Upload folder using huggingface_hub
Browse files- README.md +64 -0
- checkpoint-2858/config.json +30 -0
- checkpoint-2858/model.safetensors +3 -0
- checkpoint-2858/optimizer.pt +3 -0
- checkpoint-2858/rng_state.pth +3 -0
- checkpoint-2858/scheduler.pt +3 -0
- checkpoint-2858/trainer_state.json +860 -0
- checkpoint-2858/training_args.bin +3 -0
- config.json +30 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Apr09_07-21-59_d72aa199956d/events.out.tfevents.1744183320.d72aa199956d.7773.0 +2 -2
- runs/Apr09_07-21-59_d72aa199956d/events.out.tfevents.1744183846.d72aa199956d.7773.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +60 -0
- training_args.bin +3 -0
- training_params.json +32 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- autotrain
|
| 6 |
+
- question-answering
|
| 7 |
+
base_model: deepset/roberta-base-squad2
|
| 8 |
+
widget:
|
| 9 |
+
- text: "Who loves AutoTrain?"
|
| 10 |
+
context: "Everyone loves AutoTrain"
|
| 11 |
+
datasets:
|
| 12 |
+
- VOKulus/test
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Model Trained Using AutoTrain
|
| 16 |
+
|
| 17 |
+
- Problem type: Extractive Question Answering
|
| 18 |
+
|
| 19 |
+
## Validation Metrics
|
| 20 |
+
|
| 21 |
+
loss: 6.235438195290044e-05
|
| 22 |
+
|
| 23 |
+
exact_match: 99.7703
|
| 24 |
+
|
| 25 |
+
f1: 99.8851
|
| 26 |
+
|
| 27 |
+
runtime: 18.3183
|
| 28 |
+
|
| 29 |
+
samples_per_second: 77.627
|
| 30 |
+
|
| 31 |
+
steps_per_second: 9.717
|
| 32 |
+
|
| 33 |
+
: 2.0
|
| 34 |
+
|
| 35 |
+
## Usage
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
```python
|
| 39 |
+
import torch
|
| 40 |
+
|
| 41 |
+
from transformers import AutoModelForQuestionAnswering, AutoTokenizer
|
| 42 |
+
|
| 43 |
+
model = AutoModelForQuestionAnswering.from_pretrained(...)
|
| 44 |
+
|
| 45 |
+
tokenizer = AutoTokenizer.from_pretrained(...)
|
| 46 |
+
|
| 47 |
+
from transformers import BertTokenizer, BertForQuestionAnswering
|
| 48 |
+
|
| 49 |
+
question, text = "Who loves AutoTrain?", "Everyone loves AutoTrain"
|
| 50 |
+
|
| 51 |
+
inputs = tokenizer(question, text, return_tensors='pt')
|
| 52 |
+
|
| 53 |
+
start_positions = torch.tensor([1])
|
| 54 |
+
|
| 55 |
+
end_positions = torch.tensor([3])
|
| 56 |
+
|
| 57 |
+
outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions)
|
| 58 |
+
|
| 59 |
+
loss = outputs.loss
|
| 60 |
+
|
| 61 |
+
start_scores = outputs.start_logits
|
| 62 |
+
|
| 63 |
+
end_scores = outputs.end_logits
|
| 64 |
+
```
|
checkpoint-2858/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepset/roberta-base-squad2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"language": "english",
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "roberta",
|
| 20 |
+
"name": "Roberta",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.48.0",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 50265
|
| 30 |
+
}
|
checkpoint-2858/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d9d1bde8b7624d84887bf84e5395e3cc1556658d2a7677a1b32e7734e09fa24
|
| 3 |
+
size 496250232
|
checkpoint-2858/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bb819b0991628d959e4c7393f6085c36476a7f8645c2bbe0ad2d10ef177fc9f
|
| 3 |
+
size 992619066
|
checkpoint-2858/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b68cf39d51ae0fda37757295ed75e9048e8a51b6fcb64a1285662054773cb22
|
| 3 |
+
size 14244
|
checkpoint-2858/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c2282cfd37433b089629f81059c258eb782f84a53354c61b9d9dbe616f7d530
|
| 3 |
+
size 1064
|
checkpoint-2858/trainer_state.json
ADDED
|
@@ -0,0 +1,860 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 6.235438195290044e-05,
|
| 3 |
+
"best_model_checkpoint": "my-model-test-roberta/checkpoint-2858",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2858,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01749475157452764,
|
| 13 |
+
"grad_norm": 130.36558532714844,
|
| 14 |
+
"learning_rate": 1.3986013986013987e-06,
|
| 15 |
+
"loss": 5.7756,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03498950314905528,
|
| 20 |
+
"grad_norm": 65.01083374023438,
