Upload folder using huggingface_hub
Browse files- README.md +24 -0
- checkpoint-7518/config.json +39 -0
- checkpoint-7518/model.safetensors +3 -0
- checkpoint-7518/optimizer.pt +3 -0
- checkpoint-7518/rng_state.pth +3 -0
- checkpoint-7518/scheduler.pt +3 -0
- checkpoint-7518/trainer_state.json +2178 -0
- checkpoint-7518/training_args.bin +3 -0
- config.json +39 -0
- model.safetensors +3 -0
- runs/Oct17_19-37-46_rh/events.out.tfevents.1729186667.rh.4547.0 +2 -2
- runs/Oct17_19-37-46_rh/events.out.tfevents.1729187089.rh.4547.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- token-classification
|
| 6 |
+
base_model: dslim/bert-base-NER
|
| 7 |
+
widget:
|
| 8 |
+
- text: "I love AutoTrain"
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Trained Using AutoTrain
|
| 12 |
+
|
| 13 |
+
- Problem type: Token Classification
|
| 14 |
+
|
| 15 |
+
## Validation Metrics
|
| 16 |
+
loss: 0.00414163526147604
|
| 17 |
+
|
| 18 |
+
precision: 0.996753451427851
|
| 19 |
+
|
| 20 |
+
recall: 0.998452892144481
|
| 21 |
+
|
| 22 |
+
f1: 0.9976024480267517
|
| 23 |
+
|
| 24 |
+
accuracy: 0.9987307166569029
|
checkpoint-7518/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dslim/bert-base-NER",
|
| 3 |
+
"_num_labels": 4,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForTokenClassification"
|
| 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": "B-BRAND",
|
| 14 |
+
"1": "B-MODEL",
|
| 15 |
+
"2": "I-MODEL",
|
| 16 |
+
"3": "O"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"B-BRAND": 0,
|
| 22 |
+
"B-MODEL": 1,
|
| 23 |
+
"I-MODEL": 2,
|
| 24 |
+
"O": 3
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"output_past": true,
|
| 32 |
+
"pad_token_id": 0,
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.45.0",
|
| 36 |
+
"type_vocab_size": 2,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 28996
|
| 39 |
+
}
|
checkpoint-7518/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93e9b8fd0f9e77110a6695302c3528eed7a506000320e72dedc0e97f63e4bf5a
|
| 3 |
+
size 430914360
|
checkpoint-7518/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:477b8bea23ebecf738774c4bce32133defcb185ab22baae7db02d4f82b6762d8
|
| 3 |
+
size 861948474
|
checkpoint-7518/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b10f6ab38147386c1f85bedb99e5ba0e9f1c84617828c574d66a4ff9b65851d8
|
| 3 |
+
size 14244
|
checkpoint-7518/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3569d3e4e3b5a5b7833a2466eb6dfa3ff15333f32b21f4136f2eeef5e3b7a0c0
|
| 3 |
+
size 1064
|
checkpoint-7518/trainer_state.json
ADDED
|
@@ -0,0 +1,2178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.00414163526147604,
|
| 3 |
+
"best_model_checkpoint": "product-extractor6/checkpoint-7518",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7518,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.009976057462090982,
|
| 13 |
+
"grad_norm": 6.456821441650391,
|
| 14 |
+
"learning_rate": 1.6622340425531915e-06,
|
| 15 |
+
"loss": 1.4677,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.019952114924181964,
|
| 20 |
+
"grad_norm": 3.1717329025268555,
|
| 21 |
+
"learning_rate": 3.324468085106383e-06,
|
| 22 |
+
"loss": 1.1442,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.029928172386272944,
|
| 27 |
+
"grad_norm": 2.2782442569732666,
|
| 28 |
+
"learning_rate": 4.986702127659574e-06,
|
| 29 |
+
"loss": 0.713,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03990422984836393,
|
| 34 |
+
"grad_norm": 1.7477627992630005,
|
| 35 |
+
"learning_rate": 6.648936170212766e-06,
|
| 36 |
+
"loss": 0.2799,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04988028731045491,
|
| 41 |
+
"grad_norm": 2.2277820110321045,
|
| 42 |
+
"learning_rate": 8.311170212765958e-06,
|
| 43 |
+
"loss": 0.1226,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05985634477254589,
|
| 48 |
+
"grad_norm": 1.6012210845947266,
|
| 49 |
+
"learning_rate": 9.973404255319148e-06,
|
| 50 |
+
"loss": 0.0516,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06983240223463687,
|
| 55 |
+
"grad_norm": 0.8560931086540222,
|
| 56 |
+
"learning_rate": 1.1635638297872341e-05,
|
| 57 |
+
"loss": 0.0392,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.07980845969672785,
|
| 62 |
+
"grad_norm": 0.5693195462226868,
|
| 63 |
+
"learning_rate": 1.3297872340425532e-05,
|
| 64 |
+
"loss": 0.0216,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.08978451715881884,
|
| 69 |
+
"grad_norm": 2.080657958984375,
|
| 70 |
+
"learning_rate": 1.4960106382978726e-05,
|
| 71 |
+
"loss": 0.0281,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.09976057462090981,
|
| 76 |
+
"grad_norm": 1.4145302772521973,
|
| 77 |
+
"learning_rate": 1.6622340425531915e-05,
|
| 78 |
+
"loss": 0.0256,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1097366320830008,
|
| 83 |
+
"grad_norm": 0.06217338144779205,
|
| 84 |
+
"learning_rate": 1.8284574468085108e-05,
|
| 85 |
+
"loss": 0.0182,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.11971268954509177,
|
| 90 |
+
"grad_norm": 0.23941953480243683,
|
| 91 |
+
"learning_rate": 1.9946808510638297e-05,
|
| 92 |
+
"loss": 0.0176,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.12968874700718275,
|
| 97 |
+
"grad_norm": 12.546407699584961,
|
| 98 |
+
"learning_rate": 2.1609042553191493e-05,
|
| 99 |
+
"loss": 0.0341,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.13966480446927373,
|
| 104 |
+
"grad_norm": 1.6958712339401245,
|
| 105 |
+
"learning_rate": 2.3271276595744682e-05,
|
| 106 |
+
"loss": 0.0103,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.14964086193136472,
|
| 111 |
+
"grad_norm": 0.06107725948095322,
|
| 112 |
+
"learning_rate": 2.4933510638297874e-05,
|
| 113 |
+
"loss": 0.0181,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1596169193934557,
|
| 118 |
+
"grad_norm": 1.3681480884552002,
|
| 119 |
+
"learning_rate": 2.6595744680851064e-05,
|
| 120 |
+
"loss": 0.0171,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1695929768555467,
|
| 125 |
+
"grad_norm": 0.9856602549552917,
|
| 126 |
+
"learning_rate": 2.8257978723404256e-05,
|
| 127 |
+
"loss": 0.0142,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.17956903431763768,
|
| 132 |
+
"grad_norm": 0.29045724868774414,
|
| 133 |
+
"learning_rate": 2.9920212765957452e-05,
|
| 134 |
+
"loss": 0.0156,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.18954509177972864,
|
| 139 |
+
"grad_norm": 0.019459933042526245,
|
| 140 |
+
"learning_rate": 3.158244680851064e-05,
|
| 141 |
+
"loss": 0.0156,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.19952114924181963,
|
| 146 |
+
"grad_norm": 2.122072219848633,
|
| 147 |
+
"learning_rate": 3.324468085106383e-05,
|
| 148 |
+
"loss": 0.0284,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.20949720670391062,
|
| 153 |
+
"grad_norm": 0.7935088872909546,
|
| 154 |
+
"learning_rate": 3.490691489361702e-05,
|
| 155 |
+
"loss": 0.014,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2194732641660016,
|
| 160 |
+
"grad_norm": 7.749695777893066,
|
| 161 |
+
"learning_rate": 3.6569148936170215e-05,
|
| 162 |
+
"loss": 0.0175,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2294493216280926,
|
| 167 |
+
"grad_norm": 1.0867451429367065,
|
| 168 |
+
"learning_rate": 3.823138297872341e-05,
|
| 169 |
+
"loss": 0.0152,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.23942537909018355,
|
| 174 |
+
"grad_norm": 0.01711786724627018,
|
| 175 |
+
"learning_rate": 3.982712765957447e-05,
|
| 176 |
+
"loss": 0.0074,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.24940143655227454,
|
| 181 |
+
"grad_norm": 0.45500993728637695,
|
| 182 |
+
"learning_rate": 4.148936170212766e-05,
|
| 183 |
+
"loss": 0.0128,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2593774940143655,
|
| 188 |
+
"grad_norm": 0.3896108865737915,
|
| 189 |
+
"learning_rate": 4.315159574468085e-05,
|
| 190 |
+
"loss": 0.0141,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2693535514764565,
|
| 195 |
+
"grad_norm": 0.98828125,
|
| 196 |
+
"learning_rate": 4.481382978723405e-05,
|
| 197 |
+
"loss": 0.0146,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.27932960893854747,
|
| 202 |
+
"grad_norm": 0.03111772984266281,
|
| 203 |
+
"learning_rate": 4.6476063829787234e-05,
|
| 204 |
+
"loss": 0.0114,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.2893056664006385,
|
| 209 |
+
"grad_norm": 0.0036741234362125397,
|
| 210 |
+
"learning_rate": 4.8138297872340426e-05,
|
| 211 |
+
"loss": 0.0044,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.29928172386272944,
|
| 216 |
+
"grad_norm": 0.010378828272223473,
|
| 217 |
+
"learning_rate": 4.980053191489362e-05,
|
| 218 |
+
"loss": 0.0094,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.30925778132482046,
|
| 223 |
+
"grad_norm": 0.0023950720205903053,
|
| 224 |
+
"learning_rate": 4.9837422406148393e-05,
|
| 225 |
+
"loss": 0.0012,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3192338387869114,
|
| 230 |
+
"grad_norm": 0.280570924282074,
|
| 231 |
+
"learning_rate": 4.965267514040792e-05,
|
| 232 |
+
"loss": 0.0126,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3292098962490024,
|
| 237 |
+
"grad_norm": 0.7244165539741516,
|
| 238 |
+
"learning_rate": 4.946792787466746e-05,
|
| 239 |
+
"loss": 0.0076,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3391859537110934,
