Jiazheng Li
commited on
Commit
·
a57f764
1
Parent(s):
36102ca
init push
Browse files- README.md +80 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +19 -0
- eval_results.json +15 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2065 -0
- train_results.json +7 -0
- trainer_log.jsonl +188 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
- training_rewards_accuracies.png +0 -0
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- llama-factory
|
6 |
+
- lora
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
9 |
+
model-index:
|
10 |
+
- name: sft_trained_woaqa_llama3_dpo
|
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 |
+
# sft_trained_woaqa_llama3_dpo
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the sft_wo_aqa_pref dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 2.0569
|
22 |
+
- Rewards/chosen: 9.0148
|
23 |
+
- Rewards/rejected: 7.8220
|
24 |
+
- Rewards/accuracies: 0.6667
|
25 |
+
- Rewards/margins: 1.1928
|
26 |
+
- Logps/rejected: -180.5298
|
27 |
+
- Logps/chosen: -151.5047
|
28 |
+
- Logits/rejected: -1.4439
|
29 |
+
- Logits/chosen: -1.4397
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 1e-05
|
49 |
+
- train_batch_size: 1
|
50 |
+
- eval_batch_size: 1
|
51 |
+
- seed: 42
|
52 |
+
- gradient_accumulation_steps: 8
|
53 |
+
- total_train_batch_size: 8
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: cosine
|
56 |
+
- lr_scheduler_warmup_steps: 0.1
|
57 |
+
- num_epochs: 3.0
|
58 |
+
- mixed_precision_training: Native AMP
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
64 |
+
| 1.3287 | 0.33 | 200 | 1.8699 | 9.9343 | 9.1282 | 0.6312 | 0.8061 | -167.4677 | -142.3102 | -1.1863 | -1.1862 |
|
65 |
+
| 1.1821 | 0.67 | 400 | 1.9729 | 9.9379 | 9.2024 | 0.6113 | 0.7354 | -166.7256 | -142.2745 | -1.2732 | -1.2718 |
|
66 |
+
| 0.9116 | 1.0 | 600 | 1.9455 | 9.7997 | 8.9466 | 0.6482 | 0.8531 | -169.2835 | -143.6562 | -1.3527 | -1.3510 |
|
67 |
+
| 0.8412 | 1.33 | 800 | 2.0041 | 9.5449 | 8.5167 | 0.6397 | 1.0282 | -173.5831 | -146.2043 | -1.4206 | -1.4179 |
|
68 |
+
| 0.7345 | 1.67 | 1000 | 2.0659 | 9.1494 | 8.1514 | 0.6426 | 0.9980 | -177.2357 | -150.1593 | -1.4325 | -1.4290 |
|
69 |
+
| 0.6609 | 2.0 | 1200 | 2.0321 | 9.0327 | 7.8126 | 0.6681 | 1.2200 | -180.6237 | -151.3265 | -1.4359 | -1.4321 |
|
70 |
+
| 0.6768 | 2.33 | 1400 | 2.0313 | 9.1007 | 7.8929 | 0.6709 | 1.2079 | -179.8211 | -150.6457 | -1.4472 | -1.4432 |
|
71 |
+
| 0.615 | 2.67 | 1600 | 2.0515 | 9.0972 | 7.9582 | 0.6624 | 1.1390 | -179.1680 | -150.6812 | -1.4413 | -1.4370 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- PEFT 0.10.0
|
77 |
+
- Transformers 4.38.2
|
78 |
+
- Pytorch 2.2.1+cu121
|
79 |
+
- Datasets 2.18.0
|
80 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"o_proj",
|
26 |
+
"down_proj",
|
27 |
+
"up_proj",
|
28 |
+
"v_proj",
|
29 |
+
"q_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2493976b74b0dd11d080ba9d6c4f96634332af3dcb376eff19892306435c54a
|
3 |
+
size 83945296
|
all_results.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": -1.4396553039550781,
|
4 |
+
"eval_logits/rejected": -1.4439030885696411,
|
5 |
+
"eval_logps/chosen": -151.50469970703125,
|
6 |
+
"eval_logps/rejected": -180.52976989746094,
|
7 |
+
"eval_loss": 2.0568761825561523,
|
8 |
+
"eval_rewards/accuracies": 0.6666666865348816,
|
9 |
+
"eval_rewards/chosen": 9.014835357666016,
|
10 |
+
"eval_rewards/margins": 1.1928315162658691,
|
11 |
+
"eval_rewards/rejected": 7.822003364562988,
|
12 |
+
"eval_runtime": 280.3771,
|
13 |
+
"eval_samples_per_second": 2.514,
|
14 |
+
"eval_steps_per_second": 2.514,
|
15 |
+
"train_loss": 0.8950637202828078,
|
16 |
+
"train_runtime": 14615.0375,
|
17 |
+
"train_samples_per_second": 0.985,
|
18 |
+
"train_steps_per_second": 0.123
|
19 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": -1.4396553039550781,
|
4 |
+
"eval_logits/rejected": -1.4439030885696411,
|
5 |
+
"eval_logps/chosen": -151.50469970703125,
|
6 |
+
"eval_logps/rejected": -180.52976989746094,
|
7 |
+
"eval_loss": 2.0568761825561523,
|
8 |
+
"eval_rewards/accuracies": 0.6666666865348816,
|
9 |
+
"eval_rewards/chosen": 9.014835357666016,
|
10 |
+
"eval_rewards/margins": 1.1928315162658691,
|
11 |
+
"eval_rewards/rejected": 7.822003364562988,
|
12 |
+
"eval_runtime": 280.3771,
|
13 |
+
"eval_samples_per_second": 2.514,
|
14 |
+
"eval_steps_per_second": 2.514
|
15 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|eot_id|>"
|
17 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|reserved_special_token_2|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_3|>",
|
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": "<|reserved_special_token_4|>",
|
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": "<|reserved_special_token_5|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_6|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_7|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_8|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_9|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_10|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_11|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_12|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_13|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_14|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_15|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_16|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_17|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_18|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_19|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_20|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_21|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_22|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_23|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_24|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_25|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_26|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_27|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_28|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_29|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_30|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_31|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_32|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_33|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_34|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_35|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_36|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_37|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_38|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_39|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_40|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_41|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_42|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_43|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_44|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_45|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_46|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_47|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_48|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_49|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_50|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_51|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_52|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_53|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_54|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_55|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_56|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_57|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_58|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