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 +904 -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-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: gbert_large_pubmed_mimic_translated_german_512_2_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_large_pubmed_mimic_translated_german_512_2_epochs_multip
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [deepset/gbert-large](https://huggingface.co/deepset/gbert-large) 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: 24
|
| 37 |
+
- eval_batch_size: 8
|
| 38 |
+
- seed: 42
|
| 39 |
+
- distributed_type: multi-GPU
|
| 40 |
+
- num_devices: 6
|
| 41 |
+
- total_train_batch_size: 144
|
| 42 |
+
- total_eval_batch_size: 48
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 2.0
|
| 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-large",
|
| 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": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4096,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 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 sha256:2aa55ff8974284cb52021f247403a5d9b8f33bf274cfbb40517698ac86bc0ca5
|
| 3 |
+
size 1343207853
|
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": 2.0,
|
| 3 |
+
"train_loss": 0.795374077400056,
|
| 4 |
+
"train_runtime": 74284.0357,
|
| 5 |
+
"train_samples": 5270167,
|
| 6 |
+
"train_samples_per_second": 141.892,
|
| 7 |
+
"train_steps_per_second": 0.985
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,904 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 73198,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 4.966324216508648e-05,
|
| 14 |
+
"loss": 1.3516,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 4.93223858575371e-05,
|
| 20 |
+
"loss": 1.194,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 4.8980846471215063e-05,
|
| 26 |
+
"loss": 1.1341,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 4.863930708489303e-05,
|
| 32 |
+
"loss": 1.0893,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.07,
|
| 37 |
+
"learning_rate": 4.8297767698571e-05,
|
| 38 |
+
"loss": 1.0658,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"learning_rate": 4.795622831224897e-05,
|
| 44 |
+
"loss": 1.0419,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1,
|
| 49 |
+
"learning_rate": 4.7615372004699584e-05,
|
| 50 |
+
"loss": 1.0196,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11,
|
| 55 |
+
"learning_rate": 4.727383261837756e-05,
|
| 56 |
+
"loss": 1.0027,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.12,
|
| 61 |
+
"learning_rate": 4.6932293232055523e-05,
|
| 62 |
+
"loss": 0.9885,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.14,
|
| 67 |
+
"learning_rate": 4.659143692450614e-05,
|
| 68 |
+
"loss": 0.9824,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.15,
|
| 73 |
+
"learning_rate": 4.6249897538184105e-05,
|
| 74 |
+
"loss": 0.964,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.16,
|
| 79 |
+
"learning_rate": 4.590835815186207e-05,
|
| 80 |
+
"loss": 0.9533,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.18,
|
| 85 |
+
"learning_rate": 4.5566818765540044e-05,
|
| 86 |
+
"loss": 0.9401,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.19,
|
| 91 |
+
"learning_rate": 4.522527937921802e-05,
|
| 92 |
+
"loss": 0.9334,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2,
|
| 97 |
+
"learning_rate": 4.4883739992895983e-05,
|
| 98 |
+
"loss": 0.923,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.22,
|
| 103 |
+
"learning_rate": 4.454220060657395e-05,
|
| 104 |
+
"loss": 0.9165,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.23,
|
| 109 |
+
"learning_rate": 4.420066122025192e-05,
|
| 110 |
+
"loss": 0.9078,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.25,
|
| 115 |
+
"learning_rate": 4.385912183392989e-05,
|
