Upload folder using huggingface_hub
Browse files- README.md +75 -0
- all_results.json +22 -0
- config.json +39 -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 +1588 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: llama3.1
|
4 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
5 |
+
tags:
|
6 |
+
- alignment-handbook
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- simonycl/llama-3.1-metamath_subset_65k-annotate
|
10 |
+
model-index:
|
11 |
+
- name: llama-3.1-8b-instruct-metamath-agg-judge
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# llama-3.1-8b-instruct-metamath-agg-judge
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the simonycl/llama-3.1-metamath_subset_65k-annotate dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.5772
|
23 |
+
- Rewards/chosen: -1.7008
|
24 |
+
- Rewards/rejected: -2.0716
|
25 |
+
- Rewards/accuracies: 0.6794
|
26 |
+
- Rewards/margins: 0.3707
|
27 |
+
- Logps/rejected: -481.0541
|
28 |
+
- Logps/chosen: -432.9763
|
29 |
+
- Logits/rejected: -2.4284
|
30 |
+
- Logits/chosen: -2.5593
|
31 |
+
|
32 |
+
## Model description
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Intended uses & limitations
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training and evaluation data
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training procedure
|
45 |
+
|
46 |
+
### Training hyperparameters
|
47 |
+
|
48 |
+
The following hyperparameters were used during training:
|
49 |
+
- learning_rate: 5e-07
|
50 |
+
- train_batch_size: 2
|
51 |
+
- eval_batch_size: 4
|
52 |
+
- seed: 42
|
53 |
+
- distributed_type: multi-GPU
|
54 |
+
- num_devices: 4
|
55 |
+
- gradient_accumulation_steps: 16
|
56 |
+
- total_train_batch_size: 128
|
57 |
+
- total_eval_batch_size: 16
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: cosine
|
60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
61 |
+
- num_epochs: 1
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
66 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
67 |
+
| 0.347 | 0.7887 | 400 | 0.5772 | -1.7008 | -2.0716 | 0.6794 | 0.3707 | -481.0541 | -432.9763 | -2.4284 | -2.5593 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.44.2
|
73 |
+
- Pytorch 2.4.0+cu121
|
74 |
+
- Datasets 2.21.0
|
75 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.999630314232902,
|
3 |
+
"eval_logits/chosen": -2.554856538772583,
|
4 |
+
"eval_logits/rejected": -2.423921585083008,
|
5 |
+
"eval_logps/chosen": -432.22442626953125,
|
6 |
+
"eval_logps/rejected": -477.8772888183594,
|
7 |
+
"eval_loss": 0.5821850299835205,
|
8 |
+
"eval_rewards/accuracies": 0.6875,
|
9 |
+
"eval_rewards/chosen": -1.6933226585388184,
|
10 |
+
"eval_rewards/margins": 0.3464769423007965,
|
11 |
+
"eval_rewards/rejected": -2.039799690246582,
|
12 |
+
"eval_runtime": 322.3528,
|
13 |
+
"eval_samples": 1976,
|
14 |
+
"eval_samples_per_second": 6.13,
|
15 |
+
"eval_steps_per_second": 0.385,
|
16 |
+
"total_flos": 0.0,
|
17 |
+
"train_loss": 0.41502543125867375,
|
18 |
+
"train_runtime": 18234.8908,
|
19 |
+
"train_samples": 64919,
|
20 |
+
"train_samples_per_second": 3.56,
|
21 |
+
"train_steps_per_second": 0.028
|
22 |
+
}
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 4096,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 14336,
|
18 |
+
"max_position_embeddings": 131072,
|
19 |
+
"mlp_bias": false,
|
20 |
+
"model_type": "llama",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 32,
|
23 |
+
"num_key_value_heads": 8,
|
24 |
+
"pretraining_tp": 1,
|
25 |
+
"rms_norm_eps": 1e-05,
|
26 |
+
"rope_scaling": {
|
27 |
+
"factor": 8.0,
