Upload folder using huggingface_hub
Browse files- 1_Pooling/config.json +10 -0
- README.md +144 -3
- config.json +40 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +20 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +2833 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 1024,
|
| 3 |
+
"pooling_mode_cls_token": true,
|
| 4 |
+
"pooling_mode_mean_tokens": false,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
README.md
CHANGED
|
@@ -1,3 +1,144 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets: []
|
| 3 |
+
language: []
|
| 4 |
+
library_name: sentence-transformers
|
| 5 |
+
pipeline_tag: sentence-similarity
|
| 6 |
+
tags:
|
| 7 |
+
- sentence-transformers
|
| 8 |
+
- sentence-similarity
|
| 9 |
+
- feature-extraction
|
| 10 |
+
widget: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# SentenceTransformer
|
| 14 |
+
|
| 15 |
+
This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
- **Model Type:** Sentence Transformer
|
| 21 |
+
<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
|
| 22 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 23 |
+
- **Output Dimensionality:** 1024 tokens
|
| 24 |
+
- **Similarity Function:** Cosine Similarity
|
| 25 |
+
<!-- - **Training Dataset:** Unknown -->
|
| 26 |
+
<!-- - **Language:** Unknown -->
|
| 27 |
+
<!-- - **License:** Unknown -->
|
| 28 |
+
|
| 29 |
+
### Model Sources
|
| 30 |
+
|
| 31 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 32 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 33 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 34 |
+
|
| 35 |
+
### Full Model Architecture
|
| 36 |
+
|
| 37 |
+
```
|
| 38 |
+
SentenceTransformer(
|
| 39 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
| 40 |
+
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
| 41 |
+
(2): Normalize()
|
| 42 |
+
)
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
## Usage
|
| 46 |
+
|
| 47 |
+
### Direct Usage (Sentence Transformers)
|
| 48 |
+
|
| 49 |
+
First install the Sentence Transformers library:
|
| 50 |
+
|
| 51 |
+
```bash
|
| 52 |
+
pip install -U sentence-transformers
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
Then you can load this model and run inference.
|
| 56 |
+
```python
|
| 57 |
+
from sentence_transformers import SentenceTransformer
|
| 58 |
+
|
| 59 |
+
# Download from the 🤗 Hub
|
| 60 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 61 |
+
# Run inference
|
| 62 |
+
sentences = [
|
| 63 |
+
'The weather is lovely today.',
|
| 64 |
+
"It's so sunny outside!",
|
| 65 |
+
'He drove to the stadium.',
|
| 66 |
+
]
|
| 67 |
+
embeddings = model.encode(sentences)
|
| 68 |
+
print(embeddings.shape)
|
| 69 |
+
# [3, 1024]
|
| 70 |
+
|
| 71 |
+
# Get the similarity scores for the embeddings
|
| 72 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 73 |
+
print(similarities.shape)
|
| 74 |
+
# [3, 3]
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
<!--
|
| 78 |
+
### Direct Usage (Transformers)
|
| 79 |
+
|
| 80 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 81 |
+
|
| 82 |
+
</details>
|
| 83 |
+
-->
|
| 84 |
+
|
| 85 |
+
<!--
|
| 86 |
+
### Downstream Usage (Sentence Transformers)
|
| 87 |
+
|
| 88 |
+
You can finetune this model on your own dataset.
|
| 89 |
+
|
| 90 |
+
<details><summary>Click to expand</summary>
|
| 91 |
+
|
| 92 |
+
</details>
|
| 93 |
+
-->
|
| 94 |
+
|
| 95 |
+
<!--
|
| 96 |
+
### Out-of-Scope Use
|
| 97 |
+
|
| 98 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 99 |
+
-->
|
| 100 |
+
|
| 101 |
+
<!--
|
| 102 |
+
## Bias, Risks and Limitations
|
| 103 |
+
|
| 104 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 105 |
+
-->
|
| 106 |
+
|
| 107 |
+
<!--
|
| 108 |
+
### Recommendations
|
| 109 |
+
|
| 110 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 111 |
+
-->
|
| 112 |
+
|
| 113 |
+
## Training Details
|
| 114 |
+
|
| 115 |
+
### Framework Versions
|
| 116 |
+
- Python: 3.9.2
|
| 117 |
+
- Sentence Transformers: 3.0.1
|
| 118 |
+
- Transformers: 4.41.2
|
| 119 |
+
- PyTorch: 2.3.1+cu121
|
| 120 |
+
- Accelerate: 0.31.0
|
| 121 |
+
- Datasets: 2.20.0
|
| 122 |
+
- Tokenizers: 0.19.1
|
| 123 |
+
|
| 124 |
+
## Citation
|
| 125 |
+
|
| 126 |
+
### BibTeX
|
| 127 |
+
|
| 128 |
+
<!--
|
| 129 |
+
## Glossary
|
| 130 |
+
|
| 131 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 132 |
+
-->
|
| 133 |
+
|
| 134 |
+
<!--
|
| 135 |
+
## Model Card Authors
|
| 136 |
+
|
| 137 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 138 |
+
-->
|
| 139 |
+
|
| 140 |
+
<!--
|
| 141 |
+
## Model Card Contact
|
| 142 |
+
|
| 143 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 144 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "BGE_FT_MODEL_DENSE_40/checkpoint-20000",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"directionality": "bidi",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"output_past": true,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_fc_size": 768,
|
| 30 |
+
"pooler_num_attention_heads": 12,
|
| 31 |
+
"pooler_num_fc_layers": 3,
|
| 32 |
+
"pooler_size_per_head": 128,
|
| 33 |
+
"pooler_type": "first_token_transform",
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.41.2",
|
| 37 |
+
"type_vocab_size": 2,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 21128
|
| 40 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.0.1",
|
| 4 |
+
"transformers": "4.41.2",
|
| 5 |
+
"pytorch": "2.3.1+cu121"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a3b3c9b53cb1edf34cdfe1862c732681c57be67b7380841cec4bfae21b25913
|
| 3 |
+
size 1302134568
|
modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.models.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a3f3fd9c43d86f92cf7016d8b41eb9f3b60e975ee03f29c5dab1b8d347240c5
|
| 3 |
+
size 2596108193
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8705e2b97793e346b294fee7b65363f6f3316fce2a183259ea8d1fc6c8b8c66
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a1d724d88426b758dac0c7579247688fd3c3ab98594b5baffe79e186c02bebc
|
| 3 |
+
size 1064
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2833 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 20000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 24.59290313720703,
|
| 14 |
+
"learning_rate": 9.976e-07,
|
| 15 |
+
"loss": 2.6229,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 44.6561279296875,
|
| 21 |
+
"learning_rate": 9.951e-07,
|
| 22 |
+
"loss": 2.3333,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 31.2443790435791,
|
| 28 |
+
"learning_rate": 9.926e-07,
|
| 29 |
+
"loss": 2.1022,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04,
|
| 34 |
+
"grad_norm": 30.142139434814453,
|
| 35 |
+
"learning_rate": 9.900999999999998e-07,
|
| 36 |
+
"loss": 2.1899,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05,
|
| 41 |
+
"grad_norm": 40.865047454833984,
|
| 42 |
+
"learning_rate": 9.876e-07,
|
| 43 |
+
"loss": 2.0581,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06,
|
| 48 |
+
"grad_norm": 49.21326446533203,
|
| 49 |
+
"learning_rate": 9.850999999999999e-07,
|
| 50 |
+
"loss": 2.0981,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"grad_norm": 34.270729064941406,
|
| 56 |
+
"learning_rate": 9.826e-07,
|
| 57 |
+
"loss": 2.1487,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08,
|
| 62 |
+
"grad_norm": 37.85762405395508,
|
| 63 |
+
"learning_rate": 9.801e-07,
|
| 64 |
+
"loss": 2.0944,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09,
|
| 69 |
+
"grad_norm": 38.32168197631836,
|
| 70 |
+
"learning_rate": 9.776e-07,
|
| 71 |
+
"loss": 2.0425,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1,
|
| 76 |
+
"grad_norm": 40.687808990478516,
|
| 77 |
+
"learning_rate": 9.751e-07,
|
| 78 |
+
"loss": 1.9918,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.11,
|
| 83 |
+
"grad_norm": 41.6737174987793,
|
| 84 |
+
"learning_rate": 9.726e-07,
|
| 85 |
+
"loss": 1.9946,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.12,
|
| 90 |
+
"grad_norm": 32.36153030395508,
|
| 91 |
+
"learning_rate": 9.700999999999998e-07,
|
| 92 |
+
"loss": 2.0164,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.13,
|
| 97 |
+
"grad_norm": 30.314594268798828,
|
| 98 |
+
"learning_rate": 9.676e-07,
|
| 99 |
+
"loss": 1.9766,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.14,
|
| 104 |
+
"grad_norm": 32.16353988647461,
|
| 105 |
+
"learning_rate": 9.650999999999999e-07,
|
| 106 |
+
"loss": 1.9656,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.15,
|
| 111 |
+
"grad_norm": 53.54747772216797,
|
| 112 |
+
"learning_rate": 9.626e-07,
|
| 113 |
+
"loss": 1.9925,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.16,
|
| 118 |
+
"grad_norm": 31.085399627685547,
|
| 119 |
+
"learning_rate": 9.601e-07,
|
| 120 |
+
"loss": 1.9141,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.17,
|
| 125 |
+
"grad_norm": 44.15593719482422,
|
| 126 |
+
"learning_rate": 9.576e-07,
|
| 127 |
+
"loss": 2.0047,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.18,
|
| 132 |
+
"grad_norm": 40.597999572753906,
|
| 133 |
+
"learning_rate": 9.551e-07,
|
| 134 |
+
"loss": 1.9799,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.19,
|
| 139 |
+
"grad_norm": 40.38375473022461,
|
| 140 |
+
"learning_rate": 9.526e-07,
|
| 141 |
+
"loss": 1.9333,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2,
|
| 146 |
+
"grad_norm": 31.839799880981445,
|
| 147 |
+
"learning_rate": 9.500999999999999e-07,
|
| 148 |
+
"loss": 2.0041,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.21,
|
| 153 |
+
"grad_norm": 43.41249084472656,
|
| 154 |
+
"learning_rate": 9.475999999999999e-07,
|
| 155 |
+
"loss": 1.9008,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.22,
|
| 160 |
+
"grad_norm": 39.27376937866211,
|
| 161 |
+
"learning_rate": 9.451e-07,
|
| 162 |
+
"loss": 1.8454,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.23,
|
| 167 |
+
"grad_norm": 37.960269927978516,
|
| 168 |
+
"learning_rate": 9.426e-07,
|
| 169 |
+
"loss": 1.8152,
|
| 170 |
+
"step": 1150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.24,
|
| 174 |
+
"grad_norm": 44.50017547607422,
|
| 175 |
+
"learning_rate": 9.401e-07,
|
| 176 |
+
"loss": 1.8737,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.25,
|
| 181 |
+
"grad_norm": 37.4691162109375,
|
| 182 |
+
"learning_rate": 9.375999999999999e-07,
|
| 183 |
+
"loss": 1.808,
|
| 184 |
+
"step": 1250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.26,
|
| 188 |
+
"grad_norm": 37.40227127075195,
|
| 189 |
+
"learning_rate": 9.351e-07,
|
| 190 |
+
"loss": 1.832,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.27,
|
| 195 |
+
"grad_norm": 39.435123443603516,
|
| 196 |
+
"learning_rate": 9.326e-07,
|
| 197 |
+
"loss": 1.9672,
|
| 198 |
+
"step": 1350
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.28,
|
| 202 |
+
"grad_norm": 41.97803497314453,
|
| 203 |
+
"learning_rate": 9.301e-07,
|
| 204 |
+
"loss": 1.869,
|
| 205 |
+
"step": 1400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.29,
|
| 209 |
+
"grad_norm": 42.29490661621094,
