feat: fine-tuning japanese-mistral-300M-base with databricks-dolly-15k-ja
Browse files- README.md +201 -0
- all_results.json +14 -0
- config.json +25 -0
- eval_results.json +9 -0
- generation_config.json +6 -0
- logs/events.out.tfevents.1702213518.90c313ded1af.749823.0 +3 -0
- logs/events.out.tfevents.1702233619.90c313ded1af.749823.1 +3 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +47 -0
- train_results.json +8 -0
- trainer_state.json +798 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ce-lery/japanese-mistral-300m-base
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: checkpoints-finetuning
|
| 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 |
+
# japanese-mistral-300m-instruction
|
| 14 |
+
|
| 15 |
+
## Overview
|
| 16 |
+
|
| 17 |
+
Welcome to my model card!
|
| 18 |
+
|
| 19 |
+
This Model feature is ...
|
| 20 |
+
|
| 21 |
+
- Suppression of unknown word generation by using byte fallback in SentencePiece tokenizer and conversion to huggingface Tokenizers format
|
| 22 |
+
- Pretrained by wikipedia dataset and cc100 dataset
|
| 23 |
+
- Use of [Mistral 300M](https://huggingface.co/ce-lery/japanese-mistral-300m-base/blob/main/config.json)
|
| 24 |
+
- Fine-tuning [ce-lery/japanese-mistral-300m-base](https://huggingface.co/ce-lery/japanese-mistral-300m-base) with [kunishou/databricks-dolly-15k-ja](https://huggingface.co/datasets/kunishou/databricks-dolly-15k-ja)
|
| 25 |
+
|
| 26 |
+
Yukkuri shite ittene!
|
| 27 |
+
|
| 28 |
+
## How to use the model
|
| 29 |
+
|
| 30 |
+
```python
|
| 31 |
+
import torch
|
| 32 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 33 |
+
import os
|
| 34 |
+
|
| 35 |
+
MODEL_NAME = "ce-lery/japanese-mistral-300m-instruction"
|
| 36 |
+
torch.set_float32_matmul_precision('high')
|
| 37 |
+
|
| 38 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 39 |
+
print(device)
|
| 40 |
+
|
| 41 |
+
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=False,trust_remote_code=True)
|
| 42 |
+
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME,trust_remote_code=True).to(device)
|
| 43 |
+
|
| 44 |
+
MAX_ASSISTANT_LENGTH = 100
|
| 45 |
+
MAX_INPUT_LENGTH = 128
|
| 46 |
+
INPUT_PROMPT = r'<s>\n以下は、タスクを説明する指示と、文脈のある入力の組み合わせです。要求を適切に満たす応答を書きなさい。\n[SEP]\n指示:\n{instruction}\n[SEP]\n入力:\n{input}\n[SEP]\n応答:\n'
|
| 47 |
+
NO_INPUT_PROMPT = r'<s>\n以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。\n[SEP]\n指示:\n{instruction}\n[SEP]\n応答:\n'
|
| 48 |
+
|
| 49 |
+
def prepare_input(instruction, input_text):
|
| 50 |
+
if input_text != "":
|
| 51 |
+
prompt = INPUT_PROMPT.format(instruction=instruction, input=input_text)
|
| 52 |
+
else:
|
| 53 |
+
prompt = NO_INPUT_PROMPT.format(instruction=instruction)
|
| 54 |
+
return prompt
|
| 55 |
+
|
| 56 |
+
def format_output(output):
|
| 57 |
+
output = output.lstrip("<s>").rstrip("</s>").replace("[SEP]", "").replace("\\n", "\n")
|
| 58 |
+
return output
|
| 59 |
+
|
| 60 |
+
def generate_response(instruction, input_text):
|
| 61 |
+
prompt = prepare_input(instruction, input_text)
|
| 62 |
+
token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
|
| 63 |
+
n = len(token_ids[0])
|
| 64 |
+
# print(n)
|
| 65 |
+
|
| 66 |
+
with torch.no_grad():
|
| 67 |
+
output_ids = model.generate(
|
| 68 |
+
token_ids.to(model.device),
|
| 69 |
+
min_length=n,
|
| 70 |
+
max_length=min(MAX_INPUT_LENGTH, n + MAX_ASSISTANT_LENGTH),
|
| 71 |
+
top_p=0.95,
|
| 72 |
+
top_k=50,
|
| 73 |
+
temperature=0.4,
|
| 74 |
+
do_sample=True,
|
| 75 |
+
no_repeat_ngram_size=2,
|
| 76 |
+
num_beams=3,
|
| 77 |
+
pad_token_id=tokenizer.pad_token_id,
|
| 78 |
+
bos_token_id=tokenizer.bos_token_id,
|
| 79 |
+
eos_token_id=tokenizer.eos_token_id,
|
| 80 |
+
bad_words_ids=[[tokenizer.unk_token_id]]
|
| 81 |
+
)
|
| 82 |
+
|
| 83 |
+
output = tokenizer.decode(output_ids.tolist()[0])
|
| 84 |
+
formatted_output_all = format_output(output)
|
| 85 |
+
response = f"Assistant:{formatted_output_all.split('応答:')[-1].strip()}"
|
| 86 |
+
|
| 87 |
+
return formatted_output_all, response
|
| 88 |
+
|
| 89 |
+
instruction = "あなたは何でも正確に答えられるAIです。"
|
| 90 |
+
questions = [
|
| 91 |
+
"日本で一番高い山は？",
|
| 92 |
+
"日本で一番広い湖は？",
|
| 93 |
+
"世界で一番高い山は？",
|
| 94 |
+
"世界で一番広い湖は？",
|
| 95 |
+
"冗談を言ってください。",
|
| 96 |
+
]
|
| 97 |
+
|
| 98 |
+
# 各質問に対して応答を生成して表示
|
| 99 |
+
for question in questions:
|
| 100 |
+
formatted_output_all, response = generate_response(instruction, question)
|
| 101 |
+
print(response)
|
| 102 |
+
|
| 103 |
+
```
|
| 104 |
+
|
| 105 |
+
## Receipe
|
| 106 |
+
|
| 107 |
+
If you want to restruct this model, you can refer [this Github repository](https://github.com/ce-lery/japanese-mistral-300m-recipe).
