Upload folder using huggingface_hub
Browse files- README.md +79 -0
- all_results.json +22 -0
- checkpoint-14858/config.json +33 -0
- checkpoint-14858/merges.txt +0 -0
- checkpoint-14858/model.safetensors +3 -0
- checkpoint-14858/optimizer.pt +3 -0
- checkpoint-14858/rng_state.pth +3 -0
- checkpoint-14858/scheduler.pt +3 -0
- checkpoint-14858/special_tokens_map.json +15 -0
- checkpoint-14858/tokenizer.json +0 -0
- checkpoint-14858/tokenizer_config.json +57 -0
- checkpoint-14858/trainer_state.json +276 -0
- checkpoint-14858/training_args.bin +3 -0
- checkpoint-14858/vocab.json +0 -0
- config.json +33 -0
- dr_results.json +8 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- ood_results.json +8 -0
- special_tokens_map.json +15 -0
- test_results.json +8 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- train_results.json +7 -0
- trainer_state.json +300 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: FacebookAI/roberta-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: roberta-large
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# roberta-large
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5329
|
| 21 |
+
- Accuracy: 0.9121
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 32
|
| 42 |
+
- eval_batch_size: 256
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 20
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 52 |
+
| No log | 1.0 | 782 | 0.2406 | 0.8990 |
|
| 53 |
+
| 0.3075 | 2.0 | 1564 | 0.2539 | 0.8962 |
|
| 54 |
+
| 0.2171 | 3.0 | 2346 | 0.2650 | 0.9031 |
|
| 55 |
+
| 0.1697 | 4.0 | 3128 | 0.3427 | 0.8973 |
|
| 56 |
+
| 0.1697 | 5.0 | 3910 | 0.3241 | 0.9031 |
|
| 57 |
+
| 0.1339 | 6.0 | 4692 | 0.4141 | 0.9049 |
|
| 58 |
+
| 0.1038 | 7.0 | 5474 | 0.4572 | 0.8946 |
|
| 59 |
+
| 0.0922 | 8.0 | 6256 | 0.4154 | 0.9054 |
|
| 60 |
+
| 0.0676 | 9.0 | 7038 | 0.5020 | 0.8982 |
|
| 61 |
+
| 0.0676 | 10.0 | 7820 | 0.5070 | 0.9071 |
|
| 62 |
+
| 0.0568 | 11.0 | 8602 | 0.4826 | 0.9067 |
|
| 63 |
+
| 0.0443 | 12.0 | 9384 | 0.5104 | 0.9086 |
|
| 64 |
+
| 0.0313 | 13.0 | 10166 | 0.5456 | 0.9088 |
|
| 65 |
+
| 0.0313 | 14.0 | 10948 | 0.4740 | 0.9078 |
|
| 66 |
+
| 0.0245 | 15.0 | 11730 | 0.4977 | 0.9071 |
|
| 67 |
+
| 0.0227 | 16.0 | 12512 | 0.5136 | 0.9098 |
|
| 68 |
+
| 0.0175 | 17.0 | 13294 | 0.5131 | 0.9108 |
|
| 69 |
+
| 0.0173 | 18.0 | 14076 | 0.5370 | 0.9109 |
|
| 70 |
+
| 0.0173 | 19.0 | 14858 | 0.5344 | 0.9126 |
|
| 71 |
+
| 0.0152 | 20.0 | 15640 | 0.5329 | 0.9121 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.37.2
|
| 77 |
+
- Pytorch 2.3.0+cu121
|
| 78 |
+
- Datasets 2.19.0
|
| 79 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dr_accuracy": 0.99824,
|
| 3 |
+
"dr_loss": 0.012910463847219944,
|
| 4 |
+
"dr_runtime": 102.0036,
|
| 5 |
+
"dr_samples_per_second": 245.089,
|
| 6 |
+
"dr_steps_per_second": 0.961,
|
| 7 |
+
"epoch": 20.0,
|
| 8 |
+
"ood_accuracy": 0.8437441380604014,
|
| 9 |
+
"ood_loss": 0.9615365266799927,
|
| 10 |
+
"ood_runtime": 39.9719,
|
| 11 |
+
"ood_samples_per_second": 266.737,
|
| 12 |
+
"ood_steps_per_second": 1.051,
|
| 13 |
+
"test_accuracy": 0.9126,
|
| 14 |
+
"test_loss": 0.5343945026397705,
|
| 15 |
+
"test_runtime": 101.9284,
|
| 16 |
+
"test_samples_per_second": 245.27,
|
| 17 |
+
"test_steps_per_second": 0.961,
|
| 18 |
+
"train_loss": 0.08507246678442601,
|
| 19 |
+
"train_runtime": 7726.1299,
|
| 20 |
+
"train_samples_per_second": 64.715,
|
| 21 |
+
"train_steps_per_second": 2.024
|
| 22 |
+
}
|
checkpoint-14858/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "FacebookAI/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 |