|
28 |
+
"high_freq_factor": 4.0,
|
29 |
+
"low_freq_factor": 1.0,
|
30 |
+
"original_max_position_embeddings": 8192,
|
31 |
+
"rope_type": "llama3"
|
32 |
+
},
|
33 |
+
"rope_theta": 500000.0,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "bfloat16",
|
36 |
+
"transformers_version": "4.44.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 128256
|
39 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.999630314232902,
|
3 |
+
"eval_logits/chosen": -2.554856538772583,
|
4 |
+
"eval_logits/rejected": -2.423921585083008,
|
5 |
+
"eval_logps/chosen": -432.22442626953125,
|
6 |
+
"eval_logps/rejected": -477.8772888183594,
|
7 |
+
"eval_loss": 0.5821850299835205,
|
8 |
+
"eval_rewards/accuracies": 0.6875,
|
9 |
+
"eval_rewards/chosen": -1.6933226585388184,
|
10 |
+
"eval_rewards/margins": 0.3464769423007965,
|
11 |
+
"eval_rewards/rejected": -2.039799690246582,
|
12 |
+
"eval_runtime": 322.3528,
|
13 |
+
"eval_samples": 1976,
|
14 |
+
"eval_samples_per_second": 6.13,
|
15 |
+
"eval_steps_per_second": 0.385
|
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 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.44.2"
|
12 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:257b87de71335e55f6467f1ea6f5bf70736f32dbfddd5ad602dfcbf6a010c2fe
|
3 |
+
size 4976698672
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66170815fefccf59dfd2e3b7326393be25ad39e30022ea2843b2a30668617219
|
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:f69a3fb760a22729efb1d5441f3429f2aba4c0479abf1884a189caa31c43e935
|
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:a23b5a9b3ff4eb07322ab970974ed792ca8348e57c85af61e51d6a7bd53a4088
|
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": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
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": 0.999630314232902,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.41502543125867375,
|
5 |
+
"train_runtime": 18234.8908,
|
6 |
+
"train_samples": 64919,
|
7 |
+
"train_samples_per_second": 3.56,
|
8 |
+
"train_steps_per_second": 0.028
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1588 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.999630314232902,
|
5 |
+
"eval_steps": 400,
|
6 |
+
"global_step": 507,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.001971657424522489,
|
13 |
+
"grad_norm": 4.641391669893979,
|
14 |
+
"learning_rate": 9.803921568627451e-09,
|
15 |
+
"logits/chosen": -1.8306132555007935,
|
16 |
+
"logits/rejected": -1.2712628841400146,
|
17 |
+
"logps/chosen": -217.9743194580078,
|
18 |
+
"logps/rejected": -312.2440185546875,
|
19 |
+
"loss": 0.6931,
|
20 |
+
"rewards/accuracies": 0.0,
|
21 |
+
"rewards/chosen": 0.0,
|
22 |
+
"rewards/margins": 0.0,
|
23 |
+
"rewards/rejected": 0.0,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.009858287122612447,
|
28 |
+
"grad_norm": 3.881553151172807,
|
29 |
+
"learning_rate": 4.901960784313725e-08,
|
30 |
+
"logits/chosen": -1.3956289291381836,
|
31 |
+
"logits/rejected": -1.324476718902588,
|
32 |
+
"logps/chosen": -213.20277404785156,
|
33 |
+
"logps/rejected": -243.072509765625,
|
34 |
+
"loss": 0.6932,
|
35 |
+
"rewards/accuracies": 0.3125,
|
36 |
+
"rewards/chosen": 9.495137783233076e-05,
|
37 |
+
"rewards/margins": -0.00030715527827851474,
|
38 |
+
"rewards/rejected": 0.0004021066124550998,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.019716574245224893,
|
43 |
+
"grad_norm": 4.055647051577517,
|
44 |
+
"learning_rate": 9.80392156862745e-08,
|
45 |
+
"logits/chosen": -1.464820146560669,
|
46 |
+
"logits/rejected": -1.329075813293457,
|
47 |
