Commit
·
e8c0878
1
Parent(s):
484e5df
End of training
Browse files- README.md +105 -0
- config.json +52 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- trainer_state.json +1132 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: roberta-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- open_question_type
|
| 8 |
+
metrics:
|
| 9 |
+
- f1
|
| 10 |
+
model-index:
|
| 11 |
+
- name: roberta-large-question-classifier
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Text Classification
|
| 15 |
+
type: text-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: open_question_type
|
| 18 |
+
type: open_question_type
|
| 19 |
+
config: default
|
| 20 |
+
split: validation
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: F1
|
| 24 |
+
type: f1
|
| 25 |
+
value: 0.7954091951908298
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# roberta-large-question-classifier
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the open_question_type dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.9002
|
| 36 |
+
- F1: 0.7954
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 2e-05
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 512
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 62 |
+
- num_epochs: 30
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 68 |
+
| 1.9467 | 1.0 | 233 | 1.3099 | 0.4050 |
|
| 69 |
+
| 0.6381 | 2.0 | 466 | 0.5586 | 0.7785 |
|
| 70 |
+
| 0.628 | 3.0 | 699 | 0.6419 | 0.7831 |
|
| 71 |
+
| 0.4487 | 4.0 | 932 | 0.5770 | 0.8094 |
|
| 72 |
+
| 0.3319 | 5.0 | 1165 | 0.7713 | 0.7953 |
|
| 73 |
+
| 0.2095 | 6.0 | 1398 | 0.8799 | 0.8018 |
|
| 74 |
+
| 0.1355 | 7.0 | 1631 | 1.0646 | 0.7961 |
|
| 75 |
+
| 0.0956 | 8.0 | 1864 | 1.2175 | 0.7999 |
|
| 76 |
+
| 0.0687 | 9.0 | 2097 | 1.3647 | 0.7892 |
|
| 77 |
+
| 0.0371 | 10.0 | 2330 | 1.3809 | 0.7987 |
|
| 78 |
+
| 0.0303 | 11.0 | 2563 | 1.3591 | 0.8123 |
|
| 79 |
+
| 0.0263 | 12.0 | 2796 | 1.5317 | 0.8100 |
|
| 80 |
+
| 0.0144 | 13.0 | 3029 | 1.5726 | 0.7959 |
|
| 81 |
+
| 0.0436 | 14.0 | 3262 | 1.6160 | 0.7988 |
|
| 82 |
+
| 0.0048 | 15.0 | 3495 | 1.6826 | 0.7957 |
|
| 83 |
+
| 0.0001 | 16.0 | 3728 | 1.6913 | 0.7957 |
|
| 84 |
+
| 0.0001 | 17.0 | 3961 | 1.7076 | 0.7995 |
|
| 85 |
+
| 0.0034 | 18.0 | 4194 | 1.8018 | 0.7960 |
|
| 86 |
+
| 0.0228 | 19.0 | 4427 | 1.7457 | 0.7916 |
|
| 87 |
+
| 0.0083 | 20.0 | 4660 | 1.9279 | 0.7869 |
|
| 88 |
+
| 0.0001 | 21.0 | 4893 | 1.8367 | 0.7915 |
|
| 89 |
+
| 0.0003 | 22.0 | 5126 | 1.8620 | 0.7842 |
|
| 90 |
+
| 0.0002 | 23.0 | 5359 | 1.9192 | 0.7828 |
|
| 91 |
+
| 0.0 | 24.0 | 5592 | 1.9081 | 0.7927 |
|
| 92 |
+
| 0.0003 | 25.0 | 5825 | 1.9822 | 0.7813 |
|
| 93 |
+
| 0.0059 | 26.0 | 6058 | 1.8737 | 0.7954 |
|
| 94 |
+
| 0.0 | 27.0 | 6291 | 1.8793 | 0.7929 |
|
| 95 |
+
| 0.0 | 28.0 | 6524 | 1.8905 | 0.7940 |
|
| 96 |
+
| 0.0 | 29.0 | 6757 | 1.8971 | 0.7940 |
|
| 97 |
+
| 0.0002 | 30.0 | 6990 | 1.9002 | 0.7954 |
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
### Framework versions
|
| 101 |
+
|
| 102 |
+
- Transformers 4.33.2
|
| 103 |
+
- Pytorch 2.1.0+cu118
|
| 104 |
+
- Datasets 2.14.5
|
| 105 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "extent",
|
| 15 |
+
"1": "disjunction",
|
| 16 |
+
"2": "concept",
|
| 17 |
+
"3": "comparison",
|
| 18 |
+
"4": "procedural",
|
| 19 |
+
"5": "consequence",
|
| 20 |
+
"6": "judgmental",
|
| 21 |
+
"7": "example",
|
| 22 |
+
"8": "verification",
|
| 23 |
+
"9": "cause"
|
| 24 |
+
},
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 4096,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"cause": 9,
|
| 29 |
+
"comparison": 3,
|
| 30 |
+
"concept": 2,
|
| 31 |
+
"consequence": 5,
|
| 32 |
+
"disjunction": 1,
|
| 33 |
+
"example": 7,
|
| 34 |
+
"extent": 0,
|
| 35 |
+
"judgmental": 6,
|
| 36 |
+
"procedural": 4,
|
| 37 |
+
"verification": 8
|
| 38 |
+
},
|
| 39 |
+
"layer_norm_eps": 1e-05,
|
| 40 |
+
"max_position_embeddings": 514,
|
| 41 |
+
"model_type": "roberta",
|
| 42 |
+
"num_attention_heads": 16,
|
| 43 |
+
"num_hidden_layers": 24,
|
| 44 |
+
"pad_token_id": 1,
|
| 45 |
+
"position_embedding_type": "absolute",
|
| 46 |
+
"problem_type": "single_label_classification",
|
| 47 |
+
"torch_dtype": "float32",
|
| 48 |
+
"transformers_version": "4.33.2",
|
| 49 |
+
"type_vocab_size": 1,
|
| 50 |
+
"use_cache": true,
|
| 51 |
+
"vocab_size": 50265
|
| 52 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:632e4998b864201d52dc9bb19b649075ce06ceab00b63399c5ab76abf1a8007b
|
| 3 |
+
size 1421615982
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8123190611646329,
|
| 3 |
+
