Upload folder using huggingface_hub
Browse files- README.md +56 -0
- added_tokens.json +7 -0
- config.json +25 -0
- generation_config.json +5 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- train_results.json +8 -0
- trainer_state.json +928 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: deepset/gbert-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: gbert_base_pubmed_mimic_translated_german_512_4_epochs_multip
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# gbert_base_pubmed_mimic_translated_german_512_4_epochs_multip
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [deepset/gbert-base](https://huggingface.co/deepset/gbert-base) on the None dataset.
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 56
|
| 37 |
+
- eval_batch_size: 8
|
| 38 |
+
- seed: 42
|
| 39 |
+
- distributed_type: multi-GPU
|
| 40 |
+
- num_devices: 5
|
| 41 |
+
- total_train_batch_size: 280
|
| 42 |
+
- total_eval_batch_size: 40
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 4.0
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
### Framework versions
|
| 52 |
+
|
| 53 |
+
- Transformers 4.34.0
|
| 54 |
+
- Pytorch 1.12.1.post200
|
| 55 |
+
- Datasets 2.14.5
|
| 56 |
+
- Tokenizers 0.14.0
|
added_tokens.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[CLS]": 102,
|
| 3 |
+
"[MASK]": 104,
|
| 4 |
+
"[PAD]": 0,
|
| 5 |
+
"[SEP]": 103,
|
| 6 |
+
"[UNK]": 101
|
| 7 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepset/gbert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.34.0",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 31102
|
| 25 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.34.0"
|
| 5 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1f2ce0c4c969f9b7391289b402cec6c6d238fd3a30238e698545c04036f780a
|
| 3 |
+
size 439908397
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"101": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"102": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"103": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"additional_special_tokens": [],
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"max_len": 512,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": false,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"train_loss": 0.9333500321268725,
|
| 4 |
+
"train_runtime": 60105.9393,
|
| 5 |
+
"train_samples": 5270167,
|
| 6 |
+
"train_samples_per_second": 350.725,
|
| 7 |
+
"train_steps_per_second": 1.253
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,928 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 75292,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 4.9669951654890296e-05,
|
| 14 |
+
"loss": 1.5966,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 4.933791106624874e-05,
|
| 20 |
+
"loss": 1.3931,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.08,
|
| 25 |
+
"learning_rate": 4.900587047760719e-05,
|
| 26 |
+
"loss": 1.3138,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.11,
|
| 31 |
+
"learning_rate": 4.8673829888965626e-05,
|
| 32 |
+
"loss": 1.2591,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.13,
|
| 37 |
+
"learning_rate": 4.834178930032408e-05,
|
| 38 |
+
"loss": 1.2239,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.16,
|
| 43 |
+
"learning_rate": 4.800974871168252e-05,
|
| 44 |
+
"loss": 1.1972,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.19,
|
| 49 |
+
"learning_rate": 4.767770812304096e-05,
|
| 50 |
+
"loss": 1.1682,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21,
|
| 55 |
+
"learning_rate": 4.734566753439941e-05,
|
| 56 |
+
"loss": 1.1505,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.24,
|
| 61 |
+
"learning_rate": 4.701362694575785e-05,
|
| 62 |
+
"loss": 1.1314,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.27,
|
| 67 |
+
"learning_rate": 4.66815863571163e-05,
|
| 68 |
+
"loss": 1.1163,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.29,
|
| 73 |
+
"learning_rate": 4.634954576847474e-05,
|
| 74 |
+
"loss": 1.1029,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.32,
|
| 79 |
+
"learning_rate": 4.6017505179833184e-05,
|
| 80 |
+