+
"logps/chosen": -216.189697265625,
|
48 |
+
"logps/rejected": -249.85464477539062,
|
49 |
+
"loss": 0.6933,
|
50 |
+
"rewards/accuracies": 0.4124999940395355,
|
51 |
+
"rewards/chosen": 0.0014236138667911291,
|
52 |
+
"rewards/margins": -0.0008448967710137367,
|
53 |
+
"rewards/rejected": 0.002268511103466153,
|
54 |
+
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.029574861367837338,
|
58 |
+
"grad_norm": 3.8004259300545313,
|
59 |
+
"learning_rate": 1.4705882352941175e-07,
|
60 |
+
"logits/chosen": -1.590954065322876,
|
61 |
+
"logits/rejected": -1.3920761346817017,
|
62 |
+
"logps/chosen": -227.84024047851562,
|
63 |
+
"logps/rejected": -267.3565368652344,
|
64 |
+
"loss": 0.6928,
|
65 |
+
"rewards/accuracies": 0.518750011920929,
|
66 |
+
"rewards/chosen": 0.0014651073142886162,
|
67 |
+
"rewards/margins": 0.0005061920965090394,
|
68 |
+
"rewards/rejected": 0.0009589152177795768,
|
69 |
+
"step": 15
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.039433148490449786,
|
73 |
+
"grad_norm": 4.362970881343374,
|
74 |
+
"learning_rate": 1.96078431372549e-07,
|
75 |
+
"logits/chosen": -1.4077281951904297,
|
76 |
+
"logits/rejected": -1.438763976097107,
|
77 |
+
"logps/chosen": -216.7683563232422,
|
78 |
+
"logps/rejected": -241.71524047851562,
|
79 |
+
"loss": 0.6921,
|
80 |
+
"rewards/accuracies": 0.53125,
|
81 |
+
"rewards/chosen": -0.0071268146857619286,
|
82 |
+
"rewards/margins": 0.002329364651814103,
|
83 |
+
"rewards/rejected": -0.009456178173422813,
|
84 |
+
"step": 20
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.04929143561306223,
|
88 |
+
"grad_norm": 3.68850001761437,
|
89 |
+
"learning_rate": 2.4509803921568627e-07,
|
90 |
+
"logits/chosen": -1.368187427520752,
|
91 |
+
"logits/rejected": -1.3394204378128052,
|
92 |
+
"logps/chosen": -225.8297119140625,
|
93 |
+
"logps/rejected": -254.41439819335938,
|
94 |
+
"loss": 0.6899,
|
95 |
+
"rewards/accuracies": 0.643750011920929,
|
96 |
+
"rewards/chosen": -0.015500446781516075,
|
97 |
+
"rewards/margins": 0.005922852084040642,
|
98 |
+
"rewards/rejected": -0.021423298865556717,
|
99 |
+
"step": 25
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.059149722735674676,
|
103 |
+
"grad_norm": 4.847654340669893,
|
104 |
+
"learning_rate": 2.941176470588235e-07,
|
105 |
+
"logits/chosen": -1.4356650114059448,
|
106 |
+
"logits/rejected": -1.2754924297332764,
|
107 |
+
"logps/chosen": -221.5808563232422,
|
108 |
+
"logps/rejected": -255.44918823242188,
|
109 |
+
"loss": 0.6856,
|
110 |
+
"rewards/accuracies": 0.699999988079071,
|
111 |
+
"rewards/chosen": -0.02648136578500271,
|
112 |
+
"rewards/margins": 0.015200227499008179,
|
113 |
+
"rewards/rejected": -0.04168159142136574,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.06900800985828712,
|
118 |
+
"grad_norm": 6.653348898638824,
|
119 |
+
"learning_rate": 3.431372549019608e-07,
|
120 |
+
"logits/chosen": -1.347893476486206,
|
121 |
+
"logits/rejected": -1.2126632928848267,
|
122 |
+
"logps/chosen": -217.4748992919922,
|
123 |
+
"logps/rejected": -253.11001586914062,
|
124 |
+
"loss": 0.6716,
|
125 |
+
"rewards/accuracies": 0.699999988079071,
|
126 |
+
"rewards/chosen": -0.04387308284640312,
|
127 |
+
"rewards/margins": 0.04525812342762947,
|
128 |
+
"rewards/rejected": -0.08913120627403259,
|
129 |
+
"step": 35
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.07886629698089957,
|
133 |
+
"grad_norm": 6.964114197906881,
|
134 |
+
"learning_rate": 3.92156862745098e-07,
|
135 |
+
"logits/chosen": -1.4753751754760742,
|
136 |
+
"logits/rejected": -1.3836042881011963,
|
137 |
+