"best_model_checkpoint": "output/roberta-large-question-classifier/checkpoint-2563",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6990,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21,
|
| 13 |
+
"learning_rate": 1.430615164520744e-06,
|
| 14 |
+
"loss": 2.3372,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.43,
|
| 19 |
+
"learning_rate": 2.861230329041488e-06,
|
| 20 |
+
"loss": 2.276,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.64,
|
| 25 |
+
"learning_rate": 4.291845493562232e-06,
|
| 26 |
+
"loss": 2.1988,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.86,
|
| 31 |
+
"learning_rate": 5.722460658082976e-06,
|
| 32 |
+
"loss": 1.9467,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.0,
|
| 37 |
+
"eval_f1": 0.4050404697492347,
|
| 38 |
+
"eval_loss": 1.3099409341812134,
|
| 39 |
+
"eval_runtime": 1.3906,
|
| 40 |
+
"eval_samples_per_second": 417.1,
|
| 41 |
+
"eval_steps_per_second": 1.438,
|
| 42 |
+
"step": 233
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.07,
|
| 46 |
+
"learning_rate": 7.15307582260372e-06,
|
| 47 |
+
"loss": 1.5551,
|
| 48 |
+
"step": 250
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.29,
|
| 52 |
+
"learning_rate": 8.583690987124465e-06,
|
| 53 |
+
"loss": 1.0537,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.5,
|
| 58 |
+
"learning_rate": 1.0014306151645208e-05,
|
| 59 |
+
"loss": 0.872,
|
| 60 |
+
"step": 350
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.72,
|
| 64 |
+
"learning_rate": 1.1444921316165953e-05,
|
| 65 |
+
"loss": 0.6619,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.93,
|
| 70 |
+
"learning_rate": 1.2875536480686697e-05,
|
| 71 |
+
"loss": 0.6381,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.0,
|
| 76 |
+
"eval_f1": 0.7785421184302428,
|
| 77 |
+
"eval_loss": 0.5586220622062683,
|
| 78 |
+
"eval_runtime": 1.4464,
|
| 79 |
+
"eval_samples_per_second": 400.997,
|
| 80 |
+
"eval_steps_per_second": 1.383,
|
| 81 |
+
"step": 466
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.15,
|
| 85 |
+
"learning_rate": 1.430615164520744e-05,
|
| 86 |
+
"loss": 0.509,
|
| 87 |
+
"step": 500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.36,
|
| 91 |
+
"learning_rate": 1.5736766809728185e-05,
|
| 92 |
+
"loss": 0.5387,
|
| 93 |
+
"step": 550
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.58,
|
| 97 |
+
"learning_rate": 1.716738197424893e-05,
|
| 98 |
+
"loss": 0.5163,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.79,
|
| 103 |
+
"learning_rate": 1.859799713876967e-05,
|
| 104 |
+
"loss": 0.628,
|
| 105 |
+
"step": 650
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.0,
|
| 109 |
+
"eval_f1": 0.7831151120797589,
|
| 110 |
+
"eval_loss": 0.6418800354003906,
|
| 111 |
+
"eval_runtime": 1.467,
|
| 112 |
+
"eval_samples_per_second": 395.356,
|
| 113 |
+
"eval_steps_per_second": 1.363,
|
| 114 |
+
"step": 699
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.0,
|
| 118 |
+
"learning_rate": 1.9996820855189955e-05,
|
| 119 |
+
"loss": 0.5632,
|
| 120 |
+
"step": 700
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.22,
|
| 124 |
+
"learning_rate": 1.983786361468765e-05,
|
| 125 |
+
"loss": 0.4046,
|
| 126 |
+
"step": 750
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.43,
|
| 130 |
+
"learning_rate": 1.9678906374185345e-05,
|
| 131 |
+
"loss": 0.3985,
|
| 132 |
+
"step": 800
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.65,
|
| 136 |
+
"learning_rate": 1.951994913368304e-05,
|
| 137 |
+
"loss": 0.4307,
|
| 138 |
+
"step": 850
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.86,
|
| 142 |
+
"learning_rate": 1.9360991893180737e-05,
|
| 143 |
+
"loss": 0.4487,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 4.0,
|
| 148 |
+
"eval_f1": 0.8093842888236766,
|
| 149 |
+
"eval_loss": 0.5770355463027954,
|
| 150 |
+
"eval_runtime": 1.4647,
|
| 151 |
+
"eval_samples_per_second": 395.985,
|
| 152 |
+
"eval_steps_per_second": 1.365,
|
| 153 |
+
"step": 932
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.08,
|
| 157 |
+
"learning_rate": 1.9202034652678432e-05,
|
| 158 |
+
"loss": 0.3373,
|
| 159 |
+
"step": 950
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.29,
|
| 163 |
+
"learning_rate": 1.9043077412176127e-05,
|
| 164 |
+
"loss": 0.2578,
|
| 165 |
+
"step": 1000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.51,
|
| 169 |
+
"learning_rate": 1.888412017167382e-05,
|
| 170 |
+
"loss": 0.2675,
|
| 171 |
+
"step": 1050
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.72,
|
| 175 |
+
"learning_rate": 1.8725162931171516e-05,
|
| 176 |
+
"loss": 0.2697,
|
| 177 |
+
"step": 1100
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.94,
|
| 181 |
+
"learning_rate": 1.8566205690669214e-05,
|