"loss": 1.0916,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.35,
|
| 85 |
+
"learning_rate": 4.568546459119163e-05,
|
| 86 |
+
"loss": 1.0832,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.37,
|
| 91 |
+
"learning_rate": 4.535342400255007e-05,
|
| 92 |
+
"loss": 1.0731,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4,
|
| 97 |
+
"learning_rate": 4.502138341390852e-05,
|
| 98 |
+
"loss": 1.0622,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.43,
|
| 103 |
+
"learning_rate": 4.468934282526696e-05,
|
| 104 |
+
"loss": 1.0573,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.45,
|
| 109 |
+
"learning_rate": 4.435796631780269e-05,
|
| 110 |
+
"loss": 1.049,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.48,
|
| 115 |
+
"learning_rate": 4.402592572916113e-05,
|
| 116 |
+
"loss": 1.042,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.5,
|
| 121 |
+
"learning_rate": 4.369388514051958e-05,
|
| 122 |
+
"loss": 1.0354,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.53,
|
| 127 |
+
"learning_rate": 4.3361844551878024e-05,
|
| 128 |
+
"loss": 1.0275,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.56,
|
| 133 |
+
"learning_rate": 4.302980396323647e-05,
|
| 134 |
+
"loss": 1.0232,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.58,
|
| 139 |
+
"learning_rate": 4.2697763374594915e-05,
|
| 140 |
+
"loss": 1.019,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.61,
|
| 145 |
+
"learning_rate": 4.2365722785953354e-05,
|
| 146 |
+
"loss": 1.0141,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.64,
|
| 151 |
+
"learning_rate": 4.20336821973118e-05,
|
| 152 |
+
"loss": 1.0089,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.66,
|
| 157 |
+
"learning_rate": 4.1701641608670245e-05,
|
| 158 |
+
"loss": 1.0028,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.69,
|
| 163 |
+
"learning_rate": 4.136960102002869e-05,
|
| 164 |
+
"loss": 0.9984,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.72,
|
| 169 |
+
"learning_rate": 4.103822451256442e-05,
|
| 170 |
+
"loss": 0.9936,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.74,
|
| 175 |
+
"learning_rate": 4.0706183923922865e-05,
|
| 176 |
+
"loss": 0.9914,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.77,
|
| 181 |
+
"learning_rate": 4.0374143335281303e-05,
|
| 182 |
+
"loss": 0.9851,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.8,
|
| 187 |
+
"learning_rate": 4.0042102746639756e-05,
|
| 188 |
+
"loss": 0.9828,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.82,
|
| 193 |
+
"learning_rate": 3.9710062157998195e-05,
|
| 194 |
+
"loss": 0.9813,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.85,
|
| 199 |
+
"learning_rate": 3.937868565053392e-05,
|
| 200 |
+
"loss": 0.976,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.88,
|
| 205 |
+
"learning_rate": 3.904664506189237e-05,
|
| 206 |
+
"loss": 0.9739,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.9,
|
| 211 |
+
"learning_rate": 3.871460447325081e-05,
|
| 212 |
+
"loss": 0.9719,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.93,
|
| 217 |
+
"learning_rate": 3.838256388460926e-05,
|
| 218 |
+
"loss": 0.9664,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.96,
|
| 223 |
+
"learning_rate": 3.805118737714499e-05,
|
| 224 |
+
"loss": 0.9642,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.98,
|
| 229 |
+
"learning_rate": 3.7719146788503427e-05,
|
| 230 |
+
"loss": 0.9603,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.01,
|
| 235 |
+
"learning_rate": 3.738710619986187e-05,
|
| 236 |
+
"loss": 0.9575,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.04,
|
| 241 |
+
"learning_rate": 3.705506561122032e-05,
|
| 242 |
+
"loss": 0.9539,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.06,
|
| 247 |
+
"learning_rate": 3.672302502257876e-05,
|
| 248 |
+
"loss": 0.9525,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.09,
|
| 253 |
+
"learning_rate": 3.639164851511449e-05,
|
| 254 |
+
"loss": 0.9518,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.12,
|
| 259 |
+
"learning_rate": 3.605960792647293e-05,
|
| 260 |
+