|
| 21 |
+
"learning_rate": 3.0769230769230774e-06,
|
| 22 |
+
"loss": 3.2408,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.052484254723582924,
|
| 27 |
+
"grad_norm": 54.41019058227539,
|
| 28 |
+
"learning_rate": 4.8251748251748255e-06,
|
| 29 |
+
"loss": 1.8933,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06997900629811056,
|
| 34 |
+
"grad_norm": 66.41553497314453,
|
| 35 |
+
"learning_rate": 6.573426573426574e-06,
|
| 36 |
+
"loss": 1.2565,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08747375787263821,
|
| 41 |
+
"grad_norm": 32.627281188964844,
|
| 42 |
+
"learning_rate": 8.321678321678323e-06,
|
| 43 |
+
"loss": 0.7743,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10496850944716585,
|
| 48 |
+
"grad_norm": 46.808109283447266,
|
| 49 |
+
"learning_rate": 1.0069930069930071e-05,
|
| 50 |
+
"loss": 0.4214,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1224632610216935,
|
| 55 |
+
"grad_norm": 77.44200897216797,
|
| 56 |
+
"learning_rate": 1.181818181818182e-05,
|
| 57 |
+
"loss": 0.4034,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13995801259622112,
|
| 62 |
+
"grad_norm": 52.945068359375,
|
| 63 |
+
"learning_rate": 1.3566433566433568e-05,
|
| 64 |
+
"loss": 0.2332,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15745276417074877,
|
| 69 |
+
"grad_norm": 0.948405921459198,
|
| 70 |
+
"learning_rate": 1.5314685314685317e-05,
|
| 71 |
+
"loss": 0.1798,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17494751574527642,
|
| 76 |
+
"grad_norm": 0.12931326031684875,
|
| 77 |
+
"learning_rate": 1.7062937062937065e-05,
|
| 78 |
+
"loss": 0.0596,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.19244226731980407,
|
| 83 |
+
"grad_norm": 0.5479409098625183,
|
| 84 |
+
"learning_rate": 1.881118881118881e-05,
|
| 85 |
+
"loss": 0.0956,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2099370188943317,
|
| 90 |
+
"grad_norm": 163.63729858398438,
|
| 91 |
+
"learning_rate": 1.9937791601866253e-05,
|
| 92 |
+
"loss": 0.2539,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.22743177046885935,
|
| 97 |
+
"grad_norm": 0.04818764701485634,
|
| 98 |
+
"learning_rate": 1.974339035769829e-05,
|
| 99 |
+
"loss": 0.116,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.244926522043387,
|
| 104 |
+
"grad_norm": 0.11932364106178284,
|
| 105 |
+
"learning_rate": 1.954898911353033e-05,
|
| 106 |
+
"loss": 0.0437,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2624212736179146,
|
| 111 |
+
"grad_norm": 0.0045976778492331505,
|
| 112 |
+
"learning_rate": 1.9354587869362366e-05,
|
| 113 |
+
"loss": 0.0842,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.27991602519244224,
|
| 118 |
+
"grad_norm": 0.051815927028656006,
|
| 119 |
+
"learning_rate": 1.9160186625194403e-05,
|
| 120 |
+
"loss": 0.0512,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2974107767669699,
|
| 125 |
+
"grad_norm": 0.02530599944293499,
|
| 126 |
+
"learning_rate": 1.896578538102644e-05,
|
| 127 |
+
"loss": 0.0019,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.31490552834149754,
|
| 132 |
+
"grad_norm": 0.14514470100402832,
|
| 133 |
+
"learning_rate": 1.877138413685848e-05,
|
| 134 |
+
"loss": 0.0056,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.33240027991602517,
|
| 139 |
+
"grad_norm": 303.62939453125,
|
| 140 |
+
"learning_rate": 1.8576982892690513e-05,
|
| 141 |
+
"loss": 0.1492,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.34989503149055284,
|
| 146 |
+
"grad_norm": 0.003696146886795759,
|
| 147 |
+
"learning_rate": 1.8382581648522554e-05,
|
| 148 |
+
"loss": 0.0045,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.36738978306508047,
|
| 153 |
+
"grad_norm": 20.425518035888672,
|
| 154 |
+
"learning_rate": 1.818818040435459e-05,
|
| 155 |
+
"loss": 0.0463,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.38488453463960814,
|
| 160 |
+
"grad_norm": 0.09205462783575058,
|
| 161 |
+
"learning_rate": 1.7993779160186625e-05,
|
| 162 |
+
"loss": 0.0017,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.40237928621413577,
|
| 167 |
+