+
"finetuning_task": "text-classification",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 4096,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"0": 0,
|
| 18 |
+
"1": 1
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-05,
|
| 21 |
+
"max_position_embeddings": 514,
|
| 22 |
+
"model_type": "roberta",
|
| 23 |
+
"num_attention_heads": 16,
|
| 24 |
+
"num_hidden_layers": 24,
|
| 25 |
+
"pad_token_id": 1,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "single_label_classification",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.37.2",
|
| 30 |
+
"type_vocab_size": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 50265
|
| 33 |
+
}
|
checkpoint-14858/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-14858/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3a8e9551804807aaa2b6149c7701b8b88e3d8c437f28e8feacfb844d0b088c9
|
| 3 |
+
size 1421495416
|
checkpoint-14858/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a84d8375fcff8312ea8da868dc2d3e2d2533b316c48e700c8f8eec732cd69a84
|
| 3 |
+
size 2843223277
|
checkpoint-14858/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abda2406ce0720c925d26d48f15d32ec3379fa6f1645793e5f31e83dff13ff33
|
| 3 |
+
size 14244
|
checkpoint-14858/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a72ebeda5a47fbdd197aeee66d013851097c00d88509ddfc6697daab2a2bd2b
|
| 3 |
+
size 1064
|
checkpoint-14858/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 |
+
}
|
checkpoint-14858/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-14858/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
checkpoint-14858/trainer_state.json
ADDED
|
@@ -0,0 +1,276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9126,
|
| 3 |
+
"best_model_checkpoint": "../../checkpoint/imdb/roberta-large/checkpoint-14858",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 14858,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.89904,
|
| 14 |
+
"eval_loss": 0.2406211644411087,
|
| 15 |
+
"eval_runtime": 103.5694,
|
| 16 |
+
"eval_samples_per_second": 241.384,
|
| 17 |
+
"eval_steps_per_second": 0.946,
|
| 18 |
+
"step": 782
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.28,
|
| 22 |
+
"learning_rate": 4.680306905370844e-05,
|
| 23 |
+
"loss": 0.3075,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.8962,
|
| 29 |
+
"eval_loss": 0.2538779377937317,
|
| 30 |
+
"eval_runtime": 102.8426,
|
| 31 |
+
"eval_samples_per_second": 243.09,
|
| 32 |
+
"eval_steps_per_second": 0.953,
|
| 33 |
+
"step": 1564
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.56,
|
| 37 |
+
"learning_rate": 4.360613810741688e-05,
|
| 38 |
+
"loss": 0.2171,
|
| 39 |
+
"step": 2000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_accuracy": 0.90308,
|
| 44 |
+
"eval_loss": 0.2649693489074707,
|
| 45 |
+
"eval_runtime": 102.9465,
|
| 46 |
+
"eval_samples_per_second": 242.844,
|
| 47 |
+
"eval_steps_per_second": 0.952,
|
| 48 |
+
"step": 2346
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.84,
|
| 52 |
+
"learning_rate": 4.040920716112532e-05,
|
| 53 |
+
"loss": 0.1697,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"eval_accuracy": 0.89728,
|
| 59 |
+
"eval_loss": 0.3427022695541382,
|
| 60 |
+
"eval_runtime": 103.0024,
|
| 61 |
+
"eval_samples_per_second": 242.713,
|
| 62 |
+
"eval_steps_per_second": 0.951,
|
| 63 |
+
"step": 3128
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
+
"eval_accuracy": 0.90308,
|
| 68 |
+
"eval_loss": 0.3241328001022339,
|
| 69 |
+
"eval_runtime": 102.9184,
|
| 70 |