"loss": 0.9469,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.14,
|
| 265 |
+
"learning_rate": 3.572756733783138e-05,
|
| 266 |
+
"loss": 0.9466,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.17,
|
| 271 |
+
"learning_rate": 3.5396190830367104e-05,
|
| 272 |
+
"loss": 0.9435,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.2,
|
| 277 |
+
"learning_rate": 3.506481432290283e-05,
|
| 278 |
+
"loss": 0.9424,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.22,
|
| 283 |
+
"learning_rate": 3.473277373426128e-05,
|
| 284 |
+
"loss": 0.9373,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.25,
|
| 289 |
+
"learning_rate": 3.4400733145619723e-05,
|
| 290 |
+
"loss": 0.9374,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.28,
|
| 295 |
+
"learning_rate": 3.406869255697817e-05,
|
| 296 |
+
"loss": 0.934,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.3,
|
| 301 |
+
"learning_rate": 3.3736651968336615e-05,
|
| 302 |
+
"loss": 0.9335,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.33,
|
| 307 |
+
"learning_rate": 3.3404611379695053e-05,
|
| 308 |
+
"loss": 0.9324,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.35,
|
| 313 |
+
"learning_rate": 3.30725707910535e-05,
|
| 314 |
+
"loss": 0.9284,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.38,
|
| 319 |
+
"learning_rate": 3.2740530202411945e-05,
|
| 320 |
+
"loss": 0.9269,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.41,
|
| 325 |
+
"learning_rate": 3.240848961377039e-05,
|
| 326 |
+
"loss": 0.9257,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.43,
|
| 331 |
+
"learning_rate": 3.2076449025128836e-05,
|
| 332 |
+
"loss": 0.9203,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.46,
|
| 337 |
+
"learning_rate": 3.1744408436487275e-05,
|
| 338 |
+
"loss": 0.9233,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.49,
|
| 343 |
+
"learning_rate": 3.141236784784572e-05,
|
| 344 |
+
"loss": 0.9208,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.51,
|
| 349 |
+
"learning_rate": 3.1080327259204166e-05,
|
| 350 |
+
"loss": 0.919,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.54,
|
| 355 |
+
"learning_rate": 3.074828667056261e-05,
|
| 356 |
+
"loss": 0.9174,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.57,
|
| 361 |
+
"learning_rate": 3.0416246081921057e-05,
|
| 362 |
+
"loss": 0.9167,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.59,
|
| 367 |
+
"learning_rate": 3.00842054932795e-05,
|
| 368 |
+
"loss": 0.9138,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.62,
|
| 373 |
+
"learning_rate": 2.9752164904637948e-05,
|
| 374 |
+
"loss": 0.9133,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.65,
|
| 379 |
+
"learning_rate": 2.942078839717367e-05,
|
| 380 |
+
"loss": 0.9124,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.67,
|
| 385 |
+
"learning_rate": 2.908874780853212e-05,
|
| 386 |
+
"loss": 0.9107,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.7,
|
| 391 |
+
"learning_rate": 2.875670721989056e-05,
|
| 392 |
+
"loss": 0.9079,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.73,
|
| 397 |
+
"learning_rate": 2.842533071242629e-05,
|
| 398 |
+
"loss": 0.9069,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.75,
|
| 403 |
+
"learning_rate": 2.809329012378473e-05,
|
| 404 |
+
"loss": 0.9064,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.78,
|
| 409 |
+
"learning_rate": 2.7761249535143173e-05,
|
| 410 |
+
"loss": 0.9052,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.81,
|
| 415 |
+
"learning_rate": 2.7429208946501622e-05,
|
| 416 |
+
"loss": 0.9028,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.83,
|
| 421 |
+
"learning_rate": 2.7097168357860064e-05,
|
| 422 |
+
"loss": 0.9024,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.86,
|
| 427 |
+
"learning_rate": 2.6765127769218513e-05,
|
| 428 |
+
"loss": 0.9009,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.89,
|
| 433 |
+
"learning_rate": 2.6433087180576956e-05,
|
| 434 |
+
"loss": 0.9006,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.91,
|
| 439 |
+
"learning_rate": 2.61010465919354e-05,
|
| 440 |
+
