Upload 10 files
Browse files- README.md +61 -3
- all_results.json +8 -0
- config.json +33 -0
- generation_config.json +9 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2063 -0
- train_results.json +8 -0
- trainer_state.json +2242 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,61 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: outputs/iter0-ckpt
|
3 |
+
tags:
|
4 |
+
- alignment-handbook
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- new_data/iter0
|
8 |
+
- new_data/iter1
|
9 |
+
model-index:
|
10 |
+
- name: iter1-ckpt
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# iter1-ckpt
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [outputs/iter0-ckpt](https://huggingface.co/outputs/iter0-ckpt) on the new_data/iter0 and the new_data/iter1 datasets.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-07
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- num_devices: 8
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 64
|
46 |
+
- total_eval_batch_size: 8
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 6.0
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.37.0
|
59 |
+
- Pytorch 2.1.2+cu121
|
60 |
+
- Datasets 2.14.6
|
61 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.99,
|
3 |
+
"train_loss": 0.018845485343664946,
|
4 |
+
"train_runtime": 21431.5998,
|
5 |
+
"train_samples": 16800,
|
6 |
+
"train_samples_per_second": 4.703,
|
7 |
+
"train_steps_per_second": 0.073
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "outputs/iter0-ckpt",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128001,
|
10 |
+
"head_dim": 64,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 2048,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 8192,
|
15 |
+
"max_position_embeddings": 131072,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 32,
|
19 |
+
"num_hidden_layers": 16,
|
20 |
+
"num_key_value_heads": 8,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": {
|
24 |
+
"factor": 32.0,
|
25 |
+
"type": "linear"
|
26 |
+
},
|
27 |
+
"rope_theta": 500000.0,
|
28 |
+
"tie_word_embeddings": true,
|
29 |
+
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.37.0",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 128256
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 128000,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 128001,
|
6 |
+
"temperature": 0.6,
|
7 |
+
"top_p": 0.9,
|
8 |
+
"transformers_version": "4.37.0"
|
9 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end_of_text|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end_of_text|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|end_of_text|>",
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 131072,
|
2061 |
+
"pad_token": "<|end_of_text|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.99,
|
3 |
+
"train_loss": 0.018845485343664946,
|
4 |
+
"train_runtime": 21431.5998,
|
5 |
+
"train_samples": 16800,
|
6 |
+
"train_samples_per_second": 4.703,
|
7 |
+
"train_steps_per_second": 0.073
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2242 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.988571428571428,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 1572,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 3.1645569620253163e-09,
|
14 |
+
"logits/generated": 3.512105703353882,
|
15 |
+
"logits/real": 3.202550172805786,
|
16 |
+
"logps/generated": -465.1200256347656,
|
17 |
+
"logps/real": -1523.068603515625,
|
18 |
+
"loss": 0.6931,
|
19 |
+
"rewards/accuracies": 0.0,
|
20 |
+
"rewards/generated": 0.0,
|
21 |
+
"rewards/margins": 0.0,
|
22 |
+
"rewards/real": 0.0,
|
23 |
+
"step": 1
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.04,
|
27 |
+
"learning_rate": 3.1645569620253166e-08,
|
28 |
+
"logits/generated": 3.52996826171875,
|
29 |
+
"logits/real": 3.1474177837371826,
|
30 |
+
"logps/generated": -455.0594177246094,
|
31 |
+
"logps/real": -1564.237548828125,
|
32 |
+
"loss": 0.6843,
|
33 |
+
"rewards/accuracies": 0.4722222089767456,
|
34 |
+
"rewards/generated": 0.00841978657990694,
|
35 |
+
"rewards/margins": 0.014310520142316818,
|
36 |
+
"rewards/real": 0.022730309516191483,
|
37 |
+
"step": 10
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.08,
|
41 |
+
"learning_rate": 6.329113924050633e-08,
|
42 |
+
"logits/generated": 3.4747085571289062,
|
43 |
+
"logits/real": 2.9607560634613037,
|
44 |
+
"logps/generated": -404.8710632324219,
|
45 |
+
"logps/real": -1600.1513671875,
|
46 |
+
"loss": 0.5693,
|
47 |
+
"rewards/accuracies": 0.9125000238418579,
|
48 |
+
"rewards/generated": -0.09713525325059891,
|
49 |
+
"rewards/margins": 0.30425113439559937,
|
50 |
+
"rewards/real": 0.20711591839790344,
|
51 |
+
"step": 20
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.11,
|
55 |
+
"learning_rate": 9.49367088607595e-08,
|
56 |
+
"logits/generated": 3.6858959197998047,
|
57 |
+
"logits/real": 3.0412940979003906,
|
58 |
+
"logps/generated": -421.63653564453125,
|
59 |
+
"logps/real": -1533.8973388671875,
|
60 |
+
"loss": 0.3593,
|
61 |
+
"rewards/accuracies": 0.9624999761581421,
|
62 |
+
"rewards/generated": -0.3924674689769745,
|
63 |
+
"rewards/margins": 0.9940061569213867,
|
64 |
+
"rewards/real": 0.6015387177467346,
|
65 |
+
"step": 30
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.15,
|
69 |
+
"learning_rate": 1.2658227848101266e-07,
|
70 |
+
"logits/generated": 3.7982068061828613,
|
71 |
+
"logits/real": 2.8881797790527344,
|
72 |
+
"logps/generated": -403.89447021484375,
|
73 |
+
"logps/real": -2011.547607421875,
|
74 |
+
"loss": 0.2263,
|
75 |
+
"rewards/accuracies": 1.0,
|
76 |
+
"rewards/generated": -0.6449347734451294,
|
77 |
+
"rewards/margins": 1.951049566268921,
|
78 |
+
"rewards/real": 1.3061145544052124,
|
79 |
+
"step": 40
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.19,
|
83 |
+
"learning_rate": 1.5822784810126582e-07,
|
84 |
+
"logits/generated": 3.733821153640747,
|
85 |
+
"logits/real": 2.91530442237854,
|
86 |
+
"logps/generated": -424.7178649902344,
|
87 |
+
"logps/real": -1627.3607177734375,
|
88 |
+
"loss": 0.1737,
|
89 |
+
"rewards/accuracies": 0.987500011920929,
|
90 |
+
"rewards/generated": -1.025488257408142,
|
91 |
+
"rewards/margins": 2.2531561851501465,
|
92 |
+
"rewards/real": 1.2276678085327148,
|
93 |
+
"step": 50
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.23,
|
97 |
+
"learning_rate": 1.89873417721519e-07,
|
98 |
+
"logits/generated": 3.667829990386963,
|
99 |
+
"logits/real": 2.897120237350464,
|
100 |
+
"logps/generated": -397.2341003417969,
|
101 |
+
"logps/real": -1588.1214599609375,
|
102 |
+
"loss": 0.1079,
|
103 |
+
"rewards/accuracies": 1.0,
|
104 |
+
"rewards/generated": -1.396870493888855,
|
105 |
+
"rewards/margins": 3.004943370819092,
|
106 |
+
"rewards/real": 1.6080729961395264,
|
107 |
+
"step": 60
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.27,
|
111 |
+
"learning_rate": 2.2151898734177212e-07,
|
112 |
+
"logits/generated": 3.703988552093506,
|
113 |
+
"logits/real": 3.3058135509490967,
|
114 |
+
"logps/generated": -450.5978088378906,
|
115 |
+
"logps/real": -1583.788818359375,
|
116 |
+
"loss": 0.0638,
|
117 |
+
"rewards/accuracies": 1.0,
|
118 |
+
"rewards/generated": -2.1847541332244873,
|
119 |
+
"rewards/margins": 4.125738620758057,
|
120 |
+
"rewards/real": 1.9409840106964111,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.3,
|
125 |
+
"learning_rate": 2.5316455696202533e-07,
|
126 |
+
"logits/generated": 3.5381362438201904,
|
127 |
+
"logits/real": 3.0336380004882812,
|
128 |
+
"logps/generated": -426.459716796875,
|
129 |
+
"logps/real": -1585.524658203125,
|
130 |
+
"loss": 0.0623,
|
131 |
+
"rewards/accuracies": 0.987500011920929,
|
132 |
+
"rewards/generated": -1.9288753271102905,
|
133 |
+
"rewards/margins": 4.461968898773193,
|
134 |
+
"rewards/real": 2.533093214035034,
|
135 |
+
"step": 80
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.34,
|
139 |
+
"learning_rate": 2.848101265822785e-07,
|
140 |
+
"logits/generated": 3.9699149131774902,
|
141 |
+
"logits/real": 2.959277868270874,
|
142 |
+
"logps/generated": -462.84478759765625,
|
143 |
+
"logps/real": -1669.855712890625,
|
144 |
+
"loss": 0.0539,
|
145 |
+
"rewards/accuracies": 1.0,
|
146 |
+
"rewards/generated": -2.831137180328369,
|
147 |
+
"rewards/margins": 5.640450477600098,
|
148 |
+
"rewards/real": 2.8093132972717285,
|
149 |
+
"step": 90
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.38,
|
153 |
+
"learning_rate": 3.1645569620253163e-07,
|
154 |
+
"logits/generated": 3.649505615234375,
|
155 |
+
"logits/real": 3.228405475616455,
|
156 |
+
"logps/generated": -463.5885314941406,
|
157 |
+
"logps/real": -1659.1978759765625,
|
158 |
+
"loss": 0.0399,
|
159 |
+
"rewards/accuracies": 1.0,
|
160 |
+
"rewards/generated": -2.8427340984344482,
|
161 |
+
"rewards/margins": 6.116082668304443,
|
162 |
+
"rewards/real": 3.273348331451416,
|
163 |
+
"step": 100
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.42,
|
167 |
+
"learning_rate": 3.481012658227848e-07,
|
168 |
+
"logits/generated": 3.5634586811065674,
|
169 |
+
"logits/real": 3.0387678146362305,
|
170 |
+
"logps/generated": -475.7396545410156,
|
171 |
+
"logps/real": -1772.5689697265625,
|
172 |
+
"loss": 0.043,
|
173 |
+
"rewards/accuracies": 1.0,
|
174 |
+
"rewards/generated": -2.7554657459259033,
|
175 |
+
"rewards/margins": 6.204745292663574,
|
176 |
+
"rewards/real": 3.449280261993408,
|
177 |
+
"step": 110
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.46,
|
181 |
+
"learning_rate": 3.79746835443038e-07,
|
182 |
+
"logits/generated": 3.531033992767334,
|
183 |
+
"logits/real": 3.0381414890289307,
|
184 |
+
"logps/generated": -435.5464782714844,
|
185 |
+
"logps/real": -1628.22119140625,
|
186 |
+
"loss": 0.0403,
|
187 |
+
"rewards/accuracies": 1.0,
|
188 |
+
"rewards/generated": -2.647515296936035,
|
189 |
+
"rewards/margins": 5.9579033851623535,
|
190 |
+
"rewards/real": 3.3103878498077393,
|
191 |
+
"step": 120
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.5,
|
195 |
+
"learning_rate": 4.1139240506329117e-07,
|
196 |
+
"logits/generated": 3.513434648513794,
|
197 |
+
"logits/real": 2.99871826171875,
|
198 |
+
"logps/generated": -438.3785095214844,
|
199 |
+
"logps/real": -1705.972412109375,
|
200 |
+
"loss": 0.0341,
|
201 |
+
"rewards/accuracies": 1.0,
|
202 |
+
"rewards/generated": -3.1811232566833496,
|
203 |
+
"rewards/margins": 7.164037227630615,
|
204 |
+
"rewards/real": 3.982914447784424,
|
205 |
+
"step": 130
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.53,
|
209 |
+
"learning_rate": 4.4303797468354424e-07,
|
210 |
+
"logits/generated": 3.7991561889648438,
|
211 |
+
"logits/real": 3.105447292327881,
|
212 |
+
"logps/generated": -479.6163635253906,
|
213 |
+
"logps/real": -1677.7916259765625,
|
214 |
+
"loss": 0.0325,
|
215 |
+
"rewards/accuracies": 1.0,
|
216 |
+
"rewards/generated": -3.3546764850616455,
|
217 |
+
"rewards/margins": 7.303455352783203,
|
218 |
+
"rewards/real": 3.9487788677215576,
|
219 |
+
"step": 140
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.57,
