Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-5038/config.json +37 -0
- checkpoint-5038/model.safetensors +3 -0
- checkpoint-5038/optimizer.pt +3 -0
- checkpoint-5038/rng_state.pth +3 -0
- checkpoint-5038/scheduler.pt +3 -0
- checkpoint-5038/trainer_state.json +1485 -0
- checkpoint-5038/training_args.bin +3 -0
- config.json +37 -0
- model.safetensors +3 -0
- runs/Feb22_14-48-55_r-abgegrieft-autotrain-toxicity-metrics-gaming-commun-7b502-vaz/events.out.tfevents.1740235736.r-abgegrieft-autotrain-toxicity-metrics-gaming-commun-7b502-vaz.203.0 +2 -2
- runs/Feb22_14-48-55_r-abgegrieft-autotrain-toxicity-metrics-gaming-commun-7b502-vaz/events.out.tfevents.1740236715.r-abgegrieft-autotrain-toxicity-metrics-gaming-commun-7b502-vaz.203.1 +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 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- autotrain
|
| 6 |
+
- text-classification
|
| 7 |
+
base_model: google-bert/bert-base-german-cased
|
| 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: 0.17345599830150604
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.7547155454831698
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.9466019417475728
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.9445123807456527
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.8558757528469544
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.9466019417475728
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.9434254644943053
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.6923009042209939
|
| 32 |
+
|
| 33 |
+
recall_micro: 0.9466019417475728
|
| 34 |
+
|
| 35 |
+
recall_weighted: 0.9466019417475728
|
| 36 |
+
|
| 37 |
+
accuracy: 0.9466019417475728
|
checkpoint-5038/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-german-cased",
|
| 3 |
+
"_num_labels": 3,
|
| 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": "0",
|
| 14 |
+
"1": "1",
|
| 15 |
+
"2": "2"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"0": 0,
|
| 21 |
+
"1": 1,
|
| 22 |
+
"2": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.48.0",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 30000
|
| 37 |
+
}
|
checkpoint-5038/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ccd26129a7d60735027dec86b2e6b5aff223c7c9e50d7af7b276ce92b6350db
|
| 3 |
+
size 436358132
|
checkpoint-5038/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d3f1cc1e4f37c4ce27a313c91a5263fcf51d0adee1130bd83588a47803bfdf4
|
| 3 |
+
size 872837370
|
checkpoint-5038/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0bcb35706c487ff1c57757bc3bc703428241ccde1c3397f2d050ec33e0c2691
|
| 3 |
+
size 14244
|
checkpoint-5038/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09b2f3626f19e4525d067ddb2d71f5f10aead641d623e888b7f0874463e2f942
|
| 3 |
+
size 1064
|
checkpoint-5038/trainer_state.json
ADDED
|
@@ -0,0 +1,1485 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.17345599830150604,
|
| 3 |
+
"best_model_checkpoint": "autotrain-sijfl-oha9f/checkpoint-5038",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5038,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.009924573243350537,
|
| 13 |
+
"grad_norm": 5.93813419342041,
|
| 14 |
+
"learning_rate": 4.134965266291763e-07,
|
| 15 |
+
"loss": 1.0039,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.019849146486701073,
|
| 20 |
+
"grad_norm": 8.647444725036621,
|
| 21 |
+
"learning_rate": 8.269930532583527e-07,
|
| 22 |
+
"loss": 0.9813,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.029773719730051607,
|
| 27 |
+
"grad_norm": 8.7538480758667,
|
| 28 |
+
"learning_rate": 1.240489579887529e-06,
|
| 29 |
+
"loss": 0.955,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03969829297340215,
|
| 34 |
+
"grad_norm": 7.720163345336914,
|
| 35 |
+
"learning_rate": 1.6539861065167053e-06,
|
| 36 |
+
"loss": 0.8668,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04962286621675268,
|
| 41 |
+
"grad_norm": 4.838120937347412,
|
| 42 |
+
"learning_rate": 2.0674826331458816e-06,
|
| 43 |
+
"loss": 0.7694,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05954743946010321,
|
| 48 |
+
"grad_norm": 6.743594169616699,
|
| 49 |
+
"learning_rate": 2.480979159775058e-06,
|
| 50 |
+
"loss": 0.7645,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06947201270345375,
|
| 55 |
+
"grad_norm": 6.740540981292725,
|
| 56 |
+
"learning_rate": 2.8944756864042343e-06,
|
| 57 |
+
"loss": 0.7535,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0793965859468043,
|
| 62 |
+
"grad_norm": 5.810417175292969,
|
| 63 |
+
"learning_rate": 3.3079722130334106e-06,
|
| 64 |
+
"loss": 0.7872,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.08932115919015482,
|
| 69 |
+
"grad_norm": 5.639619827270508,
|
| 70 |
+
"learning_rate": 3.721468739662587e-06,
|
| 71 |
+
"loss": 0.7694,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.09924573243350536,
|
| 76 |
+
"grad_norm": 5.817326545715332,
|
| 77 |
+
"learning_rate": 4.134965266291763e-06,
|
| 78 |
+
"loss": 0.7925,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1091703056768559,
|
| 83 |
+
"grad_norm": 6.872006893157959,
|
| 84 |
+
"learning_rate": 4.54846179292094e-06,
|
| 85 |
+
"loss": 0.7176,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.11909487892020643,
|
| 90 |
+
"grad_norm": 6.990772247314453,
|
| 91 |
+
"learning_rate": 4.961958319550116e-06,
|
| 92 |
+
"loss": 0.7017,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.12901945216355698,
|
| 97 |
+
"grad_norm": 6.264073371887207,
|
| 98 |
+
"learning_rate": 5.375454846179293e-06,
|
| 99 |
+
"loss": 0.6863,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1389440254069075,
|
| 104 |
+
"grad_norm": 6.337187767028809,
|
| 105 |
+
"learning_rate": 5.7889513728084686e-06,
|
| 106 |
+
"loss": 0.5896,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.14886859865025803,
|
| 111 |
+
"grad_norm": 17.048295974731445,
|
| 112 |
+
"learning_rate": 6.202447899437645e-06,
|
| 113 |
+
"loss": 0.5539,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1587931718936086,
|
| 118 |
+
"grad_norm": 10.304464340209961,
|
| 119 |
+
"learning_rate": 6.615944426066821e-06,
|
| 120 |
+
"loss": 0.6003,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1687177451369591,
|
| 125 |
+
"grad_norm": 19.685894012451172,
|
| 126 |
+
"learning_rate": 7.01290109163083e-06,
|
| 127 |
+
"loss": 0.6034,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.17864231838030964,