|
| 108 |
+
|
| 109 |
+
I wrote the receipe for struction this model. For example,
|
| 110 |
+
|
| 111 |
+
- Preprocess with sentencepiece
|
| 112 |
+
- Pretraining with flash attention2 and torch.compile and DeepSpeed
|
| 113 |
+
- Fine-tuning with databricks-dolly-15k-ja
|
| 114 |
+
|
| 115 |
+
If you find my mistake,error,...etc, please create issue.
|
| 116 |
+
If you create pulreqest, I'm very happy!
|
| 117 |
+
## Training procedure
|
| 118 |
+
|
| 119 |
+
### Training hyperparameters
|
| 120 |
+
|
| 121 |
+
The following hyperparameters were used during training:
|
| 122 |
+
- learning_rate: 5e-06
|
| 123 |
+
- train_batch_size: 4
|
| 124 |
+
- eval_batch_size: 4
|
| 125 |
+
- seed: 42
|
| 126 |
+
- distributed_type: multi-GPU
|
| 127 |
+
- gradient_accumulation_steps: 64
|
| 128 |
+
- total_train_batch_size: 256
|
| 129 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=0.0001
|
| 130 |
+
- lr_scheduler_type: cosine
|
| 131 |
+
- lr_scheduler_warmup_steps: 1000
|
| 132 |
+
- num_epochs: 200
|
| 133 |
+
- mixed_precision_training: Native AMP
|
| 134 |
+
|
| 135 |
+
### Training results
|
| 136 |
+
|
| 137 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 138 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 139 |
+
| 3.595 | 3.51 | 40 | 3.5299 |
|
| 140 |
+
| 3.4769 | 7.02 | 80 | 3.3722 |
|
| 141 |
+
| 3.3037 | 10.53 | 120 | 3.1871 |
|
| 142 |
+
| 3.1255 | 14.05 | 160 | 3.0088 |
|
| 143 |
+
| 2.9615 | 17.56 | 200 | 2.8684 |
|
| 144 |
+
| 2.8468 | 21.07 | 240 | 2.7808 |
|
| 145 |
+
| 2.7699 | 24.58 | 280 | 2.7205 |
|
| 146 |
+
| 2.7139 | 28.09 | 320 | 2.6793 |
|
| 147 |
+
| 2.6712 | 31.6 | 360 | 2.6509 |
|
| 148 |
+
| 2.6356 | 35.12 | 400 | 2.6294 |
|
| 149 |
+
| 2.6048 | 38.63 | 440 | 2.6120 |
|
| 150 |
+
| 2.5823 | 42.14 | 480 | 2.5974 |
|
| 151 |
+
| 2.5536 | 45.65 | 520 | 2.5849 |
|
| 152 |
+
| 2.5293 | 49.16 | 560 | 2.5740 |
|
| 153 |
+
| 2.5058 | 52.67 | 600 | 2.5644 |
|
| 154 |
+
| 2.482 | 56.19 | 640 | 2.5556 |
|
| 155 |
+
| 2.4575 | 59.7 | 680 | 2.5477 |
|
| 156 |
+
| 2.4339 | 63.21 | 720 | 2.5405 |
|
| 157 |
+
| 2.4073 | 66.72 | 760 | 2.5350 |
|
| 158 |
+
| 2.3845 | 70.23 | 800 | 2.5303 |
|
| 159 |
+
| 2.3606 | 73.74 | 840 | 2.5253 |
|
| 160 |
+
| 2.329 | 77.26 | 880 | 2.5215 |
|
| 161 |
+
| 2.3071 | 80.77 | 920 | 2.5185 |
|
| 162 |
+
| 2.2768 | 84.28 | 960 | 2.5155 |
|
| 163 |
+
| 2.2479 | 87.79 | 1000 | 2.5144 |
|
| 164 |
+
| 2.2181 | 91.3 | 1040 | 2.5151 |
|
| 165 |
+
| 2.1901 | 94.81 | 1080 | 2.5139 |
|
| 166 |
+
| 2.1571 | 98.33 | 1120 | 2.5148 |
|
| 167 |
+
| 2.1308 | 101.84 | 1160 | 2.5166 |
|
| 168 |
+
| 2.1032 | 105.35 | 1200 | 2.5193 |
|
| 169 |
+
| 2.0761 | 108.86 | 1240 | 2.5204 |
|
| 170 |
+
| 2.0495 | 112.37 | 1280 | 2.5269 |
|
| 171 |
+
| 2.0231 | 115.88 | 1320 | 2.5285 |
|
| 172 |
+
| 2.0021 | 119.4 | 1360 | 2.5328 |
|
| 173 |
+
| 1.9793 | 122.91 | 1400 | 2.5383 |
|
| 174 |
+
| 1.9575 | 126.42 | 1440 | 2.5442 |
|
| 175 |
+
| 1.9368 | 129.93 | 1480 | 2.5488 |
|
| 176 |
+
| 1.9216 | 133.44 | 1520 | 2.5534 |
|
| 177 |
+
| 1.902 | 136.95 | 1560 | 2.5584 |
|
| 178 |
+
| 1.8885 | 140.47 | 1600 | 2.5609 |
|
| 179 |
+
| 1.8728 | 143.98 | 1640 | 2.5657 |
|
| 180 |
+
| 1.8605 | 147.49 | 1680 | 2.5697 |
|
| 181 |
+
| 1.8476 | 151.0 | 1720 | 2.5741 |
|
| 182 |
+
| 1.8402 | 154.51 | 1760 | 2.5770 |
|
| 183 |
+
| 1.8274 | 158.02 | 1800 | 2.5803 |
|
| 184 |
+
| 1.8218 | 161.54 | 1840 | 2.5829 |
|
| 185 |
+
| 1.8144 | 165.05 | 1880 | 2.5847 |
|
| 186 |
+
| 1.8097 | 168.56 | 1920 | 2.5867 |
|
| 187 |
+
| 1.8076 | 172.07 | 1960 | 2.5883 |
|
| 188 |
+
| 1.8014 | 175.58 | 2000 | 2.5892 |
|
| 189 |
+
| 1.8001 | 179.09 | 2040 | 2.5899 |
|
| 190 |
+
| 1.7987 | 182.61 | 2080 | 2.5903 |
|
| 191 |
+
| 1.7971 | 186.12 | 2120 | 2.5906 |
|
| 192 |
+
| 1.7979 | 189.63 | 2160 | 2.5907 |
|
| 193 |
+
| 1.7975 | 193.14 | 2200 | 2.5907 |
|
| 194 |
+
|
| 195 |
+
|
| 196 |
+
### Framework versions
|
| 197 |
+
|
| 198 |
+
- Transformers 4.35.2
|
| 199 |
+
- Pytorch 2.1.1+cu121
|
| 200 |
+
- Datasets 2.14.5
|
| 201 |
+
- Tokenizers 0.14.1
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 193.14,
|
| 3 |
+
"eval_loss": 2.513946056365967,
|
| 4 |
+
"eval_runtime": 4.6377,
|
| 5 |
+
"eval_samples": 313,
|
| 6 |
+
"eval_samples_per_second": 67.49,
|
| 7 |
+
"eval_steps_per_second": 17.034,
|
| 8 |
+
"perplexity": 12.353581936499637,
|
| 9 |
+
"train_loss": 2.2616969472711737,
|
| 10 |
+
"train_runtime": 20093.6832,
|
| 11 |
+
"train_samples": 2916,
|
| 12 |
+
"train_samples_per_second": 29.024,
|