"logps/chosen": -233.50979614257812,
|
138 |
+
"logps/rejected": -270.6595458984375,
|
139 |
+
"loss": 0.6487,
|
140 |
+
"rewards/accuracies": 0.71875,
|
141 |
+
"rewards/chosen": -0.09956349432468414,
|
142 |
+
"rewards/margins": 0.10375545918941498,
|
143 |
+
"rewards/rejected": -0.2033189833164215,
|
144 |
+
"step": 40
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.08872458410351201,
|
148 |
+
"grad_norm": 15.546171706823465,
|
149 |
+
"learning_rate": 4.4117647058823526e-07,
|
150 |
+
"logits/chosen": -1.4908992052078247,
|
151 |
+
"logits/rejected": -1.4922513961791992,
|
152 |
+
"logps/chosen": -260.85107421875,
|
153 |
+
"logps/rejected": -310.8064270019531,
|
154 |
+
"loss": 0.6302,
|
155 |
+
"rewards/accuracies": 0.6187499761581421,
|
156 |
+
"rewards/chosen": -0.39361271262168884,
|
157 |
+
"rewards/margins": 0.24461090564727783,
|
158 |
+
"rewards/rejected": -0.6382235884666443,
|
159 |
+
"step": 45
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.09858287122612445,
|
163 |
+
"grad_norm": 7.346421533742723,
|
164 |
+
"learning_rate": 4.901960784313725e-07,
|
165 |
+
"logits/chosen": -1.8035519123077393,
|
166 |
+
"logits/rejected": -1.7488648891448975,
|
167 |
+
"logps/chosen": -280.26544189453125,
|
168 |
+
"logps/rejected": -384.37969970703125,
|
169 |
+
"loss": 0.6188,
|
170 |
+
"rewards/accuracies": 0.65625,
|
171 |
+
"rewards/chosen": -0.6396178007125854,
|
172 |
+
"rewards/margins": 0.6693423986434937,
|
173 |
+
"rewards/rejected": -1.308960199356079,
|
174 |
+
"step": 50
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.10844115834873691,
|
178 |
+
"grad_norm": 6.928842609814235,
|
179 |
+
"learning_rate": 4.999050767562379e-07,
|
180 |
+
"logits/chosen": -1.500614881515503,
|
181 |
+
"logits/rejected": -1.514692783355713,
|
182 |
+
"logps/chosen": -259.22607421875,
|
183 |
+
"logps/rejected": -324.70147705078125,
|
184 |
+
"loss": 0.5905,
|
185 |
+
"rewards/accuracies": 0.668749988079071,
|
186 |
+
"rewards/chosen": -0.4987005591392517,
|
187 |
+
"rewards/margins": 0.39352884888648987,
|
188 |
+
"rewards/rejected": -0.8922293782234192,
|
189 |
+
"step": 55
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.11829944547134935,
|
193 |
+
"grad_norm": 5.183419407454259,
|
194 |
+
"learning_rate": 4.99519574616467e-07,
|
195 |
+
"logits/chosen": -1.6389617919921875,
|
196 |
+
"logits/rejected": -1.5824358463287354,
|
197 |
+
"logps/chosen": -283.13287353515625,
|
198 |
+
"logps/rejected": -382.1869201660156,
|
199 |
+
"loss": 0.6371,
|
200 |
+
"rewards/accuracies": 0.699999988079071,
|
201 |
+
"rewards/chosen": -0.7059253454208374,
|
202 |
+
"rewards/margins": 0.6277474164962769,
|
203 |
+
"rewards/rejected": -1.3336727619171143,
|
204 |
+
"step": 60
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.1281577325939618,
|
208 |
+
"grad_norm": 9.230406347476531,
|
209 |
+
"learning_rate": 4.988380179235842e-07,
|
210 |
+
"logits/chosen": -1.6305882930755615,
|
211 |
+
"logits/rejected": -1.6462520360946655,
|
212 |
+
"logps/chosen": -256.4553527832031,
|
213 |
+
"logps/rejected": -347.4143371582031,
|
214 |
+
"loss": 0.5805,
|
215 |
+
"rewards/accuracies": 0.793749988079071,
|
216 |
+
"rewards/chosen": -0.49059420824050903,
|
217 |
+
"rewards/margins": 0.5759122371673584,
|
218 |
+
"rewards/rejected": -1.0665065050125122,
|
219 |
+
"step": 65
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.13801601971657423,
|
223 |
+
"grad_norm": 9.206165908014777,
|
224 |
+
"learning_rate": 4.978612153434526e-07,
|
225 |
+
"logits/chosen": -1.7708934545516968,
|
226 |
+
"logits/rejected": -1.7579914331436157,