"grad_norm": 0.038981515914201736,
|
| 168 |
+
"learning_rate": 1.7799377916018663e-05,
|
| 169 |
+
"loss": 0.0606,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4198740377886634,
|
| 174 |
+
"grad_norm": 0.1848757266998291,
|
| 175 |
+
"learning_rate": 1.76049766718507e-05,
|
| 176 |
+
"loss": 0.0559,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.43736878936319107,
|
| 181 |
+
"grad_norm": 0.0069680167362093925,
|
| 182 |
+
"learning_rate": 1.7410575427682738e-05,
|
| 183 |
+
"loss": 0.0523,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4548635409377187,
|
| 188 |
+
"grad_norm": 0.011184507980942726,
|
| 189 |
+
"learning_rate": 1.7216174183514775e-05,
|
| 190 |
+
"loss": 0.0003,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4723582925122463,
|
| 195 |
+
"grad_norm": 0.011598587967455387,
|
| 196 |
+
"learning_rate": 1.7021772939346813e-05,
|
| 197 |
+
"loss": 0.0901,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.489853044086774,
|
| 202 |
+
"grad_norm": 0.7256177067756653,
|
| 203 |
+
"learning_rate": 1.682737169517885e-05,
|
| 204 |
+
"loss": 0.0006,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5073477956613016,
|
| 209 |
+
"grad_norm": 0.002232016297057271,
|
| 210 |
+
"learning_rate": 1.6632970451010888e-05,
|
| 211 |
+
"loss": 0.0017,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5248425472358292,
|
| 216 |
+
"grad_norm": 0.0009716423810459673,
|
| 217 |
+
"learning_rate": 1.6438569206842926e-05,
|
| 218 |
+
"loss": 0.0654,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5423372988103569,
|
| 223 |
+
"grad_norm": 2.8868448734283447,
|
| 224 |
+
"learning_rate": 1.6244167962674963e-05,
|
| 225 |
+
"loss": 0.0003,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5598320503848845,
|
| 230 |
+
"grad_norm": 0.002249341458082199,
|
| 231 |
+
"learning_rate": 1.6049766718507e-05,
|
| 232 |
+
"loss": 0.0002,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5773268019594122,
|
| 237 |
+
"grad_norm": 0.0035393834114074707,
|
| 238 |
+
"learning_rate": 1.5855365474339038e-05,
|
| 239 |
+
"loss": 0.0006,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5948215535339398,
|
| 244 |
+
"grad_norm": 0.007113989442586899,
|
| 245 |
+
"learning_rate": 1.5660964230171072e-05,
|
| 246 |
+
"loss": 0.0002,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6123163051084675,
|
| 251 |
+
"grad_norm": 0.813864529132843,
|
| 252 |
+
"learning_rate": 1.546656298600311e-05,
|
| 253 |
+
"loss": 0.0004,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6298110566829951,
|
| 258 |
+
"grad_norm": 0.04794127866625786,
|
| 259 |
+
"learning_rate": 1.527216174183515e-05,
|
| 260 |
+
"loss": 0.0003,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6473058082575227,
|
| 265 |
+
"grad_norm": 0.0020588026382029057,
|
| 266 |
+
"learning_rate": 1.5077760497667187e-05,
|
| 267 |
+
"loss": 0.0333,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6648005598320503,
|
| 272 |
+
"grad_norm": 4.8790507316589355,
|
| 273 |
+
"learning_rate": 1.4883359253499223e-05,
|
| 274 |
+
"loss": 0.0038,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6822953114065781,
|
| 279 |
+
"grad_norm": 0.5302098989486694,
|
| 280 |
+
"learning_rate": 1.468895800933126e-05,
|
| 281 |
+
"loss": 0.0062,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6997900629811057,
|
| 286 |
+
"grad_norm": 0.0019412849796935916,
|
| 287 |
+
"learning_rate": 1.44945567651633e-05,
|
| 288 |
+
"loss": 0.0001,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7172848145556333,
|
| 293 |
+
"grad_norm": 0.00042624305933713913,
|
| 294 |
+
"learning_rate": 1.4300155520995335e-05,
|
| 295 |
+
"loss": 0.0002,
|
| 296 |
+
"step": 1025
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7347795661301609,
|
| 300 |
+
"grad_norm": 0.002252366626635194,
|
| 301 |
+
"learning_rate": 1.4105754276827373e-05,
|
| 302 |
+
"loss": 0.0,
|
| 303 |
+
"step": 1050
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7522743177046886,
|
| 307 |
+
"grad_norm": 0.0027475322131067514,
|
| 308 |
+
"learning_rate": 1.3911353032659409e-05,