|
| 132 |
+
"grad_norm": 16.452545166015625,
|
| 133 |
+
"learning_rate": 7.426397618260007e-06,
|
| 134 |
+
"loss": 0.4894,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1885668916236602,
|
| 139 |
+
"grad_norm": 11.992972373962402,
|
| 140 |
+
"learning_rate": 7.839894144889183e-06,
|
| 141 |
+
"loss": 0.5801,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.19849146486701072,
|
| 146 |
+
"grad_norm": 20.56760025024414,
|
| 147 |
+
"learning_rate": 8.25339067151836e-06,
|
| 148 |
+
"loss": 0.4932,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.20841603811036125,
|
| 153 |
+
"grad_norm": 10.028135299682617,
|
| 154 |
+
"learning_rate": 8.666887198147537e-06,
|
| 155 |
+
"loss": 0.5882,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2183406113537118,
|
| 160 |
+
"grad_norm": 7.362673759460449,
|
| 161 |
+
"learning_rate": 9.080383724776713e-06,
|
| 162 |
+
"loss": 0.5991,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.22826518459706233,
|
| 167 |
+
"grad_norm": 5.525132179260254,
|
| 168 |
+
"learning_rate": 9.493880251405888e-06,
|
| 169 |
+
"loss": 0.4996,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.23818975784041285,
|
| 174 |
+
"grad_norm": 12.994559288024902,
|
| 175 |
+
"learning_rate": 9.907376778035065e-06,
|
| 176 |
+
"loss": 0.4295,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2481143310837634,
|
| 181 |
+
"grad_norm": 15.270442962646484,
|
| 182 |
+
"learning_rate": 1.0320873304664242e-05,
|
| 183 |
+
"loss": 0.5293,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.25803890432711396,
|
| 188 |
+
"grad_norm": 18.805465698242188,
|
| 189 |
+
"learning_rate": 1.0734369831293417e-05,
|
| 190 |
+
"loss": 0.4672,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.26796347757046446,
|
| 195 |
+
"grad_norm": 19.39354133605957,
|
| 196 |
+
"learning_rate": 1.1147866357922594e-05,
|
| 197 |
+
"loss": 0.5318,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.277888050813815,
|
| 202 |
+
"grad_norm": 13.161215782165527,
|
| 203 |
+
"learning_rate": 1.156136288455177e-05,
|
| 204 |
+
"loss": 0.5709,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.28781262405716557,
|
| 209 |
+
"grad_norm": 21.857101440429688,
|
| 210 |
+
"learning_rate": 1.1974859411180947e-05,
|
| 211 |
+
"loss": 0.5283,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.29773719730051607,
|
| 216 |
+
"grad_norm": 11.16152572631836,
|
| 217 |
+
"learning_rate": 1.2388355937810122e-05,
|
| 218 |
+
"loss": 0.4739,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3076617705438666,
|
| 223 |
+
"grad_norm": 24.86366081237793,
|
| 224 |
+
"learning_rate": 1.2801852464439299e-05,
|
| 225 |
+
"loss": 0.4864,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3175863437872172,
|
| 230 |
+
"grad_norm": 10.467317581176758,
|
| 231 |
+
"learning_rate": 1.3215348991068477e-05,
|
| 232 |
+
"loss": 0.4986,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.32751091703056767,
|
| 237 |
+
"grad_norm": 7.949365139007568,
|
| 238 |
+
"learning_rate": 1.3628845517697652e-05,
|
| 239 |
+
"loss": 0.406,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3374354902739182,
|
| 244 |
+
"grad_norm": 16.433610916137695,
|
| 245 |
+
"learning_rate": 1.4042342044326828e-05,
|
| 246 |
+
"loss": 0.4383,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3473600635172688,
|
| 251 |
+
"grad_norm": 10.170207023620605,
|
| 252 |
+
"learning_rate": 1.4455838570956004e-05,
|
| 253 |
+
"loss": 0.4705,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.3572846367606193,
|
| 258 |
+
"grad_norm": 10.97195053100586,
|
| 259 |
+
"learning_rate": 1.486933509758518e-05,
|
| 260 |
+
"loss": 0.4991,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.36720921000396983,
|
| 265 |
+
"grad_norm": 11.719902038574219,
|
| 266 |
+
"learning_rate": 1.5282831624214358e-05,
|
| 267 |
+
"loss": 0.5579,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.3771337832473204,
|
| 272 |
+
"grad_norm": 15.124497413635254,
|
| 273 |
+
"learning_rate": 1.5696328150843535e-05,
|
| 274 |
+
"loss": 0.4242,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3870583564906709,
|
| 279 |
+
"grad_norm": 24.049497604370117,
|
| 280 |
+
"learning_rate": 1.610982467747271e-05,
|
| 281 |
+
"loss": 0.4794,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.39698292973402144,
|
| 286 |
+
"grad_norm": 8.881915092468262,
|
| 287 |
+
"learning_rate": 1.6523321204101885e-05,
|
| 288 |
+
"loss": 0.4922,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.406907502977372,
|
| 293 |
+
"grad_norm": 16.32332420349121,
|
| 294 |
+
"learning_rate": 1.6936817730731065e-05,
|
| 295 |
+
"loss": 0.459,
|
| 296 |
+
"step": 1025
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4168320762207225,
|
| 300 |
+
"grad_norm": 15.874964714050293,
|
| 301 |
+
"learning_rate": 1.7350314257360238e-05,
|
| 302 |
+
"loss": 0.5216,
|
| 303 |
+
"step": 1050
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.42675664946407305,
|
| 307 |
+
"grad_norm": 21.42139434814453,
|
| 308 |
+
"learning_rate": 1.7763810783989415e-05,
|
| 309 |
+
"loss": 0.4758,
|
| 310 |
+
"step": 1075
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4366812227074236,
|
| 314 |
+
"grad_norm": 18.064491271972656,
|
| 315 |
+
"learning_rate": 1.817730731061859e-05,
|
| 316 |
+
"loss": 0.5,
|
| 317 |
+
"step": 1100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.4466057959507741,
|
| 321 |
+
"grad_norm": 9.698043823242188,
|
| 322 |
+
"learning_rate": 1.8590803837247765e-05,
|
| 323 |
+
"loss": 0.4933,
|
| 324 |
+
"step": 1125
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.45653036919412465,
|
| 328 |
+
"grad_norm": 7.853238105773926,
|
| 329 |
+
"learning_rate": 1.9004300363876945e-05,
|
| 330 |
+
"loss": 0.5082,
|
| 331 |
+
"step": 1150
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.4664549424374752,
|
| 335 |
+
"grad_norm": 5.968617916107178,
|
| 336 |
+
"learning_rate": 1.9417796890506122e-05,
|
| 337 |
+
"loss": 0.4475,
|
| 338 |
+
"step": 1175
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4763795156808257,
|
| 342 |
+
"grad_norm": 10.401561737060547,
|
| 343 |
+
"learning_rate": 1.9831293417135295e-05,
|
| 344 |
+
"loss": 0.414,
|
| 345 |
+
"step": 1200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.48630408892417626,
|
| 349 |
+
"grad_norm": 11.741177558898926,
|
| 350 |
+
"learning_rate": 2.0244789943764472e-05,
|
