 600
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.61,
|
| 739 |
+
"learning_rate": 1.9339473053645056e-05,
|
| 740 |
+
"loss": 1.656,
|
| 741 |
+
"step": 605
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.62,
|
| 745 |
+
"learning_rate": 1.931817206255651e-05,
|
| 746 |
+
"loss": 1.7196,
|
| 747 |
+
"step": 610
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.62,
|
| 751 |
+
"learning_rate": 1.9296545149921488e-05,
|
| 752 |
+
"loss": 1.686,
|
| 753 |
+
"step": 615
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.63,
|
| 757 |
+
"learning_rate": 1.9274593072184152e-05,
|
| 758 |
+
"loss": 1.7709,
|
| 759 |
+
"step": 620
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.63,
|
| 763 |
+
"learning_rate": 1.9252316597161947e-05,
|
| 764 |
+
"loss": 1.6834,
|
| 765 |
+
"step": 625
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.64,
|
| 769 |
+
"learning_rate": 1.922971650401877e-05,
|
| 770 |
+
"loss": 1.6787,
|
| 771 |
+
"step": 630
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.64,
|
| 775 |
+
"learning_rate": 1.920679358323769e-05,
|
| 776 |
+
"loss": 1.6922,
|
| 777 |
+
"step": 635
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.65,
|
| 781 |
+
"learning_rate": 1.9183548636593322e-05,
|
| 782 |
+
"loss": 1.7244,
|
| 783 |
+
"step": 640
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.65,
|
| 787 |
+
"learning_rate": 1.9159982477123776e-05,
|
| 788 |
+
"loss": 1.7187,
|
| 789 |
+
"step": 645
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.66,
|
| 793 |
+
"learning_rate": 1.9136095929102204e-05,
|
| 794 |
+
"loss": 1.6827,
|
| 795 |
+
"step": 650
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.67,
|
| 799 |
+
"learning_rate": 1.9111889828007997e-05,
|
| 800 |
+
"loss": 1.7466,
|
| 801 |
+
"step": 655
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.67,
|
| 805 |
+
"learning_rate": 1.908736502049754e-05,
|
| 806 |
+
"loss": 1.7892,
|
| 807 |
+
"step": 660
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.68,
|
| 811 |
+
"learning_rate": 1.9062522364374617e-05,
|
| 812 |
+
"loss": 1.744,
|
| 813 |
+
"step": 665
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.68,
|
| 817 |
+
"learning_rate": 1.903736272856038e-05,
|
| 818 |
+
"loss": 1.6438,
|
| 819 |
+
"step": 670
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.69,
|
| 823 |
+
"learning_rate": 1.9011886993062994e-05,
|
| 824 |
+
"loss": 1.7538,
|
| 825 |
+
"step": 675
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.69,
|
| 829 |
+
"learning_rate": 1.8986096048946826e-05,
|
| 830 |
+
"loss": 1.6889,
|
| 831 |
+
"step": 680
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.7,
|
| 835 |
+
"learning_rate": 1.8959990798301286e-05,
|
| 836 |
+
"loss": 1.7199,
|
| 837 |
+
"step": 685
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.7,
|
| 841 |
+
"learning_rate": 1.893357215420929e-05,
|
| 842 |
+
"loss": 1.7801,
|
| 843 |
+
"step": 690
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.71,
|
| 847 |
+
"learning_rate": 1.8906841040715304e-05,
|
| 848 |
+
"loss": 1.7559,
|
| 849 |
+
"step": 695
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.71,
|
| 853 |
+
"learning_rate": 1.8879798392793033e-05,
|
| 854 |
+
"loss": 1.6639,
|
| 855 |
+
"step": 700
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.72,
|
| 859 |
+
"learning_rate": 1.8852445156312713e-05,
|
| 860 |
+
"loss": 1.687,
|
| 861 |
+
"step": 705
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.72,
|
| 865 |
+
"learning_rate": 1.8824782288008038e-05,
|
| 866 |
