Upload folder using huggingface_hub
Browse files- README.md +74 -0
- all_results.json +22 -0
- config.json +29 -0
- eval_results.json +16 -0
- generation_config.json +12 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +298 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2063 -0
- train_results.json +9 -0
- trainer_state.json +1468 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
4 |
+
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- princeton-nlp/llama3-ultrafeedback
|
9 |
+
model-index:
|
10 |
+
- name: llama-3-8b-instruct-simpo
|
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 |
+
# llama-3-8b-instruct-simpo
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the princeton-nlp/llama3-ultrafeedback dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.3755
|
22 |
+
- Rewards/chosen: -2.9448
|
23 |
+
- Rewards/rejected: -3.6038
|
24 |
+
- Rewards/accuracies: 0.6613
|
25 |
+
- Rewards/margins: 0.6589
|
26 |
+
- Logps/rejected: -1.4415
|
27 |
+
- Logps/chosen: -1.1779
|
28 |
+
- Logits/rejected: -1.1545
|
29 |
+
- Logits/chosen: -1.1873
|
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-06
|
49 |
+
- train_batch_size: 2
|
50 |
+
- eval_batch_size: 4
|
51 |
+
- seed: 42
|
52 |
+
- distributed_type: multi-GPU
|
53 |
+
- num_devices: 8
|
54 |
+
- gradient_accumulation_steps: 8
|
55 |
+
- total_train_batch_size: 128
|
56 |
+
- total_eval_batch_size: 32
|
57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
+
- lr_scheduler_type: cosine
|
59 |
+
- lr_scheduler_warmup_ratio: 0.1
|
60 |
+
- num_epochs: 1
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
65 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
66 |
+
| 1.3975 | 0.8549 | 400 | 1.3755 | -2.9448 | -3.6038 | 0.6613 | 0.6589 | -1.4415 | -1.1779 | -1.1545 | -1.1873 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.41.2
|
72 |
+
- Pytorch 2.2.2+cu121
|
73 |
+
- Datasets 2.20.0
|
74 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9981298423724285,
|
3 |
+
"eval_logits/chosen": -1.1943395137786865,
|
4 |
+
"eval_logits/rejected": -1.1611931324005127,
|
5 |
+
"eval_logps/chosen": -1.2059502601623535,
|
6 |
+
"eval_logps/rejected": -1.4740996360778809,
|
7 |
+
"eval_loss": 1.373450517654419,
|
8 |
+
"eval_rewards/accuracies": 0.6653226017951965,
|
9 |
+
"eval_rewards/chosen": -3.0148754119873047,
|
10 |
+
"eval_rewards/margins": 0.6703741550445557,
|
11 |
+
"eval_rewards/rejected": -3.6852493286132812,
|
12 |
+
"eval_runtime": 71.4975,
|
13 |
+
"eval_samples": 1961,
|
14 |
+
"eval_samples_per_second": 27.428,
|
15 |
+
"eval_steps_per_second": 0.867,
|
16 |
+
"total_flos": 0.0,
|
17 |
+
"train_loss": 1.4758259897824273,
|
18 |
+
"train_runtime": 7808.6202,
|
19 |
+
"train_samples": 59876,
|
20 |
+
"train_samples_per_second": 7.668,
|
21 |
+
"train_steps_per_second": 0.06
|
22 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128009,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 500000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.41.2",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 128256
|
29 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9981298423724285,
|
3 |
+
"eval_logits/chosen": -1.1943395137786865,
|
4 |
+
"eval_logits/rejected": -1.1611931324005127,
|
5 |
+
"eval_logps/chosen": -1.2059502601623535,
|
6 |
+
"eval_logps/rejected": -1.4740996360778809,
|
7 |
+
"eval_loss": 1.373450517654419,
|
8 |
+
"eval_rewards/accuracies": 0.6653226017951965,
|
9 |
+
"eval_rewards/chosen": -3.0148754119873047,
|
10 |
+
"eval_rewards/margins": 0.6703741550445557,
|
11 |
+
"eval_rewards/rejected": -3.6852493286132812,
|
12 |
+
"eval_runtime": 71.4975,
|
13 |
+
"eval_samples": 1961,
|
14 |
+
"eval_samples_per_second": 27.428,
|
15 |
+
"eval_steps_per_second": 0.867
|
16 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128009
|
7 |
+
],
|
8 |
+
"max_length": 4096,
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.41.2"
|
12 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a02c3accc71278579cd8d92e4780abc5cfc63c8ce66d9623cd492f1dfb82c405
|
3 |
+
size 4976698672
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48e8dbee3c06d49ce1a25eea3c07ca0bdb29230374f687f015d25f6df6341a33
|
3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e17a372180113bed27179f8ce90f0ca93de7a716413d932519cde8ba337d76c
|
3 |
+
size 4915916176
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:beb4f368a8e77202a5dab3a283514e272541a27971553718168f4a85748c67ba
|
3 |
+
size 1168138808
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 16060522496
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
296 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
297 |
+
}
|
298 |
+
}
|
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 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|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 loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
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": 2048,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9981298423724285,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 1.4758259897824273,
|
5 |
+
"train_runtime": 7808.6202,
|
6 |
+
"train_samples": 59876,
|
7 |
+
"train_samples_per_second": 7.668,
|
8 |
+
"train_steps_per_second": 0.06
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1468 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9981298423724285,
|
5 |
+
"eval_steps": 400,
|
6 |
+
"global_step": 467,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0021373230029388193,
|
13 |
+
"grad_norm": 14.616270006854805,
|
14 |
+
"learning_rate": 2.127659574468085e-08,
|
15 |
+
"logits/chosen": -1.1381689310073853,
|
16 |
+
"logits/rejected": -0.9913416504859924,
|
17 |
+
"logps/chosen": -0.2839311361312866,
|
18 |
+
"logps/rejected": -0.29555341601371765,
|
19 |
+
"loss": 1.608,
|
20 |
+
"rewards/accuracies": 0.625,
|
21 |
+
"rewards/chosen": -0.7098277807235718,
|
22 |
+
"rewards/margins": 0.029055725783109665,
|
23 |
+
"rewards/rejected": -0.7388835549354553,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.010686615014694095,
|
28 |
+
"grad_norm": 15.798664787929345,
|
29 |
+
"learning_rate": 1.0638297872340425e-07,
|
30 |
+
"logits/chosen": -0.989432692527771,
|
31 |
+
"logits/rejected": -0.9188639521598816,
|
32 |
+
"logps/chosen": -0.26978519558906555,
|
33 |
+
"logps/rejected": -0.26858454942703247,
|
34 |
+
"loss": 1.6205,
|
35 |
+
"rewards/accuracies": 0.546875,
|
36 |
+
"rewards/chosen": -0.6744629740715027,
|
37 |
+
"rewards/margins": -0.0030015837401151657,
|
38 |
+
"rewards/rejected": -0.6714614033699036,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02137323002938819,
|
43 |
+
"grad_norm": 12.624563810334125,
|
44 |
+
"learning_rate": 2.127659574468085e-07,
|
45 |
+
"logits/chosen": -0.9885454177856445,
|
46 |
+
"logits/rejected": -0.9444629549980164,
|
47 |
+
"logps/chosen": -0.27237212657928467,
|
48 |
+
"logps/rejected": -0.2738865911960602,
|
49 |
+
"loss": 1.6069,
|
50 |
+
"rewards/accuracies": 0.48750001192092896,
|
51 |
+
"rewards/chosen": -0.6809303164482117,
|
52 |
+
"rewards/margins": 0.0037860602606087923,
|
53 |
+
"rewards/rejected": -0.6847164630889893,
|
54 |
+
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.03205984504408229,
|
58 |
+
"grad_norm": 8.372527145409705,
|
59 |
+
"learning_rate": 3.1914893617021275e-07,
|
60 |
+
"logits/chosen": -0.9621208906173706,
|
61 |
+
"logits/rejected": -0.9169891476631165,
|
62 |
+
"logps/chosen": -0.2949882745742798,
|
63 |
+
"logps/rejected": -0.2834514081478119,
|
64 |
+
"loss": 1.6049,
|
65 |
+
"rewards/accuracies": 0.48750001192092896,
|
66 |
+
"rewards/chosen": -0.7374706864356995,
|
67 |
+
"rewards/margins": -0.028842147439718246,
|
68 |
+
"rewards/rejected": -0.7086285352706909,
|
69 |
+
"step": 15
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.04274646005877638,
|
73 |
+
"grad_norm": 11.776984926293357,
|
74 |
+
"learning_rate": 4.25531914893617e-07,
|
75 |
+
"logits/chosen": -0.9825040102005005,
|
76 |
+
"logits/rejected": -0.983070969581604,
|
77 |
+