|
223 |
+
"learning_rate": 4.746835443037974e-07,
|
224 |
+
"logits/generated": 3.594744920730591,
|
225 |
+
"logits/real": 2.9824934005737305,
|
226 |
+
"logps/generated": -436.2431640625,
|
227 |
+
"logps/real": -1721.3759765625,
|
228 |
+
"loss": 0.0232,
|
229 |
+
"rewards/accuracies": 1.0,
|
230 |
+
"rewards/generated": -3.755667209625244,
|
231 |
+
"rewards/margins": 7.839377403259277,
|
232 |
+
"rewards/real": 4.083710670471191,
|
233 |
+
"step": 150
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.61,
|
237 |
+
"learning_rate": 4.992927864214993e-07,
|
238 |
+
"logits/generated": 3.6612861156463623,
|
239 |
+
"logits/real": 2.9343557357788086,
|
240 |
+
"logps/generated": -483.659912109375,
|
241 |
+
"logps/real": -1582.573486328125,
|
242 |
+
"loss": 0.0205,
|
243 |
+
"rewards/accuracies": 1.0,
|
244 |
+
"rewards/generated": -3.5960216522216797,
|
245 |
+
"rewards/margins": 7.640145301818848,
|
246 |
+
"rewards/real": 4.04412317276001,
|
247 |
+
"step": 160
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.65,
|
251 |
+
"learning_rate": 4.957567185289958e-07,
|
252 |
+
"logits/generated": 3.589632034301758,
|
253 |
+
"logits/real": 3.0019402503967285,
|
254 |
+
"logps/generated": -425.794677734375,
|
255 |
+
"logps/real": -1487.097412109375,
|
256 |
+
"loss": 0.0221,
|
257 |
+
"rewards/accuracies": 1.0,
|
258 |
+
"rewards/generated": -3.8624930381774902,
|
259 |
+
"rewards/margins": 8.045273780822754,
|
260 |
+
"rewards/real": 4.1827802658081055,
|
261 |
+
"step": 170
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.69,
|
265 |
+
"learning_rate": 4.922206506364922e-07,
|
266 |
+
"logits/generated": 3.754439115524292,
|
267 |
+
"logits/real": 2.9574403762817383,
|
268 |
+
"logps/generated": -503.462646484375,
|
269 |
+
"logps/real": -1799.0537109375,
|
270 |
+
"loss": 0.0181,
|
271 |
+
"rewards/accuracies": 1.0,
|
272 |
+
"rewards/generated": -4.270089149475098,
|
273 |
+
"rewards/margins": 9.556356430053711,
|
274 |
+
"rewards/real": 5.286266326904297,
|
275 |
+
"step": 180
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.72,
|
279 |
+
"learning_rate": 4.886845827439887e-07,
|
280 |
+
"logits/generated": 3.9537768363952637,
|
281 |
+
"logits/real": 2.8257808685302734,
|
282 |
+
"logps/generated": -414.7232971191406,
|
283 |
+
"logps/real": -1848.5228271484375,
|
284 |
+
"loss": 0.0182,
|
285 |
+
"rewards/accuracies": 1.0,
|
286 |
+
"rewards/generated": -3.797616958618164,
|
287 |
+
"rewards/margins": 9.304213523864746,
|
288 |
+
"rewards/real": 5.506596565246582,
|
289 |
+
"step": 190
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.76,
|
293 |
+
"learning_rate": 4.851485148514851e-07,
|
294 |
+
"logits/generated": 3.7061352729797363,
|
295 |
+
"logits/real": 2.828097105026245,
|
296 |
+
"logps/generated": -478.8387145996094,
|
297 |
+
"logps/real": -1567.3736572265625,
|
298 |
+
"loss": 0.0162,
|
299 |
+
"rewards/accuracies": 1.0,
|
300 |
+
"rewards/generated": -4.287292003631592,
|
301 |
+
"rewards/margins": 9.111185073852539,
|
302 |
+
"rewards/real": 4.823891639709473,
|
303 |
+
"step": 200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.8,
|
307 |
+
"learning_rate": 4.816124469589816e-07,
|
308 |
+
"logits/generated": 3.8071022033691406,
|
309 |
+
"logits/real": 2.786395788192749,
|
310 |
+
"logps/generated": -497.02044677734375,
|
311 |
+
"logps/real": -1951.7906494140625,
|
312 |
+
"loss": 0.0116,
|
313 |
+
"rewards/accuracies": 1.0,
|
314 |
+
"rewards/generated": -5.036887168884277,
|
315 |
+
"rewards/margins": 11.377471923828125,
|
316 |
+
"rewards/real": 6.340585231781006,
|
317 |
+
"step": 210
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.84,
|
321 |
+
"learning_rate": 4.780763790664781e-07,
|
322 |
+
"logits/generated": 3.5943808555603027,
|
323 |
+
"logits/real": 3.0639989376068115,
|
324 |
+
"logps/generated": -466.7726135253906,
|
325 |
+
"logps/real": -1364.220458984375,
|
326 |
+
"loss": 0.0138,
|
327 |
+
"rewards/accuracies": 1.0,
|
328 |
+
"rewards/generated": -4.49011754989624,
|
329 |
+
"rewards/margins": 9.089958190917969,
|
330 |
+
"rewards/real": 4.599841594696045,
|
331 |
+
"step": 220
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.88,
|
335 |
+
"learning_rate": 4.745403111739745e-07,
|
336 |
+
"logits/generated": 3.7227370738983154,
|
337 |
+
"logits/real": 2.9175028800964355,
|
338 |
+
"logps/generated": -474.84954833984375,
|
339 |
+
"logps/real": -1725.422119140625,
|
340 |
+
"loss": 0.0109,
|
341 |
+
"rewards/accuracies": 1.0,
|
342 |
+
"rewards/generated": -4.81961727142334,
|
343 |
+
"rewards/margins": 10.596981048583984,
|
344 |
+
"rewards/real": 5.777363300323486,
|
345 |
+
"step": 230
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.91,
|
349 |
+
"learning_rate": 4.7100424328147096e-07,
|
350 |
+
"logits/generated": 3.338122844696045,
|
351 |
+
"logits/real": 3.0875296592712402,
|
352 |
+
"logps/generated": -435.6485290527344,
|
353 |
+
"logps/real": -1685.8828125,
|
354 |
+
"loss": 0.0103,
|
355 |
+
"rewards/accuracies": 1.0,
|
356 |
+
"rewards/generated": -4.066224098205566,
|
357 |
+
"rewards/margins": 9.890088081359863,
|
358 |
+
"rewards/real": 5.823863506317139,
|
359 |
+
"step": 240
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.95,
|
363 |
+
"learning_rate": 4.674681753889674e-07,
|
364 |
+
"logits/generated": 3.593212127685547,
|
365 |
+
"logits/real": 2.7413556575775146,
|
366 |
+
"logps/generated": -402.1564025878906,
|
367 |
+
"logps/real": -1605.6131591796875,
|
368 |
+
"loss": 0.0143,
|
369 |
+
"rewards/accuracies": 1.0,
|
370 |
+
"rewards/generated": -4.504222869873047,
|
371 |
+
"rewards/margins": 10.564704895019531,
|
372 |
+
"rewards/real": 6.060481071472168,
|
373 |
+
"step": 250
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.99,
|
377 |
+
"learning_rate": 4.6393210749646387e-07,
|
378 |
+
"logits/generated": 3.5109028816223145,
|
379 |
+
"logits/real": 2.8503494262695312,
|
380 |
+
"logps/generated": -526.8668823242188,
|
381 |
+
"logps/real": -1490.2159423828125,
|
382 |
+
"loss": 0.013,
|
383 |
+
"rewards/accuracies": 1.0,
|
384 |
+
"rewards/generated": -5.489691257476807,
|
385 |
+
"rewards/margins": 11.207723617553711,
|
386 |
+
"rewards/real": 5.718031883239746,
|
387 |
+
"step": 260
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.03,
|
391 |
+
"learning_rate": 4.603960396039604e-07,
|
392 |
+
"logits/generated": 3.4985408782958984,
|
393 |
+
"logits/real": 2.8388476371765137,
|
394 |
+
"logps/generated": -510.9580993652344,
|
395 |
+
"logps/real": -1608.238525390625,
|
396 |
+
"loss": 0.0104,
|
397 |
+
"rewards/accuracies": 1.0,
|
398 |
+
"rewards/generated": -5.455083847045898,
|
399 |
+
"rewards/margins": 11.62474250793457,
|
400 |
+
"rewards/real": 6.1696577072143555,
|
401 |
+
"step": 270
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.07,
|
405 |
+
"learning_rate": 4.5685997171145683e-07,
|
406 |
+
"logits/generated": 3.408998966217041,
|
407 |
+
"logits/real": 2.9803500175476074,
|
408 |
+
"logps/generated": -467.8755798339844,
|
409 |
+
"logps/real": -1577.332763671875,
|
410 |
+
"loss": 0.0086,
|
411 |
+
"rewards/accuracies": 1.0,
|
412 |
+
"rewards/generated": -4.607177734375,
|
413 |
+
"rewards/margins": 10.38925552368164,
|
414 |
+
"rewards/real": 5.782077312469482,
|
415 |
+
"step": 280
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.1,
|
419 |
+
"learning_rate": 4.533239038189533e-07,
|
420 |
+
"logits/generated": 3.7580649852752686,
|
421 |
+
"logits/real": 3.202885866165161,
|
422 |
+
"logps/generated": -476.220458984375,
|
423 |
+
"logps/real": -1511.313720703125,
|
424 |
+
"loss": 0.0071,
|
425 |
+
"rewards/accuracies": 1.0,
|
426 |
+
"rewards/generated": -5.54539155960083,
|
427 |
+
"rewards/margins": 11.575006484985352,
|
428 |
+
"rewards/real": 6.0296149253845215,
|
429 |
+
"step": 290
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.14,
|
433 |
+
"learning_rate": 4.4978783592644974e-07,
|
434 |
+
"logits/generated": 3.447097063064575,
|
435 |
+
"logits/real": 2.6315269470214844,
|
436 |
+
"logps/generated": -475.2987365722656,
|
437 |
+
"logps/real": -1564.4840087890625,
|
438 |
+
"loss": 0.0076,
|
439 |
+
"rewards/accuracies": 1.0,
|
440 |
+
"rewards/generated": -5.546289443969727,
|
441 |
+
"rewards/margins": 11.75828742980957,
|
442 |
+
"rewards/real": 6.211997032165527,
|
443 |
+
"step": 300
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.18,
|
447 |
+
"learning_rate": 4.462517680339462e-07,
|
448 |
+
"logits/generated": 3.4015917778015137,
|
449 |
+
"logits/real": 2.9662914276123047,
|
450 |
+
"logps/generated": -437.78826904296875,
|
451 |
+
"logps/real": -1598.526123046875,
|
452 |
+
"loss": 0.0096,
|
453 |
+
"rewards/accuracies": 1.0,
|
454 |
+
"rewards/generated": -4.93220329284668,
|
455 |
+
"rewards/margins": 12.351015090942383,
|
456 |
+
"rewards/real": 7.4188127517700195,
|
457 |
+
"step": 310
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 1.22,
|
461 |
+
"learning_rate": 4.427157001414427e-07,
|
462 |
+
"logits/generated": 3.510097026824951,
|
463 |
+
"logits/real": 2.913818836212158,
|
464 |
+
"logps/generated": -456.273681640625,
|
465 |
+
"logps/real": -1717.4222412109375,
|
466 |
+
"loss": 0.0076,
|
467 |
+
"rewards/accuracies": 1.0,
|
468 |
+
"rewards/generated": -5.022789478302002,
|
469 |
+
"rewards/margins": 13.268719673156738,
|
470 |
+
"rewards/real": 8.245931625366211,
|
471 |
+
"step": 320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.26,
|
475 |
+
"learning_rate": 4.3917963224893915e-07,
|
476 |
+
"logits/generated": 3.4145877361297607,
|
477 |
+
"logits/real": 2.8273959159851074,
|
478 |
+
"logps/generated": -465.119873046875,
|
479 |
+
"logps/real": -1708.9052734375,
|
480 |
+
"loss": 0.0066,
|
481 |
+
"rewards/accuracies": 1.0,
|
482 |
+
"rewards/generated": -5.375365257263184,
|
483 |
+
"rewards/margins": 12.598322868347168,
|
484 |
+
"rewards/real": 7.222956657409668,
|
485 |
+
"step": 330
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 1.3,
|
489 |
+
"learning_rate": 4.356435643564356e-07,
|
490 |
+
"logits/generated": 3.495450973510742,
|
491 |
+
"logits/real": 2.7503676414489746,
|
492 |
+
"logps/generated": -445.3560485839844,
|
493 |
+
"logps/real": -1563.655517578125,
|
494 |
+
"loss": 0.0071,
|
495 |
+
"rewards/accuracies": 1.0,
|
496 |
+
"rewards/generated": -5.360494136810303,
|
497 |
+
"rewards/margins": 12.658773422241211,
|
498 |
+
"rewards/real": 7.29827880859375,
|
499 |
+
"step": 340
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 1.33,
|
503 |
+
"learning_rate": 4.3210749646393206e-07,
|
504 |
+
"logits/generated": 3.579958438873291,
|
505 |
+
"logits/real": 2.7801036834716797,
|
506 |
+
"logps/generated": -436.92364501953125,
|
507 |
+
"logps/real": -1706.568359375,
|
508 |
+
"loss": 0.0072,
|
509 |
+
"rewards/accuracies": 1.0,
|
510 |
+
"rewards/generated": -5.444735527038574,
|
511 |
+
"rewards/margins": 12.98694133758545,
|
512 |
+
"rewards/real": 7.5422043800354,
|
513 |
+
"step": 350
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.37,
|
