初始化项目,由ModelHub XC社区提供模型

Model: pre-to-post-olmo/math-1b-sft-numinamath-bs512-from-step35000
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-17 20:54:15 +08:00
commit 23a34e6cd5
17 changed files with 602298 additions and 0 deletions

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

61
README.md Normal file
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: other
base_model: pre-to-post-olmo/math-1b-anneal-from-step35000
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: math-1b-sft-numinamath-bs512-from-step35000
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# math-1b-sft-numinamath-bs512-from-step35000
This model is a fine-tuned version of [pre-to-post-olmo/math-1b-anneal-from-step35000](https://huggingface.co/pre-to-post-olmo/math-1b-anneal-from-step35000) on the numinamath_cot dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 4.57.1
- Pytorch 2.12.1+cu130
- Datasets 4.0.0
- Tokenizers 0.22.2

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.0,
"total_flos": 7.06306771390772e+18,
"train_loss": 0.5623956888186357,
"train_runtime": 4990.0178,
"train_samples_per_second": 172.243,
"train_steps_per_second": 0.673
}

4
chat_template.jinja Normal file
View File

@@ -0,0 +1,4 @@
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
' + message['content'] + '<|im_end|>' + '
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
' }}{% endif %}

30
config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"architectures": [
"Olmo2ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 100257,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 8192,
"model_type": "olmo2",
"num_attention_heads": 16,
"num_hidden_layers": 16,
"num_key_value_heads": 16,
"pad_token_id": 100277,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 500000,
"rope_type": "default"
},
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"transformers_version": "4.57.1",
"use_cache": false,
"vocab_size": 100278
}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"do_sample": true,
"eos_token_id": [
100265,
100257
],
"pad_token_id": 100277,
"transformers_version": "4.57.1"
}

100001
merges.txt Normal file

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ec70646974501ab041e67b3336b89ac9ec160647ba4ed11b5b9f04729c55d1b0
size 2969248016

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

500536
tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

195
tokenizer_config.json Normal file
View File

@@ -0,0 +1,195 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"100256": {
"content": "<|extra_id_0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100257": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100258": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100259": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100260": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100261": {
"content": "|||PHONE_NUMBER|||",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100262": {
"content": "|||EMAIL_ADDRESS|||",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100263": {
"content": "|||IP_ADDRESS|||",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100264": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100265": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100266": {
"content": "<|extra_id_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100267": {
"content": "<|extra_id_2|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100268": {
"content": "<|extra_id_3|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100269": {
"content": "<|extra_id_4|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100270": {
"content": "<|extra_id_5|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100271": {
"content": "<|extra_id_6|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100272": {
"content": "<|extra_id_7|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100273": {
"content": "<|extra_id_8|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100274": {
"content": "<|extra_id_9|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100275": {
"content": "<|extra_id_10|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100276": {
"content": "<|endofprompt|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100277": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": {},
"is_local": false,
"local_files_only": false,
"model_max_length": 8192,
"pad_token": "<|pad|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.0,
"total_flos": 7.06306771390772e+18,
"train_loss": 0.5623956888186357,
"train_runtime": 4990.0178,
"train_samples_per_second": 172.243,
"train_steps_per_second": 0.673
}

