Upload folder using huggingface_hub
Browse files- README.md +26 -0
- checkpoint-1045/config.json +33 -0
- checkpoint-1045/model.safetensors +3 -0
- checkpoint-1045/optimizer.pt +3 -0
- checkpoint-1045/rng_state.pth +3 -0
- checkpoint-1045/scheduler.pt +3 -0
- checkpoint-1045/trainer_state.json +835 -0
- checkpoint-1045/training_args.bin +3 -0
- config.json +33 -0
- model.safetensors +3 -0
- runs/Feb21_00-15-38_r-abgegrieft-train-bert-toxic-2-ylkx2gqa-afc62-whkno/events.out.tfevents.1740096940.r-abgegrieft-train-bert-toxic-2-ylkx2gqa-afc62-whkno.218.0 +2 -2
- runs/Feb21_00-15-38_r-abgegrieft-train-bert-toxic-2-ylkx2gqa-afc62-whkno/events.out.tfevents.1740097011.r-abgegrieft-train-bert-toxic-2-ylkx2gqa-afc62-whkno.218.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-regression
|
| 6 |
+
base_model: google-bert/bert-base-german-cased
|
| 7 |
+
widget:
|
| 8 |
+
- text: "I love AutoTrain"
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Trained Using AutoTrain
|
| 12 |
+
|
| 13 |
+
- Problem type: Text Regression
|
| 14 |
+
|
| 15 |
+
## Validation Metrics
|
| 16 |
+
loss: 0.02065342105925083
|
| 17 |
+
|
| 18 |
+
mse: 0.02065342292189598
|
| 19 |
+
|
| 20 |
+
mae: 0.09870430827140808
|
| 21 |
+
|
| 22 |
+
r2: 0.7598985433578491
|
| 23 |
+
|
| 24 |
+
rmse: 0.1437129880069856
|
| 25 |
+
|
| 26 |
+
explained_variance: 0.75990229845047
|
checkpoint-1045/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-german-cased",
|
| 3 |
+
"_num_labels": 1,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "target"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"target": 0
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "bert",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "regression",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.48.0",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 30000
|
| 33 |
+
}
|
checkpoint-1045/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a615ce45903fcbfba3015b559a405c6ea281d73bfe314d9cf53f775f7e59a477
|
| 3 |
+
size 436351980
|
checkpoint-1045/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d24e6de46b1b408a72ebce777cfc8d9a19c4f06065b74257655d648e0d3034ac
|
| 3 |
+
size 872825082
|
checkpoint-1045/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb19b340d48378435a343785d65a5f0358d2597c7a0333570d25f40cd7f810ac
|
| 3 |
+
size 14244
|
checkpoint-1045/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9552788ec182e52205c8956ba3235f0c5946b5ad23ebcbfb411675b508f75f2
|
| 3 |
+
size 1064
|
checkpoint-1045/trainer_state.json
ADDED
|
@@ -0,0 +1,835 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.02065342105925083,
|
| 3 |
+
"best_model_checkpoint": "autotrain-qiyqv-nm11e/checkpoint-1045",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1045,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04784688995215311,
|
| 13 |
+
"grad_norm": 4.4024553298950195,
|
| 14 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 15 |
+
"loss": 0.1368,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09569377990430622,
|
| 20 |
+
"grad_norm": 5.853402614593506,
|
| 21 |
+
"learning_rate": 9.523809523809523e-06,
|
| 22 |
+
"loss": 0.076,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.14354066985645933,
|
| 27 |
+
"grad_norm": 5.490858554840088,
|
| 28 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 29 |
+
"loss": 0.0666,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.19138755980861244,
|
| 34 |
+
"grad_norm": 4.02401065826416,
|
| 35 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 36 |
+
"loss": 0.0796,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.23923444976076555,
|
| 41 |
+
"grad_norm": 3.884706497192383,
|
| 42 |
+
"learning_rate": 2.380952380952381e-05,
|
| 43 |
+
"loss": 0.081,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.28708133971291866,
|
| 48 |
+
"grad_norm": 3.4717812538146973,