517 |
+
"learning_rate": 4.285714285714285e-07,
|
518 |
+
"logits/generated": 3.5498404502868652,
|
519 |
+
"logits/real": 2.8857247829437256,
|
520 |
+
"logps/generated": -467.14898681640625,
|
521 |
+
"logps/real": -1606.5517578125,
|
522 |
+
"loss": 0.0073,
|
523 |
+
"rewards/accuracies": 1.0,
|
524 |
+
"rewards/generated": -4.917501926422119,
|
525 |
+
"rewards/margins": 12.757287979125977,
|
526 |
+
"rewards/real": 7.839786529541016,
|
527 |
+
"step": 360
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 1.41,
|
531 |
+
"learning_rate": 4.25035360678925e-07,
|
532 |
+
"logits/generated": 3.588599681854248,
|
533 |
+
"logits/real": 2.7910194396972656,
|
534 |
+
"logps/generated": -484.51446533203125,
|
535 |
+
"logps/real": -1753.3662109375,
|
536 |
+
"loss": 0.0095,
|
537 |
+
"rewards/accuracies": 1.0,
|
538 |
+
"rewards/generated": -5.856254577636719,
|
539 |
+
"rewards/margins": 14.548685073852539,
|
540 |
+
"rewards/real": 8.69243049621582,
|
541 |
+
"step": 370
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 1.45,
|
545 |
+
"learning_rate": 4.214992927864215e-07,
|
546 |
+
"logits/generated": 3.4956557750701904,
|
547 |
+
"logits/real": 2.6511971950531006,
|
548 |
+
"logps/generated": -466.9720764160156,
|
549 |
+
"logps/real": -1695.6744384765625,
|
550 |
+
"loss": 0.0032,
|
551 |
+
"rewards/accuracies": 1.0,
|
552 |
+
"rewards/generated": -5.525470733642578,
|
553 |
+
"rewards/margins": 14.2725191116333,
|
554 |
+
"rewards/real": 8.747048377990723,
|
555 |
+
"step": 380
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 1.49,
|
559 |
+
"learning_rate": 4.1796322489391793e-07,
|
560 |
+
"logits/generated": 3.2205729484558105,
|
561 |
+
"logits/real": 2.746440887451172,
|
562 |
+
"logps/generated": -445.98779296875,
|
563 |
+
"logps/real": -1526.604736328125,
|
564 |
+
"loss": 0.006,
|
565 |
+
"rewards/accuracies": 1.0,
|
566 |
+
"rewards/generated": -5.600844383239746,
|
567 |
+
"rewards/margins": 13.368339538574219,
|
568 |
+
"rewards/real": 7.7674970626831055,
|
569 |
+
"step": 390
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.52,
|
573 |
+
"learning_rate": 4.144271570014144e-07,
|
574 |
+
"logits/generated": 3.5135910511016846,
|
575 |
+
"logits/real": 2.751537799835205,
|
576 |
+
"logps/generated": -441.55523681640625,
|
577 |
+
"logps/real": -1792.7021484375,
|
578 |
+
"loss": 0.0051,
|
579 |
+
"rewards/accuracies": 1.0,
|
580 |
+
"rewards/generated": -5.988682746887207,
|
581 |
+
"rewards/margins": 15.011758804321289,
|
582 |
+
"rewards/real": 9.023075103759766,
|
583 |
+
"step": 400
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 1.56,
|
587 |
+
"learning_rate": 4.1089108910891084e-07,
|
588 |
+
"logits/generated": 3.4969635009765625,
|
589 |
+
"logits/real": 2.874459981918335,
|
590 |
+
"logps/generated": -480.62884521484375,
|
591 |
+
"logps/real": -1726.501953125,
|
592 |
+
"loss": 0.0069,
|
593 |
+
"rewards/accuracies": 1.0,
|
594 |
+
"rewards/generated": -6.103398323059082,
|
595 |
+
"rewards/margins": 14.921289443969727,
|
596 |
+
"rewards/real": 8.817892074584961,
|
597 |
+
"step": 410
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 1.6,
|
601 |
+
"learning_rate": 4.0735502121640734e-07,
|
602 |
+
"logits/generated": 3.732043743133545,
|
603 |
+
"logits/real": 2.9122977256774902,
|
604 |
+
"logps/generated": -471.2142639160156,
|
605 |
+
"logps/real": -1475.9720458984375,
|
606 |
+
"loss": 0.006,
|
607 |
+
"rewards/accuracies": 1.0,
|
608 |
+
"rewards/generated": -5.9775614738464355,
|
609 |
+
"rewards/margins": 14.218009948730469,
|
610 |
+
"rewards/real": 8.240448951721191,
|
611 |
+
"step": 420
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 1.64,
|
615 |
+
"learning_rate": 4.038189533239038e-07,
|
616 |
+
"logits/generated": 3.5188686847686768,
|
617 |
+
"logits/real": 2.9900317192077637,
|
618 |
+
"logps/generated": -560.73486328125,
|
619 |
+
"logps/real": -1395.8021240234375,
|
620 |
+
"loss": 0.02,
|
621 |
+
"rewards/accuracies": 0.987500011920929,
|
622 |
+
"rewards/generated": -7.657801628112793,
|
623 |
+
"rewards/margins": 15.55529499053955,
|
624 |
+
"rewards/real": 7.897493839263916,
|
625 |
+
"step": 430
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 1.68,
|
629 |
+
"learning_rate": 4.0028288543140025e-07,
|
630 |
+
"logits/generated": 3.3781158924102783,
|
631 |
+
"logits/real": 2.629373073577881,
|
632 |
+
"logps/generated": -485.42156982421875,
|
633 |
+
"logps/real": -1796.0904541015625,
|
634 |
+
"loss": 0.0067,
|
635 |
+
"rewards/accuracies": 1.0,
|
636 |
+
"rewards/generated": -7.0816969871521,
|
637 |
+
"rewards/margins": 16.453693389892578,
|
638 |
+
"rewards/real": 9.371994972229004,
|
639 |
+
"step": 440
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 1.71,
|
643 |
+
"learning_rate": 3.967468175388967e-07,
|
644 |
+
"logits/generated": 3.460228443145752,
|
645 |
+
"logits/real": 2.9703357219696045,
|
646 |
+
"logps/generated": -460.6011657714844,
|
647 |
+
"logps/real": -1839.8109130859375,
|
648 |
+
"loss": 0.0032,
|
649 |
+
"rewards/accuracies": 1.0,
|
650 |
+
"rewards/generated": -6.300644397735596,
|
651 |
+
"rewards/margins": 15.726030349731445,
|
652 |
+
"rewards/real": 9.425384521484375,
|
653 |
+
"step": 450
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 1.75,
|
657 |
+
"learning_rate": 3.9321074964639316e-07,
|
658 |
+
"logits/generated": 3.0205512046813965,
|
659 |
+
"logits/real": 2.8035550117492676,
|
660 |
+
"logps/generated": -502.0563049316406,
|
661 |
+
"logps/real": -1389.227783203125,
|
662 |
+
"loss": 0.0048,
|
663 |
+
"rewards/accuracies": 1.0,
|
664 |
+
"rewards/generated": -7.311892032623291,
|
665 |
+
"rewards/margins": 15.14806842803955,
|
666 |
+
"rewards/real": 7.836176872253418,
|
667 |
+
"step": 460
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 1.79,
|
671 |
+
"learning_rate": 3.8967468175388967e-07,
|
672 |
+
"logits/generated": 3.6069533824920654,
|
673 |
+
"logits/real": 2.726623773574829,
|
674 |
+
"logps/generated": -505.29437255859375,
|
675 |
+
"logps/real": -1689.9912109375,
|
676 |
+
"loss": 0.0036,
|
677 |
+
"rewards/accuracies": 1.0,
|
678 |
+
"rewards/generated": -7.359295845031738,
|
679 |
+
"rewards/margins": 16.689287185668945,
|
680 |
+
"rewards/real": 9.32999324798584,
|
681 |
+
"step": 470
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 1.83,
|
685 |
+
"learning_rate": 3.861386138613861e-07,
|
686 |
+
"logits/generated": 3.4885826110839844,
|
687 |
+
"logits/real": 2.5398058891296387,
|
688 |
+
"logps/generated": -468.04608154296875,
|
689 |
+
"logps/real": -1690.434326171875,
|
690 |
+
"loss": 0.0029,
|
691 |
+
"rewards/accuracies": 1.0,
|
692 |
+
"rewards/generated": -7.317099571228027,
|
693 |
+
"rewards/margins": 15.526530265808105,
|
694 |
+
"rewards/real": 8.209431648254395,
|
695 |
+
"step": 480
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 1.87,
|
699 |
+
"learning_rate": 3.8260254596888257e-07,
|
700 |
+
"logits/generated": 3.4325199127197266,
|
701 |
+
"logits/real": 2.7468791007995605,
|
702 |
+
"logps/generated": -485.3282165527344,
|
703 |
+
"logps/real": -1564.2491455078125,
|
704 |
+
"loss": 0.0038,
|
705 |
+
"rewards/accuracies": 1.0,
|
706 |
+
"rewards/generated": -8.328545570373535,
|
707 |
+
"rewards/margins": 16.984691619873047,
|
708 |
+
"rewards/real": 8.656146049499512,
|
709 |
+
"step": 490
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 1.9,
|
713 |
+
"learning_rate": 3.7906647807637903e-07,
|
714 |
+
"logits/generated": 3.2969658374786377,
|
715 |
+
"logits/real": 2.644705295562744,
|
716 |
+
"logps/generated": -463.7992248535156,
|
717 |
+
"logps/real": -1622.1402587890625,
|
718 |
+
"loss": 0.0026,
|
719 |
+
"rewards/accuracies": 1.0,
|
720 |
+
"rewards/generated": -7.6635894775390625,
|
721 |
+
"rewards/margins": 16.660659790039062,
|
722 |
+
"rewards/real": 8.9970703125,
|
723 |
+
"step": 500
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 1.94,
|
727 |
+
"learning_rate": 3.755304101838755e-07,
|
728 |
+
"logits/generated": 3.4488253593444824,
|
729 |
+
"logits/real": 2.9401419162750244,
|
730 |
+
"logps/generated": -500.5553283691406,
|
731 |
+
"logps/real": -1580.5606689453125,
|
732 |
+
"loss": 0.0033,
|
733 |
+
"rewards/accuracies": 1.0,
|
734 |
+
"rewards/generated": -7.708639621734619,
|
735 |
+
"rewards/margins": 16.773143768310547,
|
736 |
+
"rewards/real": 9.064504623413086,
|
737 |
+
"step": 510
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 1.98,
|
741 |
+
"learning_rate": 3.71994342291372e-07,
|
742 |
+
"logits/generated": 3.3167099952697754,
|
743 |
+
"logits/real": 3.012571334838867,
|
744 |
+
"logps/generated": -521.168701171875,
|
745 |
+
"logps/real": -1524.885986328125,
|
746 |
+
"loss": 0.0039,
|
747 |
+
"rewards/accuracies": 1.0,
|
748 |
+
"rewards/generated": -7.435615539550781,
|
749 |
+
"rewards/margins": 16.3592472076416,
|
750 |
+
"rewards/real": 8.923630714416504,
|
751 |
+
"step": 520
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 2.02,
|
755 |
+
"learning_rate": 3.6845827439886844e-07,
|
756 |
+
"logits/generated": 3.354684352874756,
|
757 |
+
"logits/real": 2.7756412029266357,
|
758 |
+
"logps/generated": -468.66552734375,
|
759 |
+
"logps/real": -1526.357666015625,
|
760 |
+
"loss": 0.0048,
|
761 |
+
"rewards/accuracies": 1.0,
|
762 |
+
"rewards/generated": -8.224092483520508,
|
763 |
+
"rewards/margins": 16.959665298461914,
|
764 |
+
"rewards/real": 8.735573768615723,
|
765 |
+
"step": 530
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 2.06,
|
769 |
+
"learning_rate": 3.649222065063649e-07,
|
770 |
+
"logits/generated": 3.5977184772491455,
|
771 |
+
"logits/real": 2.68579363822937,
|
772 |
+
"logps/generated": -544.5694580078125,
|
773 |
+
"logps/real": -1571.634033203125,
|
774 |
+
"loss": 0.0018,
|
775 |
+
"rewards/accuracies": 1.0,
|
776 |
+
"rewards/generated": -8.363500595092773,
|
777 |
+
"rewards/margins": 17.53289794921875,
|
778 |
+
"rewards/real": 9.16939640045166,
|
779 |
+
"step": 540
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 2.1,
|
783 |
+
"learning_rate": 3.6138613861386135e-07,
|
784 |
+
"logits/generated": 3.4918408393859863,
|
785 |
+
"logits/real": 2.729196071624756,
|
786 |
+
"logps/generated": -518.4525146484375,
|
787 |
+
"logps/real": -1421.8359375,
|
788 |
+
"loss": 0.0036,
|
789 |
+
"rewards/accuracies": 1.0,
|
790 |
+
"rewards/generated": -8.855493545532227,
|
791 |
+
"rewards/margins": 17.412639617919922,
|
792 |
+
"rewards/real": 8.557147979736328,
|
793 |
+
"step": 550
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 2.13,
|
797 |
+
"learning_rate": 3.578500707213578e-07,
|
798 |
+
"logits/generated": 3.2267754077911377,
|
799 |
+
"logits/real": 2.8264071941375732,
|
800 |
+
"logps/generated": -458.85308837890625,
|
801 |
+
"logps/real": -1482.390625,
|
802 |
+
"loss": 0.0039,
|
803 |
+
"rewards/accuracies": 1.0,
|
804 |
+
"rewards/generated": -7.917211055755615,
|
805 |
+
"rewards/margins": 17.222782135009766,
|
806 |
+
"rewards/real": 9.305570602416992,
|
807 |
+
"step": 560