| 116 |
+
"loss": 0.9012,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.26,
|
| 121 |
+
"learning_rate": 4.3517582447607855e-05,
|
| 122 |
+
"loss": 0.8927,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.27,
|
| 127 |
+
"learning_rate": 4.3176043061285835e-05,
|
| 128 |
+
"loss": 0.8878,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.29,
|
| 133 |
+
"learning_rate": 4.28345036749638e-05,
|
| 134 |
+
"loss": 0.8819,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3,
|
| 139 |
+
"learning_rate": 4.249296428864177e-05,
|
| 140 |
+
"loss": 0.8744,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.31,
|
| 145 |
+
"learning_rate": 4.215142490231973e-05,
|
| 146 |
+
"loss": 0.8733,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.33,
|
| 151 |
+
"learning_rate": 4.1809885515997706e-05,
|
| 152 |
+
"loss": 0.8747,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.34,
|
| 157 |
+
"learning_rate": 4.1469029208448315e-05,
|
| 158 |
+
"loss": 0.8709,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.36,
|
| 163 |
+
"learning_rate": 4.1127489822126295e-05,
|
| 164 |
+
"loss": 0.8651,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.37,
|
| 169 |
+
"learning_rate": 4.0786633514576903e-05,
|
| 170 |
+
"loss": 0.8592,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.38,
|
| 175 |
+
"learning_rate": 4.0445094128254876e-05,
|
| 176 |
+
"loss": 0.8526,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4,
|
| 181 |
+
"learning_rate": 4.010355474193284e-05,
|
| 182 |
+
"loss": 0.8501,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.41,
|
| 187 |
+
"learning_rate": 3.976201535561081e-05,
|
| 188 |
+
"loss": 0.848,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.42,
|
| 193 |
+
"learning_rate": 3.9421159048061424e-05,
|
| 194 |
+
"loss": 0.8442,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.44,
|
| 199 |
+
"learning_rate": 3.907961966173939e-05,
|
| 200 |
+
"loss": 0.839,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.45,
|
| 205 |
+
"learning_rate": 3.8738080275417363e-05,
|
| 206 |
+
"loss": 0.8408,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.46,
|
| 211 |
+
"learning_rate": 3.8396540889095336e-05,
|
| 212 |
+
"loss": 0.8349,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48,
|
| 217 |
+
"learning_rate": 3.80550015027733e-05,
|
| 218 |
+
"loss": 0.8324,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.49,
|
| 223 |
+
"learning_rate": 3.771346211645127e-05,
|
| 224 |
+
"loss": 0.8305,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.51,
|
| 229 |
+
"learning_rate": 3.737192273012924e-05,
|
| 230 |
+
"loss": 0.8276,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.52,
|
| 235 |
+
"learning_rate": 3.7030383343807215e-05,
|
| 236 |
+
"loss": 0.8235,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.53,
|
| 241 |
+
"learning_rate": 3.668884395748518e-05,
|
| 242 |
+
"loss": 0.8206,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.55,
|
| 247 |
+
"learning_rate": 3.634730457116315e-05,
|
| 248 |
+
"loss": 0.8225,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.56,
|
| 253 |
+
"learning_rate": 3.600576518484112e-05,
|
| 254 |
+
"loss": 0.8162,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.57,
|
| 259 |
+
"learning_rate": 3.5664225798519086e-05,
|
| 260 |
+
"loss": 0.8179,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.59,
|
| 265 |
+
"learning_rate": 3.532268641219705e-05,
|
| 266 |
+
"loss": 0.8136,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.6,
|
| 271 |
+
"learning_rate": 3.4981147025875025e-05,
|
| 272 |
+
"loss": 0.8137,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.61,
|
| 277 |
+
"learning_rate": 3.4639607639553e-05,
|
| 278 |
+
"loss": 0.8061,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.63,
|
| 283 |
+