+
"eval_samples_per_second": 242.911,
|
| 71 |
+
"eval_steps_per_second": 0.952,
|
| 72 |
+
"step": 3910
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.12,
|
| 76 |
+
"learning_rate": 3.721227621483376e-05,
|
| 77 |
+
"loss": 0.1339,
|
| 78 |
+
"step": 4000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"eval_accuracy": 0.90492,
|
| 83 |
+
"eval_loss": 0.41408097743988037,
|
| 84 |
+
"eval_runtime": 102.8464,
|
| 85 |
+
"eval_samples_per_second": 243.081,
|
| 86 |
+
"eval_steps_per_second": 0.953,
|
| 87 |
+
"step": 4692
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.39,
|
| 91 |
+
"learning_rate": 3.40153452685422e-05,
|
| 92 |
+
"loss": 0.1038,
|
| 93 |
+
"step": 5000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"eval_accuracy": 0.8946,
|
| 98 |
+
"eval_loss": 0.45717746019363403,
|
| 99 |
+
"eval_runtime": 102.3334,
|
| 100 |
+
"eval_samples_per_second": 244.299,
|
| 101 |
+
"eval_steps_per_second": 0.958,
|
| 102 |
+
"step": 5474
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.67,
|
| 106 |
+
"learning_rate": 3.081841432225064e-05,
|
| 107 |
+
"loss": 0.0922,
|
| 108 |
+
"step": 6000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 8.0,
|
| 112 |
+
"eval_accuracy": 0.9054,
|
| 113 |
+
"eval_loss": 0.4153657555580139,
|
| 114 |
+
"eval_runtime": 102.2979,
|
| 115 |
+
"eval_samples_per_second": 244.384,
|
| 116 |
+
"eval_steps_per_second": 0.958,
|
| 117 |
+
"step": 6256
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 8.95,
|
| 121 |
+
"learning_rate": 2.7621483375959077e-05,
|
| 122 |
+
"loss": 0.0676,
|
| 123 |
+
"step": 7000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 9.0,
|
| 127 |
+
"eval_accuracy": 0.89824,
|
| 128 |
+
"eval_loss": 0.5019603371620178,
|
| 129 |
+
"eval_runtime": 102.1481,
|
| 130 |
+
"eval_samples_per_second": 244.743,
|
| 131 |
+
"eval_steps_per_second": 0.959,
|
| 132 |
+
"step": 7038
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 10.0,
|
| 136 |
+
"eval_accuracy": 0.90708,
|
| 137 |
+
"eval_loss": 0.507008969783783,
|
| 138 |
+
"eval_runtime": 102.4086,
|
| 139 |
+
"eval_samples_per_second": 244.12,
|
| 140 |
+
"eval_steps_per_second": 0.957,
|
| 141 |
+
"step": 7820
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.23,
|
| 145 |
+
"learning_rate": 2.442455242966752e-05,
|
| 146 |
+
"loss": 0.0568,
|
| 147 |
+
"step": 8000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 11.0,
|
| 151 |
+
"eval_accuracy": 0.90668,
|
| 152 |
+
"eval_loss": 0.48255667090415955,
|
| 153 |
+
"eval_runtime": 102.2755,
|
| 154 |
+
"eval_samples_per_second": 244.438,
|
| 155 |
+
"eval_steps_per_second": 0.958,
|
| 156 |
+
"step": 8602
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 11.51,
|
| 160 |
+
"learning_rate": 2.122762148337596e-05,
|
| 161 |
+
"loss": 0.0443,
|
| 162 |
+
"step": 9000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 12.0,
|
| 166 |
+
"eval_accuracy": 0.90856,
|
| 167 |
+
"eval_loss": 0.5103762745857239,
|
| 168 |
+
"eval_runtime": 102.4293,
|
| 169 |
+
"eval_samples_per_second": 244.071,
|
| 170 |
+
"eval_steps_per_second": 0.957,
|
| 171 |
+
"step": 9384
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.79,
|
| 175 |
+
"learning_rate": 1.80306905370844e-05,
|
| 176 |
+
"loss": 0.0313,
|
| 177 |
+
"step": 10000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"eval_accuracy": 0.90884,
|
| 182 |
+
"eval_loss": 0.545563817024231,
|
| 183 |
+
"eval_runtime": 101.9339,
|
| 184 |
+
"eval_samples_per_second": 245.257,
|
| 185 |
+
"eval_steps_per_second": 0.961,
|