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 2.17,
|
811 |
+
"learning_rate": 3.543140028288543e-07,
|
812 |
+
"logits/generated": 3.449310302734375,
|
813 |
+
"logits/real": 2.881521701812744,
|
814 |
+
"logps/generated": -479.64202880859375,
|
815 |
+
"logps/real": -1629.423095703125,
|
816 |
+
"loss": 0.002,
|
817 |
+
"rewards/accuracies": 1.0,
|
818 |
+
"rewards/generated": -7.995371341705322,
|
819 |
+
"rewards/margins": 18.3244686126709,
|
820 |
+
"rewards/real": 10.329096794128418,
|
821 |
+
"step": 570
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 2.21,
|
825 |
+
"learning_rate": 3.5077793493635076e-07,
|
826 |
+
"logits/generated": 3.4941279888153076,
|
827 |
+
"logits/real": 2.9073030948638916,
|
828 |
+
"logps/generated": -487.73846435546875,
|
829 |
+
"logps/real": -1576.749267578125,
|
830 |
+
"loss": 0.0037,
|
831 |
+
"rewards/accuracies": 1.0,
|
832 |
+
"rewards/generated": -7.9393134117126465,
|
833 |
+
"rewards/margins": 17.776561737060547,
|
834 |
+
"rewards/real": 9.837248802185059,
|
835 |
+
"step": 580
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 2.25,
|
839 |
+
"learning_rate": 3.472418670438472e-07,
|
840 |
+
"logits/generated": 3.173529863357544,
|
841 |
+
"logits/real": 2.8594255447387695,
|
842 |
+
"logps/generated": -487.2096252441406,
|
843 |
+
"logps/real": -1416.3604736328125,
|
844 |
+
"loss": 0.002,
|
845 |
+
"rewards/accuracies": 1.0,
|
846 |
+
"rewards/generated": -7.219686031341553,
|
847 |
+
"rewards/margins": 15.569984436035156,
|
848 |
+
"rewards/real": 8.350296974182129,
|
849 |
+
"step": 590
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 2.29,
|
853 |
+
"learning_rate": 3.4370579915134367e-07,
|
854 |
+
"logits/generated": 3.167581081390381,
|
855 |
+
"logits/real": 2.622349500656128,
|
856 |
+
"logps/generated": -450.83447265625,
|
857 |
+
"logps/real": -1434.6671142578125,
|
858 |
+
"loss": 0.0023,
|
859 |
+
"rewards/accuracies": 1.0,
|
860 |
+
"rewards/generated": -7.358783721923828,
|
861 |
+
"rewards/margins": 16.64669418334961,
|
862 |
+
"rewards/real": 9.287908554077148,
|
863 |
+
"step": 600
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 2.32,
|
867 |
+
"learning_rate": 3.401697312588401e-07,
|
868 |
+
"logits/generated": 3.5104973316192627,
|
869 |
+
"logits/real": 2.580019474029541,
|
870 |
+
"logps/generated": -495.33746337890625,
|
871 |
+
"logps/real": -1505.913818359375,
|
872 |
+
"loss": 0.0037,
|
873 |
+
"rewards/accuracies": 1.0,
|
874 |
+
"rewards/generated": -7.833502292633057,
|
875 |
+
"rewards/margins": 16.95751953125,
|
876 |
+
"rewards/real": 9.124017715454102,
|
877 |
+
"step": 610
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 2.36,
|
881 |
+
"learning_rate": 3.3663366336633663e-07,
|
882 |
+
"logits/generated": 3.2511913776397705,
|
883 |
+
"logits/real": 2.7187373638153076,
|
884 |
+
"logps/generated": -495.783447265625,
|
885 |
+
"logps/real": -1531.77294921875,
|
886 |
+
"loss": 0.0045,
|
887 |
+
"rewards/accuracies": 1.0,
|
888 |
+
"rewards/generated": -8.153390884399414,
|
889 |
+
"rewards/margins": 17.530384063720703,
|
890 |
+
"rewards/real": 9.376993179321289,
|
891 |
+
"step": 620
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 2.4,
|
895 |
+
"learning_rate": 3.330975954738331e-07,
|
896 |
+
"logits/generated": 3.2725577354431152,
|
897 |
+
"logits/real": 2.7447569370269775,
|
898 |
+
"logps/generated": -491.76397705078125,
|
899 |
+
"logps/real": -1607.060791015625,
|
900 |
+
"loss": 0.0027,
|
901 |
+
"rewards/accuracies": 1.0,
|
902 |
+
"rewards/generated": -7.7982048988342285,
|
903 |
+
"rewards/margins": 17.868427276611328,
|
904 |
+
"rewards/real": 10.07022476196289,
|
905 |
+
"step": 630
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 2.44,
|
909 |
+
"learning_rate": 3.2956152758132954e-07,
|
910 |
+
"logits/generated": 3.2170231342315674,
|
911 |
+
"logits/real": 2.760910749435425,
|
912 |
+
"logps/generated": -479.82989501953125,
|
913 |
+
"logps/real": -1328.6890869140625,
|
914 |
+
"loss": 0.0024,
|
915 |
+
"rewards/accuracies": 1.0,
|
916 |
+
"rewards/generated": -7.747633934020996,
|
917 |
+
"rewards/margins": 16.90505027770996,
|
918 |
+
"rewards/real": 9.157418251037598,
|
919 |
+
"step": 640
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 2.48,
|
923 |
+
"learning_rate": 3.26025459688826e-07,
|
924 |
+
"logits/generated": 3.2980682849884033,
|
925 |
+
"logits/real": 2.6026058197021484,
|
926 |
+
"logps/generated": -484.3726501464844,
|
927 |
+
"logps/real": -1501.859619140625,
|
928 |
+
"loss": 0.0012,
|
929 |
+
"rewards/accuracies": 1.0,
|
930 |
+
"rewards/generated": -7.929776668548584,
|
931 |
+
"rewards/margins": 18.278278350830078,
|
932 |
+
"rewards/real": 10.348502159118652,
|
933 |
+
"step": 650
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 2.51,
|
937 |
+
"learning_rate": 3.2248939179632245e-07,
|
938 |
+
"logits/generated": 3.410261631011963,
|
939 |
+
"logits/real": 2.8707950115203857,
|
940 |
+
"logps/generated": -550.3458251953125,
|
941 |
+
"logps/real": -1484.9326171875,
|
942 |
+
"loss": 0.0009,
|
943 |
+
"rewards/accuracies": 1.0,
|
944 |
+
"rewards/generated": -8.744172096252441,
|
945 |
+
"rewards/margins": 18.63943862915039,
|
946 |
+
"rewards/real": 9.895263671875,
|
947 |
+
"step": 660
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 2.55,
|
951 |
+
"learning_rate": 3.1895332390381895e-07,
|
952 |
+
"logits/generated": 3.624340772628784,
|
953 |
+
"logits/real": 2.644595146179199,
|
954 |
+
"logps/generated": -510.18096923828125,
|
955 |
+
"logps/real": -1679.375,
|
956 |
+
"loss": 0.0024,
|
957 |
+
"rewards/accuracies": 1.0,
|
958 |
+
"rewards/generated": -8.56155014038086,
|
959 |
+
"rewards/margins": 20.045724868774414,
|
960 |
+
"rewards/real": 11.484173774719238,
|
961 |
+
"step": 670
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 2.59,
|
965 |
+
"learning_rate": 3.154172560113154e-07,
|
966 |
+
"logits/generated": 3.5800070762634277,
|
967 |
+
"logits/real": 2.905097246170044,
|
968 |
+
"logps/generated": -514.9693603515625,
|
969 |
+
"logps/real": -1498.704345703125,
|
970 |
+
"loss": 0.0023,
|
971 |
+
"rewards/accuracies": 1.0,
|
972 |
+
"rewards/generated": -8.549358367919922,
|
973 |
+
"rewards/margins": 18.856287002563477,
|
974 |
+
"rewards/real": 10.306925773620605,
|
975 |
+
"step": 680
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 2.63,
|
979 |
+
"learning_rate": 3.1188118811881186e-07,
|
980 |
+
"logits/generated": 3.3421058654785156,
|
981 |
+
"logits/real": 2.714266538619995,
|
982 |
+
"logps/generated": -497.5679626464844,
|
983 |
+
"logps/real": -1502.726806640625,
|
984 |
+
"loss": 0.0023,
|
985 |
+
"rewards/accuracies": 1.0,
|
986 |
+
"rewards/generated": -8.259305953979492,
|
987 |
+
"rewards/margins": 18.61314582824707,
|
988 |
+
"rewards/real": 10.353840827941895,
|
989 |
+
"step": 690
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 2.67,
|
993 |
+
"learning_rate": 3.083451202263083e-07,
|
994 |
+
"logits/generated": 3.3471736907958984,
|
995 |
+
"logits/real": 2.7787163257598877,
|
996 |
+
"logps/generated": -517.1281127929688,
|
997 |
+
"logps/real": -1472.466064453125,
|
998 |
+
"loss": 0.0027,
|
999 |
+
"rewards/accuracies": 1.0,
|
1000 |
+
"rewards/generated": -8.416834831237793,
|
1001 |
+
"rewards/margins": 18.77850914001465,
|
1002 |
+
"rewards/real": 10.361673355102539,
|
1003 |
+
"step": 700
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 2.7,
|
1007 |
+
"learning_rate": 3.0480905233380477e-07,
|
1008 |
+
"logits/generated": 3.2355308532714844,
|
1009 |
+
"logits/real": 2.852546215057373,
|
1010 |
+
"logps/generated": -500.0751953125,
|
1011 |
+
"logps/real": -1651.260986328125,
|
1012 |
+
"loss": 0.0014,
|
1013 |
+
"rewards/accuracies": 1.0,
|
1014 |
+
"rewards/generated": -8.010438919067383,
|
1015 |
+
"rewards/margins": 19.449283599853516,
|
1016 |
+
"rewards/real": 11.438843727111816,
|
1017 |
+
"step": 710
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 2.74,
|
1021 |
+
"learning_rate": 3.012729844413013e-07,
|
1022 |
+
"logits/generated": 3.437945604324341,
|
1023 |
+
"logits/real": 2.749911308288574,
|
1024 |
+
"logps/generated": -542.2654418945312,
|
1025 |
+
"logps/real": -1487.933837890625,
|
1026 |
+
"loss": 0.002,
|
1027 |
+
"rewards/accuracies": 1.0,
|
1028 |
+
"rewards/generated": -8.703554153442383,
|
1029 |
+
"rewards/margins": 19.010265350341797,
|
1030 |
+
"rewards/real": 10.306710243225098,
|
1031 |
+
"step": 720
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 2.78,
|
1035 |
+
"learning_rate": 2.9773691654879773e-07,
|
1036 |
+
"logits/generated": 3.234304428100586,
|
1037 |
+
"logits/real": 2.689356803894043,
|
1038 |
+
"logps/generated": -459.7379455566406,
|
1039 |
+
"logps/real": -1269.926025390625,
|
1040 |
+
"loss": 0.0021,
|
1041 |
+
"rewards/accuracies": 1.0,
|
1042 |
+
"rewards/generated": -7.5548601150512695,
|
1043 |
+
"rewards/margins": 16.455080032348633,
|
1044 |
+
"rewards/real": 8.900218963623047,
|
1045 |
+
"step": 730
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 2.82,
|
1049 |
+
"learning_rate": 2.942008486562942e-07,
|
1050 |
+
"logits/generated": 3.4382824897766113,
|
1051 |
+
"logits/real": 2.6454930305480957,
|
1052 |
+
"logps/generated": -517.6546630859375,
|
1053 |
+
"logps/real": -1617.267333984375,
|
1054 |
+
"loss": 0.0014,
|
1055 |
+
"rewards/accuracies": 1.0,
|
1056 |
+
"rewards/generated": -8.587407112121582,
|
1057 |
+
"rewards/margins": 19.053064346313477,
|
1058 |
+
"rewards/real": 10.465655326843262,
|
1059 |
+
"step": 740
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 2.86,
|
1063 |
+
"learning_rate": 2.9066478076379064e-07,
|
1064 |
+
"logits/generated": 3.0672454833984375,
|
1065 |
+
"logits/real": 2.67156720161438,
|
1066 |
+
"logps/generated": -459.13262939453125,
|
1067 |
+
"logps/real": -1313.4677734375,
|
1068 |
+
"loss": 0.0022,
|
1069 |
+
"rewards/accuracies": 1.0,
|
1070 |
+
"rewards/generated": -8.137083053588867,
|
1071 |
+
"rewards/margins": 17.47877311706543,
|
1072 |
+
"rewards/real": 9.341691970825195,
|
1073 |
+
"step": 750
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 2.9,
|
1077 |
+
"learning_rate": 2.871287128712871e-07,
|
1078 |
+
"logits/generated": 3.4013969898223877,
|
1079 |
+
"logits/real": 2.417377233505249,
|
1080 |
+
"logps/generated": -492.2867736816406,
|
1081 |
+
"logps/real": -1638.200927734375,
|
1082 |
+
"loss": 0.0019,
|
1083 |
+
"rewards/accuracies": 1.0,
|
1084 |
+
"rewards/generated": -8.533792495727539,
|
1085 |
+
"rewards/margins": 19.663969039916992,
|
1086 |
+
"rewards/real": 11.13017749786377,
|
1087 |
+
"step": 760
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 2.93,
|
1091 |
+
"learning_rate": 2.835926449787836e-07,
|
1092 |
+
"logits/generated": 3.388955593109131,
|
1093 |
+
"logits/real": 2.9141921997070312,
|
1094 |
+
"logps/generated": -545.1387939453125,
|
1095 |
+
"logps/real": -1538.4222412109375,
|
1096 |
+
"loss": 0.0014,
|
1097 |
+
"rewards/accuracies": 1.0,
|
1098 |
+
"rewards/generated": -9.785470962524414,
|
1099 |
+