|
| 244 |
+
"grad_norm": 0.12444743514060974,
|
| 245 |
+
"learning_rate": 4.9283180608926986e-05,
|
| 246 |
+
"loss": 0.0077,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.34916201117318435,
|
| 251 |
+
"grad_norm": 0.25985321402549744,
|
| 252 |
+
"learning_rate": 4.9098433343186526e-05,
|
| 253 |
+
"loss": 0.0261,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.35913806863527536,
|
| 258 |
+
"grad_norm": 0.038247887045145035,
|
| 259 |
+
"learning_rate": 4.891368607744606e-05,
|
| 260 |
+
"loss": 0.0083,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.3691141260973663,
|
| 265 |
+
"grad_norm": 1.1658748388290405,
|
| 266 |
+
"learning_rate": 4.8728938811705586e-05,
|
| 267 |
+
"loss": 0.0327,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.3790901835594573,
|
| 272 |
+
"grad_norm": 16.90176773071289,
|
| 273 |
+
"learning_rate": 4.8544191545965126e-05,
|
| 274 |
+
"loss": 0.0143,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3890662410215483,
|
| 279 |
+
"grad_norm": 5.232182502746582,
|
| 280 |
+
"learning_rate": 4.835944428022465e-05,
|
| 281 |
+
"loss": 0.0053,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.39904229848363926,
|
| 286 |
+
"grad_norm": 0.021615318953990936,
|
| 287 |
+
"learning_rate": 4.8174697014484185e-05,
|
| 288 |
+
"loss": 0.0118,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.40901835594573027,
|
| 293 |
+
"grad_norm": 0.032547689974308014,
|
| 294 |
+
"learning_rate": 4.7989949748743725e-05,
|
| 295 |
+
"loss": 0.0089,
|
| 296 |
+
"step": 1025
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.41899441340782123,
|
| 300 |
+
"grad_norm": 0.05790809541940689,
|
| 301 |
+
"learning_rate": 4.780520248300325e-05,
|
| 302 |
+
"loss": 0.0091,
|
| 303 |
+
"step": 1050
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4289704708699122,
|
| 307 |
+
"grad_norm": 0.3983357548713684,
|
| 308 |
+
"learning_rate": 4.7620455217262785e-05,
|
| 309 |
+
"loss": 0.0104,
|
| 310 |
+
"step": 1075
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4389465283320032,
|
| 314 |
+
"grad_norm": 0.0017891308525577188,
|
| 315 |
+
"learning_rate": 4.743570795152232e-05,
|
| 316 |
+
"loss": 0.0057,
|
| 317 |
+
"step": 1100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.44892258579409416,
|
| 321 |
+
"grad_norm": 0.050744716078042984,
|
| 322 |
+
"learning_rate": 4.725096068578185e-05,
|
| 323 |
+
"loss": 0.034,
|
| 324 |
+
"step": 1125
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4588986432561852,
|
| 328 |
+
"grad_norm": 0.003633401356637478,
|
| 329 |
+
"learning_rate": 4.7066213420041384e-05,
|
| 330 |
+
"loss": 0.0027,
|
| 331 |
+
"step": 1150
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.46887470071827614,
|
| 335 |
+
"grad_norm": 1.139548659324646,
|
| 336 |
+
"learning_rate": 4.688146615430092e-05,
|
| 337 |
+
"loss": 0.0284,
|
| 338 |
+
"step": 1175
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4788507581803671,
|
| 342 |
+
"grad_norm": 0.6308386325836182,
|
| 343 |
+
"learning_rate": 4.669671888856045e-05,
|
| 344 |
+
"loss": 0.0051,
|
| 345 |
+
"step": 1200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4888268156424581,
|
| 349 |
+
"grad_norm": 0.008109364658594131,
|
| 350 |
+
"learning_rate": 4.6511971622819984e-05,
|
| 351 |
+
"loss": 0.0062,
|
| 352 |
+
"step": 1225
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.49880287310454907,
|
| 356 |
+
"grad_norm": 0.00701555423438549,
|
| 357 |
+
"learning_rate": 4.632722435707952e-05,
|
| 358 |
+
"loss": 0.0054,
|
| 359 |
+
"step": 1250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.50877893056664,
|
| 363 |
+
"grad_norm": 0.1716192066669464,
|
| 364 |
+
"learning_rate": 4.614247709133905e-05,
|
| 365 |
+
"loss": 0.0034,
|
| 366 |
+
"step": 1275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.518754988028731,
|
| 370 |
+
"grad_norm": 0.005927205551415682,
|
| 371 |
+
"learning_rate": 4.5957729825598583e-05,
|
| 372 |
+
"loss": 0.0029,
|
| 373 |
+
"step": 1300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5287310454908221,
|
| 377 |
+
"grad_norm": 0.10920026153326035,
|
| 378 |
+
"learning_rate": 4.577298255985812e-05,
|
| 379 |
+
"loss": 0.0047,
|
| 380 |
+
"step": 1325
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.538707102952913,
|
| 384 |
+
"grad_norm": 0.002323268447071314,
|
| 385 |
+
"learning_rate": 4.558823529411765e-05,
|
| 386 |
+
"loss": 0.0024,
|
| 387 |
+
"step": 1350
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.548683160415004,
|
| 391 |
+
"grad_norm": 0.2037767916917801,
|
| 392 |
+
"learning_rate": 4.540348802837718e-05,
|
| 393 |
+
"loss": 0.0091,
|
| 394 |
+
"step": 1375
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5586592178770949,
|
| 398 |
+
"grad_norm": 0.003944343887269497,
|
| 399 |
+
"learning_rate": 4.5218740762636716e-05,
|
| 400 |
+
"loss": 0.0051,
|
| 401 |
+
"step": 1400
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.568635275339186,
|
| 405 |
+
"grad_norm": 0.006337428465485573,
|
| 406 |
+
"learning_rate": 4.503399349689625e-05,
|
| 407 |
+
"loss": 0.0026,
|
| 408 |
+
"step": 1425
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.578611332801277,
|
| 412 |
+
"grad_norm": 0.08491374552249908,
|
| 413 |
+
"learning_rate": 4.484924623115578e-05,
|
| 414 |
+
"loss": 0.004,
|
| 415 |
+
"step": 1450
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5885873902633679,
|
| 419 |
+
"grad_norm": 0.11802882701158524,
|
| 420 |
+
"learning_rate": 4.4664498965415316e-05,
|
| 421 |
+
"loss": 0.0369,
|
| 422 |
+
"step": 1475
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.5985634477254589,
|
| 426 |
+
"grad_norm": 0.01340041309595108,
|
| 427 |
+
"learning_rate": 4.447975169967485e-05,
|
| 428 |
+
"loss": 0.0032,
|
| 429 |
+
"step": 1500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6085395051875498,
|
| 433 |
+
"grad_norm": 0.0033385739661753178,
|
| 434 |
+
"learning_rate": 4.4295004433934375e-05,
|
| 435 |
+
"loss": 0.0059,
|
| 436 |
+
"step": 1525
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6185155626496409,
|
| 440 |
+
"grad_norm": 0.1672859787940979,
|
| 441 |
+
"learning_rate": 4.4110257168193915e-05,
|
| 442 |
+
"loss": 0.0076,
|
| 443 |
+
"step": 1550
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6284916201117319,
|
| 447 |
+
"grad_norm": 0.0034865420311689377,
|
| 448 |
+
"learning_rate": 4.392550990245344e-05,
|
| 449 |
+
"loss": 0.0033,
|
| 450 |
+
"step": 1575
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6384676775738228,
|
| 454 |
+
"grad_norm": 0.0033787006977945566,
|
| 455 |
+
"learning_rate": 4.374076263671298e-05,
|
| 456 |
+
"loss": 0.0077,
|
| 457 |
+
"step": 1600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.6484437350359138,
|
| 461 |
+
"grad_norm": 0.23978440463542938,
|
| 462 |
+
"learning_rate": 4.3556015370972515e-05,
|
| 463 |
+
"loss": 0.0024,
|
| 464 |
+
"step": 1625
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.6584197924980048,
|
| 468 |
+
"grad_norm": 0.03524857014417648,
|
| 469 |
+
"learning_rate": 4.337126810523204e-05,
|
| 470 |
+
"loss": 0.0072,
|
| 471 |
+
"step": 1650
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.6683958499600958,
|
| 475 |
+
"grad_norm": 0.005281102377921343,
|
| 476 |
+
"learning_rate": 4.318652083949158e-05,
|
| 477 |
+
"loss": 0.0073,
|
| 478 |
+
"step": 1675
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6783719074221868,
|
| 482 |
+
"grad_norm": 0.004328446928411722,
|
| 483 |
+
"learning_rate": 4.300177357375111e-05,
|
| 484 |
+
"loss": 0.0055,
|
| 485 |
+
"step": 1700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.6883479648842777,
|
| 489 |
+
"grad_norm": 0.0014364791568368673,
|
| 490 |
+
"learning_rate": 4.281702630801064e-05,
|
| 491 |
+
"loss": 0.0044,
|
| 492 |
+
"step": 1725
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.6983240223463687,
|
| 496 |
+
"grad_norm": 0.06184546649456024,
|
| 497 |
+
"learning_rate": 4.263227904227018e-05,
|
| 498 |
+
"loss": 0.0058,
|
| 499 |
+
"step": 1750
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7083000798084597,
|
| 503 |
+
"grad_norm": 0.009667358361184597,
|
| 504 |
+
"learning_rate": 4.244753177652971e-05,
|
| 505 |
+
"loss": 0.008,
|
| 506 |
+
"step": 1775
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7182761372705507,
|
| 510 |
+
"grad_norm": 1.9500138759613037,
|
| 511 |
+
"learning_rate": 4.226278451078925e-05,
|
| 512 |
+
"loss": 0.0252,
|
| 513 |
+
"step": 1800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.7282521947326417,
|
| 517 |
+
"grad_norm": 0.2931491434574127,
|
| 518 |
+
"learning_rate": 4.2078037245048773e-05,
|
| 519 |
+
"loss": 0.0075,
|
| 520 |
+
"step": 1825
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.7382282521947326,
|
| 524 |
+
"grad_norm": 0.003551148809492588,
|
| 525 |
+
"learning_rate": 4.189328997930831e-05,
|
| 526 |
+
"loss": 0.0032,
|
| 527 |
+
"step": 1850
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.7482043096568236,
|
| 531 |
+
"grad_norm": 0.0018795117503032088,
|
| 532 |
+
"learning_rate": 4.170854271356784e-05,
|
| 533 |
+
"loss": 0.0025,
|
| 534 |
+
"step": 1875
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.7581803671189146,
|
| 538 |
+
"grad_norm": 0.0033812960609793663,
|
| 539 |
+
"learning_rate": 4.152379544782737e-05,