168
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,168 @@
{"current_steps": 20, "total_steps": 3358, "loss": 1.74, "lr": 1.8811881188118813e-06, "epoch": 0.005956813104988831, "percentage": 0.6, "elapsed_time": "0:01:00", "remaining_time": "2:47:12"}
{"current_steps": 40, "total_steps": 3358, "loss": 1.5091, "lr": 3.861386138613862e-06, "epoch": 0.011913626209977662, "percentage": 1.19, "elapsed_time": "0:01:42", "remaining_time": "2:21:13"}
{"current_steps": 60, "total_steps": 3358, "loss": 1.0497, "lr": 5.841584158415842e-06, "epoch": 0.017870439314966492, "percentage": 1.79, "elapsed_time": "0:02:20", "remaining_time": "2:08:42"}
{"current_steps": 80, "total_steps": 3358, "loss": 0.8174, "lr": 7.821782178217822e-06, "epoch": 0.023827252419955324, "percentage": 2.38, "elapsed_time": "0:02:55", "remaining_time": "1:59:56"}
{"current_steps": 100, "total_steps": 3358, "loss": 0.7124, "lr": 9.801980198019802e-06, "epoch": 0.029784065524944156, "percentage": 2.98, "elapsed_time": "0:03:30", "remaining_time": "1:54:17"}
{"current_steps": 120, "total_steps": 3358, "loss": 0.6783, "lr": 9.99924640442892e-06, "epoch": 0.035740878629932984, "percentage": 3.57, "elapsed_time": "0:04:04", "remaining_time": "1:50:07"}
{"current_steps": 140, "total_steps": 3358, "loss": 0.6554, "lr": 9.99664167434275e-06, "epoch": 0.04169769173492182, "percentage": 4.17, "elapsed_time": "0:04:39", "remaining_time": "1:47:03"}
{"current_steps": 160, "total_steps": 3358, "loss": 0.6373, "lr": 9.99217747519571e-06, "epoch": 0.04765450483991065, "percentage": 4.76, "elapsed_time": "0:05:11", "remaining_time": "1:43:50"}
{"current_steps": 180, "total_steps": 3358, "loss": 0.6351, "lr": 9.98585546831169e-06, "epoch": 0.05361131794489948, "percentage": 5.36, "elapsed_time": "0:05:45", "remaining_time": "1:41:43"}
{"current_steps": 200, "total_steps": 3358, "loss": 0.6139, "lr": 9.977678006386153e-06, "epoch": 0.05956813104988831, "percentage": 5.96, "elapsed_time": "0:06:20", "remaining_time": "1:40:01"}
{"current_steps": 220, "total_steps": 3358, "loss": 0.6134, "lr": 9.967648132610596e-06, "epoch": 0.06552494415487714, "percentage": 6.55, "elapsed_time": "0:06:52", "remaining_time": "1:37:59"}
{"current_steps": 240, "total_steps": 3358, "loss": 0.6097, "lr": 9.95576957954004e-06, "epoch": 0.07148175725986597, "percentage": 7.15, "elapsed_time": "0:07:25", "remaining_time": "1:36:23"}
{"current_steps": 260, "total_steps": 3358, "loss": 0.6071, "lr": 9.942046767703982e-06, "epoch": 0.0774385703648548, "percentage": 7.74, "elapsed_time": "0:07:59", "remaining_time": "1:35:15"}
{"current_steps": 280, "total_steps": 3358, "loss": 0.6001, "lr": 9.926484803961332e-06, "epoch": 0.08339538346984364, "percentage": 8.34, "elapsed_time": "0:08:30", "remaining_time": "1:33:34"}
{"current_steps": 300, "total_steps": 3358, "loss": 0.6004, "lr": 9.909089479599916e-06, "epoch": 0.08935219657483247, "percentage": 8.93, "elapsed_time": "0:09:00", "remaining_time": "1:31:44"}
{"current_steps": 320, "total_steps": 3358, "loss": 0.6014, "lr": 9.88986726818129e-06, "epoch": 0.0953090096798213, "percentage": 9.53, "elapsed_time": "0:09:30", "remaining_time": "1:30:16"}
{"current_steps": 340, "total_steps": 3358, "loss": 0.5873, "lr": 9.868825323131646e-06, "epoch": 0.10126582278481013, "percentage": 10.13, "elapsed_time": "0:10:01", "remaining_time": "1:28:57"}
{"current_steps": 360, "total_steps": 3358, "loss": 0.5876, "lr": 9.8459714750797e-06, "epoch": 0.10722263588979895, "percentage": 10.72, "elapsed_time": "0:10:30", "remaining_time": "1:27:29"}
{"current_steps": 380, "total_steps": 3358, "loss": 0.5954, "lr": 9.821314228942587e-06, "epoch": 0.11317944899478778, "percentage": 11.32, "elapsed_time": "0:11:00", "remaining_time": "1:26:13"}
{"current_steps": 400, "total_steps": 3358, "loss": 0.5862, "lr": 9.794862760760798e-06, "epoch": 0.11913626209977662, "percentage": 11.91, "elapsed_time": "0:11:30", "remaining_time": "1:25:03"}
{"current_steps": 420, "total_steps": 3358, "loss": 0.59, "lr": 9.76662691428337e-06, "epoch": 0.12509307520476545, "percentage": 12.51, "elapsed_time": "0:11:59", "remaining_time": "1:23:53"}
{"current_steps": 440, "total_steps": 3358, "loss": 0.5793, "lr": 9.736617197304615e-06, "epoch": 0.13104988830975428, "percentage": 13.1, "elapsed_time": "0:12:30", "remaining_time": "1:22:59"}
{"current_steps": 460, "total_steps": 3358, "loss": 0.5744, "lr": 9.704844777753686e-06, "epoch": 0.1370067014147431, "percentage": 13.7, "elapsed_time": "0:13:02", "remaining_time": "1:22:11"}
{"current_steps": 480, "total_steps": 3358, "loss": 0.5753, "lr": 9.671321479538522e-06, "epoch": 0.14296351451973194, "percentage": 14.29, "elapsed_time": "0:13:35", "remaining_time": "1:21:29"}