| 351 |
+
"loss": 0.4179,
|
| 352 |
+
"step": 1225
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.4962286621675268,
|
| 356 |
+
"grad_norm": 12.610602378845215,
|
| 357 |
+
"learning_rate": 2.0658286470393652e-05,
|
| 358 |
+
"loss": 0.5205,
|
| 359 |
+
"step": 1250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5061532354108773,
|
| 363 |
+
"grad_norm": 4.400837421417236,
|
| 364 |
+
"learning_rate": 2.1071782997022825e-05,
|
| 365 |
+
"loss": 0.3738,
|
| 366 |
+
"step": 1275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5160778086542279,
|
| 370 |
+
"grad_norm": 16.984041213989258,
|
| 371 |
+
"learning_rate": 2.1468739662586834e-05,
|
| 372 |
+
"loss": 0.4891,
|
| 373 |
+
"step": 1300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5260023818975784,
|
| 377 |
+
"grad_norm": 7.929263114929199,
|
| 378 |
+
"learning_rate": 2.1882236189216014e-05,
|
| 379 |
+
"loss": 0.4795,
|
| 380 |
+
"step": 1325
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5359269551409289,
|
| 384 |
+
"grad_norm": 16.580184936523438,
|
| 385 |
+
"learning_rate": 2.2295732715845187e-05,
|
| 386 |
+
"loss": 0.5033,
|
| 387 |
+
"step": 1350
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.5458515283842795,
|
| 391 |
+
"grad_norm": 12.853453636169434,
|
| 392 |
+
"learning_rate": 2.2709229242474364e-05,
|
| 393 |
+
"loss": 0.4629,
|
| 394 |
+
"step": 1375
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.55577610162763,
|
| 398 |
+
"grad_norm": 39.99103927612305,
|
| 399 |
+
"learning_rate": 2.312272576910354e-05,
|
| 400 |
+
"loss": 0.4954,
|
| 401 |
+
"step": 1400
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5657006748709805,
|
| 405 |
+
"grad_norm": 16.01141929626465,
|
| 406 |
+
"learning_rate": 2.3536222295732718e-05,
|
| 407 |
+
"loss": 0.4326,
|
| 408 |
+
"step": 1425
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.5756252481143311,
|
| 412 |
+
"grad_norm": 9.876302719116211,
|
| 413 |
+
"learning_rate": 2.3949718822361894e-05,
|
| 414 |
+
"loss": 0.4007,
|
| 415 |
+
"step": 1450
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5855498213576816,
|
| 419 |
+
"grad_norm": 22.113252639770508,
|
| 420 |
+
"learning_rate": 2.436321534899107e-05,
|
| 421 |
+
"loss": 0.4397,
|
| 422 |
+
"step": 1475
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.5954743946010321,
|
| 426 |
+
"grad_norm": 10.05559253692627,
|
| 427 |
+
"learning_rate": 2.4776711875620244e-05,
|
| 428 |
+
"loss": 0.5327,
|
| 429 |
+
"step": 1500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6053989678443827,
|
| 433 |
+
"grad_norm": 9.979157447814941,
|
| 434 |
+
"learning_rate": 2.519020840224942e-05,
|
| 435 |
+
"loss": 0.4146,
|
| 436 |
+
"step": 1525
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6153235410877332,
|
| 440 |
+
"grad_norm": 32.12015914916992,
|
| 441 |
+
"learning_rate": 2.5603704928878598e-05,
|
| 442 |
+
"loss": 0.3866,
|
| 443 |
+
"step": 1550
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6252481143310837,
|
| 447 |
+
"grad_norm": 5.876375198364258,
|
| 448 |
+
"learning_rate": 2.601720145550777e-05,
|
| 449 |
+
"loss": 0.4595,
|
| 450 |
+
"step": 1575
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6351726875744343,
|
| 454 |
+
"grad_norm": 12.026578903198242,
|
| 455 |
+
"learning_rate": 2.6430697982136955e-05,
|
| 456 |
+
"loss": 0.5323,
|
| 457 |
+
"step": 1600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.6450972608177848,
|
| 461 |
+
"grad_norm": 8.49512004852295,
|
| 462 |
+
"learning_rate": 2.6844194508766128e-05,
|
| 463 |
+
"loss": 0.393,
|
| 464 |
+
"step": 1625
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.6550218340611353,
|
| 468 |
+
"grad_norm": 22.53009796142578,
|
| 469 |
+
"learning_rate": 2.7257691035395305e-05,
|
| 470 |
+
"loss": 0.4501,
|
| 471 |
+
"step": 1650
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.664946407304486,
|
| 475 |
+
"grad_norm": 14.742464065551758,
|
| 476 |
+
"learning_rate": 2.767118756202448e-05,
|
| 477 |
+
"loss": 0.4946,
|
| 478 |
+
"step": 1675
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6748709805478365,
|
| 482 |
+
"grad_norm": 24.389440536499023,
|
| 483 |
+
"learning_rate": 2.8084684088653655e-05,
|
| 484 |
+
"loss": 0.3291,
|
| 485 |
+
"step": 1700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.684795553791187,
|
| 489 |
+
"grad_norm": 16.26449203491211,
|
| 490 |
+
"learning_rate": 2.8498180615282832e-05,
|
| 491 |
+
"loss": 0.5362,
|
| 492 |
+
"step": 1725
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.6947201270345376,
|
| 496 |
+
"grad_norm": 12.046720504760742,
|
| 497 |
+
"learning_rate": 2.891167714191201e-05,
|
| 498 |
+
"loss": 0.4655,
|
| 499 |
+
"step": 1750
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7046447002778881,
|
| 503 |
+
"grad_norm": 10.891408920288086,
|
| 504 |
+
"learning_rate": 2.9325173668541185e-05,
|
| 505 |
+
"loss": 0.4285,
|
| 506 |
+
"step": 1775
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7145692735212386,
|
| 510 |
+
"grad_norm": 15.83961009979248,
|
| 511 |
+
"learning_rate": 2.973867019517036e-05,
|
| 512 |
+
"loss": 0.4963,
|
| 513 |
+
"step": 1800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.7244938467645892,
|
| 517 |
+
"grad_norm": 10.055000305175781,
|
| 518 |
+
"learning_rate": 3.0152166721799542e-05,
|
| 519 |
+
"loss": 0.4438,
|
| 520 |
+
"step": 1825
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.7344184200079397,
|
| 524 |
+
"grad_norm": 9.60144329071045,
|
| 525 |
+
"learning_rate": 3.0565663248428716e-05,
|
| 526 |
+
"loss": 0.4599,
|
| 527 |
+
"step": 1850
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.7443429932512902,
|
| 531 |
+
"grad_norm": 13.515684127807617,
|
| 532 |
+
"learning_rate": 3.097915977505789e-05,
|
| 533 |
+
"loss": 0.53,
|
| 534 |
+
"step": 1875
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.7542675664946408,
|
| 538 |
+
"grad_norm": 9.59221363067627,
|
| 539 |
+
"learning_rate": 3.139265630168707e-05,
|
| 540 |
+
"loss": 0.4791,
|
| 541 |
+
"step": 1900
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.7641921397379913,
|
| 545 |
+
"grad_norm": 7.251306533813477,
|
| 546 |
+
"learning_rate": 3.1806152828316246e-05,
|
| 547 |
+
"loss": 0.4965,
|
| 548 |
+
"step": 1925
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.7741167129813418,
|
| 552 |
+
"grad_norm": 2.7141122817993164,
|
| 553 |
+
"learning_rate": 3.221964935494542e-05,
