Upload folder using huggingface_hub
Browse files- README.md +26 -0
- checkpoint-80/config.json +38 -0
- checkpoint-80/model.safetensors +3 -0
- checkpoint-80/optimizer.pt +3 -0
- checkpoint-80/rng_state.pth +3 -0
- checkpoint-80/scheduler.pt +3 -0
- checkpoint-80/trainer_state.json +706 -0
- checkpoint-80/training_args.bin +3 -0
- config.json +38 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jan07_10-38-13_r-khaled-auwad-roberta-fine-tuning-xfclzpvb-50fb1-55rxp/events.out.tfevents.1736246296.r-khaled-auwad-roberta-fine-tuning-xfclzpvb-50fb1-55rxp.110.0 +2 -2
- runs/Jan07_10-38-13_r-khaled-auwad-roberta-fine-tuning-xfclzpvb-50fb1-55rxp/events.out.tfevents.1736247114.r-khaled-auwad-roberta-fine-tuning-xfclzpvb-50fb1-55rxp.110.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
base_model: cardiffnlp/twitter-roberta-base-sentiment
|
| 7 |
+
widget:
|
| 8 |
+
- text: "I love AutoTrain"
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Trained Using AutoTrain
|
| 12 |
+
|
| 13 |
+
- Problem type: Text Classification
|
| 14 |
+
|
| 15 |
+
## Validation Metrics
|
| 16 |
+
loss: 0.00013135405606590211
|
| 17 |
+
|
| 18 |
+
f1: 1.0
|
| 19 |
+
|
| 20 |
+
precision: 1.0
|
| 21 |
+
|
| 22 |
+
recall: 1.0
|
| 23 |
+
|
| 24 |
+
auc: 1.0
|
| 25 |
+
|
| 26 |
+
accuracy: 1.0
|
checkpoint-80/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "n\u00e9gatif",
|
| 17 |
+
"1": "positif"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"n\u00e9gatif": 0,
|
| 23 |
+
"positif": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.47.1",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50265
|
| 38 |
+
}
|
checkpoint-80/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7a1664f4ce786b24d91d21dc999f205fed34994b5ea96eb83fbeb1a74c8698c
|
| 3 |
+
size 498612824
|
checkpoint-80/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6934a98dc0e6e3aaefd8a6c509a745238a28650782946c02154f7e66e56de99d
|
| 3 |
+
size 997339898
|
checkpoint-80/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb36824f4006f641c2d29a4f3b42fb5f0da9c844f8621db97941ea002c0ea643
|
| 3 |
+
size 13990
|
checkpoint-80/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8dc99e2da5ac79f74e1e4cdce10592745f965b50b2b9bf131ae5ebf73953550
|
| 3 |
+
size 1064
|
checkpoint-80/trainer_state.json
ADDED
|
@@ -0,0 +1,706 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.00013135405606590211,
|
| 3 |
+
"best_model_checkpoint": "roberta-fine-tunig-csv-data/checkpoint-80",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 80,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 7.55536413192749,
|
| 14 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 15 |
+
"loss": 0.6754,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 3.9791183471679688,
|
| 21 |
+
"learning_rate": 4.000000000000001e-06,
|
| 22 |
+
"loss": 0.6647,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3,
|
| 27 |
+
"grad_norm": 6.010430335998535,
|
| 28 |
+
"learning_rate": 6e-06,
|
| 29 |
+
"loss": 0.7395,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4,
|
| 34 |
+
"grad_norm": 3.08632755279541,
|
| 35 |
+
"learning_rate": 8.000000000000001e-06,
|
| 36 |
+
"loss": 0.631,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5,
|
| 41 |
+
"grad_norm": 4.015056133270264,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 0.6809,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6,
|
| 48 |
+
"grad_norm": 3.134782075881958,
|
| 49 |
+
"learning_rate": 1.2e-05,
|
| 50 |
+
"loss": 0.6967,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7,
|
| 55 |
+
"grad_norm": 4.557210922241211,
|
| 56 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 57 |