"learning_rate": 3.4298068253230964e-05,
|
| 284 |
+
"loss": 0.807,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.64,
|
| 289 |
+
"learning_rate": 3.395652886690893e-05,
|
| 290 |
+
"loss": 0.8053,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.66,
|
| 295 |
+
"learning_rate": 3.36149894805869e-05,
|
| 296 |
+
"loss": 0.8002,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.67,
|
| 301 |
+
"learning_rate": 3.3273450094264876e-05,
|
| 302 |
+
"loss": 0.7994,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.68,
|
| 307 |
+
"learning_rate": 3.293191070794284e-05,
|
| 308 |
+
"loss": 0.7987,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.7,
|
| 313 |
+
"learning_rate": 3.259037132162081e-05,
|
| 314 |
+
"loss": 0.7956,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.71,
|
| 319 |
+
"learning_rate": 3.224883193529878e-05,
|
| 320 |
+
"loss": 0.7939,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.72,
|
| 325 |
+
"learning_rate": 3.190729254897675e-05,
|
| 326 |
+
"loss": 0.791,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.74,
|
| 331 |
+
"learning_rate": 3.156575316265472e-05,
|
| 332 |
+
"loss": 0.7904,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.75,
|
| 337 |
+
"learning_rate": 3.1224213776332687e-05,
|
| 338 |
+
"loss": 0.7879,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.77,
|
| 343 |
+
"learning_rate": 3.088267439001066e-05,
|
| 344 |
+
"loss": 0.786,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.78,
|
| 349 |
+
"learning_rate": 3.0541135003688626e-05,
|
| 350 |
+
"loss": 0.786,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.79,
|
| 355 |
+
"learning_rate": 3.0199595617366595e-05,
|
| 356 |
+
"loss": 0.7827,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.81,
|
| 361 |
+
"learning_rate": 2.9858056231044568e-05,
|
| 362 |
+
"loss": 0.7829,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.82,
|
| 367 |
+
"learning_rate": 2.9516516844722538e-05,
|
| 368 |
+
"loss": 0.7805,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.83,
|
| 373 |
+
"learning_rate": 2.9174977458400504e-05,
|
| 374 |
+
"loss": 0.7795,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.85,
|
| 379 |
+
"learning_rate": 2.8834121150851116e-05,
|
| 380 |
+
"loss": 0.7776,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.86,
|
| 385 |
+
"learning_rate": 2.8492581764529086e-05,
|
| 386 |
+
"loss": 0.775,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.87,
|
| 391 |
+
"learning_rate": 2.8151725456979698e-05,
|
| 392 |
+
"loss": 0.7732,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.89,
|
| 397 |
+
"learning_rate": 2.7810186070657668e-05,
|
| 398 |
+
"loss": 0.7745,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.9,
|
| 403 |
+
"learning_rate": 2.746864668433564e-05,
|
| 404 |
+
"loss": 0.7746,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.92,
|
| 409 |
+
"learning_rate": 2.712710729801361e-05,
|
| 410 |
+
"loss": 0.7717,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.93,
|
| 415 |
+
"learning_rate": 2.6786250990464222e-05,
|
| 416 |
+
"loss": 0.77,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.94,
|
| 421 |
+
"learning_rate": 2.6444711604142192e-05,
|
| 422 |
+
"loss": 0.7667,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.96,
|
| 427 |
+
"learning_rate": 2.610317221782016e-05,
|
| 428 |
+
"loss": 0.7684,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.97,
|
| 433 |
+
"learning_rate": 2.5761632831498128e-05,
|
| 434 |
+
"loss": 0.7643,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.98,
|
| 439 |
+
"learning_rate": 2.5422142681494032e-05,
|
| 440 |
+
"loss": 0.7638,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.0,
|
| 445 |
+
"learning_rate": 2.5080603295172002e-05,
|
| 446 |
+
"loss": 0.7651,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.01,