|
| 49 |
+
"learning_rate": 2.857142857142857e-05,
|
| 50 |
+
"loss": 0.0948,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3349282296650718,
|
| 55 |
+
"grad_norm": 4.965182781219482,
|
| 56 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 57 |
+
"loss": 0.071,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3827751196172249,
|
| 62 |
+
"grad_norm": 2.4725799560546875,
|
| 63 |
+
"learning_rate": 3.809523809523809e-05,
|
| 64 |
+
"loss": 0.056,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.430622009569378,
|
| 69 |
+
"grad_norm": 5.283918857574463,
|
| 70 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 71 |
+
"loss": 0.0622,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4784688995215311,
|
| 76 |
+
"grad_norm": 2.1466543674468994,
|
| 77 |
+
"learning_rate": 4.761904761904762e-05,
|
| 78 |
+
"loss": 0.0973,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5263157894736842,
|
| 83 |
+
"grad_norm": 1.8952351808547974,
|
| 84 |
+
"learning_rate": 4.973404255319149e-05,
|
| 85 |
+
"loss": 0.0716,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5741626794258373,
|
| 90 |
+
"grad_norm": 1.0476309061050415,
|
| 91 |
+
"learning_rate": 4.920212765957447e-05,
|
| 92 |
+
"loss": 0.0499,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6220095693779905,
|
| 97 |
+
"grad_norm": 1.6094298362731934,
|
| 98 |
+
"learning_rate": 4.8670212765957454e-05,
|
| 99 |
+
"loss": 0.0577,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6698564593301436,
|
| 104 |
+
"grad_norm": 5.809442520141602,
|
| 105 |
+
"learning_rate": 4.8138297872340426e-05,
|
| 106 |
+
"loss": 0.0576,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7177033492822966,
|
| 111 |
+
"grad_norm": 6.288730144500732,
|
| 112 |
+
"learning_rate": 4.7606382978723405e-05,
|
| 113 |
+
"loss": 0.0637,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7655502392344498,
|
| 118 |
+
"grad_norm": 4.917440414428711,
|
| 119 |
+
"learning_rate": 4.7074468085106385e-05,
|
| 120 |
+
"loss": 0.0759,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8133971291866029,
|
| 125 |
+
"grad_norm": 3.525897741317749,
|
| 126 |
+
"learning_rate": 4.6542553191489364e-05,
|
| 127 |
+
"loss": 0.0688,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.861244019138756,
|
| 132 |
+
"grad_norm": 7.367300033569336,
|
| 133 |
+
"learning_rate": 4.601063829787234e-05,
|
| 134 |
+
"loss": 0.0669,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.9090909090909091,
|
| 139 |
+
"grad_norm": 6.313709259033203,
|
| 140 |
+
"learning_rate": 4.547872340425532e-05,
|
| 141 |
+
"loss": 0.0554,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9569377990430622,
|
| 146 |
+
"grad_norm": 1.1780610084533691,
|
| 147 |
+
"learning_rate": 4.49468085106383e-05,
|
| 148 |
+
"loss": 0.0553,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_explained_variance": 0.5684667825698853,
|
| 154 |
+
"eval_loss": 0.055994417518377304,
|
| 155 |
+
"eval_mae": 0.1900322586297989,
|
| 156 |
+
"eval_mse": 0.055994417518377304,
|
| 157 |
+
"eval_r2": 0.3490501642227173,
|
| 158 |
+
"eval_rmse": 0.23663139588477541,
|
| 159 |
+
"eval_runtime": 0.5134,
|
| 160 |
+
"eval_samples_per_second": 814.257,
|
| 161 |
+
"eval_steps_per_second": 52.596,
|
| 162 |
+
"step": 209
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.0047846889952152,
|
| 166 |
+
"grad_norm": 5.32818078994751,
|
| 167 |
+
"learning_rate": 4.441489361702128e-05,
|
| 168 |
+
"loss": 0.0673,
|
| 169 |
+
"step": 210
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.0526315789473684,
|
| 173 |
+
"grad_norm": 1.9257011413574219,
|
| 174 |
+
"learning_rate": 4.388297872340425e-05,
|
| 175 |
+
"loss": 0.0481,
|
| 176 |
+
"step": 220
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.1004784688995215,
|
| 180 |
+
"grad_norm": 4.480106353759766,
|
| 181 |
+