+
"loss": 0.664,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8,
|
| 62 |
+
"grad_norm": 5.257473468780518,
|
| 63 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 64 |
+
"loss": 0.6784,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.9,
|
| 69 |
+
"grad_norm": 7.253864288330078,
|
| 70 |
+
"learning_rate": 1.8e-05,
|
| 71 |
+
"loss": 0.7238,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0,
|
| 76 |
+
"grad_norm": 5.001877784729004,
|
| 77 |
+
"learning_rate": 2e-05,
|
| 78 |
+
"loss": 0.6213,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"eval_accuracy": 0.85,
|
| 84 |
+
"eval_auc": 0.8300000000000001,
|
| 85 |
+
"eval_f1": 0.8695652173913043,
|
| 86 |
+
"eval_loss": 0.6050769090652466,
|
| 87 |
+
"eval_precision": 0.7692307692307693,
|
| 88 |
+
"eval_recall": 1.0,
|
| 89 |
+
"eval_runtime": 4.7289,
|
| 90 |
+
"eval_samples_per_second": 4.229,
|
| 91 |
+
"eval_steps_per_second": 0.423,
|
| 92 |
+
"step": 10
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.1,
|
| 96 |
+
"grad_norm": 5.389167785644531,
|
| 97 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 98 |
+
"loss": 0.5838,
|
| 99 |
+
"step": 11
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.2,
|
| 103 |
+
"grad_norm": 4.787354469299316,
|
| 104 |
+
"learning_rate": 2.4e-05,
|
| 105 |
+
"loss": 0.5635,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.3,
|
| 110 |
+
"grad_norm": 3.8223752975463867,
|
| 111 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 112 |
+
"loss": 0.5495,
|
| 113 |
+
"step": 13
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.4,
|
| 117 |
+
"grad_norm": 10.939008712768555,
|
| 118 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 119 |
+
"loss": 0.516,
|
| 120 |
+
"step": 14
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.5,
|
| 124 |
+
"grad_norm": 7.401256084442139,
|
| 125 |
+
"learning_rate": 3e-05,
|
| 126 |
+
"loss": 0.5461,
|
| 127 |
+
"step": 15
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.6,
|
| 131 |
+
"grad_norm": 7.201862812042236,
|
| 132 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 133 |
+
"loss": 0.6245,
|
| 134 |
+
"step": 16
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.7,
|
| 138 |
+
"grad_norm": 4.209521293640137,
|
| 139 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 140 |
+
"loss": 0.3298,
|
| 141 |
+
"step": 17
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.8,
|
| 145 |
+
"grad_norm": 12.88605785369873,
|
| 146 |
+
"learning_rate": 3.6e-05,
|
| 147 |
+
"loss": 0.419,
|
| 148 |
+
"step": 18
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.9,
|
| 152 |
+
"grad_norm": 6.583014965057373,
|
| 153 |
+
"learning_rate": 3.8e-05,
|
| 154 |
+
"loss": 0.3097,
|
| 155 |
+
"step": 19
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.0,
|
| 159 |
+
"grad_norm": 8.28626537322998,
|
| 160 |
+
"learning_rate": 4e-05,
|
| 161 |
+
"loss": 0.2579,
|
| 162 |
+
"step": 20
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.0,
|
| 166 |
+
"eval_accuracy": 1.0,
|
| 167 |
+
"eval_auc": 1.0,
|
| 168 |
+
"eval_f1": 1.0,
|
| 169 |
+
"eval_loss": 0.1123519092798233,
|
| 170 |
+
"eval_precision": 1.0,
|
| 171 |
+
"eval_recall": 1.0,
|
| 172 |
+
"eval_runtime": 6.5839,
|
| 173 |
+
"eval_samples_per_second": 3.038,
|
| 174 |
+
"eval_steps_per_second": 0.304,
|
| 175 |
+
"step": 20
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 2.1,
|
| 179 |
+
"grad_norm": 8.056879043579102,
|
| 180 |
+
"learning_rate": 4.2e-05,
|
| 181 |
+
"loss": 0.1769,
|
| 182 |
+
"step": 21
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.2,
|
| 186 |
+