"logps/chosen": -0.26186102628707886,
|
78 |
+
"logps/rejected": -0.26891934871673584,
|
79 |
+
"loss": 1.6132,
|
80 |
+
"rewards/accuracies": 0.5375000238418579,
|
81 |
+
"rewards/chosen": -0.65465247631073,
|
82 |
+
"rewards/margins": 0.01764589548110962,
|
83 |
+
"rewards/rejected": -0.6722984313964844,
|
84 |
+
"step": 20
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.053433075073470476,
|
88 |
+
"grad_norm": 11.594406861763694,
|
89 |
+
"learning_rate": 5.319148936170212e-07,
|
90 |
+
"logits/chosen": -1.0304547548294067,
|
91 |
+
"logits/rejected": -1.0080630779266357,
|
92 |
+
"logps/chosen": -0.28237098455429077,
|
93 |
+
"logps/rejected": -0.28737810254096985,
|
94 |
+
"loss": 1.6046,
|
95 |
+
"rewards/accuracies": 0.4749999940395355,
|
96 |
+
"rewards/chosen": -0.7059274911880493,
|
97 |
+
"rewards/margins": 0.012517772614955902,
|
98 |
+
"rewards/rejected": -0.7184451818466187,
|
99 |
+
"step": 25
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.06411969008816458,
|
103 |
+
"grad_norm": 13.181478771123727,
|
104 |
+
"learning_rate": 6.382978723404255e-07,
|
105 |
+
"logits/chosen": -1.0607410669326782,
|
106 |
+
"logits/rejected": -0.9752001762390137,
|
107 |
+
"logps/chosen": -0.2747865319252014,
|
108 |
+
"logps/rejected": -0.27676859498023987,
|
109 |
+
"loss": 1.6169,
|
110 |
+
"rewards/accuracies": 0.4625000059604645,
|
111 |
+
"rewards/chosen": -0.6869663596153259,
|
112 |
+
"rewards/margins": 0.004955160431563854,
|
113 |
+
"rewards/rejected": -0.6919214725494385,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.07480630510285867,
|
118 |
+
"grad_norm": 20.535555442364025,
|
119 |
+
"learning_rate": 7.446808510638297e-07,
|
120 |
+
"logits/chosen": -0.9909561276435852,
|
121 |
+
"logits/rejected": -0.9133442044258118,
|
122 |
+
"logps/chosen": -0.2775736451148987,
|
123 |
+
"logps/rejected": -0.3019401431083679,
|
124 |
+
"loss": 1.6019,
|
125 |
+
"rewards/accuracies": 0.574999988079071,
|
126 |
+
"rewards/chosen": -0.6939341425895691,
|
127 |
+
"rewards/margins": 0.06091625243425369,
|
128 |
+
"rewards/rejected": -0.754850447177887,
|
129 |
+
"step": 35
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.08549292011755276,
|
133 |
+
"grad_norm": 24.246139127435896,
|
134 |
+
"learning_rate": 8.51063829787234e-07,
|
135 |
+
"logits/chosen": -0.9217761158943176,
|
136 |
+
"logits/rejected": -0.9104591608047485,
|
137 |
+
"logps/chosen": -0.2786272466182709,
|
138 |
+
"logps/rejected": -0.29105645418167114,
|
139 |
+
"loss": 1.617,
|
140 |
+
"rewards/accuracies": 0.5249999761581421,
|
141 |
+
"rewards/chosen": -0.6965680718421936,
|
142 |
+
"rewards/margins": 0.031073052436113358,
|
143 |
+
"rewards/rejected": -0.7276411056518555,
|
144 |
+
"step": 40
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.09617953513224686,
|
148 |
+
"grad_norm": 10.340400390143392,
|
149 |
+
"learning_rate": 9.574468085106384e-07,
|
150 |
+
"logits/chosen": -0.918626606464386,
|
151 |
+
"logits/rejected": -0.837913990020752,
|
152 |
+
"logps/chosen": -0.33493560552597046,
|
153 |
+
"logps/rejected": -0.33847588300704956,
|
154 |
+
"loss": 1.6012,
|
155 |
+
"rewards/accuracies": 0.5,
|
156 |
+
"rewards/chosen": -0.8373388051986694,
|
157 |
+
"rewards/margins": 0.00885077752172947,
|
158 |
+
"rewards/rejected": -0.8461896777153015,
|
159 |
+
"step": 45
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.10686615014694095,
|
163 |
+
"grad_norm": 9.374774032732045,
|
164 |
+
"learning_rate": 9.998741174712533e-07,
|
165 |
+
"logits/chosen": -0.9050552248954773,
|
166 |
+
"logits/rejected": -0.9147823452949524,
|
167 |
+
"logps/chosen": -0.29951199889183044,
|
168 |
+
"logps/rejected": -0.33792784810066223,
|
169 |
+
"loss": 1.5734,
|
170 |
+
"rewards/accuracies": 0.550000011920929,
|
171 |
+
"rewards/chosen": -0.7487800717353821,
|
172 |
+
"rewards/margins": 0.09603960067033768,
|
173 |
+
"rewards/rejected": -0.8448196649551392,
|
174 |
+
"step": 50
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.11755276516163506,
|
178 |
+
"grad_norm": 12.319781154359692,
|
179 |
+
"learning_rate": 9.991050648838675e-07,
|
180 |
+
"logits/chosen": -0.917604923248291,
|
181 |
+
"logits/rejected": -0.859523594379425,
|
182 |
+
"logps/chosen": -0.2723899185657501,
|
183 |
+
"logps/rejected": -0.3260456621646881,
|
184 |
+
"loss": 1.5698,
|
185 |
+
"rewards/accuracies": 0.675000011920929,
|
186 |
+
"rewards/chosen": -0.6809747815132141,
|
187 |
+
"rewards/margins": 0.13413934409618378,
|
188 |
+
"rewards/rejected": -0.8151141405105591,
|
189 |
+
"step": 55
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.12823938017632916,
|
193 |
+
"grad_norm": 10.399641038869387,
|
194 |
+
"learning_rate": 9.97637968732563e-07,
|
195 |
+
"logits/chosen": -0.9515789151191711,
|
196 |
+
"logits/rejected": -0.9302376508712769,
|
197 |
+
"logps/chosen": -0.28720152378082275,
|
198 |
+
"logps/rejected": -0.3024197816848755,
|
199 |
+
"loss": 1.5846,
|
200 |
+
"rewards/accuracies": 0.5874999761581421,
|
201 |
+
"rewards/chosen": -0.7180038690567017,
|
202 |
+
"rewards/margins": 0.03804563358426094,
|
203 |
+
"rewards/rejected": -0.7560494542121887,
|
204 |
+
"step": 60
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.13892599519102325,
|
208 |
+
"grad_norm": 11.022271869662724,
|
209 |
+
"learning_rate": 9.954748808839674e-07,
|
210 |
+
"logits/chosen": -0.943594753742218,
|
211 |
+
"logits/rejected": -0.9900406002998352,
|
212 |
+
"logps/chosen": -0.28493180871009827,
|
213 |
+
"logps/rejected": -0.28960293531417847,
|
214 |
+
"loss": 1.584,
|
215 |
+
"rewards/accuracies": 0.4000000059604645,
|
216 |
+
"rewards/chosen": -0.7123295664787292,
|
217 |
+
"rewards/margins": 0.01167784072458744,
|
218 |
+
"rewards/rejected": -0.7240074276924133,
|
219 |
+
"step": 65
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.14961261020571734,
|
223 |
+
"grad_norm": 16.92128796829008,
|
224 |
+
"learning_rate": 9.926188266120295e-07,
|
225 |
+
"logits/chosen": -0.9900282025337219,
|
226 |
+
"logits/rejected": -0.9590619802474976,
|
227 |
+
"logps/chosen": -0.347956120967865,
|
228 |
+
"logps/rejected": -0.3921958804130554,
|
229 |
+
"loss": 1.5789,
|
230 |
+
"rewards/accuracies": 0.4749999940395355,
|
231 |
+
"rewards/chosen": -0.8698902130126953,
|
232 |
+
"rewards/margins": 0.11059943586587906,
|
233 |
+
"rewards/rejected": -0.9804896116256714,
|
234 |
+
"step": 70
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.16029922522041143,
|
238 |
+
"grad_norm": 16.614347339411598,
|
239 |
+
"learning_rate": 9.890738003669027e-07,
|
240 |
+
"logits/chosen": -0.9594413042068481,
|
241 |
+
"logits/rejected": -0.9471073150634766,
|
242 |
+
"logps/chosen": -0.3611677289009094,
|
243 |
+
"logps/rejected": -0.4440728724002838,
|
244 |
+
"loss": 1.5386,
|
245 |
+
"rewards/accuracies": 0.637499988079071,
|
246 |
+
"rewards/chosen": -0.9029192924499512,
|
247 |
+
"rewards/margins": 0.20726287364959717,
|
248 |
+
"rewards/rejected": -1.1101821660995483,
|
249 |
+
"step": 75
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.17098584023510552,
|
253 |
+
"grad_norm": 11.76758635779136,
|
254 |
+
"learning_rate": 9.848447601883433e-07,
|
255 |
+
"logits/chosen": -0.9906526803970337,
|
256 |
+
"logits/rejected": -0.9735655784606934,
|
257 |
+
"logps/chosen": -0.32699793577194214,
|
258 |
+
"logps/rejected": -0.40725231170654297,
|
259 |
+
"loss": 1.5433,
|
260 |
+
"rewards/accuracies": 0.5249999761581421,
|
261 |
+
"rewards/chosen": -0.8174948692321777,
|
262 |
+
"rewards/margins": 0.20063595473766327,
|
263 |
+
"rewards/rejected": -1.018130898475647,
|
264 |
+
"step": 80
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.18167245524979964,
|
268 |
+
"grad_norm": 10.051730020561614,
|
269 |
+
"learning_rate": 9.799376207714444e-07,
|
270 |
+
"logits/chosen": -0.9377920031547546,
|
271 |
+
"logits/rejected": -0.889153003692627,
|
272 |
+
"logps/chosen": -0.35584911704063416,
|
273 |
+
"logps/rejected": -0.403181254863739,
|
274 |
+
"loss": 1.5549,
|
275 |
+
"rewards/accuracies": 0.550000011920929,
|
276 |
+