"learning_rate": 4.335106382978724e-05,
|
| 182 |
+
"loss": 0.0461,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.1483253588516746,
|
| 187 |
+
"grad_norm": 2.081613302230835,
|
| 188 |
+
"learning_rate": 4.281914893617022e-05,
|
| 189 |
+
"loss": 0.0679,
|
| 190 |
+
"step": 240
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.1961722488038278,
|
| 194 |
+
"grad_norm": 1.601739525794983,
|
| 195 |
+
"learning_rate": 4.228723404255319e-05,
|
| 196 |
+
"loss": 0.0422,
|
| 197 |
+
"step": 250
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.244019138755981,
|
| 201 |
+
"grad_norm": 5.248487949371338,
|
| 202 |
+
"learning_rate": 4.175531914893617e-05,
|
| 203 |
+
"loss": 0.0546,
|
| 204 |
+
"step": 260
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.291866028708134,
|
| 208 |
+
"grad_norm": 2.3544135093688965,
|
| 209 |
+
"learning_rate": 4.1223404255319156e-05,
|
| 210 |
+
"loss": 0.0527,
|
| 211 |
+
"step": 270
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.339712918660287,
|
| 215 |
+
"grad_norm": 1.0384206771850586,
|
| 216 |
+
"learning_rate": 4.069148936170213e-05,
|
| 217 |
+
"loss": 0.0386,
|
| 218 |
+
"step": 280
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.38755980861244,
|
| 222 |
+
"grad_norm": 5.871868133544922,
|
| 223 |
+
"learning_rate": 4.015957446808511e-05,
|
| 224 |
+
"loss": 0.0466,
|
| 225 |
+
"step": 290
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.4354066985645932,
|
| 229 |
+
"grad_norm": 0.8723556399345398,
|
| 230 |
+
"learning_rate": 3.962765957446809e-05,
|
| 231 |
+
"loss": 0.0559,
|
| 232 |
+
"step": 300
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.4832535885167464,
|
| 236 |
+
"grad_norm": 10.12267017364502,
|
| 237 |
+
"learning_rate": 3.9095744680851066e-05,
|
| 238 |
+
"loss": 0.0731,
|
| 239 |
+
"step": 310
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.5311004784688995,
|
| 243 |
+
"grad_norm": 6.317343235015869,
|
| 244 |
+
"learning_rate": 3.8563829787234045e-05,
|
| 245 |
+
"loss": 0.0624,
|
| 246 |
+
"step": 320
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.5789473684210527,
|
| 250 |
+
"grad_norm": 2.277057409286499,
|
| 251 |
+
"learning_rate": 3.8031914893617024e-05,
|
| 252 |
+
"loss": 0.0541,
|
| 253 |
+
"step": 330
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.6267942583732058,
|
| 257 |
+
"grad_norm": 6.247572898864746,
|
| 258 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 259 |
+
"loss": 0.0478,
|
| 260 |
+
"step": 340
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.674641148325359,
|
| 264 |
+
"grad_norm": 4.217668533325195,
|
| 265 |
+
"learning_rate": 3.696808510638298e-05,
|
| 266 |
+
"loss": 0.0365,
|
| 267 |
+
"step": 350
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.722488038277512,
|
| 271 |
+
"grad_norm": 1.396332859992981,
|
| 272 |
+
"learning_rate": 3.6436170212765955e-05,
|
| 273 |
+
"loss": 0.0473,
|
| 274 |
+
"step": 360
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.7703349282296652,
|
| 278 |
+
"grad_norm": 2.1837027072906494,
|
| 279 |
+
"learning_rate": 3.590425531914894e-05,
|
| 280 |
+
"loss": 0.0282,
|
| 281 |
+
"step": 370
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.8181818181818183,
|
| 285 |
+
"grad_norm": 2.740877151489258,
|
| 286 |
+
"learning_rate": 3.537234042553192e-05,
|
| 287 |
+
"loss": 0.0398,
|
| 288 |
+
"step": 380
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.8660287081339713,
|
| 292 |
+
"grad_norm": 4.913898468017578,
|
| 293 |
+
"learning_rate": 3.484042553191489e-05,
|
| 294 |
+
"loss": 0.0539,
|
| 295 |
+
"step": 390
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.9138755980861244,
|
| 299 |
+
"grad_norm": 2.2887203693389893,
|
| 300 |
+
"learning_rate": 3.430851063829787e-05,
|
| 301 |
+
"loss": 0.0573,
|
| 302 |
+
"step": 400