+
"loss": 1.7619,
|
| 867 |
+
"step": 710
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.73,
|
| 871 |
+
"learning_rate": 1.8796810755442675e-05,
|
| 872 |
+
"loss": 1.7529,
|
| 873 |
+
"step": 715
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.73,
|
| 877 |
+
"learning_rate": 1.8768531536976452e-05,
|
| 878 |
+
"loss": 1.7513,
|
| 879 |
+
"step": 720
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.74,
|
| 883 |
+
"learning_rate": 1.8739945621731114e-05,
|
| 884 |
+
"loss": 1.7322,
|
| 885 |
+
"step": 725
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.74,
|
| 889 |
+
"learning_rate": 1.8711054009555736e-05,
|
| 890 |
+
"loss": 1.7762,
|
| 891 |
+
"step": 730
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.75,
|
| 895 |
+
"learning_rate": 1.8681857710991745e-05,
|
| 896 |
+
"loss": 1.6949,
|
| 897 |
+
"step": 735
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.75,
|
| 901 |
+
"learning_rate": 1.865235774723758e-05,
|
| 902 |
+
"loss": 1.6526,
|
| 903 |
+
"step": 740
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.76,
|
| 907 |
+
"learning_rate": 1.862255515011298e-05,
|
| 908 |
+
"loss": 1.7155,
|
| 909 |
+
"step": 745
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.76,
|
| 913 |
+
"learning_rate": 1.8592450962022872e-05,
|
| 914 |
+
"loss": 1.8251,
|
| 915 |
+
"step": 750
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.77,
|
| 919 |
+
"learning_rate": 1.8562046235920938e-05,
|
| 920 |
+
"loss": 1.7077,
|
| 921 |
+
"step": 755
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.77,
|
| 925 |
+
"learning_rate": 1.8531342035272768e-05,
|
| 926 |
+
"loss": 1.6627,
|
| 927 |
+
"step": 760
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.78,
|
| 931 |
+
"learning_rate": 1.850033943401867e-05,
|
| 932 |
+
"loss": 1.7163,
|
| 933 |
+
"step": 765
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.78,
|
| 937 |
+
"learning_rate": 1.84690395165361e-05,
|
| 938 |
+
"loss": 1.713,
|
| 939 |
+
"step": 770
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.79,
|
| 943 |
+
"learning_rate": 1.8437443377601736e-05,
|
| 944 |
+
"loss": 1.7024,
|
| 945 |
+
"step": 775
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.79,
|
| 949 |
+
"learning_rate": 1.8405552122353212e-05,
|
| 950 |
+
"loss": 1.7253,
|
| 951 |
+
"step": 780
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.8,
|
| 955 |
+
"learning_rate": 1.8373366866250407e-05,
|
| 956 |
+
"loss": 1.7109,
|
| 957 |
+
"step": 785
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.8,
|
| 961 |
+
"learning_rate": 1.8340888735036485e-05,
|
| 962 |
+
"loss": 1.7563,
|
| 963 |
+
"step": 790
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.81,
|
| 967 |
+
"learning_rate": 1.830811886469849e-05,
|
| 968 |
+
"loss": 1.7479,
|
| 969 |
+
"step": 795
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.81,
|
| 973 |
+
"learning_rate": 1.8275058401427622e-05,
|
| 974 |
+
"loss": 1.7315,
|
| 975 |
+
"step": 800
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.82,
|
| 979 |
+
"learning_rate": 1.8241708501579146e-05,
|
| 980 |
+
"loss": 1.7126,
|
| 981 |
+
"step": 805
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.82,
|
| 985 |
+
"learning_rate": 1.8208070331631943e-05,
|
| 986 |
+
"loss": 1.6866,
|
| 987 |
+
"step": 810
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.83,
|
| 991 |
+
"learning_rate": 1.817414506814772e-05,
|
| 992 |
+
"loss": 1.6708,
|
| 993 |
+
"step": 815
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.83,
|
| 997 |
+