| 182 |
+
"loss": 0.3319,
|
| 183 |
+
"step": 1150
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 5.0,
|
| 187 |
+
"eval_f1": 0.7952503005676876,
|
| 188 |
+
"eval_loss": 0.7712982296943665,
|
| 189 |
+
"eval_runtime": 1.5475,
|
| 190 |
+
"eval_samples_per_second": 374.79,
|
| 191 |
+
"eval_steps_per_second": 1.292,
|
| 192 |
+
"step": 1165
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 5.15,
|
| 196 |
+
"learning_rate": 1.8407248450166905e-05,
|
| 197 |
+
"loss": 0.2049,
|
| 198 |
+
"step": 1200
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 5.36,
|
| 202 |
+
"learning_rate": 1.82482912096646e-05,
|
| 203 |
+
"loss": 0.2344,
|
| 204 |
+
"step": 1250
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.58,
|
| 208 |
+
"learning_rate": 1.8089333969162298e-05,
|
| 209 |
+
"loss": 0.1843,
|
| 210 |
+
"step": 1300
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 5.79,
|
| 214 |
+
"learning_rate": 1.7930376728659993e-05,
|
| 215 |
+
"loss": 0.2095,
|
| 216 |
+
"step": 1350
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 6.0,
|
| 220 |
+
"eval_f1": 0.8017807103839256,
|
| 221 |
+
"eval_loss": 0.8798965811729431,
|
| 222 |
+
"eval_runtime": 1.4572,
|
| 223 |
+
"eval_samples_per_second": 398.025,
|
| 224 |
+
"eval_steps_per_second": 1.372,
|
| 225 |
+
"step": 1398
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 6.01,
|
| 229 |
+
"learning_rate": 1.7771419488157687e-05,
|
| 230 |
+
"loss": 0.2039,
|
| 231 |
+
"step": 1400
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 6.22,
|
| 235 |
+
"learning_rate": 1.7612462247655382e-05,
|
| 236 |
+
"loss": 0.0876,
|
| 237 |
+
"step": 1450
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 6.44,
|
| 241 |
+
"learning_rate": 1.7453505007153077e-05,
|
| 242 |
+
"loss": 0.1054,
|
| 243 |
+
"step": 1500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 6.65,
|
| 247 |
+
"learning_rate": 1.7294547766650775e-05,
|
| 248 |
+
"loss": 0.1629,
|
| 249 |
+
"step": 1550
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.87,
|
| 253 |
+
"learning_rate": 1.7135590526148466e-05,
|
| 254 |
+
"loss": 0.1355,
|
| 255 |
+
"step": 1600
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 7.0,
|
| 259 |
+
"eval_f1": 0.7961224122154954,
|
| 260 |
+
"eval_loss": 1.0646474361419678,
|
| 261 |
+
"eval_runtime": 1.4774,
|
| 262 |
+
"eval_samples_per_second": 392.581,
|
| 263 |
+
"eval_steps_per_second": 1.354,
|
| 264 |
+
"step": 1631
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 7.08,
|
| 268 |
+
"learning_rate": 1.6976633285646164e-05,
|
| 269 |
+
"loss": 0.1457,
|
| 270 |
+
"step": 1650
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 7.3,
|
| 274 |
+
"learning_rate": 1.681767604514386e-05,
|
| 275 |
+
"loss": 0.0861,
|
| 276 |
+
"step": 1700
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 7.51,
|
| 280 |
+
"learning_rate": 1.6658718804641553e-05,
|
| 281 |
+
"loss": 0.0852,
|
| 282 |
+
"step": 1750
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.73,
|
| 286 |
+
"learning_rate": 1.6499761564139248e-05,
|
| 287 |
+
"loss": 0.1283,
|
| 288 |
+
"step": 1800
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 7.94,
|
| 292 |
+
"learning_rate": 1.6340804323636943e-05,
|
| 293 |
+
"loss": 0.0956,
|
| 294 |
+
"step": 1850
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 8.0,
|
| 298 |
+
"eval_f1": 0.7998718228606326,
|
| 299 |
+
"eval_loss": 1.2174800634384155,
|
| 300 |
+
"eval_runtime": 1.5358,
|
| 301 |
+
"eval_samples_per_second": 377.658,
|
| 302 |
+
"eval_steps_per_second": 1.302,
|
| 303 |
+
"step": 1864
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.15,
|
| 307 |
+
"learning_rate": 1.6181847083134637e-05,
|
| 308 |
+
"loss": 0.0862,
|
| 309 |
+
"step": 1900
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 8.37,
|
| 313 |
+
"learning_rate": 1.6022889842632335e-05,
|
| 314 |
+
"loss": 0.0486,
|
| 315 |
+
"step": 1950
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 8.58,
|
| 319 |
+
"learning_rate": 1.5863932602130026e-05,
|
| 320 |
+
"loss": 0.0321,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 8.8,
|
| 325 |
+
"learning_rate": 1.5704975361627725e-05,
|
| 326 |
+
"loss": 0.0687,
|
| 327 |
+
"step": 2050
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 9.0,
|
| 331 |
+
"eval_f1": 0.789186529273271,
|
| 332 |
+
"eval_loss": 1.3646652698516846,
|
| 333 |
+
"eval_runtime": 1.5089,
|
| 334 |
+
"eval_samples_per_second": 384.398,
|
| 335 |
+
"eval_steps_per_second": 1.326,
|
| 336 |
+
"step": 2097
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 9.01,
|
| 340 |
+
"learning_rate": 1.554601812112542e-05,
|
| 341 |
+
"loss": 0.0522,
|
| 342 |
+