|
| 309 |
+
"loss": 0.0566,
|
| 310 |
+
"step": 1075
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7697690692792163,
|
| 314 |
+
"grad_norm": 0.009604093618690968,
|
| 315 |
+
"learning_rate": 1.3716951788491448e-05,
|
| 316 |
+
"loss": 0.002,
|
| 317 |
+
"step": 1100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7872638208537439,
|
| 321 |
+
"grad_norm": 0.0056050559505820274,
|
| 322 |
+
"learning_rate": 1.3522550544323485e-05,
|
| 323 |
+
"loss": 0.0131,
|
| 324 |
+
"step": 1125
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8047585724282715,
|
| 328 |
+
"grad_norm": 0.0009983275085687637,
|
| 329 |
+
"learning_rate": 1.3328149300155521e-05,
|
| 330 |
+
"loss": 0.0055,
|
| 331 |
+
"step": 1150
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8222533240027992,
|
| 335 |
+
"grad_norm": 0.000412652239901945,
|
| 336 |
+
"learning_rate": 1.3133748055987559e-05,
|
| 337 |
+
"loss": 0.0352,
|
| 338 |
+
"step": 1175
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8397480755773268,
|
| 342 |
+
"grad_norm": 0.002874561119824648,
|
| 343 |
+
"learning_rate": 1.2939346811819598e-05,
|
| 344 |
+
"loss": 0.0006,
|
| 345 |
+
"step": 1200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8572428271518544,
|
| 349 |
+
"grad_norm": 0.01263987272977829,
|
| 350 |
+
"learning_rate": 1.2744945567651634e-05,
|
| 351 |
+
"loss": 0.0378,
|
| 352 |
+
"step": 1225
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8747375787263821,
|
| 356 |
+
"grad_norm": 0.007837435230612755,
|
| 357 |
+
"learning_rate": 1.2550544323483671e-05,
|
| 358 |
+
"loss": 0.0001,
|
| 359 |
+
"step": 1250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8922323303009098,
|
| 363 |
+
"grad_norm": 0.0008695307769812644,
|
| 364 |
+
"learning_rate": 1.2356143079315707e-05,
|
| 365 |
+
"loss": 0.0011,
|
| 366 |
+
"step": 1275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9097270818754374,
|
| 370 |
+
"grad_norm": 0.0004545428091660142,
|
| 371 |
+
"learning_rate": 1.2161741835147746e-05,
|
| 372 |
+
"loss": 0.0001,
|
| 373 |
+
"step": 1300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.927221833449965,
|
| 377 |
+
"grad_norm": 0.014842044562101364,
|
| 378 |
+
"learning_rate": 1.1967340590979784e-05,
|
| 379 |
+
"loss": 0.0,
|
| 380 |
+
"step": 1325
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9447165850244926,
|
| 384 |
+
"grad_norm": 0.008039949461817741,
|
| 385 |
+
"learning_rate": 1.177293934681182e-05,
|
| 386 |
+
"loss": 0.0017,
|
| 387 |
+
"step": 1350
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9622113365990203,
|
| 391 |
+
"grad_norm": 0.0005223533953540027,
|
| 392 |
+
"learning_rate": 1.1578538102643857e-05,
|
| 393 |
+
"loss": 0.0004,
|
| 394 |
+
"step": 1375
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.979706088173548,
|
| 398 |
+
"grad_norm": 0.0010761632584035397,
|
| 399 |
+
"learning_rate": 1.1384136858475897e-05,
|
| 400 |
+
"loss": 0.0001,
|
| 401 |
+
"step": 1400
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9972008397480756,
|
| 405 |
+
"grad_norm": 0.0003285344282630831,
|
| 406 |
+
"learning_rate": 1.1189735614307932e-05,
|
| 407 |
+
"loss": 0.0,
|
| 408 |
+
"step": 1425
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.0,
|
| 412 |
+
"eval_exact_match": 100.0,
|
| 413 |
+
"eval_f1": 100.0,
|
| 414 |
+
"eval_loss": 0.005018405616283417,
|
| 415 |
+
"eval_runtime": 17.7026,
|
| 416 |
+
"eval_samples_per_second": 80.327,
|
| 417 |
+
"eval_steps_per_second": 10.055,
|
| 418 |
+
"step": 1429
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.0146955913226032,
|
| 422 |
+
"grad_norm": 0.0008568214834667742,
|
| 423 |
+
"learning_rate": 1.099533437013997e-05,
|
| 424 |
+
"loss": 0.0,
|
| 425 |
+
"step": 1450
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.0321903428971309,
|
| 429 |
+
"grad_norm": 0.0027714003808796406,
|
| 430 |
+
"learning_rate": 1.0800933125972006e-05,
|
| 431 |
+
"loss": 0.0,
|
| 432 |
+
"step": 1475
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.0496850944716585,
|
| 436 |
+
"grad_norm": 0.0010522945085540414,