"rewards/margins": 21.193279266357422,
|
1100 |
+
"rewards/real": 11.407808303833008,
|
1101 |
+
"step": 770
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 2.97,
|
1105 |
+
"learning_rate": 2.8005657708628005e-07,
|
1106 |
+
"logits/generated": 3.622591733932495,
|
1107 |
+
"logits/real": 2.7291853427886963,
|
1108 |
+
"logps/generated": -547.1531982421875,
|
1109 |
+
"logps/real": -1743.8941650390625,
|
1110 |
+
"loss": 0.0018,
|
1111 |
+
"rewards/accuracies": 1.0,
|
1112 |
+
"rewards/generated": -10.029909133911133,
|
1113 |
+
"rewards/margins": 21.701557159423828,
|
1114 |
+
"rewards/real": 11.671648025512695,
|
1115 |
+
"step": 780
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 3.01,
|
1119 |
+
"learning_rate": 2.765205091937765e-07,
|
1120 |
+
"logits/generated": 3.347827196121216,
|
1121 |
+
"logits/real": 2.813518524169922,
|
1122 |
+
"logps/generated": -518.5848388671875,
|
1123 |
+
"logps/real": -1608.0418701171875,
|
1124 |
+
"loss": 0.0024,
|
1125 |
+
"rewards/accuracies": 1.0,
|
1126 |
+
"rewards/generated": -9.312664985656738,
|
1127 |
+
"rewards/margins": 21.00381851196289,
|
1128 |
+
"rewards/real": 11.69115161895752,
|
1129 |
+
"step": 790
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 3.05,
|
1133 |
+
"learning_rate": 2.7298444130127296e-07,
|
1134 |
+
"logits/generated": 3.2987990379333496,
|
1135 |
+
"logits/real": 2.9453186988830566,
|
1136 |
+
"logps/generated": -522.5285034179688,
|
1137 |
+
"logps/real": -1608.2236328125,
|
1138 |
+
"loss": 0.001,
|
1139 |
+
"rewards/accuracies": 1.0,
|
1140 |
+
"rewards/generated": -9.82221794128418,
|
1141 |
+
"rewards/margins": 22.511926651000977,
|
1142 |
+
"rewards/real": 12.689709663391113,
|
1143 |
+
"step": 800
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 3.09,
|
1147 |
+
"learning_rate": 2.694483734087694e-07,
|
1148 |
+
"logits/generated": 3.4462966918945312,
|
1149 |
+
"logits/real": 2.625929117202759,
|
1150 |
+
"logps/generated": -545.0180053710938,
|
1151 |
+
"logps/real": -1427.6646728515625,
|
1152 |
+
"loss": 0.0022,
|
1153 |
+
"rewards/accuracies": 1.0,
|
1154 |
+
"rewards/generated": -11.479304313659668,
|
1155 |
+
"rewards/margins": 22.244796752929688,
|
1156 |
+
"rewards/real": 10.765493392944336,
|
1157 |
+
"step": 810
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 3.12,
|
1161 |
+
"learning_rate": 2.659123055162659e-07,
|
1162 |
+
"logits/generated": 3.2480366230010986,
|
1163 |
+
"logits/real": 2.8531947135925293,
|
1164 |
+
"logps/generated": -530.7342529296875,
|
1165 |
+
"logps/real": -1727.2086181640625,
|
1166 |
+
"loss": 0.001,
|
1167 |
+
"rewards/accuracies": 1.0,
|
1168 |
+
"rewards/generated": -9.427630424499512,
|
1169 |
+
"rewards/margins": 22.206254959106445,
|
1170 |
+
"rewards/real": 12.778624534606934,
|
1171 |
+
"step": 820
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 3.16,
|
1175 |
+
"learning_rate": 2.623762376237624e-07,
|
1176 |
+
"logits/generated": 3.5078930854797363,
|
1177 |
+
"logits/real": 2.7171075344085693,
|
1178 |
+
"logps/generated": -507.3907775878906,
|
1179 |
+
"logps/real": -1634.822998046875,
|
1180 |
+
"loss": 0.0011,
|
1181 |
+
"rewards/accuracies": 1.0,
|
1182 |
+
"rewards/generated": -8.803173065185547,
|
1183 |
+
"rewards/margins": 20.158788681030273,
|
1184 |
+
"rewards/real": 11.355618476867676,
|
1185 |
+
"step": 830
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 3.2,
|
1189 |
+
"learning_rate": 2.5884016973125883e-07,
|
1190 |
+
"logits/generated": 3.389615535736084,
|
1191 |
+
"logits/real": 2.6584954261779785,
|
1192 |
+
"logps/generated": -519.1912841796875,
|
1193 |
+
"logps/real": -1511.683349609375,
|
1194 |
+
"loss": 0.0012,
|
1195 |
+
"rewards/accuracies": 1.0,
|
1196 |
+
"rewards/generated": -9.256002426147461,
|
1197 |
+
"rewards/margins": 19.75589370727539,
|
1198 |
+
"rewards/real": 10.499893188476562,
|
1199 |
+
"step": 840
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 3.24,
|
1203 |
+
"learning_rate": 2.553041018387553e-07,
|
1204 |
+
"logits/generated": 3.1219124794006348,
|
1205 |
+
"logits/real": 2.69732928276062,
|
1206 |
+
"logps/generated": -513.461181640625,
|
1207 |
+
"logps/real": -1559.185302734375,
|
1208 |
+
"loss": 0.001,
|
1209 |
+
"rewards/accuracies": 1.0,
|
1210 |
+
"rewards/generated": -9.307373046875,
|
1211 |
+
"rewards/margins": 20.579065322875977,
|
1212 |
+
"rewards/real": 11.271692276000977,
|
1213 |
+
"step": 850
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 3.28,
|
1217 |
+
"learning_rate": 2.5176803394625174e-07,
|
1218 |
+
"logits/generated": 3.169861316680908,
|
1219 |
+
"logits/real": 2.5963492393493652,
|
1220 |
+
"logps/generated": -531.0164184570312,
|
1221 |
+
"logps/real": -1578.7210693359375,
|
1222 |
+
"loss": 0.001,
|
1223 |
+
"rewards/accuracies": 1.0,
|
1224 |
+
"rewards/generated": -9.622026443481445,
|
1225 |
+
"rewards/margins": 21.500263214111328,
|
1226 |
+
"rewards/real": 11.878233909606934,
|
1227 |
+
"step": 860
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 3.31,
|
1231 |
+
"learning_rate": 2.482319660537482e-07,
|
1232 |
+
"logits/generated": 3.3711845874786377,
|
1233 |
+
"logits/real": 2.759648323059082,
|
1234 |
+
"logps/generated": -523.5821533203125,
|
1235 |
+
"logps/real": -1462.2935791015625,
|
1236 |
+
"loss": 0.0007,
|
1237 |
+
"rewards/accuracies": 1.0,
|
1238 |
+
"rewards/generated": -10.834948539733887,
|
1239 |
+
"rewards/margins": 21.79311180114746,
|
1240 |
+
"rewards/real": 10.958162307739258,
|
1241 |
+
"step": 870
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 3.35,
|
1245 |
+
"learning_rate": 2.446958981612447e-07,
|
1246 |
+
"logits/generated": 3.282954454421997,
|
1247 |
+
"logits/real": 2.7643918991088867,
|
1248 |
+
"logps/generated": -473.2938537597656,
|
1249 |
+
"logps/real": -1457.6839599609375,
|
1250 |
+
"loss": 0.0013,
|
1251 |
+
"rewards/accuracies": 1.0,
|
1252 |
+
"rewards/generated": -8.40355110168457,
|
1253 |
+
"rewards/margins": 19.281604766845703,
|
1254 |
+
"rewards/real": 10.878053665161133,
|
1255 |
+
"step": 880
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 3.39,
|
1259 |
+
"learning_rate": 2.4115983026874115e-07,
|
1260 |
+
"logits/generated": 3.4354591369628906,
|
1261 |
+
"logits/real": 2.6684250831604004,
|
1262 |
+
"logps/generated": -536.3674926757812,
|
1263 |
+
"logps/real": -1729.115966796875,
|
1264 |
+
"loss": 0.0007,
|
1265 |
+
"rewards/accuracies": 1.0,
|
1266 |
+
"rewards/generated": -10.493001937866211,
|
1267 |
+
"rewards/margins": 23.19765853881836,
|
1268 |
+
"rewards/real": 12.704656600952148,
|
1269 |
+
"step": 890
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 3.43,
|
1273 |
+
"learning_rate": 2.376237623762376e-07,
|
1274 |
+
"logits/generated": 3.266200304031372,
|
1275 |
+
"logits/real": 2.749070644378662,
|
1276 |
+
"logps/generated": -506.13970947265625,
|
1277 |
+
"logps/real": -1660.871337890625,
|
1278 |
+
"loss": 0.0006,
|
1279 |
+
"rewards/accuracies": 1.0,
|
1280 |
+
"rewards/generated": -9.553144454956055,
|
1281 |
+
"rewards/margins": 22.273033142089844,
|
1282 |
+
"rewards/real": 12.719888687133789,
|
1283 |
+
"step": 900
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 3.47,
|
1287 |
+
"learning_rate": 2.3408769448373408e-07,
|
1288 |
+
"logits/generated": 3.4035401344299316,
|
1289 |
+
"logits/real": 2.6919925212860107,
|
1290 |
+
"logps/generated": -545.0686645507812,
|
1291 |
+
"logps/real": -1454.680419921875,
|
1292 |
+
"loss": 0.0011,
|
1293 |
+
"rewards/accuracies": 1.0,
|
1294 |
+
"rewards/generated": -9.882238388061523,
|
1295 |
+
"rewards/margins": 21.769603729248047,
|
1296 |
+
"rewards/real": 11.88736629486084,
|
1297 |
+
"step": 910
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 3.5,
|
1301 |
+
"learning_rate": 2.3055162659123054e-07,
|
1302 |
+
"logits/generated": 3.244786024093628,
|
1303 |
+
"logits/real": 2.7183642387390137,
|
1304 |
+
"logps/generated": -538.6968383789062,
|
1305 |
+
"logps/real": -1382.13330078125,
|
1306 |
+
"loss": 0.001,
|
1307 |
+
"rewards/accuracies": 1.0,
|
1308 |
+
"rewards/generated": -10.824942588806152,
|
1309 |
+
"rewards/margins": 22.102800369262695,
|
1310 |
+
"rewards/real": 11.277857780456543,
|
1311 |
+
"step": 920
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 3.54,
|
1315 |
+
"learning_rate": 2.2701555869872702e-07,
|
1316 |
+
"logits/generated": 3.3680167198181152,
|
1317 |
+
"logits/real": 2.5044057369232178,
|
1318 |
+
"logps/generated": -547.4840087890625,
|
1319 |
+
"logps/real": -1493.070556640625,
|
1320 |
+
"loss": 0.0013,
|
1321 |
+
"rewards/accuracies": 1.0,
|
1322 |
+
"rewards/generated": -10.53519344329834,
|
1323 |
+
"rewards/margins": 22.55548667907715,
|
1324 |
+
"rewards/real": 12.020292282104492,
|
1325 |
+
"step": 930
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 3.58,
|
1329 |
+
"learning_rate": 2.2347949080622347e-07,
|
1330 |
+
"logits/generated": 3.4719784259796143,
|
1331 |
+
"logits/real": 2.6997435092926025,
|
1332 |
+
"logps/generated": -531.0570678710938,
|
1333 |
+
"logps/real": -1509.5135498046875,
|
1334 |
+
"loss": 0.0007,
|
1335 |
+
"rewards/accuracies": 1.0,
|
1336 |
+
"rewards/generated": -10.211065292358398,
|
1337 |
+
"rewards/margins": 22.259336471557617,
|
1338 |
+
"rewards/real": 12.048271179199219,
|
1339 |
+
"step": 940
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 3.62,
|
1343 |
+
"learning_rate": 2.1994342291371993e-07,
|
1344 |
+
"logits/generated": 3.3083972930908203,
|
1345 |
+
"logits/real": 2.4025731086730957,
|
1346 |
+
"logps/generated": -575.9044189453125,
|
1347 |
+
"logps/real": -1759.0048828125,
|
1348 |
+
"loss": 0.002,
|
1349 |
+
"rewards/accuracies": 1.0,
|
1350 |
+
"rewards/generated": -11.274171829223633,
|
1351 |
+
"rewards/margins": 24.654094696044922,
|
1352 |
+
"rewards/real": 13.379923820495605,
|
1353 |
+
"step": 950
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 3.66,
|
1357 |
+
"learning_rate": 2.164073550212164e-07,
|
1358 |
+
"logits/generated": 3.4808990955352783,
|
1359 |
+
"logits/real": 2.577362060546875,
|
1360 |
+
"logps/generated": -463.35638427734375,
|
1361 |
+
"logps/real": -1399.489013671875,
|
1362 |
+
"loss": 0.0007,
|
1363 |
+
"rewards/accuracies": 1.0,
|
1364 |
+
"rewards/generated": -8.753828048706055,
|
1365 |
+
"rewards/margins": 19.656505584716797,
|
1366 |
+
"rewards/real": 10.902679443359375,
|
1367 |
+
"step": 960
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 3.7,
|
1371 |
+
"learning_rate": 2.1287128712871286e-07,
|
1372 |
+
"logits/generated": 3.4557316303253174,
|
1373 |
+
"logits/real": 2.766918659210205,
|
1374 |
+
"logps/generated": -553.6686401367188,
|
1375 |
+
"logps/real": -1662.569091796875,
|
1376 |
+
"loss": 0.0007,
|
1377 |
+
"rewards/accuracies": 1.0,
|
1378 |
+
"rewards/generated": -10.936054229736328,
|
1379 |
+
"rewards/margins": 24.027223587036133,
|
1380 |
+
"rewards/real": 13.091169357299805,
|
1381 |
+
"step": 970
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 3.73,
|
1385 |
+
"learning_rate": 2.0933521923620934e-07,
|
1386 |
+