{"current_steps": 500, "total_steps": 3358, "loss": 0.5722, "lr": 9.63605977814564e-06, "epoch": 0.14892032762472077, "percentage": 14.89, "elapsed_time": "0:14:03", "remaining_time": "1:20:23"}
{"current_steps": 520, "total_steps": 3358, "loss": 0.5707, "lr": 9.59907279599747e-06, "epoch": 0.1548771407297096, "percentage": 15.49, "elapsed_time": "0:14:34", "remaining_time": "1:19:33"}
{"current_steps": 540, "total_steps": 3358, "loss": 0.5659, "lr": 9.56037429756892e-06, "epoch": 0.16083395383469842, "percentage": 16.08, "elapsed_time": "0:15:07", "remaining_time": "1:18:57"}
{"current_steps": 560, "total_steps": 3358, "loss": 0.5774, "lr": 9.51997868426502e-06, "epoch": 0.16679076693968728, "percentage": 16.68, "elapsed_time": "0:15:40", "remaining_time": "1:18:20"}
{"current_steps": 580, "total_steps": 3358, "loss": 0.5743, "lr": 9.477900989061519e-06, "epoch": 0.1727475800446761, "percentage": 17.27, "elapsed_time": "0:16:09", "remaining_time": "1:17:23"}
{"current_steps": 600, "total_steps": 3358, "loss": 0.5691, "lr": 9.43415687091047e-06, "epoch": 0.17870439314966494, "percentage": 17.87, "elapsed_time": "0:16:39", "remaining_time": "1:16:34"}
{"current_steps": 620, "total_steps": 3358, "loss": 0.5652, "lr": 9.388762608912834e-06, "epoch": 0.18466120625465376, "percentage": 18.46, "elapsed_time": "0:17:09", "remaining_time": "1:15:44"}
{"current_steps": 640, "total_steps": 3358, "loss": 0.5702, "lr": 9.341735096260326e-06, "epoch": 0.1906180193596426, "percentage": 19.06, "elapsed_time": "0:17:39", "remaining_time": "1:15:01"}
{"current_steps": 660, "total_steps": 3358, "loss": 0.5688, "lr": 9.293091833948709e-06, "epoch": 0.19657483246463142, "percentage": 19.65, "elapsed_time": "0:18:10", "remaining_time": "1:14:18"}
{"current_steps": 680, "total_steps": 3358, "loss": 0.5628, "lr": 9.242850924264918e-06, "epoch": 0.20253164556962025, "percentage": 20.25, "elapsed_time": "0:18:40", "remaining_time": "1:13:31"}
{"current_steps": 700, "total_steps": 3358, "loss": 0.555, "lr": 9.191031064050396e-06, "epoch": 0.20848845867460908, "percentage": 20.85, "elapsed_time": "0:19:09", "remaining_time": "1:12:43"}
{"current_steps": 720, "total_steps": 3358, "loss": 0.5591, "lr": 9.137651537743193e-06, "epoch": 0.2144452717795979, "percentage": 21.44, "elapsed_time": "0:19:38", "remaining_time": "1:11:57"}
{"current_steps": 740, "total_steps": 3358, "loss": 0.5601, "lr": 9.082732210201371e-06, "epoch": 0.22040208488458674, "percentage": 22.04, "elapsed_time": "0:20:09", "remaining_time": "1:11:19"}
{"current_steps": 760, "total_steps": 3358, "loss": 0.5569, "lr": 9.026293519310426e-06, "epoch": 0.22635889798957556, "percentage": 22.63, "elapsed_time": "0:20:38", "remaining_time": "1:10:33"}
{"current_steps": 780, "total_steps": 3358, "loss": 0.5493, "lr": 8.968356468377454e-06, "epoch": 0.23231571109456442, "percentage": 23.23, "elapsed_time": "0:21:07", "remaining_time": "1:09:49"}
{"current_steps": 800, "total_steps": 3358, "loss": 0.5531, "lr": 8.908942618314912e-06, "epoch": 0.23827252419955325, "percentage": 23.82, "elapsed_time": "0:21:37", "remaining_time": "1:09:08"}
{"current_steps": 820, "total_steps": 3358, "loss": 0.5523, "lr": 8.848074079616838e-06, "epoch": 0.24422933730454208, "percentage": 24.42, "elapsed_time": "0:22:06", "remaining_time": "1:08:25"}
{"current_steps": 840, "total_steps": 3358, "loss": 0.5493, "lr": 8.785773504130587e-06, "epoch": 0.2501861504095309, "percentage": 25.01, "elapsed_time": "0:22:36", "remaining_time": "1:07:44"}
{"current_steps": 860, "total_steps": 3358, "loss": 0.5568, "lr": 8.722064076627082e-06, "epoch": 0.2561429635145197, "percentage": 25.61, "elapsed_time": "0:23:04", "remaining_time": "1:07:01"}
{"current_steps": 880, "total_steps": 3358, "loss": 0.5494, "lr": 8.65696950617274e-06, "epoch": 0.26209977661950856, "percentage": 26.21, "elapsed_time": "0:23:32", "remaining_time": "1:06:18"}
{"current_steps": 900, "total_steps": 3358, "loss": 0.5572, "lr": 8.590514017306298e-06, "epoch": 0.2680565897244974, "percentage": 26.8, "elapsed_time": "0:24:03", "remaining_time": "1:05:41"}
{"current_steps": 920, "total_steps": 3358, "loss": 0.548, "lr": 8.522722341023795e-06, "epoch": 0.2740134028294862, "percentage": 27.4, "elapsed_time": "0:24:33", "remaining_time": "1:05:04"}
{"current_steps": 940, "total_steps": 3358, "loss": 0.5441, "lr": 8.453619705575096e-06, "epoch": 0.2799702159344751, "percentage": 27.99, "elapsed_time": "0:25:01", "remaining_time": "1:04:22"}
{"current_steps": 960, "total_steps": 3358, "loss": 0.5552, "lr": 8.38323182707535e-06, "epoch": 0.2859270290394639, "percentage": 28.59, "elapsed_time": "0:25:33", "remaining_time": "1:03:51"}