"rewards/chosen": -0.8896228671073914,
|
277 |
+
"rewards/margins": 0.11833026260137558,
|
278 |
+
"rewards/rejected": -1.0079530477523804,
|
279 |
+
"step": 85
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.19235907026449373,
|
283 |
+
"grad_norm": 12.299894230325533,
|
284 |
+
"learning_rate": 9.743592451943998e-07,
|
285 |
+
"logits/chosen": -0.9021016955375671,
|
286 |
+
"logits/rejected": -0.8429332971572876,
|
287 |
+
"logps/chosen": -0.3575811982154846,
|
288 |
+
"logps/rejected": -0.5039599537849426,
|
289 |
+
"loss": 1.5625,
|
290 |
+
"rewards/accuracies": 0.5625,
|
291 |
+
"rewards/chosen": -0.8939528465270996,
|
292 |
+
"rewards/margins": 0.36594703793525696,
|
293 |
+
"rewards/rejected": -1.2598999738693237,
|
294 |
+
"step": 90
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.20304568527918782,
|
298 |
+
"grad_norm": 14.145971876119047,
|
299 |
+
"learning_rate": 9.681174353198686e-07,
|
300 |
+
"logits/chosen": -1.002209186553955,
|
301 |
+
"logits/rejected": -1.0227996110916138,
|
302 |
+
"logps/chosen": -0.41834840178489685,
|
303 |
+
"logps/rejected": -0.47105270624160767,
|
304 |
+
"loss": 1.5299,
|
305 |
+
"rewards/accuracies": 0.5874999761581421,
|
306 |
+
"rewards/chosen": -1.0458710193634033,
|
307 |
+
"rewards/margins": 0.13176079094409943,
|
308 |
+
"rewards/rejected": -1.1776319742202759,
|
309 |
+
"step": 95
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.2137323002938819,
|
313 |
+
"grad_norm": 16.666230206302217,
|
314 |
+
"learning_rate": 9.612209208833646e-07,
|
315 |
+
"logits/chosen": -1.0650508403778076,
|
316 |
+
"logits/rejected": -1.0104029178619385,
|
317 |
+
"logps/chosen": -0.4353299140930176,
|
318 |
+
"logps/rejected": -0.4307008385658264,
|
319 |
+
"loss": 1.5889,
|
320 |
+
"rewards/accuracies": 0.6000000238418579,
|
321 |
+
"rewards/chosen": -1.088324785232544,
|
322 |
+
"rewards/margins": -0.011572673916816711,
|
323 |
+
"rewards/rejected": -1.076751947402954,
|
324 |
+
"step": 100
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.224418915308576,
|
328 |
+
"grad_norm": 17.277037383709768,
|
329 |
+
"learning_rate": 9.536793472839324e-07,
|
330 |
+
"logits/chosen": -0.9813326597213745,
|
331 |
+
"logits/rejected": -0.9346880912780762,
|
332 |
+
"logps/chosen": -0.3515966534614563,
|
333 |
+
"logps/rejected": -0.46131715178489685,
|
334 |
+
"loss": 1.5543,
|
335 |
+
"rewards/accuracies": 0.675000011920929,
|
336 |
+
"rewards/chosen": -0.8789916038513184,
|
337 |
+
"rewards/margins": 0.2743012309074402,
|
338 |
+
"rewards/rejected": -1.1532928943634033,
|
339 |
+
"step": 105
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.2351055303232701,
|
343 |
+
"grad_norm": 12.743189576436166,
|
344 |
+
"learning_rate": 9.455032620941839e-07,
|
345 |
+
"logits/chosen": -0.8806193470954895,
|
346 |
+
"logits/rejected": -0.8356341123580933,
|
347 |
+
"logps/chosen": -0.39990124106407166,
|
348 |
+
"logps/rejected": -0.42553144693374634,
|
349 |
+
"loss": 1.5602,
|
350 |
+
"rewards/accuracies": 0.5375000238418579,
|
351 |
+
"rewards/chosen": -0.9997529983520508,
|
352 |
+
"rewards/margins": 0.06407558172941208,
|
353 |
+
"rewards/rejected": -1.063828706741333,
|
354 |
+
"step": 110
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.2457921453379642,
|
358 |
+
"grad_norm": 13.62783373071176,
|
359 |
+
"learning_rate": 9.367041003085648e-07,
|
360 |
+
"logits/chosen": -0.9096847772598267,
|
361 |
+
"logits/rejected": -0.9085425138473511,
|
362 |
+
"logps/chosen": -0.40596961975097656,
|
363 |
+
"logps/rejected": -0.4234519898891449,
|
364 |
+
"loss": 1.5452,
|
365 |
+
"rewards/accuracies": 0.5249999761581421,
|
366 |
+
"rewards/chosen": -1.0149240493774414,
|
367 |
+
"rewards/margins": 0.043705932796001434,
|
368 |
+
"rewards/rejected": -1.0586299896240234,
|
369 |
+
"step": 115
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.2564787603526583,
|
373 |
+
"grad_norm": 12.129891786309633,
|
374 |
+
"learning_rate": 9.272941683504808e-07,
|
375 |
+
"logits/chosen": -0.9741169810295105,
|
376 |
+
"logits/rejected": -0.9402868151664734,
|
377 |
+
"logps/chosen": -0.3675619959831238,
|
378 |
+
"logps/rejected": -0.4012192189693451,
|
379 |
+
"loss": 1.5295,
|
380 |
+
"rewards/accuracies": 0.5249999761581421,
|
381 |
+
"rewards/chosen": -0.9189050793647766,
|
382 |
+
"rewards/margins": 0.08414317667484283,
|
383 |
+
"rewards/rejected": -1.0030481815338135,
|
384 |
+
"step": 120
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.2671653753673524,
|
388 |
+
"grad_norm": 12.760172929151745,
|
389 |
+
"learning_rate": 9.172866268606513e-07,
|
390 |
+
"logits/chosen": -1.014088749885559,
|
391 |
+
"logits/rejected": -1.007265567779541,
|
392 |
+
"logps/chosen": -0.47613659501075745,
|
393 |
+
"logps/rejected": -0.5860797166824341,
|
394 |
+
"loss": 1.5674,
|
395 |
+
"rewards/accuracies": 0.5874999761581421,
|
396 |
+
"rewards/chosen": -1.1903413534164429,
|
397 |
+
"rewards/margins": 0.2748578190803528,
|
398 |
+
"rewards/rejected": -1.4651992321014404,
|
399 |
+
"step": 125
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.2778519903820465,
|
403 |
+
"grad_norm": 14.619403511233878,
|
404 |
+
"learning_rate": 9.066954722907638e-07,
|
405 |
+
"logits/chosen": -1.0016984939575195,
|
406 |
+
"logits/rejected": -1.0274698734283447,
|
407 |
+
"logps/chosen": -0.4267544746398926,
|
408 |
+
"logps/rejected": -0.5695111155509949,
|
409 |
+
"loss": 1.5349,
|
410 |
+
"rewards/accuracies": 0.4749999940395355,
|
411 |
+
"rewards/chosen": -1.0668861865997314,
|
412 |
+
"rewards/margins": 0.35689178109169006,
|
413 |
+
"rewards/rejected": -1.4237778186798096,
|
414 |
+
"step": 130
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.2885386053967406,
|
418 |
+
"grad_norm": 10.619279201046492,
|
419 |
+
"learning_rate": 8.955355173281707e-07,
|
420 |
+
"logits/chosen": -0.9727472066879272,
|
421 |
+
"logits/rejected": -0.9219390749931335,
|
422 |
+
"logps/chosen": -0.39321380853652954,
|
423 |
+
"logps/rejected": -0.4508630633354187,
|
424 |
+
"loss": 1.4978,
|
425 |
+
"rewards/accuracies": 0.512499988079071,
|
426 |
+
"rewards/chosen": -0.9830344915390015,
|
427 |
+
"rewards/margins": 0.1441231220960617,
|
428 |
+
"rewards/rejected": -1.1271576881408691,
|
429 |
+
"step": 135
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.2992252204114347,
|
433 |
+
"grad_norm": 15.834369827499174,
|
434 |
+
"learning_rate": 8.838223701790055e-07,
|
435 |
+
"logits/chosen": -0.967811107635498,
|
436 |
+
"logits/rejected": -0.9583989977836609,
|
437 |
+
"logps/chosen": -0.43714672327041626,
|
438 |
+
"logps/rejected": -0.5161387920379639,
|
439 |
+
"loss": 1.5218,
|
440 |
+
"rewards/accuracies": 0.5625,
|
441 |
+
"rewards/chosen": -1.0928667783737183,
|
442 |
+
"rewards/margins": 0.19748012721538544,
|
443 |
+
"rewards/rejected": -1.2903468608856201,
|
444 |
+
"step": 140
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.30991183542612877,
|
448 |
+
"grad_norm": 12.847642374810391,
|
449 |
+
"learning_rate": 8.71572412738697e-07,
|
450 |
+
"logits/chosen": -0.9621770977973938,
|
451 |
+
"logits/rejected": -0.9567694664001465,
|
452 |
+
"logps/chosen": -0.43871012330055237,
|
453 |
+
"logps/rejected": -0.4793704152107239,
|
454 |
+
"loss": 1.5379,
|
455 |
+
"rewards/accuracies": 0.550000011920929,
|
456 |
+
"rewards/chosen": -1.0967752933502197,
|
457 |
+
"rewards/margins": 0.10165063291788101,
|
458 |
+
"rewards/rejected": -1.1984260082244873,
|
459 |
+
"step": 145
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.32059845044082286,
|
463 |
+
"grad_norm": 11.935024879482611,
|
464 |
+
"learning_rate": 8.588027776804058e-07,
|
465 |
+
"logits/chosen": -0.8888929486274719,
|
466 |
+
"logits/rejected": -0.8930709958076477,
|
467 |
+
"logps/chosen": -0.5125688910484314,
|
468 |
+
"logps/rejected": -0.722069263458252,
|
469 |
+
"loss": 1.5225,
|
470 |
+
"rewards/accuracies": 0.612500011920929,
|
471 |
+
"rewards/chosen": -1.2814221382141113,
|
472 |
+
"rewards/margins": 0.5237509608268738,
|
473 |
+
"rewards/rejected": -1.8051731586456299,
|
474 |
+