"step": 2100
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 9.23,
|
| 346 |
+
"learning_rate": 1.5387060880623114e-05,
|
| 347 |
+
"loss": 0.0349,
|
| 348 |
+
"step": 2150
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 9.44,
|
| 352 |
+
"learning_rate": 1.5228103640120809e-05,
|
| 353 |
+
"loss": 0.0529,
|
| 354 |
+
"step": 2200
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 9.66,
|
| 358 |
+
"learning_rate": 1.5069146399618503e-05,
|
| 359 |
+
"loss": 0.0284,
|
| 360 |
+
"step": 2250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 9.87,
|
| 364 |
+
"learning_rate": 1.49101891591162e-05,
|
| 365 |
+
"loss": 0.0371,
|
| 366 |
+
"step": 2300
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 10.0,
|
| 370 |
+
"eval_f1": 0.7986917021269787,
|
| 371 |
+
"eval_loss": 1.3809223175048828,
|
| 372 |
+
"eval_runtime": 1.6909,
|
| 373 |
+
"eval_samples_per_second": 343.007,
|
| 374 |
+
"eval_steps_per_second": 1.183,
|
| 375 |
+
"step": 2330
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 10.09,
|
| 379 |
+
"learning_rate": 1.4751231918613892e-05,
|
| 380 |
+
"loss": 0.0143,
|
| 381 |
+
"step": 2350
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 10.3,
|
| 385 |
+
"learning_rate": 1.4592274678111589e-05,
|
| 386 |
+
"loss": 0.0012,
|
| 387 |
+
"step": 2400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 10.52,
|
| 391 |
+
"learning_rate": 1.4433317437609285e-05,
|
| 392 |
+
"loss": 0.0117,
|
| 393 |
+
"step": 2450
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 10.73,
|
| 397 |
+
"learning_rate": 1.427436019710698e-05,
|
| 398 |
+
"loss": 0.0248,
|
| 399 |
+
"step": 2500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 10.94,
|
| 403 |
+
"learning_rate": 1.4115402956604673e-05,
|
| 404 |
+
"loss": 0.0303,
|
| 405 |
+
"step": 2550
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 11.0,
|
| 409 |
+
"eval_f1": 0.8123190611646329,
|
| 410 |
+
"eval_loss": 1.3591104745864868,
|
| 411 |
+
"eval_runtime": 1.57,
|
| 412 |
+
"eval_samples_per_second": 369.434,
|
| 413 |
+
"eval_steps_per_second": 1.274,
|
| 414 |
+
"step": 2563
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 11.16,
|
| 418 |
+
"learning_rate": 1.395644571610237e-05,
|
| 419 |
+
"loss": 0.0142,
|
| 420 |
+
"step": 2600
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 11.37,
|
| 424 |
+
"learning_rate": 1.3797488475600066e-05,
|
| 425 |
+
"loss": 0.0136,
|
| 426 |
+
"step": 2650
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 11.59,
|
| 430 |
+
"learning_rate": 1.363853123509776e-05,
|
| 431 |
+
"loss": 0.0126,
|
| 432 |
+
"step": 2700
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 11.8,
|
| 436 |
+
"learning_rate": 1.3479573994595455e-05,
|
| 437 |
+
"loss": 0.0263,
|
| 438 |
+
"step": 2750
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 12.0,
|
| 442 |
+
"eval_f1": 0.8100291935535177,
|
| 443 |
+
"eval_loss": 1.5316766500473022,
|
| 444 |
+
"eval_runtime": 1.5184,
|
| 445 |
+
"eval_samples_per_second": 381.982,
|
| 446 |
+
"eval_steps_per_second": 1.317,
|
| 447 |
+
"step": 2796
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 12.02,
|
| 451 |
+
"learning_rate": 1.332061675409315e-05,
|
| 452 |
+
"loss": 0.011,
|
| 453 |
+
"step": 2800
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 12.23,
|
| 457 |
+
"learning_rate": 1.3161659513590846e-05,
|
| 458 |
+
"loss": 0.0002,
|
| 459 |
+
"step": 2850
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 12.45,
|
| 463 |
+
"learning_rate": 1.300270227308854e-05,
|
| 464 |
+
"loss": 0.0057,
|
| 465 |
+
"step": 2900
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 12.66,
|
| 469 |
+
"learning_rate": 1.2843745032586235e-05,
|
| 470 |
+
"loss": 0.0016,
|
| 471 |
+
"step": 2950
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 12.88,
|
| 475 |
+
"learning_rate": 1.268478779208393e-05,
|
| 476 |
+
"loss": 0.0144,
|
| 477 |
+
"step": 3000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 13.0,
|
| 481 |
+
"eval_f1": 0.7959241618420011,
|
| 482 |
+
"eval_loss": 1.5725551843643188,
|
| 483 |
+
"eval_runtime": 1.4849,
|
| 484 |
+
"eval_samples_per_second": 390.601,
|
| 485 |
+
"eval_steps_per_second": 1.347,
|
| 486 |
+
"step": 3029
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 13.09,
|
| 490 |
+
"learning_rate": 1.2525830551581626e-05,
|
| 491 |
+
"loss": 0.006,
|
| 492 |
+
"step": 3050
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 13.3,
|
| 496 |
+
"learning_rate": 1.236687331107932e-05,
|
| 497 |
+
"loss": 0.0056,
|
| 498 |
+
"step": 3100
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 13.52,
|
| 502 |
+
"learning_rate": 1.2207916070577015e-05,
|
