Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-6081/config.json +36 -0
- checkpoint-6081/model.safetensors +3 -0
- checkpoint-6081/optimizer.pt +3 -0
- checkpoint-6081/rng_state.pth +3 -0
- checkpoint-6081/scheduler.pt +3 -0
- checkpoint-6081/trainer_state.json +1782 -0
- checkpoint-6081/training_args.bin +3 -0
- config.json +36 -0
- model.safetensors +3 -0
- runs/May22_15-42-05_r-trentmkelly-autotrain-advanced-6oq4mr6b-da706-g95do/events.out.tfevents.1747928527.r-trentmkelly-autotrain-advanced-6oq4mr6b-da706-g95do.89.0 +2 -2
- runs/May22_15-42-05_r-trentmkelly-autotrain-advanced-6oq4mr6b-da706-g95do/events.out.tfevents.1747932270.r-trentmkelly-autotrain-advanced-6oq4mr6b-da706-g95do.89.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- autotrain
|
| 6 |
+
- text-classification
|
| 7 |
+
base_model: BAAI/bge-large-en-v1.5
|
| 8 |
+
widget:
|
| 9 |
+
- text: "I love AutoTrain"
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.29475775361061096
|
| 18 |
+
|
| 19 |
+
f1: 0.9548948513415518
|
| 20 |
+
|
| 21 |
+
precision: 0.9136830419095199
|
| 22 |
+
|
| 23 |
+
recall: 1.0
|
| 24 |
+
|
| 25 |
+
auc: 0.5282966990033326
|
| 26 |
+
|
| 27 |
+
accuracy: 0.9136830419095199
|
checkpoint-6081/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "BAAI/bge-large-en-v1.5",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "BAD_USER",
|
| 15 |
+
"1": "GOOD_USER"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"BAD_USER": 0,
|
| 21 |
+
"GOOD_USER": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "bert",
|
| 26 |
+
"num_attention_heads": 16,
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.48.0",
|
| 33 |
+
"type_vocab_size": 2,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
checkpoint-6081/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:210a11360287b8671eaf6f21b6f39996c84fd82642608b82cb277de916601c7f
|
| 3 |
+
size 1340622760
|
checkpoint-6081/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b64b911aa802208d69bc6b20795704822e1161ff03f479a3625cb24ed015d270
|
| 3 |
+
size 2681480429
|
checkpoint-6081/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b7ff53905c2d8e1737614bddf91d49fc043a393982ff168f02ef3949e206658
|
| 3 |
+
size 14244
|
checkpoint-6081/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51363f8374cf05742d50650339a31d6255912d5fc9be30731cc793b4383ae190
|
| 3 |
+
size 1064
|
checkpoint-6081/trainer_state.json
ADDED
|
@@ -0,0 +1,1782 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.29475775361061096,
|
| 3 |
+
"best_model_checkpoint": "autotrain-roblox-12-with-bge-large/checkpoint-6081",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6081,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0123334977799704,
|
| 13 |
+
"grad_norm": 4.050952911376953,
|
| 14 |
+
"learning_rate": 2.052545155993432e-06,
|
| 15 |
+
"loss": 0.3312,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0246669955599408,
|
| 20 |
+
"grad_norm": 2.688647985458374,
|
| 21 |
+
"learning_rate": 4.105090311986864e-06,
|
| 22 |
+
"loss": 0.3098,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0370004933399112,
|
| 27 |
+
"grad_norm": 3.3651115894317627,
|
| 28 |
+
"learning_rate": 6.157635467980296e-06,
|
| 29 |
+
"loss": 0.2901,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0493339911198816,
|
| 34 |
+
"grad_norm": 2.1107537746429443,
|
| 35 |
+
"learning_rate": 8.12807881773399e-06,
|
| 36 |
+
"loss": 0.3309,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.061667488899852,
|
| 41 |
+
"grad_norm": 3.7403604984283447,
|
| 42 |
+
"learning_rate": 1.0180623973727423e-05,
|
| 43 |
+
"loss": 0.2453,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0740009866798224,
|
| 48 |
+
"grad_norm": 6.779322624206543,
|
| 49 |
+
"learning_rate": 1.2233169129720855e-05,
|
| 50 |
+
"loss": 0.3616,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0863344844597928,
|
| 55 |
+
"grad_norm": 8.832545280456543,
|
| 56 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 57 |
+
"loss": 0.2956,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0986679822397632,
|
| 62 |
+
"grad_norm": 10.033223152160645,
|
| 63 |
+
"learning_rate": 1.633825944170772e-05,
|
| 64 |
+
"loss": 0.2352,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1110014800197336,
|
| 69 |
+
"grad_norm": 6.968496322631836,
|
| 70 |
+
"learning_rate": 1.839080459770115e-05,
|
| 71 |
+
"loss": 0.2301,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.123334977799704,
|
| 76 |
+
"grad_norm": 2.7263169288635254,
|
| 77 |
+
"learning_rate": 2.0443349753694584e-05,
|
| 78 |
+
"loss": 0.2709,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1356684755796744,
|
| 83 |
+
"grad_norm": 0.9099070429801941,
|
| 84 |
+
"learning_rate": 2.2495894909688014e-05,
|
| 85 |
+
"loss": 0.1919,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1480019733596448,
|
| 90 |
+
"grad_norm": 1.8240989446640015,
|
| 91 |
+
"learning_rate": 2.4548440065681445e-05,
|
| 92 |
+
"loss": 0.2988,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1603354711396152,
|
| 97 |
+
"grad_norm": 4.9374895095825195,
|
| 98 |
+
"learning_rate": 2.660098522167488e-05,
|
| 99 |
+
"loss": 0.2536,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1726689689195856,
|
| 104 |
+
"grad_norm": 1.09425950050354,
|
| 105 |
+
"learning_rate": 2.865353037766831e-05,
|
| 106 |
+
"loss": 0.2008,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.185002466699556,
|
| 111 |
+
"grad_norm": 2.3137404918670654,
|
| 112 |
+
"learning_rate": 3.0706075533661744e-05,
|
| 113 |
+
"loss": 0.2165,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1973359644795264,
|
| 118 |
+
"grad_norm": 0.9012945294380188,
|
| 119 |
+
"learning_rate": 3.275862068965517e-05,
|
| 120 |
+
"loss": 0.1705,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.20966946225949679,
|
| 125 |
+
"grad_norm": 1.8131095170974731,
|
| 126 |
+
"learning_rate": 3.4811165845648605e-05,
|
| 127 |
+
"loss": 0.2665,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2220029600394672,
|
| 132 |
+
"grad_norm": 1.6614292860031128,
|
| 133 |
+
"learning_rate": 3.686371100164204e-05,
|
| 134 |
+
"loss": 0.2429,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2343364578194376,
|
| 139 |
+
"grad_norm": 2.317420482635498,
|
| 140 |
+
"learning_rate": 3.891625615763547e-05,
|
| 141 |
+
"loss": 0.1651,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.246669955599408,
|
| 146 |
+
"grad_norm": 3.639861583709717,
|
| 147 |
+
"learning_rate": 4.09688013136289e-05,
|
| 148 |
+
"loss": 0.318,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2590034533793784,
|
| 153 |
+
"grad_norm": 2.372562885284424,
|
| 154 |
+
"learning_rate": 4.3021346469622334e-05,
|
| 155 |
+
"loss": 0.3119,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2713369511593488,
|
| 160 |
+
"grad_norm": 1.7043285369873047,
|
| 161 |
+
"learning_rate": 4.507389162561577e-05,
|
| 162 |
+
"loss": 0.2579,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2836704489393192,
|
| 167 |
+
"grad_norm": 7.564747333526611,
|
| 168 |
+
"learning_rate": 4.7126436781609195e-05,
|
| 169 |
+
"loss": 0.2786,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2960039467192896,
|
| 174 |
+
"grad_norm": 12.761841773986816,
|
| 175 |
+
"learning_rate": 4.917898193760263e-05,
|
| 176 |
+
"loss": 0.2579,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.30833744449926,
|
| 181 |
+
"grad_norm": 2.404279947280884,
|
| 182 |
+
"learning_rate": 4.986293859649123e-05,
|
| 183 |
+
"loss": 0.2808,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3206709422792304,
|
| 188 |
+