"step": 150
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.33128506545551695,
|
478 |
+
"grad_norm": 16.764961972010557,
|
479 |
+
"learning_rate": 8.455313244934324e-07,
|
480 |
+
"logits/chosen": -0.9782350659370422,
|
481 |
+
"logits/rejected": -0.9396332502365112,
|
482 |
+
"logps/chosen": -0.5236457586288452,
|
483 |
+
"logps/rejected": -0.7281317710876465,
|
484 |
+
"loss": 1.4981,
|
485 |
+
"rewards/accuracies": 0.574999988079071,
|
486 |
+
"rewards/chosen": -1.309114694595337,
|
487 |
+
"rewards/margins": 0.5112148523330688,
|
488 |
+
"rewards/rejected": -1.8203294277191162,
|
489 |
+
"step": 155
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.34197168047021104,
|
493 |
+
"grad_norm": 11.439957416651609,
|
494 |
+
"learning_rate": 8.317766145051057e-07,
|
495 |
+
"logits/chosen": -0.9513300061225891,
|
496 |
+
"logits/rejected": -0.9507732391357422,
|
497 |
+
"logps/chosen": -0.4817509651184082,
|
498 |
+
"logps/rejected": -0.6095650792121887,
|
499 |
+
"loss": 1.5319,
|
500 |
+
"rewards/accuracies": 0.6625000238418579,
|
501 |
+
"rewards/chosen": -1.2043774127960205,
|
502 |
+
"rewards/margins": 0.3195350468158722,
|
503 |
+
"rewards/rejected": -1.5239124298095703,
|
504 |
+
"step": 160
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.3526582954849052,
|
508 |
+
"grad_norm": 15.127711801028411,
|
509 |
+
"learning_rate": 8.175578849210894e-07,
|
510 |
+
"logits/chosen": -1.0031640529632568,
|
511 |
+
"logits/rejected": -0.9406889081001282,
|
512 |
+
"logps/chosen": -0.5859075784683228,
|
513 |
+
"logps/rejected": -0.6615421175956726,
|
514 |
+
"loss": 1.5097,
|
515 |
+
"rewards/accuracies": 0.5625,
|
516 |
+
"rewards/chosen": -1.4647690057754517,
|
517 |
+
"rewards/margins": 0.18908634781837463,
|
518 |
+
"rewards/rejected": -1.6538550853729248,
|
519 |
+
"step": 165
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.36334491049959927,
|
523 |
+
"grad_norm": 19.457497723556852,
|
524 |
+
"learning_rate": 8.028950219204099e-07,
|
525 |
+
"logits/chosen": -0.9729808568954468,
|
526 |
+
"logits/rejected": -0.9703952670097351,
|
527 |
+
"logps/chosen": -0.5817127823829651,
|
528 |
+
"logps/rejected": -0.7540786266326904,
|
529 |
+
"loss": 1.52,
|
530 |
+
"rewards/accuracies": 0.5874999761581421,
|
531 |
+
"rewards/chosen": -1.4542819261550903,
|
532 |
+
"rewards/margins": 0.4309147298336029,
|
533 |
+
"rewards/rejected": -1.8851966857910156,
|
534 |
+
"step": 170
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.37403152551429336,
|
538 |
+
"grad_norm": 13.673431328128673,
|
539 |
+
"learning_rate": 7.878085328428368e-07,
|
540 |
+
"logits/chosen": -0.9736520051956177,
|
541 |
+
"logits/rejected": -0.9835022687911987,
|
542 |
+
"logps/chosen": -0.6428834795951843,
|
543 |
+
"logps/rejected": -0.8455599546432495,
|
544 |
+
"loss": 1.4591,
|
545 |
+
"rewards/accuracies": 0.6499999761581421,
|
546 |
+
"rewards/chosen": -1.6072088479995728,
|
547 |
+
"rewards/margins": 0.5066913366317749,
|
548 |
+
"rewards/rejected": -2.1139001846313477,
|
549 |
+
"step": 175
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.38471814052898745,
|
553 |
+
"grad_norm": 20.186619677768963,
|
554 |
+
"learning_rate": 7.723195175075135e-07,
|
555 |
+
"logits/chosen": -0.9989040493965149,
|
556 |
+
"logits/rejected": -0.9996326565742493,
|
557 |
+
"logps/chosen": -0.6329335570335388,
|
558 |
+
"logps/rejected": -0.7996684312820435,
|
559 |
+
"loss": 1.5042,
|
560 |
+
"rewards/accuracies": 0.6625000238418579,
|
561 |
+
"rewards/chosen": -1.5823338031768799,
|
562 |
+
"rewards/margins": 0.41683727502822876,
|
563 |
+
"rewards/rejected": -1.999171257019043,
|
564 |
+
"step": 180
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.39540475554368154,
|
568 |
+
"grad_norm": 20.89728549129117,
|
569 |
+
"learning_rate": 7.564496387029531e-07,
|
570 |
+
"logits/chosen": -1.0245858430862427,
|
571 |
+
"logits/rejected": -0.9974483251571655,
|
572 |
+
"logps/chosen": -0.5426946878433228,
|
573 |
+
"logps/rejected": -0.765714168548584,
|
574 |
+
"loss": 1.5357,
|
575 |
+
"rewards/accuracies": 0.625,
|
576 |
+
"rewards/chosen": -1.3567368984222412,
|
577 |
+
"rewards/margins": 0.5575486421585083,
|
578 |
+
"rewards/rejected": -1.914285659790039,
|
579 |
+
"step": 185
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.40609137055837563,
|
583 |
+
"grad_norm": 14.284349268241145,
|
584 |
+
"learning_rate": 7.402210918896689e-07,
|
585 |
+
"logits/chosen": -1.0203882455825806,
|
586 |
+
"logits/rejected": -1.002201795578003,
|
587 |
+
"logps/chosen": -0.5420663356781006,
|
588 |
+
"logps/rejected": -0.8374710083007812,
|
589 |
+
"loss": 1.4458,
|
590 |
+
"rewards/accuracies": 0.6875,
|
591 |
+
"rewards/chosen": -1.355165719985962,
|
592 |
+
"rewards/margins": 0.7385115623474121,
|
593 |
+
"rewards/rejected": -2.093677282333374,
|
594 |
+
"step": 190
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.4167779855730697,
|
598 |
+
"grad_norm": 21.006500802721117,
|
599 |
+
"learning_rate": 7.236565741578162e-07,
|
600 |
+
"logits/chosen": -0.9360872507095337,
|
601 |
+
"logits/rejected": -0.9267364740371704,
|
602 |
+
"logps/chosen": -0.6582534909248352,
|
603 |
+
"logps/rejected": -0.9019840359687805,
|
604 |
+
"loss": 1.496,
|
605 |
+
"rewards/accuracies": 0.5874999761581421,
|
606 |
+
"rewards/chosen": -1.6456336975097656,
|
607 |
+
"rewards/margins": 0.6093264818191528,
|
608 |
+
"rewards/rejected": -2.254960298538208,
|
609 |
+
"step": 195
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.4274646005877638,
|
613 |
+
"grad_norm": 17.34001688115439,
|
614 |
+
"learning_rate": 7.067792524832603e-07,
|
615 |
+
"logits/chosen": -0.9733101725578308,
|
616 |
+
"logits/rejected": -0.9737011194229126,
|
617 |
+
"logps/chosen": -0.5885142087936401,
|
618 |
+
"logps/rejected": -0.759198784828186,
|
619 |
+
"loss": 1.4947,
|
620 |
+
"rewards/accuracies": 0.6875,
|
621 |
+
"rewards/chosen": -1.4712855815887451,
|
622 |
+
"rewards/margins": 0.42671123147010803,
|
623 |
+
"rewards/rejected": -1.8979966640472412,
|
624 |
+
"step": 200
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.4381512156024579,
|
628 |
+
"grad_norm": 18.93087179194272,
|
629 |
+
"learning_rate": 6.896127313264642e-07,
|
630 |
+
"logits/chosen": -1.0645233392715454,
|
631 |
+
"logits/rejected": -1.0247756242752075,
|
632 |
+
"logps/chosen": -0.7058154940605164,
|
633 |
+
"logps/rejected": -0.8320499658584595,
|
634 |
+
"loss": 1.481,
|
635 |
+
"rewards/accuracies": 0.574999988079071,
|
636 |
+
"rewards/chosen": -1.7645390033721924,
|
637 |
+
"rewards/margins": 0.3155860900878906,
|
638 |
+
"rewards/rejected": -2.080124855041504,
|
639 |
+
"step": 205
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.448837830617152,
|
643 |
+
"grad_norm": 20.51304681116505,
|
644 |
+
"learning_rate": 6.721810196195174e-07,
|
645 |
+
"logits/chosen": -1.0714137554168701,
|
646 |
+
"logits/rejected": -0.9989116787910461,
|
647 |
+
"logps/chosen": -0.6715008020401001,
|
648 |
+
"logps/rejected": -0.8458214998245239,
|
649 |
+
"loss": 1.4931,
|
650 |
+
"rewards/accuracies": 0.6000000238418579,
|
651 |
+
"rewards/chosen": -1.6787519454956055,
|
652 |
+
"rewards/margins": 0.43580159544944763,
|
653 |
+
"rewards/rejected": -2.114553451538086,
|
654 |
+
"step": 210
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.45952444563184613,
|
658 |
+
"grad_norm": 16.46301637400639,
|
659 |
+
"learning_rate": 6.545084971874736e-07,
|
660 |
+
"logits/chosen": -1.0320379734039307,
|
661 |
+
"logits/rejected": -0.9812155961990356,
|
662 |
+
"logps/chosen": -0.7699872255325317,
|
663 |
+
"logps/rejected": -0.9591902494430542,
|
664 |
+
"loss": 1.4357,
|
665 |
+
"rewards/accuracies": 0.550000011920929,
|
666 |
+
"rewards/chosen": -1.9249680042266846,
|
667 |
+
"rewards/margins": 0.47300752997398376,
|
668 |
+
"rewards/rejected": -2.397975444793701,
|
669 |
+
"step": 215
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.4702110606465402,
|
673 |
+
"grad_norm": 21.088635750930834,
|
674 |
+
"learning_rate": 6.3661988065096e-07,
|
675 |
+