|
| 554 |
+
"loss": 0.4208,
|
| 555 |
+
"step": 1950
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7840412862246924,
|
| 559 |
+
"grad_norm": 1.079784631729126,
|
| 560 |
+
"learning_rate": 3.263314588157459e-05,
|
| 561 |
+
"loss": 0.4497,
|
| 562 |
+
"step": 1975
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7939658594680429,
|
| 566 |
+
"grad_norm": 8.680668830871582,
|
| 567 |
+
"learning_rate": 3.304664240820377e-05,
|
| 568 |
+
"loss": 0.3571,
|
| 569 |
+
"step": 2000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8038904327113934,
|
| 573 |
+
"grad_norm": 10.005072593688965,
|
| 574 |
+
"learning_rate": 3.3460138934832946e-05,
|
| 575 |
+
"loss": 0.4379,
|
| 576 |
+
"step": 2025
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.813815005954744,
|
| 580 |
+
"grad_norm": 11.514097213745117,
|
| 581 |
+
"learning_rate": 3.387363546146213e-05,
|
| 582 |
+
"loss": 0.474,
|
| 583 |
+
"step": 2050
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8237395791980945,
|
| 587 |
+
"grad_norm": 11.449129104614258,
|
| 588 |
+
"learning_rate": 3.4287131988091306e-05,
|
| 589 |
+
"loss": 0.4101,
|
| 590 |
+
"step": 2075
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.833664152441445,
|
| 594 |
+
"grad_norm": 0.43255844712257385,
|
| 595 |
+
"learning_rate": 3.4700628514720476e-05,
|
| 596 |
+
"loss": 0.3816,
|
| 597 |
+
"step": 2100
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.8435887256847956,
|
| 601 |
+
"grad_norm": 11.61715030670166,
|
| 602 |
+
"learning_rate": 3.511412504134965e-05,
|
| 603 |
+
"loss": 0.5017,
|
| 604 |
+
"step": 2125
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.8535132989281461,
|
| 608 |
+
"grad_norm": 3.4346067905426025,
|
| 609 |
+
"learning_rate": 3.552762156797883e-05,
|
| 610 |
+
"loss": 0.3903,
|
| 611 |
+
"step": 2150
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.8634378721714966,
|
| 615 |
+
"grad_norm": 14.88476276397705,
|
| 616 |
+
"learning_rate": 3.5941118094608006e-05,
|
| 617 |
+
"loss": 0.4733,
|
| 618 |
+
"step": 2175
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.8733624454148472,
|
| 622 |
+
"grad_norm": 2.3145201206207275,
|
| 623 |
+
"learning_rate": 3.635461462123718e-05,
|
| 624 |
+
"loss": 0.4176,
|
| 625 |
+
"step": 2200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.8832870186581977,
|
| 629 |
+
"grad_norm": 10.182180404663086,
|
| 630 |
+
"learning_rate": 3.676811114786636e-05,
|
| 631 |
+
"loss": 0.5835,
|
| 632 |
+
"step": 2225
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.8932115919015482,
|
| 636 |
+
"grad_norm": 10.716848373413086,
|
| 637 |
+
"learning_rate": 3.718160767449553e-05,
|
| 638 |
+
"loss": 0.4619,
|
| 639 |
+
"step": 2250
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9031361651448988,
|
| 643 |
+
"grad_norm": 8.731653213500977,
|
| 644 |
+
"learning_rate": 3.7595104201124713e-05,
|
| 645 |
+
"loss": 0.6123,
|
| 646 |
+
"step": 2275
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.9130607383882493,
|
| 650 |
+
"grad_norm": 10.721365928649902,
|
| 651 |
+
"learning_rate": 3.800860072775389e-05,
|
| 652 |
+
"loss": 0.397,
|
| 653 |
+
"step": 2300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.9229853116315998,
|
| 657 |
+
"grad_norm": 11.431262016296387,
|
| 658 |
+
"learning_rate": 3.842209725438307e-05,
|
| 659 |
+
"loss": 0.4318,
|
| 660 |
+
"step": 2325
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.9329098848749504,
|
| 664 |
+
"grad_norm": 3.0338544845581055,
|
| 665 |
+
"learning_rate": 3.8835593781012244e-05,
|
| 666 |
+
"loss": 0.3033,
|
| 667 |
+
"step": 2350
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.9428344581183009,
|
| 671 |
+
"grad_norm": 23.384145736694336,
|
| 672 |
+
"learning_rate": 3.924909030764142e-05,
|
| 673 |
+
"loss": 0.3847,
|
| 674 |
+
"step": 2375
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.9527590313616514,
|
| 678 |
+
"grad_norm": 15.867884635925293,
|
| 679 |
+
"learning_rate": 3.966258683427059e-05,
|
| 680 |
+
"loss": 0.3956,
|
| 681 |
+
"step": 2400
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.962683604605002,
|
| 685 |
+
"grad_norm": 5.550809383392334,
|
| 686 |
+
"learning_rate": 4.007608336089977e-05,
|
| 687 |
+
"loss": 0.492,
|
| 688 |
+
"step": 2425
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.9726081778483525,
|
| 692 |
+
"grad_norm": 1.8582667112350464,
|
| 693 |
+
"learning_rate": 4.0489579887528944e-05,
|
| 694 |
+
"loss": 0.376,
|
| 695 |
+
"step": 2450
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.982532751091703,
|
| 699 |
+
"grad_norm": 6.981182098388672,
|
| 700 |
+
"learning_rate": 4.090307641415813e-05,
|
| 701 |
+
"loss": 0.4754,
|
| 702 |
+
"step": 2475
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.9924573243350536,
|
| 706 |
+
"grad_norm": 21.879558563232422,
|
| 707 |
+
"learning_rate": 4.1316572940787304e-05,
|
| 708 |
+
"loss": 0.5008,
|
| 709 |
+
"step": 2500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.0,
|
| 713 |
+
"eval_accuracy": 0.9045307443365695,
|
| 714 |
+
"eval_f1_macro": 0.5263164909080015,
|
| 715 |
+
"eval_f1_micro": 0.9045307443365695,
|
| 716 |
+
"eval_f1_weighted": 0.9163480431126305,
|
| 717 |
+
"eval_loss": 0.28256678581237793,
|
| 718 |
+
"eval_precision_macro": 0.49666168555241935,
|
| 719 |
+
"eval_precision_micro": 0.9045307443365695,
|
| 720 |
+
"eval_precision_weighted": 0.9309815175276679,
|
| 721 |
+
"eval_recall_macro": 0.6908528288977522,
|
| 722 |
+
"eval_recall_micro": 0.9045307443365695,
|
| 723 |
+
"eval_recall_weighted": 0.9045307443365695,
|
| 724 |
+
"eval_runtime": 2.962,
|
| 725 |
+
"eval_samples_per_second": 834.566,
|
| 726 |
+
"eval_steps_per_second": 52.329,
|
| 727 |
+
"step": 2519
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.0023818975784042,
|
| 731 |
+
"grad_norm": 3.859447956085205,
|
| 732 |
+
"learning_rate": 4.1730069467416474e-05,
|
| 733 |
+
"loss": 0.4463,
|
| 734 |
+
"step": 2525
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.0123064708217546,
|
| 738 |
+
"grad_norm": 13.322518348693848,
|
| 739 |
+
"learning_rate": 4.214356599404565e-05,
|
| 740 |
+
"loss": 0.4674,
|
| 741 |
+
"step": 2550
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.0222310440651052,
|
| 745 |
+
"grad_norm": 2.4851415157318115,
|
| 746 |
+
"learning_rate": 4.255706252067483e-05,
|
| 747 |
+
"loss": 0.5052,
|
| 748 |
+
"step": 2575