|
227 |
+
"logps/chosen": -285.9685974121094,
|
228 |
+
"logps/rejected": -370.2804260253906,
|
229 |
+
"loss": 0.5983,
|
230 |
+
"rewards/accuracies": 0.7749999761581421,
|
231 |
+
"rewards/chosen": -0.7101233601570129,
|
232 |
+
"rewards/margins": 0.5043641328811646,
|
233 |
+
"rewards/rejected": -1.2144873142242432,
|
234 |
+
"step": 70
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.1478743068391867,
|
238 |
+
"grad_norm": 7.723809446488398,
|
239 |
+
"learning_rate": 4.965903258506806e-07,
|
240 |
+
"logits/chosen": -1.8401196002960205,
|
241 |
+
"logits/rejected": -1.7219253778457642,
|
242 |
+
"logps/chosen": -289.95068359375,
|
243 |
+
"logps/rejected": -389.30889892578125,
|
244 |
+
"loss": 0.5573,
|
245 |
+
"rewards/accuracies": 0.8125,
|
246 |
+
"rewards/chosen": -0.7532116174697876,
|
247 |
+
"rewards/margins": 0.6191812753677368,
|
248 |
+
"rewards/rejected": -1.372393012046814,
|
249 |
+
"step": 75
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.15773259396179914,
|
253 |
+
"grad_norm": 10.916878987391435,
|
254 |
+
"learning_rate": 4.950268573535011e-07,
|
255 |
+
"logits/chosen": -2.015733480453491,
|
256 |
+
"logits/rejected": -1.8680551052093506,
|
257 |
+
"logps/chosen": -325.2226257324219,
|
258 |
+
"logps/rejected": -428.49066162109375,
|
259 |
+
"loss": 0.5476,
|
260 |
+
"rewards/accuracies": 0.793749988079071,
|
261 |
+
"rewards/chosen": -1.0503952503204346,
|
262 |
+
"rewards/margins": 0.6346156597137451,
|
263 |
+
"rewards/rejected": -1.6850106716156006,
|
264 |
+
"step": 80
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.16759088108441159,
|
268 |
+
"grad_norm": 13.425184009136764,
|
269 |
+
"learning_rate": 4.93172664904641e-07,
|
270 |
+
"logits/chosen": -1.8795242309570312,
|
271 |
+
"logits/rejected": -1.913556694984436,
|
272 |
+
"logps/chosen": -317.763916015625,
|
273 |
+
"logps/rejected": -424.55450439453125,
|
274 |
+
"loss": 0.5141,
|
275 |
+
"rewards/accuracies": 0.706250011920929,
|
276 |
+
"rewards/chosen": -1.1219675540924072,
|
277 |
+
"rewards/margins": 0.7599529027938843,
|
278 |
+
"rewards/rejected": -1.881920576095581,
|
279 |
+
"step": 85
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.17744916820702403,
|
283 |
+
"grad_norm": 15.954473082571113,
|
284 |
+
"learning_rate": 4.910299485003033e-07,
|
285 |
+
"logits/chosen": -2.1529054641723633,
|
286 |
+
"logits/rejected": -2.0844523906707764,
|
287 |
+
"logps/chosen": -424.82891845703125,
|
288 |
+
"logps/rejected": -543.7278442382812,
|
289 |
+
"loss": 0.5199,
|
290 |
+
"rewards/accuracies": 0.793749988079071,
|
291 |
+
"rewards/chosen": -2.0633959770202637,
|
292 |
+
"rewards/margins": 0.886804461479187,
|
293 |
+
"rewards/rejected": -2.950200319290161,
|
294 |
+
"step": 90
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.18730745532963647,
|
298 |
+
"grad_norm": 17.544754679380226,
|
299 |
+
"learning_rate": 4.886012504698769e-07,
|
300 |
+
"logits/chosen": -1.882367730140686,
|
301 |
+
"logits/rejected": -1.9553489685058594,
|
302 |
+
"logps/chosen": -406.643310546875,
|
303 |
+
"logps/rejected": -471.86553955078125,
|
304 |
+
"loss": 0.5386,
|
305 |
+
"rewards/accuracies": 0.706250011920929,
|
306 |
+
"rewards/chosen": -1.862217664718628,
|
307 |
+
"rewards/margins": 0.4628971219062805,
|
308 |
+
"rewards/rejected": -2.3251149654388428,
|
309 |
+
"step": 95
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.1971657424522489,
|
313 |
+
"grad_norm": 13.476927825101471,
|
314 |
+
"learning_rate": 4.858894524594652e-07,
|
315 |
+
"logits/chosen": -2.1455252170562744,
|
316 |
+