"learning_rate": 1.8139933897729833e-05,
|
| 998 |
+
"loss": 1.6868,
|
| 999 |
+
"step": 820
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.84,
|
| 1003 |
+
"learning_rate": 1.8105438016981816e-05,
|
| 1004 |
+
"loss": 1.7493,
|
| 1005 |
+
"step": 825
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.84,
|
| 1009 |
+
"learning_rate": 1.807065863246551e-05,
|
| 1010 |
+
"loss": 1.7707,
|
| 1011 |
+
"step": 830
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.85,
|
| 1015 |
+
"learning_rate": 1.8035596960658856e-05,
|
| 1016 |
+
"loss": 1.7692,
|
| 1017 |
+
"step": 835
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.85,
|
| 1021 |
+
"learning_rate": 1.8000254227913346e-05,
|
| 1022 |
+
"loss": 1.7761,
|
| 1023 |
+
"step": 840
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.86,
|
| 1027 |
+
"learning_rate": 1.7964631670411154e-05,
|
| 1028 |
+
"loss": 1.6765,
|
| 1029 |
+
"step": 845
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.86,
|
| 1033 |
+
"learning_rate": 1.7928730534121872e-05,
|
| 1034 |
+
"loss": 1.6437,
|
| 1035 |
+
"step": 850
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.87,
|
| 1039 |
+
"learning_rate": 1.7892552074758932e-05,
|
| 1040 |
+
"loss": 1.6804,
|
| 1041 |
+
"step": 855
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.87,
|
| 1045 |
+
"learning_rate": 1.7856097557735697e-05,
|
| 1046 |
+
"loss": 1.7373,
|
| 1047 |
+
"step": 860
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.88,
|
| 1051 |
+
"learning_rate": 1.7819368258121188e-05,
|
| 1052 |
+
"loss": 1.7316,
|
| 1053 |
+
"step": 865
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.88,
|
| 1057 |
+
"learning_rate": 1.77823654605955e-05,
|
| 1058 |
+
"loss": 1.6764,
|
| 1059 |
+
"step": 870
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.89,
|
| 1063 |
+
"learning_rate": 1.7745090459404853e-05,
|
| 1064 |
+
"loss": 1.7456,
|
| 1065 |
+
"step": 875
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.89,
|
| 1069 |
+
"learning_rate": 1.7707544558316332e-05,
|
| 1070 |
+
"loss": 1.6518,
|
| 1071 |
+
"step": 880
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.9,
|
| 1075 |
+
"learning_rate": 1.766972907057229e-05,
|
| 1076 |
+
"loss": 1.7705,
|
| 1077 |
+
"step": 885
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.9,
|
| 1081 |
+
"learning_rate": 1.763164531884439e-05,
|
| 1082 |
+
"loss": 1.7431,
|
| 1083 |
+
"step": 890
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.91,
|
| 1087 |
+
"learning_rate": 1.7593294635187385e-05,
|
| 1088 |
+
"loss": 1.6928,
|
| 1089 |
+
"step": 895
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.91,
|
| 1093 |
+
"learning_rate": 1.7554678360992475e-05,
|
| 1094 |
+
"loss": 1.7483,
|
| 1095 |
+
"step": 900
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.91,
|
| 1099 |
+
"step": 900,
|
| 1100 |
+
"total_flos": 1.2656331456763658e+18,
|
| 1101 |
+
"train_loss": 0.0,
|
| 1102 |
+
"train_runtime": 3.9268,
|
| 1103 |
+
"train_samples_per_second": 12034.857,
|
| 1104 |
+
"train_steps_per_second": 187.937
|
| 1105 |
+
}
|
| 1106 |
+
],
|
| 1107 |
+
"logging_steps": 5,
|
| 1108 |
+
"max_steps": 738,
|
| 1109 |
+
"num_input_tokens_seen": 0,
|
| 1110 |
+
"num_train_epochs": 3,
|
| 1111 |
+
"save_steps": 100,
|
| 1112 |
+
"total_flos": 1.2656331456763658e+18,
|
| 1113 |
+
"train_batch_size": 2,
|
| 1114 |
+
"trial_name": null,
|
| 1115 |
+
"trial_params": null
|
| 1116 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de42bec59d8821be3016ce60b224b318da5a4c2cb66ba4f78d52bd199b9d223a
|
| 3 |
+
size 4728
|