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.0321556173084558,
|
| 752 |
+
"grad_norm": 4.881019115447998,
|
| 753 |
+
"learning_rate": 4.2970559047304004e-05,
|
| 754 |
+
"loss": 0.3515,
|
| 755 |
+
"step": 2600
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.0420801905518062,
|
| 759 |
+
"grad_norm": 20.766782760620117,
|
| 760 |
+
"learning_rate": 4.338405557393318e-05,
|
| 761 |
+
"loss": 0.297,
|
| 762 |
+
"step": 2625
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.0520047637951568,
|
| 766 |
+
"grad_norm": 8.236032485961914,
|
| 767 |
+
"learning_rate": 4.379755210056236e-05,
|
| 768 |
+
"loss": 0.439,
|
| 769 |
+
"step": 2650
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.0619293370385074,
|
| 773 |
+
"grad_norm": 3.516899824142456,
|
| 774 |
+
"learning_rate": 4.4211048627191535e-05,
|
| 775 |
+
"loss": 0.5696,
|
| 776 |
+
"step": 2675
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.0718539102818578,
|
| 780 |
+
"grad_norm": 7.603419780731201,
|
| 781 |
+
"learning_rate": 4.462454515382071e-05,
|
| 782 |
+
"loss": 0.4046,
|
| 783 |
+
"step": 2700
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.0817784835252084,
|
| 787 |
+
"grad_norm": 44.93229293823242,
|
| 788 |
+
"learning_rate": 4.503804168044989e-05,
|
| 789 |
+
"loss": 0.4609,
|
| 790 |
+
"step": 2725
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.091703056768559,
|
| 794 |
+
"grad_norm": 20.486032485961914,
|
| 795 |
+
"learning_rate": 4.5451538207079065e-05,
|
| 796 |
+
"loss": 0.388,
|
| 797 |
+
"step": 2750
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.1016276300119094,
|
| 801 |
+
"grad_norm": 20.40689468383789,
|
| 802 |
+
"learning_rate": 4.586503473370824e-05,
|
| 803 |
+
"loss": 0.3312,
|
| 804 |
+
"step": 2775
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.11155220325526,
|
| 808 |
+
"grad_norm": 31.87874412536621,
|
| 809 |
+
"learning_rate": 4.627853126033742e-05,
|
| 810 |
+
"loss": 0.3683,
|
| 811 |
+
"step": 2800
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.1214767764986107,
|
| 815 |
+
"grad_norm": 6.600347995758057,
|
| 816 |
+
"learning_rate": 4.669202778696659e-05,
|
| 817 |
+
"loss": 0.3465,
|
| 818 |
+
"step": 2825
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.131401349741961,
|
| 822 |
+
"grad_norm": 7.1436614990234375,
|
| 823 |
+
"learning_rate": 4.7105524313595765e-05,
|
| 824 |
+
"loss": 0.3549,
|
| 825 |
+
"step": 2850
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.1413259229853117,
|
| 829 |
+
"grad_norm": 5.500131130218506,
|
| 830 |
+
"learning_rate": 4.751902084022494e-05,
|
| 831 |
+
"loss": 0.3101,
|
| 832 |
+
"step": 2875
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.1512504962286623,
|
| 836 |
+
"grad_norm": 10.414060592651367,
|
| 837 |
+
"learning_rate": 4.793251736685412e-05,
|
| 838 |
+
"loss": 0.4034,
|
| 839 |
+
"step": 2900
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.1611750694720127,
|
| 843 |
+
"grad_norm": 6.1647796630859375,
|
| 844 |
+
"learning_rate": 4.83460138934833e-05,
|
| 845 |
+
"loss": 0.3977,
|
| 846 |
+
"step": 2925
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.1710996427153633,
|
| 850 |
+
"grad_norm": 10.712364196777344,
|
| 851 |
+
"learning_rate": 4.875951042011247e-05,
|
| 852 |
+
"loss": 0.4372,
|
| 853 |
+
"step": 2950
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.1810242159587139,
|
| 857 |
+
"grad_norm": 12.25826644897461,
|
| 858 |
+
"learning_rate": 4.917300694674165e-05,
|
| 859 |
+
"loss": 0.4261,
|
| 860 |
+
"step": 2975
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.1909487892020643,
|
| 864 |
+
"grad_norm": 4.6771955490112305,
|
| 865 |
+
"learning_rate": 4.9586503473370826e-05,
|
| 866 |
+
"loss": 0.4259,
|
| 867 |
+
"step": 3000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.2008733624454149,
|
| 871 |
+
"grad_norm": 11.67512035369873,
|
| 872 |
+
"learning_rate": 5e-05,
|
| 873 |
+
"loss": 0.3659,
|
| 874 |
+
"step": 3025
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.2107979356887655,
|
| 878 |
+
"grad_norm": 8.216063499450684,
|
| 879 |
+
"learning_rate": 4.995405256386694e-05,
|
| 880 |
+
"loss": 0.4464,
|
| 881 |
+
"step": 3050
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.2207225089321159,
|
| 885 |
+
"grad_norm": 22.267168045043945,
|
| 886 |
+
"learning_rate": 4.9908105127733874e-05,
|
| 887 |
+
"loss": 0.3732,
|
| 888 |
+
"step": 3075
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.2306470821754665,
|
| 892 |
+
"grad_norm": 1.395468831062317,
|
| 893 |
+
"learning_rate": 4.9862157691600817e-05,
|
| 894 |
+
"loss": 0.5368,
|
| 895 |
+
"step": 3100
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 1.240571655418817,
|
| 899 |
+
"grad_norm": 14.493329048156738,
|
| 900 |
+
"learning_rate": 4.9816210255467746e-05,
|
| 901 |
+
"loss": 0.5204,
|
| 902 |
+
"step": 3125
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.2504962286621675,
|
| 906 |
+
"grad_norm": 4.430512428283691,
|
| 907 |
+
"learning_rate": 4.977026281933468e-05,
|
| 908 |
+
"loss": 0.4111,
|
| 909 |
+
"step": 3150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.260420801905518,
|
| 913 |
+
"grad_norm": 4.284825325012207,
|
| 914 |
+
"learning_rate": 4.972431538320162e-05,
|
| 915 |
+
"loss": 0.4787,
|
| 916 |
+
"step": 3175
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.2703453751488687,
|
| 920 |
+
"grad_norm": 8.76174259185791,
|
| 921 |
+
"learning_rate": 4.967836794706855e-05,
|
| 922 |
+
"loss": 0.3823,
|
| 923 |
+
"step": 3200
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.280269948392219,
|
| 927 |
+
"grad_norm": 20.934642791748047,
|
| 928 |
+
"learning_rate": 4.963242051093549e-05,
|
| 929 |
+
"loss": 0.5349,
|
| 930 |
+
"step": 3225
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.2901945216355697,
|
| 934 |
+
"grad_norm": 77.49037170410156,
|
| 935 |
+
"learning_rate": 4.958647307480243e-05,
|
| 936 |
+
"loss": 0.4614,
|
| 937 |
+
"step": 3250
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.3001190948789203,
|
| 941 |
+
"grad_norm": 23.94263458251953,
|
| 942 |
+
"learning_rate": 4.954052563866937e-05,
|
| 943 |
+
"loss": 0.2915,
|
| 944 |
+
"step": 3275
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.3100436681222707,
|
| 948 |
+
"grad_norm": 30.644512176513672,
|
| 949 |
+
"learning_rate": 4.94945782025363e-05,
|
| 950 |
+
"loss": 0.4269,
|
| 951 |
+