|
| 210 |
+
"learning_rate": 9.275999999999999e-07,
|
| 211 |
+
"loss": 1.8844,
|
| 212 |
+
"step": 1450
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3,
|
| 216 |
+
"grad_norm": 39.2964973449707,
|
| 217 |
+
"learning_rate": 9.250999999999999e-07,
|
| 218 |
+
"loss": 1.8546,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.31,
|
| 223 |
+
"grad_norm": 46.49869155883789,
|
| 224 |
+
"learning_rate": 9.226e-07,
|
| 225 |
+
"loss": 1.7998,
|
| 226 |
+
"step": 1550
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.32,
|
| 230 |
+
"grad_norm": 35.85550308227539,
|
| 231 |
+
"learning_rate": 9.201e-07,
|
| 232 |
+
"loss": 1.8493,
|
| 233 |
+
"step": 1600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.33,
|
| 237 |
+
"grad_norm": 36.285282135009766,
|
| 238 |
+
"learning_rate": 9.175999999999999e-07,
|
| 239 |
+
"loss": 1.8918,
|
| 240 |
+
"step": 1650
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.34,
|
| 244 |
+
"grad_norm": 36.704795837402344,
|
| 245 |
+
"learning_rate": 9.151e-07,
|
| 246 |
+
"loss": 1.8412,
|
| 247 |
+
"step": 1700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.35,
|
| 251 |
+
"grad_norm": 39.69667434692383,
|
| 252 |
+
"learning_rate": 9.126e-07,
|
| 253 |
+
"loss": 1.809,
|
| 254 |
+
"step": 1750
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.36,
|
| 258 |
+
"grad_norm": 36.81133270263672,
|
| 259 |
+
"learning_rate": 9.101e-07,
|
| 260 |
+
"loss": 1.8425,
|
| 261 |
+
"step": 1800
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.37,
|
| 265 |
+
"grad_norm": 40.80613708496094,
|
| 266 |
+
"learning_rate": 9.075999999999999e-07,
|
| 267 |
+
"loss": 1.9628,
|
| 268 |
+
"step": 1850
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.38,
|
| 272 |
+
"grad_norm": 39.36043930053711,
|
| 273 |
+
"learning_rate": 9.051e-07,
|
| 274 |
+
"loss": 1.7546,
|
| 275 |
+
"step": 1900
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.39,
|
| 279 |
+
"grad_norm": 40.22469711303711,
|
| 280 |
+
"learning_rate": 9.025999999999999e-07,
|
| 281 |
+
"loss": 1.8055,
|
| 282 |
+
"step": 1950
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4,
|
| 286 |
+
"grad_norm": 44.26631546020508,
|
| 287 |
+
"learning_rate": 9.001e-07,
|
| 288 |
+
"loss": 1.8203,
|
| 289 |
+
"step": 2000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.41,
|
| 293 |
+
"grad_norm": 50.78614807128906,
|
| 294 |
+
"learning_rate": 8.976499999999999e-07,
|
| 295 |
+
"loss": 1.8012,
|
| 296 |
+
"step": 2050
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.42,
|
| 300 |
+
"grad_norm": 63.06776809692383,
|
| 301 |
+
"learning_rate": 8.951499999999999e-07,
|
| 302 |
+
"loss": 1.8745,
|
| 303 |
+
"step": 2100
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.43,
|
| 307 |
+
"grad_norm": 48.32567596435547,
|
| 308 |
+
"learning_rate": 8.9265e-07,
|
| 309 |
+
"loss": 1.7794,
|
| 310 |
+
"step": 2150
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.44,
|
| 314 |
+
"grad_norm": 48.12654495239258,
|
| 315 |
+
"learning_rate": 8.9015e-07,
|
| 316 |
+
"loss": 1.9107,
|
| 317 |
+
"step": 2200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.45,
|
| 321 |
+
"grad_norm": 38.266197204589844,
|
| 322 |
+
"learning_rate": 8.8765e-07,
|
| 323 |
+
"loss": 1.7588,
|
| 324 |
+
"step": 2250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.46,
|
| 328 |
+
"grad_norm": 39.421504974365234,
|
| 329 |
+
"learning_rate": 8.851499999999999e-07,
|
| 330 |
+
"loss": 1.8511,
|
| 331 |
+
"step": 2300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.47,
|
| 335 |
+
"grad_norm": 39.87221908569336,
|
| 336 |
+
"learning_rate": 8.8265e-07,
|
| 337 |
+
"loss": 1.6939,
|
| 338 |
+
"step": 2350
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.48,
|
| 342 |
+
"grad_norm": 43.736900329589844,
|
| 343 |
+
"learning_rate": 8.8015e-07,
|
| 344 |
+
"loss": 1.7321,
|
| 345 |
+
"step": 2400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.49,
|
| 349 |
+
"grad_norm": 43.2308235168457,
|
| 350 |
+
"learning_rate": 8.7765e-07,
|
| 351 |
+
"loss": 1.8803,
|
| 352 |
+
"step": 2450
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5,
|
| 356 |
+
"grad_norm": 40.887939453125,
|
| 357 |
+
"learning_rate": 8.751499999999999e-07,
|
| 358 |
+
"loss": 1.731,
|
| 359 |
+
"step": 2500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.51,
|
| 363 |
+
"grad_norm": 43.211727142333984,
|
| 364 |
+
"learning_rate": 8.7265e-07,
|
| 365 |
+
"loss": 1.8046,
|
| 366 |
+
"step": 2550
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.52,
|
| 370 |
+
"grad_norm": 51.66404342651367,
|
| 371 |
+
"learning_rate": 8.701499999999999e-07,
|
| 372 |
+
"loss": 1.774,
|
| 373 |
+
"step": 2600
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.53,
|
| 377 |
+
"grad_norm": 39.11322021484375,
|
| 378 |
+
"learning_rate": 8.6765e-07,
|
| 379 |
+
"loss": 1.8792,
|
| 380 |
+
"step": 2650
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.54,
|
| 384 |
+
"grad_norm": 48.62511444091797,
|
| 385 |
+
"learning_rate": 8.6515e-07,
|
| 386 |
+
"loss": 1.7991,
|
| 387 |
+
"step": 2700
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.55,
|
| 391 |
+
"grad_norm": 41.84499740600586,
|
| 392 |
+
"learning_rate": 8.6265e-07,
|
| 393 |
+
"loss": 1.8712,
|
| 394 |
+
"step": 2750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.56,
|
| 398 |
+
"grad_norm": 51.82795715332031,
|
| 399 |
+
"learning_rate": 8.601499999999999e-07,
|
| 400 |
+
"loss": 1.7662,
|
| 401 |
+
"step": 2800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.57,
|
| 405 |
+
"grad_norm": 54.27309799194336,
|
| 406 |
+
"learning_rate": 8.5765e-07,
|
| 407 |
+
"loss": 1.7643,
|
| 408 |
+
"step": 2850
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.58,
|
| 412 |
+
"grad_norm": 39.44385528564453,
|
| 413 |
+
"learning_rate": 8.5515e-07,
|
| 414 |
+
"loss": 1.804,
|
| 415 |
+
"step": 2900
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.59,
|
| 419 |
+
"grad_norm": 37.73311233520508,
|
| 420 |
+
"learning_rate": 8.5265e-07,
|
| 421 |
+
"loss": 1.7039,
|
| 422 |
+
"step": 2950
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6,
|
| 426 |
+
"grad_norm": 43.82680892944336,
|
| 427 |
+
"learning_rate": 8.501499999999999e-07,
|
| 428 |
+
"loss": 1.7717,
|
| 429 |
+
"step": 3000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.61,
|
| 433 |
+
"grad_norm": 44.10558319091797,
|
| 434 |
+
"learning_rate": 8.476499999999999e-07,
|
| 435 |
+
"loss": 1.7109,
|
| 436 |
+
"step": 3050
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.62,
|
| 440 |
+
"grad_norm": 43.69202423095703,
|
| 441 |
+
"learning_rate": 8.4515e-07,
|
| 442 |
+
"loss": 1.8569,
|
| 443 |
+
"step": 3100
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.63,
|
| 447 |
+
"grad_norm": 46.728538513183594,
|
| 448 |
+
"learning_rate": 8.4265e-07,
|
| 449 |
+
"loss": 1.8468,
|
| 450 |
+
"step": 3150
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.64,
|
| 454 |
+
"grad_norm": 38.28073501586914,
|
| 455 |
+
"learning_rate": 8.401499999999999e-07,
|
| 456 |
+
"loss": 1.6194,
|
| 457 |
+
"step": 3200
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.65,
|
| 461 |
+
"grad_norm": 48.87205123901367,
|
| 462 |
+
"learning_rate": 8.376499999999999e-07,
|
| 463 |
+
"loss": 1.7792,
|
| 464 |
+
"step": 3250
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.66,
|
| 468 |
+
"grad_norm": 39.80657196044922,
|
| 469 |
+
"learning_rate": 8.3515e-07,
|
| 470 |
+
"loss": 1.7198,
|
| 471 |
+
"step": 3300
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.67,
|
| 475 |
+
"grad_norm": 37.74007034301758,
|
| 476 |
+
"learning_rate": 8.3265e-07,
|
| 477 |
+
"loss": 1.7539,
|
| 478 |
+
"step": 3350
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.68,
|
| 482 |
+
"grad_norm": 47.30875015258789,
|
| 483 |
+
"learning_rate": 8.3015e-07,
|
| 484 |
+
"loss": 1.725,
|
| 485 |
+
"step": 3400
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.69,
|
| 489 |
+
"grad_norm": 44.54092025756836,
|
| 490 |
+
"learning_rate": 8.276499999999999e-07,
|
| 491 |
+
"loss": 1.7863,
|
| 492 |
+
"step": 3450
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7,
|
| 496 |
+
"grad_norm": 49.025169372558594,
|
| 497 |
+
"learning_rate": 8.251500000000001e-07,
|
| 498 |
+
"loss": 1.7914,
|
| 499 |
+
"step": 3500
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.71,
|
| 503 |
+
"grad_norm": 45.531864166259766,
|
| 504 |
+
"learning_rate": 8.2265e-07,
|
| 505 |
+
"loss": 1.8326,
|
| 506 |
+
"step": 3550
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.72,
|
| 510 |
+
"grad_norm": 37.38317108154297,
|
| 511 |
+
"learning_rate": 8.2015e-07,
|
| 512 |
+
"loss": 1.8113,
|
| 513 |
+
"step": 3600
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.73,
|
| 517 |
+
"grad_norm": 42.720829010009766,
|
| 518 |
+
"learning_rate": 8.176499999999999e-07,
|
| 519 |
+
"loss": 1.7043,
|
| 520 |
+
"step": 3650
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.74,
|
| 524 |
+
"grad_norm": 42.389339447021484,
|
| 525 |
+
"learning_rate": 8.1515e-07,
|
| 526 |
+
"loss": 1.6669,
|
| 527 |
+
"step": 3700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.75,
|
| 531 |
+
"grad_norm": 50.965545654296875,
|
| 532 |
+
"learning_rate": 8.1265e-07,
|
| 533 |
+
"loss": 1.6581,
|
| 534 |
+
"step": 3750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.76,
|
| 538 |
+
"grad_norm": 33.738948822021484,
|
| 539 |
+
"learning_rate": 8.1015e-07,
|
| 540 |
+
"loss": 1.7835,
|
| 541 |
+
"step": 3800
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.77,
|
| 545 |
+
"grad_norm": 47.6729736328125,
|
| 546 |
+
"learning_rate": 8.076499999999999e-07,
|
| 547 |
+
"loss": 1.8784,
|
| 548 |
+
"step": 3850
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.78,
|
| 552 |
+
"grad_norm": 40.22808837890625,
|
| 553 |
+
"learning_rate": 8.0515e-07,
|
| 554 |
+
"loss": 1.6733,
|
| 555 |
+
"step": 3900
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.79,
|
| 559 |
+
"grad_norm": 43.46096420288086,
|
| 560 |
+
"learning_rate": 8.0265e-07,
|
| 561 |
+
"loss": 1.7327,
|
| 562 |
+
"step": 3950
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8,
|
| 566 |
+
"grad_norm": 39.8518180847168,
|
| 567 |
+
"learning_rate": 8.0015e-07,
|
| 568 |
+
"loss": 1.6765,
|
| 569 |
+
"step": 4000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.81,
|
| 573 |
+
"grad_norm": 43.99556350708008,
|
| 574 |
+
"learning_rate": 7.976999999999999e-07,
|
| 575 |
+
"loss": 1.6858,
|
| 576 |
+
"step": 4050
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.82,
|
| 580 |
+
"grad_norm": 39.69054412841797,
|
| 581 |
+
"learning_rate": 7.952e-07,
|
| 582 |
+
"loss": 1.7666,
|
| 583 |
+
"step": 4100
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.83,
|
| 587 |
+
"grad_norm": 37.67417907714844,
|
| 588 |
+
"learning_rate": 7.926999999999999e-07,
|
| 589 |
+
"loss": 1.7942,
|
| 590 |
+
"step": 4150
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.84,
|
| 594 |
+
"grad_norm": 39.24260711669922,
|
| 595 |
+
"learning_rate": 7.902e-07,
|
| 596 |