|
| 540 |
+
"loss": 0.0032,
|
| 541 |
+
"step": 1900
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.7681564245810056,
|
| 545 |
+
"grad_norm": 0.002028366085141897,
|
| 546 |
+
"learning_rate": 4.1339048182086906e-05,
|
| 547 |
+
"loss": 0.0044,
|
| 548 |
+
"step": 1925
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.7781324820430966,
|
| 552 |
+
"grad_norm": 0.010902863927185535,
|
| 553 |
+
"learning_rate": 4.115430091634644e-05,
|
| 554 |
+
"loss": 0.0026,
|
| 555 |
+
"step": 1950
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7881085395051876,
|
| 559 |
+
"grad_norm": 0.007433483377099037,
|
| 560 |
+
"learning_rate": 4.096955365060597e-05,
|
| 561 |
+
"loss": 0.0291,
|
| 562 |
+
"step": 1975
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7980845969672785,
|
| 566 |
+
"grad_norm": 4.558260440826416,
|
| 567 |
+
"learning_rate": 4.0784806384865506e-05,
|
| 568 |
+
"loss": 0.0061,
|
| 569 |
+
"step": 2000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8080606544293695,
|
| 573 |
+
"grad_norm": 0.12536771595478058,
|
| 574 |
+
"learning_rate": 4.060005911912504e-05,
|
| 575 |
+
"loss": 0.0058,
|
| 576 |
+
"step": 2025
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.8180367118914605,
|
| 580 |
+
"grad_norm": 0.0019595527555793524,
|
| 581 |
+
"learning_rate": 4.041531185338457e-05,
|
| 582 |
+
"loss": 0.0054,
|
| 583 |
+
"step": 2050
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8280127693535515,
|
| 587 |
+
"grad_norm": 0.0017618915298953652,
|
| 588 |
+
"learning_rate": 4.0230564587644105e-05,
|
| 589 |
+
"loss": 0.0034,
|
| 590 |
+
"step": 2075
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.8379888268156425,
|
| 594 |
+
"grad_norm": 0.0034647230058908463,
|
| 595 |
+
"learning_rate": 4.004581732190364e-05,
|
| 596 |
+
"loss": 0.0038,
|
| 597 |
+
"step": 2100
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.8479648842777334,
|
| 601 |
+
"grad_norm": 0.010702223517000675,
|
| 602 |
+
"learning_rate": 3.986107005616317e-05,
|
| 603 |
+
"loss": 0.004,
|
| 604 |
+
"step": 2125
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.8579409417398244,
|
| 608 |
+
"grad_norm": 0.006897944025695324,
|
| 609 |
+
"learning_rate": 3.9676322790422705e-05,
|
| 610 |
+
"loss": 0.0028,
|
| 611 |
+
"step": 2150
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.8679169992019155,
|
| 615 |
+
"grad_norm": 0.0009841732680797577,
|
| 616 |
+
"learning_rate": 3.949157552468223e-05,
|
| 617 |
+
"loss": 0.0033,
|
| 618 |
+
"step": 2175
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.8778930566640064,
|
| 622 |
+
"grad_norm": 0.01677691750228405,
|
| 623 |
+
"learning_rate": 3.930682825894177e-05,
|
| 624 |
+
"loss": 0.0081,
|
| 625 |
+
"step": 2200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.8878691141260974,
|
| 629 |
+
"grad_norm": 0.00315505126491189,
|
| 630 |
+
"learning_rate": 3.9122080993201304e-05,
|
| 631 |
+
"loss": 0.0045,
|
| 632 |
+
"step": 2225
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.8978451715881883,
|
| 636 |
+
"grad_norm": 0.0014864664990454912,
|
| 637 |
+
"learning_rate": 3.893733372746083e-05,
|
| 638 |
+
"loss": 0.002,
|
| 639 |
+
"step": 2250
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9078212290502793,
|
| 643 |
+
"grad_norm": 0.10174369066953659,
|
| 644 |
+
"learning_rate": 3.875258646172037e-05,
|
| 645 |
+
"loss": 0.0329,
|
| 646 |
+
"step": 2275
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.9177972865123704,
|
| 650 |
+
"grad_norm": 0.005189603194594383,
|
| 651 |
+
"learning_rate": 3.85678391959799e-05,
|
| 652 |
+
"loss": 0.0008,
|
| 653 |
+
"step": 2300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.9277733439744613,
|
| 657 |
+
"grad_norm": 0.003211621893569827,
|
| 658 |
+
"learning_rate": 3.838309193023944e-05,
|
| 659 |
+
"loss": 0.0028,
|
| 660 |
+
"step": 2325
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.9377494014365523,
|
| 664 |
+
"grad_norm": 0.07335402816534042,
|
| 665 |
+
"learning_rate": 3.819834466449897e-05,
|
| 666 |
+
"loss": 0.0019,
|
| 667 |
+
"step": 2350
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.9477254588986432,
|
| 671 |
+
"grad_norm": 0.08445198088884354,
|
| 672 |
+
"learning_rate": 3.80135973987585e-05,
|
| 673 |
+
"loss": 0.0043,
|
| 674 |
+
"step": 2375
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.9577015163607342,
|
| 678 |
+
"grad_norm": 0.00201265886425972,
|
| 679 |
+
"learning_rate": 3.7828850133018037e-05,
|
| 680 |
+
"loss": 0.0033,
|
| 681 |
+
"step": 2400
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.9676775738228253,
|
| 685 |
+
"grad_norm": 0.0035803918726742268,
|
| 686 |
+
"learning_rate": 3.764410286727756e-05,
|
| 687 |
+
"loss": 0.0061,
|
| 688 |
+
"step": 2425
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.9776536312849162,
|
| 692 |
+
"grad_norm": 0.002663583494722843,
|
| 693 |
+
"learning_rate": 3.7459355601537096e-05,
|
| 694 |
+
"loss": 0.0074,
|
| 695 |
+
"step": 2450
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.9876296887470072,
|
| 699 |
+
"grad_norm": 0.19914691150188446,
|
| 700 |
+
"learning_rate": 3.7274608335796636e-05,
|
| 701 |
+
"loss": 0.0047,
|
| 702 |
+
"step": 2475
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.9976057462090981,
|
| 706 |
+
"grad_norm": 0.0037153991870582104,
|
| 707 |
+
"learning_rate": 3.708986107005616e-05,
|
| 708 |
+
"loss": 0.0068,
|
| 709 |
+
"step": 2500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.0,
|
| 713 |
+
"eval_accuracy": 0.997784856473345,
|
| 714 |
+
"eval_f1": 0.9953336813299799,
|
| 715 |
+
"eval_loss": 0.008541167713701725,
|
| 716 |
+
"eval_precision": 0.9973056075062605,
|
| 717 |
+
"eval_recall": 0.9933695377620612,
|
| 718 |
+
"eval_runtime": 8.5365,
|
| 719 |
+
"eval_samples_per_second": 587.128,
|
| 720 |
+
"eval_steps_per_second": 36.783,
|
| 721 |
+
"step": 2506
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.0075818036711892,
|
| 725 |
+
"grad_norm": 0.0020196980331093073,
|
| 726 |
+
"learning_rate": 3.69051138043157e-05,
|
| 727 |
+
"loss": 0.0042,
|
| 728 |
+
"step": 2525
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.01755786113328,
|
| 732 |
+
"grad_norm": 0.22435498237609863,
|
| 733 |
+
"learning_rate": 3.672036653857523e-05,
|
| 734 |
+
"loss": 0.0239,
|
| 735 |
+
"step": 2550
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.0275339185953711,
|
| 739 |
+
"grad_norm": 0.0028221237007528543,
|
| 740 |
+
"learning_rate": 3.653561927283476e-05,
|
| 741 |
+
"loss": 0.0048,
|
| 742 |
+
"step": 2575
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.037509976057462,
|
| 746 |
+
"grad_norm": 0.2576161026954651,
|
| 747 |
+
"learning_rate": 3.6350872007094295e-05,
|
| 748 |
+
"loss": 0.0045,
|
| 749 |
+
"step": 2600
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.047486033519553,
|
| 753 |
+
"grad_norm": 0.010775522328913212,
|
| 754 |
+
"learning_rate": 3.616612474135383e-05,
|
| 755 |
+
"loss": 0.0058,
|
| 756 |
+
"step": 2625
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.0574620909816441,
|
| 760 |
+
"grad_norm": 0.006177688017487526,
|
| 761 |
+
"learning_rate": 3.598137747561336e-05,
|
| 762 |
+
"loss": 0.0059,
|
| 763 |
+
"step": 2650
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.067438148443735,
|
| 767 |
+
"grad_norm": 0.19752149283885956,
|
| 768 |
+
"learning_rate": 3.5796630209872895e-05,
|
| 769 |
+
"loss": 0.006,
|
| 770 |
+
"step": 2675
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.077414205905826,
|
| 774 |
+
"grad_norm": 0.0031861320603638887,
|
| 775 |
+
"learning_rate": 3.561188294413243e-05,
|
| 776 |
+
"loss": 0.0026,
|
| 777 |
+
"step": 2700
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.0873902633679169,
|
| 781 |
+
"grad_norm": 0.001234862837009132,
|
| 782 |
+
"learning_rate": 3.542713567839196e-05,
|
| 783 |
+
"loss": 0.0023,
|
| 784 |
+
"step": 2725
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.097366320830008,
|
| 788 |
+
"grad_norm": 0.0011017767246812582,
|
| 789 |
+
"learning_rate": 3.5242388412651494e-05,
|
| 790 |
+
"loss": 0.0041,
|
| 791 |
+
"step": 2750
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.107342378292099,
|
| 795 |
+
"grad_norm": 0.031154826283454895,
|
| 796 |
+
"learning_rate": 3.505764114691103e-05,
|
| 797 |
+
"loss": 0.0035,
|
| 798 |
+
"step": 2775
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.1173184357541899,
|
| 802 |
+
"grad_norm": 0.0014562892029061913,
|
| 803 |
+
"learning_rate": 3.487289388117056e-05,
|
| 804 |
+
"loss": 0.0014,
|
| 805 |
+
"step": 2800
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.127294493216281,
|
| 809 |
+
"grad_norm": 6.060300827026367,
|
| 810 |
+
"learning_rate": 3.4688146615430094e-05,
|
| 811 |
+
"loss": 0.0027,
|
| 812 |
+
"step": 2825
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.1372705506783718,
|
| 816 |
+
"grad_norm": 0.001115105696953833,
|
| 817 |
+
"learning_rate": 3.450339934968963e-05,
|
| 818 |
+
"loss": 0.0057,
|
| 819 |
+
"step": 2850
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.1472466081404629,
|
| 823 |
+
"grad_norm": 0.21018145978450775,
|
| 824 |
+
"learning_rate": 3.431865208394916e-05,
|
| 825 |
+
"loss": 0.0036,
|
| 826 |
+
"step": 2875
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.157222665602554,