_59|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_60|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_61|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_62|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_63|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_64|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_65|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_66|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_67|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_68|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_69|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_70|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_71|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_72|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_73|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_74|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_75|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_76|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_77|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_78|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_79|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_80|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_81|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_82|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_83|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_84|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_85|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_86|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_87|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_88|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_89|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_90|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_91|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_92|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_93|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_94|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_95|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_96|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_97|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_98|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_99|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_100|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_101|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_102|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_103|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_104|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_105|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_106|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_107|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_108|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_109|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_110|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_111|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_112|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_113|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_114|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_115|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_116|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_117|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_118|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_119|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_120|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_121|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_122|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_123|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_124|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_125|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_126|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_127|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_128|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_129|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_130|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_131|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_132|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_133|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_134|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_135|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_136|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_137|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_138|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_139|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_140|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_141|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_142|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_143|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_144|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_145|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_146|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_147|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_148|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_149|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_150|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_151|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_152|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_153|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_154|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_155|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_156|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_157|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_158|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_159|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_160|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_161|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_162|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_163|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_164|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_165|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_166|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_167|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_168|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_169|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_170|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_171|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_172|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_173|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_174|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_175|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_176|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_177|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_178|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_179|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_180|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_181|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_182|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_183|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_184|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_185|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_186|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_187|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_188|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_189|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_190|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_191|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_192|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_193|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