| 13 |
+
"train_steps_per_second": 0.109
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../../pretrain/train/checkpoints-mistral-300M-FA2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 0,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 2400,
|
| 12 |
+
"max_position_embeddings": 4096,
|
| 13 |
+
"model_type": "mistral",
|
| 14 |
+
"num_attention_heads": 16,
|
| 15 |
+
"num_hidden_layers": 24,
|
| 16 |
+
"num_key_value_heads": 8,
|
| 17 |
+
"rms_norm_eps": 1e-05,
|
| 18 |
+
"rope_theta": 10000.0,
|
| 19 |
+
"sliding_window": 1024,
|
| 20 |
+
"tie_word_embeddings": false,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.35.2",
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 50257
|
| 25 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 193.14,
|
| 3 |
+
"eval_loss": 2.513946056365967,
|
| 4 |
+
"eval_runtime": 4.6377,
|
| 5 |
+
"eval_samples": 313,
|
| 6 |
+
"eval_samples_per_second": 67.49,
|
| 7 |
+
"eval_steps_per_second": 17.034,
|
| 8 |
+
"perplexity": 12.353581936499637
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.35.2"
|
| 6 |
+
}
|
logs/events.out.tfevents.1702213518.90c313ded1af.749823.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ab5e18d681e45befea0f89ce8bf0b3c905f0204bdceb0a194a8d5b35e106d37
|
| 3 |
+
size 28067
|
logs/events.out.tfevents.1702233619.90c313ded1af.749823.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7c98962865b1824fe059a075d55138896ddd9ae996d36db1edbab0308142f09
|
| 3 |
+
size 359
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3413550b9d3e9e0b5ea6a87537fe728760798a2ee96e83f75ec1d60b3aaa256
|
| 3 |
+
size 1421709600
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "[UNK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:604cb0c2f073ba13f04739ced6f8310f4f00ab344feea6cb5c4012af3876c684
|
| 3 |
+
size 1249735
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 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 |
+
"3": {
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"additional_special_tokens": [],
|
| 37 |
+
"bos_token": "<s>",
|
| 38 |
+
"clean_up_tokenization_spaces": true,
|
| 39 |
+
"eos_token": "</s>",
|
| 40 |
+
"extra_ids": 0,
|
| 41 |
+
"legacy": true,
|
| 42 |
+
"model_max_length": 50000,
|
| 43 |
+
"pad_token": "[PAD]",
|
| 44 |
+
"sp_model_kwargs": {},
|
| 45 |
+
"tokenizer_class": "T5Tokenizer",
|
| 46 |
+
"unk_token": "[UNK]"
|
| 47 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 193.14,
|
| 3 |
+
"train_loss": 2.2616969472711737,
|
| 4 |
+
"train_runtime": 20093.6832,
|
| 5 |
+
"train_samples": 2916,
|
| 6 |
+
"train_samples_per_second": 29.024,
|
| 7 |
+
"train_steps_per_second": 0.109
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,798 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.513946056365967,
|
| 3 |
+
"best_model_checkpoint": "checkpoints-finetuning/checkpoint-1080",
|
| 4 |
+
"epoch": 193.14128943758573,
|
| 5 |
+
"eval_steps": 40,
|
| 6 |
+
"global_step": 2200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 3.51,
|
| 13 |
+
"learning_rate": 2.0000000000000002e-07,
|
| 14 |
+
"loss": 3.595,
|
| 15 |
+
"step": 40
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 3.51,
|
| 19 |
+
"eval_loss": 3.5299072265625,
|
| 20 |
+
"eval_runtime": 5.0148,
|
| 21 |
+
"eval_samples_per_second": 62.416,
|
| 22 |
+
"eval_steps_per_second": 15.753,
|
| 23 |
+
"step": 40
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 7.02,
|
| 27 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 28 |
+
"loss": 3.4769,
|
| 29 |
+
"step": 80
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 7.02,
|
| 33 |
+
"eval_loss": 3.3721721172332764,
|
| 34 |
+
"eval_runtime": 4.4435,
|
| 35 |
+
"eval_samples_per_second": 70.441,
|
| 36 |
+
"eval_steps_per_second": 17.779,
|
| 37 |
+
"step": 80
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 10.53,
|
| 41 |
+
"learning_rate": 6.000000000000001e-07,
|
| 42 |
+
"loss": 3.3037,
|
| 43 |
+
"step": 120
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 10.53,
|
| 47 |
+
"eval_loss": 3.1870808601379395,
|
| 48 |
+
"eval_runtime": 4.6407,
|
| 49 |
+
"eval_samples_per_second": 67.446,
|
| 50 |
+
"eval_steps_per_second": 17.023,
|
| 51 |
+
"step": 120
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 14.05,
|
| 55 |
+
"learning_rate": 8.000000000000001e-07,
|
| 56 |
+
"loss": 3.1255,
|
| 57 |
+
"step": 160
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 14.05,
|
| 61 |
+
"eval_loss": 3.0087945461273193,
|
| 62 |
+
"eval_runtime": 4.7026,