|
| 830 |
+
"grad_norm": 0.001687675598077476,
|
| 831 |
+
"learning_rate": 3.413390481820869e-05,
|
| 832 |
+
"loss": 0.0034,
|
| 833 |
+
"step": 2900
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.1671987230646448,
|
| 837 |
+
"grad_norm": 0.0007496728794649243,
|
| 838 |
+
"learning_rate": 3.3949157552468227e-05,
|
| 839 |
+
"loss": 0.0019,
|
| 840 |
+
"step": 2925
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.1771747805267359,
|
| 844 |
+
"grad_norm": 0.04825098440051079,
|
| 845 |
+
"learning_rate": 3.376441028672776e-05,
|
| 846 |
+
"loss": 0.0015,
|
| 847 |
+
"step": 2950
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.1871508379888267,
|
| 851 |
+
"grad_norm": 0.022615255787968636,
|
| 852 |
+
"learning_rate": 3.357966302098729e-05,
|
| 853 |
+
"loss": 0.0256,
|
| 854 |
+
"step": 2975
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.1971268954509178,
|
| 858 |
+
"grad_norm": 0.00691673718392849,
|
| 859 |
+
"learning_rate": 3.3394915755246826e-05,
|
| 860 |
+
"loss": 0.0022,
|
| 861 |
+
"step": 3000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.2071029529130088,
|
| 865 |
+
"grad_norm": 0.013947910629212856,
|
| 866 |
+
"learning_rate": 3.321016848950635e-05,
|
| 867 |
+
"loss": 0.0049,
|
| 868 |
+
"step": 3025
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.2170790103750997,
|
| 872 |
+
"grad_norm": 0.23668746650218964,
|
| 873 |
+
"learning_rate": 3.302542122376589e-05,
|
| 874 |
+
"loss": 0.0046,
|
| 875 |
+
"step": 3050
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.2270550678371908,
|
| 879 |
+
"grad_norm": 0.0029790853150188923,
|
| 880 |
+
"learning_rate": 3.2840673958025426e-05,
|
| 881 |
+
"loss": 0.0065,
|
| 882 |
+
"step": 3075
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.2370311252992816,
|
| 886 |
+
"grad_norm": 0.0019055495504289865,
|
| 887 |
+
"learning_rate": 3.2663316582914576e-05,
|
| 888 |
+
"loss": 0.0027,
|
| 889 |
+
"step": 3100
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.2470071827613727,
|
| 893 |
+
"grad_norm": 0.0017437831265851855,
|
| 894 |
+
"learning_rate": 3.247856931717411e-05,
|
| 895 |
+
"loss": 0.0046,
|
| 896 |
+
"step": 3125
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.2569832402234637,
|
| 900 |
+
"grad_norm": 0.03664908930659294,
|
| 901 |
+
"learning_rate": 3.229382205143364e-05,
|
| 902 |
+
"loss": 0.0279,
|
| 903 |
+
"step": 3150
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.2669592976855546,
|
| 907 |
+
"grad_norm": 0.003305430756881833,
|
| 908 |
+
"learning_rate": 3.210907478569317e-05,
|
| 909 |
+
"loss": 0.0026,
|
| 910 |
+
"step": 3175
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.2769353551476457,
|
| 914 |
+
"grad_norm": 0.0025117206387221813,
|
| 915 |
+
"learning_rate": 3.192432751995271e-05,
|
| 916 |
+
"loss": 0.002,
|
| 917 |
+
"step": 3200
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.2869114126097365,
|
| 921 |
+
"grad_norm": 0.0020391775760799646,
|
| 922 |
+
"learning_rate": 3.1739580254212235e-05,
|
| 923 |
+
"loss": 0.0028,
|
| 924 |
+
"step": 3225
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.2968874700718276,
|
| 928 |
+
"grad_norm": 0.21820971369743347,
|
| 929 |
+
"learning_rate": 3.1554832988471775e-05,
|
| 930 |
+
"loss": 0.0008,
|
| 931 |
+
"step": 3250
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 1.3068635275339187,
|
| 935 |
+
"grad_norm": 0.002053961856290698,
|
| 936 |
+
"learning_rate": 3.137008572273131e-05,
|
| 937 |
+
"loss": 0.0089,
|
| 938 |
+
"step": 3275
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.3168395849960095,
|
| 942 |
+
"grad_norm": 0.05145469307899475,
|
| 943 |
+
"learning_rate": 3.1185338456990835e-05,
|
| 944 |
+
"loss": 0.0038,
|
| 945 |
+
"step": 3300
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.3268156424581006,
|
| 949 |
+
"grad_norm": 0.001505004009231925,
|
| 950 |
+
"learning_rate": 3.1000591191250375e-05,
|
| 951 |
+
"loss": 0.0051,
|
| 952 |
+
"step": 3325
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.3367916999201914,
|
| 956 |
+
"grad_norm": 0.28836873173713684,
|
| 957 |
+
"learning_rate": 3.08158439255099e-05,
|
| 958 |
+
"loss": 0.0032,
|
| 959 |
+
"step": 3350
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.3467677573822825,
|
| 963 |
+
"grad_norm": 0.004164043348282576,
|
| 964 |
+
"learning_rate": 3.0631096659769434e-05,
|
| 965 |
+
"loss": 0.0035,
|
| 966 |
+
"step": 3375
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 1.3567438148443736,
|
| 970 |
+
"grad_norm": 0.21263979375362396,
|
| 971 |
+
"learning_rate": 3.044634939402897e-05,
|
| 972 |
+
"loss": 0.0036,
|
| 973 |
+
"step": 3400
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 1.3667198723064644,
|
| 977 |
+
"grad_norm": 0.0012820661067962646,
|
| 978 |
+
"learning_rate": 3.02616021282885e-05,
|
| 979 |
+
"loss": 0.0031,
|
| 980 |
+
"step": 3425
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 1.3766959297685555,
|
| 984 |
+
"grad_norm": 0.001078963279724121,
|
| 985 |
+
"learning_rate": 3.0076854862548037e-05,
|
| 986 |
+
"loss": 0.0028,
|
| 987 |
+
"step": 3450
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 1.3866719872306463,
|
| 991 |
+
"grad_norm": 0.0011286437511444092,
|
| 992 |
+
"learning_rate": 2.9892107596807567e-05,
|
| 993 |
+
"loss": 0.0018,
|
| 994 |
+
"step": 3475
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.3966480446927374,
|
| 998 |
+
"grad_norm": 0.2223164588212967,
|
| 999 |
+
"learning_rate": 2.9707360331067103e-05,
|
| 1000 |
+
"loss": 0.0053,
|
| 1001 |
+
"step": 3500
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.4066241021548285,
|
| 1005 |
+
"grad_norm": 0.0014811749570071697,
|
| 1006 |
+
"learning_rate": 2.9522613065326633e-05,
|
| 1007 |
+
"loss": 0.0037,
|
| 1008 |
+
"step": 3525
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 1.4166001596169193,
|
| 1012 |
+
"grad_norm": 0.0008042556582950056,
|
| 1013 |
+
"learning_rate": 2.9337865799586166e-05,
|
| 1014 |
+
"loss": 0.0035,
|
| 1015 |
+
"step": 3550
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.4265762170790104,
|
| 1019 |
+
"grad_norm": 0.0018880123971030116,
|
| 1020 |
+
"learning_rate": 2.9153118533845703e-05,
|
| 1021 |
+
"loss": 0.0027,
|
| 1022 |
+
"step": 3575
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.4365522745411012,
|
| 1026 |
+
"grad_norm": 0.0008701224578544497,
|
| 1027 |
+
"learning_rate": 2.8968371268105233e-05,
|
| 1028 |
+
"loss": 0.0034,
|
| 1029 |
+
"step": 3600
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.4465283320031923,
|
| 1033 |
+
"grad_norm": 0.16421648859977722,
|
| 1034 |
+
"learning_rate": 2.8783624002364766e-05,
|
| 1035 |
+
"loss": 0.0015,
|
| 1036 |
+
"step": 3625
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.4565043894652834,
|
| 1040 |
+
"grad_norm": 0.045492418110370636,
|
| 1041 |
+
"learning_rate": 2.8598876736624296e-05,
|
| 1042 |
+
"loss": 0.0092,
|
| 1043 |
+
"step": 3650
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 1.4664804469273742,
|
| 1047 |
+
"grad_norm": 0.22111371159553528,
|
| 1048 |
+
"learning_rate": 2.8414129470883832e-05,
|
| 1049 |
+
"loss": 0.0034,
|
| 1050 |
+
"step": 3675
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.4764565043894653,
|
| 1054 |
+
"grad_norm": 0.005951441824436188,
|
| 1055 |
+
"learning_rate": 2.822938220514337e-05,
|
| 1056 |
+
"loss": 0.007,
|
| 1057 |
+
"step": 3700
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.4864325618515561,
|
| 1061 |
+
"grad_norm": 0.5036889314651489,
|
| 1062 |
+
"learning_rate": 2.80446349394029e-05,
|
| 1063 |
+
"loss": 0.0065,
|
| 1064 |
+
"step": 3725
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.4964086193136472,
|
| 1068 |
+
"grad_norm": 0.008522866293787956,
|
| 1069 |
+
"learning_rate": 2.7859887673662432e-05,
|
| 1070 |
+
"loss": 0.0028,
|
| 1071 |
+
"step": 3750
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.5063846767757383,
|
| 1075 |
+
"grad_norm": 0.025371083989739418,
|
| 1076 |
+
"learning_rate": 2.767514040792196e-05,
|
| 1077 |
+
"loss": 0.0261,
|
| 1078 |
+
"step": 3775
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.5163607342378294,
|
| 1082 |
+
"grad_norm": 0.16779935359954834,
|
| 1083 |
+
"learning_rate": 2.7490393142181498e-05,
|
| 1084 |
+
"loss": 0.0058,
|
| 1085 |
+
"step": 3800
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 1.5263367916999202,
|
| 1089 |
+
"grad_norm": 0.03642382472753525,
|
| 1090 |
+
"learning_rate": 2.7305645876441028e-05,
|
| 1091 |
+
"loss": 0.0187,
|
| 1092 |
+
"step": 3825
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 1.536312849162011,
|
| 1096 |
+
"grad_norm": 0.025805264711380005,
|
| 1097 |
+
"learning_rate": 2.712089861070056e-05,
|
| 1098 |
+
"loss": 0.0031,
|
| 1099 |
+
"step": 3850
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 1.5462889066241021,
|
| 1103 |
+
"grad_norm": 0.009107539430260658,
|
| 1104 |
+
"learning_rate": 2.6936151344960098e-05,
|
| 1105 |
+
"loss": 0.0019,
|
| 1106 |
+
"step": 3875
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.5562649640861932,
|
| 1110 |
+
"grad_norm": 0.09119360148906708,
|
| 1111 |
+
"learning_rate": 2.6751404079219627e-05,
|
| 1112 |
+
"loss": 0.0014,
|
| 1113 |
+
"step": 3900
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.5662410215482843,