"grad_norm": 1.7285759449005127,
|
| 187 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 188 |
+
"loss": 0.0837,
|
| 189 |
+
"step": 22
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.3,
|
| 193 |
+
"grad_norm": 2.3977487087249756,
|
| 194 |
+
"learning_rate": 4.600000000000001e-05,
|
| 195 |
+
"loss": 0.0737,
|
| 196 |
+
"step": 23
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.4,
|
| 200 |
+
"grad_norm": 1.4247184991836548,
|
| 201 |
+
"learning_rate": 4.8e-05,
|
| 202 |
+
"loss": 0.0464,
|
| 203 |
+
"step": 24
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.5,
|
| 207 |
+
"grad_norm": 0.7337800860404968,
|
| 208 |
+
"learning_rate": 5e-05,
|
| 209 |
+
"loss": 0.029,
|
| 210 |
+
"step": 25
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.6,
|
| 214 |
+
"grad_norm": 4.135664463043213,
|
| 215 |
+
"learning_rate": 4.977777777777778e-05,
|
| 216 |
+
"loss": 0.0347,
|
| 217 |
+
"step": 26
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.7,
|
| 221 |
+
"grad_norm": 32.47124099731445,
|
| 222 |
+
"learning_rate": 4.955555555555556e-05,
|
| 223 |
+
"loss": 0.3638,
|
| 224 |
+
"step": 27
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.8,
|
| 228 |
+
"grad_norm": 0.5017151832580566,
|
| 229 |
+
"learning_rate": 4.933333333333334e-05,
|
| 230 |
+
"loss": 0.0161,
|
| 231 |
+
"step": 28
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.9,
|
| 235 |
+
"grad_norm": 0.35994720458984375,
|
| 236 |
+
"learning_rate": 4.9111111111111114e-05,
|
| 237 |
+
"loss": 0.0116,
|
| 238 |
+
"step": 29
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.0,
|
| 242 |
+
"grad_norm": 0.2288239747285843,
|
| 243 |
+
"learning_rate": 4.888888888888889e-05,
|
| 244 |
+
"loss": 0.0083,
|
| 245 |
+
"step": 30
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.0,
|
| 249 |
+
"eval_accuracy": 1.0,
|
| 250 |
+
"eval_auc": 1.0,
|
| 251 |
+
"eval_f1": 1.0,
|
| 252 |
+
"eval_loss": 0.004921581596136093,
|
| 253 |
+
"eval_precision": 1.0,
|
| 254 |
+
"eval_recall": 1.0,
|
| 255 |
+
"eval_runtime": 5.8412,
|
| 256 |
+
"eval_samples_per_second": 3.424,
|
| 257 |
+
"eval_steps_per_second": 0.342,
|
| 258 |
+
"step": 30
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 3.1,
|
| 262 |
+
"grad_norm": 0.10766805708408356,
|
| 263 |
+
"learning_rate": 4.866666666666667e-05,
|
| 264 |
+
"loss": 0.0041,
|
| 265 |
+
"step": 31
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 3.2,
|
| 269 |
+
"grad_norm": 89.99065399169922,
|
| 270 |
+
"learning_rate": 4.844444444444445e-05,
|
| 271 |
+
"loss": 0.6085,
|
| 272 |
+
"step": 32
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.3,
|
| 276 |
+
"grad_norm": 0.1680934876203537,
|
| 277 |
+
"learning_rate": 4.8222222222222225e-05,
|
| 278 |
+
"loss": 0.0034,
|
| 279 |
+
"step": 33
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.4,
|
| 283 |
+
"grad_norm": 0.07745856046676636,
|
| 284 |
+
"learning_rate": 4.8e-05,
|
| 285 |
+
"loss": 0.003,
|
| 286 |
+
"step": 34
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 3.5,
|
| 290 |
+
"grad_norm": 0.07183021306991577,
|
| 291 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 292 |
+
"loss": 0.0024,
|
| 293 |
+
"step": 35
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.6,
|
| 297 |
+
"grad_norm": 0.11225942522287369,
|
| 298 |
+
"learning_rate": 4.755555555555556e-05,
|
| 299 |
+
"loss": 0.0031,
|
| 300 |
+
"step": 36
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.7,
|
| 304 |
+
"grad_norm": 0.06351231038570404,
|
| 305 |
+
"learning_rate": 4.7333333333333336e-05,
|
| 306 |
+
"loss": 0.0019,
|
| 307 |
+
"step": 37
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 3.8,