|
| 63 |
+
"eval_samples_per_second": 66.559,
|
| 64 |
+
"eval_steps_per_second": 16.799,
|
| 65 |
+
"step": 160
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 17.56,
|
| 69 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 70 |
+
"loss": 2.9615,
|
| 71 |
+
"step": 200
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 17.56,
|
| 75 |
+
"eval_loss": 2.8684051036834717,
|
| 76 |
+
"eval_runtime": 4.6401,
|
| 77 |
+
"eval_samples_per_second": 67.455,
|
| 78 |
+
"eval_steps_per_second": 17.026,
|
| 79 |
+
"step": 200
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 21.07,
|
| 83 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 84 |
+
"loss": 2.8468,
|
| 85 |
+
"step": 240
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 21.07,
|
| 89 |
+
"eval_loss": 2.780834436416626,
|
| 90 |
+
"eval_runtime": 4.4221,
|
| 91 |
+
"eval_samples_per_second": 70.78,
|
| 92 |
+
"eval_steps_per_second": 17.865,
|
| 93 |
+
"step": 240
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 24.58,
|
| 97 |
+
"learning_rate": 1.4000000000000001e-06,
|
| 98 |
+
"loss": 2.7699,
|
| 99 |
+
"step": 280
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 24.58,
|
| 103 |
+
"eval_loss": 2.720453977584839,
|
| 104 |
+
"eval_runtime": 4.5663,
|
| 105 |
+
"eval_samples_per_second": 68.546,
|
| 106 |
+
"eval_steps_per_second": 17.301,
|
| 107 |
+
"step": 280
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 28.09,
|
| 111 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 112 |
+
"loss": 2.7139,
|
| 113 |
+
"step": 320
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 28.09,
|
| 117 |
+
"eval_loss": 2.679349422454834,
|
| 118 |
+
"eval_runtime": 4.7784,
|
| 119 |
+
"eval_samples_per_second": 65.504,
|
| 120 |
+
"eval_steps_per_second": 16.533,
|
| 121 |
+
"step": 320
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 31.6,
|
| 125 |
+
"learning_rate": 1.8000000000000001e-06,
|
| 126 |
+
"loss": 2.6712,
|
| 127 |
+
"step": 360
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 31.6,
|
| 131 |
+
"eval_loss": 2.650853395462036,
|
| 132 |
+
"eval_runtime": 4.6713,
|
| 133 |
+
"eval_samples_per_second": 67.005,
|
| 134 |
+
"eval_steps_per_second": 16.912,
|
| 135 |
+
"step": 360
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 35.12,
|
| 139 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 140 |
+
"loss": 2.6356,
|
| 141 |
+
"step": 400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 35.12,
|
| 145 |
+
"eval_loss": 2.6293749809265137,
|
| 146 |
+
"eval_runtime": 4.6364,
|
| 147 |
+
"eval_samples_per_second": 67.51,
|
| 148 |
+
"eval_steps_per_second": 17.039,
|
| 149 |
+
"step": 400
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 38.63,
|
| 153 |
+
"learning_rate": 2.2e-06,
|
| 154 |
+
"loss": 2.6048,
|
| 155 |
+
"step": 440
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 38.63,
|
| 159 |
+
"eval_loss": 2.611950635910034,
|
| 160 |
+
"eval_runtime": 4.5116,
|
| 161 |
+
"eval_samples_per_second": 69.377,
|
| 162 |
+
"eval_steps_per_second": 17.511,
|
| 163 |
+
"step": 440
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 42.14,
|
| 167 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 168 |
+
"loss": 2.5823,
|
| 169 |
+
"step": 480
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 42.14,
|
| 173 |
+
"eval_loss": 2.597449541091919,
|
| 174 |
+
"eval_runtime": 4.5213,
|
| 175 |
+
"eval_samples_per_second": 69.228,
|
| 176 |
+
"eval_steps_per_second": 17.473,
|
| 177 |
+
"step": 480
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 45.65,
|
| 181 |
+
"learning_rate": 2.6e-06,
|
| 182 |
+
"loss": 2.5536,
|
| 183 |
+
"step": 520
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 45.65,
|
| 187 |
+
"eval_loss": 2.5848779678344727,
|
| 188 |
+
"eval_runtime": 4.4398,
|
| 189 |
+
"eval_samples_per_second": 70.498,
|
| 190 |
+
"eval_steps_per_second": 17.793,
|
| 191 |
+
"step": 520
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 49.16,
|
| 195 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 196 |
+
"loss": 2.5293,
|
| 197 |
+
"step": 560
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 49.16,
|
| 201 |
+
"eval_loss": 2.574049472808838,
|
| 202 |
+
"eval_runtime": 4.6572,
|
| 203 |
+
"eval_samples_per_second": 67.208,
|
| 204 |
+
"eval_steps_per_second": 16.963,
|
| 205 |
+
"step": 560
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 52.67,
|
| 209 |
+
"learning_rate": 3e-06,
|
| 210 |
+
"loss": 2.5058,
|
| 211 |
+
"step": 600