{"current_steps": 980, "total_steps": 3358, "loss": 0.5427, "lr": 8.31158489993489e-06, "epoch": 0.29188384214445273, "percentage": 29.18, "elapsed_time": "0:26:04", "remaining_time": "1:03:15"}
{"current_steps": 1000, "total_steps": 3358, "loss": 0.5522, "lr": 8.238705587111162e-06, "epoch": 0.29784065524944153, "percentage": 29.78, "elapsed_time": "0:26:33", "remaining_time": "1:02:36"}
{"current_steps": 1020, "total_steps": 3358, "loss": 0.546, "lr": 8.16462101018626e-06, "epoch": 0.3037974683544304, "percentage": 30.38, "elapsed_time": "0:27:02", "remaining_time": "1:01:59"}
{"current_steps": 1040, "total_steps": 3358, "loss": 0.5428, "lr": 8.089358739273806e-06, "epoch": 0.3097542814594192, "percentage": 30.97, "elapsed_time": "0:27:30", "remaining_time": "1:01:17"}
{"current_steps": 1060, "total_steps": 3358, "loss": 0.5423, "lr": 8.0129467827589e-06, "epoch": 0.31571109456440805, "percentage": 31.57, "elapsed_time": "0:27:59", "remaining_time": "1:00:42"}
{"current_steps": 1080, "total_steps": 3358, "loss": 0.5479, "lr": 7.935413576874966e-06, "epoch": 0.32166790766939685, "percentage": 32.16, "elapsed_time": "0:28:27", "remaining_time": "1:00:02"}
{"current_steps": 1100, "total_steps": 3358, "loss": 0.5487, "lr": 7.856787975121407e-06, "epoch": 0.3276247207743857, "percentage": 32.76, "elapsed_time": "0:28:58", "remaining_time": "0:59:28"}
{"current_steps": 1120, "total_steps": 3358, "loss": 0.5365, "lr": 7.777099237525929e-06, "epoch": 0.33358153387937456, "percentage": 33.35, "elapsed_time": "0:29:27", "remaining_time": "0:58:51"}
{"current_steps": 1140, "total_steps": 3358, "loss": 0.5364, "lr": 7.696377019755624e-06, "epoch": 0.33953834698436336, "percentage": 33.95, "elapsed_time": "0:29:57", "remaining_time": "0:58:17"}
{"current_steps": 1160, "total_steps": 3358, "loss": 0.5398, "lr": 7.614651362080787e-06, "epoch": 0.3454951600893522, "percentage": 34.54, "elapsed_time": "0:30:27", "remaining_time": "0:57:42"}
{"current_steps": 1180, "total_steps": 3358, "loss": 0.5438, "lr": 7.531952678195621e-06, "epoch": 0.351451973194341, "percentage": 35.14, "elapsed_time": "0:30:55", "remaining_time": "0:57:05"}
{"current_steps": 1200, "total_steps": 3358, "loss": 0.5501, "lr": 7.4483117438999685e-06, "epoch": 0.3574087862993299, "percentage": 35.74, "elapsed_time": "0:31:24", "remaining_time": "0:56:28"}
{"current_steps": 1220, "total_steps": 3358, "loss": 0.5488, "lr": 7.3637596856462945e-06, "epoch": 0.3633655994043187, "percentage": 36.33, "elapsed_time": "0:31:51", "remaining_time": "0:55:50"}
{"current_steps": 1240, "total_steps": 3358, "loss": 0.5365, "lr": 7.278327968956159e-06, "epoch": 0.36932241250930753, "percentage": 36.93, "elapsed_time": "0:32:21", "remaining_time": "0:55:16"}
{"current_steps": 1260, "total_steps": 3358, "loss": 0.5403, "lr": 7.192048386710537e-06, "epoch": 0.37527922561429633, "percentage": 37.52, "elapsed_time": "0:32:50", "remaining_time": "0:54:41"}
{"current_steps": 1280, "total_steps": 3358, "loss": 0.5466, "lr": 7.10495304731828e-06, "epoch": 0.3812360387192852, "percentage": 38.12, "elapsed_time": "0:33:20", "remaining_time": "0:54:08"}
{"current_steps": 1300, "total_steps": 3358, "loss": 0.5393, "lr": 7.017074362767176e-06, "epoch": 0.387192851824274, "percentage": 38.71, "elapsed_time": "0:33:49", "remaining_time": "0:53:32"}
{"current_steps": 1320, "total_steps": 3358, "loss": 0.5365, "lr": 6.9284450365620385e-06, "epoch": 0.39314966492926284, "percentage": 39.31, "elapsed_time": "0:34:17", "remaining_time": "0:52:56"}
{"current_steps": 1340, "total_steps": 3358, "loss": 0.5467, "lr": 6.83909805155429e-06, "epoch": 0.3991064780342517, "percentage": 39.9, "elapsed_time": "0:34:46", "remaining_time": "0:52:22"}
{"current_steps": 1360, "total_steps": 3358, "loss": 0.5395, "lr": 6.749066657667609e-06, "epoch": 0.4050632911392405, "percentage": 40.5, "elapsed_time": "0:35:16", "remaining_time": "0:51:49"}
{"current_steps": 1380, "total_steps": 3358, "loss": 0.5331, "lr": 6.658384359524166e-06, "epoch": 0.41102010424422936, "percentage": 41.1, "elapsed_time": "0:35:45", "remaining_time": "0:51:15"}
{"current_steps": 1400, "total_steps": 3358, "loss": 0.5371, "lr": 6.5670849039761e-06, "epoch": 0.41697691734921816, "percentage": 41.69, "elapsed_time": "0:36:13", "remaining_time": "0:50:40"}
{"current_steps": 1420, "total_steps": 3358, "loss": 0.5372, "lr": 6.475202267546829e-06, "epoch": 0.422933730454207, "percentage": 42.29, "elapsed_time": "0:36:42", "remaining_time": "0:50:05"}
{"current_steps": 1440, "total_steps": 3358, "loss": 0.531, "lr": 6.382770643786907e-06, "epoch": 0.4288905435591958, "percentage": 42.88, "elapsed_time": "0:37:11", "remaining_time": "0:49:32"}
{"current_steps": 1460, "total_steps": 3358, "loss": 0.5394, "lr": 6.289824430549092e-06, "epoch": 0.43484735666418467, "percentage": 43.48, "elapsed_time": "0:37:39", "remaining_time": "0:48:57"}