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.9617224880382775,
|
| 306 |
+
"grad_norm": 4.039773464202881,
|
| 307 |
+
"learning_rate": 3.377659574468085e-05,
|
| 308 |
+
"loss": 0.0408,
|
| 309 |
+
"step": 410
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.0,
|
| 313 |
+
"eval_explained_variance": 0.6925871968269348,
|
| 314 |
+
"eval_loss": 0.03033822402358055,
|
| 315 |
+
"eval_mae": 0.1332806497812271,
|
| 316 |
+
"eval_mse": 0.03033822402358055,
|
| 317 |
+
"eval_r2": 0.647310197353363,
|
| 318 |
+
"eval_rmse": 0.17417871288874698,
|
| 319 |
+
"eval_runtime": 0.5153,
|
| 320 |
+
"eval_samples_per_second": 811.122,
|
| 321 |
+
"eval_steps_per_second": 52.393,
|
| 322 |
+
"step": 418
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.0095693779904304,
|
| 326 |
+
"grad_norm": 2.9417381286621094,
|
| 327 |
+
"learning_rate": 3.324468085106383e-05,
|
| 328 |
+
"loss": 0.0622,
|
| 329 |
+
"step": 420
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.0574162679425836,
|
| 333 |
+
"grad_norm": 0.857741117477417,
|
| 334 |
+
"learning_rate": 3.271276595744681e-05,
|
| 335 |
+
"loss": 0.0325,
|
| 336 |
+
"step": 430
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.1052631578947367,
|
| 340 |
+
"grad_norm": 3.941061496734619,
|
| 341 |
+
"learning_rate": 3.218085106382979e-05,
|
| 342 |
+
"loss": 0.0182,
|
| 343 |
+
"step": 440
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.15311004784689,
|
| 347 |
+
"grad_norm": 2.1936357021331787,
|
| 348 |
+
"learning_rate": 3.164893617021277e-05,
|
| 349 |
+
"loss": 0.0244,
|
| 350 |
+
"step": 450
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.200956937799043,
|
| 354 |
+
"grad_norm": 5.872335433959961,
|
| 355 |
+
"learning_rate": 3.111702127659575e-05,
|
| 356 |
+
"loss": 0.0235,
|
| 357 |
+
"step": 460
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.248803827751196,
|
| 361 |
+
"grad_norm": 2.8920586109161377,
|
| 362 |
+
"learning_rate": 3.0585106382978726e-05,
|
| 363 |
+
"loss": 0.0495,
|
| 364 |
+
"step": 470
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.2966507177033493,
|
| 368 |
+
"grad_norm": 2.471548080444336,
|
| 369 |
+
"learning_rate": 3.0053191489361706e-05,
|
| 370 |
+
"loss": 0.0339,
|
| 371 |
+
"step": 480
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.3444976076555024,
|
| 375 |
+
"grad_norm": 4.543760776519775,
|
| 376 |
+
"learning_rate": 2.9521276595744685e-05,
|
| 377 |
+
"loss": 0.035,
|
| 378 |
+
"step": 490
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.3923444976076556,
|
| 382 |
+
"grad_norm": 1.5639833211898804,
|
| 383 |
+
"learning_rate": 2.898936170212766e-05,
|
| 384 |
+
"loss": 0.0316,
|
| 385 |
+
"step": 500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.4401913875598087,
|
| 389 |
+
"grad_norm": 1.6251667737960815,
|
| 390 |
+
"learning_rate": 2.845744680851064e-05,
|
| 391 |
+
"loss": 0.0376,
|
| 392 |
+
"step": 510
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.488038277511962,
|
| 396 |
+
"grad_norm": 2.550877809524536,
|
| 397 |
+
"learning_rate": 2.7925531914893616e-05,
|
| 398 |
+
"loss": 0.0229,
|
| 399 |
+
"step": 520
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.535885167464115,
|
| 403 |
+
"grad_norm": 1.3332566022872925,
|
| 404 |
+
"learning_rate": 2.7393617021276595e-05,
|
| 405 |
+
"loss": 0.0241,
|
| 406 |
+
"step": 530
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.583732057416268,
|
| 410 |
+
"grad_norm": 0.9760203957557678,
|
| 411 |
+
"learning_rate": 2.6861702127659577e-05,
|
| 412 |
+
"loss": 0.023,
|
| 413 |
+
"step": 540
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.6315789473684212,
|
| 417 |
+
"grad_norm": 1.0983035564422607,
|
| 418 |
+
"learning_rate": 2.6329787234042553e-05,
|
| 419 |
+
"loss": 0.0187,
|
| 420 |
+
"step": 550
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.679425837320574,
|
| 424 |
+