"logits/rejected": -2.0651824474334717,
|
317 |
+
"logps/chosen": -392.774169921875,
|
318 |
+
"logps/rejected": -530.4494018554688,
|
319 |
+
"loss": 0.4917,
|
320 |
+
"rewards/accuracies": 0.800000011920929,
|
321 |
+
"rewards/chosen": -1.8280452489852905,
|
322 |
+
"rewards/margins": 0.902090847492218,
|
323 |
+
"rewards/rejected": -2.7301361560821533,
|
324 |
+
"step": 100
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.20702402957486138,
|
328 |
+
"grad_norm": 23.287769508042025,
|
329 |
+
"learning_rate": 4.828977720128198e-07,
|
330 |
+
"logits/chosen": -1.9681150913238525,
|
331 |
+
"logits/rejected": -1.9559170007705688,
|
332 |
+
"logps/chosen": -431.6632385253906,
|
333 |
+
"logps/rejected": -570.6896362304688,
|
334 |
+
"loss": 0.4834,
|
335 |
+
"rewards/accuracies": 0.768750011920929,
|
336 |
+
"rewards/chosen": -2.2001523971557617,
|
337 |
+
"rewards/margins": 1.0563952922821045,
|
338 |
+
"rewards/rejected": -3.2565484046936035,
|
339 |
+
"step": 105
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.21688231669747382,
|
343 |
+
"grad_norm": 23.293354005808915,
|
344 |
+
"learning_rate": 4.796297587537285e-07,
|
345 |
+
"logits/chosen": -2.096468448638916,
|
346 |
+
"logits/rejected": -1.9595563411712646,
|
347 |
+
"logps/chosen": -497.79400634765625,
|
348 |
+
"logps/rejected": -643.2481689453125,
|
349 |
+
"loss": 0.483,
|
350 |
+
"rewards/accuracies": 0.762499988079071,
|
351 |
+
"rewards/chosen": -2.711547374725342,
|
352 |
+
"rewards/margins": 1.0744675397872925,
|
353 |
+
"rewards/rejected": -3.7860145568847656,
|
354 |
+
"step": 110
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.22674060382008626,
|
358 |
+
"grad_norm": 16.815054431474035,
|
359 |
+
"learning_rate": 4.760892901743944e-07,
|
360 |
+
"logits/chosen": -2.1025643348693848,
|
361 |
+
"logits/rejected": -2.091360092163086,
|
362 |
+
"logps/chosen": -450.98028564453125,
|
363 |
+
"logps/rejected": -575.75439453125,
|
364 |
+
"loss": 0.4619,
|
365 |
+
"rewards/accuracies": 0.75,
|
366 |
+
"rewards/chosen": -2.345163106918335,
|
367 |
+
"rewards/margins": 1.00288987159729,
|
368 |
+
"rewards/rejected": -3.348052978515625,
|
369 |
+
"step": 115
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.2365988909426987,
|
373 |
+
"grad_norm": 18.736725526597898,
|
374 |
+
"learning_rate": 4.7228056703479626e-07,
|
375 |
+
"logits/chosen": -1.9844331741333008,
|
376 |
+
"logits/rejected": -2.1090264320373535,
|
377 |
+
"logps/chosen": -505.28509521484375,
|
378 |
+
"logps/rejected": -649.0353393554688,
|
379 |
+
"loss": 0.4298,
|
380 |
+
"rewards/accuracies": 0.800000011920929,
|
381 |
+
"rewards/chosen": -2.8585612773895264,
|
382 |
+
"rewards/margins": 1.334934949874878,
|
383 |
+
"rewards/rejected": -4.193496227264404,
|
384 |
+
"step": 120
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.24645717806531114,
|
388 |
+
"grad_norm": 29.41530429769772,
|
389 |
+
"learning_rate": 4.6820810837849535e-07,
|
390 |
+
"logits/chosen": -1.9075158834457397,
|
391 |
+
"logits/rejected": -1.952182412147522,
|
392 |
+
"logps/chosen": -443.2312927246094,
|
393 |
+
"logps/rejected": -584.6851196289062,
|
394 |
+
"loss": 0.4647,
|
395 |
+
"rewards/accuracies": 0.800000011920929,
|
396 |
+
"rewards/chosen": -2.3362534046173096,
|
397 |
+
"rewards/margins": 1.1353000402450562,
|
398 |
+
"rewards/rejected": -3.471553087234497,
|
399 |
+
"step": 125
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.2563154651879236,
|
403 |
+
"grad_norm": 28.047847807749136,
|
404 |
+
"learning_rate": 4.63876746170797e-07,
|
405 |
+
"logits/chosen": -1.9407484531402588,
|