{"current_steps": 1480, "total_steps": 3358, "loss": 0.5368, "lr": 6.196398217187418e-06, "epoch": 0.44080416976917347, "percentage": 44.07, "elapsed_time": "0:38:07", "remaining_time": "0:48:22"}
{"current_steps": 1500, "total_steps": 3358, "loss": 0.5313, "lr": 6.102526771684971e-06, "epoch": 0.4467609828741623, "percentage": 44.67, "elapsed_time": "0:38:36", "remaining_time": "0:47:49"}
{"current_steps": 1520, "total_steps": 3358, "loss": 0.5398, "lr": 6.008245027715205e-06, "epoch": 0.4527177959791511, "percentage": 45.27, "elapsed_time": "0:39:04", "remaining_time": "0:47:14"}
{"current_steps": 1540, "total_steps": 3358, "loss": 0.5448, "lr": 5.9135880716415885e-06, "epoch": 0.45867460908414, "percentage": 45.86, "elapsed_time": "0:39:34", "remaining_time": "0:46:43"}
{"current_steps": 1560, "total_steps": 3358, "loss": 0.5287, "lr": 5.818591129460437e-06, "epoch": 0.46463142218912884, "percentage": 46.46, "elapsed_time": "0:40:02", "remaining_time": "0:46:09"}
{"current_steps": 1580, "total_steps": 3358, "loss": 0.5299, "lr": 5.723289553691782e-06, "epoch": 0.47058823529411764, "percentage": 47.05, "elapsed_time": "0:40:32", "remaining_time": "0:45:37"}
{"current_steps": 1600, "total_steps": 3358, "loss": 0.5395, "lr": 5.6277188102231396e-06, "epoch": 0.4765450483991065, "percentage": 47.65, "elapsed_time": "0:41:03", "remaining_time": "0:45:06"}
{"current_steps": 1620, "total_steps": 3358, "loss": 0.5463, "lr": 5.531914465111109e-06, "epoch": 0.4825018615040953, "percentage": 48.24, "elapsed_time": "0:41:32", "remaining_time": "0:44:33"}
{"current_steps": 1640, "total_steps": 3358, "loss": 0.5333, "lr": 5.435912171345691e-06, "epoch": 0.48845867460908415, "percentage": 48.84, "elapsed_time": "0:42:01", "remaining_time": "0:44:00"}
{"current_steps": 1660, "total_steps": 3358, "loss": 0.5355, "lr": 5.3397476555822365e-06, "epoch": 0.49441548771407295, "percentage": 49.43, "elapsed_time": "0:42:29", "remaining_time": "0:43:27"}
{"current_steps": 1680, "total_steps": 3358, "loss": 0.5307, "lr": 5.243456704846011e-06, "epoch": 0.5003723008190618, "percentage": 50.03, "elapsed_time": "0:42:57", "remaining_time": "0:42:54"}
{"current_steps": 1700, "total_steps": 3358, "loss": 0.5366, "lr": 5.147075153214256e-06, "epoch": 0.5063291139240507, "percentage": 50.63, "elapsed_time": "0:43:27", "remaining_time": "0:42:22"}
{"current_steps": 1720, "total_steps": 3358, "loss": 0.5339, "lr": 5.0506388684807805e-06, "epoch": 0.5122859270290394, "percentage": 51.22, "elapsed_time": "0:43:55", "remaining_time": "0:41:49"}
{"current_steps": 1740, "total_steps": 3358, "loss": 0.5396, "lr": 4.954183738807972e-06, "epoch": 0.5182427401340283, "percentage": 51.82, "elapsed_time": "0:44:25", "remaining_time": "0:41:18"}
{"current_steps": 1760, "total_steps": 3358, "loss": 0.5306, "lr": 4.857745659371249e-06, "epoch": 0.5241995532390171, "percentage": 52.41, "elapsed_time": "0:44:53", "remaining_time": "0:40:45"}
{"current_steps": 1780, "total_steps": 3358, "loss": 0.5278, "lr": 4.761360519000884e-06, "epoch": 0.530156366344006, "percentage": 53.01, "elapsed_time": "0:45:21", "remaining_time": "0:40:12"}
{"current_steps": 1800, "total_steps": 3358, "loss": 0.5286, "lr": 4.665064186826211e-06, "epoch": 0.5361131794489948, "percentage": 53.6, "elapsed_time": "0:45:51", "remaining_time": "0:39:41"}
{"current_steps": 1820, "total_steps": 3358, "loss": 0.5314, "lr": 4.568892498927148e-06, "epoch": 0.5420699925539836, "percentage": 54.2, "elapsed_time": "0:46:20", "remaining_time": "0:39:09"}
{"current_steps": 1840, "total_steps": 3358, "loss": 0.5276, "lr": 4.47288124499802e-06, "epoch": 0.5480268056589724, "percentage": 54.79, "elapsed_time": "0:46:50", "remaining_time": "0:38:38"}
{"current_steps": 1860, "total_steps": 3358, "loss": 0.525, "lr": 4.3770661550286485e-06, "epoch": 0.5539836187639613, "percentage": 55.39, "elapsed_time": "0:47:18", "remaining_time": "0:38:06"}
{"current_steps": 1880, "total_steps": 3358, "loss": 0.5334, "lr": 4.281482886007665e-06, "epoch": 0.5599404318689502, "percentage": 55.99, "elapsed_time": "0:47:47", "remaining_time": "0:37:34"}
{"current_steps": 1900, "total_steps": 3358, "loss": 0.5292, "lr": 4.186167008652975e-06, "epoch": 0.5658972449739389, "percentage": 56.58, "elapsed_time": "0:48:17", "remaining_time": "0:37:03"}
{"current_steps": 1920, "total_steps": 3358, "loss": 0.532, "lr": 4.091153994174343e-06, "epoch": 0.5718540580789278, "percentage": 57.18, "elapsed_time": "0:48:46", "remaining_time": "0:36:31"}
{"current_steps": 1940, "total_steps": 3358, "loss": 0.5238, "lr": 3.996479201073005e-06, "epoch": 0.5778108711839166, "percentage": 57.77, "elapsed_time": "0:49:14", "remaining_time": "0:35:59"}