| 186 |
+
"step": 10166
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 14.0,
|
| 190 |
+
"eval_accuracy": 0.90776,
|
| 191 |
+
"eval_loss": 0.47395065426826477,
|
| 192 |
+
"eval_runtime": 102.2186,
|
| 193 |
+
"eval_samples_per_second": 244.574,
|
| 194 |
+
"eval_steps_per_second": 0.959,
|
| 195 |
+
"step": 10948
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 14.07,
|
| 199 |
+
"learning_rate": 1.483375959079284e-05,
|
| 200 |
+
"loss": 0.0245,
|
| 201 |
+
"step": 11000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 15.0,
|
| 205 |
+
"eval_accuracy": 0.90712,
|
| 206 |
+
"eval_loss": 0.4977429211139679,
|
| 207 |
+
"eval_runtime": 102.2005,
|
| 208 |
+
"eval_samples_per_second": 244.617,
|
| 209 |
+
"eval_steps_per_second": 0.959,
|
| 210 |
+
"step": 11730
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 15.35,
|
| 214 |
+
"learning_rate": 1.163682864450128e-05,
|
| 215 |
+
"loss": 0.0227,
|
| 216 |
+
"step": 12000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 16.0,
|
| 220 |
+
"eval_accuracy": 0.90984,
|
| 221 |
+
"eval_loss": 0.5135776400566101,
|
| 222 |
+
"eval_runtime": 102.5324,
|
| 223 |
+
"eval_samples_per_second": 243.825,
|
| 224 |
+
"eval_steps_per_second": 0.956,
|
| 225 |
+
"step": 12512
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 16.62,
|
| 229 |
+
"learning_rate": 8.439897698209718e-06,
|
| 230 |
+
"loss": 0.0175,
|
| 231 |
+
"step": 13000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 17.0,
|
| 235 |
+
"eval_accuracy": 0.91076,
|
| 236 |
+
"eval_loss": 0.5130705833435059,
|
| 237 |
+
"eval_runtime": 102.0766,
|
| 238 |
+
"eval_samples_per_second": 244.914,
|
| 239 |
+
"eval_steps_per_second": 0.96,
|
| 240 |
+
"step": 13294
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 17.9,
|
| 244 |
+
"learning_rate": 5.242966751918159e-06,
|
| 245 |
+
"loss": 0.0173,
|
| 246 |
+
"step": 14000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"eval_accuracy": 0.91092,
|
| 251 |
+
"eval_loss": 0.5370119214057922,
|
| 252 |
+
"eval_runtime": 102.316,
|
| 253 |
+
"eval_samples_per_second": 244.341,
|
| 254 |
+
"eval_steps_per_second": 0.958,
|
| 255 |
+
"step": 14076
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 19.0,
|
| 259 |
+
"eval_accuracy": 0.9126,
|
| 260 |
+
"eval_loss": 0.5343945026397705,
|
| 261 |
+
"eval_runtime": 102.4054,
|
| 262 |
+
"eval_samples_per_second": 244.128,
|
| 263 |
+
"eval_steps_per_second": 0.957,
|
| 264 |
+
"step": 14858
|
| 265 |
+
}
|
| 266 |
+
],
|
| 267 |
+
"logging_steps": 1000,
|
| 268 |
+
"max_steps": 15640,
|
| 269 |
+
"num_input_tokens_seen": 0,
|
| 270 |
+
"num_train_epochs": 20,
|
| 271 |
+
"save_steps": 500,
|
| 272 |
+
"total_flos": 1.106668493952e+17,
|
| 273 |
+
"train_batch_size": 32,
|
| 274 |
+
"trial_name": null,
|
| 275 |
+
"trial_params": null
|
| 276 |
+
}
|
checkpoint-14858/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da80ea56a9719bc4599c7ca4a4cb6abbbb962c564c55b6570d50342c22772ad3
|
| 3 |
+
size 4792
|
checkpoint-14858/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "FacebookAI/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 |
+
"finetuning_task": "text-classification",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 4096,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"0": 0,
|
| 18 |
+
"1": 1
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-05,
|
| 21 |
+
"max_position_embeddings": 514,
|
| 22 |
+
"model_type": "roberta",
|
| 23 |
+
"num_attention_heads": 16,
|
| 24 |
+
"num_hidden_layers": 24,
|
| 25 |
+