|
| 437 |
+
"learning_rate": 1.0606531881804045e-05,
|
| 438 |
+
"loss": 0.0,
|
| 439 |
+
"step": 1500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.067179846046186,
|
| 443 |
+
"grad_norm": 0.0003821647842414677,
|
| 444 |
+
"learning_rate": 1.0412130637636083e-05,
|
| 445 |
+
"loss": 0.0,
|
| 446 |
+
"step": 1525
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.0846745976207137,
|
| 450 |
+
"grad_norm": 0.0006792128551751375,
|
| 451 |
+
"learning_rate": 1.0217729393468118e-05,
|
| 452 |
+
"loss": 0.0,
|
| 453 |
+
"step": 1550
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.1021693491952413,
|
| 457 |
+
"grad_norm": 0.0005681074107997119,
|
| 458 |
+
"learning_rate": 1.0023328149300156e-05,
|
| 459 |
+
"loss": 0.0,
|
| 460 |
+
"step": 1575
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.119664100769769,
|
| 464 |
+
"grad_norm": 0.001575466594658792,
|
| 465 |
+
"learning_rate": 9.828926905132194e-06,
|
| 466 |
+
"loss": 0.02,
|
| 467 |
+
"step": 1600
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.1371588523442968,
|
| 471 |
+
"grad_norm": 0.0008907430456019938,
|
| 472 |
+
"learning_rate": 9.634525660964231e-06,
|
| 473 |
+
"loss": 0.0015,
|
| 474 |
+
"step": 1625
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.1546536039188244,
|
| 478 |
+
"grad_norm": 0.3030645549297333,
|
| 479 |
+
"learning_rate": 9.440124416796269e-06,
|
| 480 |
+
"loss": 0.0,
|
| 481 |
+
"step": 1650
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.172148355493352,
|
| 485 |
+
"grad_norm": 0.000742213916964829,
|
| 486 |
+
"learning_rate": 9.245723172628306e-06,
|
| 487 |
+
"loss": 0.0617,
|
| 488 |
+
"step": 1675
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.1896431070678797,
|
| 492 |
+
"grad_norm": 0.0004069434362463653,
|
| 493 |
+
"learning_rate": 9.051321928460342e-06,
|
| 494 |
+
"loss": 0.0001,
|
| 495 |
+
"step": 1700
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.2071378586424073,
|
| 499 |
+
"grad_norm": 0.0017081464175134897,
|
| 500 |
+
"learning_rate": 8.856920684292381e-06,
|
| 501 |
+
"loss": 0.0,
|
| 502 |
+
"step": 1725
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.224632610216935,
|
| 506 |
+
"grad_norm": 0.0006449994398280978,
|
| 507 |
+
"learning_rate": 8.662519440124417e-06,
|
| 508 |
+
"loss": 0.0,
|
| 509 |
+
"step": 1750
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.2421273617914625,
|
| 513 |
+
"grad_norm": 1.1132986545562744,
|
| 514 |
+
"learning_rate": 8.468118195956455e-06,
|
| 515 |
+
"loss": 0.0151,
|
| 516 |
+
"step": 1775
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.2596221133659902,
|
| 520 |
+
"grad_norm": 0.0004918717895634472,
|
| 521 |
+
"learning_rate": 8.273716951788492e-06,
|
| 522 |
+
"loss": 0.0012,
|
| 523 |
+
"step": 1800
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.2771168649405178,
|
| 527 |
+
"grad_norm": 0.0007090566796250641,
|
| 528 |
+
"learning_rate": 8.07931570762053e-06,
|
| 529 |
+
"loss": 0.0136,
|
| 530 |
+
"step": 1825
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.2946116165150454,
|
| 534 |
+
"grad_norm": 0.020147522911429405,
|
| 535 |
+
"learning_rate": 7.884914463452567e-06,
|
| 536 |
+
"loss": 0.0002,
|
| 537 |
+
"step": 1850
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.312106368089573,
|
| 541 |
+
"grad_norm": 0.0021832261700183153,
|
| 542 |
+
"learning_rate": 7.690513219284605e-06,
|
| 543 |
+
"loss": 0.0001,
|
| 544 |
+
"step": 1875
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.3296011196641007,
|
| 548 |
+
"grad_norm": 0.028366833925247192,
|
| 549 |
+
"learning_rate": 7.496111975116641e-06,
|
| 550 |
+
"loss": 0.0,
|
| 551 |
+
"step": 1900
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.3470958712386283,
|
| 555 |
+
"grad_norm": 0.0010503004305064678,
|
| 556 |
+
"learning_rate": 7.301710730948679e-06,
|
| 557 |
+
"loss": 0.0007,
|
| 558 |
+
"step": 1925
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.3645906228131561,
|
| 562 |
+
"grad_norm": 0.008805891498923302,
|
| 563 |
+
"learning_rate": 7.107309486780716e-06,