{"current_steps": 1960, "total_steps": 3358, "loss": 0.527, "lr": 3.902177861983213e-06, "epoch": 0.5837676842889055, "percentage": 58.37, "elapsed_time": "0:49:43", "remaining_time": "0:35:28"}
{"current_steps": 1980, "total_steps": 3358, "loss": 0.5307, "lr": 3.8082850705606387e-06, "epoch": 0.5897244973938943, "percentage": 58.96, "elapsed_time": "0:50:11", "remaining_time": "0:34:55"}
{"current_steps": 2000, "total_steps": 3358, "loss": 0.5349, "lr": 3.7148357684224887e-06, "epoch": 0.5956813104988831, "percentage": 59.56, "elapsed_time": "0:50:39", "remaining_time": "0:34:23"}
{"current_steps": 2020, "total_steps": 3358, "loss": 0.5271, "lr": 3.6218647321441934e-06, "epoch": 0.6016381236038719, "percentage": 60.15, "elapsed_time": "0:51:07", "remaining_time": "0:33:51"}
{"current_steps": 2040, "total_steps": 3358, "loss": 0.5299, "lr": 3.529406560317521e-06, "epoch": 0.6075949367088608, "percentage": 60.75, "elapsed_time": "0:51:35", "remaining_time": "0:33:20"}
{"current_steps": 2060, "total_steps": 3358, "loss": 0.5258, "lr": 3.4374956606749337e-06, "epoch": 0.6135517498138496, "percentage": 61.35, "elapsed_time": "0:52:03", "remaining_time": "0:32:48"}
{"current_steps": 2080, "total_steps": 3358, "loss": 0.5212, "lr": 3.3461662372849635e-06, "epoch": 0.6195085629188384, "percentage": 61.94, "elapsed_time": "0:52:32", "remaining_time": "0:32:16"}
{"current_steps": 2100, "total_steps": 3358, "loss": 0.5329, "lr": 3.25545227782337e-06, "epoch": 0.6254653760238272, "percentage": 62.54, "elapsed_time": "0:53:01", "remaining_time": "0:31:45"}
{"current_steps": 2120, "total_steps": 3358, "loss": 0.525, "lr": 3.1653875409248557e-06, "epoch": 0.6314221891288161, "percentage": 63.13, "elapsed_time": "0:53:28", "remaining_time": "0:31:13"}
{"current_steps": 2140, "total_steps": 3358, "loss": 0.5252, "lr": 3.07600554361999e-06, "epoch": 0.637379002233805, "percentage": 63.73, "elapsed_time": "0:53:57", "remaining_time": "0:30:42"}
{"current_steps": 2160, "total_steps": 3358, "loss": 0.5301, "lr": 2.987339548862054e-06, "epoch": 0.6433358153387937, "percentage": 64.32, "elapsed_time": "0:54:25", "remaining_time": "0:30:11"}
{"current_steps": 2180, "total_steps": 3358, "loss": 0.5287, "lr": 2.8994225531484456e-06, "epoch": 0.6492926284437825, "percentage": 64.92, "elapsed_time": "0:54:54", "remaining_time": "0:29:40"}
{"current_steps": 2200, "total_steps": 3358, "loss": 0.5243, "lr": 2.812287274241238e-06, "epoch": 0.6552494415487714, "percentage": 65.52, "elapsed_time": "0:55:23", "remaining_time": "0:29:09"}
{"current_steps": 2220, "total_steps": 3358, "loss": 0.5284, "lr": 2.7259661389914597e-06, "epoch": 0.6612062546537603, "percentage": 66.11, "elapsed_time": "0:55:52", "remaining_time": "0:28:38"}
{"current_steps": 2240, "total_steps": 3358, "loss": 0.5285, "lr": 2.6404912712716585e-06, "epoch": 0.6671630677587491, "percentage": 66.71, "elapsed_time": "0:56:20", "remaining_time": "0:28:07"}
{"current_steps": 2260, "total_steps": 3358, "loss": 0.529, "lr": 2.5558944800211892e-06, "epoch": 0.6731198808637379, "percentage": 67.3, "elapsed_time": "0:56:49", "remaining_time": "0:27:36"}
{"current_steps": 2280, "total_steps": 3358, "loss": 0.5312, "lr": 2.472207247408727e-06, "epoch": 0.6790766939687267, "percentage": 67.9, "elapsed_time": "0:57:17", "remaining_time": "0:27:05"}
{"current_steps": 2300, "total_steps": 3358, "loss": 0.5238, "lr": 2.389460717116358e-06, "epoch": 0.6850335070737156, "percentage": 68.49, "elapsed_time": "0:57:45", "remaining_time": "0:26:34"}
{"current_steps": 2320, "total_steps": 3358, "loss": 0.5247, "lr": 2.30768568274967e-06, "epoch": 0.6909903201787044, "percentage": 69.09, "elapsed_time": "0:58:15", "remaining_time": "0:26:03"}
{"current_steps": 2340, "total_steps": 3358, "loss": 0.5194, "lr": 2.2269125763780974e-06, "epoch": 0.6969471332836932, "percentage": 69.68, "elapsed_time": "0:58:44", "remaining_time": "0:25:33"}
{"current_steps": 2360, "total_steps": 3358, "loss": 0.5211, "lr": 2.147171457209807e-06, "epoch": 0.702903946388682, "percentage": 70.28, "elapsed_time": "0:59:13", "remaining_time": "0:25:02"}
{"current_steps": 2380, "total_steps": 3358, "loss": 0.5204, "lr": 2.0684920004053666e-06, "epoch": 0.7088607594936709, "percentage": 70.88, "elapsed_time": "0:59:41", "remaining_time": "0:24:31"}
{"current_steps": 2400, "total_steps": 3358, "loss": 0.5273, "lr": 1.990903486034308e-06, "epoch": 0.7148175725986597, "percentage": 71.47, "elapsed_time": "1:00:10", "remaining_time": "0:24:01"}
{"current_steps": 2420, "total_steps": 3358, "loss": 0.5263, "lr": 1.914434788178737e-06, "epoch": 0.7207743857036486, "percentage": 72.07, "elapsed_time": "1:00:38", "remaining_time": "0:23:30"}