"grad_norm": 8.739703178405762,
|
| 189 |
+
"learning_rate": 4.9643640350877194e-05,
|
| 190 |
+
"loss": 0.2623,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.33300444005920077,
|
| 195 |
+
"grad_norm": 2.1071040630340576,
|
| 196 |
+
"learning_rate": 4.941520467836258e-05,
|
| 197 |
+
"loss": 0.231,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3453379378391712,
|
| 202 |
+
"grad_norm": 5.691776275634766,
|
| 203 |
+
"learning_rate": 4.918676900584795e-05,
|
| 204 |
+
"loss": 0.2743,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3576714356191416,
|
| 209 |
+
"grad_norm": 3.2197370529174805,
|
| 210 |
+
"learning_rate": 4.8958333333333335e-05,
|
| 211 |
+
"loss": 0.2375,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.370004933399112,
|
| 216 |
+
"grad_norm": 3.8034095764160156,
|
| 217 |
+
"learning_rate": 4.872989766081872e-05,
|
| 218 |
+
"loss": 0.2107,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3823384311790824,
|
| 223 |
+
"grad_norm": 1.8795045614242554,
|
| 224 |
+
"learning_rate": 4.85014619883041e-05,
|
| 225 |
+
"loss": 0.2305,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3946719289590528,
|
| 230 |
+
"grad_norm": 7.548186302185059,
|
| 231 |
+
"learning_rate": 4.8273026315789476e-05,
|
| 232 |
+
"loss": 0.2984,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4070054267390232,
|
| 237 |
+
"grad_norm": 3.3918960094451904,
|
| 238 |
+
"learning_rate": 4.804459064327486e-05,
|
| 239 |
+
"loss": 0.2313,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.41933892451899357,
|
| 244 |
+
"grad_norm": 8.099982261657715,
|
| 245 |
+
"learning_rate": 4.7816154970760235e-05,
|
| 246 |
+
"loss": 0.3721,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.43167242229896396,
|
| 251 |
+
"grad_norm": 3.144808053970337,
|
| 252 |
+
"learning_rate": 4.758771929824562e-05,
|
| 253 |
+
"loss": 0.3335,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4440059200789344,
|
| 258 |
+
"grad_norm": 2.1939008235931396,
|
| 259 |
+
"learning_rate": 4.7359283625731e-05,
|
| 260 |
+
"loss": 0.3207,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.4563394178589048,
|
| 265 |
+
"grad_norm": 1.2243921756744385,
|
| 266 |
+
"learning_rate": 4.7130847953216375e-05,
|
| 267 |
+
"loss": 0.3064,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4686729156388752,
|
| 272 |
+
"grad_norm": 5.97895622253418,
|
| 273 |
+
"learning_rate": 4.690241228070176e-05,
|
| 274 |
+
"loss": 0.3317,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4810064134188456,
|
| 279 |
+
"grad_norm": 4.540741443634033,
|
| 280 |
+
"learning_rate": 4.6673976608187134e-05,
|
| 281 |
+
"loss": 0.3653,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.493339911198816,
|
| 286 |
+
"grad_norm": 3.360098361968994,
|
| 287 |
+
"learning_rate": 4.6445540935672516e-05,
|
| 288 |
+
"loss": 0.2999,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5056734089787864,
|
| 293 |
+
"grad_norm": 2.302455186843872,
|
| 294 |
+
"learning_rate": 4.621710526315789e-05,
|
| 295 |
+
"loss": 0.2998,
|
| 296 |
+
"step": 1025
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5180069067587568,
|
| 300 |
+
"grad_norm": 4.192526817321777,
|
| 301 |
+
"learning_rate": 4.598866959064328e-05,
|
| 302 |
+
"loss": 0.2962,
|
| 303 |
+
"step": 1050
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5303404045387272,
|
| 307 |
+
"grad_norm": 2.745168924331665,
|
| 308 |
+
"learning_rate": 4.576023391812866e-05,
|
| 309 |
+
"loss": 0.3066,
|
| 310 |
+
"step": 1075
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5426739023186976,
|
| 314 |
+
"grad_norm": 2.6728932857513428,
|
| 315 |
+
"learning_rate": 4.553179824561404e-05,
|
| 316 |
+
"loss": 0.3107,
|
| 317 |
+
"step": 1100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.555007400098668,
|
| 321 |
+
"grad_norm": 1.7235779762268066,
|
| 322 |
+
"learning_rate": 4.5303362573099416e-05,
|
| 323 |
+
"loss": 0.3383,
|
| 324 |
+
"step": 1125
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5673408978786384,
|
| 328 |
+
"grad_norm": 4.529238224029541,
|
| 329 |
+
"learning_rate": 4.50749269005848e-05,
|
| 330 |
+
"loss": 0.3597,
|
| 331 |
+
"step": 1150
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5796743956586088,
|
| 335 |
+
"grad_norm": 9.228950500488281,
|
| 336 |
+
"learning_rate": 4.4846491228070174e-05,
|
| 337 |
+
"loss": 0.2667,
|
| 338 |
+
"step": 1175
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5920078934385792,
|
| 342 |
+
"grad_norm": 2.5120201110839844,
|
| 343 |
+
"learning_rate": 4.4618055555555563e-05,
|
| 344 |
+
"loss": 0.2917,
|
| 345 |
+
"step": 1200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6043413912185496,
|
| 349 |
+
"grad_norm": 2.3404152393341064,
|
| 350 |
+
"learning_rate": 4.438961988304094e-05,
|
| 351 |
+
"loss": 0.3255,
|
| 352 |
+
"step": 1225
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.61667488899852,
|
| 356 |
+
"grad_norm": 3.546064853668213,
|
| 357 |
+
"learning_rate": 4.416118421052632e-05,
|
| 358 |
+
"loss": 0.3204,
|
| 359 |
+
"step": 1250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6290083867784904,
|
| 363 |
+
"grad_norm": 1.058401346206665,
|
| 364 |
+
"learning_rate": 4.39327485380117e-05,
|
| 365 |
+
"loss": 0.2542,
|
| 366 |
+
"step": 1275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6413418845584608,
|
| 370 |
+
"grad_norm": 2.9787142276763916,
|
| 371 |
+
"learning_rate": 4.370431286549708e-05,
|
| 372 |
+
"loss": 0.3204,
|
| 373 |
+
"step": 1300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6536753823384311,
|
| 377 |
+
"grad_norm": 1.3214211463928223,
|
| 378 |
+
"learning_rate": 4.3475877192982456e-05,
|
| 379 |
+
"loss": 0.3145,
|
| 380 |
+
"step": 1325
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6660088801184015,
|
| 384 |
+
"grad_norm": 8.694450378417969,
|
| 385 |
+
"learning_rate": 4.324744152046784e-05,
|
| 386 |
+
"loss": 0.3172,
|
| 387 |
+
"step": 1350
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6783423778983719,
|
| 391 |
+
"grad_norm": 1.451136827468872,
|
| 392 |
+
"learning_rate": 4.301900584795322e-05,
|
| 393 |
+
"loss": 0.3318,
|
| 394 |
+
"step": 1375
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6906758756783424,
|
| 398 |
+
"grad_norm": 1.4986424446105957,
|
| 399 |
+
"learning_rate": 4.27905701754386e-05,
|
| 400 |
+
"loss": 0.3323,
|
| 401 |
+
"step": 1400
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7030093734583128,
|
| 405 |
+
"grad_norm": 2.1326487064361572,
|
| 406 |
+
"learning_rate": 4.256213450292398e-05,
|
| 407 |
+
"loss": 0.3485,
|
| 408 |
+
"step": 1425
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7153428712382832,
|
| 412 |
+
"grad_norm": 2.9651310443878174,
|
| 413 |
+
"learning_rate": 4.2333698830409355e-05,
|
| 414 |
+
"loss": 0.3854,
|
| 415 |
+
"step": 1450
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7276763690182536,
|
| 419 |
+
"grad_norm": 5.734078884124756,
|
| 420 |
+
"learning_rate": 4.210526315789474e-05,
|
| 421 |
+
"loss": 0.2711,
|
| 422 |
+
"step": 1475
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.740009866798224,
|
| 426 |
+
"grad_norm": 1.449973464012146,
|
| 427 |
+
"learning_rate": 4.187682748538012e-05,
|
| 428 |
+
"loss": 0.3442,
|
| 429 |
+
"step": 1500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7523433645781944,
|
| 433 |
+
"grad_norm": 11.361034393310547,
|
| 434 |
+
"learning_rate": 4.16483918128655e-05,
|
| 435 |
+
"loss": 0.3168,
|
| 436 |
+
"step": 1525
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7646768623581648,
|
| 440 |
+
"grad_norm": 3.920637845993042,
|