+
"loss": 1.7449,
|
| 597 |
+
"step": 4200
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.85,
|
| 601 |
+
"grad_norm": 44.0001220703125,
|
| 602 |
+
"learning_rate": 7.876999999999999e-07,
|
| 603 |
+
"loss": 1.7139,
|
| 604 |
+
"step": 4250
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.86,
|
| 608 |
+
"grad_norm": 41.069236755371094,
|
| 609 |
+
"learning_rate": 7.852e-07,
|
| 610 |
+
"loss": 1.6626,
|
| 611 |
+
"step": 4300
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.87,
|
| 615 |
+
"grad_norm": 40.02455139160156,
|
| 616 |
+
"learning_rate": 7.826999999999999e-07,
|
| 617 |
+
"loss": 1.6679,
|
| 618 |
+
"step": 4350
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.88,
|
| 622 |
+
"grad_norm": 38.73442077636719,
|
| 623 |
+
"learning_rate": 7.802e-07,
|
| 624 |
+
"loss": 1.7561,
|
| 625 |
+
"step": 4400
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.89,
|
| 629 |
+
"grad_norm": 44.03123474121094,
|
| 630 |
+
"learning_rate": 7.776999999999999e-07,
|
| 631 |
+
"loss": 1.7519,
|
| 632 |
+
"step": 4450
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9,
|
| 636 |
+
"grad_norm": 38.86705017089844,
|
| 637 |
+
"learning_rate": 7.752e-07,
|
| 638 |
+
"loss": 1.7051,
|
| 639 |
+
"step": 4500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.91,
|
| 643 |
+
"grad_norm": 42.8055534362793,
|
| 644 |
+
"learning_rate": 7.727e-07,
|
| 645 |
+
"loss": 1.7045,
|
| 646 |
+
"step": 4550
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.92,
|
| 650 |
+
"grad_norm": 50.77599334716797,
|
| 651 |
+
"learning_rate": 7.702e-07,
|
| 652 |
+
"loss": 1.7706,
|
| 653 |
+
"step": 4600
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.93,
|
| 657 |
+
"grad_norm": 39.55324935913086,
|
| 658 |
+
"learning_rate": 7.677e-07,
|
| 659 |
+
"loss": 1.7337,
|
| 660 |
+
"step": 4650
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.94,
|
| 664 |
+
"grad_norm": 48.40109634399414,
|
| 665 |
+
"learning_rate": 7.652e-07,
|
| 666 |
+
"loss": 1.6519,
|
| 667 |
+
"step": 4700
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.95,
|
| 671 |
+
"grad_norm": 47.08484649658203,
|
| 672 |
+
"learning_rate": 7.627e-07,
|
| 673 |
+
"loss": 1.7528,
|
| 674 |
+
"step": 4750
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.96,
|
| 678 |
+
"grad_norm": 41.425846099853516,
|
| 679 |
+
"learning_rate": 7.601999999999999e-07,
|
| 680 |
+
"loss": 1.6663,
|
| 681 |
+
"step": 4800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.97,
|
| 685 |
+
"grad_norm": 42.3223991394043,
|
| 686 |
+
"learning_rate": 7.577e-07,
|
| 687 |
+
"loss": 1.6747,
|
| 688 |
+
"step": 4850
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.98,
|
| 692 |
+
"grad_norm": 44.03189468383789,
|
| 693 |
+
"learning_rate": 7.552e-07,
|
| 694 |
+
"loss": 1.6487,
|
| 695 |
+
"step": 4900
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.99,
|
| 699 |
+
"grad_norm": 41.170108795166016,
|
| 700 |
+
"learning_rate": 7.527e-07,
|
| 701 |
+
"loss": 1.7019,
|
| 702 |
+
"step": 4950
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.0,
|
| 706 |
+
"grad_norm": 42.10016632080078,
|
| 707 |
+
"learning_rate": 7.501999999999999e-07,
|
| 708 |
+
"loss": 1.6696,
|
| 709 |
+
"step": 5000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.01,
|
| 713 |
+
"grad_norm": 34.27055358886719,
|
| 714 |
+
"learning_rate": 7.477e-07,
|
| 715 |
+
"loss": 1.62,
|
| 716 |
+
"step": 5050
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.02,
|
| 720 |
+
"grad_norm": 41.19538116455078,
|
| 721 |
+
"learning_rate": 7.452e-07,
|
| 722 |
+
"loss": 1.6309,
|
| 723 |
+
"step": 5100
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.03,
|
| 727 |
+
"grad_norm": 45.550575256347656,
|
| 728 |
+
"learning_rate": 7.427e-07,
|
| 729 |
+
"loss": 1.6535,
|
| 730 |
+
"step": 5150
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.04,
|
| 734 |
+
"grad_norm": 45.184539794921875,
|
| 735 |
+
"learning_rate": 7.401999999999999e-07,
|
| 736 |
+
"loss": 1.7223,
|
| 737 |
+
"step": 5200
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.05,
|
| 741 |
+
"grad_norm": 43.35379409790039,
|
| 742 |
+
"learning_rate": 7.376999999999999e-07,
|
| 743 |
+
"loss": 1.6844,
|
| 744 |
+
"step": 5250
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.06,
|
| 748 |
+
"grad_norm": 40.49492645263672,
|
| 749 |
+
"learning_rate": 7.352e-07,
|
| 750 |
+
"loss": 1.689,
|
| 751 |
+
"step": 5300
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.07,
|
| 755 |
+
"grad_norm": 38.820106506347656,
|
| 756 |
+
"learning_rate": 7.327e-07,
|
| 757 |
+
"loss": 1.7506,
|
| 758 |
+
"step": 5350
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.08,
|
| 762 |
+
"grad_norm": 38.87533187866211,
|
| 763 |
+
"learning_rate": 7.301999999999999e-07,
|
| 764 |
+
"loss": 1.5689,
|
| 765 |
+
"step": 5400
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.09,
|
| 769 |
+
"grad_norm": 34.46385192871094,
|
| 770 |
+
"learning_rate": 7.276999999999999e-07,
|
| 771 |
+
"loss": 1.6876,
|
| 772 |
+
"step": 5450
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.1,
|
| 776 |
+
"grad_norm": 39.77639389038086,
|
| 777 |
+
"learning_rate": 7.252e-07,
|
| 778 |
+
"loss": 1.6515,
|
| 779 |
+
"step": 5500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.11,
|
| 783 |
+
"grad_norm": 42.202735900878906,
|
| 784 |
+
"learning_rate": 7.227e-07,
|
| 785 |
+
"loss": 1.5767,
|
| 786 |
+
"step": 5550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.12,
|
| 790 |
+
"grad_norm": 36.47328186035156,
|
| 791 |
+
"learning_rate": 7.201999999999999e-07,
|
| 792 |
+
"loss": 1.7376,
|
| 793 |
+
"step": 5600
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.13,
|
| 797 |
+
"grad_norm": 40.54157257080078,
|
| 798 |
+
"learning_rate": 7.176999999999999e-07,
|
| 799 |
+
"loss": 1.768,
|
| 800 |
+
"step": 5650
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.1400000000000001,
|
| 804 |
+
"grad_norm": 36.865177154541016,
|
| 805 |
+
"learning_rate": 7.151999999999999e-07,
|
| 806 |
+
"loss": 1.5431,
|
| 807 |
+
"step": 5700
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.15,
|
| 811 |
+
"grad_norm": 32.530216217041016,
|
| 812 |
+
"learning_rate": 7.127e-07,
|
| 813 |
+
"loss": 1.6509,
|
| 814 |
+
"step": 5750
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.16,
|
| 818 |
+
"grad_norm": 38.9181022644043,
|
| 819 |
+
"learning_rate": 7.102e-07,
|
| 820 |
+
"loss": 1.6686,
|
| 821 |
+
"step": 5800
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.17,
|
| 825 |
+
"grad_norm": 47.71958541870117,
|
| 826 |
+
"learning_rate": 7.076999999999999e-07,
|
| 827 |
+
"loss": 1.6332,
|
| 828 |
+
"step": 5850
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.18,
|
| 832 |
+
"grad_norm": 33.65346908569336,
|
| 833 |
+
"learning_rate": 7.052e-07,
|
| 834 |
+
"loss": 1.6374,
|
| 835 |
+
"step": 5900
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.19,
|
| 839 |
+
"grad_norm": 50.740474700927734,
|
| 840 |
+
"learning_rate": 7.027e-07,
|
| 841 |
+
"loss": 1.6919,
|
| 842 |
+
"step": 5950
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.2,
|
| 846 |
+
"grad_norm": 35.024147033691406,
|
| 847 |
+
"learning_rate": 7.002e-07,
|
| 848 |
+
"loss": 1.5119,
|
| 849 |
+
"step": 6000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.21,
|
| 853 |
+
"grad_norm": 46.42051315307617,
|
| 854 |
+
"learning_rate": 6.977499999999999e-07,
|
| 855 |
+
"loss": 1.7009,
|
| 856 |
+
"step": 6050
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.22,
|
| 860 |
+
"grad_norm": 40.99652099609375,
|
| 861 |
+
"learning_rate": 6.9525e-07,
|
| 862 |
+
"loss": 1.671,
|
| 863 |
+
"step": 6100
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.23,
|
| 867 |
+
"grad_norm": 48.398765563964844,
|
| 868 |
+
"learning_rate": 6.9275e-07,
|
| 869 |
+
"loss": 1.5888,
|
| 870 |
+
"step": 6150
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.24,
|
| 874 |
+
"grad_norm": 37.039058685302734,
|
| 875 |
+
"learning_rate": 6.9025e-07,
|
| 876 |
+
"loss": 1.7995,
|
| 877 |
+
"step": 6200
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.25,
|
| 881 |
+
"grad_norm": 39.58694839477539,
|
| 882 |
+
"learning_rate": 6.877499999999999e-07,
|
| 883 |
+
"loss": 1.6646,
|
| 884 |
+
"step": 6250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.26,
|
| 888 |
+
"grad_norm": 43.098045349121094,
|
| 889 |
+
"learning_rate": 6.8525e-07,
|
| 890 |
+
"loss": 1.7114,
|
| 891 |
+
"step": 6300
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.27,
|
| 895 |
+
"grad_norm": 38.67097091674805,
|
| 896 |
+
"learning_rate": 6.827499999999999e-07,
|
| 897 |
+
"loss": 1.5854,
|
| 898 |
+
"step": 6350
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.28,
|
| 902 |
+
"grad_norm": 43.86952590942383,
|
| 903 |
+
"learning_rate": 6.8025e-07,
|
| 904 |
+
"loss": 1.6068,
|
| 905 |
+
"step": 6400
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.29,
|
| 909 |
+
"grad_norm": 43.158714294433594,
|
| 910 |
+
"learning_rate": 6.777499999999999e-07,
|
| 911 |
+
"loss": 1.7206,
|
| 912 |
+
"step": 6450
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.3,
|
| 916 |
+
"grad_norm": 44.74959945678711,
|
| 917 |
+
"learning_rate": 6.7525e-07,
|
| 918 |
+
"loss": 1.656,
|
| 919 |
+
"step": 6500
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.31,
|
| 923 |
+
"grad_norm": 34.64699172973633,
|
| 924 |
+
"learning_rate": 6.727499999999999e-07,
|
| 925 |
+
"loss": 1.6306,
|
| 926 |
+
"step": 6550
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.32,
|
| 930 |
+
"grad_norm": 51.52064895629883,
|
| 931 |
+
"learning_rate": 6.7025e-07,
|
| 932 |
+
"loss": 1.7831,
|
| 933 |
+
"step": 6600
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.33,
|
| 937 |
+
"grad_norm": 55.97758102416992,
|
| 938 |
+
"learning_rate": 6.677499999999999e-07,
|
| 939 |
+
"loss": 1.5366,
|
| 940 |
+
"step": 6650
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.34,
|
| 944 |
+
"grad_norm": 40.172523498535156,
|
| 945 |
+
"learning_rate": 6.6525e-07,
|
| 946 |
+
"loss": 1.7331,
|
| 947 |
+
"step": 6700
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.35,
|
| 951 |
+
"grad_norm": 42.77679443359375,
|
| 952 |
+
"learning_rate": 6.627499999999999e-07,
|
| 953 |
+
"loss": 1.6112,
|
| 954 |
+
"step": 6750
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.3599999999999999,
|
| 958 |
+
"grad_norm": 36.01056671142578,
|
| 959 |
+
"learning_rate": 6.602499999999999e-07,
|
| 960 |
+
"loss": 1.5688,
|
| 961 |
+
"step": 6800
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.37,
|
| 965 |
+
"grad_norm": 40.94023895263672,
|
| 966 |
+
"learning_rate": 6.577499999999999e-07,
|
| 967 |
+
"loss": 1.5867,
|
| 968 |
+
"step": 6850
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.38,
|
| 972 |
+
"grad_norm": 45.53089141845703,
|
| 973 |
+
"learning_rate": 6.5525e-07,
|
| 974 |
+
"loss": 1.5666,
|
| 975 |
+
"step": 6900
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.3900000000000001,
|
| 979 |
+
"grad_norm": 37.20089340209961,
|
| 980 |
+