"loss": 0.8988,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.94,
|
| 445 |
+
"learning_rate": 2.5769006003293843e-05,
|
| 446 |
+
"loss": 0.898,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.97,
|
| 451 |
+
"learning_rate": 2.5437629495829575e-05,
|
| 452 |
+
"loss": 0.8953,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.99,
|
| 457 |
+
"learning_rate": 2.5105588907188017e-05,
|
| 458 |
+
"loss": 0.8956,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.02,
|
| 463 |
+
"learning_rate": 2.477354831854646e-05,
|
| 464 |
+
"loss": 0.8945,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.05,
|
| 469 |
+
"learning_rate": 2.4441507729904905e-05,
|
| 470 |
+
"loss": 0.8926,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.07,
|
| 475 |
+
"learning_rate": 2.410946714126335e-05,
|
| 476 |
+
"loss": 0.8892,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.1,
|
| 481 |
+
"learning_rate": 2.3777426552621793e-05,
|
| 482 |
+
"loss": 0.8905,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.13,
|
| 487 |
+
"learning_rate": 2.3445385963980238e-05,
|
| 488 |
+
"loss": 0.8877,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.15,
|
| 493 |
+
"learning_rate": 2.3113345375338684e-05,
|
| 494 |
+
"loss": 0.8876,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.18,
|
| 499 |
+
"learning_rate": 2.2782632949051695e-05,
|
| 500 |
+
"loss": 0.8872,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.2,
|
| 505 |
+
"learning_rate": 2.245059236041014e-05,
|
| 506 |
+
"loss": 0.8855,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.23,
|
| 511 |
+
"learning_rate": 2.2118551771768582e-05,
|
| 512 |
+
"loss": 0.8839,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.26,
|
| 517 |
+
"learning_rate": 2.1786511183127025e-05,
|
| 518 |
+
"loss": 0.8853,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.28,
|
| 523 |
+
"learning_rate": 2.145447059448547e-05,
|
| 524 |
+
"loss": 0.8834,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.31,
|
| 529 |
+
"learning_rate": 2.1122430005843916e-05,
|
| 530 |
+
"loss": 0.8823,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.34,
|
| 535 |
+
"learning_rate": 2.0791053498379644e-05,
|
| 536 |
+
"loss": 0.8832,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.36,
|
| 541 |
+
"learning_rate": 2.0459012909738086e-05,
|
| 542 |
+
"loss": 0.8812,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.39,
|
| 547 |
+
"learning_rate": 2.0126972321096532e-05,
|
| 548 |
+
"loss": 0.8805,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.42,
|
| 553 |
+
"learning_rate": 1.9794931732454977e-05,
|
| 554 |
+
"loss": 0.8795,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.44,
|
| 559 |
+
"learning_rate": 1.9463555224990705e-05,
|
| 560 |
+
"loss": 0.8784,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.47,
|
| 565 |
+
"learning_rate": 1.913217871752643e-05,
|
| 566 |
+
"loss": 0.8777,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.5,
|
| 571 |
+
"learning_rate": 1.8800138128884876e-05,
|
| 572 |
+
"loss": 0.876,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.52,
|
| 577 |
+
"learning_rate": 1.846809754024332e-05,
|
| 578 |
+
"loss": 0.877,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.55,
|
| 583 |
+
"learning_rate": 1.8136056951601764e-05,
|
| 584 |
+
"loss": 0.876,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.58,
|
| 589 |
+
"learning_rate": 1.780401636296021e-05,
|
| 590 |
+
"loss": 0.8765,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.6,
|
| 595 |
+
"learning_rate": 1.7472639855495937e-05,
|
| 596 |
+
"loss": 0.8752,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.63,
|
| 601 |
+
"learning_rate": 1.7140599266854383e-05,
|
| 602 |
+
"loss": 0.873,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.66,
|
| 607 |
+
"learning_rate": 1.6808558678212825e-05,
|
| 608 |
+
"loss": 0.8713,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.68,
|
| 613 |
+
"learning_rate": 1.6476518089571267e-05,
|
| 614 |
+
"loss": 0.8736,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.71,
|
| 619 |
+
"learning_rate": 1.6144477500929713e-05,
|
| 620 |