|
| 311 |
+
"grad_norm": 0.042991191148757935,
|
| 312 |
+
"learning_rate": 4.711111111111111e-05,
|
| 313 |
+
"loss": 0.0015,
|
| 314 |
+
"step": 38
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.9,
|
| 318 |
+
"grad_norm": 0.044900573790073395,
|
| 319 |
+
"learning_rate": 4.6888888888888895e-05,
|
| 320 |
+
"loss": 0.0016,
|
| 321 |
+
"step": 39
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.0,
|
| 325 |
+
"grad_norm": 0.047522518783807755,
|
| 326 |
+
"learning_rate": 4.666666666666667e-05,
|
| 327 |
+
"loss": 0.0013,
|
| 328 |
+
"step": 40
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.0,
|
| 332 |
+
"eval_accuracy": 1.0,
|
| 333 |
+
"eval_auc": 1.0,
|
| 334 |
+
"eval_f1": 1.0,
|
| 335 |
+
"eval_loss": 0.000673093309160322,
|
| 336 |
+
"eval_precision": 1.0,
|
| 337 |
+
"eval_recall": 1.0,
|
| 338 |
+
"eval_runtime": 5.7321,
|
| 339 |
+
"eval_samples_per_second": 3.489,
|
| 340 |
+
"eval_steps_per_second": 0.349,
|
| 341 |
+
"step": 40
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 4.1,
|
| 345 |
+
"grad_norm": 0.035493236035108566,
|
| 346 |
+
"learning_rate": 4.644444444444445e-05,
|
| 347 |
+
"loss": 0.0012,
|
| 348 |
+
"step": 41
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 4.2,
|
| 352 |
+
"grad_norm": 0.025220071896910667,
|
| 353 |
+
"learning_rate": 4.6222222222222224e-05,
|
| 354 |
+
"loss": 0.0009,
|
| 355 |
+
"step": 42
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 4.3,
|
| 359 |
+
"grad_norm": 0.023590650409460068,
|
| 360 |
+
"learning_rate": 4.600000000000001e-05,
|
| 361 |
+
"loss": 0.0008,
|
| 362 |
+
"step": 43
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.4,
|
| 366 |
+
"grad_norm": 0.018522851169109344,
|
| 367 |
+
"learning_rate": 4.577777777777778e-05,
|
| 368 |
+
"loss": 0.0008,
|
| 369 |
+
"step": 44
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.5,
|
| 373 |
+
"grad_norm": 0.014903909526765347,
|
| 374 |
+
"learning_rate": 4.555555555555556e-05,
|
| 375 |
+
"loss": 0.0006,
|
| 376 |
+
"step": 45
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 4.6,
|
| 380 |
+
"grad_norm": 0.016450949013233185,
|
| 381 |
+
"learning_rate": 4.5333333333333335e-05,
|
| 382 |
+
"loss": 0.0006,
|
| 383 |
+
"step": 46
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.7,
|
| 387 |
+
"grad_norm": 0.010661164298653603,
|
| 388 |
+
"learning_rate": 4.511111111111112e-05,
|
| 389 |
+
"loss": 0.0005,
|
| 390 |
+
"step": 47
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 4.8,
|
| 394 |
+
"grad_norm": 0.010659057646989822,
|
| 395 |
+
"learning_rate": 4.4888888888888894e-05,
|
| 396 |
+
"loss": 0.0005,
|
| 397 |
+
"step": 48
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 4.9,
|
| 401 |
+
"grad_norm": 0.012150386348366737,
|
| 402 |
+
"learning_rate": 4.466666666666667e-05,
|
| 403 |
+
"loss": 0.0005,
|
| 404 |
+
"step": 49
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.0,
|
| 408 |
+
"grad_norm": 0.010467156767845154,
|
| 409 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 410 |
+
"loss": 0.0004,
|
| 411 |
+
"step": 50
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 5.0,
|
| 415 |
+
"eval_accuracy": 1.0,
|
| 416 |
+
"eval_auc": 1.0,
|
| 417 |
+
"eval_f1": 1.0,
|
| 418 |
+
"eval_loss": 0.0002530492492951453,
|
| 419 |
+
"eval_precision": 1.0,
|
| 420 |
+
"eval_recall": 1.0,
|
| 421 |
+
"eval_runtime": 5.6924,
|
| 422 |
+
"eval_samples_per_second": 3.513,
|
| 423 |
+
"eval_steps_per_second": 0.351,
|
| 424 |
+
"step": 50
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 5.1,
|
| 428 |
+
"grad_norm": 0.0089597562327981,
|
| 429 |
+