|
| 564 |
+
"loss": 0.033,
|
| 565 |
+
"step": 1950
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.3820853743876838,
|
| 569 |
+
"grad_norm": 0.021400198340415955,
|
| 570 |
+
"learning_rate": 6.912908242612753e-06,
|
| 571 |
+
"loss": 0.0,
|
| 572 |
+
"step": 1975
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.3995801259622114,
|
| 576 |
+
"grad_norm": 0.0005948548787273467,
|
| 577 |
+
"learning_rate": 6.71850699844479e-06,
|
| 578 |
+
"loss": 0.0,
|
| 579 |
+
"step": 2000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.417074877536739,
|
| 583 |
+
"grad_norm": 0.0006943101761862636,
|
| 584 |
+
"learning_rate": 6.524105754276828e-06,
|
| 585 |
+
"loss": 0.0,
|
| 586 |
+
"step": 2025
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.4345696291112666,
|
| 590 |
+
"grad_norm": 0.0013550578150898218,
|
| 591 |
+
"learning_rate": 6.329704510108865e-06,
|
| 592 |
+
"loss": 0.0,
|
| 593 |
+
"step": 2050
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.4520643806857942,
|
| 597 |
+
"grad_norm": 0.0002896255755331367,
|
| 598 |
+
"learning_rate": 6.135303265940903e-06,
|
| 599 |
+
"loss": 0.0,
|
| 600 |
+
"step": 2075
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.4695591322603219,
|
| 604 |
+
"grad_norm": 0.0011648598592728376,
|
| 605 |
+
"learning_rate": 5.940902021772939e-06,
|
| 606 |
+
"loss": 0.0001,
|
| 607 |
+
"step": 2100
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 1.4870538838348495,
|
| 611 |
+
"grad_norm": 0.020712416619062424,
|
| 612 |
+
"learning_rate": 5.746500777604978e-06,
|
| 613 |
+
"loss": 0.0,
|
| 614 |
+
"step": 2125
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.5045486354093773,
|
| 618 |
+
"grad_norm": 0.0005796013865619898,
|
| 619 |
+
"learning_rate": 5.5520995334370144e-06,
|
| 620 |
+
"loss": 0.0005,
|
| 621 |
+
"step": 2150
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.522043386983905,
|
| 625 |
+
"grad_norm": 0.014175205491483212,
|
| 626 |
+
"learning_rate": 5.357698289269052e-06,
|
| 627 |
+
"loss": 0.0015,
|
| 628 |
+
"step": 2175
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.5395381385584326,
|
| 632 |
+
"grad_norm": 7.142549991607666,
|
| 633 |
+
"learning_rate": 5.163297045101089e-06,
|
| 634 |
+
"loss": 0.0215,
|
| 635 |
+
"step": 2200
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.5570328901329602,
|
| 639 |
+
"grad_norm": 0.0004311289812903851,
|
| 640 |
+
"learning_rate": 4.968895800933126e-06,
|
| 641 |
+
"loss": 0.0,
|
| 642 |
+
"step": 2225
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.5745276417074878,
|
| 646 |
+
"grad_norm": 0.0007753855898045003,
|
| 647 |
+
"learning_rate": 4.774494556765164e-06,
|
| 648 |
+
"loss": 0.0,
|
| 649 |
+
"step": 2250
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.5920223932820154,
|
| 653 |
+
"grad_norm": 0.0002963803126476705,
|
| 654 |
+
"learning_rate": 4.5800933125972005e-06,
|
| 655 |
+
"loss": 0.0,
|
| 656 |
+
"step": 2275
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 1.609517144856543,
|
| 660 |
+
"grad_norm": 0.0010399603052064776,
|
| 661 |
+
"learning_rate": 4.385692068429238e-06,
|
| 662 |
+
"loss": 0.0,
|
| 663 |
+
"step": 2300
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.6270118964310707,
|
| 667 |
+
"grad_norm": 0.000952723843511194,
|
| 668 |
+
"learning_rate": 4.1912908242612755e-06,
|
| 669 |
+
"loss": 0.0,
|
| 670 |
+
"step": 2325
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.6445066480055983,
|
| 674 |
+
"grad_norm": 0.00023090622562449425,
|
| 675 |
+
"learning_rate": 3.996889580093313e-06,
|
| 676 |
+
"loss": 0.0,
|
| 677 |
+
"step": 2350
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.662001399580126,
|
| 681 |
+
"grad_norm": 0.008954511024057865,
|
| 682 |
+
"learning_rate": 3.80248833592535e-06,
|
| 683 |
+
"loss": 0.0003,
|
| 684 |
+
"step": 2375
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.6794961511546536,
|
| 688 |
+
"grad_norm": 0.0010821650503203273,
|
| 689 |
+
"learning_rate": 3.6080870917573873e-06,
|
| 690 |
+
"loss": 0.0,
|
| 691 |
+
"step": 2400