"step": 3300
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.3199682413656213,
|
| 955 |
+
"grad_norm": 45.83186721801758,
|
| 956 |
+
"learning_rate": 4.944863076640324e-05,
|
| 957 |
+
"loss": 0.3725,
|
| 958 |
+
"step": 3325
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.329892814608972,
|
| 962 |
+
"grad_norm": 60.0178337097168,
|
| 963 |
+
"learning_rate": 4.9402683330270175e-05,
|
| 964 |
+
"loss": 0.2582,
|
| 965 |
+
"step": 3350
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.3398173878523223,
|
| 969 |
+
"grad_norm": 6.330191612243652,
|
| 970 |
+
"learning_rate": 4.935673589413711e-05,
|
| 971 |
+
"loss": 0.4748,
|
| 972 |
+
"step": 3375
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 1.349741961095673,
|
| 976 |
+
"grad_norm": 1.5071791410446167,
|
| 977 |
+
"learning_rate": 4.9310788458004046e-05,
|
| 978 |
+
"loss": 0.3084,
|
| 979 |
+
"step": 3400
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 1.3596665343390235,
|
| 983 |
+
"grad_norm": 1.9346116781234741,
|
| 984 |
+
"learning_rate": 4.9266678919316307e-05,
|
| 985 |
+
"loss": 0.4375,
|
| 986 |
+
"step": 3425
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.369591107582374,
|
| 990 |
+
"grad_norm": 18.12363052368164,
|
| 991 |
+
"learning_rate": 4.922073148318324e-05,
|
| 992 |
+
"loss": 0.3925,
|
| 993 |
+
"step": 3450
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.3795156808257245,
|
| 997 |
+
"grad_norm": 5.436924457550049,
|
| 998 |
+
"learning_rate": 4.917478404705018e-05,
|
| 999 |
+
"loss": 0.5044,
|
| 1000 |
+
"step": 3475
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.3894402540690751,
|
| 1004 |
+
"grad_norm": 0.3939330577850342,
|
| 1005 |
+
"learning_rate": 4.9128836610917114e-05,
|
| 1006 |
+
"loss": 0.2836,
|
| 1007 |
+
"step": 3500
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.3993648273124255,
|
| 1011 |
+
"grad_norm": 96.05244445800781,
|
| 1012 |
+
"learning_rate": 4.908288917478405e-05,
|
| 1013 |
+
"loss": 0.4089,
|
| 1014 |
+
"step": 3525
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.4092894005557761,
|
| 1018 |
+
"grad_norm": 20.134159088134766,
|
| 1019 |
+
"learning_rate": 4.9036941738650986e-05,
|
| 1020 |
+
"loss": 0.7075,
|
| 1021 |
+
"step": 3550
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.4192139737991267,
|
| 1025 |
+
"grad_norm": 4.473691940307617,
|
| 1026 |
+
"learning_rate": 4.899099430251792e-05,
|
| 1027 |
+
"loss": 0.3586,
|
| 1028 |
+
"step": 3575
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.4291385470424771,
|
| 1032 |
+
"grad_norm": 8.926084518432617,
|
| 1033 |
+
"learning_rate": 4.894504686638486e-05,
|
| 1034 |
+
"loss": 0.3725,
|
| 1035 |
+
"step": 3600
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.4390631202858277,
|
| 1039 |
+
"grad_norm": 19.507497787475586,
|
| 1040 |
+
"learning_rate": 4.889909943025179e-05,
|
| 1041 |
+
"loss": 0.3892,
|
| 1042 |
+
"step": 3625
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.4489876935291783,
|
| 1046 |
+
"grad_norm": 3.8205032348632812,
|
| 1047 |
+
"learning_rate": 4.885315199411873e-05,
|
| 1048 |
+
"loss": 0.4628,
|
| 1049 |
+
"step": 3650
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.4589122667725287,
|
| 1053 |
+
"grad_norm": 2.284642457962036,
|
| 1054 |
+
"learning_rate": 4.8807204557985665e-05,
|
| 1055 |
+
"loss": 0.3998,
|
| 1056 |
+
"step": 3675
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.4688368400158793,
|
| 1060 |
+
"grad_norm": 23.338348388671875,
|
| 1061 |
+
"learning_rate": 4.876125712185261e-05,
|
| 1062 |
+
"loss": 0.4429,
|
| 1063 |
+
"step": 3700
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 1.47876141325923,
|
| 1067 |
+
"grad_norm": 4.310792446136475,
|
| 1068 |
+
"learning_rate": 4.871530968571954e-05,
|
| 1069 |
+
"loss": 0.4766,
|
| 1070 |
+
"step": 3725
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.4886859865025803,
|
| 1074 |
+
"grad_norm": 16.83978271484375,
|
| 1075 |
+
"learning_rate": 4.866936224958647e-05,
|
| 1076 |
+
"loss": 0.3595,
|
| 1077 |
+
"step": 3750
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.498610559745931,
|
| 1081 |
+
"grad_norm": 7.984683036804199,
|
| 1082 |
+
"learning_rate": 4.862341481345341e-05,
|
| 1083 |
+
"loss": 0.4414,
|
| 1084 |
+
"step": 3775
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.5085351329892815,
|
| 1088 |
+
"grad_norm": 12.33156967163086,
|
| 1089 |
+
"learning_rate": 4.8577467377320344e-05,
|
| 1090 |
+
"loss": 0.3373,
|
| 1091 |
+
"step": 3800
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.518459706232632,
|
| 1095 |
+
"grad_norm": 9.190964698791504,
|
| 1096 |
+
"learning_rate": 4.8531519941187286e-05,
|
| 1097 |
+
"loss": 0.4159,
|
| 1098 |
+
"step": 3825
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.5283842794759825,
|
| 1102 |
+
"grad_norm": 1.6938592195510864,
|
| 1103 |
+
"learning_rate": 4.848557250505422e-05,
|
| 1104 |
+
"loss": 0.3068,
|
| 1105 |
+
"step": 3850
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.5383088527193332,
|
| 1109 |
+
"grad_norm": 12.588111877441406,
|
| 1110 |
+
"learning_rate": 4.843962506892116e-05,
|
| 1111 |
+
"loss": 0.3482,
|
| 1112 |
+
"step": 3875
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.5482334259626835,
|
| 1116 |
+
"grad_norm": 10.160625457763672,
|
| 1117 |
+
"learning_rate": 4.8393677632788094e-05,
|
| 1118 |
+
"loss": 0.4085,
|
| 1119 |
+
"step": 3900
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.5581579992060341,
|
| 1123 |
+
"grad_norm": 9.008238792419434,
|
| 1124 |
+
"learning_rate": 4.834773019665503e-05,
|
| 1125 |
+
"loss": 0.3555,
|
| 1126 |
+
"step": 3925
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.5680825724493848,
|
| 1130 |
+
"grad_norm": 10.664636611938477,
|
| 1131 |
+
"learning_rate": 4.8301782760521965e-05,
|
| 1132 |
+
"loss": 0.4347,
|
| 1133 |
+
"step": 3950
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.5780071456927351,
|
| 1137 |
+
"grad_norm": 12.878474235534668,
|
| 1138 |
+
"learning_rate": 4.8257673221834226e-05,
|
| 1139 |
+
"loss": 0.3514,
|
| 1140 |
+
"step": 3975
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.5879317189360858,
|
| 1144 |
+
"grad_norm": 28.640953063964844,
|
| 1145 |
+
"learning_rate": 4.821172578570116e-05,
|
| 1146 |
+
"loss": 0.4373,
|
| 1147 |
+
"step": 4000
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.5978562921794364,
|
| 1151 |
+