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 52.67,
|
| 215 |
+
"eval_loss": 2.5643808841705322,
|
| 216 |
+
"eval_runtime": 4.6849,
|
| 217 |
+
"eval_samples_per_second": 66.81,
|
| 218 |
+
"eval_steps_per_second": 16.863,
|
| 219 |
+
"step": 600
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 56.19,
|
| 223 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 224 |
+
"loss": 2.482,
|
| 225 |
+
"step": 640
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 56.19,
|
| 229 |
+
"eval_loss": 2.555607557296753,
|
| 230 |
+
"eval_runtime": 4.491,
|
| 231 |
+
"eval_samples_per_second": 69.695,
|
| 232 |
+
"eval_steps_per_second": 17.591,
|
| 233 |
+
"step": 640
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 59.7,
|
| 237 |
+
"learning_rate": 3.4000000000000005e-06,
|
| 238 |
+
"loss": 2.4575,
|
| 239 |
+
"step": 680
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 59.7,
|
| 243 |
+
"eval_loss": 2.547734260559082,
|
| 244 |
+
"eval_runtime": 4.6182,
|
| 245 |
+
"eval_samples_per_second": 67.776,
|
| 246 |
+
"eval_steps_per_second": 17.106,
|
| 247 |
+
"step": 680
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 63.21,
|
| 251 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 252 |
+
"loss": 2.4339,
|
| 253 |
+
"step": 720
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 63.21,
|
| 257 |
+
"eval_loss": 2.5405359268188477,
|
| 258 |
+
"eval_runtime": 4.5137,
|
| 259 |
+
"eval_samples_per_second": 69.345,
|
| 260 |
+
"eval_steps_per_second": 17.502,
|
| 261 |
+
"step": 720
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 66.72,
|
| 265 |
+
"learning_rate": 3.8000000000000005e-06,
|
| 266 |
+
"loss": 2.4073,
|
| 267 |
+
"step": 760
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 66.72,
|
| 271 |
+
"eval_loss": 2.5350451469421387,
|
| 272 |
+
"eval_runtime": 4.6034,
|
| 273 |
+
"eval_samples_per_second": 67.993,
|
| 274 |
+
"eval_steps_per_second": 17.161,
|
| 275 |
+
"step": 760
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 70.23,
|
| 279 |
+
"learning_rate": 4.000000000000001e-06,
|
| 280 |
+
"loss": 2.3845,
|
| 281 |
+
"step": 800
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 70.23,
|
| 285 |
+
"eval_loss": 2.530299186706543,
|
| 286 |
+
"eval_runtime": 4.6325,
|
| 287 |
+
"eval_samples_per_second": 67.566,
|
| 288 |
+
"eval_steps_per_second": 17.053,
|
| 289 |
+
"step": 800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 73.74,
|
| 293 |
+
"learning_rate": 4.2000000000000004e-06,
|
| 294 |
+
"loss": 2.3606,
|
| 295 |
+
"step": 840
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 73.74,
|
| 299 |
+
"eval_loss": 2.525312662124634,
|
| 300 |
+
"eval_runtime": 4.4668,
|
| 301 |
+
"eval_samples_per_second": 70.072,
|
| 302 |
+
"eval_steps_per_second": 17.686,
|
| 303 |
+
"step": 840
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 77.26,
|
| 307 |
+
"learning_rate": 4.4e-06,
|
| 308 |
+
"loss": 2.329,
|
| 309 |
+
"step": 880
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 77.26,
|
| 313 |
+
"eval_loss": 2.5215225219726562,
|
| 314 |
+
"eval_runtime": 4.4699,
|
| 315 |
+
"eval_samples_per_second": 70.023,
|
| 316 |
+
"eval_steps_per_second": 17.674,
|
| 317 |
+
"step": 880
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 80.77,
|
| 321 |
+
"learning_rate": 4.600000000000001e-06,
|
| 322 |
+
"loss": 2.3071,
|
| 323 |
+
"step": 920
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 80.77,
|
| 327 |
+
"eval_loss": 2.5184576511383057,
|
| 328 |
+
"eval_runtime": 4.3807,
|
| 329 |
+
"eval_samples_per_second": 71.45,
|
| 330 |
+
"eval_steps_per_second": 18.034,
|
| 331 |
+
"step": 920
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 84.28,
|
| 335 |
+
"learning_rate": 4.800000000000001e-06,
|
| 336 |
+
"loss": 2.2768,
|
| 337 |
+
"step": 960
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 84.28,
|
| 341 |
+
"eval_loss": 2.515460729598999,
|
| 342 |
+
"eval_runtime": 4.6634,
|
| 343 |
+
"eval_samples_per_second": 67.119,
|
| 344 |
+
"eval_steps_per_second": 16.941,
|
| 345 |
+
"step": 960
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 87.79,
|
| 349 |
+
"learning_rate": 5e-06,
|
| 350 |
+
"loss": 2.2479,
|
| 351 |
+
"step": 1000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 87.79,
|
| 355 |
+
"eval_loss": 2.514392852783203,
|
| 356 |
+
"eval_runtime": 4.5583,
|
| 357 |
+
"eval_samples_per_second": 68.665,
|
| 358 |
+
"eval_steps_per_second": 17.331,
|
| 359 |
+
"step": 1000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 91.3,