| 441 |
+
"learning_rate": 4.141995614035088e-05,
|
| 442 |
+
"loss": 0.343,
|
| 443 |
+
"step": 1550
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.7770103601381352,
|
| 447 |
+
"grad_norm": 4.118240833282471,
|
| 448 |
+
"learning_rate": 4.119152046783626e-05,
|
| 449 |
+
"loss": 0.3151,
|
| 450 |
+
"step": 1575
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7893438579181056,
|
| 454 |
+
"grad_norm": 6.998331069946289,
|
| 455 |
+
"learning_rate": 4.096308479532164e-05,
|
| 456 |
+
"loss": 0.3482,
|
| 457 |
+
"step": 1600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.801677355698076,
|
| 461 |
+
"grad_norm": 2.7872273921966553,
|
| 462 |
+
"learning_rate": 4.073464912280702e-05,
|
| 463 |
+
"loss": 0.246,
|
| 464 |
+
"step": 1625
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8140108534780464,
|
| 468 |
+
"grad_norm": 2.5942187309265137,
|
| 469 |
+
"learning_rate": 4.05062134502924e-05,
|
| 470 |
+
"loss": 0.3405,
|
| 471 |
+
"step": 1650
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8263443512580168,
|
| 475 |
+
"grad_norm": 0.8587321639060974,
|
| 476 |
+
"learning_rate": 4.027777777777778e-05,
|
| 477 |
+
"loss": 0.2433,
|
| 478 |
+
"step": 1675
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8386778490379871,
|
| 482 |
+
"grad_norm": 1.0923521518707275,
|
| 483 |
+
"learning_rate": 4.004934210526316e-05,
|
| 484 |
+
"loss": 0.3077,
|
| 485 |
+
"step": 1700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8510113468179575,
|
| 489 |
+
"grad_norm": 5.740424156188965,
|
| 490 |
+
"learning_rate": 3.9820906432748536e-05,
|
| 491 |
+
"loss": 0.2671,
|
| 492 |
+
"step": 1725
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.8633448445979279,
|
| 496 |
+
"grad_norm": 1.0194257497787476,
|
| 497 |
+
"learning_rate": 3.959247076023392e-05,
|
| 498 |
+
"loss": 0.3116,
|
| 499 |
+
"step": 1750
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8756783423778983,
|
| 503 |
+
"grad_norm": 3.4499142169952393,
|
| 504 |
+
"learning_rate": 3.9364035087719295e-05,
|
| 505 |
+
"loss": 0.2414,
|
| 506 |
+
"step": 1775
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8880118401578688,
|
| 510 |
+
"grad_norm": 1.5569651126861572,
|
| 511 |
+
"learning_rate": 3.9135599415204684e-05,
|
| 512 |
+
"loss": 0.2674,
|
| 513 |
+
"step": 1800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.9003453379378392,
|
| 517 |
+
"grad_norm": 2.4388108253479004,
|
| 518 |
+
"learning_rate": 3.890716374269006e-05,
|
| 519 |
+
"loss": 0.2521,
|
| 520 |
+
"step": 1825
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9126788357178096,
|
| 524 |
+
"grad_norm": 1.0378559827804565,
|
| 525 |
+
"learning_rate": 3.867872807017544e-05,
|
| 526 |
+
"loss": 0.3289,
|
| 527 |
+
"step": 1850
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.92501233349778,
|
| 531 |
+
"grad_norm": 0.8580950498580933,
|
| 532 |
+
"learning_rate": 3.845029239766082e-05,
|
| 533 |
+
"loss": 0.2546,
|
| 534 |
+
"step": 1875
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9373458312777504,
|
| 538 |
+
"grad_norm": 2.7251040935516357,
|
| 539 |
+
"learning_rate": 3.82218567251462e-05,
|
| 540 |
+
"loss": 0.2795,
|
| 541 |
+
"step": 1900
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.9496793290577208,
|
| 545 |
+
"grad_norm": 1.980296015739441,
|
| 546 |
+
"learning_rate": 3.7993421052631577e-05,
|
| 547 |
+
"loss": 0.3605,
|
| 548 |
+
"step": 1925
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9620128268376912,
|
| 552 |
+
"grad_norm": 3.8409457206726074,
|
| 553 |
+
"learning_rate": 3.7764985380116966e-05,
|
| 554 |
+
"loss": 0.3254,
|
| 555 |
+
"step": 1950
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.9743463246176616,
|
| 559 |
+
"grad_norm": 0.9380149841308594,
|
| 560 |
+
"learning_rate": 3.753654970760234e-05,
|
| 561 |
+
"loss": 0.3083,
|
| 562 |
+
"step": 1975
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.986679822397632,
|
| 566 |
+
"grad_norm": 4.170345783233643,
|
| 567 |
+
"learning_rate": 3.7308114035087724e-05,
|
| 568 |
+
"loss": 0.4037,
|
| 569 |
+
"step": 2000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9990133201776024,
|
| 573 |
+
"grad_norm": 0.9810841083526611,
|
| 574 |
+
"learning_rate": 3.70796783625731e-05,
|
| 575 |
+
"loss": 0.2871,
|
| 576 |
+
"step": 2025
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.0,
|
| 580 |
+
"eval_accuracy": 0.9136830419095199,
|
| 581 |
+
"eval_auc": 0.5081137943294276,
|
| 582 |
+
"eval_f1": 0.9548948513415518,
|
| 583 |
+
"eval_loss": 0.29672279953956604,
|
| 584 |
+
"eval_precision": 0.9136830419095199,
|
| 585 |
+
"eval_recall": 1.0,
|
| 586 |
+
"eval_runtime": 33.752,
|
| 587 |
+
"eval_samples_per_second": 106.749,
|
| 588 |
+
"eval_steps_per_second": 3.348,
|
| 589 |
+
"step": 2027
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.0113468179575729,
|
| 593 |
+
"grad_norm": 0.8372642993927002,
|
| 594 |
+
"learning_rate": 3.685124269005848e-05,
|
| 595 |
+
"loss": 0.269,
|
| 596 |
+
"step": 2050
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.0236803157375431,
|
| 600 |
+
"grad_norm": 5.589089870452881,
|
| 601 |
+
"learning_rate": 3.662280701754386e-05,
|
| 602 |
+
"loss": 0.2937,
|
| 603 |
+
"step": 2075
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.0360138135175136,
|
| 607 |
+
"grad_norm": 2.6755239963531494,
|
| 608 |
+
"learning_rate": 3.639437134502924e-05,
|
| 609 |
+
"loss": 0.3236,
|
| 610 |
+
"step": 2100
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.048347311297484,
|
| 614 |
+
"grad_norm": 2.6148569583892822,
|
| 615 |
+
"learning_rate": 3.6165935672514624e-05,
|
| 616 |
+
"loss": 0.2979,
|
| 617 |
+
"step": 2125
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.0606808090774544,
|
| 621 |
+
"grad_norm": 3.675825595855713,
|
| 622 |
+
"learning_rate": 3.59375e-05,
|
| 623 |
+
"loss": 0.2943,
|
| 624 |
+
"step": 2150
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.0730143068574247,
|
| 628 |
+
"grad_norm": 0.9110400676727295,
|
| 629 |
+
"learning_rate": 3.570906432748538e-05,
|
| 630 |
+
"loss": 0.3048,
|
| 631 |
+
"step": 2175
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.0853478046373952,
|
| 635 |
+
"grad_norm": 4.680244445800781,
|
| 636 |
+
"learning_rate": 3.548062865497076e-05,
|
| 637 |
+
"loss": 0.3244,
|
| 638 |
+
"step": 2200
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.0976813024173655,
|
| 642 |
+
"grad_norm": 5.2665605545043945,
|
| 643 |
+
"learning_rate": 3.525219298245615e-05,
|
| 644 |
+
"loss": 0.3156,
|
| 645 |
+
"step": 2225
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.110014800197336,
|
| 649 |
+
"grad_norm": 2.348223924636841,
|
| 650 |
+
"learning_rate": 3.502375730994152e-05,
|
| 651 |
+
"loss": 0.2805,
|
| 652 |
+
"step": 2250
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.1223482979773063,
|
| 656 |
+
"grad_norm": 2.7092299461364746,
|
| 657 |
+
"learning_rate": 3.4795321637426905e-05,
|
| 658 |
+
"loss": 0.3142,
|
| 659 |
+
"step": 2275
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.1346817957572768,
|
| 663 |
+
"grad_norm": 3.3490219116210938,
|
| 664 |
+
"learning_rate": 3.456688596491228e-05,
|
| 665 |
+
"loss": 0.2897,
|
| 666 |
+
"step": 2300
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.147015293537247,
|
| 670 |
+
"grad_norm": 1.7662327289581299,
|
| 671 |
+
"learning_rate": 3.4338450292397664e-05,
|
| 672 |
+
"loss": 0.3327,
|
| 673 |
+
"step": 2325
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.1593487913172176,
|
| 677 |
+
"grad_norm": 2.353829860687256,
|
| 678 |
+
"learning_rate": 3.411001461988304e-05,