"logits/generated": 3.14534592628479,
|
1387 |
+
"logits/real": 2.6436448097229004,
|
1388 |
+
"logps/generated": -510.17950439453125,
|
1389 |
+
"logps/real": -1495.9129638671875,
|
1390 |
+
"loss": 0.0006,
|
1391 |
+
"rewards/accuracies": 1.0,
|
1392 |
+
"rewards/generated": -9.579751968383789,
|
1393 |
+
"rewards/margins": 21.640422821044922,
|
1394 |
+
"rewards/real": 12.06067180633545,
|
1395 |
+
"step": 980
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 3.77,
|
1399 |
+
"learning_rate": 2.057991513437058e-07,
|
1400 |
+
"logits/generated": 3.3893933296203613,
|
1401 |
+
"logits/real": 2.515793800354004,
|
1402 |
+
"logps/generated": -507.2007751464844,
|
1403 |
+
"logps/real": -1553.794189453125,
|
1404 |
+
"loss": 0.0011,
|
1405 |
+
"rewards/accuracies": 1.0,
|
1406 |
+
"rewards/generated": -10.590211868286133,
|
1407 |
+
"rewards/margins": 23.068220138549805,
|
1408 |
+
"rewards/real": 12.478008270263672,
|
1409 |
+
"step": 990
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 3.81,
|
1413 |
+
"learning_rate": 2.0226308345120225e-07,
|
1414 |
+
"logits/generated": 3.168189525604248,
|
1415 |
+
"logits/real": 2.5998377799987793,
|
1416 |
+
"logps/generated": -535.4756469726562,
|
1417 |
+
"logps/real": -1227.1500244140625,
|
1418 |
+
"loss": 0.0011,
|
1419 |
+
"rewards/accuracies": 1.0,
|
1420 |
+
"rewards/generated": -11.283498764038086,
|
1421 |
+
"rewards/margins": 21.739755630493164,
|
1422 |
+
"rewards/real": 10.456255912780762,
|
1423 |
+
"step": 1000
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 3.85,
|
1427 |
+
"learning_rate": 1.9872701555869873e-07,
|
1428 |
+
"logits/generated": 3.0489237308502197,
|
1429 |
+
"logits/real": 2.500216484069824,
|
1430 |
+
"logps/generated": -534.8651123046875,
|
1431 |
+
"logps/real": -1446.293701171875,
|
1432 |
+
"loss": 0.0006,
|
1433 |
+
"rewards/accuracies": 1.0,
|
1434 |
+
"rewards/generated": -11.704988479614258,
|
1435 |
+
"rewards/margins": 22.91129493713379,
|
1436 |
+
"rewards/real": 11.206305503845215,
|
1437 |
+
"step": 1010
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 3.89,
|
1441 |
+
"learning_rate": 1.9519094766619518e-07,
|
1442 |
+
"logits/generated": 3.4261863231658936,
|
1443 |
+
"logits/real": 2.486532688140869,
|
1444 |
+
"logps/generated": -550.0924072265625,
|
1445 |
+
"logps/real": -1607.067138671875,
|
1446 |
+
"loss": 0.0004,
|
1447 |
+
"rewards/accuracies": 1.0,
|
1448 |
+
"rewards/generated": -11.577852249145508,
|
1449 |
+
"rewards/margins": 24.368900299072266,
|
1450 |
+
"rewards/real": 12.791049003601074,
|
1451 |
+
"step": 1020
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 3.92,
|
1455 |
+
"learning_rate": 1.9165487977369166e-07,
|
1456 |
+
"logits/generated": 3.2348227500915527,
|
1457 |
+
"logits/real": 2.7686595916748047,
|
1458 |
+
"logps/generated": -570.3921508789062,
|
1459 |
+
"logps/real": -1670.5628662109375,
|
1460 |
+
"loss": 0.0009,
|
1461 |
+
"rewards/accuracies": 1.0,
|
1462 |
+
"rewards/generated": -11.573652267456055,
|
1463 |
+
"rewards/margins": 25.506744384765625,
|
1464 |
+
"rewards/real": 13.93309211730957,
|
1465 |
+
"step": 1030
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 3.96,
|
1469 |
+
"learning_rate": 1.8811881188118812e-07,
|
1470 |
+
"logits/generated": 3.115082263946533,
|
1471 |
+
"logits/real": 2.5799102783203125,
|
1472 |
+
"logps/generated": -503.86956787109375,
|
1473 |
+
"logps/real": -1525.8857421875,
|
1474 |
+
"loss": 0.0013,
|
1475 |
+
"rewards/accuracies": 1.0,
|
1476 |
+
"rewards/generated": -9.889609336853027,
|
1477 |
+
"rewards/margins": 22.231243133544922,
|
1478 |
+
"rewards/real": 12.341632843017578,
|
1479 |
+
"step": 1040
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 4.0,
|
1483 |
+
"learning_rate": 1.8458274398868457e-07,
|
1484 |
+
"logits/generated": 3.2662482261657715,
|
1485 |
+
"logits/real": 2.468737840652466,
|
1486 |
+
"logps/generated": -522.85498046875,
|
1487 |
+
"logps/real": -1517.8037109375,
|
1488 |
+
"loss": 0.0004,
|
1489 |
+
"rewards/accuracies": 1.0,
|
1490 |
+
"rewards/generated": -11.054136276245117,
|
1491 |
+
"rewards/margins": 24.148630142211914,
|
1492 |
+
"rewards/real": 13.094491958618164,
|
1493 |
+
"step": 1050
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 4.04,
|
1497 |
+
"learning_rate": 1.8104667609618105e-07,
|
1498 |
+
"logits/generated": 3.3418450355529785,
|
1499 |
+
"logits/real": 2.6237406730651855,
|
1500 |
+
"logps/generated": -586.31591796875,
|
1501 |
+
"logps/real": -1651.44921875,
|
1502 |
+
"loss": 0.0007,
|
1503 |
+
"rewards/accuracies": 1.0,
|
1504 |
+
"rewards/generated": -13.165428161621094,
|
1505 |
+
"rewards/margins": 27.307897567749023,
|
1506 |
+
"rewards/real": 14.142468452453613,
|
1507 |
+
"step": 1060
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 4.08,
|
1511 |
+
"learning_rate": 1.775106082036775e-07,
|
1512 |
+
"logits/generated": 3.2586989402770996,
|
1513 |
+
"logits/real": 2.557404041290283,
|
1514 |
+
"logps/generated": -502.6537170410156,
|
1515 |
+
"logps/real": -1429.9771728515625,
|
1516 |
+
"loss": 0.0009,
|
1517 |
+
"rewards/accuracies": 1.0,
|
1518 |
+
"rewards/generated": -11.023027420043945,
|
1519 |
+
"rewards/margins": 23.140275955200195,
|
1520 |
+
"rewards/real": 12.117250442504883,
|
1521 |
+
"step": 1070
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 4.11,
|
1525 |
+
"learning_rate": 1.7397454031117398e-07,
|
1526 |
+
"logits/generated": 3.426239013671875,
|
1527 |
+
"logits/real": 2.6774344444274902,
|
1528 |
+
"logps/generated": -572.1189575195312,
|
1529 |
+
"logps/real": -1397.4552001953125,
|
1530 |
+
"loss": 0.0004,
|
1531 |
+
"rewards/accuracies": 1.0,
|
1532 |
+
"rewards/generated": -13.265462875366211,
|
1533 |
+
"rewards/margins": 24.69881820678711,
|
1534 |
+
"rewards/real": 11.433354377746582,
|
1535 |
+
"step": 1080
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 4.15,
|
1539 |
+
"learning_rate": 1.7043847241867044e-07,
|
1540 |
+
"logits/generated": 3.0871334075927734,
|
1541 |
+
"logits/real": 2.5882654190063477,
|
1542 |
+
"logps/generated": -550.581298828125,
|
1543 |
+
"logps/real": -1440.5426025390625,
|
1544 |
+
"loss": 0.0005,
|
1545 |
+
"rewards/accuracies": 1.0,
|
1546 |
+
"rewards/generated": -11.109870910644531,
|
1547 |
+
"rewards/margins": 25.10569190979004,
|
1548 |
+
"rewards/real": 13.995819091796875,
|
1549 |
+
"step": 1090
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 4.19,
|
1553 |
+
"learning_rate": 1.669024045261669e-07,
|
1554 |
+
"logits/generated": 3.4628639221191406,
|
1555 |
+
"logits/real": 2.6520979404449463,
|
1556 |
+
"logps/generated": -516.7633666992188,
|
1557 |
+
"logps/real": -1631.560302734375,
|
1558 |
+
"loss": 0.0004,
|
1559 |
+
"rewards/accuracies": 1.0,
|
1560 |
+
"rewards/generated": -11.816521644592285,
|
1561 |
+
"rewards/margins": 25.77557373046875,
|
1562 |
+
"rewards/real": 13.959050178527832,
|
1563 |
+
"step": 1100
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 4.23,
|
1567 |
+
"learning_rate": 1.6336633663366337e-07,
|
1568 |
+
"logits/generated": 3.325192928314209,
|
1569 |
+
"logits/real": 2.6561620235443115,
|
1570 |
+
"logps/generated": -579.8635864257812,
|
1571 |
+
"logps/real": -1503.974609375,
|
1572 |
+
"loss": 0.0004,
|
1573 |
+
"rewards/accuracies": 1.0,
|
1574 |
+
"rewards/generated": -12.559514045715332,
|
1575 |
+
"rewards/margins": 25.418582916259766,
|
1576 |
+
"rewards/real": 12.85906982421875,
|
1577 |
+
"step": 1110
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 4.27,
|
1581 |
+
"learning_rate": 1.5983026874115983e-07,
|
1582 |
+
"logits/generated": 3.2172133922576904,
|
1583 |
+
"logits/real": 2.644768238067627,
|
1584 |
+
"logps/generated": -523.1590576171875,
|
1585 |
+
"logps/real": -1488.0220947265625,
|
1586 |
+
"loss": 0.0005,
|
1587 |
+
"rewards/accuracies": 1.0,
|
1588 |
+
"rewards/generated": -11.404559135437012,
|
1589 |
+
"rewards/margins": 23.979520797729492,
|
1590 |
+
"rewards/real": 12.574960708618164,
|
1591 |
+
"step": 1120
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 4.3,
|
1595 |
+
"learning_rate": 1.562942008486563e-07,
|
1596 |
+
"logits/generated": 3.0821359157562256,
|
1597 |
+
"logits/real": 2.5439810752868652,
|
1598 |
+
"logps/generated": -466.92694091796875,
|
1599 |
+
"logps/real": -1334.6812744140625,
|
1600 |
+
"loss": 0.0004,
|
1601 |
+
"rewards/accuracies": 1.0,
|
1602 |
+
"rewards/generated": -10.233351707458496,
|
1603 |
+
"rewards/margins": 21.963369369506836,
|
1604 |
+
"rewards/real": 11.73001766204834,
|
1605 |
+
"step": 1130
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 4.34,
|
1609 |
+
"learning_rate": 1.5275813295615276e-07,
|
1610 |
+
"logits/generated": 3.4721286296844482,
|
1611 |
+
"logits/real": 2.5629734992980957,
|
1612 |
+
"logps/generated": -569.9315795898438,
|
1613 |
+
"logps/real": -1553.0869140625,
|
1614 |
+
"loss": 0.0003,
|
1615 |
+
"rewards/accuracies": 1.0,
|
1616 |
+
"rewards/generated": -11.754822731018066,
|
1617 |
+
"rewards/margins": 25.470844268798828,
|
1618 |
+
"rewards/real": 13.716024398803711,
|
1619 |
+
"step": 1140
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 4.38,
|
1623 |
+
"learning_rate": 1.4922206506364921e-07,
|
1624 |
+
"logits/generated": 3.156252384185791,
|
1625 |
+
"logits/real": 2.703667163848877,
|
1626 |
+
"logps/generated": -512.1444091796875,
|
1627 |
+
"logps/real": -1513.850830078125,
|
1628 |
+
"loss": 0.0003,
|
1629 |
+
"rewards/accuracies": 1.0,
|
1630 |
+
"rewards/generated": -11.257915496826172,
|
1631 |
+
"rewards/margins": 24.550378799438477,
|
1632 |
+
"rewards/real": 13.292462348937988,
|
1633 |
+
"step": 1150
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 4.42,
|
1637 |
+
"learning_rate": 1.456859971711457e-07,
|
1638 |
+
"logits/generated": 3.141005277633667,
|
1639 |
+
"logits/real": 2.8431308269500732,
|
1640 |
+
"logps/generated": -560.7545776367188,
|
1641 |
+
"logps/real": -1514.60693359375,
|
1642 |
+
"loss": 0.0001,
|
1643 |
+
"rewards/accuracies": 1.0,
|
1644 |
+
"rewards/generated": -12.668886184692383,
|
1645 |
+
"rewards/margins": 25.635141372680664,
|
1646 |
+
"rewards/real": 12.966257095336914,
|
1647 |
+
"step": 1160
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 4.46,
|
1651 |
+
"learning_rate": 1.4214992927864215e-07,
|
1652 |
+
"logits/generated": 3.4051051139831543,
|
1653 |
+
"logits/real": 2.6105704307556152,
|
1654 |
+
"logps/generated": -574.8484497070312,
|
1655 |
+
"logps/real": -1481.771484375,
|
1656 |
+
"loss": 0.0002,
|
1657 |
+
"rewards/accuracies": 1.0,
|
1658 |
+
"rewards/generated": -12.965988159179688,
|
1659 |
+
"rewards/margins": 26.073007583618164,
|
1660 |
+
"rewards/real": 13.107017517089844,
|
1661 |
+
"step": 1170
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 4.5,
|
1665 |
+
"learning_rate": 1.3861386138613863e-07,
|
1666 |
+
"logits/generated": 3.417850971221924,
|
1667 |
+
"logits/real": 2.5431482791900635,
|
1668 |
+
"logps/generated": -557.5526123046875,
|
1669 |
+
"logps/real": -1832.751953125,
|
1670 |
+
"loss": 0.0005,
|
1671 |