"learning_rate": 6.5275e-07,
|
| 981 |
+
"loss": 1.5804,
|
| 982 |
+
"step": 6950
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.4,
|
| 986 |
+
"grad_norm": 33.455230712890625,
|
| 987 |
+
"learning_rate": 6.502499999999999e-07,
|
| 988 |
+
"loss": 1.5933,
|
| 989 |
+
"step": 7000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.41,
|
| 993 |
+
"grad_norm": 39.31380844116211,
|
| 994 |
+
"learning_rate": 6.477500000000001e-07,
|
| 995 |
+
"loss": 1.6599,
|
| 996 |
+
"step": 7050
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.42,
|
| 1000 |
+
"grad_norm": 40.90291976928711,
|
| 1001 |
+
"learning_rate": 6.4525e-07,
|
| 1002 |
+
"loss": 1.7809,
|
| 1003 |
+
"step": 7100
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.43,
|
| 1007 |
+
"grad_norm": 38.44248580932617,
|
| 1008 |
+
"learning_rate": 6.4275e-07,
|
| 1009 |
+
"loss": 1.554,
|
| 1010 |
+
"step": 7150
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.44,
|
| 1014 |
+
"grad_norm": 41.40769958496094,
|
| 1015 |
+
"learning_rate": 6.402499999999999e-07,
|
| 1016 |
+
"loss": 1.5848,
|
| 1017 |
+
"step": 7200
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.45,
|
| 1021 |
+
"grad_norm": 34.839202880859375,
|
| 1022 |
+
"learning_rate": 6.377500000000001e-07,
|
| 1023 |
+
"loss": 1.5506,
|
| 1024 |
+
"step": 7250
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.46,
|
| 1028 |
+
"grad_norm": 39.07792663574219,
|
| 1029 |
+
"learning_rate": 6.3525e-07,
|
| 1030 |
+
"loss": 1.6936,
|
| 1031 |
+
"step": 7300
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.47,
|
| 1035 |
+
"grad_norm": 47.81125259399414,
|
| 1036 |
+
"learning_rate": 6.3275e-07,
|
| 1037 |
+
"loss": 1.7948,
|
| 1038 |
+
"step": 7350
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.48,
|
| 1042 |
+
"grad_norm": 33.074684143066406,
|
| 1043 |
+
"learning_rate": 6.302499999999999e-07,
|
| 1044 |
+
"loss": 1.5964,
|
| 1045 |
+
"step": 7400
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.49,
|
| 1049 |
+
"grad_norm": 35.54746627807617,
|
| 1050 |
+
"learning_rate": 6.2775e-07,
|
| 1051 |
+
"loss": 1.5494,
|
| 1052 |
+
"step": 7450
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.5,
|
| 1056 |
+
"grad_norm": 47.26594543457031,
|
| 1057 |
+
"learning_rate": 6.2525e-07,
|
| 1058 |
+
"loss": 1.6013,
|
| 1059 |
+
"step": 7500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.51,
|
| 1063 |
+
"grad_norm": 47.13039779663086,
|
| 1064 |
+
"learning_rate": 6.2275e-07,
|
| 1065 |
+
"loss": 1.5403,
|
| 1066 |
+
"step": 7550
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.52,
|
| 1070 |
+
"grad_norm": 42.410614013671875,
|
| 1071 |
+
"learning_rate": 6.202499999999999e-07,
|
| 1072 |
+
"loss": 1.5956,
|
| 1073 |
+
"step": 7600
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.53,
|
| 1077 |
+
"grad_norm": 38.69276428222656,
|
| 1078 |
+
"learning_rate": 6.1775e-07,
|
| 1079 |
+
"loss": 1.6829,
|
| 1080 |
+
"step": 7650
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.54,
|
| 1084 |
+
"grad_norm": 41.635135650634766,
|
| 1085 |
+
"learning_rate": 6.1525e-07,
|
| 1086 |
+
"loss": 1.5228,
|
| 1087 |
+
"step": 7700
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.55,
|
| 1091 |
+
"grad_norm": 38.301753997802734,
|
| 1092 |
+
"learning_rate": 6.1275e-07,
|
| 1093 |
+
"loss": 1.5039,
|
| 1094 |
+
"step": 7750
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.56,
|
| 1098 |
+
"grad_norm": 40.455101013183594,
|
| 1099 |
+
"learning_rate": 6.102499999999999e-07,
|
| 1100 |
+
"loss": 1.5666,
|
| 1101 |
+
"step": 7800
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.5699999999999998,
|
| 1105 |
+
"grad_norm": 49.50397491455078,
|
| 1106 |
+
"learning_rate": 6.0775e-07,
|
| 1107 |
+
"loss": 1.5666,
|
| 1108 |
+
"step": 7850
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.58,
|
| 1112 |
+
"grad_norm": 51.95878601074219,
|
| 1113 |
+
"learning_rate": 6.052499999999999e-07,
|
| 1114 |
+
"loss": 1.5874,
|
| 1115 |
+
"step": 7900
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.5899999999999999,
|
| 1119 |
+
"grad_norm": 36.6114501953125,
|
| 1120 |
+
"learning_rate": 6.0275e-07,
|
| 1121 |
+
"loss": 1.63,
|
| 1122 |
+
"step": 7950
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.6,
|
| 1126 |
+
"grad_norm": 41.69790267944336,
|
| 1127 |
+
"learning_rate": 6.002499999999999e-07,
|
| 1128 |
+
"loss": 1.5995,
|
| 1129 |
+
"step": 8000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.6099999999999999,
|
| 1133 |
+
"grad_norm": 38.66043472290039,
|
| 1134 |
+
"learning_rate": 5.978e-07,
|
| 1135 |
+
"loss": 1.5629,
|
| 1136 |
+
"step": 8050
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.62,
|
| 1140 |
+
"grad_norm": 59.15949249267578,
|
| 1141 |
+
"learning_rate": 5.953e-07,
|
| 1142 |
+
"loss": 1.6076,
|
| 1143 |
+
"step": 8100
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.63,
|
| 1147 |
+
"grad_norm": 37.75910186767578,
|
| 1148 |
+
"learning_rate": 5.928e-07,
|
| 1149 |
+
"loss": 1.5531,
|
| 1150 |
+
"step": 8150
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.6400000000000001,
|
| 1154 |
+
"grad_norm": 40.374855041503906,
|
| 1155 |
+
"learning_rate": 5.903e-07,
|
| 1156 |
+
"loss": 1.5393,
|
| 1157 |
+
"step": 8200
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.65,
|
| 1161 |
+
"grad_norm": 47.41810989379883,
|
| 1162 |
+
"learning_rate": 5.878e-07,
|
| 1163 |
+
"loss": 1.5062,
|
| 1164 |
+
"step": 8250
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.6600000000000001,
|
| 1168 |
+
"grad_norm": 46.51014709472656,
|
| 1169 |
+
"learning_rate": 5.853e-07,
|
| 1170 |
+
"loss": 1.6144,
|
| 1171 |
+
"step": 8300
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.67,
|
| 1175 |
+
"grad_norm": 49.626834869384766,
|
| 1176 |
+
"learning_rate": 5.828e-07,
|
| 1177 |
+
"loss": 1.6439,
|
| 1178 |
+
"step": 8350
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.6800000000000002,
|
| 1182 |
+
"grad_norm": 32.59950256347656,
|
| 1183 |
+
"learning_rate": 5.803e-07,
|
| 1184 |
+
"loss": 1.5362,
|
| 1185 |
+
"step": 8400
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.69,
|
| 1189 |
+
"grad_norm": 49.02924346923828,
|
| 1190 |
+
"learning_rate": 5.778e-07,
|
| 1191 |
+
"loss": 1.7244,
|
| 1192 |
+
"step": 8450
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.7,
|
| 1196 |
+
"grad_norm": 41.86074447631836,
|
| 1197 |
+
"learning_rate": 5.753e-07,
|
| 1198 |
+
"loss": 1.5701,
|
| 1199 |
+
"step": 8500
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.71,
|
| 1203 |
+
"grad_norm": 30.711210250854492,
|
| 1204 |
+
"learning_rate": 5.727999999999999e-07,
|
| 1205 |
+
"loss": 1.6219,
|
| 1206 |
+
"step": 8550
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.72,
|
| 1210 |
+
"grad_norm": 47.8115234375,
|
| 1211 |
+
"learning_rate": 5.703e-07,
|
| 1212 |
+
"loss": 1.5723,
|
| 1213 |
+
"step": 8600
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.73,
|
| 1217 |
+
"grad_norm": 39.29584884643555,
|
| 1218 |
+
"learning_rate": 5.678e-07,
|
| 1219 |
+
"loss": 1.5869,
|
| 1220 |
+
"step": 8650
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.74,
|
| 1224 |
+
"grad_norm": 31.378740310668945,
|
| 1225 |
+
"learning_rate": 5.653e-07,
|
| 1226 |
+
"loss": 1.635,
|
| 1227 |
+
"step": 8700
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.75,
|
| 1231 |
+
"grad_norm": 38.850608825683594,
|
| 1232 |
+
"learning_rate": 5.627999999999999e-07,
|
| 1233 |
+
"loss": 1.6046,
|
| 1234 |
+
"step": 8750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.76,
|
| 1238 |
+
"grad_norm": 26.495405197143555,
|
| 1239 |
+
"learning_rate": 5.603e-07,
|
| 1240 |
+
"loss": 1.6276,
|
| 1241 |
+
"step": 8800
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.77,
|
| 1245 |
+
"grad_norm": 44.871849060058594,
|
| 1246 |
+
"learning_rate": 5.578e-07,
|
| 1247 |
+
"loss": 1.6889,
|
| 1248 |
+
"step": 8850
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.78,
|
| 1252 |
+
"grad_norm": 47.68773651123047,
|
| 1253 |
+
"learning_rate": 5.553e-07,
|
| 1254 |
+
"loss": 1.7151,
|
| 1255 |
+
"step": 8900
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.79,
|
| 1259 |
+
"grad_norm": 31.6007080078125,
|
| 1260 |
+
"learning_rate": 5.527999999999999e-07,
|
| 1261 |
+
"loss": 1.5286,
|
| 1262 |
+
"step": 8950
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.8,
|
| 1266 |
+
"grad_norm": 30.19587516784668,
|
| 1267 |
+
"learning_rate": 5.502999999999999e-07,
|
| 1268 |
+
"loss": 1.6597,
|
| 1269 |
+
"step": 9000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.81,
|
| 1273 |
+
"grad_norm": 36.03053665161133,
|
| 1274 |
+
"learning_rate": 5.478e-07,
|
| 1275 |
+
"loss": 1.6422,
|
| 1276 |
+
"step": 9050
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.8199999999999998,
|
| 1280 |
+
"grad_norm": 41.28793716430664,
|
| 1281 |
+
"learning_rate": 5.453e-07,
|
| 1282 |
+
"loss": 1.6893,
|
| 1283 |
+
"step": 9100
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.83,
|
| 1287 |
+
"grad_norm": 32.481689453125,
|
| 1288 |
+
"learning_rate": 5.427999999999999e-07,
|
| 1289 |
+
"loss": 1.5683,
|
| 1290 |
+
"step": 9150
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.8399999999999999,
|
| 1294 |
+
"grad_norm": 40.114654541015625,
|
| 1295 |
+
"learning_rate": 5.402999999999999e-07,
|
| 1296 |
+
"loss": 1.6021,
|
| 1297 |
+
"step": 9200
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.85,
|
| 1301 |
+
"grad_norm": 44.78034210205078,
|
| 1302 |
+
"learning_rate": 5.378e-07,
|
| 1303 |
+
"loss": 1.6241,
|
| 1304 |
+
"step": 9250
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.8599999999999999,
|
| 1308 |
+
"grad_norm": 32.96756362915039,
|
| 1309 |
+
"learning_rate": 5.353e-07,
|
| 1310 |
+
"loss": 1.4664,
|
| 1311 |
+
"step": 9300
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.87,
|
| 1315 |
+
"grad_norm": 35.44109344482422,
|
| 1316 |
+
"learning_rate": 5.328e-07,
|
| 1317 |
+
"loss": 1.6045,
|
| 1318 |
+
"step": 9350
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.88,
|
| 1322 |
+
"grad_norm": 47.10539245605469,
|
| 1323 |
+
"learning_rate": 5.302999999999999e-07,
|
| 1324 |
+
"loss": 1.6529,
|
| 1325 |
+
"step": 9400
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.8900000000000001,
|
| 1329 |
+
"grad_norm": 35.667083740234375,
|
| 1330 |
+
"learning_rate": 5.278000000000001e-07,
|
| 1331 |
+
"loss": 1.6878,
|
| 1332 |
+
"step": 9450
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.9,
|
| 1336 |
+
"grad_norm": 42.152652740478516,
|
| 1337 |
+
"learning_rate": 5.253e-07,
|
| 1338 |
+
"loss": 1.6694,
|
| 1339 |
+
"step": 9500
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.9100000000000001,
|
| 1343 |
+
"grad_norm": 44.23321533203125,
|
| 1344 |
+
"learning_rate": 5.228e-07,
|
| 1345 |
+
"loss": 1.61,
|
| 1346 |
+
"step": 9550
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.92,
|
| 1350 |
+
"grad_norm": 37.32196807861328,
|
| 1351 |
+
"learning_rate": 5.202999999999999e-07,
|
| 1352 |
+
"loss": 1.5521,
|
| 1353 |
+
"step": 9600