"logits/chosen": -1.0327280759811401,
|
676 |
+
"logits/rejected": -0.9874359965324402,
|
677 |
+
"logps/chosen": -0.8896724581718445,
|
678 |
+
"logps/rejected": -1.0073192119598389,
|
679 |
+
"loss": 1.4954,
|
680 |
+
"rewards/accuracies": 0.625,
|
681 |
+
"rewards/chosen": -2.2241809368133545,
|
682 |
+
"rewards/margins": 0.2941167950630188,
|
683 |
+
"rewards/rejected": -2.5182979106903076,
|
684 |
+
"step": 220
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.4808976756612343,
|
688 |
+
"grad_norm": 19.02142810522417,
|
689 |
+
"learning_rate": 6.185401888577487e-07,
|
690 |
+
"logits/chosen": -0.9864276051521301,
|
691 |
+
"logits/rejected": -0.9660781621932983,
|
692 |
+
"logps/chosen": -0.772359311580658,
|
693 |
+
"logps/rejected": -0.794577956199646,
|
694 |
+
"loss": 1.557,
|
695 |
+
"rewards/accuracies": 0.6499999761581421,
|
696 |
+
"rewards/chosen": -1.9308984279632568,
|
697 |
+
"rewards/margins": 0.0555465929210186,
|
698 |
+
"rewards/rejected": -1.9864448308944702,
|
699 |
+
"step": 225
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.4915842906759284,
|
703 |
+
"grad_norm": 17.867436451445265,
|
704 |
+
"learning_rate": 6.002947078916364e-07,
|
705 |
+
"logits/chosen": -1.0150645971298218,
|
706 |
+
"logits/rejected": -0.9232436418533325,
|
707 |
+
"logps/chosen": -0.8819006085395813,
|
708 |
+
"logps/rejected": -1.0791282653808594,
|
709 |
+
"loss": 1.4692,
|
710 |
+
"rewards/accuracies": 0.625,
|
711 |
+
"rewards/chosen": -2.2047512531280518,
|
712 |
+
"rewards/margins": 0.49306946992874146,
|
713 |
+
"rewards/rejected": -2.6978209018707275,
|
714 |
+
"step": 230
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.5022709056906225,
|
718 |
+
"grad_norm": 19.261147315812543,
|
719 |
+
"learning_rate": 5.819089557075688e-07,
|
720 |
+
"logits/chosen": -0.996496319770813,
|
721 |
+
"logits/rejected": -0.9518272280693054,
|
722 |
+
"logps/chosen": -0.8440850377082825,
|
723 |
+
"logps/rejected": -0.9660031199455261,
|
724 |
+
"loss": 1.4942,
|
725 |
+
"rewards/accuracies": 0.550000011920929,
|
726 |
+
"rewards/chosen": -2.110212564468384,
|
727 |
+
"rewards/margins": 0.30479517579078674,
|
728 |
+
"rewards/rejected": -2.4150078296661377,
|
729 |
+
"step": 235
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.5129575207053166,
|
733 |
+
"grad_norm": 18.32103206829717,
|
734 |
+
"learning_rate": 5.634086464424742e-07,
|
735 |
+
"logits/chosen": -1.0355093479156494,
|
736 |
+
"logits/rejected": -1.006392002105713,
|
737 |
+
"logps/chosen": -0.7564712762832642,
|
738 |
+
"logps/rejected": -0.9403325319290161,
|
739 |
+
"loss": 1.4046,
|
740 |
+
"rewards/accuracies": 0.6625000238418579,
|
741 |
+
"rewards/chosen": -1.8911781311035156,
|
742 |
+
"rewards/margins": 0.4596532881259918,
|
743 |
+
"rewards/rejected": -2.3508315086364746,
|
744 |
+
"step": 240
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.5236441357200107,
|
748 |
+
"grad_norm": 13.624682866914808,
|
749 |
+
"learning_rate": 5.448196544517167e-07,
|
750 |
+
"logits/chosen": -1.0392498970031738,
|
751 |
+
"logits/rejected": -1.0080206394195557,
|
752 |
+
"logps/chosen": -0.7070968151092529,
|
753 |
+
"logps/rejected": -0.8767108917236328,
|
754 |
+
"loss": 1.4407,
|
755 |
+
"rewards/accuracies": 0.5375000238418579,
|
756 |
+
"rewards/chosen": -1.7677417993545532,
|
757 |
+
"rewards/margins": 0.4240352213382721,
|
758 |
+
"rewards/rejected": -2.191777229309082,
|
759 |
+
"step": 245
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.5343307507347048,
|
763 |
+
"grad_norm": 22.22843267157582,
|
764 |
+
"learning_rate": 5.26167978121472e-07,
|
765 |
+
"logits/chosen": -1.048105001449585,
|
766 |
+
"logits/rejected": -1.028188943862915,
|
767 |
+
"logps/chosen": -0.8559715151786804,
|
768 |
+
"logps/rejected": -1.2052185535430908,
|
769 |
+
"loss": 1.467,
|
770 |
+
"rewards/accuracies": 0.6625000238418579,
|
771 |
+
"rewards/chosen": -2.1399290561676025,
|
772 |
+
"rewards/margins": 0.8731171488761902,
|
773 |
+
"rewards/rejected": -3.0130460262298584,
|
774 |
+
"step": 250
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.5450173657493989,
|
778 |
+
"grad_norm": 21.7502246417763,
|
779 |
+
"learning_rate": 5.074797035076318e-07,
|
780 |
+
"logits/chosen": -1.0093282461166382,
|
781 |
+
"logits/rejected": -1.0085898637771606,
|
782 |
+
"logps/chosen": -0.8086752891540527,
|
783 |
+
"logps/rejected": -0.9931262731552124,
|
784 |
+
"loss": 1.4101,
|
785 |
+
"rewards/accuracies": 0.612500011920929,
|
786 |
+
"rewards/chosen": -2.021688222885132,
|
787 |
+
"rewards/margins": 0.4611276090145111,
|
788 |
+
"rewards/rejected": -2.4828155040740967,
|
789 |
+
"step": 255
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.555703980764093,
|
793 |
+
"grad_norm": 17.422008542886676,
|
794 |
+
"learning_rate": 4.887809678520975e-07,
|
795 |
+
"logits/chosen": -0.9935086369514465,
|
796 |
+
"logits/rejected": -0.9804226160049438,
|
797 |
+
"logps/chosen": -0.7468116879463196,
|
798 |
+
"logps/rejected": -1.0926599502563477,
|
799 |
+
"loss": 1.4384,
|
800 |
+
"rewards/accuracies": 0.7250000238418579,
|
801 |
+
"rewards/chosen": -1.8670291900634766,
|
802 |
+
"rewards/margins": 0.8646209836006165,
|
803 |
+
"rewards/rejected": -2.731649875640869,
|
804 |
+
"step": 260
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.566390595778787,
|
808 |
+
"grad_norm": 21.42359137838811,
|
809 |
+
"learning_rate": 4.700979230274829e-07,
|
810 |
+
"logits/chosen": -1.0343437194824219,
|
811 |
+
"logits/rejected": -1.0285662412643433,
|
812 |
+
"logps/chosen": -0.8779309391975403,
|
813 |
+
"logps/rejected": -0.9997223019599915,
|
814 |
+
"loss": 1.4835,
|
815 |
+
"rewards/accuracies": 0.6625000238418579,
|
816 |
+
"rewards/chosen": -2.19482684135437,
|
817 |
+
"rewards/margins": 0.3044784963130951,
|
818 |
+
"rewards/rejected": -2.4993057250976562,
|
819 |
+
"step": 265
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.5770772107934812,
|
823 |
+
"grad_norm": 27.361650975575174,
|
824 |
+
"learning_rate": 4.514566989613559e-07,
|
825 |
+
"logits/chosen": -1.022482991218567,
|
826 |
+
"logits/rejected": -1.030027151107788,
|
827 |
+
"logps/chosen": -0.8233085870742798,
|
828 |
+
"logps/rejected": -1.0775353908538818,
|
829 |
+
"loss": 1.4746,
|
830 |
+
"rewards/accuracies": 0.612500011920929,
|
831 |
+
"rewards/chosen": -2.058271646499634,
|
832 |
+
"rewards/margins": 0.6355669498443604,
|
833 |
+
"rewards/rejected": -2.693838596343994,
|
834 |
+
"step": 270
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.5877638258081752,
|
838 |
+
"grad_norm": 19.306011967200188,
|
839 |
+
"learning_rate": 4.328833670911724e-07,
|
840 |
+
"logits/chosen": -0.8774306178092957,
|
841 |
+
"logits/rejected": -0.841380774974823,
|
842 |
+
"logps/chosen": -0.977648138999939,
|
843 |
+
"logps/rejected": -1.1523730754852295,
|
844 |
+
"loss": 1.4355,
|
845 |
+
"rewards/accuracies": 0.5625,
|
846 |
+
"rewards/chosen": -2.444120168685913,
|
847 |
+
"rewards/margins": 0.43681272864341736,
|
848 |
+
"rewards/rejected": -2.8809328079223633,
|
849 |
+
"step": 275
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.5984504408228694,
|
853 |
+
"grad_norm": 18.830991297114817,
|
854 |
+
"learning_rate": 4.144039039010124e-07,
|
855 |
+
"logits/chosen": -1.0766229629516602,
|
856 |
+
"logits/rejected": -1.034156084060669,
|
857 |
+
"logps/chosen": -0.9281458854675293,
|
858 |
+
"logps/rejected": -1.0838878154754639,
|
859 |
+
"loss": 1.4465,
|
860 |
+
"rewards/accuracies": 0.625,
|
861 |
+
"rewards/chosen": -2.3203647136688232,
|
862 |
+
"rewards/margins": 0.38935500383377075,
|
863 |
+
"rewards/rejected": -2.709719657897949,
|
864 |
+
"step": 280
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.6091370558375635,
|
868 |
+
"grad_norm": 20.938307778539542,
|
869 |
+
"learning_rate": 3.960441545911204e-07,
|
870 |
+
"logits/chosen": -0.9466499090194702,
|
871 |
+
"logits/rejected": -0.9020398855209351,
|
872 |
+
"logps/chosen": -1.1035289764404297,
|
873 |
+
"logps/rejected": -1.1428934335708618,
|
874 |
+
"loss": 1.4739,
|