|
| 363 |
+
"learning_rate": 4.986304738420684e-06,
|
| 364 |
+
"loss": 2.2181,
|
| 365 |
+
"step": 1040
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 91.3,
|
| 369 |
+
"eval_loss": 2.515076160430908,
|
| 370 |
+
"eval_runtime": 4.6324,
|
| 371 |
+
"eval_samples_per_second": 67.568,
|
| 372 |
+
"eval_steps_per_second": 17.054,
|
| 373 |
+
"step": 1040
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 94.81,
|
| 377 |
+
"learning_rate": 4.9453690018345144e-06,
|
| 378 |
+
"loss": 2.1901,
|
| 379 |
+
"step": 1080
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 94.81,
|
| 383 |
+
"eval_loss": 2.513946056365967,
|
| 384 |
+
"eval_runtime": 4.635,
|
| 385 |
+
"eval_samples_per_second": 67.53,
|
| 386 |
+
"eval_steps_per_second": 17.044,
|
| 387 |
+
"step": 1080
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 98.33,
|
| 391 |
+
"learning_rate": 4.8776412907378845e-06,
|
| 392 |
+
"loss": 2.1571,
|
| 393 |
+
"step": 1120
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 98.33,
|
| 397 |
+
"eval_loss": 2.514775037765503,
|
| 398 |
+
"eval_runtime": 4.7132,
|
| 399 |
+
"eval_samples_per_second": 66.41,
|
| 400 |
+
"eval_steps_per_second": 16.762,
|
| 401 |
+
"step": 1120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 101.84,
|
| 405 |
+
"learning_rate": 4.783863644106502e-06,
|
| 406 |
+
"loss": 2.1308,
|
| 407 |
+
"step": 1160
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 101.84,
|
| 411 |
+
"eval_loss": 2.5165762901306152,
|
| 412 |
+
"eval_runtime": 4.6347,
|
| 413 |
+
"eval_samples_per_second": 67.535,
|
| 414 |
+
"eval_steps_per_second": 17.046,
|
| 415 |
+
"step": 1160
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 105.35,
|
| 419 |
+
"learning_rate": 4.665063509461098e-06,
|
| 420 |
+
"loss": 2.1032,
|
| 421 |
+
"step": 1200
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 105.35,
|
| 425 |
+
"eval_loss": 2.5192971229553223,
|
| 426 |
+
"eval_runtime": 4.6292,
|
| 427 |
+
"eval_samples_per_second": 67.614,
|
| 428 |
+
"eval_steps_per_second": 17.066,
|
| 429 |
+
"step": 1200
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 108.86,
|
| 433 |
+
"learning_rate": 4.522542485937369e-06,
|
| 434 |
+
"loss": 2.0761,
|
| 435 |
+
"step": 1240
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 108.86,
|
| 439 |
+
"eval_loss": 2.5203866958618164,
|
| 440 |
+
"eval_runtime": 4.6638,
|
| 441 |
+
"eval_samples_per_second": 67.113,
|
| 442 |
+
"eval_steps_per_second": 16.939,
|
| 443 |
+
"step": 1240
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 112.37,
|
| 447 |
+
"learning_rate": 4.357862063693486e-06,
|
| 448 |
+
"loss": 2.0495,
|
| 449 |
+
"step": 1280
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 112.37,
|
| 453 |
+
"eval_loss": 2.5268709659576416,
|
| 454 |
+
"eval_runtime": 4.6504,
|
| 455 |
+
"eval_samples_per_second": 67.306,
|
| 456 |
+
"eval_steps_per_second": 16.988,
|
| 457 |
+
"step": 1280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 115.88,
|
| 461 |
+
"learning_rate": 4.172826515897146e-06,
|
| 462 |
+
"loss": 2.0231,
|
| 463 |
+
"step": 1320
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 115.88,
|
| 467 |
+
"eval_loss": 2.5284526348114014,
|
| 468 |
+
"eval_runtime": 4.6029,
|
| 469 |
+
"eval_samples_per_second": 68.0,
|
| 470 |
+
"eval_steps_per_second": 17.163,
|
| 471 |
+
"step": 1320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 119.4,
|
| 475 |
+
"learning_rate": 3.969463130731183e-06,
|
| 476 |
+
"loss": 2.0021,
|
| 477 |
+
"step": 1360
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 119.4,
|
| 481 |
+
"eval_loss": 2.5327632427215576,
|
| 482 |
+
"eval_runtime": 4.7118,
|
| 483 |
+
"eval_samples_per_second": 66.429,
|
| 484 |
+
"eval_steps_per_second": 16.767,
|
| 485 |
+
"step": 1360
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 122.91,
|
| 489 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 490 |
+
"loss": 1.9793,
|
| 491 |
+
"step": 1400
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 122.91,
|
| 495 |
+
"eval_loss": 2.5382816791534424,
|
| 496 |
+
"eval_runtime": 4.6299,
|
| 497 |
+
"eval_samples_per_second": 67.603,
|
| 498 |
+
"eval_steps_per_second": 17.063,
|
| 499 |
+
"step": 1400
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 126.42,
|
| 503 |
+
"learning_rate": 3.516841607689501e-06,
|
| 504 |
+
"loss": 1.9575,
|
| 505 |
+
"step": 1440
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 126.42,
|
| 509 |
+