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.9300000000000002,
|
| 1357 |
+
"grad_norm": 51.841514587402344,
|
| 1358 |
+
"learning_rate": 5.178e-07,
|
| 1359 |
+
"loss": 1.682,
|
| 1360 |
+
"step": 9650
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.94,
|
| 1364 |
+
"grad_norm": 41.69253158569336,
|
| 1365 |
+
"learning_rate": 5.153e-07,
|
| 1366 |
+
"loss": 1.6228,
|
| 1367 |
+
"step": 9700
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.95,
|
| 1371 |
+
"grad_norm": 32.16023635864258,
|
| 1372 |
+
"learning_rate": 5.128e-07,
|
| 1373 |
+
"loss": 1.6022,
|
| 1374 |
+
"step": 9750
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.96,
|
| 1378 |
+
"grad_norm": 40.430206298828125,
|
| 1379 |
+
"learning_rate": 5.102999999999999e-07,
|
| 1380 |
+
"loss": 1.6262,
|
| 1381 |
+
"step": 9800
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.97,
|
| 1385 |
+
"grad_norm": 47.571449279785156,
|
| 1386 |
+
"learning_rate": 5.078e-07,
|
| 1387 |
+
"loss": 1.6431,
|
| 1388 |
+
"step": 9850
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.98,
|
| 1392 |
+
"grad_norm": 40.32009506225586,
|
| 1393 |
+
"learning_rate": 5.053e-07,
|
| 1394 |
+
"loss": 1.4864,
|
| 1395 |
+
"step": 9900
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.99,
|
| 1399 |
+
"grad_norm": 40.59520721435547,
|
| 1400 |
+
"learning_rate": 5.028e-07,
|
| 1401 |
+
"loss": 1.595,
|
| 1402 |
+
"step": 9950
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.0,
|
| 1406 |
+
"grad_norm": 44.62666702270508,
|
| 1407 |
+
"learning_rate": 5.002999999999999e-07,
|
| 1408 |
+
"loss": 1.5604,
|
| 1409 |
+
"step": 10000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.01,
|
| 1413 |
+
"grad_norm": 37.61200714111328,
|
| 1414 |
+
"learning_rate": 4.9785e-07,
|
| 1415 |
+
"loss": 1.6435,
|
| 1416 |
+
"step": 10050
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.02,
|
| 1420 |
+
"grad_norm": 40.34099197387695,
|
| 1421 |
+
"learning_rate": 4.953499999999999e-07,
|
| 1422 |
+
"loss": 1.7094,
|
| 1423 |
+
"step": 10100
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.03,
|
| 1427 |
+
"grad_norm": 47.07732009887695,
|
| 1428 |
+
"learning_rate": 4.9285e-07,
|
| 1429 |
+
"loss": 1.5482,
|
| 1430 |
+
"step": 10150
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.04,
|
| 1434 |
+
"grad_norm": 23.103185653686523,
|
| 1435 |
+
"learning_rate": 4.9035e-07,
|
| 1436 |
+
"loss": 1.6298,
|
| 1437 |
+
"step": 10200
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.05,
|
| 1441 |
+
"grad_norm": 44.33336639404297,
|
| 1442 |
+
"learning_rate": 4.8785e-07,
|
| 1443 |
+
"loss": 1.5512,
|
| 1444 |
+
"step": 10250
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.06,
|
| 1448 |
+
"grad_norm": 41.70211410522461,
|
| 1449 |
+
"learning_rate": 4.853499999999999e-07,
|
| 1450 |
+
"loss": 1.4399,
|
| 1451 |
+
"step": 10300
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.07,
|
| 1455 |
+
"grad_norm": 36.45768737792969,
|
| 1456 |
+
"learning_rate": 4.8285e-07,
|
| 1457 |
+
"loss": 1.5103,
|
| 1458 |
+
"step": 10350
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.08,
|
| 1462 |
+
"grad_norm": 30.36566162109375,
|
| 1463 |
+
"learning_rate": 4.8035e-07,
|
| 1464 |
+
"loss": 1.4481,
|
| 1465 |
+
"step": 10400
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.09,
|
| 1469 |
+
"grad_norm": 35.793094635009766,
|
| 1470 |
+
"learning_rate": 4.7785e-07,
|
| 1471 |
+
"loss": 1.5339,
|
| 1472 |
+
"step": 10450
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.1,
|
| 1476 |
+
"grad_norm": 52.48720932006836,
|
| 1477 |
+
"learning_rate": 4.7535e-07,
|
| 1478 |
+
"loss": 1.6079,
|
| 1479 |
+
"step": 10500
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.11,
|
| 1483 |
+
"grad_norm": 41.160335540771484,
|
| 1484 |
+
"learning_rate": 4.7284999999999995e-07,
|
| 1485 |
+
"loss": 1.4992,
|
| 1486 |
+
"step": 10550
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.12,
|
| 1490 |
+
"grad_norm": 40.25874710083008,
|
| 1491 |
+
"learning_rate": 4.7034999999999997e-07,
|
| 1492 |
+
"loss": 1.601,
|
| 1493 |
+
"step": 10600
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.13,
|
| 1497 |
+
"grad_norm": 35.40253829956055,
|
| 1498 |
+
"learning_rate": 4.6784999999999994e-07,
|
| 1499 |
+
"loss": 1.5437,
|
| 1500 |
+
"step": 10650
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.14,
|
| 1504 |
+
"grad_norm": 42.93209457397461,
|
| 1505 |
+
"learning_rate": 4.6534999999999997e-07,
|
| 1506 |
+
"loss": 1.5923,
|
| 1507 |
+
"step": 10700
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.15,
|
| 1511 |
+
"grad_norm": 43.273956298828125,
|
| 1512 |
+
"learning_rate": 4.6284999999999994e-07,
|
| 1513 |
+
"loss": 1.5925,
|
| 1514 |
+
"step": 10750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.16,
|
| 1518 |
+
"grad_norm": 49.30186080932617,
|
| 1519 |
+
"learning_rate": 4.6034999999999996e-07,
|
| 1520 |
+
"loss": 1.538,
|
| 1521 |
+
"step": 10800
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.17,
|
| 1525 |
+
"grad_norm": 40.10365295410156,
|
| 1526 |
+
"learning_rate": 4.5784999999999993e-07,
|
| 1527 |
+
"loss": 1.545,
|
| 1528 |
+
"step": 10850
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.18,
|
| 1532 |
+
"grad_norm": 40.76726531982422,
|
| 1533 |
+
"learning_rate": 4.5534999999999996e-07,
|
| 1534 |
+
"loss": 1.4837,
|
| 1535 |
+
"step": 10900
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.19,
|
| 1539 |
+
"grad_norm": 36.3805046081543,
|
| 1540 |
+
"learning_rate": 4.5284999999999993e-07,
|
| 1541 |
+
"loss": 1.5463,
|
| 1542 |
+
"step": 10950
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.2,
|
| 1546 |
+
"grad_norm": 25.484167098999023,
|
| 1547 |
+
"learning_rate": 4.5034999999999995e-07,
|
| 1548 |
+
"loss": 1.5916,
|
| 1549 |
+
"step": 11000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.21,
|
| 1553 |
+
"grad_norm": 33.473121643066406,
|
| 1554 |
+
"learning_rate": 4.4785000000000003e-07,
|
| 1555 |
+
"loss": 1.5033,
|
| 1556 |
+
"step": 11050
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.22,
|
| 1560 |
+
"grad_norm": 36.8259391784668,
|
| 1561 |
+
"learning_rate": 4.4535e-07,
|
| 1562 |
+
"loss": 1.552,
|
| 1563 |
+
"step": 11100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.23,
|
| 1567 |
+
"grad_norm": 32.61063766479492,
|
| 1568 |
+
"learning_rate": 4.4285e-07,
|
| 1569 |
+
"loss": 1.5759,
|
| 1570 |
+
"step": 11150
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.24,
|
| 1574 |
+
"grad_norm": 51.49959945678711,
|
| 1575 |
+
"learning_rate": 4.4035e-07,
|
| 1576 |
+
"loss": 1.556,
|
| 1577 |
+
"step": 11200
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.25,
|
| 1581 |
+
"grad_norm": 44.21879959106445,
|
| 1582 |
+
"learning_rate": 4.3785e-07,
|
| 1583 |
+
"loss": 1.4935,
|
| 1584 |
+
"step": 11250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.26,
|
| 1588 |
+
"grad_norm": 36.884010314941406,
|
| 1589 |
+
"learning_rate": 4.3535e-07,
|
| 1590 |
+
"loss": 1.4284,
|
| 1591 |
+
"step": 11300
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.27,
|
| 1595 |
+
"grad_norm": 38.094329833984375,
|
| 1596 |
+
"learning_rate": 4.3285e-07,
|
| 1597 |
+
"loss": 1.6868,
|
| 1598 |
+
"step": 11350
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.2800000000000002,
|
| 1602 |
+
"grad_norm": 41.53178024291992,
|
| 1603 |
+
"learning_rate": 4.3035e-07,
|
| 1604 |
+
"loss": 1.6034,
|
| 1605 |
+
"step": 11400
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.29,
|
| 1609 |
+
"grad_norm": 46.737213134765625,
|
| 1610 |
+
"learning_rate": 4.2785e-07,
|
| 1611 |
+
"loss": 1.5557,
|
| 1612 |
+
"step": 11450
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 2.3,
|
| 1616 |
+
"grad_norm": 50.67173385620117,
|
| 1617 |
+
"learning_rate": 4.2535e-07,
|
| 1618 |
+
"loss": 1.6998,
|
| 1619 |
+
"step": 11500
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.31,
|
| 1623 |
+
"grad_norm": 52.222557067871094,
|
| 1624 |
+
"learning_rate": 4.2285e-07,
|
| 1625 |
+
"loss": 1.5495,
|
| 1626 |
+
"step": 11550
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.32,
|
| 1630 |
+
"grad_norm": 48.568050384521484,
|
| 1631 |
+
"learning_rate": 4.2035e-07,
|
| 1632 |
+
"loss": 1.5441,
|
| 1633 |
+
"step": 11600
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.33,
|
| 1637 |
+
"grad_norm": 55.280521392822266,
|
| 1638 |
+
"learning_rate": 4.1785e-07,
|
| 1639 |
+
"loss": 1.68,
|
| 1640 |
+
"step": 11650
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.34,
|
| 1644 |
+
"grad_norm": 42.30193328857422,
|
| 1645 |
+
"learning_rate": 4.1534999999999997e-07,
|
| 1646 |
+
"loss": 1.6276,
|
| 1647 |
+
"step": 11700
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.35,
|
| 1651 |
+
"grad_norm": 54.417327880859375,
|
| 1652 |
+
"learning_rate": 4.1285e-07,
|
| 1653 |
+
"loss": 1.5603,
|
| 1654 |
+
"step": 11750
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.36,
|
| 1658 |
+
"grad_norm": 33.117340087890625,
|
| 1659 |
+
"learning_rate": 4.1034999999999997e-07,
|
| 1660 |
+
"loss": 1.5169,
|
| 1661 |
+
"step": 11800
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.37,
|
| 1665 |
+
"grad_norm": 43.10250473022461,
|
| 1666 |
+
"learning_rate": 4.0785e-07,
|
| 1667 |
+
"loss": 1.4491,
|
| 1668 |
+
"step": 11850
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.38,
|
| 1672 |
+
"grad_norm": 48.663917541503906,
|
| 1673 |
+
"learning_rate": 4.0534999999999996e-07,
|
| 1674 |
+
"loss": 1.5617,
|
| 1675 |
+
"step": 11900
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.39,
|
| 1679 |
+
"grad_norm": 41.02192687988281,
|
| 1680 |
+
"learning_rate": 4.0285e-07,
|
| 1681 |
+
"loss": 1.6111,
|
| 1682 |
+
"step": 11950
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.4,
|
| 1686 |
+
"grad_norm": 42.699256896972656,
|
| 1687 |
+
"learning_rate": 4.0034999999999996e-07,
|
| 1688 |
+
"loss": 1.4217,
|
| 1689 |
+
"step": 12000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.41,
|
| 1693 |
+
"grad_norm": 49.665855407714844,
|
| 1694 |
+
"learning_rate": 3.979e-07,
|
| 1695 |
+
"loss": 1.4223,
|
| 1696 |
+
"step": 12050
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.42,
|
| 1700 |
+
"grad_norm": 43.366397857666016,
|
| 1701 |
+
"learning_rate": 3.9539999999999995e-07,
|
| 1702 |
+
"loss": 1.5452,
|
| 1703 |
+
"step": 12100
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.43,
|
| 1707 |
+
"grad_norm": 35.55706024169922,
|
| 1708 |
+
"learning_rate": 3.9290000000000003e-07,
|
| 1709 |
+
"loss": 1.545,
|
| 1710 |
+
"step": 12150
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.44,
|
| 1714 |
+
"grad_norm": 42.98080062866211,
|
| 1715 |
+
"learning_rate": 3.904e-07,
|
| 1716 |
+
"loss": 1.5648,
|
| 1717 |
+
"step": 12200
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.45,
|
| 1721 |
+
"grad_norm": 36.39263916015625,
|
| 1722 |
+
"learning_rate": 3.879e-07,
|
| 1723 |
+
"loss": 1.5724,
|
| 1724 |
+
"step": 12250
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.46,
|
| 1728 |
+
"grad_norm": 42.547401428222656,