|
| 1117 |
+
"grad_norm": 0.010866549797356129,
|
| 1118 |
+
"learning_rate": 2.6566656813479164e-05,
|
| 1119 |
+
"loss": 0.0002,
|
| 1120 |
+
"step": 3925
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 1.576217079010375,
|
| 1124 |
+
"grad_norm": 0.0031453550327569246,
|
| 1125 |
+
"learning_rate": 2.6381909547738694e-05,
|
| 1126 |
+
"loss": 0.0032,
|
| 1127 |
+
"step": 3950
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.586193136472466,
|
| 1131 |
+
"grad_norm": 0.13580499589443207,
|
| 1132 |
+
"learning_rate": 2.6197162281998227e-05,
|
| 1133 |
+
"loss": 0.0185,
|
| 1134 |
+
"step": 3975
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.596169193934557,
|
| 1138 |
+
"grad_norm": 0.004639145918190479,
|
| 1139 |
+
"learning_rate": 2.601980490688738e-05,
|
| 1140 |
+
"loss": 0.0124,
|
| 1141 |
+
"step": 4000
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 1.606145251396648,
|
| 1145 |
+
"grad_norm": 0.015105273574590683,
|
| 1146 |
+
"learning_rate": 2.5835057641146914e-05,
|
| 1147 |
+
"loss": 0.0073,
|
| 1148 |
+
"step": 4025
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 1.6161213088587392,
|
| 1152 |
+
"grad_norm": 0.007127686869353056,
|
| 1153 |
+
"learning_rate": 2.5650310375406444e-05,
|
| 1154 |
+
"loss": 0.0021,
|
| 1155 |
+
"step": 4050
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.62609736632083,
|
| 1159 |
+
"grad_norm": 0.010529367253184319,
|
| 1160 |
+
"learning_rate": 2.546556310966598e-05,
|
| 1161 |
+
"loss": 0.0053,
|
| 1162 |
+
"step": 4075
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.6360734237829209,
|
| 1166 |
+
"grad_norm": 0.2831868529319763,
|
| 1167 |
+
"learning_rate": 2.528081584392551e-05,
|
| 1168 |
+
"loss": 0.0015,
|
| 1169 |
+
"step": 4100
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 1.646049481245012,
|
| 1173 |
+
"grad_norm": 0.0013676858507096767,
|
| 1174 |
+
"learning_rate": 2.5096068578185043e-05,
|
| 1175 |
+
"loss": 0.0013,
|
| 1176 |
+
"step": 4125
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 1.656025538707103,
|
| 1180 |
+
"grad_norm": 0.0011926931329071522,
|
| 1181 |
+
"learning_rate": 2.4911321312444576e-05,
|
| 1182 |
+
"loss": 0.0002,
|
| 1183 |
+
"step": 4150
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 1.666001596169194,
|
| 1187 |
+
"grad_norm": 0.0013146502897143364,
|
| 1188 |
+
"learning_rate": 2.472657404670411e-05,
|
| 1189 |
+
"loss": 0.0022,
|
| 1190 |
+
"step": 4175
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.675977653631285,
|
| 1194 |
+
"grad_norm": 0.20606344938278198,
|
| 1195 |
+
"learning_rate": 2.4541826780963643e-05,
|
| 1196 |
+
"loss": 0.0045,
|
| 1197 |
+
"step": 4200
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.6859537110933758,
|
| 1201 |
+
"grad_norm": 0.5096789002418518,
|
| 1202 |
+
"learning_rate": 2.4357079515223176e-05,
|
| 1203 |
+
"loss": 0.0049,
|
| 1204 |
+
"step": 4225
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 1.6959297685554668,
|
| 1208 |
+
"grad_norm": 0.8010555505752563,
|
| 1209 |
+
"learning_rate": 2.417233224948271e-05,
|
| 1210 |
+
"loss": 0.0023,
|
| 1211 |
+
"step": 4250
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 1.705905826017558,
|
| 1215 |
+
"grad_norm": 0.0023227622732520103,
|
| 1216 |
+
"learning_rate": 2.3987584983742242e-05,
|
| 1217 |
+
"loss": 0.0035,
|
| 1218 |
+
"step": 4275
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.715881883479649,
|
| 1222 |
+
"grad_norm": 0.002598476829007268,
|
| 1223 |
+
"learning_rate": 2.3802837718001775e-05,
|
| 1224 |
+
"loss": 0.0033,
|
| 1225 |
+
"step": 4300
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.7258579409417398,
|
| 1229 |
+
"grad_norm": 0.0010407950030639768,
|
| 1230 |
+
"learning_rate": 2.361809045226131e-05,
|
| 1231 |
+
"loss": 0.0017,
|
| 1232 |
+
"step": 4325
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.7358339984038307,
|
| 1236 |
+
"grad_norm": 0.0009124928619712591,
|
| 1237 |
+
"learning_rate": 2.343334318652084e-05,
|
| 1238 |
+
"loss": 0.0021,
|
| 1239 |
+
"step": 4350
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.7458100558659218,
|
| 1243 |
+
"grad_norm": 0.0009513483964838088,
|
| 1244 |
+
"learning_rate": 2.324859592078037e-05,
|
| 1245 |
+
"loss": 0.0046,
|
| 1246 |
+
"step": 4375
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.7557861133280128,
|
| 1250 |
+
"grad_norm": 0.003370137419551611,
|
| 1251 |
+
"learning_rate": 2.3063848655039908e-05,
|
| 1252 |
+
"loss": 0.001,
|
| 1253 |
+
"step": 4400
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 1.765762170790104,
|
| 1257 |
+
"grad_norm": 0.019700469449162483,
|
| 1258 |
+
"learning_rate": 2.287910138929944e-05,
|
| 1259 |
+
"loss": 0.0035,
|
| 1260 |
+
"step": 4425
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 1.7757382282521947,
|
| 1264 |
+
"grad_norm": 0.39680203795433044,
|
| 1265 |
+
"learning_rate": 2.269435412355897e-05,
|
| 1266 |
+
"loss": 0.003,
|
| 1267 |
+
"step": 4450
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 1.7857142857142856,
|
| 1271 |
+
"grad_norm": 0.0012863815063610673,
|
| 1272 |
+
"learning_rate": 2.2509606857818504e-05,
|
| 1273 |
+
"loss": 0.0012,
|
| 1274 |
+
"step": 4475
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.7956903431763767,
|
| 1278 |
+
"grad_norm": 0.10338558256626129,
|
| 1279 |
+
"learning_rate": 2.2324859592078037e-05,
|
| 1280 |
+
"loss": 0.0002,
|
| 1281 |
+
"step": 4500
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.8056664006384677,
|
| 1285 |
+
"grad_norm": 0.0006012976518832147,
|
| 1286 |
+
"learning_rate": 2.2140112326337574e-05,
|
| 1287 |
+
"loss": 0.0025,
|
| 1288 |
+
"step": 4525
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 1.8156424581005588,
|
| 1292 |
+
"grad_norm": 0.0015600507613271475,
|
| 1293 |
+
"learning_rate": 2.1955365060597104e-05,
|
| 1294 |
+
"loss": 0.0045,
|
| 1295 |
+
"step": 4550
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.8256185155626496,
|
| 1299 |
+
"grad_norm": 0.0010370941599830985,
|
| 1300 |
+
"learning_rate": 2.1770617794856637e-05,
|
| 1301 |
+
"loss": 0.0039,
|
| 1302 |
+
"step": 4575
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 1.8355945730247405,
|
| 1306 |
+
"grad_norm": 0.001004413003101945,
|
| 1307 |
+
"learning_rate": 2.158587052911617e-05,
|
| 1308 |
+
"loss": 0.0013,
|
| 1309 |
+
"step": 4600
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 1.8455706304868316,
|
| 1313 |
+
"grad_norm": 0.0008648243965581059,
|
| 1314 |
+
"learning_rate": 2.1401123263375703e-05,
|
| 1315 |
+
"loss": 0.0013,
|
| 1316 |
+
"step": 4625
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 1.8555466879489226,
|
| 1320 |
+
"grad_norm": 0.0005984778981655836,
|
| 1321 |
+
"learning_rate": 2.1216375997635237e-05,
|
| 1322 |
+
"loss": 0.003,
|
| 1323 |
+
"step": 4650
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 1.8655227454110137,
|
| 1327 |
+
"grad_norm": 0.022275598719716072,
|
| 1328 |
+
"learning_rate": 2.103162873189477e-05,
|
| 1329 |
+
"loss": 0.0096,
|
| 1330 |
+
"step": 4675
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.8754988028731046,
|
| 1334 |
+
"grad_norm": 0.001242508296854794,
|
| 1335 |
+
"learning_rate": 2.0846881466154303e-05,
|
| 1336 |
+
"loss": 0.0009,
|
| 1337 |
+
"step": 4700
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.8854748603351954,
|
| 1341 |
+
"grad_norm": 0.12456066906452179,
|
| 1342 |
+
"learning_rate": 2.0662134200413836e-05,
|
| 1343 |
+
"loss": 0.0009,
|
| 1344 |
+
"step": 4725
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 1.8954509177972865,
|
| 1348 |
+
"grad_norm": 0.00505377072840929,
|
| 1349 |
+
"learning_rate": 2.047738693467337e-05,
|
| 1350 |
+
"loss": 0.0009,
|
| 1351 |
+
"step": 4750
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 1.9054269752593775,
|
| 1355 |
+
"grad_norm": 0.0009244637913070619,
|
| 1356 |
+
"learning_rate": 2.02926396689329e-05,
|
| 1357 |
+
"loss": 0.0022,
|
| 1358 |
+
"step": 4775
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 1.9154030327214686,
|
| 1362 |
+
"grad_norm": 0.0006068416405469179,
|
| 1363 |
+
"learning_rate": 2.0107892403192432e-05,
|
| 1364 |
+
"loss": 0.0021,
|
| 1365 |
+
"step": 4800
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 1.9253790901835595,
|
| 1369 |
+
"grad_norm": 0.0009826399618759751,
|
| 1370 |
+
"learning_rate": 1.992314513745197e-05,
|
| 1371 |
+
"loss": 0.0025,
|
| 1372 |
+
"step": 4825
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 1.9353551476456503,
|
| 1376 |
+
"grad_norm": 0.0008530529448762536,
|
| 1377 |
+
"learning_rate": 1.9738397871711502e-05,
|
| 1378 |
+
"loss": 0.0011,
|
| 1379 |
+
"step": 4850
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 1.9453312051077414,
|
| 1383 |
+
"grad_norm": 0.000995517591945827,
|
| 1384 |
+
"learning_rate": 1.9553650605971032e-05,
|
| 1385 |
+
"loss": 0.0012,
|
| 1386 |
+
"step": 4875
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 1.9553072625698324,
|
| 1390 |
+
"grad_norm": 0.3080498278141022,
|
| 1391 |
+
"learning_rate": 1.9368903340230565e-05,
|
| 1392 |
+
"loss": 0.0193,
|
| 1393 |
+
"step": 4900
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 1.9652833200319235,
|
| 1397 |
+
"grad_norm": 0.01077496912330389,
|
| 1398 |
+
"learning_rate": 1.9184156074490098e-05,
|