_194|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_195|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_196|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_197|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_198|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_199|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_200|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_201|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_202|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_203|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_204|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_205|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_206|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_207|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_208|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_209|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_210|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_211|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_212|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_213|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_214|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_215|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_216|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_217|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_218|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_219|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_220|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_221|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_222|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_223|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_224|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_225|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_226|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_227|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_228|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_229|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_230|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_231|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_232|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_233|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_234|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_235|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_236|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_237|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_238|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_239|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_240|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_241|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_242|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_243|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_244|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_245|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_246|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_247|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_248|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_249|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_250|>",
|
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": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>\\n\\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\\n\\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 1000000000000000019884624838656,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
+
"padding_side": "right",
|
2063 |
+
"split_special_tokens": false,
|
2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2065 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.8950637202828078,
|
4 |
+
"train_runtime": 14615.0375,
|
5 |
+
"train_samples_per_second": 0.985,
|
6 |
+
"train_steps_per_second": 0.123
|
7 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,188 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 10, "total_steps": 1797, "loss": 1.5859, "accuracy": 0.6625000238418579, "learning_rate": 9.999523086940423e-06, "epoch": 0.02, "percentage": 0.56, "elapsed_time": "0:01:07", "remaining_time": "3:21:35"}
|
2 |
+
{"current_steps": 20, "total_steps": 1797, "loss": 1.786, "accuracy": 0.5874999761581421, "learning_rate": 9.997817603030276e-06, "epoch": 0.03, "percentage": 1.11, "elapsed_time": "0:02:16", "remaining_time": "3:21:56"}
|
3 |
+
{"current_steps": 30, "total_steps": 1797, "loss": 1.4256, "accuracy": 0.75, "learning_rate": 9.994471383754724e-06, "epoch": 0.05, "percentage": 1.67, "elapsed_time": "0:03:24", "remaining_time": "3:21:02"}
|
4 |
+
{"current_steps": 40, "total_steps": 1797, "loss": 1.5826, "accuracy": 0.699999988079071, "learning_rate": 9.990154489175436e-06, "epoch": 0.07, "percentage": 2.23, "elapsed_time": "0:04:33", "remaining_time": "3:20:12"}
|
5 |
+
{"current_steps": 50, "total_steps": 1797, "loss": 1.4624, "accuracy": 0.7749999761581421, "learning_rate": 9.983908955774398e-06, "epoch": 0.08, "percentage": 2.78, "elapsed_time": "0:05:43", "remaining_time": "3:19:53"}
|
6 |
+
{"current_steps": 60, "total_steps": 1797, "loss": 1.5662, "accuracy": 0.75, "learning_rate": 9.976140032846158e-06, "epoch": 0.1, "percentage": 3.34, "elapsed_time": "0:06:53", "remaining_time": "3:19:28"}
|
7 |
+
{"current_steps": 70, "total_steps": 1797, "loss": 1.3566, "accuracy": 0.8125, "learning_rate": 9.966850095052043e-06, "epoch": 0.12, "percentage": 3.9, "elapsed_time": "0:08:02", "remaining_time": "3:18:15"}
|
8 |
+
{"current_steps": 80, "total_steps": 1797, "loss": 1.3657, "accuracy": 0.8125, "learning_rate": 9.956041981969192e-06, "epoch": 0.13, "percentage": 4.45, "elapsed_time": "0:09:09", "remaining_time": "3:16:29"}
|
9 |
+
{"current_steps": 90, "total_steps": 1797, "loss": 1.3773, "accuracy": 0.8374999761581421, "learning_rate": 9.943718997222616e-06, "epoch": 0.15, "percentage": 5.01, "elapsed_time": "0:10:18", "remaining_time": "3:15:29"}
|
10 |
+
{"current_steps": 100, "total_steps": 1797, "loss": 1.3082, "accuracy": 0.7749999761581421, "learning_rate": 9.929884907475405e-06, "epoch": 0.17, "percentage": 5.56, "elapsed_time": "0:11:26", "remaining_time": "3:14:12"}
|
11 |
+
{"current_steps": 110, "total_steps": 1797, "loss": 1.2816, "accuracy": 0.862500011920929, "learning_rate": 9.914543941277401e-06, "epoch": 0.18, "percentage": 6.12, "elapsed_time": "0:12:38", "remaining_time": "3:13:56"}
|
12 |
+
{"current_steps": 120, "total_steps": 1797, "loss": 1.4305, "accuracy": 0.7749999761581421, "learning_rate": 9.897700787772703e-06, "epoch": 0.2, "percentage": 6.68, "elapsed_time": "0:13:48", "remaining_time": "3:12:51"}
|
13 |
+
{"current_steps": 130, "total_steps": 1797, "loss": 1.1746, "accuracy": 0.8374999761581421, "learning_rate": 9.879360595266359e-06, "epoch": 0.22, "percentage": 7.23, "elapsed_time": "0:14:55", "remaining_time": "3:11:20"}
|
14 |
+
{"current_steps": 140, "total_steps": 1797, "loss": 1.3081, "accuracy": 0.8500000238418579, "learning_rate": 9.861579077506591e-06, "epoch": 0.23, "percentage": 7.79, "elapsed_time": "0:16:05", "remaining_time": "3:10:25"}
|
15 |
+
{"current_steps": 150, "total_steps": 1797, "loss": 1.3711, "accuracy": 0.7749999761581421, "learning_rate": 9.84041033194796e-06, "epoch": 0.25, "percentage": 8.35, "elapsed_time": "0:17:15", "remaining_time": "3:09:31"}
|
16 |
+
{"current_steps": 160, "total_steps": 1797, "loss": 1.4901, "accuracy": 0.7250000238418579, "learning_rate": 9.817762058879405e-06, "epoch": 0.27, "percentage": 8.9, "elapsed_time": "0:18:23", "remaining_time": "3:08:10"}
|
17 |
+
{"current_steps": 170, "total_steps": 1797, "loss": 1.3182, "accuracy": 0.862500011920929, "learning_rate": 9.793641181008042e-06, "epoch": 0.28, "percentage": 9.46, "elapsed_time": "0:19:34", "remaining_time": "3:07:20"}