"learning_rate": 4.422222222222222e-05,
|
| 430 |
+
"loss": 0.0004,
|
| 431 |
+
"step": 51
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 5.2,
|
| 435 |
+
"grad_norm": 0.010481887497007847,
|
| 436 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 437 |
+
"loss": 0.0004,
|
| 438 |
+
"step": 52
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 5.3,
|
| 442 |
+
"grad_norm": 0.011729219928383827,
|
| 443 |
+
"learning_rate": 4.377777777777778e-05,
|
| 444 |
+
"loss": 0.0004,
|
| 445 |
+
"step": 53
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 5.4,
|
| 449 |
+
"grad_norm": 0.010350607335567474,
|
| 450 |
+
"learning_rate": 4.355555555555556e-05,
|
| 451 |
+
"loss": 0.0004,
|
| 452 |
+
"step": 54
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 5.5,
|
| 456 |
+
"grad_norm": 0.008362277410924435,
|
| 457 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 458 |
+
"loss": 0.0003,
|
| 459 |
+
"step": 55
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 5.6,
|
| 463 |
+
"grad_norm": 0.010905866511166096,
|
| 464 |
+
"learning_rate": 4.311111111111111e-05,
|
| 465 |
+
"loss": 0.0004,
|
| 466 |
+
"step": 56
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 5.7,
|
| 470 |
+
"grad_norm": 0.007537131197750568,
|
| 471 |
+
"learning_rate": 4.2888888888888886e-05,
|
| 472 |
+
"loss": 0.0003,
|
| 473 |
+
"step": 57
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 5.8,
|
| 477 |
+
"grad_norm": 0.009093648754060268,
|
| 478 |
+
"learning_rate": 4.266666666666667e-05,
|
| 479 |
+
"loss": 0.0004,
|
| 480 |
+
"step": 58
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 5.9,
|
| 484 |
+
"grad_norm": 0.006778199225664139,
|
| 485 |
+
"learning_rate": 4.2444444444444445e-05,
|
| 486 |
+
"loss": 0.0003,
|
| 487 |
+
"step": 59
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 6.0,
|
| 491 |
+
"grad_norm": 0.007238809950649738,
|
| 492 |
+
"learning_rate": 4.222222222222222e-05,
|
| 493 |
+
"loss": 0.0003,
|
| 494 |
+
"step": 60
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.0,
|
| 498 |
+
"eval_accuracy": 1.0,
|
| 499 |
+
"eval_auc": 1.0,
|
| 500 |
+
"eval_f1": 1.0,
|
| 501 |
+
"eval_loss": 0.0001882673241198063,
|
| 502 |
+
"eval_precision": 1.0,
|
| 503 |
+
"eval_recall": 1.0,
|
| 504 |
+
"eval_runtime": 4.6118,
|
| 505 |
+
"eval_samples_per_second": 4.337,
|
| 506 |
+
"eval_steps_per_second": 0.434,
|
| 507 |
+
"step": 60
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 6.1,
|
| 511 |
+
"grad_norm": 0.007917866110801697,
|
| 512 |
+
"learning_rate": 4.2e-05,
|
| 513 |
+
"loss": 0.0003,
|
| 514 |
+
"step": 61
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 6.2,
|
| 518 |
+
"grad_norm": 0.007155848667025566,
|
| 519 |
+
"learning_rate": 4.177777777777778e-05,
|
| 520 |
+
"loss": 0.0003,
|
| 521 |
+
"step": 62
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 6.3,
|
| 525 |
+
"grad_norm": 0.006979298312216997,
|
| 526 |
+
"learning_rate": 4.155555555555556e-05,
|
| 527 |
+
"loss": 0.0003,
|
| 528 |
+
"step": 63
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 6.4,
|
| 532 |
+
"grad_norm": 0.010923142544925213,
|
| 533 |
+
"learning_rate": 4.133333333333333e-05,
|
| 534 |
+
"loss": 0.0004,
|
| 535 |
+
"step": 64
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 6.5,
|
| 539 |
+
"grad_norm": 0.007328235078603029,
|
| 540 |
+
"learning_rate": 4.111111111111111e-05,
|
| 541 |
+
"loss": 0.0003,
|
| 542 |
+
"step": 65
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 6.6,
|
| 546 |
+
"grad_norm": 0.005914509296417236,
|
| 547 |
+
"learning_rate": 4.088888888888889e-05,
|
| 548 |
+
"loss": 0.0002,
|
| 549 |
+