| 1399 |
+
"loss": 0.0034,
|
| 1400 |
+
"step": 4925
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 1.9752593774940144,
|
| 1404 |
+
"grad_norm": 0.0010128016583621502,
|
| 1405 |
+
"learning_rate": 1.899940880874963e-05,
|
| 1406 |
+
"loss": 0.0025,
|
| 1407 |
+
"step": 4950
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 1.9852354349561052,
|
| 1411 |
+
"grad_norm": 0.0010960666695609689,
|
| 1412 |
+
"learning_rate": 1.8814661543009164e-05,
|
| 1413 |
+
"loss": 0.0028,
|
| 1414 |
+
"step": 4975
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 1.9952114924181963,
|
| 1418 |
+
"grad_norm": 0.5445042848587036,
|
| 1419 |
+
"learning_rate": 1.8629914277268698e-05,
|
| 1420 |
+
"loss": 0.0033,
|
| 1421 |
+
"step": 5000
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 2.0,
|
| 1425 |
+
"eval_accuracy": 0.9979191075961726,
|
| 1426 |
+
"eval_f1": 0.9954595073486371,
|
| 1427 |
+
"eval_loss": 0.00481545552611351,
|
| 1428 |
+
"eval_precision": 0.9975901322256397,
|
| 1429 |
+
"eval_recall": 0.9933379641323566,
|
| 1430 |
+
"eval_runtime": 7.1062,
|
| 1431 |
+
"eval_samples_per_second": 705.299,
|
| 1432 |
+
"eval_steps_per_second": 44.187,
|
| 1433 |
+
"step": 5012
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 2.0051875498802874,
|
| 1437 |
+
"grad_norm": 0.0006674908217974007,
|
| 1438 |
+
"learning_rate": 1.844516701152823e-05,
|
| 1439 |
+
"loss": 0.0017,
|
| 1440 |
+
"step": 5025
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 2.0151636073423784,
|
| 1444 |
+
"grad_norm": 0.0014617441920563579,
|
| 1445 |
+
"learning_rate": 1.8260419745787764e-05,
|
| 1446 |
+
"loss": 0.0018,
|
| 1447 |
+
"step": 5050
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 2.0251396648044695,
|
| 1451 |
+
"grad_norm": 0.3307023346424103,
|
| 1452 |
+
"learning_rate": 1.8075672480047294e-05,
|
| 1453 |
+
"loss": 0.0042,
|
| 1454 |
+
"step": 5075
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 2.03511572226656,
|
| 1458 |
+
"grad_norm": 0.0007593869231641293,
|
| 1459 |
+
"learning_rate": 1.7890925214306827e-05,
|
| 1460 |
+
"loss": 0.0012,
|
| 1461 |
+
"step": 5100
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 2.045091779728651,
|
| 1465 |
+
"grad_norm": 0.0006126170628704131,
|
| 1466 |
+
"learning_rate": 1.7706177948566364e-05,
|
| 1467 |
+
"loss": 0.0028,
|
| 1468 |
+
"step": 5125
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 2.0550678371907423,
|
| 1472 |
+
"grad_norm": 0.0018221965292468667,
|
| 1473 |
+
"learning_rate": 1.7521430682825897e-05,
|
| 1474 |
+
"loss": 0.0155,
|
| 1475 |
+
"step": 5150
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 2.0650438946528333,
|
| 1479 |
+
"grad_norm": 0.2457825094461441,
|
| 1480 |
+
"learning_rate": 1.7336683417085427e-05,
|
| 1481 |
+
"loss": 0.0021,
|
| 1482 |
+
"step": 5175
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 2.075019952114924,
|
| 1486 |
+
"grad_norm": 0.0010028661927208304,
|
| 1487 |
+
"learning_rate": 1.715193615134496e-05,
|
| 1488 |
+
"loss": 0.0026,
|
| 1489 |
+
"step": 5200
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 2.084996009577015,
|
| 1493 |
+
"grad_norm": 0.0007341373711824417,
|
| 1494 |
+
"learning_rate": 1.6967188885604493e-05,
|
| 1495 |
+
"loss": 0.0011,
|
| 1496 |
+
"step": 5225
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 2.094972067039106,
|
| 1500 |
+
"grad_norm": 0.17410235106945038,
|
| 1501 |
+
"learning_rate": 1.6782441619864026e-05,
|
| 1502 |
+
"loss": 0.0025,
|
| 1503 |
+
"step": 5250
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 2.104948124501197,
|
| 1507 |
+
"grad_norm": 0.0018121938919648528,
|
| 1508 |
+
"learning_rate": 1.659769435412356e-05,
|
| 1509 |
+
"loss": 0.0017,
|
| 1510 |
+
"step": 5275
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 2.1149241819632882,
|
| 1514 |
+
"grad_norm": 0.0012474131071940064,
|
| 1515 |
+
"learning_rate": 1.6412947088383092e-05,
|
| 1516 |
+
"loss": 0.0011,
|
| 1517 |
+
"step": 5300
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 2.1249002394253793,
|
| 1521 |
+
"grad_norm": 0.0014015095075592399,
|
| 1522 |
+
"learning_rate": 1.6228199822642626e-05,
|
| 1523 |
+
"loss": 0.0014,
|
| 1524 |
+
"step": 5325
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 2.13487629688747,
|
| 1528 |
+
"grad_norm": 0.0009790038457140326,
|
| 1529 |
+
"learning_rate": 1.604345255690216e-05,
|
| 1530 |
+
"loss": 0.0021,
|
| 1531 |
+
"step": 5350
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 2.144852354349561,
|
| 1535 |
+
"grad_norm": 0.0006486671045422554,
|
| 1536 |
+
"learning_rate": 1.5858705291161692e-05,
|
| 1537 |
+
"loss": 0.0029,
|
| 1538 |
+
"step": 5375
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 2.154828411811652,
|
| 1542 |
+
"grad_norm": 0.0005367296980693936,
|
| 1543 |
+
"learning_rate": 1.5673958025421222e-05,
|
| 1544 |
+
"loss": 0.0027,
|
| 1545 |
+
"step": 5400
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 2.164804469273743,
|
| 1549 |
+
"grad_norm": 0.0005186652415432036,
|
| 1550 |
+
"learning_rate": 1.5489210759680758e-05,
|
| 1551 |
+
"loss": 0.0008,
|
| 1552 |
+
"step": 5425
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 2.1747805267358338,
|
| 1556 |
+
"grad_norm": 0.0010013518622145057,
|
| 1557 |
+
"learning_rate": 1.530446349394029e-05,
|
| 1558 |
+
"loss": 0.0128,
|
| 1559 |
+
"step": 5450
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 2.184756584197925,
|
| 1563 |
+
"grad_norm": 0.03524576872587204,
|
| 1564 |
+
"learning_rate": 1.5119716228199823e-05,
|
| 1565 |
+
"loss": 0.0028,
|
| 1566 |
+
"step": 5475
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 2.194732641660016,
|
| 1570 |
+
"grad_norm": 0.0013949783751741052,
|
| 1571 |
+
"learning_rate": 1.4934968962459356e-05,
|
| 1572 |
+
"loss": 0.0033,
|
| 1573 |
+
"step": 5500
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 2.204708699122107,
|
| 1577 |
+
"grad_norm": 0.0004396065778564662,
|
| 1578 |
+
"learning_rate": 1.4750221696718888e-05,
|
| 1579 |
+
"loss": 0.0018,
|
| 1580 |
+
"step": 5525
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 2.214684756584198,
|
| 1584 |
+
"grad_norm": 0.0007160959648899734,
|
| 1585 |
+
"learning_rate": 1.4565474430978424e-05,
|
| 1586 |
+
"loss": 0.0008,
|
| 1587 |
+
"step": 5550
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 2.224660814046289,
|
| 1591 |
+
"grad_norm": 0.0008434823248535395,
|
| 1592 |
+
"learning_rate": 1.4380727165237956e-05,
|
| 1593 |
+
"loss": 0.0024,
|
| 1594 |
+
"step": 5575
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 2.2346368715083798,
|
| 1598 |
+
"grad_norm": 0.0005646327044814825,
|
| 1599 |
+
"learning_rate": 1.4195979899497489e-05,
|
| 1600 |
+
"loss": 0.0006,
|
| 1601 |
+
"step": 5600
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 2.244612928970471,
|
| 1605 |
+
"grad_norm": 1.379267692565918,
|
| 1606 |
+
"learning_rate": 1.401123263375702e-05,
|
| 1607 |
+
"loss": 0.0017,
|
| 1608 |
+
"step": 5625
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 2.254588986432562,
|
| 1612 |
+
"grad_norm": 0.0018891971558332443,
|
| 1613 |
+
"learning_rate": 1.3826485368016554e-05,
|
| 1614 |
+
"loss": 0.001,
|
| 1615 |
+
"step": 5650
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 2.264565043894653,
|
| 1619 |
+
"grad_norm": 0.536622941493988,
|
| 1620 |
+
"learning_rate": 1.3641738102276087e-05,
|
| 1621 |
+
"loss": 0.0036,
|
| 1622 |
+
"step": 5675
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 2.2745411013567436,
|
| 1626 |
+
"grad_norm": 0.00465416768565774,
|
| 1627 |
+
"learning_rate": 1.3456990836535622e-05,
|
| 1628 |
+
"loss": 0.0317,
|
| 1629 |
+
"step": 5700
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 2.2845171588188347,
|
| 1633 |
+
"grad_norm": 0.06848159432411194,
|
| 1634 |
+
"learning_rate": 1.3272243570795153e-05,
|
| 1635 |
+
"loss": 0.0039,
|
| 1636 |
+
"step": 5725
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 2.2944932162809257,
|
| 1640 |
+
"grad_norm": 0.5269453525543213,
|
| 1641 |
+
"learning_rate": 1.3087496305054686e-05,
|
| 1642 |
+
"loss": 0.0029,
|
| 1643 |
+
"step": 5750
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.304469273743017,
|
| 1647 |
+
"grad_norm": 0.0010541366646066308,
|
| 1648 |
+
"learning_rate": 1.290274903931422e-05,
|
| 1649 |
+
"loss": 0.002,
|
| 1650 |
+
"step": 5775
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.314445331205108,
|
| 1654 |
+
"grad_norm": 0.2798452377319336,
|
| 1655 |
+
"learning_rate": 1.2718001773573751e-05,
|
| 1656 |
+
"loss": 0.0185,
|
| 1657 |
+
"step": 5800
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.324421388667199,
|
| 1661 |
+
"grad_norm": 0.005444707814604044,
|
| 1662 |
+
"learning_rate": 1.2533254507833284e-05,
|
| 1663 |
+
"loss": 0.0029,
|
| 1664 |
+
"step": 5825
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.3343974461292896,
|
| 1668 |
+
"grad_norm": 0.002500380389392376,
|
| 1669 |
+
"learning_rate": 1.2348507242092817e-05,
|
| 1670 |
+
"loss": 0.0027,
|
| 1671 |
+
"step": 5850
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.3443735035913806,
|
| 1675 |
+
"grad_norm": 0.00044498228817246854,
|
| 1676 |
+
"learning_rate": 1.216375997635235e-05,
|
| 1677 |
+
"loss": 0.0017,
|
| 1678 |
+
"step": 5875