|
18 |
+
{"current_steps": 180, "total_steps": 1797, "loss": 1.3317, "accuracy": 0.8374999761581421, "learning_rate": 9.76805507115971e-06, "epoch": 0.3, "percentage": 10.02, "elapsed_time": "0:20:42", "remaining_time": "3:06:02"}
|
19 |
+
{"current_steps": 190, "total_steps": 1797, "loss": 1.3589, "accuracy": 0.7875000238418579, "learning_rate": 9.741011550025385e-06, "epoch": 0.32, "percentage": 10.57, "elapsed_time": "0:21:50", "remaining_time": "3:04:47"}
|
20 |
+
{"current_steps": 200, "total_steps": 1797, "loss": 1.3287, "accuracy": 0.75, "learning_rate": 9.71251888377069e-06, "epoch": 0.33, "percentage": 11.13, "elapsed_time": "0:22:59", "remaining_time": "3:03:37"}
|
21 |
+
{"current_steps": 200, "total_steps": 1797, "eval_loss": 1.8699389696121216, "epoch": 0.33, "percentage": 11.13, "elapsed_time": "0:27:40", "remaining_time": "3:40:56"}
|
22 |
+
{"current_steps": 210, "total_steps": 1797, "loss": 1.1424, "accuracy": 0.9125000238418579, "learning_rate": 9.682585781509243e-06, "epoch": 0.35, "percentage": 11.69, "elapsed_time": "0:28:49", "remaining_time": "3:37:46"}
|
23 |
+
{"current_steps": 220, "total_steps": 1797, "loss": 1.3393, "accuracy": 0.7875000238418579, "learning_rate": 9.651221392640626e-06, "epoch": 0.37, "percentage": 12.24, "elapsed_time": "0:29:58", "remaining_time": "3:34:55"}
|
24 |
+
{"current_steps": 230, "total_steps": 1797, "loss": 1.0207, "accuracy": 0.9375, "learning_rate": 9.618435304053756e-06, "epoch": 0.38, "percentage": 12.8, "elapsed_time": "0:31:06", "remaining_time": "3:31:55"}
|
25 |
+
{"current_steps": 240, "total_steps": 1797, "loss": 1.3149, "accuracy": 0.8500000238418579, "learning_rate": 9.584237537196539e-06, "epoch": 0.4, "percentage": 13.36, "elapsed_time": "0:32:15", "remaining_time": "3:29:18"}
|
26 |
+
{"current_steps": 250, "total_steps": 1797, "loss": 1.2689, "accuracy": 0.824999988079071, "learning_rate": 9.548638545012714e-06, "epoch": 0.42, "percentage": 13.91, "elapsed_time": "0:33:22", "remaining_time": "3:26:33"}
|
27 |
+
{"current_steps": 260, "total_steps": 1797, "loss": 1.2776, "accuracy": 0.824999988079071, "learning_rate": 9.511649208746768e-06, "epoch": 0.43, "percentage": 14.47, "elapsed_time": "0:34:31", "remaining_time": "3:24:03"}
|
28 |
+
{"current_steps": 270, "total_steps": 1797, "loss": 1.3095, "accuracy": 0.7875000238418579, "learning_rate": 9.473280834617975e-06, "epoch": 0.45, "percentage": 15.03, "elapsed_time": "0:35:39", "remaining_time": "3:21:38"}
|
29 |
+
{"current_steps": 280, "total_steps": 1797, "loss": 1.3453, "accuracy": 0.8500000238418579, "learning_rate": 9.43354515036451e-06, "epoch": 0.47, "percentage": 15.58, "elapsed_time": "0:36:50", "remaining_time": "3:19:35"}
|
30 |
+
{"current_steps": 290, "total_steps": 1797, "loss": 1.3024, "accuracy": 0.8500000238418579, "learning_rate": 9.392454301658734e-06, "epoch": 0.48, "percentage": 16.14, "elapsed_time": "0:38:00", "remaining_time": "3:17:28"}
|
31 |
+
{"current_steps": 300, "total_steps": 1797, "loss": 1.3095, "accuracy": 0.8500000238418579, "learning_rate": 9.350020848394722e-06, "epoch": 0.5, "percentage": 16.69, "elapsed_time": "0:39:09", "remaining_time": "3:15:23"}
|
32 |
+
{"current_steps": 310, "total_steps": 1797, "loss": 1.1376, "accuracy": 0.862500011920929, "learning_rate": 9.306257760849198e-06, "epoch": 0.52, "percentage": 17.25, "elapsed_time": "0:40:18", "remaining_time": "3:13:19"}
|
33 |
+
{"current_steps": 320, "total_steps": 1797, "loss": 1.1728, "accuracy": 0.875, "learning_rate": 9.261178415717006e-06, "epoch": 0.53, "percentage": 17.81, "elapsed_time": "0:41:27", "remaining_time": "3:11:21"}
|
34 |
+
{"current_steps": 330, "total_steps": 1797, "loss": 1.1413, "accuracy": 0.887499988079071, "learning_rate": 9.214796592022378e-06, "epoch": 0.55, "percentage": 18.36, "elapsed_time": "0:42:35", "remaining_time": "3:09:22"}
|
35 |
+
{"current_steps": 340, "total_steps": 1797, "loss": 1.2402, "accuracy": 0.8374999761581421, "learning_rate": 9.167126466907215e-06, "epoch": 0.57, "percentage": 18.92, "elapsed_time": "0:43:44", "remaining_time": "3:07:25"}
|
36 |
+
{"current_steps": 350, "total_steps": 1797, "loss": 1.327, "accuracy": 0.8125, "learning_rate": 9.118182611297665e-06, "epoch": 0.58, "percentage": 19.48, "elapsed_time": "0:44:55", "remaining_time": "3:05:43"}
|
37 |
+
{"current_steps": 360, "total_steps": 1797, "loss": 1.1041, "accuracy": 0.925000011920929, "learning_rate": 9.067979985450377e-06, "epoch": 0.6, "percentage": 20.03, "elapsed_time": "0:46:04", "remaining_time": "3:03:56"}
|
38 |
+
{"current_steps": 370, "total_steps": 1797, "loss": 1.0528, "accuracy": 0.925000011920929, "learning_rate": 9.016533934379697e-06, "epoch": 0.62, "percentage": 20.59, "elapsed_time": "0:47:13", "remaining_time": "3:02:07"}
|
39 |
+
{"current_steps": 380, "total_steps": 1797, "loss": 1.0856, "accuracy": 0.887499988079071, "learning_rate": 8.96386018316731e-06, "epoch": 0.63, "percentage": 21.15, "elapsed_time": "0:48:23", "remaining_time": "3:00:26"}
|
40 |
+
{"current_steps": 390, "total_steps": 1797, "loss": 1.2607, "accuracy": 0.8500000238418579, "learning_rate": 8.909974832155667e-06, "epoch": 0.65, "percentage": 21.7, "elapsed_time": "0:49:33", "remaining_time": "2:58:48"}
|
41 |
+
{"current_steps": 400, "total_steps": 1797, "loss": 1.1821, "accuracy": 0.875, "learning_rate": 8.854894352026746e-06, "epoch": 0.67, "percentage": 22.26, "elapsed_time": "0:50:43", "remaining_time": "2:57:10"}
|
42 |
+
{"current_steps": 400, "total_steps": 1797, "eval_loss": 1.9728976488113403, "epoch": 0.67, "percentage": 22.26, "elapsed_time": "0:55:24", "remaining_time": "3:13:30"}
|
43 |
+
{"current_steps": 410, "total_steps": 1797, "loss": 1.2384, "accuracy": 0.862500011920929, "learning_rate": 8.798635578767584e-06, "epoch": 0.68, "percentage": 22.82, "elapsed_time": "0:56:33", "remaining_time": "3:11:18"}
|
44 |
+
{"current_steps": 420, "total_steps": 1797, "loss": 1.1389, "accuracy": 0.875, "learning_rate": 8.74121570852417e-06, "epoch": 0.7, "percentage": 23.37, "elapsed_time": "0:57:42", "remaining_time": "3:09:11"}
|
45 |
+
{"current_steps": 430, "total_steps": 1797, "loss": 1.0862, "accuracy": 0.887499988079071, "learning_rate": 8.682652292345239e-06, "epoch": 0.72, "percentage": 23.93, "elapsed_time": "0:58:52", "remaining_time": "3:07:09"}
|
46 |
+
{"current_steps": 440, "total_steps": 1797, "loss": 1.0189, "accuracy": 0.925000011920929, "learning_rate": 8.622963230817599e-06, "epoch": 0.73, "percentage": 24.49, "elapsed_time": "1:00:01", "remaining_time": "3:05:06"}
|
47 |
+
{"current_steps": 450, "total_steps": 1797, "loss": 1.0986, "accuracy": 0.887499988079071, "learning_rate": 8.562166768594592e-06, "epoch": 0.75, "percentage": 25.04, "elapsed_time": "1:01:09", "remaining_time": "3:03:02"}
|
48 |
+
{"current_steps": 460, "total_steps": 1797, "loss": 1.25, "accuracy": 0.887499988079071, "learning_rate": 8.500281488819426e-06, "epoch": 0.77, "percentage": 25.6, "elapsed_time": "1:02:19", "remaining_time": "3:01:07"}
|
49 |
+
{"current_steps": 470, "total_steps": 1797, "loss": 1.067, "accuracy": 0.9125000238418579, "learning_rate": 8.43732630744501e-06, "epoch": 0.78, "percentage": 26.15, "elapsed_time": "1:03:27", "remaining_time": "2:59:10"}
|
50 |
+
{"current_steps": 480, "total_steps": 1797, "loss": 1.0214, "accuracy": 0.8999999761581421, "learning_rate": 8.373320467452069e-06, "epoch": 0.8, "percentage": 26.71, "elapsed_time": "1:04:34", "remaining_time": "2:57:10"}
|
51 |
+
{"current_steps": 490, "total_steps": 1797, "loss": 1.0341, "accuracy": 0.925000011920929, "learning_rate": 8.308283532967311e-06, "epoch": 0.82, "percentage": 27.27, "elapsed_time": "1:05:41", "remaining_time": "2:55:12"}
|
52 |
+