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.6969909027291812,
|
| 695 |
+
"grad_norm": 0.0006221202784217894,
|
| 696 |
+
"learning_rate": 3.413685847589425e-06,
|
| 697 |
+
"loss": 0.0214,
|
| 698 |
+
"step": 2425
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.7144856543037088,
|
| 702 |
+
"grad_norm": 0.004466580227017403,
|
| 703 |
+
"learning_rate": 3.219284603421462e-06,
|
| 704 |
+
"loss": 0.0,
|
| 705 |
+
"step": 2450
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.7319804058782364,
|
| 709 |
+
"grad_norm": 0.002296778140589595,
|
| 710 |
+
"learning_rate": 3.024883359253499e-06,
|
| 711 |
+
"loss": 0.0015,
|
| 712 |
+
"step": 2475
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.749475157452764,
|
| 716 |
+
"grad_norm": 0.00047575862845405936,
|
| 717 |
+
"learning_rate": 2.8304821150855366e-06,
|
| 718 |
+
"loss": 0.0,
|
| 719 |
+
"step": 2500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.7669699090272917,
|
| 723 |
+
"grad_norm": 0.0030999884475022554,
|
| 724 |
+
"learning_rate": 2.6360808709175738e-06,
|
| 725 |
+
"loss": 0.0,
|
| 726 |
+
"step": 2525
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 1.7844646606018193,
|
| 730 |
+
"grad_norm": 0.04565088450908661,
|
| 731 |
+
"learning_rate": 2.4416796267496113e-06,
|
| 732 |
+
"loss": 0.0003,
|
| 733 |
+
"step": 2550
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.8019594121763471,
|
| 737 |
+
"grad_norm": 0.003935549408197403,
|
| 738 |
+
"learning_rate": 2.247278382581649e-06,
|
| 739 |
+
"loss": 0.0,
|
| 740 |
+
"step": 2575
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.8194541637508748,
|
| 744 |
+
"grad_norm": 0.0007768659852445126,
|
| 745 |
+
"learning_rate": 2.052877138413686e-06,
|
| 746 |
+
"loss": 0.0001,
|
| 747 |
+
"step": 2600
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.8369489153254024,
|
| 751 |
+
"grad_norm": 9.082518577575684,
|
| 752 |
+
"learning_rate": 1.8584758942457235e-06,
|
| 753 |
+
"loss": 0.0007,
|
| 754 |
+
"step": 2625
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.85444366689993,
|
| 758 |
+
"grad_norm": 0.00017582898726686835,
|
| 759 |
+
"learning_rate": 1.6640746500777608e-06,
|
| 760 |
+
"loss": 0.0,
|
| 761 |
+
"step": 2650
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.8719384184744576,
|
| 765 |
+
"grad_norm": 0.0005721878260374069,
|
| 766 |
+
"learning_rate": 1.4696734059097982e-06,
|
| 767 |
+
"loss": 0.0,
|
| 768 |
+
"step": 2675
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.8894331700489853,
|
| 772 |
+
"grad_norm": 0.0014160927385091782,
|
| 773 |
+
"learning_rate": 1.2752721617418353e-06,
|
| 774 |
+
"loss": 0.0,
|
| 775 |
+
"step": 2700
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.906927921623513,
|
| 779 |
+
"grad_norm": 0.0003491580719128251,
|
| 780 |
+
"learning_rate": 1.0808709175738726e-06,
|
| 781 |
+
"loss": 0.0,
|
| 782 |
+
"step": 2725
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.9244226731980407,
|
| 786 |
+
"grad_norm": 0.00031783856684342027,
|
| 787 |
+
"learning_rate": 8.864696734059098e-07,
|
| 788 |
+
"loss": 0.0,
|
| 789 |
+
"step": 2750
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.9419174247725683,
|
| 793 |
+
"grad_norm": 0.0011913523776456714,
|
| 794 |
+
"learning_rate": 6.920684292379472e-07,
|
| 795 |
+
"loss": 0.0001,
|
| 796 |
+
"step": 2775
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.959412176347096,
|
| 800 |
+
"grad_norm": 0.0027918724808841944,
|
| 801 |
+
"learning_rate": 4.976671850699845e-07,
|
| 802 |
+
"loss": 0.0,
|
| 803 |
+
"step": 2800
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.9769069279216236,
|
| 807 |
+
"grad_norm": 0.002089190762490034,
|
| 808 |
+
"learning_rate": 3.032659409020218e-07,
|
| 809 |
+
"loss": 0.0037,
|
| 810 |
+
"step": 2825
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.9944016794961512,
|
| 814 |
+
"grad_norm": 0.0003496000135783106,
|
| 815 |
+
"learning_rate": 1.088646967340591e-07,
|
| 816 |
+
"loss": 0.0,
|
| 817 |
+
"step": 2850
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.0,
|
| 821 |