875 |
+
"rewards/accuracies": 0.550000011920929,
|
876 |
+
"rewards/chosen": -2.758822441101074,
|
877 |
+
"rewards/margins": 0.09841099381446838,
|
878 |
+
"rewards/rejected": -2.8572330474853516,
|
879 |
+
"step": 285
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.6198236708522575,
|
883 |
+
"grad_norm": 23.245653263780497,
|
884 |
+
"learning_rate": 3.778297969310529e-07,
|
885 |
+
"logits/chosen": -0.9969805479049683,
|
886 |
+
"logits/rejected": -0.9768760800361633,
|
887 |
+
"logps/chosen": -0.9135320782661438,
|
888 |
+
"logps/rejected": -1.1653510332107544,
|
889 |
+
"loss": 1.3943,
|
890 |
+
"rewards/accuracies": 0.6499999761581421,
|
891 |
+
"rewards/chosen": -2.283830165863037,
|
892 |
+
"rewards/margins": 0.6295474767684937,
|
893 |
+
"rewards/rejected": -2.9133777618408203,
|
894 |
+
"step": 290
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.6305102858669517,
|
898 |
+
"grad_norm": 18.66753481518412,
|
899 |
+
"learning_rate": 3.5978630534699865e-07,
|
900 |
+
"logits/chosen": -1.0683342218399048,
|
901 |
+
"logits/rejected": -1.0506360530853271,
|
902 |
+
"logps/chosen": -1.0534954071044922,
|
903 |
+
"logps/rejected": -1.2509009838104248,
|
904 |
+
"loss": 1.4446,
|
905 |
+
"rewards/accuracies": 0.6625000238418579,
|
906 |
+
"rewards/chosen": -2.6337387561798096,
|
907 |
+
"rewards/margins": 0.4935137629508972,
|
908 |
+
"rewards/rejected": -3.1272525787353516,
|
909 |
+
"step": 295
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.6411969008816457,
|
913 |
+
"grad_norm": 21.410873330760186,
|
914 |
+
"learning_rate": 3.4193891529348795e-07,
|
915 |
+
"logits/chosen": -0.943785548210144,
|
916 |
+
"logits/rejected": -0.8960458040237427,
|
917 |
+
"logps/chosen": -0.9090589284896851,
|
918 |
+
"logps/rejected": -1.2448195219039917,
|
919 |
+
"loss": 1.4048,
|
920 |
+
"rewards/accuracies": 0.637499988079071,
|
921 |
+
"rewards/chosen": -2.2726473808288574,
|
922 |
+
"rewards/margins": 0.8394016027450562,
|
923 |
+
"rewards/rejected": -3.112048625946045,
|
924 |
+
"step": 300
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.6518835158963399,
|
928 |
+
"grad_norm": 16.99902973812307,
|
929 |
+
"learning_rate": 3.243125879593286e-07,
|
930 |
+
"logits/chosen": -1.001460075378418,
|
931 |
+
"logits/rejected": -0.9785451889038086,
|
932 |
+
"logps/chosen": -1.0239307880401611,
|
933 |
+
"logps/rejected": -1.286873698234558,
|
934 |
+
"loss": 1.4219,
|
935 |
+
"rewards/accuracies": 0.6875,
|
936 |
+
"rewards/chosen": -2.5598270893096924,
|
937 |
+
"rewards/margins": 0.6573570370674133,
|
938 |
+
"rewards/rejected": -3.217184543609619,
|
939 |
+
"step": 305
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.6625701309110339,
|
943 |
+
"grad_norm": 35.891043777341494,
|
944 |
+
"learning_rate": 3.069319753571269e-07,
|
945 |
+
"logits/chosen": -0.9791940450668335,
|
946 |
+
"logits/rejected": -1.024137258529663,
|
947 |
+
"logps/chosen": -1.0476067066192627,
|
948 |
+
"logps/rejected": -1.3181588649749756,
|
949 |
+
"loss": 1.4695,
|
950 |
+
"rewards/accuracies": 0.6000000238418579,
|
951 |
+
"rewards/chosen": -2.619016170501709,
|
952 |
+
"rewards/margins": 0.6763805747032166,
|
953 |
+
"rewards/rejected": -3.2953972816467285,
|
954 |
+
"step": 310
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.673256745925728,
|
958 |
+
"grad_norm": 22.292608497489727,
|
959 |
+
"learning_rate": 2.898213858452173e-07,
|
960 |
+
"logits/chosen": -1.1296494007110596,
|
961 |
+
"logits/rejected": -1.086306095123291,
|
962 |
+
"logps/chosen": -1.0372415781021118,
|
963 |
+
"logps/rejected": -1.1678041219711304,
|
964 |
+
"loss": 1.469,
|
965 |
+
"rewards/accuracies": 0.612500011920929,
|
966 |
+
"rewards/chosen": -2.593104124069214,
|
967 |
+
"rewards/margins": 0.3264063894748688,
|
968 |
+
"rewards/rejected": -2.9195103645324707,
|
969 |
+
"step": 315
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.6839433609404221,
|
973 |
+
"grad_norm": 24.37127385244042,
|
974 |
+
"learning_rate": 2.730047501302266e-07,
|
975 |
+
"logits/chosen": -1.0386595726013184,
|
976 |
+
"logits/rejected": -1.019863486289978,
|
977 |
+
"logps/chosen": -0.9849531054496765,
|
978 |
+
"logps/rejected": -1.240861177444458,
|
979 |
+
"loss": 1.4399,
|
980 |
+
"rewards/accuracies": 0.625,
|
981 |
+
"rewards/chosen": -2.4623827934265137,
|
982 |
+
"rewards/margins": 0.6397703289985657,
|
983 |
+
"rewards/rejected": -3.1021530628204346,
|
984 |
+
"step": 320
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.6946299759551162,
|
988 |
+
"grad_norm": 28.3616490001571,
|
989 |
+
"learning_rate": 2.5650558779781635e-07,
|
990 |
+
"logits/chosen": -0.9190061688423157,
|
991 |
+
"logits/rejected": -0.9376241564750671,
|
992 |
+
"logps/chosen": -1.0179104804992676,
|
993 |
+
"logps/rejected": -1.1567823886871338,
|
994 |
+
"loss": 1.3944,
|
995 |
+
"rewards/accuracies": 0.612500011920929,
|
996 |
+
"rewards/chosen": -2.544776439666748,
|
997 |
+
"rewards/margins": 0.3471793532371521,
|
998 |
+
"rewards/rejected": -2.891955614089966,
|
999 |
+
"step": 325
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.7053165909698104,
|
1003 |
+
"grad_norm": 23.089017555469844,
|
1004 |
+
"learning_rate": 2.403469744184154e-07,
|
1005 |
+
"logits/chosen": -1.0184417963027954,
|
1006 |
+
"logits/rejected": -0.9639641642570496,
|
1007 |
+
"logps/chosen": -1.065198540687561,
|
1008 |
+
"logps/rejected": -1.4555224180221558,
|
1009 |
+
"loss": 1.4179,
|
1010 |
+
"rewards/accuracies": 0.6875,
|
1011 |
+
"rewards/chosen": -2.6629960536956787,
|
1012 |
+
"rewards/margins": 0.9758095741271973,
|
1013 |
+
"rewards/rejected": -3.638806104660034,
|
1014 |
+
"step": 330
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.7160032059845044,
|
1018 |
+
"grad_norm": 19.01160663909916,
|
1019 |
+
"learning_rate": 2.2455150927394878e-07,
|
1020 |
+
"logits/chosen": -0.9782741665840149,
|
1021 |
+
"logits/rejected": -1.0168932676315308,
|
1022 |
+
"logps/chosen": -1.1860311031341553,
|
1023 |
+
"logps/rejected": -1.3966830968856812,
|
1024 |
+
"loss": 1.4107,
|
1025 |
+
"rewards/accuracies": 0.5874999761581421,
|
1026 |
+
"rewards/chosen": -2.965078115463257,
|
1027 |
+
"rewards/margins": 0.5266298651695251,
|
1028 |
+
"rewards/rejected": -3.4917080402374268,
|
1029 |
+
"step": 335
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.7266898209991985,
|
1033 |
+
"grad_norm": 24.023962985538827,
|
1034 |
+
"learning_rate": 2.0914128375069722e-07,
|
1035 |
+
"logits/chosen": -0.9762552380561829,
|
1036 |
+
"logits/rejected": -0.9652606248855591,
|
1037 |
+
"logps/chosen": -1.0335513353347778,
|
1038 |
+
"logps/rejected": -1.3794705867767334,
|
1039 |
+
"loss": 1.4363,
|
1040 |
+
"rewards/accuracies": 0.675000011920929,
|
1041 |
+
"rewards/chosen": -2.5838780403137207,
|
1042 |
+
"rewards/margins": 0.8647986650466919,
|
1043 |
+
"rewards/rejected": -3.448676586151123,
|
1044 |
+
"step": 340
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.7373764360138926,
|
1048 |
+
"grad_norm": 24.338376358621,
|
1049 |
+
"learning_rate": 1.9413785044249676e-07,
|
1050 |
+
"logits/chosen": -0.9369735717773438,
|
1051 |
+
"logits/rejected": -0.9039338827133179,
|
1052 |
+
"logps/chosen": -1.2081493139266968,
|
1053 |
+
"logps/rejected": -1.3959646224975586,
|
1054 |
+
"loss": 1.3412,
|
1055 |
+
"rewards/accuracies": 0.6000000238418579,
|
1056 |
+
"rewards/chosen": -3.020373821258545,
|
1057 |
+
"rewards/margins": 0.4695381224155426,
|
1058 |
+
"rewards/rejected": -3.4899115562438965,
|
1059 |
+
"step": 345
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.7480630510285867,
|
1063 |
+
"grad_norm": 25.7573169489427,
|
1064 |
+
"learning_rate": 1.7956219300748792e-07,
|
1065 |
+
"logits/chosen": -1.0008254051208496,
|
1066 |
+
"logits/rejected": -1.0084810256958008,
|
1067 |
+
"logps/chosen": -1.048879861831665,
|
1068 |
+
"logps/rejected": -1.3672925233840942,
|
1069 |
+
"loss": 1.3953,
|
1070 |
+
"rewards/accuracies": 0.7124999761581421,
|
1071 |
+
"rewards/chosen": -2.622199773788452,
|
1072 |
+
"rewards/margins": 0.7960314750671387,