"grad_norm": 0.8970646262168884,
|
| 425 |
+
"learning_rate": 2.5797872340425532e-05,
|
| 426 |
+
"loss": 0.0288,
|
| 427 |
+
"step": 560
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.7272727272727275,
|
| 431 |
+
"grad_norm": 3.670253038406372,
|
| 432 |
+
"learning_rate": 2.5265957446808515e-05,
|
| 433 |
+
"loss": 0.0125,
|
| 434 |
+
"step": 570
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.77511961722488,
|
| 438 |
+
"grad_norm": 2.996281623840332,
|
| 439 |
+
"learning_rate": 2.473404255319149e-05,
|
| 440 |
+
"loss": 0.0218,
|
| 441 |
+
"step": 580
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.8229665071770333,
|
| 445 |
+
"grad_norm": 0.5742462873458862,
|
| 446 |
+
"learning_rate": 2.420212765957447e-05,
|
| 447 |
+
"loss": 0.0184,
|
| 448 |
+
"step": 590
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.8708133971291865,
|
| 452 |
+
"grad_norm": 1.122542381286621,
|
| 453 |
+
"learning_rate": 2.3670212765957446e-05,
|
| 454 |
+
"loss": 0.0196,
|
| 455 |
+
"step": 600
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.9186602870813396,
|
| 459 |
+
"grad_norm": 1.6919171810150146,
|
| 460 |
+
"learning_rate": 2.3138297872340425e-05,
|
| 461 |
+
"loss": 0.0328,
|
| 462 |
+
"step": 610
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.9665071770334928,
|
| 466 |
+
"grad_norm": 1.0849560499191284,
|
| 467 |
+
"learning_rate": 2.2606382978723408e-05,
|
| 468 |
+
"loss": 0.0176,
|
| 469 |
+
"step": 620
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 3.0,
|
| 473 |
+
"eval_explained_variance": 0.7042545080184937,
|
| 474 |
+
"eval_loss": 0.025607816874980927,
|
| 475 |
+
"eval_mae": 0.11611536890268326,
|
| 476 |
+
"eval_mse": 0.025607818737626076,
|
| 477 |
+
"eval_r2": 0.7023023962974548,
|
| 478 |
+
"eval_rmse": 0.16002443168974567,
|
| 479 |
+
"eval_runtime": 0.5099,
|
| 480 |
+
"eval_samples_per_second": 819.73,
|
| 481 |
+
"eval_steps_per_second": 52.949,
|
| 482 |
+
"step": 627
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.014354066985646,
|
| 486 |
+
"grad_norm": 2.3343703746795654,
|
| 487 |
+
"learning_rate": 2.2074468085106383e-05,
|
| 488 |
+
"loss": 0.0181,
|
| 489 |
+
"step": 630
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.062200956937799,
|
| 493 |
+
"grad_norm": 1.1856133937835693,
|
| 494 |
+
"learning_rate": 2.1542553191489363e-05,
|
| 495 |
+
"loss": 0.017,
|
| 496 |
+
"step": 640
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 3.110047846889952,
|
| 500 |
+
"grad_norm": 1.4654027223587036,
|
| 501 |
+
"learning_rate": 2.1010638297872342e-05,
|
| 502 |
+
"loss": 0.0152,
|
| 503 |
+
"step": 650
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 3.1578947368421053,
|
| 507 |
+
"grad_norm": 2.233487606048584,
|
| 508 |
+
"learning_rate": 2.047872340425532e-05,
|
| 509 |
+
"loss": 0.014,
|
| 510 |
+
"step": 660
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.2057416267942584,
|
| 514 |
+
"grad_norm": 2.7898600101470947,
|
| 515 |
+
"learning_rate": 1.9946808510638297e-05,
|
| 516 |
+
"loss": 0.0162,
|
| 517 |
+
"step": 670
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 3.2535885167464116,
|
| 521 |
+
"grad_norm": 1.0753400325775146,
|
| 522 |
+
"learning_rate": 1.9414893617021276e-05,
|
| 523 |
+
"loss": 0.0111,
|
| 524 |
+
"step": 680
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.3014354066985647,
|
| 528 |
+
"grad_norm": 0.6512526869773865,
|
| 529 |
+
"learning_rate": 1.888297872340426e-05,
|
| 530 |
+
"loss": 0.0138,
|
| 531 |
+
"step": 690
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.349282296650718,
|
| 535 |
+
"grad_norm": 0.4936651587486267,
|
| 536 |
+
"learning_rate": 1.8351063829787234e-05,
|
| 537 |
+
"loss": 0.0164,
|
| 538 |
+
"step": 700
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 3.397129186602871,
|
| 542 |
+
"grad_norm": 1.5646798610687256,