"grad_norm": 8.114662170410156,
|
| 1152 |
+
"learning_rate": 4.81657783495681e-05,
|
| 1153 |
+
"loss": 0.5475,
|
| 1154 |
+
"step": 4025
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.6077808654227868,
|
| 1158 |
+
"grad_norm": 1.0270618200302124,
|
| 1159 |
+
"learning_rate": 4.811983091343503e-05,
|
| 1160 |
+
"loss": 0.4004,
|
| 1161 |
+
"step": 4050
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.6177054386661374,
|
| 1165 |
+
"grad_norm": 14.404735565185547,
|
| 1166 |
+
"learning_rate": 4.807388347730197e-05,
|
| 1167 |
+
"loss": 0.4026,
|
| 1168 |
+
"step": 4075
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.627630011909488,
|
| 1172 |
+
"grad_norm": 6.056324005126953,
|
| 1173 |
+
"learning_rate": 4.8027936041168905e-05,
|
| 1174 |
+
"loss": 0.4614,
|
| 1175 |
+
"step": 4100
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.6375545851528384,
|
| 1179 |
+
"grad_norm": 5.233348369598389,
|
| 1180 |
+
"learning_rate": 4.798198860503584e-05,
|
| 1181 |
+
"loss": 0.4217,
|
| 1182 |
+
"step": 4125
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.647479158396189,
|
| 1186 |
+
"grad_norm": 3.042595624923706,
|
| 1187 |
+
"learning_rate": 4.7936041168902776e-05,
|
| 1188 |
+
"loss": 0.3176,
|
| 1189 |
+
"step": 4150
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.6574037316395396,
|
| 1193 |
+
"grad_norm": 25.57343101501465,
|
| 1194 |
+
"learning_rate": 4.789009373276971e-05,
|
| 1195 |
+
"loss": 0.3368,
|
| 1196 |
+
"step": 4175
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.66732830488289,
|
| 1200 |
+
"grad_norm": 2.8646833896636963,
|
| 1201 |
+
"learning_rate": 4.784414629663665e-05,
|
| 1202 |
+
"loss": 0.5038,
|
| 1203 |
+
"step": 4200
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.6772528781262406,
|
| 1207 |
+
"grad_norm": 1.7347346544265747,
|
| 1208 |
+
"learning_rate": 4.7798198860503584e-05,
|
| 1209 |
+
"loss": 0.3747,
|
| 1210 |
+
"step": 4225
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.6871774513695912,
|
| 1214 |
+
"grad_norm": 6.473698139190674,
|
| 1215 |
+
"learning_rate": 4.775225142437052e-05,
|
| 1216 |
+
"loss": 0.3714,
|
| 1217 |
+
"step": 4250
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.6971020246129416,
|
| 1221 |
+
"grad_norm": 21.557994842529297,
|
| 1222 |
+
"learning_rate": 4.770630398823746e-05,
|
| 1223 |
+
"loss": 0.3321,
|
| 1224 |
+
"step": 4275
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.7070265978562922,
|
| 1228 |
+
"grad_norm": 13.182591438293457,
|
| 1229 |
+
"learning_rate": 4.76603565521044e-05,
|
| 1230 |
+
"loss": 0.3855,
|
| 1231 |
+
"step": 4300
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 1.7169511710996428,
|
| 1235 |
+
"grad_norm": 10.095991134643555,
|
| 1236 |
+
"learning_rate": 4.7614409115971334e-05,
|
| 1237 |
+
"loss": 0.4551,
|
| 1238 |
+
"step": 4325
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.7268757443429932,
|
| 1242 |
+
"grad_norm": 9.291120529174805,
|
| 1243 |
+
"learning_rate": 4.756846167983827e-05,
|
| 1244 |
+
"loss": 0.3452,
|
| 1245 |
+
"step": 4350
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 1.7368003175863438,
|
| 1249 |
+
"grad_norm": 8.871414184570312,
|
| 1250 |
+
"learning_rate": 4.75225142437052e-05,
|
| 1251 |
+
"loss": 0.5005,
|
| 1252 |
+
"step": 4375
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 1.7467248908296944,
|
| 1256 |
+
"grad_norm": 5.440658092498779,
|
| 1257 |
+
"learning_rate": 4.7476566807572134e-05,
|
| 1258 |
+
"loss": 0.5013,
|
| 1259 |
+
"step": 4400
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.7566494640730448,
|
| 1263 |
+
"grad_norm": 23.01534652709961,
|
| 1264 |
+
"learning_rate": 4.743061937143908e-05,
|
| 1265 |
+
"loss": 0.3396,
|
| 1266 |
+
"step": 4425
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.7665740373163954,
|
| 1270 |
+
"grad_norm": 0.980478823184967,
|
| 1271 |
+
"learning_rate": 4.738467193530601e-05,
|
| 1272 |
+
"loss": 0.3813,
|
| 1273 |
+
"step": 4450
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.776498610559746,
|
| 1277 |
+
"grad_norm": 3.2273223400115967,
|
| 1278 |
+
"learning_rate": 4.733872449917295e-05,
|
| 1279 |
+
"loss": 0.4385,
|
| 1280 |
+
"step": 4475
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.7864231838030964,
|
| 1284 |
+
"grad_norm": 19.515819549560547,
|
| 1285 |
+
"learning_rate": 4.7292777063039884e-05,
|
| 1286 |
+
"loss": 0.3571,
|
| 1287 |
+
"step": 4500
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.796347757046447,
|
| 1291 |
+
"grad_norm": 13.477526664733887,
|
| 1292 |
+
"learning_rate": 4.724682962690682e-05,
|
| 1293 |
+
"loss": 0.518,
|
| 1294 |
+
"step": 4525
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.8062723302897976,
|
| 1298 |
+
"grad_norm": 5.6759934425354,
|
| 1299 |
+
"learning_rate": 4.720088219077376e-05,
|
| 1300 |
+
"loss": 0.5254,
|
| 1301 |
+
"step": 4550
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 1.816196903533148,
|
| 1305 |
+
"grad_norm": 7.790989398956299,
|
| 1306 |
+
"learning_rate": 4.715493475464069e-05,
|
| 1307 |
+
"loss": 0.345,
|
| 1308 |
+
"step": 4575
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 1.8261214767764986,
|
| 1312 |
+
"grad_norm": 12.977177619934082,
|
| 1313 |
+
"learning_rate": 4.710898731850763e-05,
|
| 1314 |
+
"loss": 0.4941,
|
| 1315 |
+
"step": 4600
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 1.8360460500198492,
|
| 1319 |
+
"grad_norm": 4.775055885314941,
|
| 1320 |
+
"learning_rate": 4.706303988237456e-05,
|
| 1321 |
+
"loss": 0.4253,
|
| 1322 |
+
"step": 4625
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.8459706232631996,
|
| 1326 |
+
"grad_norm": 9.108200073242188,
|
| 1327 |
+
"learning_rate": 4.70170924462415e-05,
|
| 1328 |
+
"loss": 0.338,
|
| 1329 |
+
"step": 4650
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.8558951965065502,
|
| 1333 |
+
"grad_norm": 12.792155265808105,
|
| 1334 |
+
"learning_rate": 4.6971145010108435e-05,
|
| 1335 |
+
"loss": 0.4233,
|
| 1336 |
+
"step": 4675
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 1.8658197697499008,
|
| 1340 |
+
"grad_norm": 5.169973850250244,
|
| 1341 |
+
"learning_rate": 4.692519757397538e-05,
|
| 1342 |
+
"loss": 0.3696,
|
| 1343 |
+
"step": 4700
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.8757443429932512,
|
| 1347 |
+
"grad_norm": 1.6966049671173096,
|
| 1348 |
+
"learning_rate": 4.687925013784231e-05,