406 |
+
"logits/rejected": -1.9303442239761353,
|
407 |
+
"logps/chosen": -533.4217529296875,
|
408 |
+
"logps/rejected": -713.83740234375,
|
409 |
+
"loss": 0.4145,
|
410 |
+
"rewards/accuracies": 0.7875000238418579,
|
411 |
+
"rewards/chosen": -3.180513858795166,
|
412 |
+
"rewards/margins": 1.4735915660858154,
|
413 |
+
"rewards/rejected": -4.6541056632995605,
|
414 |
+
"step": 130
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.266173752310536,
|
418 |
+
"grad_norm": 18.58702447039976,
|
419 |
+
"learning_rate": 4.592916195656321e-07,
|
420 |
+
"logits/chosen": -2.0613300800323486,
|
421 |
+
"logits/rejected": -1.971636414527893,
|
422 |
+
"logps/chosen": -469.5445251464844,
|
423 |
+
"logps/rejected": -650.7494506835938,
|
424 |
+
"loss": 0.4332,
|
425 |
+
"rewards/accuracies": 0.800000011920929,
|
426 |
+
"rewards/chosen": -2.464566946029663,
|
427 |
+
"rewards/margins": 1.3873087167739868,
|
428 |
+
"rewards/rejected": -3.8518757820129395,
|
429 |
+
"step": 135
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.27603203943314847,
|
433 |
+
"grad_norm": 43.43885248557689,
|
434 |
+
"learning_rate": 4.544581688079602e-07,
|
435 |
+
"logits/chosen": -1.8543685674667358,
|
436 |
+
"logits/rejected": -1.960680365562439,
|
437 |
+
"logps/chosen": -499.29150390625,
|
438 |
+
"logps/rejected": -682.0525512695312,
|
439 |
+
"loss": 0.4126,
|
440 |
+
"rewards/accuracies": 0.8062499761581421,
|
441 |
+
"rewards/chosen": -2.7792274951934814,
|
442 |
+
"rewards/margins": 1.672224998474121,
|
443 |
+
"rewards/rejected": -4.45145320892334,
|
444 |
+
"step": 140
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.2858903265557609,
|
448 |
+
"grad_norm": 25.06136332684734,
|
449 |
+
"learning_rate": 4.493821287789272e-07,
|
450 |
+
"logits/chosen": -2.0097248554229736,
|
451 |
+
"logits/rejected": -2.05975604057312,
|
452 |
+
"logps/chosen": -622.1812744140625,
|
453 |
+
"logps/rejected": -857.2575073242188,
|
454 |
+
"loss": 0.4115,
|
455 |
+
"rewards/accuracies": 0.7562500238418579,
|
456 |
+
"rewards/chosen": -4.092832565307617,
|
457 |
+
"rewards/margins": 1.9847408533096313,
|
458 |
+
"rewards/rejected": -6.077573299407959,
|
459 |
+
"step": 145
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.2957486136783734,
|
463 |
+
"grad_norm": 23.62970192824471,
|
464 |
+
"learning_rate": 4.4406952219143934e-07,
|
465 |
+
"logits/chosen": -1.9738140106201172,
|
466 |
+
"logits/rejected": -1.8969192504882812,
|
467 |
+
"logps/chosen": -505.8863220214844,
|
468 |
+
"logps/rejected": -674.2682495117188,
|
469 |
+
"loss": 0.4551,
|
470 |
+
"rewards/accuracies": 0.8125,
|
471 |
+
"rewards/chosen": -2.9365577697753906,
|
472 |
+
"rewards/margins": 1.3609775304794312,
|
473 |
+
"rewards/rejected": -4.297535419464111,
|
474 |
+
"step": 150
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.30560690080098585,
|
478 |
+
"grad_norm": 36.928411112871835,
|
479 |
+
"learning_rate": 4.38526652444224e-07,
|
480 |
+
"logits/chosen": -1.9676620960235596,
|
481 |
+
"logits/rejected": -1.9335002899169922,
|
482 |
+
"logps/chosen": -526.3443603515625,
|
483 |
+
"logps/rejected": -675.4140625,
|
484 |
+
"loss": 0.4316,
|
485 |
+
"rewards/accuracies": 0.7875000238418579,
|
486 |
+
"rewards/chosen": -3.1301074028015137,
|
487 |
+
"rewards/margins": 1.176997423171997,
|
488 |
+
"rewards/rejected": -4.30710506439209,
|
489 |
+
"step": 155
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.3154651879235983,
|
493 |
+
"grad_norm": 35.737507476172006,
|
494 |
+
"learning_rate": 4.3276009614285824e-07,
|
495 |
+
"logits/chosen": -2.08416748046875,