|
| 543 |
+
"learning_rate": 1.7819148936170214e-05,
|
| 544 |
+
"loss": 0.0176,
|
| 545 |
+
"step": 710
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 3.444976076555024,
|
| 549 |
+
"grad_norm": 0.7278246283531189,
|
| 550 |
+
"learning_rate": 1.7287234042553193e-05,
|
| 551 |
+
"loss": 0.0138,
|
| 552 |
+
"step": 720
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 3.492822966507177,
|
| 556 |
+
"grad_norm": 0.5005846619606018,
|
| 557 |
+
"learning_rate": 1.6755319148936172e-05,
|
| 558 |
+
"loss": 0.0107,
|
| 559 |
+
"step": 730
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 3.5406698564593304,
|
| 563 |
+
"grad_norm": 1.2038078308105469,
|
| 564 |
+
"learning_rate": 1.6223404255319148e-05,
|
| 565 |
+
"loss": 0.0135,
|
| 566 |
+
"step": 740
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.588516746411483,
|
| 570 |
+
"grad_norm": 1.4103667736053467,
|
| 571 |
+
"learning_rate": 1.5691489361702127e-05,
|
| 572 |
+
"loss": 0.0171,
|
| 573 |
+
"step": 750
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.6363636363636362,
|
| 577 |
+
"grad_norm": 3.186798095703125,
|
| 578 |
+
"learning_rate": 1.5159574468085108e-05,
|
| 579 |
+
"loss": 0.0148,
|
| 580 |
+
"step": 760
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 3.6842105263157894,
|
| 584 |
+
"grad_norm": 1.5543982982635498,
|
| 585 |
+
"learning_rate": 1.4627659574468085e-05,
|
| 586 |
+
"loss": 0.0214,
|
| 587 |
+
"step": 770
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 3.7320574162679425,
|
| 591 |
+
"grad_norm": 0.5485432744026184,
|
| 592 |
+
"learning_rate": 1.4095744680851065e-05,
|
| 593 |
+
"loss": 0.0132,
|
| 594 |
+
"step": 780
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 3.7799043062200957,
|
| 598 |
+
"grad_norm": 2.0616867542266846,
|
| 599 |
+
"learning_rate": 1.3563829787234042e-05,
|
| 600 |
+
"loss": 0.0158,
|
| 601 |
+
"step": 790
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 3.827751196172249,
|
| 605 |
+
"grad_norm": 0.35062626004219055,
|
| 606 |
+
"learning_rate": 1.3031914893617023e-05,
|
| 607 |
+
"loss": 0.0086,
|
| 608 |
+
"step": 800
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.875598086124402,
|
| 612 |
+
"grad_norm": 1.0128910541534424,
|
| 613 |
+
"learning_rate": 1.25e-05,
|
| 614 |
+
"loss": 0.0163,
|
| 615 |
+
"step": 810
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.923444976076555,
|
| 619 |
+
"grad_norm": 1.6581486463546753,
|
| 620 |
+
"learning_rate": 1.196808510638298e-05,
|
| 621 |
+
"loss": 0.0143,
|
| 622 |
+
"step": 820
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 3.971291866028708,
|
| 626 |
+
"grad_norm": 1.5640918016433716,
|
| 627 |
+
"learning_rate": 1.1436170212765957e-05,
|
| 628 |
+
"loss": 0.0119,
|
| 629 |
+
"step": 830
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 4.0,
|
| 633 |
+
"eval_explained_variance": 0.7581204175949097,
|
| 634 |
+
"eval_loss": 0.02080734819173813,
|
| 635 |
+
"eval_mae": 0.09978120028972626,
|
| 636 |
+
"eval_mse": 0.02080734819173813,
|
| 637 |
+
"eval_r2": 0.7581090927124023,
|
| 638 |
+
"eval_rmse": 0.14424752404023483,
|
| 639 |
+
"eval_runtime": 0.5099,
|
| 640 |
+
"eval_samples_per_second": 819.705,
|
| 641 |
+
"eval_steps_per_second": 52.947,
|
| 642 |
+
"step": 836
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 4.019138755980861,
|
| 646 |
+
"grad_norm": 0.42241960763931274,
|
| 647 |
+
"learning_rate": 1.0904255319148937e-05,
|
| 648 |
+
"loss": 0.0088,
|
| 649 |
+
"step": 840
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 4.0669856459330145,
|
| 653 |
+
"grad_norm": 0.7787032127380371,
|
| 654 |
+
"learning_rate": 1.0372340425531916e-05,
|
| 655 |
+
"loss": 0.0061,
|
| 656 |
+
"step": 850
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 4.114832535885167,
|
| 660 |
+
"grad_norm": 0.774537980556488,
|
| 661 |
+