|
| 451 |
+
"learning_rate": 2.4739063908849968e-05,
|
| 452 |
+
"loss": 0.7578,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.02,
|
| 457 |
+
"learning_rate": 2.439752452252794e-05,
|
| 458 |
+
"loss": 0.7578,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.04,
|
| 463 |
+
"learning_rate": 2.4055985136205907e-05,
|
| 464 |
+
"loss": 0.7576,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.05,
|
| 469 |
+
"learning_rate": 2.371444574988388e-05,
|
| 470 |
+
"loss": 0.7572,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.07,
|
| 475 |
+
"learning_rate": 2.3372906363561846e-05,
|
| 476 |
+
"loss": 0.7549,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.08,
|
| 481 |
+
"learning_rate": 2.3031366977239816e-05,
|
| 482 |
+
"loss": 0.7552,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.09,
|
| 487 |
+
"learning_rate": 2.2689827590917785e-05,
|
| 488 |
+
"loss": 0.7524,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.11,
|
| 493 |
+
"learning_rate": 2.2348288204595755e-05,
|
| 494 |
+
"loss": 0.7505,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.12,
|
| 499 |
+
"learning_rate": 2.2006748818273724e-05,
|
| 500 |
+
"loss": 0.7513,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.13,
|
| 505 |
+
"learning_rate": 2.1665209431951694e-05,
|
| 506 |
+
"loss": 0.7476,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.15,
|
| 511 |
+
"learning_rate": 2.1323670045629663e-05,
|
| 512 |
+
"loss": 0.7489,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.16,
|
| 517 |
+
"learning_rate": 2.0982813738080276e-05,
|
| 518 |
+
"loss": 0.7483,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.17,
|
| 523 |
+
"learning_rate": 2.064127435175825e-05,
|
| 524 |
+
"loss": 0.7447,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.19,
|
| 529 |
+
"learning_rate": 2.0299734965436215e-05,
|
| 530 |
+
"loss": 0.7472,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.2,
|
| 535 |
+
"learning_rate": 1.9958195579114184e-05,
|
| 536 |
+
"loss": 0.7436,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.22,
|
| 541 |
+
"learning_rate": 1.9616656192792154e-05,
|
| 542 |
+
"loss": 0.7428,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.23,
|
| 547 |
+
"learning_rate": 1.9275116806470123e-05,
|
| 548 |
+
"loss": 0.7411,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.24,
|
| 553 |
+
"learning_rate": 1.8933577420148093e-05,
|
| 554 |
+
"loss": 0.7421,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.26,
|
| 559 |
+
"learning_rate": 1.8592038033826062e-05,
|
| 560 |
+
"loss": 0.7397,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.27,
|
| 565 |
+
"learning_rate": 1.825049864750403e-05,
|
| 566 |
+
"loss": 0.7396,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.28,
|
| 571 |
+
"learning_rate": 1.7908959261182e-05,
|
| 572 |
+
"loss": 0.7372,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.3,
|
| 577 |
+
"learning_rate": 1.756741987485997e-05,
|
| 578 |
+
"loss": 0.7367,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.31,
|
| 583 |
+
"learning_rate": 1.7225880488537937e-05,
|
| 584 |
+
"loss": 0.7381,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.33,
|
| 589 |
+
"learning_rate": 1.688434110221591e-05,
|
| 590 |
+
"loss": 0.7357,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.34,
|
| 595 |
+
"learning_rate": 1.6543484794666522e-05,
|
| 596 |
+
"loss": 0.7331,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.35,
|
| 601 |
+
"learning_rate": 1.6201945408344492e-05,
|
| 602 |
+
"loss": 0.7346,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.37,
|
| 607 |
+
"learning_rate": 1.586040602202246e-05,
|
| 608 |
+
"loss": 0.7328,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.38,
|
| 613 |
+
"learning_rate": 1.5519549714473074e-05,
|
| 614 |
+