{"current_steps": 500, "total_steps": 1797, "loss": 0.9832, "accuracy": 0.9125000238418579, "learning_rate": 8.242235383283433e-06, "epoch": 0.83, "percentage": 27.82, "elapsed_time": "1:06:47", "remaining_time": "2:53:15"}
|
53 |
+
{"current_steps": 510, "total_steps": 1797, "loss": 1.1563, "accuracy": 0.8999999761581421, "learning_rate": 8.175196206782765e-06, "epoch": 0.85, "percentage": 28.38, "elapsed_time": "1:07:56", "remaining_time": "2:51:26"}
|
54 |
+
{"current_steps": 520, "total_steps": 1797, "loss": 1.0753, "accuracy": 0.925000011920929, "learning_rate": 8.107186494766475e-06, "epoch": 0.87, "percentage": 28.94, "elapsed_time": "1:09:05", "remaining_time": "2:49:41"}
|
55 |
+
{"current_steps": 530, "total_steps": 1797, "loss": 0.9557, "accuracy": 0.9375, "learning_rate": 8.038227035191152e-06, "epoch": 0.88, "percentage": 29.49, "elapsed_time": "1:10:13", "remaining_time": "2:47:53"}
|
56 |
+
{"current_steps": 540, "total_steps": 1797, "loss": 0.9715, "accuracy": 0.9375, "learning_rate": 7.968338906314739e-06, "epoch": 0.9, "percentage": 30.05, "elapsed_time": "1:11:21", "remaining_time": "2:46:05"}
|
57 |
+
{"current_steps": 550, "total_steps": 1797, "loss": 0.987, "accuracy": 0.925000011920929, "learning_rate": 7.897543470253708e-06, "epoch": 0.92, "percentage": 30.61, "elapsed_time": "1:12:29", "remaining_time": "2:44:22"}
|
58 |
+
{"current_steps": 560, "total_steps": 1797, "loss": 1.0165, "accuracy": 0.8999999761581421, "learning_rate": 7.825862366453487e-06, "epoch": 0.93, "percentage": 31.16, "elapsed_time": "1:13:39", "remaining_time": "2:42:42"}
|
59 |
+
{"current_steps": 570, "total_steps": 1797, "loss": 1.088, "accuracy": 0.925000011920929, "learning_rate": 7.753317505074114e-06, "epoch": 0.95, "percentage": 31.72, "elapsed_time": "1:14:49", "remaining_time": "2:41:03"}
|
60 |
+
{"current_steps": 580, "total_steps": 1797, "loss": 1.0683, "accuracy": 0.875, "learning_rate": 7.679931060293137e-06, "epoch": 0.97, "percentage": 32.28, "elapsed_time": "1:15:57", "remaining_time": "2:39:23"}
|
61 |
+
{"current_steps": 590, "total_steps": 1797, "loss": 1.0435, "accuracy": 0.887499988079071, "learning_rate": 7.605725463527825e-06, "epoch": 0.98, "percentage": 32.83, "elapsed_time": "1:17:07", "remaining_time": "2:37:47"}
|
62 |
+
{"current_steps": 600, "total_steps": 1797, "loss": 0.9116, "accuracy": 0.925000011920929, "learning_rate": 7.530723396578745e-06, "epoch": 1.0, "percentage": 33.39, "elapsed_time": "1:18:14", "remaining_time": "2:36:06"}
|
63 |
+
{"current_steps": 600, "total_steps": 1797, "eval_loss": 1.9454625844955444, "epoch": 1.0, "percentage": 33.39, "elapsed_time": "1:22:55", "remaining_time": "2:45:26"}
|
64 |
+
{"current_steps": 610, "total_steps": 1797, "loss": 0.8744, "accuracy": 0.949999988079071, "learning_rate": 7.454947784696804e-06, "epoch": 1.02, "percentage": 33.95, "elapsed_time": "1:24:06", "remaining_time": "2:43:39"}
|
65 |
+
{"current_steps": 620, "total_steps": 1797, "loss": 0.8906, "accuracy": 0.987500011920929, "learning_rate": 7.3784217895758804e-06, "epoch": 1.03, "percentage": 34.5, "elapsed_time": "1:25:16", "remaining_time": "2:41:53"}
|
66 |
+
{"current_steps": 630, "total_steps": 1797, "loss": 0.8893, "accuracy": 0.987500011920929, "learning_rate": 7.3011688022731865e-06, "epoch": 1.05, "percentage": 35.06, "elapsed_time": "1:26:26", "remaining_time": "2:40:07"}
|
67 |
+
{"current_steps": 640, "total_steps": 1797, "loss": 0.7873, "accuracy": 1.0, "learning_rate": 7.2232124360595205e-06, "epoch": 1.07, "percentage": 35.61, "elapsed_time": "1:27:34", "remaining_time": "2:38:19"}
|
68 |
+
{"current_steps": 650, "total_steps": 1797, "loss": 0.8148, "accuracy": 0.9750000238418579, "learning_rate": 7.144576519201595e-06, "epoch": 1.08, "percentage": 36.17, "elapsed_time": "1:28:44", "remaining_time": "2:36:35"}
|
69 |
+
{"current_steps": 660, "total_steps": 1797, "loss": 0.7832, "accuracy": 0.9750000238418579, "learning_rate": 7.0652850876786485e-06, "epoch": 1.1, "percentage": 36.73, "elapsed_time": "1:29:51", "remaining_time": "2:34:48"}
|
70 |
+
{"current_steps": 670, "total_steps": 1797, "loss": 0.8512, "accuracy": 0.9750000238418579, "learning_rate": 6.9853623778355805e-06, "epoch": 1.12, "percentage": 37.28, "elapsed_time": "1:31:00", "remaining_time": "2:33:04"}
|
71 |
+
{"current_steps": 680, "total_steps": 1797, "loss": 0.8077, "accuracy": 0.9624999761581421, "learning_rate": 6.904832818974818e-06, "epoch": 1.13, "percentage": 37.84, "elapsed_time": "1:32:08", "remaining_time": "2:31:21"}
|
72 |
+
{"current_steps": 690, "total_steps": 1797, "loss": 0.8814, "accuracy": 0.9624999761581421, "learning_rate": 6.823721025889227e-06, "epoch": 1.15, "percentage": 38.4, "elapsed_time": "1:33:17", "remaining_time": "2:29:41"}
|
73 |
+
{"current_steps": 700, "total_steps": 1797, "loss": 0.8541, "accuracy": 0.925000011920929, "learning_rate": 6.742051791338305e-06, "epoch": 1.17, "percentage": 38.95, "elapsed_time": "1:34:26", "remaining_time": "2:28:00"}
|
74 |
+
{"current_steps": 710, "total_steps": 1797, "loss": 0.8385, "accuracy": 0.987500011920929, "learning_rate": 6.6598500784700016e-06, "epoch": 1.18, "percentage": 39.51, "elapsed_time": "1:35:37", "remaining_time": "2:26:23"}
|
75 |
+
{"current_steps": 720, "total_steps": 1797, "loss": 0.7852, "accuracy": 0.9624999761581421, "learning_rate": 6.577141013190428e-06, "epoch": 1.2, "percentage": 40.07, "elapsed_time": "1:36:46", "remaining_time": "2:24:45"}
|
76 |
+
{"current_steps": 730, "total_steps": 1797, "loss": 0.8683, "accuracy": 0.949999988079071, "learning_rate": 6.493949876483841e-06, "epoch": 1.22, "percentage": 40.62, "elapsed_time": "1:37:56", "remaining_time": "2:23:08"}
|
77 |
+
{"current_steps": 740, "total_steps": 1797, "loss": 0.7898, "accuracy": 0.9624999761581421, "learning_rate": 6.410302096685219e-06, "epoch": 1.23, "percentage": 41.18, "elapsed_time": "1:39:05", "remaining_time": "2:21:31"}
|
78 |
+
{"current_steps": 750, "total_steps": 1797, "loss": 0.7898, "accuracy": 1.0, "learning_rate": 6.326223241707787e-06, "epoch": 1.25, "percentage": 41.74, "elapsed_time": "1:40:13", "remaining_time": "2:19:55"}
|
79 |
+
{"current_steps": 760, "total_steps": 1797, "loss": 0.8029, "accuracy": 0.9750000238418579, "learning_rate": 6.241739011227899e-06, "epoch": 1.27, "percentage": 42.29, "elapsed_time": "1:41:21", "remaining_time": "2:18:17"}
|
80 |
+
{"current_steps": 770, "total_steps": 1797, "loss": 0.9354, "accuracy": 0.949999988079071, "learning_rate": 6.156875228829627e-06, "epoch": 1.28, "percentage": 42.85, "elapsed_time": "1:42:31", "remaining_time": "2:16:44"}
|
81 |
+
{"current_steps": 780, "total_steps": 1797, "loss": 0.8551, "accuracy": 0.9375, "learning_rate": 6.071657834111483e-06, "epoch": 1.3, "percentage": 43.41, "elapsed_time": "1:43:39", "remaining_time": "2:15:09"}
|
82 |
+
{"current_steps": 790, "total_steps": 1797, "loss": 0.8269, "accuracy": 0.9624999761581421, "learning_rate": 5.986112874757688e-06, "epoch": 1.32, "percentage": 43.96, "elapsed_time": "1:44:49", "remaining_time": "2:13:37"}
|
83 |
+
{"current_steps": 800, "total_steps": 1797, "loss": 0.8412, "accuracy": 0.9624999761581421, "learning_rate": 5.900266498576383e-06, "epoch": 1.33, "percentage": 44.52, "elapsed_time": "1:45:58", "remaining_time": "2:12:03"}
|
84 |
+
{"current_steps": 800, "total_steps": 1797, "eval_loss": 2.0040743350982666, "epoch": 1.33, "percentage": 44.52, "elapsed_time": "1:50:38", "remaining_time": "2:17:53"}
|
85 |
+
{"current_steps": 810, "total_steps": 1797, "loss": 0.7899, "accuracy": 0.9624999761581421, "learning_rate": 5.81414494550726e-06, "epoch": 1.35, "percentage": 45.08, "elapsed_time": "1:51:46", "remaining_time": "2:16:12"}
|
86 |
+
{"current_steps": 820, "total_steps": 1797, "loss": 0.7704, "accuracy": 0.949999988079071, "learning_rate": 5.727774539601015e-06, "epoch": 1.37, "percentage": 45.63, "elapsed_time": "1:52:55", "remaining_time": "2:14:33"}