"eval_loss": 2.5441536903381348,
|
| 510 |
+
"eval_runtime": 4.6442,
|
| 511 |
+
"eval_samples_per_second": 67.396,
|
| 512 |
+
"eval_steps_per_second": 17.01,
|
| 513 |
+
"step": 1440
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 129.93,
|
| 517 |
+
"learning_rate": 3.272542485937369e-06,
|
| 518 |
+
"loss": 1.9368,
|
| 519 |
+
"step": 1480
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 129.93,
|
| 523 |
+
"eval_loss": 2.5487852096557617,
|
| 524 |
+
"eval_runtime": 4.6396,
|
| 525 |
+
"eval_samples_per_second": 67.462,
|
| 526 |
+
"eval_steps_per_second": 17.027,
|
| 527 |
+
"step": 1480
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 133.44,
|
| 531 |
+
"learning_rate": 3.019779227044398e-06,
|
| 532 |
+
"loss": 1.9216,
|
| 533 |
+
"step": 1520
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 133.44,
|
| 537 |
+
"eval_loss": 2.5533745288848877,
|
| 538 |
+
"eval_runtime": 4.6038,
|
| 539 |
+
"eval_samples_per_second": 67.987,
|
| 540 |
+
"eval_steps_per_second": 17.16,
|
| 541 |
+
"step": 1520
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 136.95,
|
| 545 |
+
"learning_rate": 2.761321158169134e-06,
|
| 546 |
+
"loss": 1.902,
|
| 547 |
+
"step": 1560
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 136.95,
|
| 551 |
+
"eval_loss": 2.558429479598999,
|
| 552 |
+
"eval_runtime": 4.605,
|
| 553 |
+
"eval_samples_per_second": 67.969,
|
| 554 |
+
"eval_steps_per_second": 17.155,
|
| 555 |
+
"step": 1560
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 140.47,
|
| 559 |
+
"learning_rate": 2.5e-06,
|
| 560 |
+
"loss": 1.8885,
|
| 561 |
+
"step": 1600
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 140.47,
|
| 565 |
+
"eval_loss": 2.560931444168091,
|
| 566 |
+
"eval_runtime": 4.6137,
|
| 567 |
+
"eval_samples_per_second": 67.842,
|
| 568 |
+
"eval_steps_per_second": 17.123,
|
| 569 |
+
"step": 1600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 143.98,
|
| 573 |
+
"learning_rate": 2.238678841830867e-06,
|
| 574 |
+
"loss": 1.8728,
|
| 575 |
+
"step": 1640
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 143.98,
|
| 579 |
+
"eval_loss": 2.565746307373047,
|
| 580 |
+
"eval_runtime": 4.6085,
|
| 581 |
+
"eval_samples_per_second": 67.918,
|
| 582 |
+
"eval_steps_per_second": 17.142,
|
| 583 |
+
"step": 1640
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 147.49,
|
| 587 |
+
"learning_rate": 1.9802207729556023e-06,
|
| 588 |
+
"loss": 1.8605,
|
| 589 |
+
"step": 1680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 147.49,
|
| 593 |
+
"eval_loss": 2.569748640060425,
|
| 594 |
+
"eval_runtime": 4.6652,
|
| 595 |
+
"eval_samples_per_second": 67.092,
|
| 596 |
+
"eval_steps_per_second": 16.934,
|
| 597 |
+
"step": 1680
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 151.0,
|
| 601 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 602 |
+
"loss": 1.8476,
|
| 603 |
+
"step": 1720
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 151.0,
|
| 607 |
+
"eval_loss": 2.5741446018218994,
|
| 608 |
+
"eval_runtime": 4.7429,
|
| 609 |
+
"eval_samples_per_second": 65.994,
|
| 610 |
+
"eval_steps_per_second": 16.657,
|
| 611 |
+
"step": 1720
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 154.51,
|
| 615 |
+
"learning_rate": 1.4831583923105e-06,
|
| 616 |
+
"loss": 1.8402,
|
| 617 |
+
"step": 1760
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 154.51,
|
| 621 |
+
"eval_loss": 2.5770394802093506,
|
| 622 |
+
"eval_runtime": 4.6184,
|
| 623 |
+
"eval_samples_per_second": 67.772,
|
| 624 |
+
"eval_steps_per_second": 17.105,
|
| 625 |
+
"step": 1760
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 158.02,
|
| 629 |
+
"learning_rate": 1.2500000000000007e-06,
|
| 630 |
+
"loss": 1.8274,
|
| 631 |
+
"step": 1800
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 158.02,
|
| 635 |
+
"eval_loss": 2.580260992050171,
|
| 636 |
+
"eval_runtime": 4.5687,
|
| 637 |
+
"eval_samples_per_second": 68.509,
|
| 638 |
+
"eval_steps_per_second": 17.291,
|
| 639 |
+
"step": 1800
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 161.54,
|
| 643 |
+
"learning_rate": 1.0305368692688175e-06,
|
| 644 |
+
"loss": 1.8218,
|
| 645 |
+
"step": 1840
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 161.54,
|
| 649 |
+
"eval_loss": 2.582859992980957,
|
| 650 |
+
"eval_runtime": 4.6266,
|
| 651 |
+
"eval_samples_per_second": 67.653,
|
| 652 |
+
"eval_steps_per_second": 17.075,
|
| 653 |
+
"step": 1840
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 165.05,
|