|
| 1349 |
+
"loss": 0.3511,
|
| 1350 |
+
"step": 4725
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.8856689162366018,
|
| 1354 |
+
"grad_norm": 6.585522174835205,
|
| 1355 |
+
"learning_rate": 4.683330270170925e-05,
|
| 1356 |
+
"loss": 0.4427,
|
| 1357 |
+
"step": 4750
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 1.8955934894799524,
|
| 1361 |
+
"grad_norm": 20.628782272338867,
|
| 1362 |
+
"learning_rate": 4.6787355265576185e-05,
|
| 1363 |
+
"loss": 0.3483,
|
| 1364 |
+
"step": 4775
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.9055180627233028,
|
| 1368 |
+
"grad_norm": 3.5332088470458984,
|
| 1369 |
+
"learning_rate": 4.674140782944312e-05,
|
| 1370 |
+
"loss": 0.3393,
|
| 1371 |
+
"step": 4800
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 1.9154426359666534,
|
| 1375 |
+
"grad_norm": 3.3597798347473145,
|
| 1376 |
+
"learning_rate": 4.669546039331005e-05,
|
| 1377 |
+
"loss": 0.4498,
|
| 1378 |
+
"step": 4825
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.925367209210004,
|
| 1382 |
+
"grad_norm": 34.44575500488281,
|
| 1383 |
+
"learning_rate": 4.664951295717699e-05,
|
| 1384 |
+
"loss": 0.477,
|
| 1385 |
+
"step": 4850
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.9352917824533544,
|
| 1389 |
+
"grad_norm": 7.198688507080078,
|
| 1390 |
+
"learning_rate": 4.660356552104393e-05,
|
| 1391 |
+
"loss": 0.4628,
|
| 1392 |
+
"step": 4875
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.945216355696705,
|
| 1396 |
+
"grad_norm": 9.399107933044434,
|
| 1397 |
+
"learning_rate": 4.6557618084910864e-05,
|
| 1398 |
+
"loss": 0.3823,
|
| 1399 |
+
"step": 4900
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.9551409289400556,
|
| 1403 |
+
"grad_norm": 4.068615436553955,
|
| 1404 |
+
"learning_rate": 4.65116706487778e-05,
|
| 1405 |
+
"loss": 0.3621,
|
| 1406 |
+
"step": 4925
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.965065502183406,
|
| 1410 |
+
"grad_norm": 8.930496215820312,
|
| 1411 |
+
"learning_rate": 4.6465723212644736e-05,
|
| 1412 |
+
"loss": 0.4224,
|
| 1413 |
+
"step": 4950
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.9749900754267566,
|
| 1417 |
+
"grad_norm": 16.361087799072266,
|
| 1418 |
+
"learning_rate": 4.641977577651167e-05,
|
| 1419 |
+
"loss": 0.3773,
|
| 1420 |
+
"step": 4975
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.9849146486701073,
|
| 1424 |
+
"grad_norm": 7.0522565841674805,
|
| 1425 |
+
"learning_rate": 4.6373828340378614e-05,
|
| 1426 |
+
"loss": 0.4883,
|
| 1427 |
+
"step": 5000
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.9948392219134576,
|
| 1431 |
+
"grad_norm": 5.567374229431152,
|
| 1432 |
+
"learning_rate": 4.632788090424554e-05,
|
| 1433 |
+
"loss": 0.5359,
|
| 1434 |
+
"step": 5025
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.0,
|
| 1438 |
+
"eval_accuracy": 0.9466019417475728,
|
| 1439 |
+
"eval_f1_macro": 0.7547155454831698,
|
| 1440 |
+
"eval_f1_micro": 0.9466019417475728,
|
| 1441 |
+
"eval_f1_weighted": 0.9445123807456527,
|
| 1442 |
+
"eval_loss": 0.17345599830150604,
|
| 1443 |
+
"eval_precision_macro": 0.8558757528469544,
|
| 1444 |
+
"eval_precision_micro": 0.9466019417475728,
|
| 1445 |
+
"eval_precision_weighted": 0.9434254644943053,
|
| 1446 |
+
"eval_recall_macro": 0.6923009042209939,
|
| 1447 |
+
"eval_recall_micro": 0.9466019417475728,
|
| 1448 |
+
"eval_recall_weighted": 0.9466019417475728,
|
| 1449 |
+
"eval_runtime": 2.9599,
|
| 1450 |
+
"eval_samples_per_second": 835.167,
|
| 1451 |
+
"eval_steps_per_second": 52.367,
|
| 1452 |
+
"step": 5038
|
| 1453 |
+
}
|
| 1454 |
+
],
|
| 1455 |
+
"logging_steps": 25,
|
| 1456 |
+
"max_steps": 30228,
|
| 1457 |
+
"num_input_tokens_seen": 0,
|
| 1458 |
+
"num_train_epochs": 12,
|
| 1459 |
+
"save_steps": 500,
|
| 1460 |
+
"stateful_callbacks": {
|
| 1461 |
+
"EarlyStoppingCallback": {
|
| 1462 |
+
"args": {
|
| 1463 |
+
"early_stopping_patience": 5,
|
| 1464 |
+
"early_stopping_threshold": 0.01
|
| 1465 |
+
},
|
| 1466 |
+
"attributes": {
|
| 1467 |
+
"early_stopping_patience_counter": 0
|
| 1468 |
+
}
|
| 1469 |
+
},
|
| 1470 |
+
"TrainerControl": {
|
| 1471 |
+
"args": {
|
| 1472 |
+
"should_epoch_stop": false,
|
| 1473 |
+
"should_evaluate": false,
|
| 1474 |
+
"should_log": false,
|
| 1475 |
+
"should_save": true,
|
| 1476 |
+
"should_training_stop": false
|
| 1477 |
+
},
|
| 1478 |
+
"attributes": {}
|
| 1479 |
+
}
|
| 1480 |
+
},
|
| 1481 |
+
"total_flos": 2650867683609600.0,
|
| 1482 |
+
"train_batch_size": 8,
|
| 1483 |
+
"trial_name": null,
|
| 1484 |
+
"trial_params": null
|
| 1485 |
+
}
|
checkpoint-5038/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3f8c1835f8561468477cb6250516dc2e03fefc0a4c32200a6bf44662d850f60
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-german-cased",
|
| 3 |
+
"_num_labels": 3,
|
| 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": "0",
|
| 14 |
+
"1": "1",
|
| 15 |
+
"2": "2"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"0": 0,
|
| 21 |
+
"1": 1,
|
| 22 |
+
"2": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.48.0",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 30000
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ccd26129a7d60735027dec86b2e6b5aff223c7c9e50d7af7b276ce92b6350db
|
| 3 |
+
size 436358132
|
runs/Feb22_14-48-55_r-abgegrieft-autotrain-toxicity-metrics-gaming-commun-7b502-vaz/events.out.tfevents.1740235736.r-abgegrieft-autotrain-toxicity-metrics-gaming-commun-7b502-vaz.203.0
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 sha256:6a65b72c519faaa5dc815a158a1d42b0fc1b34103642159e9f5357bb2139d09a
|
| 3 |
+
size 160358
|
runs/Feb22_14-48-55_r-abgegrieft-autotrain-toxicity-metrics-gaming-commun-7b502-vaz/events.out.tfevents.1740236715.r-abgegrieft-autotrain-toxicity-metrics-gaming-commun-7b502-vaz.203.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25bd5f7831a265bfa548e66229c1af7bb5607ab8c48d339115338af5f8ba5f16
|
| 3 |
+
size 936
|
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:f3f8c1835f8561468477cb6250516dc2e03fefc0a4c32200a6bf44662d850f60
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-sijfl-oha9f/autotrain-data",
|
| 3 |
+
"model": "google-bert/bert-base-german-cased",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 12,
|
| 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-sijfl-oha9f",
|
| 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
|
|
|