| 503 |
+
"loss": 0.0114,
|
| 504 |
+
"step": 3150
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 13.73,
|
| 508 |
+
"learning_rate": 1.204895883007471e-05,
|
| 509 |
+
"loss": 0.021,
|
| 510 |
+
"step": 3200
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 13.95,
|
| 514 |
+
"learning_rate": 1.1890001589572406e-05,
|
| 515 |
+
"loss": 0.0436,
|
| 516 |
+
"step": 3250
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 14.0,
|
| 520 |
+
"eval_f1": 0.7987626313618129,
|
| 521 |
+
"eval_loss": 1.6159876585006714,
|
| 522 |
+
"eval_runtime": 1.4555,
|
| 523 |
+
"eval_samples_per_second": 398.497,
|
| 524 |
+
"eval_steps_per_second": 1.374,
|
| 525 |
+
"step": 3262
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 14.16,
|
| 529 |
+
"learning_rate": 1.1731044349070103e-05,
|
| 530 |
+
"loss": 0.0002,
|
| 531 |
+
"step": 3300
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 14.38,
|
| 535 |
+
"learning_rate": 1.1572087108567796e-05,
|
| 536 |
+
"loss": 0.0062,
|
| 537 |
+
"step": 3350
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 14.59,
|
| 541 |
+
"learning_rate": 1.141312986806549e-05,
|
| 542 |
+
"loss": 0.0056,
|
| 543 |
+
"step": 3400
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 14.81,
|
| 547 |
+
"learning_rate": 1.1254172627563187e-05,
|
| 548 |
+
"loss": 0.0048,
|
| 549 |
+
"step": 3450
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 15.0,
|
| 553 |
+
"eval_f1": 0.7957479636902922,
|
| 554 |
+
"eval_loss": 1.6826026439666748,
|
| 555 |
+
"eval_runtime": 1.4617,
|
| 556 |
+
"eval_samples_per_second": 396.789,
|
| 557 |
+
"eval_steps_per_second": 1.368,
|
| 558 |
+
"step": 3495
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 15.02,
|
| 562 |
+
"learning_rate": 1.1095215387060883e-05,
|
| 563 |
+
"loss": 0.0039,
|
| 564 |
+
"step": 3500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 15.24,
|
| 568 |
+
"learning_rate": 1.0936258146558576e-05,
|
| 569 |
+
"loss": 0.0001,
|
| 570 |
+
"step": 3550
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 15.45,
|
| 574 |
+
"learning_rate": 1.0777300906056272e-05,
|
| 575 |
+
"loss": 0.0236,
|
| 576 |
+
"step": 3600
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 15.67,
|
| 580 |
+
"learning_rate": 1.0618343665553967e-05,
|
| 581 |
+
"loss": 0.0004,
|
| 582 |
+
"step": 3650
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 15.88,
|
| 586 |
+
"learning_rate": 1.0459386425051663e-05,
|
| 587 |
+
"loss": 0.0001,
|
| 588 |
+
"step": 3700
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 16.0,
|
| 592 |
+
"eval_f1": 0.7956639409293647,
|
| 593 |
+
"eval_loss": 1.6912556886672974,
|
| 594 |
+
"eval_runtime": 1.4563,
|
| 595 |
+
"eval_samples_per_second": 398.278,
|
| 596 |
+
"eval_steps_per_second": 1.373,
|
| 597 |
+
"step": 3728
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 16.09,
|
| 601 |
+
"learning_rate": 1.0300429184549356e-05,
|
| 602 |
+
"loss": 0.0002,
|
| 603 |
+
"step": 3750
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 16.31,
|
| 607 |
+
"learning_rate": 1.0141471944047053e-05,
|
| 608 |
+
"loss": 0.0002,
|
| 609 |
+
"step": 3800
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 16.52,
|
| 613 |
+
"learning_rate": 9.982514703544747e-06,
|
| 614 |
+
"loss": 0.0006,
|
| 615 |
+
"step": 3850
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 16.74,
|
| 619 |
+
"learning_rate": 9.823557463042442e-06,
|
| 620 |
+
"loss": 0.0002,
|
| 621 |
+
"step": 3900
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 16.95,
|
| 625 |
+
"learning_rate": 9.664600222540137e-06,
|
| 626 |
+
"loss": 0.0001,
|
| 627 |
+
"step": 3950
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 17.0,
|
| 631 |
+
"eval_f1": 0.7994751240525658,
|
| 632 |
+
"eval_loss": 1.7075979709625244,
|
| 633 |
+
"eval_runtime": 1.4886,
|
| 634 |
+
"eval_samples_per_second": 389.634,
|
| 635 |
+
"eval_steps_per_second": 1.344,
|
| 636 |
+
"step": 3961
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 17.17,
|
| 640 |
+
"learning_rate": 9.505642982037833e-06,
|
| 641 |
+
"loss": 0.0002,
|
| 642 |
+
"step": 4000
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 17.38,
|
| 646 |
+
"learning_rate": 9.346685741535528e-06,
|
| 647 |
+
"loss": 0.0185,
|
| 648 |
+
"step": 4050
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 17.6,
|
| 652 |
+
"learning_rate": 9.187728501033222e-06,
|
| 653 |
+
"loss": 0.0001,
|
| 654 |
+
"step": 4100
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 17.81,
|
| 658 |
+
"learning_rate": 9.028771260530917e-06,
|
| 659 |
+
"loss": 0.0034,
|
| 660 |
+
"step": 4150
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 18.0,
|