"loss": 0.7319,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.39,
|
| 619 |
+
"learning_rate": 1.5178010328151043e-05,
|
| 620 |
+
"loss": 0.73,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.41,
|
| 625 |
+
"learning_rate": 1.4836470941829011e-05,
|
| 626 |
+
"loss": 0.7314,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.42,
|
| 631 |
+
"learning_rate": 1.4494931555506982e-05,
|
| 632 |
+
"loss": 0.7281,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.43,
|
| 637 |
+
"learning_rate": 1.415339216918495e-05,
|
| 638 |
+
"loss": 0.7282,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.45,
|
| 643 |
+
"learning_rate": 1.381185278286292e-05,
|
| 644 |
+
"loss": 0.7275,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.46,
|
| 649 |
+
"learning_rate": 1.3470996475313532e-05,
|
| 650 |
+
"loss": 0.7286,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.48,
|
| 655 |
+
"learning_rate": 1.3129457088991503e-05,
|
| 656 |
+
"loss": 0.727,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.49,
|
| 661 |
+
"learning_rate": 1.2787917702669471e-05,
|
| 662 |
+
"loss": 0.7263,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.5,
|
| 667 |
+
"learning_rate": 1.244637831634744e-05,
|
| 668 |
+
"loss": 0.7261,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.52,
|
| 673 |
+
"learning_rate": 1.2104838930025412e-05,
|
| 674 |
+
"loss": 0.7241,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.53,
|
| 679 |
+
"learning_rate": 1.1763299543703381e-05,
|
| 680 |
+
"loss": 0.7243,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.54,
|
| 685 |
+
"learning_rate": 1.1421760157381351e-05,
|
| 686 |
+
"loss": 0.7246,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.56,
|
| 691 |
+
"learning_rate": 1.1080220771059319e-05,
|
| 692 |
+
"loss": 0.7249,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.57,
|
| 697 |
+
"learning_rate": 1.0738681384737288e-05,
|
| 698 |
+
"loss": 0.7193,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.58,
|
| 703 |
+
"learning_rate": 1.0397141998415258e-05,
|
| 704 |
+
"loss": 0.7206,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.6,
|
| 709 |
+
"learning_rate": 1.0055602612093227e-05,
|
| 710 |
+
"loss": 0.72,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.61,
|
| 715 |
+
"learning_rate": 9.714746304543841e-06,
|
| 716 |
+
"loss": 0.7189,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.63,
|
| 721 |
+
"learning_rate": 9.37320691822181e-06,
|
| 722 |
+
"loss": 0.7193,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.64,
|
| 727 |
+
"learning_rate": 9.031667531899779e-06,
|
| 728 |
+
"loss": 0.7173,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.65,
|
| 733 |
+
"learning_rate": 8.690128145577748e-06,
|
| 734 |
+
"loss": 0.7181,
|
| 735 |
+
"step": 60500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.67,
|
| 739 |
+
"learning_rate": 8.348588759255718e-06,
|
| 740 |
+
"loss": 0.7155,
|
| 741 |
+
"step": 61000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.68,
|
| 745 |
+
"learning_rate": 8.007049372933686e-06,
|
| 746 |
+
"loss": 0.7183,
|
| 747 |
+
"step": 61500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.69,
|
| 751 |
+
"learning_rate": 7.665509986611655e-06,
|
| 752 |
+
"loss": 0.7175,
|
| 753 |
+
"step": 62000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.71,
|
| 757 |
+
"learning_rate": 7.323970600289626e-06,
|
| 758 |
+
"loss": 0.7157,
|
| 759 |
+
"step": 62500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.72,
|
| 763 |
+
"learning_rate": 6.98311429274024e-06,
|
| 764 |
+
"loss": 0.7164,
|
| 765 |
+
"step": 63000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.74,
|
| 769 |
+
"learning_rate": 6.642257985190853e-06,
|
| 770 |
+
"loss": 0.7147,
|
| 771 |
+
"step": 63500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.75,
|
| 775 |
+