"step": 66
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 6.7,
|
| 553 |
+
"grad_norm": 0.006119257304817438,
|
| 554 |
+
"learning_rate": 4.066666666666667e-05,
|
| 555 |
+
"loss": 0.0003,
|
| 556 |
+
"step": 67
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 6.8,
|
| 560 |
+
"grad_norm": 0.005710636265575886,
|
| 561 |
+
"learning_rate": 4.0444444444444444e-05,
|
| 562 |
+
"loss": 0.0002,
|
| 563 |
+
"step": 68
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 6.9,
|
| 567 |
+
"grad_norm": 0.005685439333319664,
|
| 568 |
+
"learning_rate": 4.022222222222222e-05,
|
| 569 |
+
"loss": 0.0002,
|
| 570 |
+
"step": 69
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 7.0,
|
| 574 |
+
"grad_norm": 0.009583599865436554,
|
| 575 |
+
"learning_rate": 4e-05,
|
| 576 |
+
"loss": 0.0003,
|
| 577 |
+
"step": 70
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 7.0,
|
| 581 |
+
"eval_accuracy": 1.0,
|
| 582 |
+
"eval_auc": 1.0,
|
| 583 |
+
"eval_f1": 1.0,
|
| 584 |
+
"eval_loss": 0.00015127708320505917,
|
| 585 |
+
"eval_precision": 1.0,
|
| 586 |
+
"eval_recall": 1.0,
|
| 587 |
+
"eval_runtime": 5.2577,
|
| 588 |
+
"eval_samples_per_second": 3.804,
|
| 589 |
+
"eval_steps_per_second": 0.38,
|
| 590 |
+
"step": 70
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.1,
|
| 594 |
+
"grad_norm": 0.005983178969472647,
|
| 595 |
+
"learning_rate": 3.977777777777778e-05,
|
| 596 |
+
"loss": 0.0002,
|
| 597 |
+
"step": 71
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 7.2,
|
| 601 |
+
"grad_norm": 0.00594620406627655,
|
| 602 |
+
"learning_rate": 3.9555555555555556e-05,
|
| 603 |
+
"loss": 0.0002,
|
| 604 |
+
"step": 72
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.3,
|
| 608 |
+
"grad_norm": 0.005957406479865313,
|
| 609 |
+
"learning_rate": 3.933333333333333e-05,
|
| 610 |
+
"loss": 0.0002,
|
| 611 |
+
"step": 73
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.4,
|
| 615 |
+
"grad_norm": 0.006083622109144926,
|
| 616 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 617 |
+
"loss": 0.0002,
|
| 618 |
+
"step": 74
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.5,
|
| 622 |
+
"grad_norm": 0.006562595721334219,
|
| 623 |
+
"learning_rate": 3.888888888888889e-05,
|
| 624 |
+
"loss": 0.0003,
|
| 625 |
+
"step": 75
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.6,
|
| 629 |
+
"grad_norm": 0.006515933200716972,
|
| 630 |
+
"learning_rate": 3.866666666666667e-05,
|
| 631 |
+
"loss": 0.0003,
|
| 632 |
+
"step": 76
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.7,
|
| 636 |
+
"grad_norm": 0.005742065608501434,
|
| 637 |
+
"learning_rate": 3.844444444444444e-05,
|
| 638 |
+
"loss": 0.0002,
|
| 639 |
+
"step": 77
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.8,
|
| 643 |
+
"grad_norm": 0.00555277056992054,
|
| 644 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 645 |
+
"loss": 0.0002,
|
| 646 |
+
"step": 78
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 7.9,
|
| 650 |
+
"grad_norm": 0.006111868191510439,
|
| 651 |
+
"learning_rate": 3.8e-05,
|
| 652 |
+
"loss": 0.0002,
|
| 653 |
+
"step": 79
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 8.0,
|
| 657 |
+
"grad_norm": 0.005914055742323399,
|
| 658 |
+
"learning_rate": 3.777777777777778e-05,
|
| 659 |
+
"loss": 0.0003,
|
| 660 |
+
"step": 80
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 8.0,
|
| 664 |
+
"eval_accuracy": 1.0,
|
| 665 |
+
"eval_auc": 1.0,
|
| 666 |
+
"eval_f1": 1.0,
|
| 667 |
+
"eval_loss": 0.00013135405606590211,
|
| 668 |
+
"eval_precision": 1.0,
|
| 669 |
+
"eval_recall": 1.0,
|
| 670 |
+
"eval_runtime": 5.721,
|
| 671 |