|
| 1729 |
+
"learning_rate": 3.854e-07,
|
| 1730 |
+
"loss": 1.7179,
|
| 1731 |
+
"step": 12300
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.4699999999999998,
|
| 1735 |
+
"grad_norm": 45.591087341308594,
|
| 1736 |
+
"learning_rate": 3.829e-07,
|
| 1737 |
+
"loss": 1.5122,
|
| 1738 |
+
"step": 12350
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.48,
|
| 1742 |
+
"grad_norm": 43.481258392333984,
|
| 1743 |
+
"learning_rate": 3.804e-07,
|
| 1744 |
+
"loss": 1.4843,
|
| 1745 |
+
"step": 12400
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.49,
|
| 1749 |
+
"grad_norm": 44.69862747192383,
|
| 1750 |
+
"learning_rate": 3.779e-07,
|
| 1751 |
+
"loss": 1.5978,
|
| 1752 |
+
"step": 12450
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.5,
|
| 1756 |
+
"grad_norm": 43.04928970336914,
|
| 1757 |
+
"learning_rate": 3.754e-07,
|
| 1758 |
+
"loss": 1.512,
|
| 1759 |
+
"step": 12500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.51,
|
| 1763 |
+
"grad_norm": 35.41480255126953,
|
| 1764 |
+
"learning_rate": 3.729e-07,
|
| 1765 |
+
"loss": 1.6957,
|
| 1766 |
+
"step": 12550
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 2.52,
|
| 1770 |
+
"grad_norm": 42.25669860839844,
|
| 1771 |
+
"learning_rate": 3.704e-07,
|
| 1772 |
+
"loss": 1.4797,
|
| 1773 |
+
"step": 12600
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.5300000000000002,
|
| 1777 |
+
"grad_norm": 23.68979835510254,
|
| 1778 |
+
"learning_rate": 3.679e-07,
|
| 1779 |
+
"loss": 1.515,
|
| 1780 |
+
"step": 12650
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.54,
|
| 1784 |
+
"grad_norm": 39.010196685791016,
|
| 1785 |
+
"learning_rate": 3.654e-07,
|
| 1786 |
+
"loss": 1.5484,
|
| 1787 |
+
"step": 12700
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.55,
|
| 1791 |
+
"grad_norm": 40.15721130371094,
|
| 1792 |
+
"learning_rate": 3.629e-07,
|
| 1793 |
+
"loss": 1.595,
|
| 1794 |
+
"step": 12750
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.56,
|
| 1798 |
+
"grad_norm": 32.100643157958984,
|
| 1799 |
+
"learning_rate": 3.6039999999999997e-07,
|
| 1800 |
+
"loss": 1.5125,
|
| 1801 |
+
"step": 12800
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.57,
|
| 1805 |
+
"grad_norm": 51.687583923339844,
|
| 1806 |
+
"learning_rate": 3.579e-07,
|
| 1807 |
+
"loss": 1.6924,
|
| 1808 |
+
"step": 12850
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.58,
|
| 1812 |
+
"grad_norm": 40.378807067871094,
|
| 1813 |
+
"learning_rate": 3.5539999999999997e-07,
|
| 1814 |
+
"loss": 1.5349,
|
| 1815 |
+
"step": 12900
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.59,
|
| 1819 |
+
"grad_norm": 46.35411834716797,
|
| 1820 |
+
"learning_rate": 3.529e-07,
|
| 1821 |
+
"loss": 1.4451,
|
| 1822 |
+
"step": 12950
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.6,
|
| 1826 |
+
"grad_norm": 39.091644287109375,
|
| 1827 |
+
"learning_rate": 3.5039999999999996e-07,
|
| 1828 |
+
"loss": 1.5871,
|
| 1829 |
+
"step": 13000
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.61,
|
| 1833 |
+
"grad_norm": 46.588539123535156,
|
| 1834 |
+
"learning_rate": 3.479e-07,
|
| 1835 |
+
"loss": 1.5514,
|
| 1836 |
+
"step": 13050
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.62,
|
| 1840 |
+
"grad_norm": 40.58433151245117,
|
| 1841 |
+
"learning_rate": 3.4539999999999996e-07,
|
| 1842 |
+
"loss": 1.6805,
|
| 1843 |
+
"step": 13100
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 2.63,
|
| 1847 |
+
"grad_norm": 44.80520248413086,
|
| 1848 |
+
"learning_rate": 3.429e-07,
|
| 1849 |
+
"loss": 1.4672,
|
| 1850 |
+
"step": 13150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.64,
|
| 1854 |
+
"grad_norm": 42.662078857421875,
|
| 1855 |
+
"learning_rate": 3.4039999999999995e-07,
|
| 1856 |
+
"loss": 1.5712,
|
| 1857 |
+
"step": 13200
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.65,
|
| 1861 |
+
"grad_norm": 40.33576583862305,
|
| 1862 |
+
"learning_rate": 3.379e-07,
|
| 1863 |
+
"loss": 1.4617,
|
| 1864 |
+
"step": 13250
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.66,
|
| 1868 |
+
"grad_norm": 44.45260238647461,
|
| 1869 |
+
"learning_rate": 3.3539999999999995e-07,
|
| 1870 |
+
"loss": 1.5336,
|
| 1871 |
+
"step": 13300
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.67,
|
| 1875 |
+
"grad_norm": 48.2208251953125,
|
| 1876 |
+
"learning_rate": 3.3289999999999997e-07,
|
| 1877 |
+
"loss": 1.5241,
|
| 1878 |
+
"step": 13350
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.68,
|
| 1882 |
+
"grad_norm": 37.904762268066406,
|
| 1883 |
+
"learning_rate": 3.304e-07,
|
| 1884 |
+
"loss": 1.5679,
|
| 1885 |
+
"step": 13400
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 2.69,
|
| 1889 |
+
"grad_norm": 39.32900619506836,
|
| 1890 |
+
"learning_rate": 3.279e-07,
|
| 1891 |
+
"loss": 1.5121,
|
| 1892 |
+
"step": 13450
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 2.7,
|
| 1896 |
+
"grad_norm": 36.95504379272461,
|
| 1897 |
+
"learning_rate": 3.254e-07,
|
| 1898 |
+
"loss": 1.4855,
|
| 1899 |
+
"step": 13500
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 2.71,
|
| 1903 |
+
"grad_norm": 29.145931243896484,
|
| 1904 |
+
"learning_rate": 3.229e-07,
|
| 1905 |
+
"loss": 1.5645,
|
| 1906 |
+
"step": 13550
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.7199999999999998,
|
| 1910 |
+
"grad_norm": 41.01043701171875,
|
| 1911 |
+
"learning_rate": 3.204e-07,
|
| 1912 |
+
"loss": 1.4902,
|
| 1913 |
+
"step": 13600
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 2.73,
|
| 1917 |
+
"grad_norm": 42.938472747802734,
|
| 1918 |
+
"learning_rate": 3.179e-07,
|
| 1919 |
+
"loss": 1.421,
|
| 1920 |
+
"step": 13650
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.74,
|
| 1924 |
+
"grad_norm": 42.611812591552734,
|
| 1925 |
+
"learning_rate": 3.154e-07,
|
| 1926 |
+
"loss": 1.6238,
|
| 1927 |
+
"step": 13700
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.75,
|
| 1931 |
+
"grad_norm": 40.880706787109375,
|
| 1932 |
+
"learning_rate": 3.129e-07,
|
| 1933 |
+
"loss": 1.554,
|
| 1934 |
+
"step": 13750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.76,
|
| 1938 |
+
"grad_norm": 44.605411529541016,
|
| 1939 |
+
"learning_rate": 3.104e-07,
|
| 1940 |
+
"loss": 1.631,
|
| 1941 |
+
"step": 13800
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.77,
|
| 1945 |
+
"grad_norm": 35.732723236083984,
|
| 1946 |
+
"learning_rate": 3.079e-07,
|
| 1947 |
+
"loss": 1.5479,
|
| 1948 |
+
"step": 13850
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 2.7800000000000002,
|
| 1952 |
+
"grad_norm": 38.93905258178711,
|
| 1953 |
+
"learning_rate": 3.0539999999999997e-07,
|
| 1954 |
+
"loss": 1.5417,
|
| 1955 |
+
"step": 13900
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 2.79,
|
| 1959 |
+
"grad_norm": 50.35736083984375,
|
| 1960 |
+
"learning_rate": 3.029e-07,
|
| 1961 |
+
"loss": 1.6767,
|
| 1962 |
+
"step": 13950
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 2.8,
|
| 1966 |
+
"grad_norm": 35.24892807006836,
|
| 1967 |
+
"learning_rate": 3.0039999999999996e-07,
|
| 1968 |
+
"loss": 1.5639,
|
| 1969 |
+
"step": 14000
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 2.81,
|
| 1973 |
+
"grad_norm": 41.46996307373047,
|
| 1974 |
+
"learning_rate": 2.9795e-07,
|
| 1975 |
+
"loss": 1.4937,
|
| 1976 |
+
"step": 14050
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 2.82,
|
| 1980 |
+
"grad_norm": 39.519866943359375,
|
| 1981 |
+
"learning_rate": 2.9544999999999996e-07,
|
| 1982 |
+
"loss": 1.6308,
|
| 1983 |
+
"step": 14100
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 2.83,
|
| 1987 |
+
"grad_norm": 44.51643753051758,
|
| 1988 |
+
"learning_rate": 2.9295e-07,
|
| 1989 |
+
"loss": 1.4379,
|
| 1990 |
+
"step": 14150
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 2.84,
|
| 1994 |
+
"grad_norm": 35.87133026123047,
|
| 1995 |
+
"learning_rate": 2.9044999999999996e-07,
|
| 1996 |
+
"loss": 1.4668,
|
| 1997 |
+
"step": 14200
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 2.85,
|
| 2001 |
+
"grad_norm": 45.94535446166992,
|
| 2002 |
+
"learning_rate": 2.8795e-07,
|
| 2003 |
+
"loss": 1.6009,
|
| 2004 |
+
"step": 14250
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 2.86,
|
| 2008 |
+
"grad_norm": 44.09996032714844,
|
| 2009 |
+
"learning_rate": 2.8544999999999995e-07,
|
| 2010 |
+
"loss": 1.5932,
|
| 2011 |
+
"step": 14300
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 2.87,
|
| 2015 |
+
"grad_norm": 48.415313720703125,
|
| 2016 |
+
"learning_rate": 2.8295e-07,
|
| 2017 |
+
"loss": 1.5851,
|
| 2018 |
+
"step": 14350
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 2.88,
|
| 2022 |
+
"grad_norm": 33.39976501464844,
|
| 2023 |
+
"learning_rate": 2.8044999999999995e-07,
|
| 2024 |
+
"loss": 1.6999,
|
| 2025 |
+
"step": 14400
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 2.89,
|
| 2029 |
+
"grad_norm": 40.66514587402344,
|
| 2030 |
+
"learning_rate": 2.7794999999999997e-07,
|
| 2031 |
+
"loss": 1.4782,
|
| 2032 |
+
"step": 14450
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 2.9,
|
| 2036 |
+
"grad_norm": 45.65864944458008,
|
| 2037 |
+
"learning_rate": 2.7544999999999994e-07,
|
| 2038 |
+
"loss": 1.6338,
|
| 2039 |
+
"step": 14500
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 2.91,
|
| 2043 |
+
"grad_norm": 39.462677001953125,
|
| 2044 |
+
"learning_rate": 2.7295e-07,
|
| 2045 |
+
"loss": 1.5968,
|
| 2046 |
+
"step": 14550
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 2.92,
|
| 2050 |
+
"grad_norm": 41.13777542114258,
|
| 2051 |
+
"learning_rate": 2.7045e-07,
|
| 2052 |
+
"loss": 1.4837,
|
| 2053 |
+
"step": 14600
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 2.93,
|
| 2057 |
+
"grad_norm": 38.25054168701172,
|
| 2058 |
+
"learning_rate": 2.6795e-07,
|
| 2059 |
+
"loss": 1.5727,
|
| 2060 |
+
"step": 14650
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 2.94,
|
| 2064 |
+
"grad_norm": 37.76020431518555,
|
| 2065 |
+
"learning_rate": 2.6545e-07,
|
| 2066 |
+
"loss": 1.642,
|
| 2067 |
+
"step": 14700
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 2.95,
|
| 2071 |
+
"grad_norm": 50.80886459350586,
|
| 2072 |
+
"learning_rate": 2.6295e-07,
|
| 2073 |
+
"loss": 1.605,
|
| 2074 |
+
"step": 14750
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 2.96,
|
| 2078 |
+
"grad_norm": 52.12263870239258,
|
| 2079 |
+
"learning_rate": 2.6045e-07,
|
| 2080 |
+
"loss": 1.5843,
|
| 2081 |
+
"step": 14800
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 2.9699999999999998,
|
| 2085 |
+
"grad_norm": 40.298282623291016,
|
| 2086 |
+
"learning_rate": 2.5795e-07,
|
| 2087 |
+
"loss": 1.4729,
|
| 2088 |
+
"step": 14850
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 2.98,
|
| 2092 |
+
"grad_norm": 30.732044219970703,
|
| 2093 |
+
"learning_rate": 2.5545e-07,
|
| 2094 |
+
"loss": 1.5218,
|
| 2095 |
+
"step": 14900
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 2.99,
|
| 2099 |
+
"grad_norm": 43.94182586669922,
|
| 2100 |
+
"learning_rate": 2.5295e-07,
|
| 2101 |
+
"loss": 1.5147,