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.3543495610534717,
|
| 1682 |
+
"grad_norm": 0.019100671634078026,
|
| 1683 |
+
"learning_rate": 1.1979012710611884e-05,
|
| 1684 |
+
"loss": 0.0026,
|
| 1685 |
+
"step": 5900
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 2.3643256185155628,
|
| 1689 |
+
"grad_norm": 0.003481657709926367,
|
| 1690 |
+
"learning_rate": 1.1794265444871417e-05,
|
| 1691 |
+
"loss": 0.0015,
|
| 1692 |
+
"step": 5925
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 2.3743016759776534,
|
| 1696 |
+
"grad_norm": 0.011755410581827164,
|
| 1697 |
+
"learning_rate": 1.1609518179130948e-05,
|
| 1698 |
+
"loss": 0.0022,
|
| 1699 |
+
"step": 5950
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 2.3842777334397445,
|
| 1703 |
+
"grad_norm": 0.0014704465866088867,
|
| 1704 |
+
"learning_rate": 1.1424770913390483e-05,
|
| 1705 |
+
"loss": 0.0021,
|
| 1706 |
+
"step": 5975
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 2.3942537909018355,
|
| 1710 |
+
"grad_norm": 0.0007962892414070666,
|
| 1711 |
+
"learning_rate": 1.1240023647650015e-05,
|
| 1712 |
+
"loss": 0.0027,
|
| 1713 |
+
"step": 6000
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 2.4042298483639266,
|
| 1717 |
+
"grad_norm": 0.6859905123710632,
|
| 1718 |
+
"learning_rate": 1.105527638190955e-05,
|
| 1719 |
+
"loss": 0.0029,
|
| 1720 |
+
"step": 6025
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 2.4142059058260177,
|
| 1724 |
+
"grad_norm": 0.0015323414700105786,
|
| 1725 |
+
"learning_rate": 1.0870529116169081e-05,
|
| 1726 |
+
"loss": 0.0014,
|
| 1727 |
+
"step": 6050
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 2.4241819632881088,
|
| 1731 |
+
"grad_norm": 0.24034078419208527,
|
| 1732 |
+
"learning_rate": 1.0685781850428614e-05,
|
| 1733 |
+
"loss": 0.0028,
|
| 1734 |
+
"step": 6075
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 2.4341580207501994,
|
| 1738 |
+
"grad_norm": 0.0006519823218695819,
|
| 1739 |
+
"learning_rate": 1.0501034584688147e-05,
|
| 1740 |
+
"loss": 0.001,
|
| 1741 |
+
"step": 6100
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 2.4441340782122905,
|
| 1745 |
+
"grad_norm": 0.0011842703679576516,
|
| 1746 |
+
"learning_rate": 1.031628731894768e-05,
|
| 1747 |
+
"loss": 0.0023,
|
| 1748 |
+
"step": 6125
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 2.4541101356743815,
|
| 1752 |
+
"grad_norm": 0.0005461367545649409,
|
| 1753 |
+
"learning_rate": 1.0131540053207212e-05,
|
| 1754 |
+
"loss": 0.001,
|
| 1755 |
+
"step": 6150
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 2.4640861931364726,
|
| 1759 |
+
"grad_norm": 0.0004023006185889244,
|
| 1760 |
+
"learning_rate": 9.946792787466747e-06,
|
| 1761 |
+
"loss": 0.0011,
|
| 1762 |
+
"step": 6175
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 2.474062250598563,
|
| 1766 |
+
"grad_norm": 0.0007840055041015148,
|
| 1767 |
+
"learning_rate": 9.762045521726278e-06,
|
| 1768 |
+
"loss": 0.0028,
|
| 1769 |
+
"step": 6200
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 2.4840383080606543,
|
| 1773 |
+
"grad_norm": 0.0012692664749920368,
|
| 1774 |
+
"learning_rate": 9.577298255985812e-06,
|
| 1775 |
+
"loss": 0.0024,
|
| 1776 |
+
"step": 6225
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 2.4940143655227454,
|
| 1780 |
+
"grad_norm": 0.0006806539604440331,
|
| 1781 |
+
"learning_rate": 9.392550990245345e-06,
|
| 1782 |
+
"loss": 0.0015,
|
| 1783 |
+
"step": 6250
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 2.5039904229848364,
|
| 1787 |
+
"grad_norm": 0.0008270195103250444,
|
| 1788 |
+
"learning_rate": 9.207803724504878e-06,
|
| 1789 |
+
"loss": 0.0028,
|
| 1790 |
+
"step": 6275
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 2.5139664804469275,
|
| 1794 |
+
"grad_norm": 0.0004925117245875299,
|
| 1795 |
+
"learning_rate": 9.023056458764411e-06,
|
| 1796 |
+
"loss": 0.0003,
|
| 1797 |
+
"step": 6300
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 2.5239425379090186,
|
| 1801 |
+
"grad_norm": 0.011834337376058102,
|
| 1802 |
+
"learning_rate": 8.838309193023944e-06,
|
| 1803 |
+
"loss": 0.0036,
|
| 1804 |
+
"step": 6325
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 2.533918595371109,
|
| 1808 |
+
"grad_norm": 0.0009045172482728958,
|
| 1809 |
+
"learning_rate": 8.653561927283477e-06,
|
| 1810 |
+
"loss": 0.0016,
|
| 1811 |
+
"step": 6350
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 2.5438946528332003,
|
| 1815 |
+
"grad_norm": 0.002521322574466467,
|
| 1816 |
+
"learning_rate": 8.468814661543009e-06,
|
| 1817 |
+
"loss": 0.0169,
|
| 1818 |
+
"step": 6375
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 2.5538707102952913,
|
| 1822 |
+
"grad_norm": 0.0016536839539185166,
|
| 1823 |
+
"learning_rate": 8.284067395802544e-06,
|
| 1824 |
+
"loss": 0.0004,
|
| 1825 |
+
"step": 6400
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 2.5638467677573824,
|
| 1829 |
+
"grad_norm": 0.0008687068475410342,
|
| 1830 |
+
"learning_rate": 8.099320130062075e-06,
|
| 1831 |
+
"loss": 0.0015,
|
| 1832 |
+
"step": 6425
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 2.573822825219473,
|
| 1836 |
+
"grad_norm": 0.0007957812049426138,
|
| 1837 |
+
"learning_rate": 7.914572864321608e-06,
|
| 1838 |
+
"loss": 0.0025,
|
| 1839 |
+
"step": 6450
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 2.583798882681564,
|
| 1843 |
+
"grad_norm": 0.0007942553493194282,
|
| 1844 |
+
"learning_rate": 7.729825598581142e-06,
|
| 1845 |
+
"loss": 0.0011,
|
| 1846 |
+
"step": 6475
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 2.593774940143655,
|
| 1850 |
+
"grad_norm": 0.0012382810236886144,
|
| 1851 |
+
"learning_rate": 7.545078332840674e-06,
|
| 1852 |
+
"loss": 0.002,
|
| 1853 |
+
"step": 6500
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 2.6037509976057462,
|
| 1857 |
+
"grad_norm": 0.0005860702367499471,
|
| 1858 |
+
"learning_rate": 7.360331067100207e-06,
|
| 1859 |
+
"loss": 0.0011,
|
| 1860 |
+
"step": 6525
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 2.6137270550678373,
|
| 1864 |
+
"grad_norm": 0.0005730630364269018,
|
| 1865 |
+
"learning_rate": 7.17558380135974e-06,
|
| 1866 |
+
"loss": 0.0017,
|
| 1867 |
+
"step": 6550
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 2.6237031125299284,
|
| 1871 |
+
"grad_norm": 0.0005257041775621474,
|
| 1872 |
+
"learning_rate": 6.9908365356192735e-06,
|
| 1873 |
+
"loss": 0.0021,
|
| 1874 |
+
"step": 6575
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 2.633679169992019,
|
| 1878 |
+
"grad_norm": 0.0004204232827760279,
|
| 1879 |
+
"learning_rate": 6.806089269878806e-06,
|
| 1880 |
+
"loss": 0.0012,
|
| 1881 |
+
"step": 6600
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 2.64365522745411,
|
| 1885 |
+
"grad_norm": 0.0006845107418484986,
|
| 1886 |
+
"learning_rate": 6.62134200413834e-06,
|
| 1887 |
+
"loss": 0.0048,
|
| 1888 |
+
"step": 6625
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 2.653631284916201,
|
| 1892 |
+
"grad_norm": 0.0027906603645533323,
|
| 1893 |
+
"learning_rate": 6.436594738397872e-06,
|
| 1894 |
+
"loss": 0.0015,
|
| 1895 |
+
"step": 6650
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 2.663607342378292,
|
| 1899 |
+
"grad_norm": 0.000480479997349903,
|
| 1900 |
+
"learning_rate": 6.2518474726574046e-06,
|
| 1901 |
+
"loss": 0.0005,
|
| 1902 |
+
"step": 6675
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 2.673583399840383,
|
| 1906 |
+
"grad_norm": 0.0006570586119778454,
|
| 1907 |
+
"learning_rate": 6.067100206916938e-06,
|
| 1908 |
+
"loss": 0.0022,
|
| 1909 |
+
"step": 6700
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 2.683559457302474,
|
| 1913 |
+
"grad_norm": 0.20743273198604584,
|
| 1914 |
+
"learning_rate": 5.882352941176471e-06,
|
| 1915 |
+
"loss": 0.003,
|
| 1916 |
+
"step": 6725
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 2.693535514764565,
|
| 1920 |
+
"grad_norm": 0.14513282477855682,
|
| 1921 |
+
"learning_rate": 5.697605675436004e-06,
|
| 1922 |
+
"loss": 0.0022,
|
| 1923 |
+
"step": 6750
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 2.703511572226656,
|
| 1927 |
+
"grad_norm": 0.001159708364866674,
|
| 1928 |
+
"learning_rate": 5.5128584096955364e-06,
|
| 1929 |
+
"loss": 0.0007,
|
| 1930 |
+
"step": 6775
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 2.713487629688747,
|
| 1934 |
+
"grad_norm": 0.0006871894584037364,
|
| 1935 |
+
"learning_rate": 5.32811114395507e-06,
|
| 1936 |
+
"loss": 0.0083,
|
| 1937 |
+
"step": 6800
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 2.723463687150838,
|
| 1941 |
+
"grad_norm": 0.29086247086524963,
|
| 1942 |
+
"learning_rate": 5.143363878214603e-06,
|
| 1943 |
+
"loss": 0.0026,
|
| 1944 |
+
"step": 6825
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 2.733439744612929,
|
| 1948 |
+
"grad_norm": 0.20610134303569794,
|
| 1949 |
+
"learning_rate": 4.958616612474136e-06,
|
| 1950 |
+
"loss": 0.0024,
|
| 1951 |
+
"step": 6850
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 2.74341580207502,
|
| 1955 |
+
"grad_norm": 0.0009273093892261386,
|
| 1956 |
+
"learning_rate": 4.773869346733668e-06,
|
| 1957 |
+
"loss": 0.0028,
|
| 1958 |
+
"step": 6875
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 2.753391859537111,
|
| 1962 |
+
"grad_norm": 0.036556895822286606,