+
"eval_samples_per_second": 3.496,
|
| 672 |
+
"eval_steps_per_second": 0.35,
|
| 673 |
+
"step": 80
|
| 674 |
+
}
|
| 675 |
+
],
|
| 676 |
+
"logging_steps": 1,
|
| 677 |
+
"max_steps": 250,
|
| 678 |
+
"num_input_tokens_seen": 0,
|
| 679 |
+
"num_train_epochs": 25,
|
| 680 |
+
"save_steps": 500,
|
| 681 |
+
"stateful_callbacks": {
|
| 682 |
+
"EarlyStoppingCallback": {
|
| 683 |
+
"args": {
|
| 684 |
+
"early_stopping_patience": 5,
|
| 685 |
+
"early_stopping_threshold": 0.01
|
| 686 |
+
},
|
| 687 |
+
"attributes": {
|
| 688 |
+
"early_stopping_patience_counter": 5
|
| 689 |
+
}
|
| 690 |
+
},
|
| 691 |
+
"TrainerControl": {
|
| 692 |
+
"args": {
|
| 693 |
+
"should_epoch_stop": false,
|
| 694 |
+
"should_evaluate": false,
|
| 695 |
+
"should_log": false,
|
| 696 |
+
"should_save": true,
|
| 697 |
+
"should_training_stop": true
|
| 698 |
+
},
|
| 699 |
+
"attributes": {}
|
| 700 |
+
}
|
| 701 |
+
},
|
| 702 |
+
"total_flos": 42097768857600.0,
|
| 703 |
+
"train_batch_size": 8,
|
| 704 |
+
"trial_name": null,
|
| 705 |
+
"trial_params": null
|
| 706 |
+
}
|
checkpoint-80/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92f8bb8bcd7773d3e7fb428a379b5b9e25c61a097bcbc9dfa8b5776c0289569e
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "n\u00e9gatif",
|
| 17 |
+
"1": "positif"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"n\u00e9gatif": 0,
|
| 23 |
+
"positif": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.47.1",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50265
|
| 38 |
+
}
|
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:b7a1664f4ce786b24d91d21dc999f205fed34994b5ea96eb83fbeb1a74c8698c
|
| 3 |
+
size 498612824
|
runs/Jan07_10-38-13_r-khaled-auwad-roberta-fine-tuning-xfclzpvb-50fb1-55rxp/events.out.tfevents.1736246296.r-khaled-auwad-roberta-fine-tuning-xfclzpvb-50fb1-55rxp.110.0
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:e72e833758de00b6fa2fe0da4122b9dcad30f098c4066e94fa5da09db3d9ea5a
|
| 3 |
+
size 26318
|
runs/Jan07_10-38-13_r-khaled-auwad-roberta-fine-tuning-xfclzpvb-50fb1-55rxp/events.out.tfevents.1736247114.r-khaled-auwad-roberta-fine-tuning-xfclzpvb-50fb1-55rxp.110.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5625e5f0073ab2cff8dc99464529ac3e97f4af45897506725497ac6b5d53a40
|
| 3 |
+
size 597
|
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": false,
|
| 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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92f8bb8bcd7773d3e7fb428a379b5b9e25c61a097bcbc9dfa8b5776c0289569e
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "roberta-fine-tunig-csv-data/autotrain-data",
|
| 3 |
+
"model": "cardiffnlp/twitter-roberta-base-sentiment",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 25,
|
| 6 |
+
"max_seq_length": 128,
|
| 7 |
+
"batch_size": 8,
|
| 8 |
+
"warmup_ratio": 0.1,
|
| 9 |
+
"gradient_accumulation": 1,
|
| 10 |
+
"optimizer": "adamw_torch",
|
| 11 |
+
"scheduler": "linear",
|
| 12 |
+
"weight_decay": 0.0,
|
| 13 |
+
"max_grad_norm": 1.0,
|
| 14 |
+
"seed": 42,
|
| 15 |
+
"train_split": "train",
|
| 16 |
+
"valid_split": "validation",
|
| 17 |
+
"text_column": "autotrain_text",
|
| 18 |
+
"target_column": "autotrain_label",
|
| 19 |
+
"logging_steps": -1,
|
| 20 |
+
"project_name": "roberta-fine-tunig-csv-data",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"push_to_hub": true,
|
| 25 |
+
"eval_strategy": "epoch",
|
| 26 |
+
"username": "khaled-auwad",
|
| 27 |
+
"log": "tensorboard",
|
| 28 |
+
"early_stopping_patience": 5,
|
| 29 |
+
"early_stopping_threshold": 0.01
|
| 30 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|