{"current_steps": 2440, "total_steps": 3358, "loss": 0.5177, "lr": 1.8391143641880188e-06, "epoch": 0.7267311988086373, "percentage": 72.66, "elapsed_time": "1:01:07", "remaining_time": "0:22:59"}
{"current_steps": 2460, "total_steps": 3358, "loss": 0.5269, "lr": 1.7649702440885597e-06, "epoch": 0.7326880119136262, "percentage": 73.26, "elapsed_time": "1:01:36", "remaining_time": "0:22:29"}
{"current_steps": 2480, "total_steps": 3358, "loss": 0.5285, "lr": 1.692030020152598e-06, "epoch": 0.7386448250186151, "percentage": 73.85, "elapsed_time": "1:02:05", "remaining_time": "0:21:58"}
{"current_steps": 2500, "total_steps": 3358, "loss": 0.5314, "lr": 1.6203208366299216e-06, "epoch": 0.7446016381236039, "percentage": 74.45, "elapsed_time": "1:02:33", "remaining_time": "0:21:28"}
{"current_steps": 2520, "total_steps": 3358, "loss": 0.527, "lr": 1.5498693796462994e-06, "epoch": 0.7505584512285927, "percentage": 75.04, "elapsed_time": "1:03:01", "remaining_time": "0:20:57"}
{"current_steps": 2540, "total_steps": 3358, "loss": 0.5201, "lr": 1.4807018672724066e-06, "epoch": 0.7565152643335815, "percentage": 75.64, "elapsed_time": "1:03:30", "remaining_time": "0:20:27"}
{"current_steps": 2560, "total_steps": 3358, "loss": 0.5211, "lr": 1.4128440397669301e-06, "epoch": 0.7624720774385704, "percentage": 76.24, "elapsed_time": "1:03:59", "remaining_time": "0:19:56"}
{"current_steps": 2580, "total_steps": 3358, "loss": 0.5228, "lr": 1.3463211499974993e-06, "epoch": 0.7684288905435592, "percentage": 76.83, "elapsed_time": "1:04:28", "remaining_time": "0:19:26"}
{"current_steps": 2600, "total_steps": 3358, "loss": 0.5263, "lr": 1.2811579540429836e-06, "epoch": 0.774385703648548, "percentage": 77.43, "elapsed_time": "1:04:56", "remaining_time": "0:18:56"}
{"current_steps": 2620, "total_steps": 3358, "loss": 0.5218, "lr": 1.2173787019806688e-06, "epoch": 0.7803425167535368, "percentage": 78.02, "elapsed_time": "1:05:25", "remaining_time": "0:18:25"}
{"current_steps": 2640, "total_steps": 3358, "loss": 0.5247, "lr": 1.1550071288617486e-06, "epoch": 0.7862993298585257, "percentage": 78.62, "elapsed_time": "1:05:54", "remaining_time": "0:17:55"}
{"current_steps": 2660, "total_steps": 3358, "loss": 0.5215, "lr": 1.0940664458784733e-06, "epoch": 0.7922561429635145, "percentage": 79.21, "elapsed_time": "1:06:22", "remaining_time": "0:17:25"}
{"current_steps": 2680, "total_steps": 3358, "loss": 0.5207, "lr": 1.0345793317262387e-06, "epoch": 0.7982129560685034, "percentage": 79.81, "elapsed_time": "1:06:51", "remaining_time": "0:16:54"}
{"current_steps": 2700, "total_steps": 3358, "loss": 0.5301, "lr": 9.765679241638649e-07, "epoch": 0.8041697691734921, "percentage": 80.41, "elapsed_time": "1:07:19", "remaining_time": "0:16:24"}
{"current_steps": 2720, "total_steps": 3358, "loss": 0.5316, "lr": 9.200538117751595e-07, "epoch": 0.810126582278481, "percentage": 81.0, "elapsed_time": "1:07:48", "remaining_time": "0:15:54"}
{"current_steps": 2740, "total_steps": 3358, "loss": 0.5307, "lr": 8.650580259348595e-07, "epoch": 0.8160833953834699, "percentage": 81.6, "elapsed_time": "1:08:16", "remaining_time": "0:15:24"}
{"current_steps": 2760, "total_steps": 3358, "loss": 0.5274, "lr": 8.116010329819418e-07, "epoch": 0.8220402084884587, "percentage": 82.19, "elapsed_time": "1:08:45", "remaining_time": "0:14:53"}
{"current_steps": 2780, "total_steps": 3358, "loss": 0.5223, "lr": 7.597027266031992e-07, "epoch": 0.8279970215934475, "percentage": 82.79, "elapsed_time": "1:09:14", "remaining_time": "0:14:23"}
{"current_steps": 2800, "total_steps": 3358, "loss": 0.5226, "lr": 7.093824204299299e-07, "epoch": 0.8339538346984363, "percentage": 83.38, "elapsed_time": "1:09:43", "remaining_time": "0:13:53"}
{"current_steps": 2820, "total_steps": 3358, "loss": 0.5367, "lr": 6.60658840850486e-07, "epoch": 0.8399106478034252, "percentage": 83.98, "elapsed_time": "1:10:13", "remaining_time": "0:13:23"}
{"current_steps": 2840, "total_steps": 3358, "loss": 0.5215, "lr": 6.135501200413724e-07, "epoch": 0.845867460908414, "percentage": 84.57, "elapsed_time": "1:10:40", "remaining_time": "0:12:53"}
{"current_steps": 2860, "total_steps": 3358, "loss": 0.5271, "lr": 5.680737892194654e-07, "epoch": 0.8518242740134029, "percentage": 85.17, "elapsed_time": "1:11:09", "remaining_time": "0:12:23"}
{"current_steps": 2880, "total_steps": 3358, "loss": 0.526, "lr": 5.242467721178774e-07, "epoch": 0.8577810871183916, "percentage": 85.77, "elapsed_time": "1:11:37", "remaining_time": "0:11:53"}
{"current_steps": 2900, "total_steps": 3358, "loss": 0.5198, "lr": 4.82085378687901e-07, "epoch": 0.8637379002233805, "percentage": 86.36, "elapsed_time": "1:12:08", "remaining_time": "0:11:23"}