|
| 679 |
+
"loss": 0.3108,
|
| 680 |
+
"step": 2350
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.171682289097188,
|
| 684 |
+
"grad_norm": 2.7905948162078857,
|
| 685 |
+
"learning_rate": 3.388157894736842e-05,
|
| 686 |
+
"loss": 0.3048,
|
| 687 |
+
"step": 2375
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.1840157868771584,
|
| 691 |
+
"grad_norm": 5.659600257873535,
|
| 692 |
+
"learning_rate": 3.3653143274853805e-05,
|
| 693 |
+
"loss": 0.298,
|
| 694 |
+
"step": 2400
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.1963492846571286,
|
| 698 |
+
"grad_norm": 2.632979393005371,
|
| 699 |
+
"learning_rate": 3.342470760233918e-05,
|
| 700 |
+
"loss": 0.258,
|
| 701 |
+
"step": 2425
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 1.2086827824370991,
|
| 705 |
+
"grad_norm": 1.1394457817077637,
|
| 706 |
+
"learning_rate": 3.319627192982456e-05,
|
| 707 |
+
"loss": 0.36,
|
| 708 |
+
"step": 2450
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 1.2210162802170696,
|
| 712 |
+
"grad_norm": 2.0683844089508057,
|
| 713 |
+
"learning_rate": 3.296783625730994e-05,
|
| 714 |
+
"loss": 0.379,
|
| 715 |
+
"step": 2475
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 1.23334977799704,
|
| 719 |
+
"grad_norm": 1.8254059553146362,
|
| 720 |
+
"learning_rate": 3.273940058479532e-05,
|
| 721 |
+
"loss": 0.3444,
|
| 722 |
+
"step": 2500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.2456832757770104,
|
| 726 |
+
"grad_norm": 9.155421257019043,
|
| 727 |
+
"learning_rate": 3.2510964912280704e-05,
|
| 728 |
+
"loss": 0.3649,
|
| 729 |
+
"step": 2525
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.2580167735569807,
|
| 733 |
+
"grad_norm": 7.08811092376709,
|
| 734 |
+
"learning_rate": 3.228252923976609e-05,
|
| 735 |
+
"loss": 0.3281,
|
| 736 |
+
"step": 2550
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.2703502713369512,
|
| 740 |
+
"grad_norm": 2.375296115875244,
|
| 741 |
+
"learning_rate": 3.205409356725146e-05,
|
| 742 |
+
"loss": 0.3021,
|
| 743 |
+
"step": 2575
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.2826837691169215,
|
| 747 |
+
"grad_norm": 1.9335981607437134,
|
| 748 |
+
"learning_rate": 3.1825657894736845e-05,
|
| 749 |
+
"loss": 0.3525,
|
| 750 |
+
"step": 2600
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 1.295017266896892,
|
| 754 |
+
"grad_norm": 1.156570315361023,
|
| 755 |
+
"learning_rate": 3.159722222222222e-05,
|
| 756 |
+
"loss": 0.2859,
|
| 757 |
+
"step": 2625
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.3073507646768623,
|
| 761 |
+
"grad_norm": 3.328901529312134,
|
| 762 |
+
"learning_rate": 3.13687865497076e-05,
|
| 763 |
+
"loss": 0.3364,
|
| 764 |
+
"step": 2650
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.3196842624568328,
|
| 768 |
+
"grad_norm": 2.6319520473480225,
|
| 769 |
+
"learning_rate": 3.1140350877192986e-05,
|
| 770 |
+
"loss": 0.3775,
|
| 771 |
+
"step": 2675
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.3320177602368033,
|
| 775 |
+
"grad_norm": 1.337823510169983,
|
| 776 |
+
"learning_rate": 3.091191520467837e-05,
|
| 777 |
+
"loss": 0.2888,
|
| 778 |
+
"step": 2700
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.3443512580167736,
|
| 782 |
+
"grad_norm": 1.1048977375030518,
|
| 783 |
+
"learning_rate": 3.0683479532163744e-05,
|
| 784 |
+
"loss": 0.3207,
|
| 785 |
+
"step": 2725
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.3566847557967439,
|
| 789 |
+
"grad_norm": 2.2134850025177,
|
| 790 |
+
"learning_rate": 3.0455043859649123e-05,
|
| 791 |
+
"loss": 0.4205,
|
| 792 |
+
"step": 2750
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.3690182535767144,
|
| 796 |
+
"grad_norm": 4.411900520324707,
|
| 797 |
+
"learning_rate": 3.0226608187134503e-05,
|
| 798 |
+
"loss": 0.2979,
|
| 799 |
+
"step": 2775
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 1.3813517513566849,
|
| 803 |
+
"grad_norm": 2.7205402851104736,
|
| 804 |
+
"learning_rate": 2.9998172514619882e-05,
|
| 805 |
+
"loss": 0.2927,
|
| 806 |
+
"step": 2800
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 1.3936852491366551,
|
| 810 |
+
"grad_norm": 1.4053397178649902,
|
| 811 |
+
"learning_rate": 2.9769736842105268e-05,
|
| 812 |
+
"loss": 0.3394,
|
| 813 |
+
"step": 2825
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.4060187469166254,
|
| 817 |
+
"grad_norm": 1.3051424026489258,
|
| 818 |
+
"learning_rate": 2.9541301169590647e-05,
|
| 819 |
+
"loss": 0.3368,
|
| 820 |
+
"step": 2850
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 1.418352244696596,
|
| 824 |
+
"grad_norm": 4.241896152496338,
|
| 825 |
+
"learning_rate": 2.9312865497076026e-05,
|
| 826 |
+
"loss": 0.3273,
|
| 827 |
+
"step": 2875
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 1.4306857424765664,
|
| 831 |
+
"grad_norm": 1.2715412378311157,
|
| 832 |
+
"learning_rate": 2.9084429824561405e-05,
|
| 833 |
+
"loss": 0.2459,
|
| 834 |
+
"step": 2900
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.4430192402565367,
|
| 838 |
+
"grad_norm": 2.4846601486206055,
|
| 839 |
+
"learning_rate": 2.8855994152046784e-05,
|
| 840 |
+
"loss": 0.3038,
|
| 841 |
+
"step": 2925
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.4553527380365072,
|
| 845 |
+
"grad_norm": 0.9074434638023376,
|
| 846 |
+
"learning_rate": 2.8627558479532164e-05,
|
| 847 |
+
"loss": 0.2596,
|
| 848 |
+
"step": 2950
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 1.4676862358164775,
|
| 852 |
+
"grad_norm": 6.2226481437683105,
|
| 853 |
+
"learning_rate": 2.8399122807017546e-05,
|
| 854 |
+
"loss": 0.3292,
|
| 855 |
+
"step": 2975
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.480019733596448,
|
| 859 |
+
"grad_norm": 2.897814989089966,
|
| 860 |
+
"learning_rate": 2.8170687134502925e-05,
|
| 861 |
+
"loss": 0.2897,
|
| 862 |
+
"step": 3000
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.4923532313764183,
|
| 866 |
+
"grad_norm": 1.7691318988800049,
|
| 867 |
+
"learning_rate": 2.7942251461988305e-05,
|
| 868 |
+
"loss": 0.3451,
|
| 869 |
+
"step": 3025
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.5046867291563888,
|
| 873 |
+
"grad_norm": 7.944800853729248,
|
| 874 |
+
"learning_rate": 2.7713815789473684e-05,
|
| 875 |
+
"loss": 0.3526,
|
| 876 |
+
"step": 3050
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.517020226936359,
|
| 880 |
+
"grad_norm": 5.50998067855835,
|
| 881 |
+
"learning_rate": 2.7485380116959063e-05,
|
| 882 |
+
"loss": 0.2618,
|
| 883 |
+
"step": 3075
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.5293537247163296,
|
| 887 |
+
"grad_norm": 4.9781107902526855,
|
| 888 |
+
"learning_rate": 2.7256944444444442e-05,
|
| 889 |
+
"loss": 0.3387,
|
| 890 |
+
"step": 3100
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.5416872224963,
|
| 894 |
+
"grad_norm": 2.1930160522460938,
|
| 895 |
+
"learning_rate": 2.7028508771929828e-05,
|
| 896 |
+
"loss": 0.3274,
|
| 897 |
+
"step": 3125
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.5540207202762704,
|
| 901 |
+
"grad_norm": 3.252208948135376,
|
| 902 |
+
"learning_rate": 2.6800073099415207e-05,
|
| 903 |
+
"loss": 0.2491,
|
| 904 |
+
"step": 3150
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.5663542180562406,
|
| 908 |
+
"grad_norm": 13.36633586883545,
|
| 909 |
+
"learning_rate": 2.6571637426900586e-05,
|
| 910 |
+
"loss": 0.359,
|
| 911 |
+
"step": 3175
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.5786877158362111,
|
| 915 |
+
"grad_norm": 3.641357183456421,
|
| 916 |
+
"learning_rate": 2.6343201754385966e-05,
|
| 917 |