"learning_rate": 9.840425531914895e-06,
|
| 662 |
+
"loss": 0.008,
|
| 663 |
+
"step": 860
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 4.162679425837321,
|
| 667 |
+
"grad_norm": 0.9715988636016846,
|
| 668 |
+
"learning_rate": 9.308510638297872e-06,
|
| 669 |
+
"loss": 0.0094,
|
| 670 |
+
"step": 870
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 4.2105263157894735,
|
| 674 |
+
"grad_norm": 0.9758203029632568,
|
| 675 |
+
"learning_rate": 8.776595744680852e-06,
|
| 676 |
+
"loss": 0.0102,
|
| 677 |
+
"step": 880
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 4.258373205741627,
|
| 681 |
+
"grad_norm": 1.2616456747055054,
|
| 682 |
+
"learning_rate": 8.244680851063829e-06,
|
| 683 |
+
"loss": 0.0105,
|
| 684 |
+
"step": 890
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 4.30622009569378,
|
| 688 |
+
"grad_norm": 2.5576059818267822,
|
| 689 |
+
"learning_rate": 7.712765957446808e-06,
|
| 690 |
+
"loss": 0.0119,
|
| 691 |
+
"step": 900
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 4.354066985645933,
|
| 695 |
+
"grad_norm": 1.0013601779937744,
|
| 696 |
+
"learning_rate": 7.180851063829788e-06,
|
| 697 |
+
"loss": 0.0093,
|
| 698 |
+
"step": 910
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 4.401913875598086,
|
| 702 |
+
"grad_norm": 0.8951208591461182,
|
| 703 |
+
"learning_rate": 6.648936170212766e-06,
|
| 704 |
+
"loss": 0.0123,
|
| 705 |
+
"step": 920
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 4.44976076555024,
|
| 709 |
+
"grad_norm": 1.9875566959381104,
|
| 710 |
+
"learning_rate": 6.117021276595745e-06,
|
| 711 |
+
"loss": 0.0093,
|
| 712 |
+
"step": 930
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 4.497607655502392,
|
| 716 |
+
"grad_norm": 0.8690968155860901,
|
| 717 |
+
"learning_rate": 5.5851063829787235e-06,
|
| 718 |
+
"loss": 0.0101,
|
| 719 |
+
"step": 940
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 4.545454545454545,
|
| 723 |
+
"grad_norm": 1.086692452430725,
|
| 724 |
+
"learning_rate": 5.053191489361702e-06,
|
| 725 |
+
"loss": 0.0112,
|
| 726 |
+
"step": 950
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 4.5933014354066986,
|
| 730 |
+
"grad_norm": 0.5685741305351257,
|
| 731 |
+
"learning_rate": 4.521276595744681e-06,
|
| 732 |
+
"loss": 0.0084,
|
| 733 |
+
"step": 960
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 4.641148325358852,
|
| 737 |
+
"grad_norm": 0.4419994652271271,
|
| 738 |
+
"learning_rate": 3.98936170212766e-06,
|
| 739 |
+
"loss": 0.0055,
|
| 740 |
+
"step": 970
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.688995215311005,
|
| 744 |
+
"grad_norm": 0.5267429351806641,
|
| 745 |
+
"learning_rate": 3.4574468085106386e-06,
|
| 746 |
+
"loss": 0.0099,
|
| 747 |
+
"step": 980
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.7368421052631575,
|
| 751 |
+
"grad_norm": 0.5490550398826599,
|
| 752 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 753 |
+
"loss": 0.0082,
|
| 754 |
+
"step": 990
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 4.784688995215311,
|
| 758 |
+
"grad_norm": 0.45929694175720215,
|
| 759 |
+
"learning_rate": 2.3936170212765957e-06,
|
| 760 |
+
"loss": 0.0076,
|
| 761 |
+
"step": 1000
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 4.832535885167464,
|
| 765 |
+
"grad_norm": 1.4791394472122192,
|
| 766 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 767 |
+
"loss": 0.0096,
|
| 768 |
+
"step": 1010
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.880382775119617,
|
| 772 |
+
"grad_norm": 0.8548759818077087,
|
| 773 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 774 |
+
"loss": 0.008,
|
| 775 |
+
"step": 1020
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 4.92822966507177,
|
| 779 |
+
"grad_norm": 0.7836734652519226,
|
| 780 |
+
"learning_rate": 7.978723404255319e-07,
|
| 781 |
+
"loss": 0.0097,