|
1073 |
+
"rewards/rejected": -3.418231248855591,
|
1074 |
+
"step": 350
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.7587496660432808,
|
1078 |
+
"grad_norm": 26.96889041092714,
|
1079 |
+
"learning_rate": 1.6543469682057104e-07,
|
1080 |
+
"logits/chosen": -1.0293567180633545,
|
1081 |
+
"logits/rejected": -0.9677215814590454,
|
1082 |
+
"logps/chosen": -1.0719913244247437,
|
1083 |
+
"logps/rejected": -1.2735936641693115,
|
1084 |
+
"loss": 1.3954,
|
1085 |
+
"rewards/accuracies": 0.5874999761581421,
|
1086 |
+
"rewards/chosen": -2.679978370666504,
|
1087 |
+
"rewards/margins": 0.5040060877799988,
|
1088 |
+
"rewards/rejected": -3.1839847564697266,
|
1089 |
+
"step": 355
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.7694362810579749,
|
1093 |
+
"grad_norm": 21.661999756036945,
|
1094 |
+
"learning_rate": 1.5177512046261666e-07,
|
1095 |
+
"logits/chosen": -0.9887057542800903,
|
1096 |
+
"logits/rejected": -1.0177589654922485,
|
1097 |
+
"logps/chosen": -1.291603922843933,
|
1098 |
+
"logps/rejected": -1.665748953819275,
|
1099 |
+
"loss": 1.3804,
|
1100 |
+
"rewards/accuracies": 0.612500011920929,
|
1101 |
+
"rewards/chosen": -3.2290101051330566,
|
1102 |
+
"rewards/margins": 0.9353626370429993,
|
1103 |
+
"rewards/rejected": -4.164372444152832,
|
1104 |
+
"step": 360
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.7801228960726689,
|
1108 |
+
"grad_norm": 21.098443523944745,
|
1109 |
+
"learning_rate": 1.3860256808630427e-07,
|
1110 |
+
"logits/chosen": -0.9724413752555847,
|
1111 |
+
"logits/rejected": -0.9351035952568054,
|
1112 |
+
"logps/chosen": -1.203754186630249,
|
1113 |
+
"logps/rejected": -1.3952935934066772,
|
1114 |
+
"loss": 1.3868,
|
1115 |
+
"rewards/accuracies": 0.6000000238418579,
|
1116 |
+
"rewards/chosen": -3.009385347366333,
|
1117 |
+
"rewards/margins": 0.4788486063480377,
|
1118 |
+
"rewards/rejected": -3.488234043121338,
|
1119 |
+
"step": 365
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.7908095110873631,
|
1123 |
+
"grad_norm": 25.021776262301575,
|
1124 |
+
"learning_rate": 1.2593546269723647e-07,
|
1125 |
+
"logits/chosen": -1.0209473371505737,
|
1126 |
+
"logits/rejected": -1.0015369653701782,
|
1127 |
+
"logps/chosen": -1.2007997035980225,
|
1128 |
+
"logps/rejected": -1.3749370574951172,
|
1129 |
+
"loss": 1.3739,
|
1130 |
+
"rewards/accuracies": 0.625,
|
1131 |
+
"rewards/chosen": -3.0019993782043457,
|
1132 |
+
"rewards/margins": 0.43534326553344727,
|
1133 |
+
"rewards/rejected": -3.437342405319214,
|
1134 |
+
"step": 370
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.8014961261020572,
|
1138 |
+
"grad_norm": 25.159927366829866,
|
1139 |
+
"learning_rate": 1.1379152038770029e-07,
|
1140 |
+
"logits/chosen": -1.0015761852264404,
|
1141 |
+
"logits/rejected": -1.0289709568023682,
|
1142 |
+
"logps/chosen": -1.0982341766357422,
|
1143 |
+
"logps/rejected": -1.3828232288360596,
|
1144 |
+
"loss": 1.4606,
|
1145 |
+
"rewards/accuracies": 0.675000011920929,
|
1146 |
+
"rewards/chosen": -2.7455852031707764,
|
1147 |
+
"rewards/margins": 0.7114725708961487,
|
1148 |
+
"rewards/rejected": -3.4570579528808594,
|
1149 |
+
"step": 375
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.8121827411167513,
|
1153 |
+
"grad_norm": 20.84984615780728,
|
1154 |
+
"learning_rate": 1.0218772555910954e-07,
|
1155 |
+
"logits/chosen": -1.087043046951294,
|
1156 |
+
"logits/rejected": -1.0346585512161255,
|
1157 |
+
"logps/chosen": -1.2293280363082886,
|
1158 |
+
"logps/rejected": -1.4728463888168335,
|
1159 |
+
"loss": 1.3777,
|
1160 |
+
"rewards/accuracies": 0.612500011920929,
|
1161 |
+
"rewards/chosen": -3.073319911956787,
|
1162 |
+
"rewards/margins": 0.6087957620620728,
|
1163 |
+
"rewards/rejected": -3.6821160316467285,
|
1164 |
+
"step": 380
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.8228693561314454,
|
1168 |
+
"grad_norm": 22.784469290812634,
|
1169 |
+
"learning_rate": 9.114030716778432e-08,
|
1170 |
+
"logits/chosen": -1.0404977798461914,
|
1171 |
+
"logits/rejected": -1.0313512086868286,
|
1172 |
+
"logps/chosen": -1.2078773975372314,
|
1173 |
+
"logps/rejected": -1.5215582847595215,
|
1174 |
+
"loss": 1.3372,
|
1175 |
+
"rewards/accuracies": 0.675000011920929,
|
1176 |
+
"rewards/chosen": -3.019693613052368,
|
1177 |
+
"rewards/margins": 0.7842024564743042,
|
1178 |
+
"rewards/rejected": -3.803895950317383,
|
1179 |
+
"step": 385
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.8335559711461394,
|
1183 |
+
"grad_norm": 38.2013964652558,
|
1184 |
+
"learning_rate": 8.066471602728803e-08,
|
1185 |
+
"logits/chosen": -1.0984976291656494,
|
1186 |
+
"logits/rejected": -1.0727328062057495,
|
1187 |
+
"logps/chosen": -1.2440178394317627,
|
1188 |
+
"logps/rejected": -1.535946011543274,
|
1189 |
+
"loss": 1.3633,
|
1190 |
+
"rewards/accuracies": 0.6499999761581421,
|
1191 |
+
"rewards/chosen": -3.110044479370117,
|
1192 |
+
"rewards/margins": 0.7298205494880676,
|
1193 |
+
"rewards/rejected": -3.839865207672119,
|
1194 |
+
"step": 390
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.8442425861608336,
|
1198 |
+
"grad_norm": 21.29430884924605,
|
1199 |
+
"learning_rate": 7.077560319906694e-08,
|
1200 |
+
"logits/chosen": -0.9021504521369934,
|
1201 |
+
"logits/rejected": -0.817115306854248,
|
1202 |
+
"logps/chosen": -1.1583576202392578,
|
1203 |
+
"logps/rejected": -1.3431838750839233,
|
1204 |
+
"loss": 1.396,
|
1205 |
+
"rewards/accuracies": 0.612500011920929,
|
1206 |
+
"rewards/chosen": -2.8958938121795654,
|
1207 |
+
"rewards/margins": 0.46206584572792053,
|
1208 |
+
"rewards/rejected": -3.357959747314453,
|
1209 |
+
"step": 395
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.8549292011755276,
|
1213 |
+
"grad_norm": 18.542727738232298,
|
1214 |
+
"learning_rate": 6.148679950161672e-08,
|
1215 |
+
"logits/chosen": -0.9785951375961304,
|
1216 |
+
"logits/rejected": -0.9371121525764465,
|
1217 |
+
"logps/chosen": -1.3020581007003784,
|
1218 |
+
"logps/rejected": -1.5772645473480225,
|
1219 |
+
"loss": 1.3975,
|
1220 |
+
"rewards/accuracies": 0.7250000238418579,
|
1221 |
+
"rewards/chosen": -3.255145311355591,
|
1222 |
+
"rewards/margins": 0.6880159974098206,
|
1223 |
+
"rewards/rejected": -3.9431610107421875,
|
1224 |
+
"step": 400
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.8549292011755276,
|
1228 |
+
"eval_logits/chosen": -1.1872848272323608,
|
1229 |
+
"eval_logits/rejected": -1.1544642448425293,
|
1230 |
+
"eval_logps/chosen": -1.1779358386993408,
|
1231 |
+
"eval_logps/rejected": -1.4415003061294556,
|
1232 |
+
"eval_loss": 1.375516653060913,
|
1233 |
+
"eval_rewards/accuracies": 0.6612903475761414,
|
1234 |
+
"eval_rewards/chosen": -2.9448394775390625,
|
1235 |
+
"eval_rewards/margins": 0.6589111685752869,
|
1236 |
+
"eval_rewards/rejected": -3.603750705718994,
|
1237 |
+
"eval_runtime": 72.7978,
|
1238 |
+
"eval_samples_per_second": 26.938,
|
1239 |
+
"eval_steps_per_second": 0.852,
|
1240 |
+
"step": 400
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 0.8656158161902218,
|
1244 |
+
"grad_norm": 23.254725123506937,
|
1245 |
+
"learning_rate": 5.2811296166831666e-08,
|
1246 |
+
"logits/chosen": -0.9737190008163452,
|
1247 |
+
"logits/rejected": -0.8999165296554565,
|
1248 |
+
"logps/chosen": -1.2110763788223267,
|
1249 |
+
"logps/rejected": -1.4770066738128662,
|
1250 |
+
"loss": 1.4197,
|
1251 |
+
"rewards/accuracies": 0.6875,
|
1252 |
+
"rewards/chosen": -3.027691125869751,
|
1253 |
+
"rewards/margins": 0.6648265719413757,
|
1254 |
+
"rewards/rejected": -3.6925175189971924,
|
1255 |
+
"step": 405
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.8763024312049158,
|
1259 |
+
"grad_norm": 31.565832295867562,
|
1260 |
+
"learning_rate": 4.4761226670592066e-08,
|
1261 |
+
"logits/chosen": -0.9489310383796692,
|
1262 |
+
"logits/rejected": -0.9287575483322144,
|
1263 |
+
"logps/chosen": -1.2163779735565186,
|
1264 |
+
"logps/rejected": -1.4926642179489136,
|
1265 |
+
"loss": 1.3848,
|
1266 |
+
"rewards/accuracies": 0.6499999761581421,
|
1267 |
+