+
"rewards/accuracies": 1.0,
|
1672 |
+
"rewards/generated": -11.886221885681152,
|
1673 |
+
"rewards/margins": 26.28768539428711,
|
1674 |
+
"rewards/real": 14.401464462280273,
|
1675 |
+
"step": 1180
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 4.53,
|
1679 |
+
"learning_rate": 1.3507779349363508e-07,
|
1680 |
+
"logits/generated": 3.3368937969207764,
|
1681 |
+
"logits/real": 2.492691993713379,
|
1682 |
+
"logps/generated": -503.24652099609375,
|
1683 |
+
"logps/real": -1523.6234130859375,
|
1684 |
+
"loss": 0.0007,
|
1685 |
+
"rewards/accuracies": 1.0,
|
1686 |
+
"rewards/generated": -11.509819030761719,
|
1687 |
+
"rewards/margins": 25.515331268310547,
|
1688 |
+
"rewards/real": 14.005514144897461,
|
1689 |
+
"step": 1190
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 4.57,
|
1693 |
+
"learning_rate": 1.3154172560113154e-07,
|
1694 |
+
"logits/generated": 3.381847858428955,
|
1695 |
+
"logits/real": 2.6287689208984375,
|
1696 |
+
"logps/generated": -530.4554443359375,
|
1697 |
+
"logps/real": -1445.392333984375,
|
1698 |
+
"loss": 0.0004,
|
1699 |
+
"rewards/accuracies": 1.0,
|
1700 |
+
"rewards/generated": -12.088003158569336,
|
1701 |
+
"rewards/margins": 25.268281936645508,
|
1702 |
+
"rewards/real": 13.180277824401855,
|
1703 |
+
"step": 1200
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 4.61,
|
1707 |
+
"learning_rate": 1.2800565770862802e-07,
|
1708 |
+
"logits/generated": 3.0044195652008057,
|
1709 |
+
"logits/real": 2.6941545009613037,
|
1710 |
+
"logps/generated": -580.5851440429688,
|
1711 |
+
"logps/real": -1566.2730712890625,
|
1712 |
+
"loss": 0.0006,
|
1713 |
+
"rewards/accuracies": 1.0,
|
1714 |
+
"rewards/generated": -13.416638374328613,
|
1715 |
+
"rewards/margins": 27.365131378173828,
|
1716 |
+
"rewards/real": 13.948491096496582,
|
1717 |
+
"step": 1210
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 4.65,
|
1721 |
+
"learning_rate": 1.2446958981612447e-07,
|
1722 |
+
"logits/generated": 3.0417532920837402,
|
1723 |
+
"logits/real": 2.775116443634033,
|
1724 |
+
"logps/generated": -564.0277099609375,
|
1725 |
+
"logps/real": -1237.641357421875,
|
1726 |
+
"loss": 0.0003,
|
1727 |
+
"rewards/accuracies": 1.0,
|
1728 |
+
"rewards/generated": -12.711797714233398,
|
1729 |
+
"rewards/margins": 24.17923355102539,
|
1730 |
+
"rewards/real": 11.467435836791992,
|
1731 |
+
"step": 1220
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 4.69,
|
1735 |
+
"learning_rate": 1.2093352192362092e-07,
|
1736 |
+
"logits/generated": 3.1363422870635986,
|
1737 |
+
"logits/real": 2.7018938064575195,
|
1738 |
+
"logps/generated": -546.12109375,
|
1739 |
+
"logps/real": -1475.1849365234375,
|
1740 |
+
"loss": 0.0003,
|
1741 |
+
"rewards/accuracies": 1.0,
|
1742 |
+
"rewards/generated": -12.732572555541992,
|
1743 |
+
"rewards/margins": 26.642467498779297,
|
1744 |
+
"rewards/real": 13.90989875793457,
|
1745 |
+
"step": 1230
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 4.72,
|
1749 |
+
"learning_rate": 1.1739745403111739e-07,
|
1750 |
+
"logits/generated": 3.2991225719451904,
|
1751 |
+
"logits/real": 2.5671286582946777,
|
1752 |
+
"logps/generated": -463.2415466308594,
|
1753 |
+
"logps/real": -1702.0286865234375,
|
1754 |
+
"loss": 0.0004,
|
1755 |
+
"rewards/accuracies": 1.0,
|
1756 |
+
"rewards/generated": -11.021214485168457,
|
1757 |
+
"rewards/margins": 26.277912139892578,
|
1758 |
+
"rewards/real": 15.256696701049805,
|
1759 |
+
"step": 1240
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 4.76,
|
1763 |
+
"learning_rate": 1.1386138613861386e-07,
|
1764 |
+
"logits/generated": 3.336590528488159,
|
1765 |
+
"logits/real": 2.4211459159851074,
|
1766 |
+
"logps/generated": -574.0828857421875,
|
1767 |
+
"logps/real": -1439.0128173828125,
|
1768 |
+
"loss": 0.0003,
|
1769 |
+
"rewards/accuracies": 1.0,
|
1770 |
+
"rewards/generated": -13.705076217651367,
|
1771 |
+
"rewards/margins": 25.831045150756836,
|
1772 |
+
"rewards/real": 12.125969886779785,
|
1773 |
+
"step": 1250
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 4.8,
|
1777 |
+
"learning_rate": 1.1032531824611033e-07,
|
1778 |
+
"logits/generated": 3.1198062896728516,
|
1779 |
+
"logits/real": 2.5011868476867676,
|
1780 |
+
"logps/generated": -568.57177734375,
|
1781 |
+
"logps/real": -1326.2716064453125,
|
1782 |
+
"loss": 0.0006,
|
1783 |
+
"rewards/accuracies": 1.0,
|
1784 |
+
"rewards/generated": -12.998083114624023,
|
1785 |
+
"rewards/margins": 25.015640258789062,
|
1786 |
+
"rewards/real": 12.017557144165039,
|
1787 |
+
"step": 1260
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 4.84,
|
1791 |
+
"learning_rate": 1.0678925035360678e-07,
|
1792 |
+
"logits/generated": 3.2028965950012207,
|
1793 |
+
"logits/real": 2.5122649669647217,
|
1794 |
+
"logps/generated": -561.6862182617188,
|
1795 |
+
"logps/real": -1607.349365234375,
|
1796 |
+
"loss": 0.0005,
|
1797 |
+
"rewards/accuracies": 1.0,
|
1798 |
+
"rewards/generated": -13.135000228881836,
|
1799 |
+
"rewards/margins": 26.576717376708984,
|
1800 |
+
"rewards/real": 13.441716194152832,
|
1801 |
+
"step": 1270
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 4.88,
|
1805 |
+
"learning_rate": 1.0325318246110325e-07,
|
1806 |
+
"logits/generated": 3.216439723968506,
|
1807 |
+
"logits/real": 2.6768908500671387,
|
1808 |
+
"logps/generated": -613.3177490234375,
|
1809 |
+
"logps/real": -1402.431396484375,
|
1810 |
+
"loss": 0.0003,
|
1811 |
+
"rewards/accuracies": 1.0,
|
1812 |
+
"rewards/generated": -15.124387741088867,
|
1813 |
+
"rewards/margins": 28.185840606689453,
|
1814 |
+
"rewards/real": 13.061452865600586,
|
1815 |
+
"step": 1280
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 4.91,
|
1819 |
+
"learning_rate": 9.971711456859971e-08,
|
1820 |
+
"logits/generated": 3.2150936126708984,
|
1821 |
+
"logits/real": 2.443791627883911,
|
1822 |
+
"logps/generated": -570.3302001953125,
|
1823 |
+
"logps/real": -1579.4129638671875,
|
1824 |
+
"loss": 0.0003,
|
1825 |
+
"rewards/accuracies": 1.0,
|
1826 |
+
"rewards/generated": -13.96008586883545,
|
1827 |
+
"rewards/margins": 27.931583404541016,
|
1828 |
+
"rewards/real": 13.97149658203125,
|
1829 |
+
"step": 1290
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 4.95,
|
1833 |
+
"learning_rate": 9.618104667609618e-08,
|
1834 |
+
"logits/generated": 3.172091007232666,
|
1835 |
+
"logits/real": 2.476423978805542,
|
1836 |
+
"logps/generated": -550.3682250976562,
|
1837 |
+
"logps/real": -1797.6273193359375,
|
1838 |
+
"loss": 0.0003,
|
1839 |
+
"rewards/accuracies": 1.0,
|
1840 |
+
"rewards/generated": -13.748133659362793,
|
1841 |
+
"rewards/margins": 27.63075828552246,
|
1842 |
+
"rewards/real": 13.882623672485352,
|
1843 |
+
"step": 1300
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 4.99,
|
1847 |
+
"learning_rate": 9.264497878359263e-08,
|
1848 |
+
"logits/generated": 3.2214691638946533,
|
1849 |
+
"logits/real": 2.508018732070923,
|
1850 |
+
"logps/generated": -520.4338989257812,
|
1851 |
+
"logps/real": -1491.5899658203125,
|
1852 |
+
"loss": 0.0001,
|
1853 |
+
"rewards/accuracies": 1.0,
|
1854 |
+
"rewards/generated": -12.596437454223633,
|
1855 |
+
"rewards/margins": 27.078861236572266,
|
1856 |
+
"rewards/real": 14.482423782348633,
|
1857 |
+
"step": 1310
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 5.03,
|
1861 |
+
"learning_rate": 8.91089108910891e-08,
|
1862 |
+
"logits/generated": 3.090144634246826,
|
1863 |
+
"logits/real": 2.64501953125,
|
1864 |
+
"logps/generated": -575.699462890625,
|
1865 |
+
"logps/real": -1449.6285400390625,
|
1866 |
+
"loss": 0.0003,
|
1867 |
+
"rewards/accuracies": 1.0,
|
1868 |
+
"rewards/generated": -13.906789779663086,
|
1869 |
+
"rewards/margins": 27.012332916259766,
|
1870 |
+
"rewards/real": 13.105542182922363,
|
1871 |
+
"step": 1320
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 5.07,
|
1875 |
+
"learning_rate": 8.557284299858557e-08,
|
1876 |
+
"logits/generated": 3.216085910797119,
|
1877 |
+
"logits/real": 2.628757953643799,
|
1878 |
+
"logps/generated": -563.4234619140625,
|
1879 |
+
"logps/real": -1506.6536865234375,
|
1880 |
+
"loss": 0.0002,
|
1881 |
+
"rewards/accuracies": 1.0,
|
1882 |
+
"rewards/generated": -14.473469734191895,
|
1883 |
+
"rewards/margins": 27.185466766357422,
|
1884 |
+
"rewards/real": 12.711997032165527,
|
1885 |
+
"step": 1330
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 5.1,
|
1889 |
+
"learning_rate": 8.203677510608204e-08,
|
1890 |
+
"logits/generated": 3.2252001762390137,
|
1891 |
+
"logits/real": 2.5635406970977783,
|
1892 |
+
"logps/generated": -554.8922119140625,
|
1893 |
+
"logps/real": -1379.961669921875,
|
1894 |
+
"loss": 0.0003,
|
1895 |
+
"rewards/accuracies": 1.0,
|
1896 |
+
"rewards/generated": -13.215415954589844,
|
1897 |
+
"rewards/margins": 24.81317138671875,
|
1898 |
+
"rewards/real": 11.597757339477539,
|
1899 |
+
"step": 1340
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 5.14,
|
1903 |
+
"learning_rate": 7.85007072135785e-08,
|
1904 |
+
"logits/generated": 3.1512575149536133,
|
1905 |
+
"logits/real": 2.3962998390197754,
|
1906 |
+
"logps/generated": -574.1869506835938,
|
1907 |
+
"logps/real": -1498.155517578125,
|
1908 |
+
"loss": 0.0002,
|
1909 |
+
"rewards/accuracies": 1.0,
|
1910 |
+
"rewards/generated": -13.913461685180664,
|
1911 |
+
"rewards/margins": 27.563989639282227,
|
1912 |
+
"rewards/real": 13.650527954101562,
|
1913 |
+
"step": 1350
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 5.18,
|
1917 |
+
"learning_rate": 7.496463932107496e-08,
|
1918 |
+
"logits/generated": 3.3186583518981934,
|
1919 |
+
"logits/real": 2.5883545875549316,
|
1920 |
+
"logps/generated": -550.5670166015625,
|
1921 |
+
"logps/real": -1544.77392578125,
|
1922 |
+
"loss": 0.0002,
|
1923 |
+
"rewards/accuracies": 1.0,
|
1924 |
+
"rewards/generated": -12.482427597045898,
|
1925 |
+
"rewards/margins": 27.15085220336914,
|
1926 |
+
"rewards/real": 14.668424606323242,
|
1927 |
+
"step": 1360
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 5.22,
|
1931 |
+
"learning_rate": 7.142857142857142e-08,
|
1932 |
+
"logits/generated": 3.263967990875244,
|
1933 |
+
"logits/real": 2.536264181137085,
|
1934 |
+
"logps/generated": -589.7340698242188,
|
1935 |
+
"logps/real": -1500.179931640625,
|
1936 |
+
"loss": 0.0004,
|
1937 |
+
"rewards/accuracies": 1.0,
|
1938 |
+
"rewards/generated": -15.068285942077637,
|
1939 |
+
"rewards/margins": 28.84073829650879,
|
1940 |
+
"rewards/real": 13.772455215454102,
|
1941 |
+
"step": 1370
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 5.26,
|
1945 |
+
"learning_rate": 6.789250353606789e-08,
|
1946 |
+
"logits/generated": 3.497816801071167,
|
1947 |
+
"logits/real": 2.428816318511963,
|
1948 |
+
"logps/generated": -596.6787109375,
|
1949 |
+
"logps/real": -1555.1085205078125,
|
1950 |
+
"loss": 0.0003,
|
1951 |
+
"rewards/accuracies": 1.0,
|
1952 |
+
"rewards/generated": -15.438451766967773,
|
1953 |
+
"rewards/margins": 29.081518173217773,
|
1954 |
+
"rewards/real": 13.643072128295898,
|
1955 |
+
"step": 1380