| 657 |
+
"learning_rate": 8.271734841028553e-07,
|
| 658 |
+
"loss": 1.8144,
|
| 659 |
+
"step": 1880
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 165.05,
|
| 663 |
+
"eval_loss": 2.5846669673919678,
|
| 664 |
+
"eval_runtime": 4.601,
|
| 665 |
+
"eval_samples_per_second": 68.029,
|
| 666 |
+
"eval_steps_per_second": 17.17,
|
| 667 |
+
"step": 1880
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 168.56,
|
| 671 |
+
"learning_rate": 6.421379363065142e-07,
|
| 672 |
+
"loss": 1.8097,
|
| 673 |
+
"step": 1920
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 168.56,
|
| 677 |
+
"eval_loss": 2.5867464542388916,
|
| 678 |
+
"eval_runtime": 4.593,
|
| 679 |
+
"eval_samples_per_second": 68.148,
|
| 680 |
+
"eval_steps_per_second": 17.2,
|
| 681 |
+
"step": 1920
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 172.07,
|
| 685 |
+
"learning_rate": 4.774575140626317e-07,
|
| 686 |
+
"loss": 1.8076,
|
| 687 |
+
"step": 1960
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 172.07,
|
| 691 |
+
"eval_loss": 2.5882575511932373,
|
| 692 |
+
"eval_runtime": 4.601,
|
| 693 |
+
"eval_samples_per_second": 68.028,
|
| 694 |
+
"eval_steps_per_second": 17.17,
|
| 695 |
+
"step": 1960
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 175.58,
|
| 699 |
+
"learning_rate": 3.3493649053890325e-07,
|
| 700 |
+
"loss": 1.8014,
|
| 701 |
+
"step": 2000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 175.58,
|
| 705 |
+
"eval_loss": 2.589245080947876,
|
| 706 |
+
"eval_runtime": 4.5976,
|
| 707 |
+
"eval_samples_per_second": 68.079,
|
| 708 |
+
"eval_steps_per_second": 17.183,
|
| 709 |
+
"step": 2000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 179.09,
|
| 713 |
+
"learning_rate": 2.1613635589349756e-07,
|
| 714 |
+
"loss": 1.8001,
|
| 715 |
+
"step": 2040
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 179.09,
|
| 719 |
+
"eval_loss": 2.589866876602173,
|
| 720 |
+
"eval_runtime": 4.5824,
|
| 721 |
+
"eval_samples_per_second": 68.305,
|
| 722 |
+
"eval_steps_per_second": 17.24,
|
| 723 |
+
"step": 2040
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 182.61,
|
| 727 |
+
"learning_rate": 1.223587092621162e-07,
|
| 728 |
+
"loss": 1.7987,
|
| 729 |
+
"step": 2080
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 182.61,
|
| 733 |
+
"eval_loss": 2.5903093814849854,
|
| 734 |
+
"eval_runtime": 4.6146,
|
| 735 |
+
"eval_samples_per_second": 67.829,
|
| 736 |
+
"eval_steps_per_second": 17.12,
|
| 737 |
+
"step": 2080
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 186.12,
|
| 741 |
+
"learning_rate": 5.463099816548578e-08,
|
| 742 |
+
"loss": 1.7971,
|
| 743 |
+
"step": 2120
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 186.12,
|
| 747 |
+
"eval_loss": 2.590583562850952,
|
| 748 |
+
"eval_runtime": 4.609,
|
| 749 |
+
"eval_samples_per_second": 67.911,
|
| 750 |
+
"eval_steps_per_second": 17.141,
|
| 751 |
+
"step": 2120
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 189.63,
|
| 755 |
+
"learning_rate": 1.3695261579316776e-08,
|
| 756 |
+
"loss": 1.7979,
|
| 757 |
+
"step": 2160
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 189.63,
|
| 761 |
+
"eval_loss": 2.5907208919525146,
|
| 762 |
+
"eval_runtime": 4.6125,
|
| 763 |
+
"eval_samples_per_second": 67.859,
|
| 764 |
+
"eval_steps_per_second": 17.127,
|
| 765 |
+
"step": 2160
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 193.14,
|
| 769 |
+
"learning_rate": 0.0,
|
| 770 |
+
"loss": 1.7975,
|
| 771 |
+
"step": 2200
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 193.14,
|
| 775 |
+
"eval_loss": 2.590698719024658,
|
| 776 |
+
"eval_runtime": 4.6213,
|
| 777 |
+
"eval_samples_per_second": 67.729,
|
| 778 |
+
"eval_steps_per_second": 17.095,
|
| 779 |
+
"step": 2200
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 193.14,
|
| 783 |
+
"step": 2200,
|
| 784 |
+
"total_flos": 1.0517861659312128e+18,
|
| 785 |
+
"train_loss": 2.2616969472711737,
|
| 786 |
+
"train_runtime": 20093.6832,
|
| 787 |
+
"train_samples_per_second": 29.024,
|
| 788 |
+
"train_steps_per_second": 0.109
|
| 789 |
+
}
|
| 790 |
+
],
|
| 791 |
+
"logging_steps": 40,
|
| 792 |
+
"max_steps": 2200,
|
| 793 |
+
"num_train_epochs": 200,
|
| 794 |
+
"save_steps": 40,
|
| 795 |
+
"total_flos": 1.0517861659312128e+18,
|
| 796 |
+
"trial_name": null,
|
| 797 |
+
"trial_params": null
|
| 798 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f815d8b0257d2db0dc8b65f8b60c00f75c67865ca45e0bab814f141b01b092e
|
| 3 |
+
size 4536
|