+
"eval_exact_match": 99.7703,
|
| 822 |
+
"eval_f1": 99.8851,
|
| 823 |
+
"eval_loss": 6.235438195290044e-05,
|
| 824 |
+
"eval_runtime": 18.4334,
|
| 825 |
+
"eval_samples_per_second": 77.143,
|
| 826 |
+
"eval_steps_per_second": 9.656,
|
| 827 |
+
"step": 2858
|
| 828 |
+
}
|
| 829 |
+
],
|
| 830 |
+
"logging_steps": 25,
|
| 831 |
+
"max_steps": 2858,
|
| 832 |
+
"num_input_tokens_seen": 0,
|
| 833 |
+
"num_train_epochs": 2,
|
| 834 |
+
"save_steps": 500,
|
| 835 |
+
"stateful_callbacks": {
|
| 836 |
+
"EarlyStoppingCallback": {
|
| 837 |
+
"args": {
|
| 838 |
+
"early_stopping_patience": 5,
|
| 839 |
+
"early_stopping_threshold": 0.01
|
| 840 |
+
},
|
| 841 |
+
"attributes": {
|
| 842 |
+
"early_stopping_patience_counter": 1
|
| 843 |
+
}
|
| 844 |
+
},
|
| 845 |
+
"TrainerControl": {
|
| 846 |
+
"args": {
|
| 847 |
+
"should_epoch_stop": false,
|
| 848 |
+
"should_evaluate": false,
|
| 849 |
+
"should_log": false,
|
| 850 |
+
"should_save": true,
|
| 851 |
+
"should_training_stop": true
|
| 852 |
+
},
|
| 853 |
+
"attributes": {}
|
| 854 |
+
}
|
| 855 |
+
},
|
| 856 |
+
"total_flos": 2986621929492480.0,
|
| 857 |
+
"train_batch_size": 4,
|
| 858 |
+
"trial_name": null,
|
| 859 |
+
"trial_params": null
|
| 860 |
+
}
|
checkpoint-2858/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e10234dc1d4393c789f6886e8c45d4fa1c50db25477b6f263223c0983b048889
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepset/roberta-base-squad2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"language": "english",
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "roberta",
|
| 20 |
+
"name": "Roberta",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.48.0",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 50265
|
| 30 |
+
}
|
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 sha256:4d9d1bde8b7624d84887bf84e5395e3cc1556658d2a7677a1b32e7734e09fa24
|
| 3 |
+
size 496250232
|
runs/Apr09_07-21-59_d72aa199956d/events.out.tfevents.1744183320.d72aa199956d.7773.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43cb6364399072b4e123fbbbce9a9776d97d2ee2c70d7a49a97db2367d6ab856
|
| 3 |
+
size 30289
|
runs/Apr09_07-21-59_d72aa199956d/events.out.tfevents.1744183846.d72aa199956d.7773.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b204507b6743200391c0ea5130bb5c20da17f7186637e6e4b2d4868c56707705
|
| 3 |
+
size 460
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "</s>",
|
| 50 |
+
"errors": "replace",
|
| 51 |
+
"extra_special_tokens": {},
|
| 52 |
+
"full_tokenizer_file": null,
|
| 53 |
+
"mask_token": "<mask>",
|
| 54 |
+
"model_max_length": 512,
|
| 55 |
+
"pad_token": "<pad>",
|
| 56 |
+
"sep_token": "</s>",
|
| 57 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 58 |
+
"trim_offsets": true,
|
| 59 |
+
"unk_token": "<unk>"
|
| 60 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e10234dc1d4393c789f6886e8c45d4fa1c50db25477b6f263223c0983b048889
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "VOKulus/test",
|
| 3 |
+
"model": "deepset/roberta-base-squad2",
|
| 4 |
+
"lr": 2e-05,
|
| 5 |
+
"epochs": 2,
|
| 6 |
+
"max_seq_length": 512,
|
| 7 |
+
"max_doc_stride": 128,
|
| 8 |
+
"batch_size": 4,
|
| 9 |
+
"warmup_ratio": 0.1,
|
| 10 |
+
"gradient_accumulation": 1,
|
| 11 |
+
"optimizer": "adamw_torch",
|
| 12 |
+
"scheduler": "linear",
|
| 13 |
+
"weight_decay": 0.0,
|
| 14 |
+
"max_grad_norm": 1.0,
|
| 15 |
+
"seed": 42,
|
| 16 |
+
"train_split": "train",
|
| 17 |
+
"valid_split": "validation",
|
| 18 |
+
"text_column": "context",
|
| 19 |
+
"question_column": "question",
|
| 20 |
+
"answer_column": "answer",
|
| 21 |
+
"logging_steps": -1,
|
| 22 |
+
"project_name": "my-model-test-roberta",
|
| 23 |
+
"auto_find_batch_size": false,
|
| 24 |
+
"mixed_precision": "fp16",
|
| 25 |
+
"save_total_limit": 1,
|
| 26 |
+
"push_to_hub": true,
|
| 27 |
+
"eval_strategy": "epoch",
|
| 28 |
+
"username": "VOKulus",
|
| 29 |
+
"log": "tensorboard",
|
| 30 |
+
"early_stopping_patience": 5,
|
| 31 |
+
"early_stopping_threshold": 0.01
|
| 32 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|