|
| 2102 |
+
"step": 14950
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 3.0,
|
| 2106 |
+
"grad_norm": 60.4287223815918,
|
| 2107 |
+
"learning_rate": 2.5044999999999997e-07,
|
| 2108 |
+
"loss": 1.446,
|
| 2109 |
+
"step": 15000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 3.01,
|
| 2113 |
+
"grad_norm": 35.2944221496582,
|
| 2114 |
+
"learning_rate": 2.4795e-07,
|
| 2115 |
+
"loss": 1.5543,
|
| 2116 |
+
"step": 15050
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.02,
|
| 2120 |
+
"grad_norm": 53.06623077392578,
|
| 2121 |
+
"learning_rate": 2.4544999999999996e-07,
|
| 2122 |
+
"loss": 1.5674,
|
| 2123 |
+
"step": 15100
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.03,
|
| 2127 |
+
"grad_norm": 56.413692474365234,
|
| 2128 |
+
"learning_rate": 2.4295e-07,
|
| 2129 |
+
"loss": 1.4601,
|
| 2130 |
+
"step": 15150
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.04,
|
| 2134 |
+
"grad_norm": 44.59477233886719,
|
| 2135 |
+
"learning_rate": 2.4045e-07,
|
| 2136 |
+
"loss": 1.5439,
|
| 2137 |
+
"step": 15200
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.05,
|
| 2141 |
+
"grad_norm": 46.42093276977539,
|
| 2142 |
+
"learning_rate": 2.3794999999999998e-07,
|
| 2143 |
+
"loss": 1.4917,
|
| 2144 |
+
"step": 15250
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.06,
|
| 2148 |
+
"grad_norm": 31.83967399597168,
|
| 2149 |
+
"learning_rate": 2.3544999999999998e-07,
|
| 2150 |
+
"loss": 1.5199,
|
| 2151 |
+
"step": 15300
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.07,
|
| 2155 |
+
"grad_norm": 52.99776077270508,
|
| 2156 |
+
"learning_rate": 2.3294999999999998e-07,
|
| 2157 |
+
"loss": 1.509,
|
| 2158 |
+
"step": 15350
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 3.08,
|
| 2162 |
+
"grad_norm": 47.901885986328125,
|
| 2163 |
+
"learning_rate": 2.3044999999999998e-07,
|
| 2164 |
+
"loss": 1.4072,
|
| 2165 |
+
"step": 15400
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 3.09,
|
| 2169 |
+
"grad_norm": 35.03591537475586,
|
| 2170 |
+
"learning_rate": 2.2795e-07,
|
| 2171 |
+
"loss": 1.4489,
|
| 2172 |
+
"step": 15450
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 3.1,
|
| 2176 |
+
"grad_norm": 40.465789794921875,
|
| 2177 |
+
"learning_rate": 2.2545e-07,
|
| 2178 |
+
"loss": 1.4475,
|
| 2179 |
+
"step": 15500
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 3.11,
|
| 2183 |
+
"grad_norm": 38.67084503173828,
|
| 2184 |
+
"learning_rate": 2.2295e-07,
|
| 2185 |
+
"loss": 1.4501,
|
| 2186 |
+
"step": 15550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 3.12,
|
| 2190 |
+
"grad_norm": 44.53215026855469,
|
| 2191 |
+
"learning_rate": 2.2045e-07,
|
| 2192 |
+
"loss": 1.5509,
|
| 2193 |
+
"step": 15600
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 3.13,
|
| 2197 |
+
"grad_norm": 50.45119857788086,
|
| 2198 |
+
"learning_rate": 2.1795e-07,
|
| 2199 |
+
"loss": 1.5862,
|
| 2200 |
+
"step": 15650
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 3.14,
|
| 2204 |
+
"grad_norm": 42.37192153930664,
|
| 2205 |
+
"learning_rate": 2.1545e-07,
|
| 2206 |
+
"loss": 1.6511,
|
| 2207 |
+
"step": 15700
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 3.15,
|
| 2211 |
+
"grad_norm": 39.11933898925781,
|
| 2212 |
+
"learning_rate": 2.1294999999999998e-07,
|
| 2213 |
+
"loss": 1.5206,
|
| 2214 |
+
"step": 15750
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 3.16,
|
| 2218 |
+
"grad_norm": 39.057823181152344,
|
| 2219 |
+
"learning_rate": 2.1044999999999998e-07,
|
| 2220 |
+
"loss": 1.4265,
|
| 2221 |
+
"step": 15800
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 3.17,
|
| 2225 |
+
"grad_norm": 32.509098052978516,
|
| 2226 |
+
"learning_rate": 2.0794999999999998e-07,
|
| 2227 |
+
"loss": 1.5199,
|
| 2228 |
+
"step": 15850
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 3.18,
|
| 2232 |
+
"grad_norm": 34.1364860534668,
|
| 2233 |
+
"learning_rate": 2.0544999999999998e-07,
|
| 2234 |
+
"loss": 1.5162,
|
| 2235 |
+
"step": 15900
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 3.19,
|
| 2239 |
+
"grad_norm": 48.204994201660156,
|
| 2240 |
+
"learning_rate": 2.0294999999999997e-07,
|
| 2241 |
+
"loss": 1.4383,
|
| 2242 |
+
"step": 15950
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 3.2,
|
| 2246 |
+
"grad_norm": 53.505615234375,
|
| 2247 |
+
"learning_rate": 2.0044999999999997e-07,
|
| 2248 |
+
"loss": 1.5337,
|
| 2249 |
+
"step": 16000
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 3.21,
|
| 2253 |
+
"grad_norm": 48.69506072998047,
|
| 2254 |
+
"learning_rate": 1.98e-07,
|
| 2255 |
+
"loss": 1.4313,
|
| 2256 |
+
"step": 16050
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 3.22,
|
| 2260 |
+
"grad_norm": 45.98126220703125,
|
| 2261 |
+
"learning_rate": 1.955e-07,
|
| 2262 |
+
"loss": 1.5255,
|
| 2263 |
+
"step": 16100
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 3.23,
|
| 2267 |
+
"grad_norm": 39.528587341308594,
|
| 2268 |
+
"learning_rate": 1.93e-07,
|
| 2269 |
+
"loss": 1.5407,
|
| 2270 |
+
"step": 16150
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 3.24,
|
| 2274 |
+
"grad_norm": 41.41926956176758,
|
| 2275 |
+
"learning_rate": 1.905e-07,
|
| 2276 |
+
"loss": 1.4167,
|
| 2277 |
+
"step": 16200
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 3.25,
|
| 2281 |
+
"grad_norm": 50.91017150878906,
|
| 2282 |
+
"learning_rate": 1.88e-07,
|
| 2283 |
+
"loss": 1.5819,
|
| 2284 |
+
"step": 16250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 3.26,
|
| 2288 |
+
"grad_norm": 51.679622650146484,
|
| 2289 |
+
"learning_rate": 1.855e-07,
|
| 2290 |
+
"loss": 1.573,
|
| 2291 |
+
"step": 16300
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 3.27,
|
| 2295 |
+
"grad_norm": 39.97464370727539,
|
| 2296 |
+
"learning_rate": 1.8299999999999998e-07,
|
| 2297 |
+
"loss": 1.4209,
|
| 2298 |
+
"step": 16350
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 3.2800000000000002,
|
| 2302 |
+
"grad_norm": 37.9398307800293,
|
| 2303 |
+
"learning_rate": 1.8049999999999998e-07,
|
| 2304 |
+
"loss": 1.4962,
|
| 2305 |
+
"step": 16400
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 3.29,
|
| 2309 |
+
"grad_norm": 41.62467956542969,
|
| 2310 |
+
"learning_rate": 1.7799999999999998e-07,
|
| 2311 |
+
"loss": 1.5011,
|
| 2312 |
+
"step": 16450
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 3.3,
|
| 2316 |
+
"grad_norm": 39.8488655090332,
|
| 2317 |
+
"learning_rate": 1.7549999999999998e-07,
|
| 2318 |
+
"loss": 1.5504,
|
| 2319 |
+
"step": 16500
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 3.31,
|
| 2323 |
+
"grad_norm": 39.093360900878906,
|
| 2324 |
+
"learning_rate": 1.7299999999999997e-07,
|
| 2325 |
+
"loss": 1.4504,
|
| 2326 |
+
"step": 16550
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 3.32,
|
| 2330 |
+
"grad_norm": 46.60807800292969,
|
| 2331 |
+
"learning_rate": 1.705e-07,
|
| 2332 |
+
"loss": 1.5712,
|
| 2333 |
+
"step": 16600
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 3.33,
|
| 2337 |
+
"grad_norm": 37.40671920776367,
|
| 2338 |
+
"learning_rate": 1.68e-07,
|
| 2339 |
+
"loss": 1.5793,
|
| 2340 |
+
"step": 16650
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 3.34,
|
| 2344 |
+
"grad_norm": 45.785953521728516,
|
| 2345 |
+
"learning_rate": 1.655e-07,
|
| 2346 |
+
"loss": 1.4975,
|
| 2347 |
+
"step": 16700
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 3.35,
|
| 2351 |
+
"grad_norm": 42.13127517700195,
|
| 2352 |
+
"learning_rate": 1.63e-07,
|
| 2353 |
+
"loss": 1.5418,
|
| 2354 |
+
"step": 16750
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 3.36,
|
| 2358 |
+
"grad_norm": 51.313777923583984,
|
| 2359 |
+
"learning_rate": 1.605e-07,
|
| 2360 |
+
"loss": 1.6146,
|
| 2361 |
+
"step": 16800
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 3.37,
|
| 2365 |
+
"grad_norm": 38.90798568725586,
|
| 2366 |
+
"learning_rate": 1.5799999999999999e-07,
|
| 2367 |
+
"loss": 1.5328,
|
| 2368 |
+
"step": 16850
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 3.38,
|
| 2372 |
+
"grad_norm": 42.80254364013672,
|
| 2373 |
+
"learning_rate": 1.5549999999999998e-07,
|
| 2374 |
+
"loss": 1.4382,
|
| 2375 |
+
"step": 16900
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 3.39,
|
| 2379 |
+
"grad_norm": 38.583885192871094,
|
| 2380 |
+
"learning_rate": 1.5299999999999998e-07,
|
| 2381 |
+
"loss": 1.421,
|
| 2382 |
+
"step": 16950
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 3.4,
|
| 2386 |
+
"grad_norm": 45.506473541259766,
|
| 2387 |
+
"learning_rate": 1.5049999999999998e-07,
|
| 2388 |
+
"loss": 1.4643,
|
| 2389 |
+
"step": 17000
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 3.41,
|
| 2393 |
+
"grad_norm": 37.714202880859375,
|
| 2394 |
+
"learning_rate": 1.4799999999999998e-07,
|
| 2395 |
+
"loss": 1.4807,
|
| 2396 |
+
"step": 17050
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 3.42,
|
| 2400 |
+
"grad_norm": 52.356605529785156,
|
| 2401 |
+
"learning_rate": 1.4549999999999997e-07,
|
| 2402 |
+
"loss": 1.4663,
|
| 2403 |
+
"step": 17100
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 3.43,
|
| 2407 |
+
"grad_norm": 40.869590759277344,
|
| 2408 |
+
"learning_rate": 1.4299999999999997e-07,
|
| 2409 |
+
"loss": 1.542,
|
| 2410 |
+
"step": 17150
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 3.44,
|
| 2414 |
+
"grad_norm": 55.49686813354492,
|
| 2415 |
+
"learning_rate": 1.4050000000000002e-07,
|
| 2416 |
+
"loss": 1.5719,
|
| 2417 |
+
"step": 17200
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 3.45,
|
| 2421 |
+
"grad_norm": 41.89445114135742,
|
| 2422 |
+
"learning_rate": 1.3800000000000002e-07,
|
| 2423 |
+
"loss": 1.4327,
|
| 2424 |
+
"step": 17250
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 3.46,
|
| 2428 |
+
"grad_norm": 41.772361755371094,
|
| 2429 |
+
"learning_rate": 1.3550000000000002e-07,
|
| 2430 |
+
"loss": 1.5065,
|
| 2431 |
+
"step": 17300
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 3.4699999999999998,
|
| 2435 |
+
"grad_norm": 45.570396423339844,
|
| 2436 |
+
"learning_rate": 1.33e-07,
|
| 2437 |
+
"loss": 1.4851,
|
| 2438 |
+
"step": 17350
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 3.48,
|
| 2442 |
+
"grad_norm": 45.119693756103516,
|
| 2443 |
+
"learning_rate": 1.305e-07,
|
| 2444 |
+
"loss": 1.4926,
|
| 2445 |
+
"step": 17400
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 3.49,
|
| 2449 |
+
"grad_norm": 39.28087615966797,
|
| 2450 |
+
"learning_rate": 1.28e-07,
|
| 2451 |
+
"loss": 1.5135,
|
| 2452 |
+
"step": 17450
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 3.5,
|
| 2456 |
+
"grad_norm": 49.64841079711914,
|
| 2457 |
+
"learning_rate": 1.255e-07,
|
| 2458 |
+
"loss": 1.5662,
|
| 2459 |
+
"step": 17500
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 3.51,
|
| 2463 |
+
"grad_norm": 39.4202995300293,
|
| 2464 |
+
"learning_rate": 1.23e-07,
|
| 2465 |
+
"loss": 1.5854,
|
| 2466 |
+
"step": 17550
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 3.52,
|
| 2470 |
+
"grad_norm": 39.55594253540039,