|
87 |
+
{"current_steps": 830, "total_steps": 1797, "loss": 0.7649, "accuracy": 0.987500011920929, "learning_rate": 5.641181680973094e-06, "epoch": 1.38, "percentage": 46.19, "elapsed_time": "1:54:03", "remaining_time": "2:12:53"}
|
88 |
+
{"current_steps": 840, "total_steps": 1797, "loss": 0.9745, "accuracy": 0.9624999761581421, "learning_rate": 5.554392837734201e-06, "epoch": 1.4, "percentage": 46.74, "elapsed_time": "1:55:14", "remaining_time": "2:11:17"}
|
89 |
+
{"current_steps": 850, "total_steps": 1797, "loss": 0.8372, "accuracy": 0.9624999761581421, "learning_rate": 5.467434537900002e-06, "epoch": 1.42, "percentage": 47.3, "elapsed_time": "1:56:22", "remaining_time": "2:09:39"}
|
90 |
+
{"current_steps": 860, "total_steps": 1797, "loss": 0.9258, "accuracy": 0.925000011920929, "learning_rate": 5.380333361282537e-06, "epoch": 1.43, "percentage": 47.86, "elapsed_time": "1:57:34", "remaining_time": "2:08:06"}
|
91 |
+
{"current_steps": 870, "total_steps": 1797, "loss": 0.8764, "accuracy": 0.949999988079071, "learning_rate": 5.293115931365793e-06, "epoch": 1.45, "percentage": 48.41, "elapsed_time": "1:58:42", "remaining_time": "2:06:29"}
|
92 |
+
{"current_steps": 880, "total_steps": 1797, "loss": 0.7908, "accuracy": 0.9624999761581421, "learning_rate": 5.20580890716792e-06, "epoch": 1.47, "percentage": 48.97, "elapsed_time": "1:59:50", "remaining_time": "2:04:53"}
|
93 |
+
{"current_steps": 890, "total_steps": 1797, "loss": 0.8541, "accuracy": 0.949999988079071, "learning_rate": 5.118438975092605e-06, "epoch": 1.48, "percentage": 49.53, "elapsed_time": "2:01:00", "remaining_time": "2:03:18"}
|
94 |
+
{"current_steps": 900, "total_steps": 1797, "loss": 0.8419, "accuracy": 0.9750000238418579, "learning_rate": 5.031032840772048e-06, "epoch": 1.5, "percentage": 50.08, "elapsed_time": "2:02:10", "remaining_time": "2:01:46"}
|
95 |
+
{"current_steps": 910, "total_steps": 1797, "loss": 0.8271, "accuracy": 0.9375, "learning_rate": 4.943617220904091e-06, "epoch": 1.52, "percentage": 50.64, "elapsed_time": "2:03:19", "remaining_time": "2:00:12"}
|
96 |
+
{"current_steps": 920, "total_steps": 1797, "loss": 0.7193, "accuracy": 0.9750000238418579, "learning_rate": 4.856218835085946e-06, "epoch": 1.53, "percentage": 51.2, "elapsed_time": "2:04:27", "remaining_time": "1:58:38"}
|
97 |
+
{"current_steps": 930, "total_steps": 1797, "loss": 0.6819, "accuracy": 0.987500011920929, "learning_rate": 4.768864397647031e-06, "epoch": 1.55, "percentage": 51.75, "elapsed_time": "2:05:35", "remaining_time": "1:57:05"}
|
98 |
+
{"current_steps": 940, "total_steps": 1797, "loss": 0.7475, "accuracy": 0.9624999761581421, "learning_rate": 4.681580609483436e-06, "epoch": 1.57, "percentage": 52.31, "elapsed_time": "2:06:43", "remaining_time": "1:55:32"}
|
99 |
+
{"current_steps": 950, "total_steps": 1797, "loss": 0.7442, "accuracy": 0.9750000238418579, "learning_rate": 4.594394149896481e-06, "epoch": 1.58, "percentage": 52.87, "elapsed_time": "2:07:50", "remaining_time": "1:53:58"}
|
100 |
+
{"current_steps": 960, "total_steps": 1797, "loss": 0.7509, "accuracy": 0.949999988079071, "learning_rate": 4.507331668437878e-06, "epoch": 1.6, "percentage": 53.42, "elapsed_time": "2:08:58", "remaining_time": "1:52:26"}
|
101 |
+
{"current_steps": 970, "total_steps": 1797, "loss": 0.7403, "accuracy": 0.9624999761581421, "learning_rate": 4.42041977676399e-06, "epoch": 1.62, "percentage": 53.98, "elapsed_time": "2:10:06", "remaining_time": "1:50:55"}
|
102 |
+
{"current_steps": 980, "total_steps": 1797, "loss": 0.7967, "accuracy": 0.925000011920929, "learning_rate": 4.333685040501664e-06, "epoch": 1.63, "percentage": 54.54, "elapsed_time": "2:11:14", "remaining_time": "1:49:24"}
|
103 |
+
{"current_steps": 990, "total_steps": 1797, "loss": 0.7513, "accuracy": 0.9750000238418579, "learning_rate": 4.247153971128145e-06, "epoch": 1.65, "percentage": 55.09, "elapsed_time": "2:12:22", "remaining_time": "1:47:54"}
|
104 |
+
{"current_steps": 1000, "total_steps": 1797, "loss": 0.7345, "accuracy": 0.987500011920929, "learning_rate": 4.160853017867531e-06, "epoch": 1.67, "percentage": 55.65, "elapsed_time": "2:13:31", "remaining_time": "1:46:25"}
|
105 |
+
{"current_steps": 1000, "total_steps": 1797, "eval_loss": 2.0659372806549072, "epoch": 1.67, "percentage": 55.65, "elapsed_time": "2:18:12", "remaining_time": "1:50:08"}
|
106 |
+
{"current_steps": 1010, "total_steps": 1797, "loss": 0.6972, "accuracy": 0.987500011920929, "learning_rate": 4.074808559606264e-06, "epoch": 1.68, "percentage": 56.2, "elapsed_time": "2:19:21", "remaining_time": "1:48:35"}
|
107 |
+
{"current_steps": 1020, "total_steps": 1797, "loss": 0.8484, "accuracy": 0.9375, "learning_rate": 3.989046896830119e-06, "epoch": 1.7, "percentage": 56.76, "elapsed_time": "2:20:28", "remaining_time": "1:47:00"}
|
108 |
+
{"current_steps": 1030, "total_steps": 1797, "loss": 0.7447, "accuracy": 0.9624999761581421, "learning_rate": 3.9035942435851504e-06, "epoch": 1.72, "percentage": 57.32, "elapsed_time": "2:21:37", "remaining_time": "1:45:27"}
|
109 |
+
{"current_steps": 1040, "total_steps": 1797, "loss": 0.9205, "accuracy": 0.9375, "learning_rate": 3.818476719465073e-06, "epoch": 1.73, "percentage": 57.87, "elapsed_time": "2:22:44", "remaining_time": "1:43:54"}
|
110 |
+
{"current_steps": 1050, "total_steps": 1797, "loss": 0.7114, "accuracy": 0.9624999761581421, "learning_rate": 3.7337203416274993e-06, "epoch": 1.75, "percentage": 58.43, "elapsed_time": "2:23:52", "remaining_time": "1:42:21"}
|
111 |
+
{"current_steps": 1060, "total_steps": 1797, "loss": 0.8006, "accuracy": 0.9375, "learning_rate": 3.6493510168414924e-06, "epoch": 1.77, "percentage": 58.99, "elapsed_time": "2:25:00", "remaining_time": "1:40:49"}
|
112 |
+
{"current_steps": 1070, "total_steps": 1797, "loss": 0.7484, "accuracy": 0.9750000238418579, "learning_rate": 3.5653945335688688e-06, "epoch": 1.78, "percentage": 59.54, "elapsed_time": "2:26:10", "remaining_time": "1:39:18"}
|
113 |
+
{"current_steps": 1080, "total_steps": 1797, "loss": 0.8644, "accuracy": 0.9750000238418579, "learning_rate": 3.4818765540816505e-06, "epoch": 1.8, "percentage": 60.1, "elapsed_time": "2:27:21", "remaining_time": "1:37:50"}
|
114 |
+
{"current_steps": 1090, "total_steps": 1797, "loss": 0.6905, "accuracy": 0.9624999761581421, "learning_rate": 3.398822606618095e-06, "epoch": 1.82, "percentage": 60.66, "elapsed_time": "2:28:30", "remaining_time": "1:36:19"}
|
115 |
+
{"current_steps": 1100, "total_steps": 1797, "loss": 0.8403, "accuracy": 0.9375, "learning_rate": 3.3162580775796994e-06, "epoch": 1.83, "percentage": 61.21, "elapsed_time": "2:29:39", "remaining_time": "1:34:49"}
|
116 |
+
{"current_steps": 1110, "total_steps": 1797, "loss": 0.7783, "accuracy": 0.9624999761581421, "learning_rate": 3.2342082037715404e-06, "epoch": 1.85, "percentage": 61.77, "elapsed_time": "2:30:51", "remaining_time": "1:33:21"}
|
117 |
+
{"current_steps": 1120, "total_steps": 1797, "loss": 0.8398, "accuracy": 0.9624999761581421, "learning_rate": 3.1526980646883664e-06, "epoch": 1.87, "percentage": 62.33, "elapsed_time": "2:32:00", "remaining_time": "1:31:53"}
|
118 |
+
{"current_steps": 1130, "total_steps": 1797, "loss": 0.7723, "accuracy": 0.9750000238418579, "learning_rate": 3.071752574848747e-06, "epoch": 1.88, "percentage": 62.88, "elapsed_time": "2:33:10", "remaining_time": "1:30:24"}
|
119 |
+
{"current_steps": 1140, "total_steps": 1797, "loss": 0.7185, "accuracy": 0.9750000238418579, "learning_rate": 2.991396476179671e-06, "epoch": 1.9, "percentage": 63.44, "elapsed_time": "2:34:18", "remaining_time": "1:28:55"}
|
120 |
+