"pad_token_id": 1,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "single_label_classification",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.37.2",
|
| 30 |
+
"type_vocab_size": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 50265
|
| 33 |
+
}
|
dr_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dr_accuracy": 0.99824,
|
| 3 |
+
"dr_loss": 0.012910463847219944,
|
| 4 |
+
"dr_runtime": 102.0036,
|
| 5 |
+
"dr_samples_per_second": 245.089,
|
| 6 |
+
"dr_steps_per_second": 0.961,
|
| 7 |
+
"epoch": 20.0
|
| 8 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3a8e9551804807aaa2b6149c7701b8b88e3d8c437f28e8feacfb844d0b088c9
|
| 3 |
+
size 1421495416
|
ood_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"ood_accuracy": 0.8437441380604014,
|
| 4 |
+
"ood_loss": 0.9615365266799927,
|
| 5 |
+
"ood_runtime": 39.9719,
|
| 6 |
+
"ood_samples_per_second": 266.737,
|
| 7 |
+
"ood_steps_per_second": 1.051
|
| 8 |
+
}
|
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 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"test_accuracy": 0.9126,
|
| 4 |
+
"test_loss": 0.5343945026397705,
|
| 5 |
+
"test_runtime": 101.9284,
|
| 6 |
+
"test_samples_per_second": 245.27,
|
| 7 |
+
"test_steps_per_second": 0.961
|
| 8 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.08507246678442601,
|
| 4 |
+
"train_runtime": 7726.1299,
|
| 5 |
+
"train_samples_per_second": 64.715,
|
| 6 |
+
"train_steps_per_second": 2.024
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9126,
|
| 3 |
+
"best_model_checkpoint": "../../checkpoint/imdb/roberta-large/checkpoint-14858",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 15640,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.89904,
|
| 14 |
+
"eval_loss": 0.2406211644411087,
|
| 15 |
+
"eval_runtime": 103.5694,
|
| 16 |
+
"eval_samples_per_second": 241.384,
|
| 17 |
+
"eval_steps_per_second": 0.946,
|
| 18 |
+
"step": 782
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.28,
|
| 22 |
+
"learning_rate": 4.680306905370844e-05,
|
| 23 |
+
"loss": 0.3075,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.8962,
|
| 29 |
+
"eval_loss": 0.2538779377937317,
|
| 30 |
+
"eval_runtime": 102.8426,
|
| 31 |
+
"eval_samples_per_second": 243.09,
|
| 32 |
+
"eval_steps_per_second": 0.953,
|
| 33 |
+
"step": 1564
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.56,
|
| 37 |
+
"learning_rate": 4.360613810741688e-05,
|
| 38 |
+
"loss": 0.2171,
|
| 39 |
+
"step": 2000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_accuracy": 0.90308,
|
| 44 |
+
"eval_loss": 0.2649693489074707,
|
| 45 |
+
"eval_runtime": 102.9465,
|
| 46 |
+
"eval_samples_per_second": 242.844,
|
| 47 |
+
"eval_steps_per_second": 0.952,
|
| 48 |
+
"step": 2346
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.84,
|
| 52 |
+
"learning_rate": 4.040920716112532e-05,
|
| 53 |
+
"loss": 0.1697,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"eval_accuracy": 0.89728,
|
| 59 |
+
"eval_loss": 0.3427022695541382,
|
| 60 |
+
"eval_runtime": 103.0024,
|
| 61 |
+
"eval_samples_per_second": 242.713,
|
| 62 |
+
"eval_steps_per_second": 0.951,
|
| 63 |
+
"step": 3128
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
+
"eval_accuracy": 0.90308,
|
| 68 |
+
"eval_loss": 0.3241328001022339,
|
| 69 |
+
"eval_runtime": 102.9184,
|
| 70 |
+
"eval_samples_per_second": 242.911,
|
| 71 |
+
"eval_steps_per_second": 0.952,
|
| 72 |
+
"step": 3910
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.12,
|
| 76 |
+
"learning_rate": 3.721227621483376e-05,
|
| 77 |
+
"loss": 0.1339,