|
| 2471 |
+
"learning_rate": 1.205e-07,
|
| 2472 |
+
"loss": 1.5577,
|
| 2473 |
+
"step": 17600
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 3.5300000000000002,
|
| 2477 |
+
"grad_norm": 38.05757522583008,
|
| 2478 |
+
"learning_rate": 1.1799999999999998e-07,
|
| 2479 |
+
"loss": 1.4087,
|
| 2480 |
+
"step": 17650
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 3.54,
|
| 2484 |
+
"grad_norm": 35.86211013793945,
|
| 2485 |
+
"learning_rate": 1.155e-07,
|
| 2486 |
+
"loss": 1.4881,
|
| 2487 |
+
"step": 17700
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 3.55,
|
| 2491 |
+
"grad_norm": 39.4666862487793,
|
| 2492 |
+
"learning_rate": 1.1299999999999999e-07,
|
| 2493 |
+
"loss": 1.5927,
|
| 2494 |
+
"step": 17750
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 3.56,
|
| 2498 |
+
"grad_norm": 42.395320892333984,
|
| 2499 |
+
"learning_rate": 1.1049999999999999e-07,
|
| 2500 |
+
"loss": 1.5176,
|
| 2501 |
+
"step": 17800
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 3.57,
|
| 2505 |
+
"grad_norm": 34.1979866027832,
|
| 2506 |
+
"learning_rate": 1.0799999999999999e-07,
|
| 2507 |
+
"loss": 1.545,
|
| 2508 |
+
"step": 17850
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 3.58,
|
| 2512 |
+
"grad_norm": 41.41266632080078,
|
| 2513 |
+
"learning_rate": 1.0549999999999999e-07,
|
| 2514 |
+
"loss": 1.5388,
|
| 2515 |
+
"step": 17900
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 3.59,
|
| 2519 |
+
"grad_norm": 40.88737869262695,
|
| 2520 |
+
"learning_rate": 1.03e-07,
|
| 2521 |
+
"loss": 1.4851,
|
| 2522 |
+
"step": 17950
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 3.6,
|
| 2526 |
+
"grad_norm": 44.86513137817383,
|
| 2527 |
+
"learning_rate": 1.005e-07,
|
| 2528 |
+
"loss": 1.5413,
|
| 2529 |
+
"step": 18000
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 3.61,
|
| 2533 |
+
"grad_norm": 38.92195510864258,
|
| 2534 |
+
"learning_rate": 9.805e-08,
|
| 2535 |
+
"loss": 1.5463,
|
| 2536 |
+
"step": 18050
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 3.62,
|
| 2540 |
+
"grad_norm": 46.53792953491211,
|
| 2541 |
+
"learning_rate": 9.554999999999999e-08,
|
| 2542 |
+
"loss": 1.5022,
|
| 2543 |
+
"step": 18100
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 3.63,
|
| 2547 |
+
"grad_norm": 35.3355598449707,
|
| 2548 |
+
"learning_rate": 9.304999999999999e-08,
|
| 2549 |
+
"loss": 1.5245,
|
| 2550 |
+
"step": 18150
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 3.64,
|
| 2554 |
+
"grad_norm": 55.84636306762695,
|
| 2555 |
+
"learning_rate": 9.055e-08,
|
| 2556 |
+
"loss": 1.6236,
|
| 2557 |
+
"step": 18200
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 3.65,
|
| 2561 |
+
"grad_norm": 36.84891128540039,
|
| 2562 |
+
"learning_rate": 8.805e-08,
|
| 2563 |
+
"loss": 1.3286,
|
| 2564 |
+
"step": 18250
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 3.66,
|
| 2568 |
+
"grad_norm": 51.336795806884766,
|
| 2569 |
+
"learning_rate": 8.555e-08,
|
| 2570 |
+
"loss": 1.5488,
|
| 2571 |
+
"step": 18300
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 3.67,
|
| 2575 |
+
"grad_norm": 38.55815887451172,
|
| 2576 |
+
"learning_rate": 8.304999999999999e-08,
|
| 2577 |
+
"loss": 1.4718,
|
| 2578 |
+
"step": 18350
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 3.68,
|
| 2582 |
+
"grad_norm": 47.52061462402344,
|
| 2583 |
+
"learning_rate": 8.054999999999999e-08,
|
| 2584 |
+
"loss": 1.5148,
|
| 2585 |
+
"step": 18400
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 3.69,
|
| 2589 |
+
"grad_norm": 42.93059539794922,
|
| 2590 |
+
"learning_rate": 7.804999999999999e-08,
|
| 2591 |
+
"loss": 1.5243,
|
| 2592 |
+
"step": 18450
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 3.7,
|
| 2596 |
+
"grad_norm": 40.72081756591797,
|
| 2597 |
+
"learning_rate": 7.555e-08,
|
| 2598 |
+
"loss": 1.4389,
|
| 2599 |
+
"step": 18500
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 3.71,
|
| 2603 |
+
"grad_norm": 42.075836181640625,
|
| 2604 |
+
"learning_rate": 7.305e-08,
|
| 2605 |
+
"loss": 1.5487,
|
| 2606 |
+
"step": 18550
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 3.7199999999999998,
|
| 2610 |
+
"grad_norm": 50.6606559753418,
|
| 2611 |
+
"learning_rate": 7.054999999999999e-08,
|
| 2612 |
+
"loss": 1.6045,
|
| 2613 |
+
"step": 18600
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 3.73,
|
| 2617 |
+
"grad_norm": 39.99626541137695,
|
| 2618 |
+
"learning_rate": 6.804999999999999e-08,
|
| 2619 |
+
"loss": 1.5214,
|
| 2620 |
+
"step": 18650
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 3.74,
|
| 2624 |
+
"grad_norm": 48.29393005371094,
|
| 2625 |
+
"learning_rate": 6.554999999999999e-08,
|
| 2626 |
+
"loss": 1.471,
|
| 2627 |
+
"step": 18700
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 3.75,
|
| 2631 |
+
"grad_norm": 41.546470642089844,
|
| 2632 |
+
"learning_rate": 6.304999999999999e-08,
|
| 2633 |
+
"loss": 1.4242,
|
| 2634 |
+
"step": 18750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 3.76,
|
| 2638 |
+
"grad_norm": 43.29277420043945,
|
| 2639 |
+
"learning_rate": 6.055e-08,
|
| 2640 |
+
"loss": 1.3872,
|
| 2641 |
+
"step": 18800
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 3.77,
|
| 2645 |
+
"grad_norm": 60.80516052246094,
|
| 2646 |
+
"learning_rate": 5.8049999999999994e-08,
|
| 2647 |
+
"loss": 1.5309,
|
| 2648 |
+
"step": 18850
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 3.7800000000000002,
|
| 2652 |
+
"grad_norm": 37.9664421081543,
|
| 2653 |
+
"learning_rate": 5.555e-08,
|
| 2654 |
+
"loss": 1.4366,
|
| 2655 |
+
"step": 18900
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 3.79,
|
| 2659 |
+
"grad_norm": 41.17642593383789,
|
| 2660 |
+
"learning_rate": 5.3049999999999995e-08,
|
| 2661 |
+
"loss": 1.5797,
|
| 2662 |
+
"step": 18950
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 3.8,
|
| 2666 |
+
"grad_norm": 36.21015167236328,
|
| 2667 |
+
"learning_rate": 5.054999999999999e-08,
|
| 2668 |
+
"loss": 1.5096,
|
| 2669 |
+
"step": 19000
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 3.81,
|
| 2673 |
+
"grad_norm": 47.9669075012207,
|
| 2674 |
+
"learning_rate": 4.8050000000000003e-08,
|
| 2675 |
+
"loss": 1.5302,
|
| 2676 |
+
"step": 19050
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 3.82,
|
| 2680 |
+
"grad_norm": 28.955060958862305,
|
| 2681 |
+
"learning_rate": 4.555e-08,
|
| 2682 |
+
"loss": 1.498,
|
| 2683 |
+
"step": 19100
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 3.83,
|
| 2687 |
+
"grad_norm": 52.464290618896484,
|
| 2688 |
+
"learning_rate": 4.305e-08,
|
| 2689 |
+
"loss": 1.4575,
|
| 2690 |
+
"step": 19150
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 3.84,
|
| 2694 |
+
"grad_norm": 29.458721160888672,
|
| 2695 |
+
"learning_rate": 4.055e-08,
|
| 2696 |
+
"loss": 1.484,
|
| 2697 |
+
"step": 19200
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 3.85,
|
| 2701 |
+
"grad_norm": 41.32457733154297,
|
| 2702 |
+
"learning_rate": 3.805e-08,
|
| 2703 |
+
"loss": 1.4677,
|
| 2704 |
+
"step": 19250
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 3.86,
|
| 2708 |
+
"grad_norm": 48.74892807006836,
|
| 2709 |
+
"learning_rate": 3.555e-08,
|
| 2710 |
+
"loss": 1.4268,
|
| 2711 |
+
"step": 19300
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 3.87,
|
| 2715 |
+
"grad_norm": 30.619657516479492,
|
| 2716 |
+
"learning_rate": 3.305e-08,
|
| 2717 |
+
"loss": 1.5416,
|
| 2718 |
+
"step": 19350
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 3.88,
|
| 2722 |
+
"grad_norm": 48.18694305419922,
|
| 2723 |
+
"learning_rate": 3.055e-08,
|
| 2724 |
+
"loss": 1.4068,
|
| 2725 |
+
"step": 19400
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 3.89,
|
| 2729 |
+
"grad_norm": 35.75336456298828,
|
| 2730 |
+
"learning_rate": 2.8049999999999996e-08,
|
| 2731 |
+
"loss": 1.3868,
|
| 2732 |
+
"step": 19450
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 3.9,
|
| 2736 |
+
"grad_norm": 46.65244674682617,
|
| 2737 |
+
"learning_rate": 2.5549999999999997e-08,
|
| 2738 |
+
"loss": 1.5598,
|
| 2739 |
+
"step": 19500
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 3.91,
|
| 2743 |
+
"grad_norm": 48.187679290771484,
|
| 2744 |
+
"learning_rate": 2.305e-08,
|
| 2745 |
+
"loss": 1.5666,
|
| 2746 |
+
"step": 19550
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 3.92,
|
| 2750 |
+
"grad_norm": 36.0362663269043,
|
| 2751 |
+
"learning_rate": 2.055e-08,
|
| 2752 |
+
"loss": 1.6636,
|
| 2753 |
+
"step": 19600
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 3.93,
|
| 2757 |
+
"grad_norm": 55.22818374633789,
|
| 2758 |
+
"learning_rate": 1.805e-08,
|
| 2759 |
+
"loss": 1.5572,
|
| 2760 |
+
"step": 19650
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 3.94,
|
| 2764 |
+
"grad_norm": 32.651451110839844,
|
| 2765 |
+
"learning_rate": 1.555e-08,
|
| 2766 |
+
"loss": 1.5158,
|
| 2767 |
+
"step": 19700
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 3.95,
|
| 2771 |
+
"grad_norm": 42.34391403198242,
|
| 2772 |
+
"learning_rate": 1.3050000000000001e-08,
|
| 2773 |
+
"loss": 1.4648,
|
| 2774 |
+
"step": 19750
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 3.96,
|
| 2778 |
+
"grad_norm": 48.5484733581543,
|
| 2779 |
+
"learning_rate": 1.055e-08,
|
| 2780 |
+
"loss": 1.5808,
|
| 2781 |
+
"step": 19800
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 3.9699999999999998,
|
| 2785 |
+
"grad_norm": 51.64519500732422,
|
| 2786 |
+
"learning_rate": 8.05e-09,
|
| 2787 |
+
"loss": 1.4912,
|
| 2788 |
+
"step": 19850
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 3.98,
|
| 2792 |
+
"grad_norm": 44.73149490356445,
|
| 2793 |
+
"learning_rate": 5.55e-09,
|
| 2794 |
+
"loss": 1.694,
|
| 2795 |
+
"step": 19900
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 3.99,
|
| 2799 |
+
"grad_norm": 50.322174072265625,
|
| 2800 |
+
"learning_rate": 3.05e-09,
|
| 2801 |
+
"loss": 1.5025,
|
| 2802 |
+
"step": 19950
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 4.0,
|
| 2806 |
+
"grad_norm": 51.53582763671875,
|
| 2807 |
+
"learning_rate": 5.5e-10,
|
| 2808 |
+
"loss": 1.5558,
|
| 2809 |
+
"step": 20000
|
| 2810 |
+
}
|
| 2811 |
+
],
|
| 2812 |
+
"logging_steps": 50,
|
| 2813 |
+
"max_steps": 20000,
|
| 2814 |
+
"num_input_tokens_seen": 0,
|
| 2815 |
+
"num_train_epochs": 4,
|
| 2816 |
+
"save_steps": 1000,
|
| 2817 |
+
"stateful_callbacks": {
|
| 2818 |
+
"TrainerControl": {
|
| 2819 |
+
"args": {
|
| 2820 |
+
"should_epoch_stop": false,
|
| 2821 |
+
"should_evaluate": false,
|
| 2822 |
+
"should_log": false,
|
| 2823 |
+
"should_save": true,
|
| 2824 |
+
"should_training_stop": true
|
| 2825 |
+
},
|
| 2826 |
+
"attributes": {}
|
| 2827 |
+
}
|
| 2828 |
+
},
|
| 2829 |
+
"total_flos": 0.0,
|
| 2830 |
+
"train_batch_size": 8,
|
| 2831 |
+
"trial_name": null,
|
| 2832 |
+
"trial_params": null
|
| 2833 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:821091129660e331b5e9290e0f1e29183ca11670f5b35d0b75b8777e17556111
|
| 3 |
+
size 5304
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|