|
| 1963 |
+
"learning_rate": 4.5891220809932015e-06,
|
| 1964 |
+
"loss": 0.0015,
|
| 1965 |
+
"step": 6900
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 2.763367916999202,
|
| 1969 |
+
"grad_norm": 0.7557047605514526,
|
| 1970 |
+
"learning_rate": 4.404374815252735e-06,
|
| 1971 |
+
"loss": 0.002,
|
| 1972 |
+
"step": 6925
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 2.7733439744612927,
|
| 1976 |
+
"grad_norm": 0.3542492985725403,
|
| 1977 |
+
"learning_rate": 4.219627549512267e-06,
|
| 1978 |
+
"loss": 0.0057,
|
| 1979 |
+
"step": 6950
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 2.7833200319233837,
|
| 1983 |
+
"grad_norm": 0.0009435478714294732,
|
| 1984 |
+
"learning_rate": 4.0348802837718e-06,
|
| 1985 |
+
"loss": 0.0016,
|
| 1986 |
+
"step": 6975
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 2.793296089385475,
|
| 1990 |
+
"grad_norm": 0.0007737234118394554,
|
| 1991 |
+
"learning_rate": 3.850133018031333e-06,
|
| 1992 |
+
"loss": 0.0013,
|
| 1993 |
+
"step": 7000
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 2.803272146847566,
|
| 1997 |
+
"grad_norm": 0.0007262477301992476,
|
| 1998 |
+
"learning_rate": 3.665385752290866e-06,
|
| 1999 |
+
"loss": 0.0036,
|
| 2000 |
+
"step": 7025
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 2.813248204309657,
|
| 2004 |
+
"grad_norm": 0.0009191161952912807,
|
| 2005 |
+
"learning_rate": 3.4806384865503993e-06,
|
| 2006 |
+
"loss": 0.002,
|
| 2007 |
+
"step": 7050
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 2.823224261771748,
|
| 2011 |
+
"grad_norm": 0.0007111378945410252,
|
| 2012 |
+
"learning_rate": 3.2958912208099325e-06,
|
| 2013 |
+
"loss": 0.0006,
|
| 2014 |
+
"step": 7075
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 2.8332003192338386,
|
| 2018 |
+
"grad_norm": 0.0006967505323700607,
|
| 2019 |
+
"learning_rate": 3.1111439550694652e-06,
|
| 2020 |
+
"loss": 0.0035,
|
| 2021 |
+
"step": 7100
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 2.8431763766959297,
|
| 2025 |
+
"grad_norm": 0.005879946053028107,
|
| 2026 |
+
"learning_rate": 2.926396689328998e-06,
|
| 2027 |
+
"loss": 0.0033,
|
| 2028 |
+
"step": 7125
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 2.853152434158021,
|
| 2032 |
+
"grad_norm": 0.0006571909179911017,
|
| 2033 |
+
"learning_rate": 2.7416494235885307e-06,
|
| 2034 |
+
"loss": 0.0025,
|
| 2035 |
+
"step": 7150
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 2.863128491620112,
|
| 2039 |
+
"grad_norm": 0.07370542734861374,
|
| 2040 |
+
"learning_rate": 2.556902157848064e-06,
|
| 2041 |
+
"loss": 0.0019,
|
| 2042 |
+
"step": 7175
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 2.8731045490822025,
|
| 2046 |
+
"grad_norm": 0.13073043525218964,
|
| 2047 |
+
"learning_rate": 2.3721548921075967e-06,
|
| 2048 |
+
"loss": 0.0015,
|
| 2049 |
+
"step": 7200
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 2.8830806065442935,
|
| 2053 |
+
"grad_norm": 0.0007191087934188545,
|
| 2054 |
+
"learning_rate": 2.18740762636713e-06,
|
| 2055 |
+
"loss": 0.0074,
|
| 2056 |
+
"step": 7225
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 2.8930566640063846,
|
| 2060 |
+
"grad_norm": 0.0005886733415536582,
|
| 2061 |
+
"learning_rate": 2.002660360626663e-06,
|
| 2062 |
+
"loss": 0.0007,
|
| 2063 |
+
"step": 7250
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 2.9030327214684757,
|
| 2067 |
+
"grad_norm": 0.007630261592566967,
|
| 2068 |
+
"learning_rate": 1.8179130948861958e-06,
|
| 2069 |
+
"loss": 0.0,
|
| 2070 |
+
"step": 7275
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 2.9130087789305668,
|
| 2074 |
+
"grad_norm": 0.17814847826957703,
|
| 2075 |
+
"learning_rate": 1.6331658291457288e-06,
|
| 2076 |
+
"loss": 0.0016,
|
| 2077 |
+
"step": 7300
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 2.922984836392658,
|
| 2081 |
+
"grad_norm": 0.0005158995627425611,
|
| 2082 |
+
"learning_rate": 1.4484185634052617e-06,
|
| 2083 |
+
"loss": 0.0006,
|
| 2084 |
+
"step": 7325
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 2.9329608938547485,
|
| 2088 |
+
"grad_norm": 0.0007457538740709424,
|
| 2089 |
+
"learning_rate": 1.2636712976647947e-06,
|
| 2090 |
+
"loss": 0.0097,
|
| 2091 |
+
"step": 7350
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 2.9429369513168395,
|
| 2095 |
+
"grad_norm": 0.0007376657449640334,
|
| 2096 |
+
"learning_rate": 1.0789240319243274e-06,
|
| 2097 |
+
"loss": 0.001,
|
| 2098 |
+
"step": 7375
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 2.9529130087789306,
|
| 2102 |
+
"grad_norm": 0.05235452577471733,
|
| 2103 |
+
"learning_rate": 8.941767661838605e-07,
|
| 2104 |
+
"loss": 0.0017,
|
| 2105 |
+
"step": 7400
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 2.9628890662410217,
|
| 2109 |
+
"grad_norm": 0.00046603597002103925,
|
| 2110 |
+
"learning_rate": 7.094295004433935e-07,
|
| 2111 |
+
"loss": 0.0001,
|
| 2112 |
+
"step": 7425
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 2.9728651237031123,
|
| 2116 |
+
"grad_norm": 0.0016722336877137423,
|
| 2117 |
+
"learning_rate": 5.246822347029265e-07,
|
| 2118 |
+
"loss": 0.0071,
|
| 2119 |
+
"step": 7450
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 2.9828411811652034,
|
| 2123 |
+
"grad_norm": 0.00046282404218800366,
|
| 2124 |
+
"learning_rate": 3.3993496896245937e-07,
|
| 2125 |
+
"loss": 0.0009,
|
| 2126 |
+
"step": 7475
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 2.9928172386272944,
|
| 2130 |
+
"grad_norm": 0.0005693003768101335,
|
| 2131 |
+
"learning_rate": 1.5518770322199233e-07,
|
| 2132 |
+
"loss": 0.0024,
|
| 2133 |
+
"step": 7500
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 3.0,
|
| 2137 |
+
"eval_accuracy": 0.9987307166569029,
|
| 2138 |
+
"eval_f1": 0.9976024480267517,
|
| 2139 |
+
"eval_loss": 0.00414163526147604,
|
| 2140 |
+
"eval_precision": 0.996753451427851,
|
| 2141 |
+
"eval_recall": 0.998452892144481,
|
| 2142 |
+
"eval_runtime": 8.553,
|
| 2143 |
+
"eval_samples_per_second": 585.992,
|
| 2144 |
+
"eval_steps_per_second": 36.712,
|
| 2145 |
+
"step": 7518
|
| 2146 |
+
}
|
| 2147 |
+
],
|
| 2148 |
+
"logging_steps": 25,
|
| 2149 |
+
"max_steps": 7518,
|
| 2150 |
+
"num_input_tokens_seen": 0,
|
| 2151 |
+
"num_train_epochs": 3,
|
| 2152 |
+
"save_steps": 500,
|
| 2153 |
+
"stateful_callbacks": {
|
| 2154 |
+
"EarlyStoppingCallback": {
|
| 2155 |
+
"args": {
|
| 2156 |
+
"early_stopping_patience": 5,
|
| 2157 |
+
"early_stopping_threshold": 0.01
|
| 2158 |
+
},
|
| 2159 |
+
"attributes": {
|
| 2160 |
+
"early_stopping_patience_counter": 2
|
| 2161 |
+
}
|
| 2162 |
+
},
|
| 2163 |
+
"TrainerControl": {
|
| 2164 |
+
"args": {
|
| 2165 |
+
"should_epoch_stop": false,
|
| 2166 |
+
"should_evaluate": false,
|
| 2167 |
+
"should_log": false,
|
| 2168 |
+
"should_save": true,
|
| 2169 |
+
"should_training_stop": true
|
| 2170 |
+
},
|
| 2171 |
+
"attributes": {}
|
| 2172 |
+
}
|
| 2173 |
+
},
|
| 2174 |
+
"total_flos": 3928341147079680.0,
|
| 2175 |
+
"train_batch_size": 8,
|
| 2176 |
+
"trial_name": null,
|
| 2177 |
+
"trial_params": null
|
| 2178 |
+
}
|
checkpoint-7518/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4df04af647adfcc4b2b59a92394c0b5476ef0ddbb612617fac3de483b9fdb1fd
|
| 3 |
+
size 5176
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dslim/bert-base-NER",
|
| 3 |
+
"_num_labels": 4,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForTokenClassification"
|
| 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": "B-BRAND",
|
| 14 |
+
"1": "B-MODEL",
|
| 15 |
+
"2": "I-MODEL",
|
| 16 |
+
"3": "O"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"B-BRAND": 0,
|
| 22 |
+
"B-MODEL": 1,
|
| 23 |
+
"I-MODEL": 2,
|
| 24 |
+
"O": 3
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"output_past": true,
|
| 32 |
+
"pad_token_id": 0,
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.45.0",
|
| 36 |
+
"type_vocab_size": 2,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 28996
|
| 39 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93e9b8fd0f9e77110a6695302c3528eed7a506000320e72dedc0e97f63e4bf5a
|
| 3 |
+
size 430914360
|
runs/Oct17_19-37-46_rh/events.out.tfevents.1729186667.rh.4547.0
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 sha256:4cd8534a7385ad798d7966a4ddedd9f3bfbd146b312d8c21a27a8ad8af9a54f1
|
| 3 |
+
size 70167
|
runs/Oct17_19-37-46_rh/events.out.tfevents.1729187089.rh.4547.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fdbf20d59a3a9d5f23791eca0ac80fcaf0226102707a2590935204164d789bd
|
| 3 |
+
size 560
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"max_len": 512,
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4df04af647adfcc4b2b59a92394c0b5476ef0ddbb612617fac3de483b9fdb1fd
|
| 3 |
+
size 5176
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "product-extractor6/autotrain-data",
|
| 3 |
+
"model": "dslim/bert-base-NER",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 3,
|
| 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 |
+
"tokens_column": "autotrain_text",
|
| 18 |
+
"tags_column": "autotrain_label",
|
| 19 |
+
"logging_steps": -1,
|
| 20 |
+
"project_name": "product-extractor6",
|
| 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": "xenogy",
|
| 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
|
|
|