|
| 78 |
+
"step": 4000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"eval_accuracy": 0.90492,
|
| 83 |
+
"eval_loss": 0.41408097743988037,
|
| 84 |
+
"eval_runtime": 102.8464,
|
| 85 |
+
"eval_samples_per_second": 243.081,
|
| 86 |
+
"eval_steps_per_second": 0.953,
|
| 87 |
+
"step": 4692
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.39,
|
| 91 |
+
"learning_rate": 3.40153452685422e-05,
|
| 92 |
+
"loss": 0.1038,
|
| 93 |
+
"step": 5000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"eval_accuracy": 0.8946,
|
| 98 |
+
"eval_loss": 0.45717746019363403,
|
| 99 |
+
"eval_runtime": 102.3334,
|
| 100 |
+
"eval_samples_per_second": 244.299,
|
| 101 |
+
"eval_steps_per_second": 0.958,
|
| 102 |
+
"step": 5474
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.67,
|
| 106 |
+
"learning_rate": 3.081841432225064e-05,
|
| 107 |
+
"loss": 0.0922,
|
| 108 |
+
"step": 6000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 8.0,
|
| 112 |
+
"eval_accuracy": 0.9054,
|
| 113 |
+
"eval_loss": 0.4153657555580139,
|
| 114 |
+
"eval_runtime": 102.2979,
|
| 115 |
+
"eval_samples_per_second": 244.384,
|
| 116 |
+
"eval_steps_per_second": 0.958,
|
| 117 |
+
"step": 6256
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 8.95,
|
| 121 |
+
"learning_rate": 2.7621483375959077e-05,
|
| 122 |
+
"loss": 0.0676,
|
| 123 |
+
"step": 7000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 9.0,
|
| 127 |
+
"eval_accuracy": 0.89824,
|
| 128 |
+
"eval_loss": 0.5019603371620178,
|
| 129 |
+
"eval_runtime": 102.1481,
|
| 130 |
+
"eval_samples_per_second": 244.743,
|
| 131 |
+
"eval_steps_per_second": 0.959,
|
| 132 |
+
"step": 7038
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 10.0,
|
| 136 |
+
"eval_accuracy": 0.90708,
|
| 137 |
+
"eval_loss": 0.507008969783783,
|
| 138 |
+
"eval_runtime": 102.4086,
|
| 139 |
+
"eval_samples_per_second": 244.12,
|
| 140 |
+
"eval_steps_per_second": 0.957,
|
| 141 |
+
"step": 7820
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.23,
|
| 145 |
+
"learning_rate": 2.442455242966752e-05,
|
| 146 |
+
"loss": 0.0568,
|
| 147 |
+
"step": 8000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 11.0,
|
| 151 |
+
"eval_accuracy": 0.90668,
|
| 152 |
+
"eval_loss": 0.48255667090415955,
|
| 153 |
+
"eval_runtime": 102.2755,
|
| 154 |
+
"eval_samples_per_second": 244.438,
|
| 155 |
+
"eval_steps_per_second": 0.958,
|
| 156 |
+
"step": 8602
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 11.51,
|
| 160 |
+
"learning_rate": 2.122762148337596e-05,
|
| 161 |
+
"loss": 0.0443,
|
| 162 |
+
"step": 9000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 12.0,
|
| 166 |
+
"eval_accuracy": 0.90856,
|
| 167 |
+
"eval_loss": 0.5103762745857239,
|
| 168 |
+
"eval_runtime": 102.4293,
|
| 169 |
+
"eval_samples_per_second": 244.071,
|
| 170 |
+
"eval_steps_per_second": 0.957,
|
| 171 |
+
"step": 9384
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.79,
|
| 175 |
+
"learning_rate": 1.80306905370844e-05,
|
| 176 |
+
"loss": 0.0313,
|
| 177 |
+
"step": 10000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"eval_accuracy": 0.90884,
|
| 182 |
+
"eval_loss": 0.545563817024231,
|
| 183 |
+
"eval_runtime": 101.9339,
|
| 184 |
+
"eval_samples_per_second": 245.257,
|
| 185 |
+
"eval_steps_per_second": 0.961,
|
| 186 |
+
"step": 10166
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 14.0,
|
| 190 |
+
"eval_accuracy": 0.90776,
|
| 191 |
+
"eval_loss": 0.47395065426826477,
|
| 192 |
+
"eval_runtime": 102.2186,
|
| 193 |
+
"eval_samples_per_second": 244.574,