| 664 |
+
"eval_f1": 0.7960354805040918,
|
| 665 |
+
"eval_loss": 1.8018221855163574,
|
| 666 |
+
"eval_runtime": 1.5408,
|
| 667 |
+
"eval_samples_per_second": 376.422,
|
| 668 |
+
"eval_steps_per_second": 1.298,
|
| 669 |
+
"step": 4194
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 18.03,
|
| 673 |
+
"learning_rate": 8.869814020028613e-06,
|
| 674 |
+
"loss": 0.013,
|
| 675 |
+
"step": 4200
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 18.24,
|
| 679 |
+
"learning_rate": 8.710856779526308e-06,
|
| 680 |
+
"loss": 0.0003,
|
| 681 |
+
"step": 4250
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 18.45,
|
| 685 |
+
"learning_rate": 8.551899539024003e-06,
|
| 686 |
+
"loss": 0.0001,
|
| 687 |
+
"step": 4300
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 18.67,
|
| 691 |
+
"learning_rate": 8.392942298521697e-06,
|
| 692 |
+
"loss": 0.0002,
|
| 693 |
+
"step": 4350
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 18.88,
|
| 697 |
+
"learning_rate": 8.233985058019394e-06,
|
| 698 |
+
"loss": 0.0228,
|
| 699 |
+
"step": 4400
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 19.0,
|
| 703 |
+
"eval_f1": 0.7915974698658704,
|
| 704 |
+
"eval_loss": 1.7456856966018677,
|
| 705 |
+
"eval_runtime": 1.4762,
|
| 706 |
+
"eval_samples_per_second": 392.912,
|
| 707 |
+
"eval_steps_per_second": 1.355,
|
| 708 |
+
"step": 4427
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 19.1,
|
| 712 |
+
"learning_rate": 8.075027817517088e-06,
|
| 713 |
+
"loss": 0.0006,
|
| 714 |
+
"step": 4450
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 19.31,
|
| 718 |
+
"learning_rate": 7.916070577014783e-06,
|
| 719 |
+
"loss": 0.0037,
|
| 720 |
+
"step": 4500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 19.53,
|
| 724 |
+
"learning_rate": 7.757113336512478e-06,
|
| 725 |
+
"loss": 0.0314,
|
| 726 |
+
"step": 4550
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 19.74,
|
| 730 |
+
"learning_rate": 7.598156096010174e-06,
|
| 731 |
+
"loss": 0.0028,
|
| 732 |
+
"step": 4600
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 19.96,
|
| 736 |
+
"learning_rate": 7.439198855507869e-06,
|
| 737 |
+
"loss": 0.0083,
|
| 738 |
+
"step": 4650
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 20.0,
|
| 742 |
+
"eval_f1": 0.7868576028090374,
|
| 743 |
+
"eval_loss": 1.9279075860977173,
|
| 744 |
+
"eval_runtime": 1.4679,
|
| 745 |
+
"eval_samples_per_second": 395.119,
|
| 746 |
+
"eval_steps_per_second": 1.362,
|
| 747 |
+
"step": 4660
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 20.17,
|
| 751 |
+
"learning_rate": 7.280241615005564e-06,
|
| 752 |
+
"loss": 0.0009,
|
| 753 |
+
"step": 4700
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 20.39,
|
| 757 |
+
"learning_rate": 7.121284374503259e-06,
|
| 758 |
+
"loss": 0.0002,
|
| 759 |
+
"step": 4750
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 20.6,
|
| 763 |
+
"learning_rate": 6.962327134000954e-06,
|
| 764 |
+
"loss": 0.0082,
|
| 765 |
+
"step": 4800
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 20.82,
|
| 769 |
+
"learning_rate": 6.803369893498649e-06,
|
| 770 |
+
"loss": 0.0001,
|
| 771 |
+
"step": 4850
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 21.0,
|
| 775 |
+
"eval_f1": 0.7915377946685866,
|
| 776 |
+
"eval_loss": 1.8367053270339966,
|
| 777 |
+
"eval_runtime": 2.0999,
|
| 778 |
+
"eval_samples_per_second": 276.201,
|
| 779 |
+
"eval_steps_per_second": 0.952,
|
| 780 |
+
"step": 4893
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 21.03,
|
| 784 |
+
"learning_rate": 6.6444126529963445e-06,
|
| 785 |
+
"loss": 0.0001,
|
| 786 |
+
"step": 4900
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 21.24,
|
| 790 |
+
"learning_rate": 6.485455412494039e-06,
|
| 791 |
+
"loss": 0.0072,
|
| 792 |
+
"step": 4950
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 21.46,
|
| 796 |
+
"learning_rate": 6.326498171991735e-06,
|
| 797 |
+
"loss": 0.0,
|
| 798 |
+
"step": 5000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 21.67,
|
| 802 |
+
"learning_rate": 6.167540931489429e-06,
|
| 803 |
+
"loss": 0.0,
|
| 804 |
+
"step": 5050
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 21.89,
|
| 808 |
+
"learning_rate": 6.008583690987126e-06,
|
| 809 |
+
"loss": 0.0003,
|
| 810 |
+
"step": 5100
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 22.0,
|
| 814 |
+
"eval_f1": 0.7842117575951872,
|
| 815 |
+
"eval_loss": 1.8620420694351196,
|
| 816 |
+
"eval_runtime": 1.8603,
|
| 817 |
+
"eval_samples_per_second": 311.785,
|
| 818 |
+
"eval_steps_per_second": 1.075,
|
| 819 |
+
"step": 5126
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 22.1,
|