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 5.3,
|
1959 |
+
"learning_rate": 6.435643564356436e-08,
|
1960 |
+
"logits/generated": 3.010061264038086,
|
1961 |
+
"logits/real": 2.4792978763580322,
|
1962 |
+
"logps/generated": -526.48046875,
|
1963 |
+
"logps/real": -1130.676513671875,
|
1964 |
+
"loss": 0.0002,
|
1965 |
+
"rewards/accuracies": 1.0,
|
1966 |
+
"rewards/generated": -13.853174209594727,
|
1967 |
+
"rewards/margins": 25.5134334564209,
|
1968 |
+
"rewards/real": 11.660261154174805,
|
1969 |
+
"step": 1390
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 5.33,
|
1973 |
+
"learning_rate": 6.082036775106081e-08,
|
1974 |
+
"logits/generated": 3.1093571186065674,
|
1975 |
+
"logits/real": 2.4732513427734375,
|
1976 |
+
"logps/generated": -529.5757446289062,
|
1977 |
+
"logps/real": -1343.6026611328125,
|
1978 |
+
"loss": 0.0001,
|
1979 |
+
"rewards/accuracies": 1.0,
|
1980 |
+
"rewards/generated": -12.401544570922852,
|
1981 |
+
"rewards/margins": 25.137725830078125,
|
1982 |
+
"rewards/real": 12.736178398132324,
|
1983 |
+
"step": 1400
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 5.37,
|
1987 |
+
"learning_rate": 5.7284299858557285e-08,
|
1988 |
+
"logits/generated": 3.3876266479492188,
|
1989 |
+
"logits/real": 2.5899083614349365,
|
1990 |
+
"logps/generated": -588.9549560546875,
|
1991 |
+
"logps/real": -1509.0943603515625,
|
1992 |
+
"loss": 0.0002,
|
1993 |
+
"rewards/accuracies": 1.0,
|
1994 |
+
"rewards/generated": -13.996371269226074,
|
1995 |
+
"rewards/margins": 27.71066665649414,
|
1996 |
+
"rewards/real": 13.714296340942383,
|
1997 |
+
"step": 1410
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 5.41,
|
2001 |
+
"learning_rate": 5.374823196605375e-08,
|
2002 |
+
"logits/generated": 3.112064838409424,
|
2003 |
+
"logits/real": 2.6190438270568848,
|
2004 |
+
"logps/generated": -551.2916870117188,
|
2005 |
+
"logps/real": -1541.237060546875,
|
2006 |
+
"loss": 0.0003,
|
2007 |
+
"rewards/accuracies": 1.0,
|
2008 |
+
"rewards/generated": -13.962061882019043,
|
2009 |
+
"rewards/margins": 27.94354248046875,
|
2010 |
+
"rewards/real": 13.981483459472656,
|
2011 |
+
"step": 1420
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 5.45,
|
2015 |
+
"learning_rate": 5.0212164073550206e-08,
|
2016 |
+
"logits/generated": 3.4540042877197266,
|
2017 |
+
"logits/real": 2.519503116607666,
|
2018 |
+
"logps/generated": -547.7754516601562,
|
2019 |
+
"logps/real": -1539.6217041015625,
|
2020 |
+
"loss": 0.0002,
|
2021 |
+
"rewards/accuracies": 1.0,
|
2022 |
+
"rewards/generated": -13.80566692352295,
|
2023 |
+
"rewards/margins": 27.109554290771484,
|
2024 |
+
"rewards/real": 13.303888320922852,
|
2025 |
+
"step": 1430
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 5.49,
|
2029 |
+
"learning_rate": 4.667609618104667e-08,
|
2030 |
+
"logits/generated": 3.2564361095428467,
|
2031 |
+
"logits/real": 2.5632336139678955,
|
2032 |
+
"logps/generated": -564.44287109375,
|
2033 |
+
"logps/real": -1403.699951171875,
|
2034 |
+
"loss": 0.0004,
|
2035 |
+
"rewards/accuracies": 1.0,
|
2036 |
+
"rewards/generated": -14.87768268585205,
|
2037 |
+
"rewards/margins": 27.802310943603516,
|
2038 |
+
"rewards/real": 12.924627304077148,
|
2039 |
+
"step": 1440
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 5.52,
|
2043 |
+
"learning_rate": 4.3140028288543134e-08,
|
2044 |
+
"logits/generated": 3.235797166824341,
|
2045 |
+
"logits/real": 2.559129238128662,
|
2046 |
+
"logps/generated": -535.4729614257812,
|
2047 |
+
"logps/real": -1371.961669921875,
|
2048 |
+
"loss": 0.0001,
|
2049 |
+
"rewards/accuracies": 1.0,
|
2050 |
+
"rewards/generated": -13.979475021362305,
|
2051 |
+
"rewards/margins": 26.749774932861328,
|
2052 |
+
"rewards/real": 12.770299911499023,
|
2053 |
+
"step": 1450
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 5.56,
|
2057 |
+
"learning_rate": 3.96039603960396e-08,
|
2058 |
+
"logits/generated": 3.105957508087158,
|
2059 |
+
"logits/real": 2.7094485759735107,
|
2060 |
+
"logps/generated": -624.28662109375,
|
2061 |
+
"logps/real": -1619.6658935546875,
|
2062 |
+
"loss": 0.0002,
|
2063 |
+
"rewards/accuracies": 1.0,
|
2064 |
+
"rewards/generated": -16.26133155822754,
|
2065 |
+
"rewards/margins": 30.236867904663086,
|
2066 |
+
"rewards/real": 13.97553825378418,
|
2067 |
+
"step": 1460
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 5.6,
|
2071 |
+
"learning_rate": 3.606789250353607e-08,
|
2072 |
+
"logits/generated": 3.269968032836914,
|
2073 |
+
"logits/real": 2.525156021118164,
|
2074 |
+
"logps/generated": -547.2183837890625,
|
2075 |
+
"logps/real": -1683.659423828125,
|
2076 |
+
"loss": 0.0001,
|
2077 |
+
"rewards/accuracies": 1.0,
|
2078 |
+
"rewards/generated": -13.063116073608398,
|
2079 |
+
"rewards/margins": 28.569652557373047,
|
2080 |
+
"rewards/real": 15.506538391113281,
|
2081 |
+
"step": 1470
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 5.64,
|
2085 |
+
"learning_rate": 3.253182461103253e-08,
|
2086 |
+
"logits/generated": 3.100898265838623,
|
2087 |
+
"logits/real": 2.5007834434509277,
|
2088 |
+
"logps/generated": -537.1228637695312,
|
2089 |
+
"logps/real": -1622.945556640625,
|
2090 |
+
"loss": 0.0003,
|
2091 |
+
"rewards/accuracies": 1.0,
|
2092 |
+
"rewards/generated": -13.297723770141602,
|
2093 |
+
"rewards/margins": 27.18996810913086,
|
2094 |
+
"rewards/real": 13.892248153686523,
|
2095 |
+
"step": 1480
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 5.68,
|
2099 |
+
"learning_rate": 2.8995756718528992e-08,
|
2100 |
+
"logits/generated": 3.1697795391082764,
|
2101 |
+
"logits/real": 2.515049457550049,
|
2102 |
+
"logps/generated": -528.9276733398438,
|
2103 |
+
"logps/real": -1365.165771484375,
|
2104 |
+
"loss": 0.0001,
|
2105 |
+
"rewards/accuracies": 1.0,
|
2106 |
+
"rewards/generated": -12.908604621887207,
|
2107 |
+
"rewards/margins": 25.516712188720703,
|
2108 |
+
"rewards/real": 12.608107566833496,
|
2109 |
+
"step": 1490
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 5.71,
|
2113 |
+
"learning_rate": 2.545968882602546e-08,
|
2114 |
+
"logits/generated": 3.247465133666992,
|
2115 |
+
"logits/real": 2.738851308822632,
|
2116 |
+
"logps/generated": -526.6806030273438,
|
2117 |
+
"logps/real": -1680.171142578125,
|
2118 |
+
"loss": 0.0002,
|
2119 |
+
"rewards/accuracies": 1.0,
|
2120 |
+
"rewards/generated": -13.784246444702148,
|
2121 |
+
"rewards/margins": 29.31841468811035,
|
2122 |
+
"rewards/real": 15.53416633605957,
|
2123 |
+
"step": 1500
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 5.75,
|
2127 |
+
"learning_rate": 2.1923620933521923e-08,
|
2128 |
+
"logits/generated": 3.180821180343628,
|
2129 |
+
"logits/real": 2.666006565093994,
|
2130 |
+
"logps/generated": -635.9178466796875,
|
2131 |
+
"logps/real": -1368.9986572265625,
|
2132 |
+
"loss": 0.0001,
|
2133 |
+
"rewards/accuracies": 1.0,
|
2134 |
+
"rewards/generated": -14.650575637817383,
|
2135 |
+
"rewards/margins": 27.650531768798828,
|
2136 |
+
"rewards/real": 12.999956130981445,
|
2137 |
+
"step": 1510
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 5.79,
|
2141 |
+
"learning_rate": 1.8387553041018386e-08,
|
2142 |
+
"logits/generated": 3.0839998722076416,
|
2143 |
+
"logits/real": 2.581054210662842,
|
2144 |
+
"logps/generated": -544.0230712890625,
|
2145 |
+
"logps/real": -1359.1251220703125,
|
2146 |
+
"loss": 0.0003,
|
2147 |
+
"rewards/accuracies": 1.0,
|
2148 |
+
"rewards/generated": -12.829536437988281,
|
2149 |
+
"rewards/margins": 26.41360855102539,
|
2150 |
+
"rewards/real": 13.584071159362793,
|
2151 |
+
"step": 1520
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 5.83,
|
2155 |
+
"learning_rate": 1.485148514851485e-08,
|
2156 |
+
"logits/generated": 3.3319427967071533,
|
2157 |
+
"logits/real": 2.6179628372192383,
|
2158 |
+
"logps/generated": -590.0933837890625,
|
2159 |
+
"logps/real": -1592.672119140625,
|
2160 |
+
"loss": 0.0001,
|
2161 |
+
"rewards/accuracies": 1.0,
|
2162 |
+
"rewards/generated": -14.341830253601074,
|
2163 |
+
"rewards/margins": 29.359546661376953,
|
2164 |
+
"rewards/real": 15.017718315124512,
|
2165 |
+
"step": 1530
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 5.87,
|
2169 |
+
"learning_rate": 1.1315417256011316e-08,
|
2170 |
+
"logits/generated": 3.4769108295440674,
|
2171 |
+
"logits/real": 2.5944294929504395,
|
2172 |
+
"logps/generated": -614.6587524414062,
|
2173 |
+
"logps/real": -1540.0328369140625,
|
2174 |
+
"loss": 0.0003,
|
2175 |
+
"rewards/accuracies": 1.0,
|
2176 |
+
"rewards/generated": -15.357019424438477,
|
2177 |
+
"rewards/margins": 28.344806671142578,
|
2178 |
+
"rewards/real": 12.987787246704102,
|
2179 |
+
"step": 1540
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 5.9,
|
2183 |
+
"learning_rate": 7.77934936350778e-09,
|
2184 |
+
"logits/generated": 3.231849193572998,
|
2185 |
+
"logits/real": 2.5611472129821777,
|
2186 |
+
"logps/generated": -572.6622314453125,
|
2187 |
+
"logps/real": -1665.4876708984375,
|
2188 |
+
"loss": 0.0002,
|
2189 |
+
"rewards/accuracies": 1.0,
|
2190 |
+
"rewards/generated": -14.289937019348145,
|
2191 |
+
"rewards/margins": 29.341079711914062,
|
2192 |
+
"rewards/real": 15.051142692565918,
|
2193 |
+
"step": 1550
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 5.94,
|
2197 |
+
"learning_rate": 4.243281471004243e-09,
|
2198 |
+
"logits/generated": 3.283064603805542,
|
2199 |
+
"logits/real": 2.623944044113159,
|
2200 |
+
"logps/generated": -635.8428955078125,
|
2201 |
+
"logps/real": -1552.221923828125,
|
2202 |
+
"loss": 0.0001,
|
2203 |
+
"rewards/accuracies": 1.0,
|
2204 |
+
"rewards/generated": -15.60615348815918,
|
2205 |
+
"rewards/margins": 30.579345703125,
|
2206 |
+
"rewards/real": 14.973190307617188,
|
2207 |
+
"step": 1560
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 5.98,
|
2211 |
+
"learning_rate": 7.072135785007072e-10,
|
2212 |
+
"logits/generated": 3.2523193359375,
|
2213 |
+
"logits/real": 2.4982213973999023,
|
2214 |
+
"logps/generated": -530.0173950195312,
|
2215 |
+
"logps/real": -1398.9669189453125,
|
2216 |
+
"loss": 0.0001,
|
2217 |
+
"rewards/accuracies": 1.0,
|
2218 |
+
"rewards/generated": -12.438911437988281,
|
2219 |
+
"rewards/margins": 25.966604232788086,
|
2220 |
+
"rewards/real": 13.527694702148438,
|
2221 |
+
"step": 1570
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 5.99,
|
2225 |
+
"step": 1572,
|
2226 |
+
"total_flos": 0.0,
|
2227 |
+
"train_loss": 0.018845485343664946,
|
2228 |
+
"train_runtime": 21431.5998,
|
2229 |
+
"train_samples_per_second": 4.703,
|
2230 |
+
"train_steps_per_second": 0.073
|
2231 |
+
}
|
2232 |
+
],
|
2233 |
+
"logging_steps": 10,
|
2234 |
+
"max_steps": 1572,
|
2235 |
+
"num_input_tokens_seen": 0,
|
2236 |
+
"num_train_epochs": 6,
|
2237 |
+
"save_steps": 500,
|
2238 |
+
"total_flos": 0.0,
|
2239 |
+
"train_batch_size": 2,
|
2240 |
+
"trial_name": null,
|
2241 |
+
"trial_params": null
|
2242 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50037d17611f90440fcb35088ca100f6dd9295793a54b1724e58314bd6742dfb
|
3 |
+
size 5816
|