+
"loss": 0.3285,
|
| 918 |
+
"step": 3200
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 1.5910212136161817,
|
| 922 |
+
"grad_norm": 2.2045693397521973,
|
| 923 |
+
"learning_rate": 2.6114766081871345e-05,
|
| 924 |
+
"loss": 0.3226,
|
| 925 |
+
"step": 3225
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 1.603354711396152,
|
| 929 |
+
"grad_norm": 11.105202674865723,
|
| 930 |
+
"learning_rate": 2.5886330409356724e-05,
|
| 931 |
+
"loss": 0.2832,
|
| 932 |
+
"step": 3250
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.6156882091761222,
|
| 936 |
+
"grad_norm": 4.253530025482178,
|
| 937 |
+
"learning_rate": 2.565789473684211e-05,
|
| 938 |
+
"loss": 0.3696,
|
| 939 |
+
"step": 3275
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.6280217069560927,
|
| 943 |
+
"grad_norm": 0.993763267993927,
|
| 944 |
+
"learning_rate": 2.542945906432749e-05,
|
| 945 |
+
"loss": 0.2776,
|
| 946 |
+
"step": 3300
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.6403552047360632,
|
| 950 |
+
"grad_norm": 2.813020944595337,
|
| 951 |
+
"learning_rate": 2.520102339181287e-05,
|
| 952 |
+
"loss": 0.2947,
|
| 953 |
+
"step": 3325
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.6526887025160335,
|
| 957 |
+
"grad_norm": 1.1125609874725342,
|
| 958 |
+
"learning_rate": 2.4972587719298248e-05,
|
| 959 |
+
"loss": 0.293,
|
| 960 |
+
"step": 3350
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.6650222002960038,
|
| 964 |
+
"grad_norm": 3.3155879974365234,
|
| 965 |
+
"learning_rate": 2.4744152046783627e-05,
|
| 966 |
+
"loss": 0.3083,
|
| 967 |
+
"step": 3375
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 1.6773556980759743,
|
| 971 |
+
"grad_norm": 5.092229843139648,
|
| 972 |
+
"learning_rate": 2.4515716374269006e-05,
|
| 973 |
+
"loss": 0.2883,
|
| 974 |
+
"step": 3400
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.6896891958559448,
|
| 978 |
+
"grad_norm": 0.8376036286354065,
|
| 979 |
+
"learning_rate": 2.4287280701754385e-05,
|
| 980 |
+
"loss": 0.266,
|
| 981 |
+
"step": 3425
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.7020226936359153,
|
| 985 |
+
"grad_norm": 2.6180572509765625,
|
| 986 |
+
"learning_rate": 2.4058845029239768e-05,
|
| 987 |
+
"loss": 0.3319,
|
| 988 |
+
"step": 3450
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.7143561914158856,
|
| 992 |
+
"grad_norm": 1.0887091159820557,
|
| 993 |
+
"learning_rate": 2.3830409356725147e-05,
|
| 994 |
+
"loss": 0.2878,
|
| 995 |
+
"step": 3475
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.7266896891958559,
|
| 999 |
+
"grad_norm": 3.4597008228302,
|
| 1000 |
+
"learning_rate": 2.3601973684210526e-05,
|
| 1001 |
+
"loss": 0.3143,
|
| 1002 |
+
"step": 3500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.7390231869758264,
|
| 1006 |
+
"grad_norm": 1.2458105087280273,
|
| 1007 |
+
"learning_rate": 2.337353801169591e-05,
|
| 1008 |
+
"loss": 0.2772,
|
| 1009 |
+
"step": 3525
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.7513566847557969,
|
| 1013 |
+
"grad_norm": 1.0016106367111206,
|
| 1014 |
+
"learning_rate": 2.3145102339181288e-05,
|
| 1015 |
+
"loss": 0.254,
|
| 1016 |
+
"step": 3550
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.7636901825357671,
|
| 1020 |
+
"grad_norm": 0.9371845722198486,
|
| 1021 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 1022 |
+
"loss": 0.2866,
|
| 1023 |
+
"step": 3575
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.7760236803157374,
|
| 1027 |
+
"grad_norm": 2.7984836101531982,
|
| 1028 |
+
"learning_rate": 2.268823099415205e-05,
|
| 1029 |
+
"loss": 0.314,
|
| 1030 |
+
"step": 3600
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.788357178095708,
|
| 1034 |
+
"grad_norm": 8.407980918884277,
|
| 1035 |
+
"learning_rate": 2.245979532163743e-05,
|
| 1036 |
+
"loss": 0.3354,
|
| 1037 |
+
"step": 3625
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.8006906758756784,
|
| 1041 |
+
"grad_norm": 1.4253339767456055,
|
| 1042 |
+
"learning_rate": 2.2231359649122808e-05,
|
| 1043 |
+
"loss": 0.6666,
|
| 1044 |
+
"step": 3650
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.8130241736556487,
|
| 1048 |
+
"grad_norm": 1.8990155458450317,
|
| 1049 |
+
"learning_rate": 2.200292397660819e-05,
|
| 1050 |
+
"loss": 0.332,
|
| 1051 |
+
"step": 3675
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.825357671435619,
|
| 1055 |
+
"grad_norm": 3.489974021911621,
|
| 1056 |
+
"learning_rate": 2.177448830409357e-05,
|
| 1057 |
+
"loss": 0.2955,
|
| 1058 |
+
"step": 3700
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.8376911692155895,
|
| 1062 |
+
"grad_norm": 4.009921550750732,
|
| 1063 |
+
"learning_rate": 2.154605263157895e-05,
|
| 1064 |
+
"loss": 0.2922,
|
| 1065 |
+
"step": 3725
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.85002466699556,
|
| 1069 |
+
"grad_norm": 1.8342875242233276,
|
| 1070 |
+
"learning_rate": 2.1317616959064328e-05,
|
| 1071 |
+
"loss": 0.3508,
|
| 1072 |
+
"step": 3750
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.8623581647755303,
|
| 1076 |
+
"grad_norm": 1.782589316368103,
|
| 1077 |
+
"learning_rate": 2.1089181286549707e-05,
|
| 1078 |
+
"loss": 0.3245,
|
| 1079 |
+
"step": 3775
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.8746916625555008,
|
| 1083 |
+
"grad_norm": 2.984060049057007,
|
| 1084 |
+
"learning_rate": 2.0860745614035086e-05,
|
| 1085 |
+
"loss": 0.276,
|
| 1086 |
+
"step": 3800
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.887025160335471,
|
| 1090 |
+
"grad_norm": 1.6987401247024536,
|
| 1091 |
+
"learning_rate": 2.063230994152047e-05,
|
| 1092 |
+
"loss": 0.3445,
|
| 1093 |
+
"step": 3825
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.8993586581154416,
|
| 1097 |
+
"grad_norm": 1.4252331256866455,
|
| 1098 |
+
"learning_rate": 2.0403874269005848e-05,
|
| 1099 |
+
"loss": 0.316,
|
| 1100 |
+
"step": 3850
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.911692155895412,
|
| 1104 |
+
"grad_norm": 1.4252597093582153,
|
| 1105 |
+
"learning_rate": 2.0175438596491227e-05,
|
| 1106 |
+
"loss": 0.3233,
|
| 1107 |
+
"step": 3875
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.9240256536753824,
|
| 1111 |
+
"grad_norm": 6.7763752937316895,
|
| 1112 |
+
"learning_rate": 1.994700292397661e-05,
|
| 1113 |
+
"loss": 0.3568,
|
| 1114 |
+
"step": 3900
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.9363591514553526,
|
| 1118 |
+
"grad_norm": 1.0406028032302856,
|
| 1119 |
+
"learning_rate": 1.971856725146199e-05,
|
| 1120 |
+
"loss": 0.256,
|
| 1121 |
+
"step": 3925
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.9486926492353231,
|
| 1125 |
+
"grad_norm": 5.012691974639893,
|
| 1126 |
+
"learning_rate": 1.9490131578947368e-05,
|
| 1127 |
+
"loss": 0.3714,
|
| 1128 |
+
"step": 3950
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 1.9610261470152937,
|
| 1132 |
+
"grad_norm": 4.675971031188965,
|
| 1133 |
+
"learning_rate": 1.926169590643275e-05,
|
| 1134 |
+
"loss": 0.3189,
|
| 1135 |
+
"step": 3975
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 1.973359644795264,
|
| 1139 |
+
"grad_norm": 2.5267465114593506,
|
| 1140 |
+
"learning_rate": 1.903326023391813e-05,
|
| 1141 |
+
"loss": 0.2358,
|
| 1142 |
+
"step": 4000
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 1.9856931425752342,
|
| 1146 |
+
"grad_norm": 0.8952421545982361,
|
| 1147 |
+
"learning_rate": 1.880482456140351e-05,
|
| 1148 |
+
"loss": 0.2809,
|
| 1149 |
+
"step": 4025
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.9980266403552047,
|
| 1153 |
+
"grad_norm": 3.1482090950012207,