| 823 |
+
"learning_rate": 5.8496264504848195e-06,
|
| 824 |
+
"loss": 0.0007,
|
| 825 |
+
"step": 5150
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 22.32,
|
| 829 |
+
"learning_rate": 5.690669209982516e-06,
|
| 830 |
+
"loss": 0.0,
|
| 831 |
+
"step": 5200
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 22.53,
|
| 835 |
+
"learning_rate": 5.5317119694802105e-06,
|
| 836 |
+
"loss": 0.0021,
|
| 837 |
+
"step": 5250
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 22.75,
|
| 841 |
+
"learning_rate": 5.372754728977906e-06,
|
| 842 |
+
"loss": 0.0077,
|
| 843 |
+
"step": 5300
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 22.96,
|
| 847 |
+
"learning_rate": 5.213797488475601e-06,
|
| 848 |
+
"loss": 0.0002,
|
| 849 |
+
"step": 5350
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 23.0,
|
| 853 |
+
"eval_f1": 0.7828476594276503,
|
| 854 |
+
"eval_loss": 1.919188141822815,
|
| 855 |
+
"eval_runtime": 1.4859,
|
| 856 |
+
"eval_samples_per_second": 390.344,
|
| 857 |
+
"eval_steps_per_second": 1.346,
|
| 858 |
+
"step": 5359
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 23.18,
|
| 862 |
+
"learning_rate": 5.054840247973296e-06,
|
| 863 |
+
"loss": 0.0194,
|
| 864 |
+
"step": 5400
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 23.39,
|
| 868 |
+
"learning_rate": 4.895883007470991e-06,
|
| 869 |
+
"loss": 0.0132,
|
| 870 |
+
"step": 5450
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 23.61,
|
| 874 |
+
"learning_rate": 4.7369257669686855e-06,
|
| 875 |
+
"loss": 0.0001,
|
| 876 |
+
"step": 5500
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 23.82,
|
| 880 |
+
"learning_rate": 4.577968526466381e-06,
|
| 881 |
+
"loss": 0.0,
|
| 882 |
+
"step": 5550
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 24.0,
|
| 886 |
+
"eval_f1": 0.7927310235612234,
|
| 887 |
+
"eval_loss": 1.9081404209136963,
|
| 888 |
+
"eval_runtime": 1.4831,
|
| 889 |
+
"eval_samples_per_second": 391.082,
|
| 890 |
+
"eval_steps_per_second": 1.349,
|
| 891 |
+
"step": 5592
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 24.03,
|
| 895 |
+
"learning_rate": 4.419011285964076e-06,
|
| 896 |
+
"loss": 0.0,
|
| 897 |
+
"step": 5600
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 24.25,
|
| 901 |
+
"learning_rate": 4.260054045461771e-06,
|
| 902 |
+
"loss": 0.0001,
|
| 903 |
+
"step": 5650
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 24.46,
|
| 907 |
+
"learning_rate": 4.101096804959467e-06,
|
| 908 |
+
"loss": 0.0122,
|
| 909 |
+
"step": 5700
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 24.68,
|
| 913 |
+
"learning_rate": 3.942139564457161e-06,
|
| 914 |
+
"loss": 0.0,
|
| 915 |
+
"step": 5750
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 24.89,
|
| 919 |
+
"learning_rate": 3.7831823239548564e-06,
|
| 920 |
+
"loss": 0.0003,
|
| 921 |
+
"step": 5800
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 25.0,
|
| 925 |
+
"eval_f1": 0.7812550199347442,
|
| 926 |
+
"eval_loss": 1.9822450876235962,
|
| 927 |
+
"eval_runtime": 1.5174,
|
| 928 |
+
"eval_samples_per_second": 382.228,
|
| 929 |
+
"eval_steps_per_second": 1.318,
|
| 930 |
+
"step": 5825
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 25.11,
|
| 934 |
+
"learning_rate": 3.6242250834525515e-06,
|
| 935 |
+
"loss": 0.0116,
|
| 936 |
+
"step": 5850
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 25.32,
|
| 940 |
+
"learning_rate": 3.4652678429502466e-06,
|
| 941 |
+
"loss": 0.0,
|
| 942 |
+
"step": 5900
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 25.54,
|
| 946 |
+
"learning_rate": 3.306310602447942e-06,
|
| 947 |
+
"loss": 0.0004,
|
| 948 |
+
"step": 5950
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 25.75,
|
| 952 |
+
"learning_rate": 3.147353361945637e-06,
|
| 953 |
+
"loss": 0.0027,
|
| 954 |
+
"step": 6000
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 25.97,
|
| 958 |
+
"learning_rate": 2.9883961214433322e-06,
|
| 959 |
+
"loss": 0.0059,
|
| 960 |
+
"step": 6050
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 26.0,
|
| 964 |
+
"eval_f1": 0.7953953204096383,
|
| 965 |
+
"eval_loss": 1.8736791610717773,
|
| 966 |
+
"eval_runtime": 1.4646,
|
| 967 |
+
"eval_samples_per_second": 396.003,
|
| 968 |
+
"eval_steps_per_second": 1.366,
|
| 969 |
+
"step": 6058
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 26.18,
|
| 973 |
+
"learning_rate": 2.8294388809410273e-06,
|
| 974 |
+
"loss": 0.0001,
|
| 975 |
+
"step": 6100
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 26.39,
|
| 979 |
+
"learning_rate": 2.6704816404387224e-06,
|
| 980 |
+
"loss": 0.0,
|
| 981 |
+
"step": 6150
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 26.61,