+
"loss": 0.8715,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.74,
|
| 625 |
+
"learning_rate": 1.581243691228816e-05,
|
| 626 |
+
"loss": 0.8708,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.76,
|
| 631 |
+
"learning_rate": 1.5481060404823887e-05,
|
| 632 |
+
"loss": 0.8694,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.79,
|
| 637 |
+
"learning_rate": 1.514901981618233e-05,
|
| 638 |
+
"loss": 0.8698,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.82,
|
| 643 |
+
"learning_rate": 1.4816979227540776e-05,
|
| 644 |
+
"loss": 0.8686,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.84,
|
| 649 |
+
"learning_rate": 1.448493863889922e-05,
|
| 650 |
+
"loss": 0.8696,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 2.87,
|
| 655 |
+
"learning_rate": 1.4152898050257666e-05,
|
| 656 |
+
"loss": 0.8685,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.9,
|
| 661 |
+
"learning_rate": 1.3820857461616108e-05,
|
| 662 |
+
"loss": 0.8664,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 2.92,
|
| 667 |
+
"learning_rate": 1.3489480954151836e-05,
|
| 668 |
+
"loss": 0.8666,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.95,
|
| 673 |
+
"learning_rate": 1.3157440365510282e-05,
|
| 674 |
+
"loss": 0.8664,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.98,
|
| 679 |
+
"learning_rate": 1.2825399776868724e-05,
|
| 680 |
+
"loss": 0.8687,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.0,
|
| 685 |
+
"learning_rate": 1.249335918822717e-05,
|
| 686 |
+
"loss": 0.8643,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 3.03,
|
| 691 |
+
"learning_rate": 1.2161318599585613e-05,
|
| 692 |
+
"loss": 0.8626,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 3.05,
|
| 697 |
+
"learning_rate": 1.1829278010944059e-05,
|
| 698 |
+
"loss": 0.8628,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.08,
|
| 703 |
+
"learning_rate": 1.1497237422302503e-05,
|
| 704 |
+
"loss": 0.8622,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 3.11,
|
| 709 |
+
"learning_rate": 1.1165196833660947e-05,
|
| 710 |
+
"loss": 0.8618,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.13,
|
| 715 |
+
"learning_rate": 1.0833156245019392e-05,
|
| 716 |
+
"loss": 0.862,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.16,
|
| 721 |
+
"learning_rate": 1.0501115656377836e-05,
|
| 722 |
+
"loss": 0.8605,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.19,
|
| 727 |
+
"learning_rate": 1.016907506773628e-05,
|
| 728 |
+
"loss": 0.8595,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.21,
|
| 733 |
+
"learning_rate": 9.837698560272008e-06,
|
| 734 |
+
"loss": 0.8604,
|
| 735 |
+
"step": 60500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 3.24,
|
| 739 |
+
"learning_rate": 9.505657971630452e-06,
|
| 740 |
+
"loss": 0.8595,
|
| 741 |
+
"step": 61000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 3.27,
|
| 745 |
+
"learning_rate": 9.173617382988898e-06,
|
| 746 |
+
"loss": 0.8602,
|
| 747 |
+
"step": 61500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 3.29,
|
| 751 |
+
"learning_rate": 8.841576794347342e-06,
|
| 752 |
+
"loss": 0.8583,
|
| 753 |
+
"step": 62000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 3.32,
|
| 757 |
+
"learning_rate": 8.510200286883068e-06,
|
| 758 |
+
"loss": 0.8575,
|
| 759 |
+
"step": 62500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.35,
|
| 763 |
+
"learning_rate": 8.178159698241514e-06,
|
| 764 |
+
"loss": 0.8583,
|
| 765 |
+
"step": 63000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.37,
|
| 769 |
+
"learning_rate": 7.846119109599958e-06,
|
| 770 |
+
"loss": 0.8568,
|
| 771 |
+
"step": 63500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 3.4,
|
| 775 |
+
"learning_rate": 7.514078520958402e-06,
|
| 776 |
+
"loss": 0.8555,
|
| 777 |
+
"step": 64000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.43,
|
| 781 |
+
"learning_rate": 7.182037932316847e-06,
|
| 782 |
+
"loss": 0.8562,
|
| 783 |
+
"step": 64500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 3.45,
|
| 787 |
+
"learning_rate": 6.849997343675291e-06,
|
| 788 |
+