|
| 1154 |
+
"learning_rate": 1.857638888888889e-05,
|
| 1155 |
+
"loss": 0.2778,
|
| 1156 |
+
"step": 4050
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 2.0,
|
| 1160 |
+
"eval_accuracy": 0.9136830419095199,
|
| 1161 |
+
"eval_auc": 0.5388596734556735,
|
| 1162 |
+
"eval_f1": 0.9548948513415518,
|
| 1163 |
+
"eval_loss": 0.29811790585517883,
|
| 1164 |
+
"eval_precision": 0.9136830419095199,
|
| 1165 |
+
"eval_recall": 1.0,
|
| 1166 |
+
"eval_runtime": 33.6179,
|
| 1167 |
+
"eval_samples_per_second": 107.175,
|
| 1168 |
+
"eval_steps_per_second": 3.361,
|
| 1169 |
+
"step": 4054
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 2.0103601381351752,
|
| 1173 |
+
"grad_norm": 8.418047904968262,
|
| 1174 |
+
"learning_rate": 1.834795321637427e-05,
|
| 1175 |
+
"loss": 0.3508,
|
| 1176 |
+
"step": 4075
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 2.0226936359151457,
|
| 1180 |
+
"grad_norm": 0.8750646710395813,
|
| 1181 |
+
"learning_rate": 1.811951754385965e-05,
|
| 1182 |
+
"loss": 0.2411,
|
| 1183 |
+
"step": 4100
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 2.035027133695116,
|
| 1187 |
+
"grad_norm": 0.9350325465202332,
|
| 1188 |
+
"learning_rate": 1.789108187134503e-05,
|
| 1189 |
+
"loss": 0.2911,
|
| 1190 |
+
"step": 4125
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 2.0473606314750863,
|
| 1194 |
+
"grad_norm": 2.846468687057495,
|
| 1195 |
+
"learning_rate": 1.766264619883041e-05,
|
| 1196 |
+
"loss": 0.2719,
|
| 1197 |
+
"step": 4150
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 2.059694129255057,
|
| 1201 |
+
"grad_norm": 1.3613282442092896,
|
| 1202 |
+
"learning_rate": 1.7434210526315788e-05,
|
| 1203 |
+
"loss": 0.3131,
|
| 1204 |
+
"step": 4175
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 2.0720276270350273,
|
| 1208 |
+
"grad_norm": 1.0005241632461548,
|
| 1209 |
+
"learning_rate": 1.720577485380117e-05,
|
| 1210 |
+
"loss": 0.3139,
|
| 1211 |
+
"step": 4200
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 2.0843611248149974,
|
| 1215 |
+
"grad_norm": 1.0721725225448608,
|
| 1216 |
+
"learning_rate": 1.697733918128655e-05,
|
| 1217 |
+
"loss": 0.2719,
|
| 1218 |
+
"step": 4225
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 2.096694622594968,
|
| 1222 |
+
"grad_norm": 8.915780067443848,
|
| 1223 |
+
"learning_rate": 1.674890350877193e-05,
|
| 1224 |
+
"loss": 0.2804,
|
| 1225 |
+
"step": 4250
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 2.1090281203749384,
|
| 1229 |
+
"grad_norm": 2.3782267570495605,
|
| 1230 |
+
"learning_rate": 1.652046783625731e-05,
|
| 1231 |
+
"loss": 0.3442,
|
| 1232 |
+
"step": 4275
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 2.121361618154909,
|
| 1236 |
+
"grad_norm": 3.0817372798919678,
|
| 1237 |
+
"learning_rate": 1.629203216374269e-05,
|
| 1238 |
+
"loss": 0.289,
|
| 1239 |
+
"step": 4300
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.133695115934879,
|
| 1243 |
+
"grad_norm": 2.1607894897460938,
|
| 1244 |
+
"learning_rate": 1.6063596491228073e-05,
|
| 1245 |
+
"loss": 0.3078,
|
| 1246 |
+
"step": 4325
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 2.1460286137148494,
|
| 1250 |
+
"grad_norm": 2.4886415004730225,
|
| 1251 |
+
"learning_rate": 1.5835160818713452e-05,
|
| 1252 |
+
"loss": 0.3563,
|
| 1253 |
+
"step": 4350
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 2.15836211149482,
|
| 1257 |
+
"grad_norm": 2.146252393722534,
|
| 1258 |
+
"learning_rate": 1.560672514619883e-05,
|
| 1259 |
+
"loss": 0.3134,
|
| 1260 |
+
"step": 4375
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 2.1706956092747904,
|
| 1264 |
+
"grad_norm": 3.740633726119995,
|
| 1265 |
+
"learning_rate": 1.5378289473684214e-05,
|
| 1266 |
+
"loss": 0.3253,
|
| 1267 |
+
"step": 4400
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 2.183029107054761,
|
| 1271 |
+
"grad_norm": 2.453158140182495,
|
| 1272 |
+
"learning_rate": 1.5149853801169591e-05,
|
| 1273 |
+
"loss": 0.2921,
|
| 1274 |
+
"step": 4425
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 2.195362604834731,
|
| 1278 |
+
"grad_norm": 4.490250587463379,
|
| 1279 |
+
"learning_rate": 1.492141812865497e-05,
|
| 1280 |
+
"loss": 0.3505,
|
| 1281 |
+
"step": 4450
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 2.2076961026147015,
|
| 1285 |
+
"grad_norm": 1.5068897008895874,
|
| 1286 |
+
"learning_rate": 1.4692982456140353e-05,
|
| 1287 |
+
"loss": 0.307,
|
| 1288 |
+
"step": 4475
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 2.220029600394672,
|
| 1292 |
+
"grad_norm": 1.2755985260009766,
|
| 1293 |
+
"learning_rate": 1.4464546783625732e-05,
|
| 1294 |
+
"loss": 0.3071,
|
| 1295 |
+
"step": 4500
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 2.2323630981746425,
|
| 1299 |
+
"grad_norm": 2.845574378967285,
|
| 1300 |
+
"learning_rate": 1.4236111111111111e-05,
|
| 1301 |
+
"loss": 0.2902,
|
| 1302 |
+
"step": 4525
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 2.2446965959546126,
|
| 1306 |
+
"grad_norm": 0.8793368935585022,
|
| 1307 |
+
"learning_rate": 1.4007675438596494e-05,
|
| 1308 |
+
"loss": 0.3147,
|
| 1309 |
+
"step": 4550
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 2.257030093734583,
|
| 1313 |
+
"grad_norm": 2.616255521774292,
|
| 1314 |
+
"learning_rate": 1.3779239766081873e-05,
|
| 1315 |
+
"loss": 0.3844,
|
| 1316 |
+
"step": 4575
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 2.2693635915145536,
|
| 1320 |
+
"grad_norm": 1.2506290674209595,
|
| 1321 |
+
"learning_rate": 1.355080409356725e-05,
|
| 1322 |
+
"loss": 0.2602,
|
| 1323 |
+
"step": 4600
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 2.281697089294524,
|
| 1327 |
+
"grad_norm": 5.174871444702148,
|
| 1328 |
+
"learning_rate": 1.3322368421052633e-05,
|
| 1329 |
+
"loss": 0.3425,
|
| 1330 |
+
"step": 4625
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 2.294030587074494,
|
| 1334 |
+
"grad_norm": 2.352529764175415,
|
| 1335 |
+
"learning_rate": 1.3093932748538012e-05,
|
| 1336 |
+
"loss": 0.3513,
|
| 1337 |
+
"step": 4650
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 2.3063640848544646,
|
| 1341 |
+
"grad_norm": 3.686067819595337,
|
| 1342 |
+
"learning_rate": 1.2865497076023392e-05,
|
| 1343 |
+
"loss": 0.3017,
|
| 1344 |
+
"step": 4675
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.318697582634435,
|
| 1348 |
+
"grad_norm": 2.6614937782287598,
|
| 1349 |
+
"learning_rate": 1.2637061403508774e-05,
|
| 1350 |
+
"loss": 0.2407,
|
| 1351 |
+
"step": 4700
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 2.3310310804144057,
|
| 1355 |
+
"grad_norm": 3.1493828296661377,
|
| 1356 |
+
"learning_rate": 1.2408625730994153e-05,
|
| 1357 |
+
"loss": 0.3013,
|
| 1358 |
+
"step": 4725
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 2.343364578194376,
|
| 1362 |
+
"grad_norm": 2.7974276542663574,
|
| 1363 |
+
"learning_rate": 1.2180190058479534e-05,
|
| 1364 |
+
"loss": 0.3496,
|
| 1365 |
+
"step": 4750
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 2.355698075974346,
|
| 1369 |
+
"grad_norm": 0.8237548470497131,
|
| 1370 |
+
"learning_rate": 1.1951754385964913e-05,
|
| 1371 |
+
"loss": 0.2785,
|
| 1372 |
+
"step": 4775
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 2.3680315737543167,
|
| 1376 |
+
"grad_norm": 0.9614822864532471,
|
| 1377 |
+
"learning_rate": 1.1723318713450293e-05,
|
| 1378 |
+
"loss": 0.3653,
|
| 1379 |
+
"step": 4800
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 2.3803650715342872,
|
| 1383 |
+
"grad_norm": 2.6732375621795654,
|
| 1384 |
+