"learning_rate": 6.3007185988688224e-06,
|
| 776 |
+
"loss": 0.7143,
|
| 777 |
+
"step": 64000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.76,
|
| 781 |
+
"learning_rate": 5.959179212546791e-06,
|
| 782 |
+
"loss": 0.713,
|
| 783 |
+
"step": 64500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.78,
|
| 787 |
+
"learning_rate": 5.617639826224761e-06,
|
| 788 |
+
"loss": 0.7115,
|
| 789 |
+
"step": 65000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.79,
|
| 793 |
+
"learning_rate": 5.27610043990273e-06,
|
| 794 |
+
"loss": 0.7106,
|
| 795 |
+
"step": 65500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.8,
|
| 799 |
+
"learning_rate": 4.935244132353343e-06,
|
| 800 |
+
"loss": 0.7095,
|
| 801 |
+
"step": 66000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.82,
|
| 805 |
+
"learning_rate": 4.593704746031312e-06,
|
| 806 |
+
"loss": 0.7119,
|
| 807 |
+
"step": 66500
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.83,
|
| 811 |
+
"learning_rate": 4.2521653597092825e-06,
|
| 812 |
+
"loss": 0.7099,
|
| 813 |
+
"step": 67000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.84,
|
| 817 |
+
"learning_rate": 3.910625973387251e-06,
|
| 818 |
+
"loss": 0.7084,
|
| 819 |
+
"step": 67500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.86,
|
| 823 |
+
"learning_rate": 3.5690865870652207e-06,
|
| 824 |
+
"loss": 0.71,
|
| 825 |
+
"step": 68000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.87,
|
| 829 |
+
"learning_rate": 3.22754720074319e-06,
|
| 830 |
+
"loss": 0.7093,
|
| 831 |
+
"step": 68500
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.89,
|
| 835 |
+
"learning_rate": 2.886690893193803e-06,
|
| 836 |
+
"loss": 0.7086,
|
| 837 |
+
"step": 69000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.9,
|
| 841 |
+
"learning_rate": 2.5451515068717725e-06,
|
| 842 |
+
"loss": 0.7096,
|
| 843 |
+
"step": 69500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.91,
|
| 847 |
+
"learning_rate": 2.204295199322386e-06,
|
| 848 |
+
"loss": 0.7072,
|
| 849 |
+
"step": 70000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.93,
|
| 853 |
+
"learning_rate": 1.8627558130003552e-06,
|
| 854 |
+
"loss": 0.707,
|
| 855 |
+
"step": 70500
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.94,
|
| 859 |
+
"learning_rate": 1.5212164266783245e-06,
|
| 860 |
+
"loss": 0.7087,
|
| 861 |
+
"step": 71000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.95,
|
| 865 |
+
"learning_rate": 1.180360119128938e-06,
|
| 866 |
+
"loss": 0.707,
|
| 867 |
+
"step": 71500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.97,
|
| 871 |
+
"learning_rate": 8.388207328069074e-07,
|
| 872 |
+
"loss": 0.7074,
|
| 873 |
+
"step": 72000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.98,
|
| 877 |
+
"learning_rate": 4.972813464848767e-07,
|
| 878 |
+
"loss": 0.7069,
|
| 879 |
+
"step": 72500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.99,
|
| 883 |
+
"learning_rate": 1.5574196016284598e-07,
|
| 884 |
+
"loss": 0.7074,
|
| 885 |
+
"step": 73000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.0,
|
| 889 |
+
"step": 73198,
|
| 890 |
+
"total_flos": 9.8240404403142e+18,
|
| 891 |
+
"train_loss": 0.795374077400056,
|
| 892 |
+
"train_runtime": 74284.0357,
|
| 893 |
+
"train_samples_per_second": 141.892,
|
| 894 |
+
"train_steps_per_second": 0.985
|
| 895 |
+
}
|
| 896 |
+
],
|
| 897 |
+
"logging_steps": 500,
|
| 898 |
+
"max_steps": 73198,
|
| 899 |
+
"num_train_epochs": 2,
|
| 900 |
+
"save_steps": 500,
|
| 901 |
+
"total_flos": 9.8240404403142e+18,
|
| 902 |
+
"trial_name": null,
|
| 903 |
+
"trial_params": null
|
| 904 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e548ff49c5d486f6416ed76fd7392dc6bc8f42f5c83a213070ba2a1a64ee4891
|
| 3 |
+
size 4143
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|