"loss": 0.8553,
|
| 789 |
+
"step": 65000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.48,
|
| 793 |
+
"learning_rate": 6.517956755033736e-06,
|
| 794 |
+
"loss": 0.8537,
|
| 795 |
+
"step": 65500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 3.51,
|
| 799 |
+
"learning_rate": 6.186580247569463e-06,
|
| 800 |
+
"loss": 0.8556,
|
| 801 |
+
"step": 66000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.53,
|
| 805 |
+
"learning_rate": 5.854539658927908e-06,
|
| 806 |
+
"loss": 0.8556,
|
| 807 |
+
"step": 66500
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 3.56,
|
| 811 |
+
"learning_rate": 5.5224990702863525e-06,
|
| 812 |
+
"loss": 0.8559,
|
| 813 |
+
"step": 67000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.59,
|
| 817 |
+
"learning_rate": 5.190458481644796e-06,
|
| 818 |
+
"loss": 0.8538,
|
| 819 |
+
"step": 67500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 3.61,
|
| 823 |
+
"learning_rate": 4.85841789300324e-06,
|
| 824 |
+
"loss": 0.8538,
|
| 825 |
+
"step": 68000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.64,
|
| 829 |
+
"learning_rate": 4.526377304361686e-06,
|
| 830 |
+
"loss": 0.8523,
|
| 831 |
+
"step": 68500
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 3.67,
|
| 835 |
+
"learning_rate": 4.19433671572013e-06,
|
| 836 |
+
"loss": 0.8529,
|
| 837 |
+
"step": 69000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 3.69,
|
| 841 |
+
"learning_rate": 3.862296127078574e-06,
|
| 842 |
+
"loss": 0.8538,
|
| 843 |
+
"step": 69500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 3.72,
|
| 847 |
+
"learning_rate": 3.5302555384370188e-06,
|
| 848 |
+
"loss": 0.8541,
|
| 849 |
+
"step": 70000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.75,
|
| 853 |
+
"learning_rate": 3.198214949795463e-06,
|
| 854 |
+
"loss": 0.8521,
|
| 855 |
+
"step": 70500
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 3.77,
|
| 859 |
+
"learning_rate": 2.8668384423311904e-06,
|
| 860 |
+
"loss": 0.8529,
|
| 861 |
+
"step": 71000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 3.8,
|
| 865 |
+
"learning_rate": 2.534797853689635e-06,
|
| 866 |
+
"loss": 0.8522,
|
| 867 |
+
"step": 71500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 3.83,
|
| 871 |
+
"learning_rate": 2.20275726504808e-06,
|
| 872 |
+
"loss": 0.855,
|
| 873 |
+
"step": 72000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.85,
|
| 877 |
+
"learning_rate": 1.870716676406524e-06,
|
| 878 |
+
"loss": 0.8542,
|
| 879 |
+
"step": 72500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 3.88,
|
| 883 |
+
"learning_rate": 1.5386760877649683e-06,
|
| 884 |
+
"loss": 0.8516,
|
| 885 |
+
"step": 73000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.9,
|
| 889 |
+
"learning_rate": 1.206635499123413e-06,
|
| 890 |
+
"loss": 0.8521,
|
| 891 |
+
"step": 73500
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 3.93,
|
| 895 |
+
"learning_rate": 8.745949104818574e-07,
|
| 896 |
+
"loss": 0.8514,
|
| 897 |
+
"step": 74000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 3.96,
|
| 901 |
+
"learning_rate": 5.425543218403018e-07,
|
| 902 |
+
"loss": 0.852,
|
| 903 |
+
"step": 74500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 3.98,
|
| 907 |
+
"learning_rate": 2.1184189555331246e-07,
|
| 908 |
+
"loss": 0.8498,
|
| 909 |
+
"step": 75000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 4.0,
|
| 913 |
+
"step": 75292,
|
| 914 |
+
"total_flos": 5.54885793210119e+18,
|
| 915 |
+
"train_loss": 0.9333500321268725,
|
| 916 |
+
"train_runtime": 60105.9393,
|
| 917 |
+
"train_samples_per_second": 350.725,
|
| 918 |
+
"train_steps_per_second": 1.253
|
| 919 |
+
}
|
| 920 |
+
],
|
| 921 |
+
"logging_steps": 500,
|
| 922 |
+
"max_steps": 75292,
|
| 923 |
+
"num_train_epochs": 4,
|
| 924 |
+
"save_steps": 500,
|
| 925 |
+
"total_flos": 5.54885793210119e+18,
|
| 926 |
+
"trial_name": null,
|
| 927 |
+
"trial_params": null
|
| 928 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69e455097472ec48d6d42358a29ff65c69f5d5baf4d3073ffbb4960239554d05
|
| 3 |
+
size 4143
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|