"learning_rate": 1.1494883040935673e-05,
|
| 1385 |
+
"loss": 0.3071,
|
| 1386 |
+
"step": 4825
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 2.3926985693142573,
|
| 1390 |
+
"grad_norm": 5.766613960266113,
|
| 1391 |
+
"learning_rate": 1.1266447368421053e-05,
|
| 1392 |
+
"loss": 0.3271,
|
| 1393 |
+
"step": 4850
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 2.405032067094228,
|
| 1397 |
+
"grad_norm": 4.799734115600586,
|
| 1398 |
+
"learning_rate": 1.1038011695906433e-05,
|
| 1399 |
+
"loss": 0.3366,
|
| 1400 |
+
"step": 4875
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 2.4173655648741983,
|
| 1404 |
+
"grad_norm": 4.730321407318115,
|
| 1405 |
+
"learning_rate": 1.0809576023391814e-05,
|
| 1406 |
+
"loss": 0.3906,
|
| 1407 |
+
"step": 4900
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 2.429699062654169,
|
| 1411 |
+
"grad_norm": 1.9978655576705933,
|
| 1412 |
+
"learning_rate": 1.0581140350877194e-05,
|
| 1413 |
+
"loss": 0.2988,
|
| 1414 |
+
"step": 4925
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 2.4420325604341393,
|
| 1418 |
+
"grad_norm": 7.501604080200195,
|
| 1419 |
+
"learning_rate": 1.0352704678362574e-05,
|
| 1420 |
+
"loss": 0.2983,
|
| 1421 |
+
"step": 4950
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 2.4543660582141094,
|
| 1425 |
+
"grad_norm": 2.636504650115967,
|
| 1426 |
+
"learning_rate": 1.0124269005847954e-05,
|
| 1427 |
+
"loss": 0.241,
|
| 1428 |
+
"step": 4975
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.46669955599408,
|
| 1432 |
+
"grad_norm": 0.9329339861869812,
|
| 1433 |
+
"learning_rate": 9.895833333333333e-06,
|
| 1434 |
+
"loss": 0.2748,
|
| 1435 |
+
"step": 5000
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.4790330537740504,
|
| 1439 |
+
"grad_norm": 3.177311897277832,
|
| 1440 |
+
"learning_rate": 9.667397660818714e-06,
|
| 1441 |
+
"loss": 0.2675,
|
| 1442 |
+
"step": 5025
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 2.491366551554021,
|
| 1446 |
+
"grad_norm": 2.898000717163086,
|
| 1447 |
+
"learning_rate": 9.438961988304094e-06,
|
| 1448 |
+
"loss": 0.3033,
|
| 1449 |
+
"step": 5050
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.5037000493339914,
|
| 1453 |
+
"grad_norm": 2.6203970909118652,
|
| 1454 |
+
"learning_rate": 9.210526315789474e-06,
|
| 1455 |
+
"loss": 0.2777,
|
| 1456 |
+
"step": 5075
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.5160335471139614,
|
| 1460 |
+
"grad_norm": 3.7342023849487305,
|
| 1461 |
+
"learning_rate": 8.982090643274855e-06,
|
| 1462 |
+
"loss": 0.3422,
|
| 1463 |
+
"step": 5100
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 2.528367044893932,
|
| 1467 |
+
"grad_norm": 1.0027085542678833,
|
| 1468 |
+
"learning_rate": 8.753654970760235e-06,
|
| 1469 |
+
"loss": 0.3629,
|
| 1470 |
+
"step": 5125
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 2.5407005426739024,
|
| 1474 |
+
"grad_norm": 4.914186477661133,
|
| 1475 |
+
"learning_rate": 8.525219298245615e-06,
|
| 1476 |
+
"loss": 0.2853,
|
| 1477 |
+
"step": 5150
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 2.5530340404538725,
|
| 1481 |
+
"grad_norm": 1.0409221649169922,
|
| 1482 |
+
"learning_rate": 8.296783625730994e-06,
|
| 1483 |
+
"loss": 0.2965,
|
| 1484 |
+
"step": 5175
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 2.565367538233843,
|
| 1488 |
+
"grad_norm": 5.284379482269287,
|
| 1489 |
+
"learning_rate": 8.068347953216375e-06,
|
| 1490 |
+
"loss": 0.3599,
|
| 1491 |
+
"step": 5200
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 2.5777010360138135,
|
| 1495 |
+
"grad_norm": 4.738578796386719,
|
| 1496 |
+
"learning_rate": 7.839912280701754e-06,
|
| 1497 |
+
"loss": 0.3871,
|
| 1498 |
+
"step": 5225
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 2.590034533793784,
|
| 1502 |
+
"grad_norm": 3.7173986434936523,
|
| 1503 |
+
"learning_rate": 7.611476608187135e-06,
|
| 1504 |
+
"loss": 0.3364,
|
| 1505 |
+
"step": 5250
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 2.6023680315737545,
|
| 1509 |
+
"grad_norm": 1.101990818977356,
|
| 1510 |
+
"learning_rate": 7.383040935672516e-06,
|
| 1511 |
+
"loss": 0.2705,
|
| 1512 |
+
"step": 5275
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 2.6147015293537246,
|
| 1516 |
+
"grad_norm": 0.8991968035697937,
|
| 1517 |
+
"learning_rate": 7.154605263157895e-06,
|
| 1518 |
+
"loss": 0.2464,
|
| 1519 |
+
"step": 5300
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 2.627035027133695,
|
| 1523 |
+
"grad_norm": 1.0676743984222412,
|
| 1524 |
+
"learning_rate": 6.926169590643275e-06,
|
| 1525 |
+
"loss": 0.2874,
|
| 1526 |
+
"step": 5325
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 2.6393685249136656,
|
| 1530 |
+
"grad_norm": 3.034912347793579,
|
| 1531 |
+
"learning_rate": 6.697733918128656e-06,
|
| 1532 |
+
"loss": 0.282,
|
| 1533 |
+
"step": 5350
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 2.6517020226936356,
|
| 1537 |
+
"grad_norm": 0.8661335706710815,
|
| 1538 |
+
"learning_rate": 6.469298245614036e-06,
|
| 1539 |
+
"loss": 0.2463,
|
| 1540 |
+
"step": 5375
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 2.6640355204736066,
|
| 1544 |
+
"grad_norm": 2.791443109512329,
|
| 1545 |
+
"learning_rate": 6.240862573099415e-06,
|
| 1546 |
+
"loss": 0.2501,
|
| 1547 |
+
"step": 5400
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 2.6763690182535766,
|
| 1551 |
+
"grad_norm": 1.0052167177200317,
|
| 1552 |
+
"learning_rate": 6.012426900584796e-06,
|
| 1553 |
+
"loss": 0.3198,
|
| 1554 |
+
"step": 5425
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 2.688702516033547,
|
| 1558 |
+
"grad_norm": 2.621087074279785,
|
| 1559 |
+
"learning_rate": 5.783991228070176e-06,
|
| 1560 |
+
"loss": 0.3273,
|
| 1561 |
+
"step": 5450
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 2.7010360138135177,
|
| 1565 |
+
"grad_norm": 1.0234779119491577,
|
| 1566 |
+
"learning_rate": 5.555555555555556e-06,
|
| 1567 |
+
"loss": 0.3213,
|
| 1568 |
+
"step": 5475
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 2.7133695115934877,
|
| 1572 |
+
"grad_norm": 4.86189603805542,
|
| 1573 |
+
"learning_rate": 5.327119883040936e-06,
|
| 1574 |
+
"loss": 0.3636,
|
| 1575 |
+
"step": 5500
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 2.725703009373458,
|
| 1579 |
+
"grad_norm": 1.8415815830230713,
|
| 1580 |
+
"learning_rate": 5.098684210526316e-06,
|
| 1581 |
+
"loss": 0.3645,
|
| 1582 |
+
"step": 5525
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 2.7380365071534287,
|
| 1586 |
+
"grad_norm": 1.44539213180542,
|
| 1587 |
+
"learning_rate": 4.870248538011697e-06,
|
| 1588 |
+
"loss": 0.301,
|
| 1589 |
+
"step": 5550
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 2.7503700049333992,
|
| 1593 |
+
"grad_norm": 4.458736896514893,
|
| 1594 |
+
"learning_rate": 4.641812865497076e-06,
|
| 1595 |
+
"loss": 0.3528,
|
| 1596 |
+
"step": 5575
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 2.7627035027133697,
|
| 1600 |
+
"grad_norm": 2.022102117538452,
|
| 1601 |
+
"learning_rate": 4.413377192982456e-06,
|
| 1602 |
+
"loss": 0.2988,
|
| 1603 |
+
"step": 5600
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 2.77503700049334,
|
| 1607 |
+
"grad_norm": 1.420719027519226,
|
| 1608 |
+
"learning_rate": 4.184941520467837e-06,
|
| 1609 |
+
"loss": 0.2752,
|
| 1610 |
+
"step": 5625
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 2.7873704982733103,
|
| 1614 |
+
"grad_norm": 0.9011722803115845,
|
| 1615 |
+
"learning_rate": 3.956505847953217e-06,
|
| 1616 |
+
"loss": 0.2944,
|
| 1617 |
+
"step": 5650