{"current_steps": 2920, "total_steps": 3358, "loss": 0.5207, "lr": 4.416052990293596e-07, "epoch": 0.8696947133283693, "percentage": 86.96, "elapsed_time": "1:12:38", "remaining_time": "0:10:53"}
{"current_steps": 2940, "total_steps": 3358, "loss": 0.5262, "lr": 4.028215975516314e-07, "epoch": 0.8756515264333582, "percentage": 87.55, "elapsed_time": "1:13:07", "remaining_time": "0:10:23"}
{"current_steps": 2960, "total_steps": 3358, "loss": 0.5346, "lr": 3.657487073675281e-07, "epoch": 0.8816083395383469, "percentage": 88.15, "elapsed_time": "1:13:35", "remaining_time": "0:09:53"}
{"current_steps": 2980, "total_steps": 3358, "loss": 0.5192, "lr": 3.3040042492210103e-07, "epoch": 0.8875651526433358, "percentage": 88.74, "elapsed_time": "1:14:02", "remaining_time": "0:09:23"}
{"current_steps": 3000, "total_steps": 3358, "loss": 0.5343, "lr": 2.9678990485837553e-07, "epoch": 0.8935219657483247, "percentage": 89.34, "elapsed_time": "1:14:31", "remaining_time": "0:08:53"}
{"current_steps": 3020, "total_steps": 3358, "loss": 0.5279, "lr": 2.6492965512193934e-07, "epoch": 0.8994787788533135, "percentage": 89.93, "elapsed_time": "1:15:00", "remaining_time": "0:08:23"}
{"current_steps": 3040, "total_steps": 3358, "loss": 0.5392, "lr": 2.348315323061845e-07, "epoch": 0.9054355919583023, "percentage": 90.53, "elapsed_time": "1:15:28", "remaining_time": "0:07:53"}
{"current_steps": 3060, "total_steps": 3358, "loss": 0.5163, "lr": 2.0650673723995097e-07, "epoch": 0.9113924050632911, "percentage": 91.13, "elapsed_time": "1:15:56", "remaining_time": "0:07:23"}
{"current_steps": 3080, "total_steps": 3358, "loss": 0.521, "lr": 1.7996581081920483e-07, "epoch": 0.91734921816828, "percentage": 91.72, "elapsed_time": "1:16:25", "remaining_time": "0:06:53"}
{"current_steps": 3100, "total_steps": 3358, "loss": 0.5264, "lr": 1.5521863008431725e-07, "epoch": 0.9233060312732688, "percentage": 92.32, "elapsed_time": "1:16:53", "remaining_time": "0:06:24"}
{"current_steps": 3120, "total_steps": 3358, "loss": 0.5224, "lr": 1.3227440454437745e-07, "epoch": 0.9292628443782577, "percentage": 92.91, "elapsed_time": "1:17:22", "remaining_time": "0:05:54"}
{"current_steps": 3140, "total_steps": 3358, "loss": 0.5371, "lr": 1.1114167274993537e-07, "epoch": 0.9352196574832464, "percentage": 93.51, "elapsed_time": "1:17:51", "remaining_time": "0:05:24"}
{"current_steps": 3160, "total_steps": 3358, "loss": 0.5271, "lr": 9.1828299115434e-08, "epoch": 0.9411764705882353, "percentage": 94.1, "elapsed_time": "1:18:19", "remaining_time": "0:04:54"}
{"current_steps": 3180, "total_steps": 3358, "loss": 0.5235, "lr": 7.434147099251165e-08, "epoch": 0.9471332836932241, "percentage": 94.7, "elapsed_time": "1:18:47", "remaining_time": "0:04:24"}
{"current_steps": 3200, "total_steps": 3358, "loss": 0.5214, "lr": 5.86876959952809e-08, "epoch": 0.953090096798213, "percentage": 95.29, "elapsed_time": "1:19:16", "remaining_time": "0:03:54"}
{"current_steps": 3220, "total_steps": 3358, "loss": 0.5247, "lr": 4.4872799578554724e-08, "epoch": 0.9590469099032017, "percentage": 95.89, "elapsed_time": "1:19:44", "remaining_time": "0:03:25"}
{"current_steps": 3240, "total_steps": 3358, "loss": 0.5281, "lr": 3.290192286994287e-08, "epoch": 0.9650037230081906, "percentage": 96.49, "elapsed_time": "1:20:13", "remaining_time": "0:02:55"}
{"current_steps": 3260, "total_steps": 3358, "loss": 0.5166, "lr": 2.2779520756611163e-08, "epoch": 0.9709605361131795, "percentage": 97.08, "elapsed_time": "1:20:40", "remaining_time": "0:02:25"}
{"current_steps": 3280, "total_steps": 3358, "loss": 0.5329, "lr": 1.450936022742544e-08, "epoch": 0.9769173492181683, "percentage": 97.68, "elapsed_time": "1:21:08", "remaining_time": "0:01:55"}
{"current_steps": 3300, "total_steps": 3358, "loss": 0.5281, "lr": 8.094518971088484e-09, "epoch": 0.9828741623231572, "percentage": 98.27, "elapsed_time": "1:21:36", "remaining_time": "0:01:26"}
{"current_steps": 3320, "total_steps": 3358, "loss": 0.523, "lr": 3.537384230797303e-09, "epoch": 0.9888309754281459, "percentage": 98.87, "elapsed_time": "1:22:04", "remaining_time": "0:00:56"}
{"current_steps": 3340, "total_steps": 3358, "loss": 0.5215, "lr": 8.396519158465621e-10, "epoch": 0.9947877885331348, "percentage": 99.46, "elapsed_time": "1:22:33", "remaining_time": "0:00:26"}
{"current_steps": 3358, "total_steps": 3358, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:23:07", "remaining_time": "0:00:00"}

1212
trainer_state.json Normal file

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:09b3778b33c4d4522f8099a9b3df897b49917aefff2b3f84f67ad5be216ca415
size 8017

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 35 KiB

1
vocab.json Normal file

File diff suppressed because one or more lines are too long