{"current_steps": 1150, "total_steps": 1797, "loss": 0.8524, "accuracy": 0.9750000238418579, "learning_rate": 2.911654330453882e-06, "epoch": 1.92, "percentage": 64.0, "elapsed_time": "2:35:25", "remaining_time": "1:27:26"}
|
121 |
+
{"current_steps": 1160, "total_steps": 1797, "loss": 0.6951, "accuracy": 0.987500011920929, "learning_rate": 2.8325505117822984e-06, "epoch": 1.93, "percentage": 64.55, "elapsed_time": "2:36:33", "remaining_time": "1:25:58"}
|
122 |
+
{"current_steps": 1170, "total_steps": 1797, "loss": 0.7587, "accuracy": 0.9624999761581421, "learning_rate": 2.754109199163771e-06, "epoch": 1.95, "percentage": 65.11, "elapsed_time": "2:37:44", "remaining_time": "1:24:31"}
|
123 |
+
{"current_steps": 1180, "total_steps": 1797, "loss": 0.913, "accuracy": 0.9375, "learning_rate": 2.6763543690945004e-06, "epoch": 1.97, "percentage": 65.66, "elapsed_time": "2:38:53", "remaining_time": "1:23:04"}
|
124 |
+
{"current_steps": 1190, "total_steps": 1797, "loss": 0.7224, "accuracy": 1.0, "learning_rate": 2.599309788239339e-06, "epoch": 1.98, "percentage": 66.22, "elapsed_time": "2:40:01", "remaining_time": "1:21:37"}
|
125 |
+
{"current_steps": 1200, "total_steps": 1797, "loss": 0.6609, "accuracy": 1.0, "learning_rate": 2.5229990061672414e-06, "epoch": 2.0, "percentage": 66.78, "elapsed_time": "2:41:10", "remaining_time": "1:20:10"}
|
126 |
+
{"current_steps": 1200, "total_steps": 1797, "eval_loss": 2.032116174697876, "epoch": 2.0, "percentage": 66.78, "elapsed_time": "2:45:50", "remaining_time": "1:22:30"}
|
127 |
+
{"current_steps": 1210, "total_steps": 1797, "loss": 0.6373, "accuracy": 1.0, "learning_rate": 2.4474453481530587e-06, "epoch": 2.02, "percentage": 67.33, "elapsed_time": "2:46:59", "remaining_time": "1:21:00"}
|
128 |
+
{"current_steps": 1220, "total_steps": 1797, "loss": 0.7128, "accuracy": 0.9750000238418579, "learning_rate": 2.3726719080478962e-06, "epoch": 2.03, "percentage": 67.89, "elapsed_time": "2:48:08", "remaining_time": "1:19:31"}
|
129 |
+
{"current_steps": 1230, "total_steps": 1797, "loss": 0.6432, "accuracy": 1.0, "learning_rate": 2.298701541220218e-06, "epoch": 2.05, "percentage": 68.45, "elapsed_time": "2:49:17", "remaining_time": "1:18:02"}
|
130 |
+
{"current_steps": 1240, "total_steps": 1797, "loss": 0.6538, "accuracy": 1.0, "learning_rate": 2.22555685756983e-06, "epoch": 2.07, "percentage": 69.0, "elapsed_time": "2:50:26", "remaining_time": "1:16:33"}
|
131 |
+
{"current_steps": 1250, "total_steps": 1797, "loss": 0.5986, "accuracy": 1.0, "learning_rate": 2.153260214616915e-06, "epoch": 2.08, "percentage": 69.56, "elapsed_time": "2:51:33", "remaining_time": "1:15:04"}
|
132 |
+
{"current_steps": 1260, "total_steps": 1797, "loss": 0.6944, "accuracy": 0.9750000238418579, "learning_rate": 2.081833710668181e-06, "epoch": 2.1, "percentage": 70.12, "elapsed_time": "2:52:44", "remaining_time": "1:13:37"}
|
133 |
+
{"current_steps": 1270, "total_steps": 1797, "loss": 0.6708, "accuracy": 1.0, "learning_rate": 2.0112991780622725e-06, "epoch": 2.12, "percentage": 70.67, "elapsed_time": "2:53:55", "remaining_time": "1:12:10"}
|
134 |
+
{"current_steps": 1280, "total_steps": 1797, "loss": 0.654, "accuracy": 0.987500011920929, "learning_rate": 1.9416781764964486e-06, "epoch": 2.13, "percentage": 71.23, "elapsed_time": "2:55:05", "remaining_time": "1:10:43"}
|
135 |
+
{"current_steps": 1290, "total_steps": 1797, "loss": 0.6446, "accuracy": 0.9750000238418579, "learning_rate": 1.8729919864366292e-06, "epoch": 2.15, "percentage": 71.79, "elapsed_time": "2:56:13", "remaining_time": "1:09:15"}
|
136 |
+
{"current_steps": 1300, "total_steps": 1797, "loss": 0.6627, "accuracy": 0.9750000238418579, "learning_rate": 1.8052616026127563e-06, "epoch": 2.17, "percentage": 72.34, "elapsed_time": "2:57:21", "remaining_time": "1:07:48"}
|
137 |
+
{"current_steps": 1310, "total_steps": 1797, "loss": 0.6345, "accuracy": 0.9750000238418579, "learning_rate": 1.7385077276015267e-06, "epoch": 2.18, "percentage": 72.9, "elapsed_time": "2:58:32", "remaining_time": "1:06:22"}
|
138 |
+
{"current_steps": 1320, "total_steps": 1797, "loss": 0.7373, "accuracy": 0.987500011920929, "learning_rate": 1.6727507654983977e-06, "epoch": 2.2, "percentage": 73.46, "elapsed_time": "2:59:41", "remaining_time": "1:04:55"}
|
139 |
+
{"current_steps": 1330, "total_steps": 1797, "loss": 0.6678, "accuracy": 1.0, "learning_rate": 1.6080108156808439e-06, "epoch": 2.22, "percentage": 74.01, "elapsed_time": "3:00:48", "remaining_time": "1:03:29"}
|
140 |
+
{"current_steps": 1340, "total_steps": 1797, "loss": 0.5832, "accuracy": 0.987500011920929, "learning_rate": 1.5443076666647545e-06, "epoch": 2.23, "percentage": 74.57, "elapsed_time": "3:01:55", "remaining_time": "1:02:02"}
|
141 |
+
{"current_steps": 1350, "total_steps": 1797, "loss": 0.6009, "accuracy": 0.987500011920929, "learning_rate": 1.4816607900558311e-06, "epoch": 2.25, "percentage": 75.13, "elapsed_time": "3:03:02", "remaining_time": "1:00:36"}
|
142 |
+
{"current_steps": 1360, "total_steps": 1797, "loss": 0.6347, "accuracy": 1.0, "learning_rate": 1.4200893345978816e-06, "epoch": 2.27, "percentage": 75.68, "elapsed_time": "3:04:12", "remaining_time": "0:59:11"}
|
143 |
+
{"current_steps": 1370, "total_steps": 1797, "loss": 0.7345, "accuracy": 0.987500011920929, "learning_rate": 1.3596121203197715e-06, "epoch": 2.28, "percentage": 76.24, "elapsed_time": "3:05:22", "remaining_time": "0:57:46"}
|
144 |
+
{"current_steps": 1380, "total_steps": 1797, "loss": 0.6705, "accuracy": 0.987500011920929, "learning_rate": 1.3002476327828717e-06, "epoch": 2.3, "percentage": 76.79, "elapsed_time": "3:06:29", "remaining_time": "0:56:21"}
|
145 |
+
{"current_steps": 1390, "total_steps": 1797, "loss": 0.6701, "accuracy": 0.987500011920929, "learning_rate": 1.2420140174307267e-06, "epoch": 2.32, "percentage": 77.35, "elapsed_time": "3:07:38", "remaining_time": "0:54:56"}
|
146 |
+
{"current_steps": 1400, "total_steps": 1797, "loss": 0.6768, "accuracy": 1.0, "learning_rate": 1.1849290740426994e-06, "epoch": 2.33, "percentage": 77.91, "elapsed_time": "3:08:47", "remaining_time": "0:53:32"}
|
147 |
+
{"current_steps": 1400, "total_steps": 1797, "eval_loss": 2.0312814712524414, "epoch": 2.33, "percentage": 77.91, "elapsed_time": "3:13:27", "remaining_time": "0:54:51"}
|
148 |
+
{"current_steps": 1410, "total_steps": 1797, "loss": 0.6084, "accuracy": 0.987500011920929, "learning_rate": 1.1290102512932482e-06, "epoch": 2.35, "percentage": 78.46, "elapsed_time": "3:14:34", "remaining_time": "0:53:24"}
|
149 |
+
{"current_steps": 1420, "total_steps": 1797, "loss": 0.6596, "accuracy": 0.9750000238418579, "learning_rate": 1.074274641418554e-06, "epoch": 2.37, "percentage": 79.02, "elapsed_time": "3:15:44", "remaining_time": "0:51:58"}
|
150 |
+
{"current_steps": 1430, "total_steps": 1797, "loss": 0.6782, "accuracy": 1.0, "learning_rate": 1.0207389749920593e-06, "epoch": 2.38, "percentage": 79.58, "elapsed_time": "3:16:52", "remaining_time": "0:50:31"}
|
151 |
+
{"current_steps": 1440, "total_steps": 1797, "loss": 0.6454, "accuracy": 1.0, "learning_rate": 9.68419615810598e-07, "epoch": 2.4, "percentage": 80.13, "elapsed_time": "3:18:02", "remaining_time": "0:49:05"}
|
152 |
+
{"current_steps": 1450, "total_steps": 1797, "loss": 0.6051, "accuracy": 1.0, "learning_rate": 9.173325558925905e-07, "epoch": 2.42, "percentage": 80.69, "elapsed_time": "3:19:11", "remaining_time": "0:47:40"}
|
153 |
+
{"current_steps": 1460, "total_steps": 1797, "loss": 0.6823, "accuracy": 1.0, "learning_rate": 8.674934105899152e-07, "epoch": 2.43, "percentage": 81.25, "elapsed_time": "3:20:21", "remaining_time": "0:46:14"}
|
154 |
+
{"current_steps": 1470, "total_steps": 1797, "loss": 0.5823, "accuracy": 0.987500011920929, "learning_rate": 8.189174138148814e-07, "epoch": 2.45, "percentage": 81.8, "elapsed_time": "3:21:29", "remaining_time": "0:44:49"}
|
155 |
+