|
| 782 |
+
"step": 1030
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 4.976076555023924,
|
| 786 |
+
"grad_norm": 0.6923006176948547,
|
| 787 |
+
"learning_rate": 2.6595744680851066e-07,
|
| 788 |
+
"loss": 0.0104,
|
| 789 |
+
"step": 1040
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 5.0,
|
| 793 |
+
"eval_explained_variance": 0.75990229845047,
|
| 794 |
+
"eval_loss": 0.02065342105925083,
|
| 795 |
+
"eval_mae": 0.09870430827140808,
|
| 796 |
+
"eval_mse": 0.02065342292189598,
|
| 797 |
+
"eval_r2": 0.7598985433578491,
|
| 798 |
+
"eval_rmse": 0.1437129880069856,
|
| 799 |
+
"eval_runtime": 0.5047,
|
| 800 |
+
"eval_samples_per_second": 828.293,
|
| 801 |
+
"eval_steps_per_second": 53.502,
|
| 802 |
+
"step": 1045
|
| 803 |
+
}
|
| 804 |
+
],
|
| 805 |
+
"logging_steps": 10,
|
| 806 |
+
"max_steps": 1045,
|
| 807 |
+
"num_input_tokens_seen": 0,
|
| 808 |
+
"num_train_epochs": 5,
|
| 809 |
+
"save_steps": 500,
|
| 810 |
+
"stateful_callbacks": {
|
| 811 |
+
"EarlyStoppingCallback": {
|
| 812 |
+
"args": {
|
| 813 |
+
"early_stopping_patience": 5,
|
| 814 |
+
"early_stopping_threshold": 0.01
|
| 815 |
+
},
|
| 816 |
+
"attributes": {
|
| 817 |
+
"early_stopping_patience_counter": 3
|
| 818 |
+
}
|
| 819 |
+
},
|
| 820 |
+
"TrainerControl": {
|
| 821 |
+
"args": {
|
| 822 |
+
"should_epoch_stop": false,
|
| 823 |
+
"should_evaluate": false,
|
| 824 |
+
"should_log": false,
|
| 825 |
+
"should_save": true,
|
| 826 |
+
"should_training_stop": true
|
| 827 |
+
},
|
| 828 |
+
"attributes": {}
|
| 829 |
+
}
|
| 830 |
+
},
|
| 831 |
+
"total_flos": 549897168353280.0,
|
| 832 |
+
"train_batch_size": 8,
|
| 833 |
+
"trial_name": null,
|
| 834 |
+
"trial_params": null
|
| 835 |
+
}
|
checkpoint-1045/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91353a18a2d22b839f966426e70f6b19aace99612251431544efeecb4f8a5e0a
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-german-cased",
|
| 3 |
+
"_num_labels": 1,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "target"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"target": 0
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "bert",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "regression",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.48.0",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 30000
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a615ce45903fcbfba3015b559a405c6ea281d73bfe314d9cf53f775f7e59a477
|
| 3 |
+
size 436351980
|
runs/Feb21_00-15-38_r-abgegrieft-train-bert-toxic-2-ylkx2gqa-afc62-whkno/events.out.tfevents.1740096940.r-abgegrieft-train-bert-toxic-2-ylkx2gqa-afc62-whkno.218.0
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 sha256:2ddcd6b52d36b1bdb8a5a9e01756847d002d632ef77a2937804ff87817ddfb9d
|
| 3 |
+
size 30018
|
runs/Feb21_00-15-38_r-abgegrieft-train-bert-toxic-2-ylkx2gqa-afc62-whkno/events.out.tfevents.1740097011.r-abgegrieft-train-bert-toxic-2-ylkx2gqa-afc62-whkno.218.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fe7ba999e7485680ecda97e7c0b1b699975bfca80934ac442e5ba8b7a8af439
|
| 3 |
+
size 609
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"2": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"3": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"4": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"5": {
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91353a18a2d22b839f966426e70f6b19aace99612251431544efeecb4f8a5e0a
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-qiyqv-nm11e/autotrain-data",
|
| 3 |
+
"model": "google-bert/bert-base-german-cased",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 5,
|
| 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": "autotrain-qiyqv-nm11e",
|
| 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": "Abgegrieft",
|
| 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
|
|
|