"rewards/chosen": -3.040944814682007,
|
1268 |
+
"rewards/margins": 0.6907154321670532,
|
1269 |
+
"rewards/rejected": -3.7316603660583496,
|
1270 |
+
"step": 410
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.88698904621961,
|
1274 |
+
"grad_norm": 22.344503337533215,
|
1275 |
+
"learning_rate": 3.734784976300165e-08,
|
1276 |
+
"logits/chosen": -0.92424076795578,
|
1277 |
+
"logits/rejected": -0.913791298866272,
|
1278 |
+
"logps/chosen": -1.1991280317306519,
|
1279 |
+
"logps/rejected": -1.3796842098236084,
|
1280 |
+
"loss": 1.3718,
|
1281 |
+
"rewards/accuracies": 0.6499999761581421,
|
1282 |
+
"rewards/chosen": -2.9978199005126953,
|
1283 |
+
"rewards/margins": 0.45139074325561523,
|
1284 |
+
"rewards/rejected": -3.4492106437683105,
|
1285 |
+
"step": 415
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.897675661234304,
|
1289 |
+
"grad_norm": 25.79666616123638,
|
1290 |
+
"learning_rate": 3.058153372200695e-08,
|
1291 |
+
"logits/chosen": -0.9958304166793823,
|
1292 |
+
"logits/rejected": -0.9945958256721497,
|
1293 |
+
"logps/chosen": -1.3022658824920654,
|
1294 |
+
"logps/rejected": -1.4703620672225952,
|
1295 |
+
"loss": 1.4021,
|
1296 |
+
"rewards/accuracies": 0.612500011920929,
|
1297 |
+
"rewards/chosen": -3.255664348602295,
|
1298 |
+
"rewards/margins": 0.4202408194541931,
|
1299 |
+
"rewards/rejected": -3.675905704498291,
|
1300 |
+
"step": 420
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 0.9083622762489981,
|
1304 |
+
"grad_norm": 24.252773163543072,
|
1305 |
+
"learning_rate": 2.4471741852423233e-08,
|
1306 |
+
"logits/chosen": -0.9615448713302612,
|
1307 |
+
"logits/rejected": -0.9239951968193054,
|
1308 |
+
"logps/chosen": -1.2393920421600342,
|
1309 |
+
"logps/rejected": -1.5796483755111694,
|
1310 |
+
"loss": 1.3444,
|
1311 |
+
"rewards/accuracies": 0.625,
|
1312 |
+
"rewards/chosen": -3.098480224609375,
|
1313 |
+
"rewards/margins": 0.8506406545639038,
|
1314 |
+
"rewards/rejected": -3.9491209983825684,
|
1315 |
+
"step": 425
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 0.9190488912636923,
|
1319 |
+
"grad_norm": 25.840588676616843,
|
1320 |
+
"learning_rate": 1.9027019250647036e-08,
|
1321 |
+
"logits/chosen": -0.9318382143974304,
|
1322 |
+
"logits/rejected": -0.895746111869812,
|
1323 |
+
"logps/chosen": -1.19111168384552,
|
1324 |
+
"logps/rejected": -1.4055861234664917,
|
1325 |
+
"loss": 1.3383,
|
1326 |
+
"rewards/accuracies": 0.6000000238418579,
|
1327 |
+
"rewards/chosen": -2.9777793884277344,
|
1328 |
+
"rewards/margins": 0.536186158657074,
|
1329 |
+
"rewards/rejected": -3.513965606689453,
|
1330 |
+
"step": 430
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 0.9297355062783863,
|
1334 |
+
"grad_norm": 24.38677858349731,
|
1335 |
+
"learning_rate": 1.4254980853566246e-08,
|
1336 |
+
"logits/chosen": -0.9664777517318726,
|
1337 |
+
"logits/rejected": -0.9452959299087524,
|
1338 |
+
"logps/chosen": -1.1789872646331787,
|
1339 |
+
"logps/rejected": -1.4990911483764648,
|
1340 |
+
"loss": 1.3959,
|
1341 |
+
"rewards/accuracies": 0.675000011920929,
|
1342 |
+
"rewards/chosen": -2.9474682807922363,
|
1343 |
+
"rewards/margins": 0.8002597093582153,
|
1344 |
+
"rewards/rejected": -3.747727870941162,
|
1345 |
+
"step": 435
|
1346 |
+
},
|
1347 |
+
{
|
1348 |
+
"epoch": 0.9404221212930804,
|
1349 |
+
"grad_norm": 20.846346077184034,
|
1350 |
+
"learning_rate": 1.016230078838226e-08,
|
1351 |
+
"logits/chosen": -0.9898012280464172,
|
1352 |
+
"logits/rejected": -0.9755558967590332,
|
1353 |
+
"logps/chosen": -1.205000638961792,
|
1354 |
+
"logps/rejected": -1.4142088890075684,
|
1355 |
+
"loss": 1.3646,
|
1356 |
+
"rewards/accuracies": 0.625,
|
1357 |
+
"rewards/chosen": -3.0125012397766113,
|
1358 |
+
"rewards/margins": 0.5230205059051514,
|
1359 |
+
"rewards/rejected": -3.535521984100342,
|
1360 |
+
"step": 440
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.9511087363077745,
|
1364 |
+
"grad_norm": 25.087392613196315,
|
1365 |
+
"learning_rate": 6.754703038239329e-09,
|
1366 |
+
"logits/chosen": -0.9521238207817078,
|
1367 |
+
"logits/rejected": -0.9080606698989868,
|
1368 |
+
"logps/chosen": -1.1550867557525635,
|
1369 |
+
"logps/rejected": -1.3055427074432373,
|
1370 |
+
"loss": 1.3825,
|
1371 |
+
"rewards/accuracies": 0.6625000238418579,
|
1372 |
+
"rewards/chosen": -2.887716770172119,
|
1373 |
+
"rewards/margins": 0.3761400282382965,
|
1374 |
+
"rewards/rejected": -3.263856887817383,
|
1375 |
+
"step": 445
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.9617953513224686,
|
1379 |
+
"grad_norm": 24.725896653899223,
|
1380 |
+
"learning_rate": 4.036953436716895e-09,
|
1381 |
+
"logits/chosen": -0.9332659840583801,
|
1382 |
+
"logits/rejected": -0.9464728236198425,
|
1383 |
+
"logps/chosen": -1.2779486179351807,
|
1384 |
+
"logps/rejected": -1.5308974981307983,
|
1385 |
+
"loss": 1.3408,
|
1386 |
+
"rewards/accuracies": 0.6625000238418579,
|
1387 |
+
"rewards/chosen": -3.194871425628662,
|
1388 |
+
"rewards/margins": 0.6323727369308472,
|
1389 |
+
"rewards/rejected": -3.8272438049316406,
|
1390 |
+
"step": 450
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 0.9724819663371627,
|
1394 |
+
"grad_norm": 28.975077371611935,
|
1395 |
+
"learning_rate": 2.0128530023804656e-09,
|
1396 |
+
"logits/chosen": -0.9732203483581543,
|
1397 |
+
"logits/rejected": -0.9457721710205078,
|
1398 |
+
"logps/chosen": -1.345735788345337,
|
1399 |
+
"logps/rejected": -1.4330954551696777,
|
1400 |
+
"loss": 1.4589,
|
1401 |
+
"rewards/accuracies": 0.5249999761581421,
|
1402 |
+
"rewards/chosen": -3.3643393516540527,
|
1403 |
+
"rewards/margins": 0.21839912235736847,
|
1404 |
+
"rewards/rejected": -3.5827383995056152,
|
1405 |
+
"step": 455
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 0.9831685813518568,
|
1409 |
+
"grad_norm": 26.785266092328502,
|
1410 |
+
"learning_rate": 6.852326227130833e-10,
|
1411 |
+
"logits/chosen": -0.9476199150085449,
|
1412 |
+
"logits/rejected": -0.9895550608634949,
|
1413 |
+
"logps/chosen": -1.4385395050048828,
|
1414 |
+
"logps/rejected": -1.8012183904647827,
|
1415 |
+
"loss": 1.3759,
|
1416 |
+
"rewards/accuracies": 0.6499999761581421,
|
1417 |
+
"rewards/chosen": -3.596348524093628,
|
1418 |
+
"rewards/margins": 0.906697154045105,
|
1419 |
+
"rewards/rejected": -4.503045558929443,
|
1420 |
+
"step": 460
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.9938551963665508,
|
1424 |
+
"grad_norm": 25.28595563871724,
|
1425 |
+
"learning_rate": 5.594909486328348e-11,
|
1426 |
+
"logits/chosen": -1.0385969877243042,
|
1427 |
+
"logits/rejected": -0.9505317807197571,
|
1428 |
+
"logps/chosen": -1.1505335569381714,
|
1429 |
+
"logps/rejected": -1.4205496311187744,
|
1430 |
+
"loss": 1.3506,
|
1431 |
+
"rewards/accuracies": 0.6625000238418579,
|
1432 |
+
"rewards/chosen": -2.8763339519500732,
|
1433 |
+
"rewards/margins": 0.6750401258468628,
|
1434 |
+
"rewards/rejected": -3.5513739585876465,
|
1435 |
+
"step": 465
|
1436 |
+
},
|
1437 |
+
{
|
1438 |
+
"epoch": 0.9981298423724285,
|
1439 |
+
"step": 467,
|
1440 |
+
"total_flos": 0.0,
|
1441 |
+
"train_loss": 1.4758259897824273,
|
1442 |
+
"train_runtime": 7808.6202,
|
1443 |
+
"train_samples_per_second": 7.668,
|
1444 |
+
"train_steps_per_second": 0.06
|
1445 |
+
}
|
1446 |
+
],
|
1447 |
+
"logging_steps": 5,
|
1448 |
+
"max_steps": 467,
|
1449 |
+
"num_input_tokens_seen": 0,
|
1450 |
+
"num_train_epochs": 1,
|
1451 |
+
"save_steps": 1000000,
|
1452 |
+
"stateful_callbacks": {
|
1453 |
+
"TrainerControl": {
|
1454 |
+
"args": {
|
1455 |
+
"should_epoch_stop": false,
|
1456 |
+
"should_evaluate": false,
|
1457 |
+
"should_log": false,
|
1458 |
+
"should_save": false,
|
1459 |
+
"should_training_stop": false
|
1460 |
+
},
|
1461 |
+
"attributes": {}
|
1462 |
+
}
|
1463 |
+
},
|
1464 |
+
"total_flos": 0.0,
|
1465 |
+
"train_batch_size": 2,
|
1466 |
+
"trial_name": null,
|
1467 |
+
"trial_params": null
|
1468 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ebebe2ce8ef8642ab75204e69ab3d4b82135e2c91f2622f1db6a72ec3e674d8
|
3 |
+
size 6840
|