|
| 194 |
+
"eval_steps_per_second": 0.959,
|
| 195 |
+
"step": 10948
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 14.07,
|
| 199 |
+
"learning_rate": 1.483375959079284e-05,
|
| 200 |
+
"loss": 0.0245,
|
| 201 |
+
"step": 11000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 15.0,
|
| 205 |
+
"eval_accuracy": 0.90712,
|
| 206 |
+
"eval_loss": 0.4977429211139679,
|
| 207 |
+
"eval_runtime": 102.2005,
|
| 208 |
+
"eval_samples_per_second": 244.617,
|
| 209 |
+
"eval_steps_per_second": 0.959,
|
| 210 |
+
"step": 11730
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 15.35,
|
| 214 |
+
"learning_rate": 1.163682864450128e-05,
|
| 215 |
+
"loss": 0.0227,
|
| 216 |
+
"step": 12000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 16.0,
|
| 220 |
+
"eval_accuracy": 0.90984,
|
| 221 |
+
"eval_loss": 0.5135776400566101,
|
| 222 |
+
"eval_runtime": 102.5324,
|
| 223 |
+
"eval_samples_per_second": 243.825,
|
| 224 |
+
"eval_steps_per_second": 0.956,
|
| 225 |
+
"step": 12512
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 16.62,
|
| 229 |
+
"learning_rate": 8.439897698209718e-06,
|
| 230 |
+
"loss": 0.0175,
|
| 231 |
+
"step": 13000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 17.0,
|
| 235 |
+
"eval_accuracy": 0.91076,
|
| 236 |
+
"eval_loss": 0.5130705833435059,
|
| 237 |
+
"eval_runtime": 102.0766,
|
| 238 |
+
"eval_samples_per_second": 244.914,
|
| 239 |
+
"eval_steps_per_second": 0.96,
|
| 240 |
+
"step": 13294
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 17.9,
|
| 244 |
+
"learning_rate": 5.242966751918159e-06,
|
| 245 |
+
"loss": 0.0173,
|
| 246 |
+
"step": 14000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"eval_accuracy": 0.91092,
|
| 251 |
+
"eval_loss": 0.5370119214057922,
|
| 252 |
+
"eval_runtime": 102.316,
|
| 253 |
+
"eval_samples_per_second": 244.341,
|
| 254 |
+
"eval_steps_per_second": 0.958,
|
| 255 |
+
"step": 14076
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 19.0,
|
| 259 |
+
"eval_accuracy": 0.9126,
|
| 260 |
+
"eval_loss": 0.5343945026397705,
|
| 261 |
+
"eval_runtime": 102.4054,
|
| 262 |
+
"eval_samples_per_second": 244.128,
|
| 263 |
+
"eval_steps_per_second": 0.957,
|
| 264 |
+
"step": 14858
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 19.18,
|
| 268 |
+
"learning_rate": 2.0460358056265987e-06,
|
| 269 |
+
"loss": 0.0152,
|
| 270 |
+
"step": 15000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 20.0,
|
| 274 |
+
"eval_accuracy": 0.91212,
|
| 275 |
+
"eval_loss": 0.5329343676567078,
|
| 276 |
+
"eval_runtime": 102.1338,
|
| 277 |
+
"eval_samples_per_second": 244.777,
|
| 278 |
+
"eval_steps_per_second": 0.96,
|
| 279 |
+
"step": 15640
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 20.0,
|
| 283 |
+
"step": 15640,
|
| 284 |
+
"total_flos": 1.16491420416e+17,
|
| 285 |
+
"train_loss": 0.08507246678442601,
|
| 286 |
+
"train_runtime": 7726.1299,
|
| 287 |
+
"train_samples_per_second": 64.715,
|
| 288 |
+
"train_steps_per_second": 2.024
|
| 289 |
+
}
|
| 290 |
+
],
|
| 291 |
+
"logging_steps": 1000,
|
| 292 |
+
"max_steps": 15640,
|
| 293 |
+
"num_input_tokens_seen": 0,
|
| 294 |
+
"num_train_epochs": 20,
|
| 295 |
+
"save_steps": 500,
|
| 296 |
+
"total_flos": 1.16491420416e+17,
|
| 297 |
+
"train_batch_size": 32,
|
| 298 |
+
"trial_name": null,
|
| 299 |
+
"trial_params": null
|
| 300 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da80ea56a9719bc4599c7ca4a4cb6abbbb962c564c55b6570d50342c22772ad3
|
| 3 |
+
size 4792
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|