|
| 985 |
+
"learning_rate": 2.5115243999364175e-06,
|
| 986 |
+
"loss": 0.0,
|
| 987 |
+
"step": 6200
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 26.82,
|
| 991 |
+
"learning_rate": 2.3525671594341126e-06,
|
| 992 |
+
"loss": 0.0,
|
| 993 |
+
"step": 6250
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 27.0,
|
| 997 |
+
"eval_f1": 0.7929217495075929,
|
| 998 |
+
"eval_loss": 1.879309892654419,
|
| 999 |
+
"eval_runtime": 1.9514,
|
| 1000 |
+
"eval_samples_per_second": 297.228,
|
| 1001 |
+
"eval_steps_per_second": 1.025,
|
| 1002 |
+
"step": 6291
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 27.04,
|
| 1006 |
+
"learning_rate": 2.1936099189318076e-06,
|
| 1007 |
+
"loss": 0.0,
|
| 1008 |
+
"step": 6300
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 27.25,
|
| 1012 |
+
"learning_rate": 2.0346526784295027e-06,
|
| 1013 |
+
"loss": 0.0,
|
| 1014 |
+
"step": 6350
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 27.47,
|
| 1018 |
+
"learning_rate": 1.8756954379271978e-06,
|
| 1019 |
+
"loss": 0.0111,
|
| 1020 |
+
"step": 6400
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 27.68,
|
| 1024 |
+
"learning_rate": 1.7167381974248929e-06,
|
| 1025 |
+
"loss": 0.0,
|
| 1026 |
+
"step": 6450
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 27.9,
|
| 1030 |
+
"learning_rate": 1.557780956922588e-06,
|
| 1031 |
+
"loss": 0.0,
|
| 1032 |
+
"step": 6500
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 28.0,
|
| 1036 |
+
"eval_f1": 0.794029634093503,
|
| 1037 |
+
"eval_loss": 1.8904625177383423,
|
| 1038 |
+
"eval_runtime": 2.2478,
|
| 1039 |
+
"eval_samples_per_second": 258.035,
|
| 1040 |
+
"eval_steps_per_second": 0.89,
|
| 1041 |
+
"step": 6524
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 28.11,
|
| 1045 |
+
"learning_rate": 1.398823716420283e-06,
|
| 1046 |
+
"loss": 0.0,
|
| 1047 |
+
"step": 6550
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 28.33,
|
| 1051 |
+
"learning_rate": 1.2398664759179781e-06,
|
| 1052 |
+
"loss": 0.0,
|
| 1053 |
+
"step": 6600
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 28.54,
|
| 1057 |
+
"learning_rate": 1.0809092354156734e-06,
|
| 1058 |
+
"loss": 0.0,
|
| 1059 |
+
"step": 6650
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 28.76,
|
| 1063 |
+
"learning_rate": 9.219519949133683e-07,
|
| 1064 |
+
"loss": 0.0,
|
| 1065 |
+
"step": 6700
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 28.97,
|
| 1069 |
+
"learning_rate": 7.629947544110635e-07,
|
| 1070 |
+
"loss": 0.0,
|
| 1071 |
+
"step": 6750
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 29.0,
|
| 1075 |
+
"eval_f1": 0.794029634093503,
|
| 1076 |
+
"eval_loss": 1.8970826864242554,
|
| 1077 |
+
"eval_runtime": 1.9492,
|
| 1078 |
+
"eval_samples_per_second": 297.551,
|
| 1079 |
+
"eval_steps_per_second": 1.026,
|
| 1080 |
+
"step": 6757
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 29.18,
|
| 1084 |
+
"learning_rate": 6.040375139087585e-07,
|
| 1085 |
+
"loss": 0.0,
|
| 1086 |
+
"step": 6800
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 29.4,
|
| 1090 |
+
"learning_rate": 4.450802734064537e-07,
|
| 1091 |
+
"loss": 0.0,
|
| 1092 |
+
"step": 6850
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 29.61,
|
| 1096 |
+
"learning_rate": 2.861230329041488e-07,
|
| 1097 |
+
"loss": 0.0,
|
| 1098 |
+
"step": 6900
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 29.83,
|
| 1102 |
+
"learning_rate": 1.2716579240184392e-07,
|
| 1103 |
+
"loss": 0.0002,
|
| 1104 |
+
"step": 6950
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 30.0,
|
| 1108 |
+
"eval_f1": 0.7954091951908298,
|
| 1109 |
+
"eval_loss": 1.9001948833465576,
|
| 1110 |
+
"eval_runtime": 1.8428,
|
| 1111 |
+
"eval_samples_per_second": 314.746,
|
| 1112 |
+
"eval_steps_per_second": 1.085,
|
| 1113 |
+
"step": 6990
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 30.0,
|
| 1117 |
+
"step": 6990,
|
| 1118 |
+
"total_flos": 5566168764425088.0,
|
| 1119 |
+
"train_loss": 0.16078996370909257,
|
| 1120 |
+
"train_runtime": 2045.6711,
|
| 1121 |
+
"train_samples_per_second": 54.496,
|
| 1122 |
+
"train_steps_per_second": 3.417
|
| 1123 |
+
}
|
| 1124 |
+
],
|
| 1125 |
+
"logging_steps": 50,
|
| 1126 |
+
"max_steps": 6990,
|
| 1127 |
+
"num_train_epochs": 30,
|
| 1128 |
+
"save_steps": 500,
|
| 1129 |
+
"total_flos": 5566168764425088.0,
|
| 1130 |
+
"trial_name": null,
|
| 1131 |
+
"trial_params": null
|
| 1132 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f7d007681c7fac4efe338744ae0ead6b261215bad92b4852a05a8e9b609f753
|
| 3 |
+
size 4536
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|