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 2.799703996053281,
|
| 1621 |
+
"grad_norm": 2.3301029205322266,
|
| 1622 |
+
"learning_rate": 3.7280701754385965e-06,
|
| 1623 |
+
"loss": 0.2935,
|
| 1624 |
+
"step": 5675
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 2.812037493833251,
|
| 1628 |
+
"grad_norm": 0.8454089760780334,
|
| 1629 |
+
"learning_rate": 3.499634502923977e-06,
|
| 1630 |
+
"loss": 0.2912,
|
| 1631 |
+
"step": 5700
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 2.8243709916132214,
|
| 1635 |
+
"grad_norm": 1.046055555343628,
|
| 1636 |
+
"learning_rate": 3.271198830409357e-06,
|
| 1637 |
+
"loss": 0.2726,
|
| 1638 |
+
"step": 5725
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 2.836704489393192,
|
| 1642 |
+
"grad_norm": 5.1950201988220215,
|
| 1643 |
+
"learning_rate": 3.042763157894737e-06,
|
| 1644 |
+
"loss": 0.3481,
|
| 1645 |
+
"step": 5750
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 2.8490379871731624,
|
| 1649 |
+
"grad_norm": 2.519756317138672,
|
| 1650 |
+
"learning_rate": 2.814327485380117e-06,
|
| 1651 |
+
"loss": 0.2713,
|
| 1652 |
+
"step": 5775
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 2.861371484953133,
|
| 1656 |
+
"grad_norm": 0.9701582193374634,
|
| 1657 |
+
"learning_rate": 2.585891812865497e-06,
|
| 1658 |
+
"loss": 0.3381,
|
| 1659 |
+
"step": 5800
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 2.873704982733103,
|
| 1663 |
+
"grad_norm": 2.884457588195801,
|
| 1664 |
+
"learning_rate": 2.3574561403508775e-06,
|
| 1665 |
+
"loss": 0.3101,
|
| 1666 |
+
"step": 5825
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 2.8860384805130734,
|
| 1670 |
+
"grad_norm": 1.04812753200531,
|
| 1671 |
+
"learning_rate": 2.1290204678362575e-06,
|
| 1672 |
+
"loss": 0.3222,
|
| 1673 |
+
"step": 5850
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 2.898371978293044,
|
| 1677 |
+
"grad_norm": 5.422378063201904,
|
| 1678 |
+
"learning_rate": 1.9005847953216373e-06,
|
| 1679 |
+
"loss": 0.3344,
|
| 1680 |
+
"step": 5875
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 2.9107054760730144,
|
| 1684 |
+
"grad_norm": 2.4429121017456055,
|
| 1685 |
+
"learning_rate": 1.6721491228070176e-06,
|
| 1686 |
+
"loss": 0.3438,
|
| 1687 |
+
"step": 5900
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 2.923038973852985,
|
| 1691 |
+
"grad_norm": 3.2756924629211426,
|
| 1692 |
+
"learning_rate": 1.4437134502923976e-06,
|
| 1693 |
+
"loss": 0.2633,
|
| 1694 |
+
"step": 5925
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 2.935372471632955,
|
| 1698 |
+
"grad_norm": 3.166130781173706,
|
| 1699 |
+
"learning_rate": 1.2152777777777778e-06,
|
| 1700 |
+
"loss": 0.3795,
|
| 1701 |
+
"step": 5950
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 2.9477059694129255,
|
| 1705 |
+
"grad_norm": 2.424431085586548,
|
| 1706 |
+
"learning_rate": 9.868421052631579e-07,
|
| 1707 |
+
"loss": 0.3337,
|
| 1708 |
+
"step": 5975
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 2.960039467192896,
|
| 1712 |
+
"grad_norm": 5.236613750457764,
|
| 1713 |
+
"learning_rate": 7.58406432748538e-07,
|
| 1714 |
+
"loss": 0.3092,
|
| 1715 |
+
"step": 6000
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 2.972372964972866,
|
| 1719 |
+
"grad_norm": 1.0767054557800293,
|
| 1720 |
+
"learning_rate": 5.299707602339181e-07,
|
| 1721 |
+
"loss": 0.3348,
|
| 1722 |
+
"step": 6025
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 2.9847064627528366,
|
| 1726 |
+
"grad_norm": 4.74832010269165,
|
| 1727 |
+
"learning_rate": 3.0153508771929827e-07,
|
| 1728 |
+
"loss": 0.3349,
|
| 1729 |
+
"step": 6050
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 2.997039960532807,
|
| 1733 |
+
"grad_norm": 2.1578445434570312,
|
| 1734 |
+
"learning_rate": 7.309941520467836e-08,
|
| 1735 |
+
"loss": 0.3508,
|
| 1736 |
+
"step": 6075
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 3.0,
|
| 1740 |
+
"eval_accuracy": 0.9136830419095199,
|
| 1741 |
+
"eval_auc": 0.5282966990033326,
|
| 1742 |
+
"eval_f1": 0.9548948513415518,
|
| 1743 |
+
"eval_loss": 0.29475775361061096,
|
| 1744 |
+
"eval_precision": 0.9136830419095199,
|
| 1745 |
+
"eval_recall": 1.0,
|
| 1746 |
+
"eval_runtime": 33.2805,
|
| 1747 |
+
"eval_samples_per_second": 108.262,
|
| 1748 |
+
"eval_steps_per_second": 3.395,
|
| 1749 |
+
"step": 6081
|
| 1750 |
+
}
|
| 1751 |
+
],
|
| 1752 |
+
"logging_steps": 25,
|
| 1753 |
+
"max_steps": 6081,
|
| 1754 |
+
"num_input_tokens_seen": 0,
|
| 1755 |
+
"num_train_epochs": 3,
|
| 1756 |
+
"save_steps": 500,
|
| 1757 |
+
"stateful_callbacks": {
|
| 1758 |
+
"EarlyStoppingCallback": {
|
| 1759 |
+
"args": {
|
| 1760 |
+
"early_stopping_patience": 5,
|
| 1761 |
+
"early_stopping_threshold": 0.01
|
| 1762 |
+
},
|
| 1763 |
+
"attributes": {
|
| 1764 |
+
"early_stopping_patience_counter": 2
|
| 1765 |
+
}
|
| 1766 |
+
},
|
| 1767 |
+
"TrainerControl": {
|
| 1768 |
+
"args": {
|
| 1769 |
+
"should_epoch_stop": false,
|
| 1770 |
+
"should_evaluate": false,
|
| 1771 |
+
"should_log": false,
|
| 1772 |
+
"should_save": true,
|
| 1773 |
+
"should_training_stop": true
|
| 1774 |
+
},
|
| 1775 |
+
"attributes": {}
|
| 1776 |
+
}
|
| 1777 |
+
},
|
| 1778 |
+
"total_flos": 4.532261799273062e+16,
|
| 1779 |
+
"train_batch_size": 16,
|
| 1780 |
+
"trial_name": null,
|
| 1781 |
+
"trial_params": null
|
| 1782 |
+
}
|
checkpoint-6081/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2462a44f8bfd2c5c132a34fe87a12bdf94977fa46efcc9df9186adca0030c51d
|
| 3 |
+
size 5432
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "BAAI/bge-large-en-v1.5",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "BAD_USER",
|
| 15 |
+
"1": "GOOD_USER"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"BAD_USER": 0,
|
| 21 |
+
"GOOD_USER": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "bert",
|
| 26 |
+
"num_attention_heads": 16,
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.48.0",
|
| 33 |
+
"type_vocab_size": 2,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:210a11360287b8671eaf6f21b6f39996c84fd82642608b82cb277de916601c7f
|
| 3 |
+
size 1340622760
|
runs/May22_15-42-05_r-trentmkelly-autotrain-advanced-6oq4mr6b-da706-g95do/events.out.tfevents.1747928527.r-trentmkelly-autotrain-advanced-6oq4mr6b-da706-g95do.89.0
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 sha256:258d6c73dc7731b83ce624cd23239cfc19675a90a2bcdb60550d1a46c26de99d
|
| 3 |
+
size 58460
|
runs/May22_15-42-05_r-trentmkelly-autotrain-advanced-6oq4mr6b-da706-g95do/events.out.tfevents.1747932270.r-trentmkelly-autotrain-advanced-6oq4mr6b-da706-g95do.89.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24e68ac3f41cb98afd769ea3673308335c81632dddbb09230d1c369b75ead20a
|
| 3 |
+
size 607
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
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 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2462a44f8bfd2c5c132a34fe87a12bdf94977fa46efcc9df9186adca0030c51d
|
| 3 |
+
size 5432
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-roblox-12-with-bge-large/autotrain-data",
|
| 3 |
+
"model": "BAAI/bge-large-en-v1.5",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 3,
|
| 6 |
+
"max_seq_length": 256,
|
| 7 |
+
"batch_size": 16,
|
| 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": "autotrain-roblox-12-with-bge-large",
|
| 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": "trentmkelly",
|
| 27 |
+
"log": "tensorboard",
|
| 28 |
+
"early_stopping_patience": 5,
|
| 29 |
+
"early_stopping_threshold": 0.01
|
| 30 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|