{"current_steps": 1480, "total_steps": 1797, "loss": 0.654, "accuracy": 1.0, "learning_rate": 7.716194133838135e-07, "epoch": 2.47, "percentage": 82.36, "elapsed_time": "3:22:38", "remaining_time": "0:43:24"}
|
156 |
+
{"current_steps": 1490, "total_steps": 1797, "loss": 0.5732, "accuracy": 1.0, "learning_rate": 7.256138664786477e-07, "epoch": 2.48, "percentage": 82.92, "elapsed_time": "3:23:45", "remaining_time": "0:41:59"}
|
157 |
+
{"current_steps": 1500, "total_steps": 1797, "loss": 0.6148, "accuracy": 0.987500011920929, "learning_rate": 6.809148352279182e-07, "epoch": 2.5, "percentage": 83.47, "elapsed_time": "3:24:52", "remaining_time": "0:40:33"}
|
158 |
+
{"current_steps": 1510, "total_steps": 1797, "loss": 0.7931, "accuracy": 0.9750000238418579, "learning_rate": 6.375359824085126e-07, "epoch": 2.52, "percentage": 84.03, "elapsed_time": "3:26:02", "remaining_time": "0:39:09"}
|
159 |
+
{"current_steps": 1520, "total_steps": 1797, "loss": 0.5817, "accuracy": 1.0, "learning_rate": 5.954905672694805e-07, "epoch": 2.53, "percentage": 84.59, "elapsed_time": "3:27:10", "remaining_time": "0:37:45"}
|
160 |
+
{"current_steps": 1530, "total_steps": 1797, "loss": 0.6644, "accuracy": 0.9750000238418579, "learning_rate": 5.547914414791922e-07, "epoch": 2.55, "percentage": 85.14, "elapsed_time": "3:28:17", "remaining_time": "0:36:20"}
|
161 |
+
{"current_steps": 1540, "total_steps": 1797, "loss": 0.698, "accuracy": 0.9750000238418579, "learning_rate": 5.154510451970762e-07, "epoch": 2.57, "percentage": 85.7, "elapsed_time": "3:29:27", "remaining_time": "0:34:57"}
|
162 |
+
{"current_steps": 1550, "total_steps": 1797, "loss": 0.6773, "accuracy": 1.0, "learning_rate": 4.774814032711461e-07, "epoch": 2.58, "percentage": 86.25, "elapsed_time": "3:30:35", "remaining_time": "0:33:33"}
|
163 |
+
{"current_steps": 1560, "total_steps": 1797, "loss": 0.5745, "accuracy": 1.0, "learning_rate": 4.4089412156245793e-07, "epoch": 2.6, "percentage": 86.81, "elapsed_time": "3:31:42", "remaining_time": "0:32:09"}
|
164 |
+
{"current_steps": 1570, "total_steps": 1797, "loss": 0.6679, "accuracy": 1.0, "learning_rate": 4.0570038339764803e-07, "epoch": 2.62, "percentage": 87.37, "elapsed_time": "3:32:51", "remaining_time": "0:30:46"}
|
165 |
+
{"current_steps": 1580, "total_steps": 1797, "loss": 0.6389, "accuracy": 0.987500011920929, "learning_rate": 3.719109461506215e-07, "epoch": 2.63, "percentage": 87.92, "elapsed_time": "3:34:01", "remaining_time": "0:29:23"}
|
166 |
+
{"current_steps": 1590, "total_steps": 1797, "loss": 0.7039, "accuracy": 0.9125000238418579, "learning_rate": 3.3953613795443376e-07, "epoch": 2.65, "percentage": 88.48, "elapsed_time": "3:35:09", "remaining_time": "0:28:00"}
|
167 |
+
{"current_steps": 1600, "total_steps": 1797, "loss": 0.615, "accuracy": 1.0, "learning_rate": 3.0858585454437927e-07, "epoch": 2.67, "percentage": 89.04, "elapsed_time": "3:36:20", "remaining_time": "0:26:38"}
|
168 |
+
{"current_steps": 1600, "total_steps": 1797, "eval_loss": 2.051481008529663, "epoch": 2.67, "percentage": 89.04, "elapsed_time": "3:41:00", "remaining_time": "0:27:12"}
|
169 |
+
{"current_steps": 1610, "total_steps": 1797, "loss": 0.6712, "accuracy": 0.9750000238418579, "learning_rate": 2.7906955623324074e-07, "epoch": 2.68, "percentage": 89.59, "elapsed_time": "3:42:10", "remaining_time": "0:25:48"}
|
170 |
+
{"current_steps": 1620, "total_steps": 1797, "loss": 0.6203, "accuracy": 1.0, "learning_rate": 2.509962650196407e-07, "epoch": 2.7, "percentage": 90.15, "elapsed_time": "3:43:19", "remaining_time": "0:24:23"}
|
171 |
+
{"current_steps": 1630, "total_steps": 1797, "loss": 0.6213, "accuracy": 0.987500011920929, "learning_rate": 2.2437456183035833e-07, "epoch": 2.72, "percentage": 90.71, "elapsed_time": "3:44:27", "remaining_time": "0:22:59"}
|
172 |
+
{"current_steps": 1640, "total_steps": 1797, "loss": 0.6311, "accuracy": 1.0, "learning_rate": 1.99212583897474e-07, "epoch": 2.73, "percentage": 91.26, "elapsed_time": "3:45:37", "remaining_time": "0:21:35"}
|
173 |
+
{"current_steps": 1650, "total_steps": 1797, "loss": 0.622, "accuracy": 1.0, "learning_rate": 1.7551802227112558e-07, "epoch": 2.75, "percentage": 91.82, "elapsed_time": "3:46:47", "remaining_time": "0:20:12"}
|
174 |
+
{"current_steps": 1660, "total_steps": 1797, "loss": 0.6516, "accuracy": 0.987500011920929, "learning_rate": 1.5329811946865392e-07, "epoch": 2.77, "percentage": 92.38, "elapsed_time": "3:47:56", "remaining_time": "0:18:48"}
|
175 |
+
{"current_steps": 1670, "total_steps": 1797, "loss": 0.6145, "accuracy": 1.0, "learning_rate": 1.3255966726084036e-07, "epoch": 2.78, "percentage": 92.93, "elapsed_time": "3:49:04", "remaining_time": "0:17:25"}
|
176 |
+
{"current_steps": 1680, "total_steps": 1797, "loss": 0.6203, "accuracy": 1.0, "learning_rate": 1.1330900459592564e-07, "epoch": 2.8, "percentage": 93.49, "elapsed_time": "3:50:12", "remaining_time": "0:16:01"}
|
177 |
+
{"current_steps": 1690, "total_steps": 1797, "loss": 0.6481, "accuracy": 0.987500011920929, "learning_rate": 9.55520156620332e-08, "epoch": 2.82, "percentage": 94.05, "elapsed_time": "3:51:22", "remaining_time": "0:14:38"}
|
178 |
+
{"current_steps": 1700, "total_steps": 1797, "loss": 0.619, "accuracy": 0.987500011920929, "learning_rate": 7.92941280886056e-08, "epoch": 2.83, "percentage": 94.6, "elapsed_time": "3:52:29", "remaining_time": "0:13:15"}
|
179 |
+
{"current_steps": 1710, "total_steps": 1797, "loss": 0.6241, "accuracy": 1.0, "learning_rate": 6.454031128737881e-08, "epoch": 2.85, "percentage": 95.16, "elapsed_time": "3:53:39", "remaining_time": "0:11:53"}
|
180 |
+
{"current_steps": 1720, "total_steps": 1797, "loss": 0.6836, "accuracy": 0.949999988079071, "learning_rate": 5.129507493343011e-08, "epoch": 2.87, "percentage": 95.72, "elapsed_time": "3:54:48", "remaining_time": "0:10:30"}
|
181 |
+
{"current_steps": 1730, "total_steps": 1797, "loss": 0.6813, "accuracy": 0.987500011920929, "learning_rate": 3.956246758674065e-08, "epoch": 2.88, "percentage": 96.27, "elapsed_time": "3:55:56", "remaining_time": "0:09:08"}
|
182 |
+
{"current_steps": 1740, "total_steps": 1797, "loss": 0.6653, "accuracy": 0.987500011920929, "learning_rate": 2.934607545470536e-08, "epoch": 2.9, "percentage": 96.83, "elapsed_time": "3:57:04", "remaining_time": "0:07:45"}
|
183 |
+
{"current_steps": 1750, "total_steps": 1797, "loss": 0.6212, "accuracy": 0.9624999761581421, "learning_rate": 2.0649021295970906e-08, "epoch": 2.92, "percentage": 97.38, "elapsed_time": "3:58:12", "remaining_time": "0:06:23"}
|
184 |
+
{"current_steps": 1760, "total_steps": 1797, "loss": 0.6385, "accuracy": 0.987500011920929, "learning_rate": 1.3473963465924222e-08, "epoch": 2.93, "percentage": 97.94, "elapsed_time": "3:59:23", "remaining_time": "0:05:01"}
|
185 |
+
{"current_steps": 1770, "total_steps": 1797, "loss": 0.7437, "accuracy": 0.987500011920929, "learning_rate": 7.823095104137479e-09, "epoch": 2.95, "percentage": 98.5, "elapsed_time": "4:00:31", "remaining_time": "0:03:40"}
|
186 |
+
{"current_steps": 1780, "total_steps": 1797, "loss": 0.6192, "accuracy": 1.0, "learning_rate": 3.6981434640093183e-09, "epoch": 2.97, "percentage": 99.05, "elapsed_time": "4:01:39", "remaining_time": "0:02:18"}
|
187 |
+
{"current_steps": 1790, "total_steps": 1797, "loss": 0.7154, "accuracy": 0.9750000238418579, "learning_rate": 1.1003693848093965e-09, "epoch": 2.98, "percentage": 99.61, "elapsed_time": "4:02:47", "remaining_time": "0:00:56"}
|
188 |
+
{"current_steps": 1797, "total_steps": 1797, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:03:35", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be323aa16eccebb5e233b6772089b4ac49c7e88818bc239d03249f1dac337d4e
|
3 |
+
size 5112
|
training_eval_loss.png
ADDED
training_loss.png
ADDED
training_rewards_accuracies.png
ADDED