|
496 |
+
"logits/rejected": -2.0275375843048096,
|
497 |
+
"logps/chosen": -547.2161254882812,
|
498 |
+
"logps/rejected": -734.8326416015625,
|
499 |
+
"loss": 0.4361,
|
500 |
+
"rewards/accuracies": 0.8187500238418579,
|
501 |
+
"rewards/chosen": -3.296079635620117,
|
502 |
+
"rewards/margins": 1.489527940750122,
|
503 |
+
"rewards/rejected": -4.78560733795166,
|
504 |
+
"step": 160
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.32532347504621073,
|
508 |
+
"grad_norm": 25.388193696092944,
|
509 |
+
"learning_rate": 4.2677669529663686e-07,
|
510 |
+
"logits/chosen": -1.8684972524642944,
|
511 |
+
"logits/rejected": -1.98639714717865,
|
512 |
+
"logps/chosen": -492.37518310546875,
|
513 |
+
"logps/rejected": -663.5337524414062,
|
514 |
+
"loss": 0.3908,
|
515 |
+
"rewards/accuracies": 0.793749988079071,
|
516 |
+
"rewards/chosen": -2.736380100250244,
|
517 |
+
"rewards/margins": 1.5142922401428223,
|
518 |
+
"rewards/rejected": -4.250672340393066,
|
519 |
+
"step": 165
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.33518176216882317,
|
523 |
+
"grad_norm": 26.163756341836816,
|
524 |
+
"learning_rate": 4.2058354920054043e-07,
|
525 |
+
"logits/chosen": -2.0008151531219482,
|
526 |
+
"logits/rejected": -2.1545004844665527,
|
527 |
+
"logps/chosen": -558.0103759765625,
|
528 |
+
"logps/rejected": -783.8531494140625,
|
529 |
+
"loss": 0.3635,
|
530 |
+
"rewards/accuracies": 0.875,
|
531 |
+
"rewards/chosen": -3.2563652992248535,
|
532 |
+
"rewards/margins": 2.108079433441162,
|
533 |
+
"rewards/rejected": -5.364445209503174,
|
534 |
+
"step": 170
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.3450400492914356,
|
538 |
+
"grad_norm": 20.146161792615796,
|
539 |
+
"learning_rate": 4.141880060119336e-07,
|
540 |
+
"logits/chosen": -2.138545036315918,
|
541 |
+
"logits/rejected": -2.1449027061462402,
|
542 |
+
"logps/chosen": -580.8723754882812,
|
543 |
+
"logps/rejected": -799.7882690429688,
|
544 |
+
"loss": 0.4178,
|
545 |
+
"rewards/accuracies": 0.8187500238418579,
|
546 |
+
"rewards/chosen": -3.6856274604797363,
|
547 |
+
"rewards/margins": 1.9810088872909546,
|
548 |
+
"rewards/rejected": -5.6666364669799805,
|
549 |
+
"step": 175
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.35489833641404805,
|
553 |
+
"grad_norm": 20.25459576341684,
|
554 |
+
"learning_rate": 4.0759765403198877e-07,
|
555 |
+
"logits/chosen": -1.9771722555160522,
|
556 |
+
"logits/rejected": -1.9267823696136475,
|
557 |
+
"logps/chosen": -448.6309509277344,
|
558 |
+
"logps/rejected": -687.6984252929688,
|
559 |
+
"loss": 0.3941,
|
560 |
+
"rewards/accuracies": 0.831250011920929,
|
561 |
+
"rewards/chosen": -2.361887216567993,
|
562 |
+
"rewards/margins": 1.849793791770935,
|
563 |
+
"rewards/rejected": -4.211681365966797,
|
564 |
+
"step": 180
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.3647566235366605,
|
568 |
+
"grad_norm": 23.732608340062967,
|
569 |
+
"learning_rate": 4.008203127021797e-07,
|
570 |
+
"logits/chosen": -2.0232439041137695,
|
571 |
+
"logits/rejected": -2.0282373428344727,
|
572 |
+
"logps/chosen": -536.0543212890625,
|
573 |
+
"logps/rejected": -753.0247802734375,
|
574 |
+
"loss": 0.3758,
|
575 |
+
"rewards/accuracies": 0.8125,
|
576 |
+
"rewards/chosen": -3.216007947921753,
|
577 |
+
"rewards/margins": 1.8679723739624023,
|
578 |
+
"rewards/rejected": -5.083980560302734,
|
579 |
+
"step": 185
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.37461491065927294,
|
583 |
+
"grad_norm": 33.821388543016646,
|
584 |
+
"learning_rate": 3.9386402332652754e-07,
|
585 |
+
"logits/chosen": -2.0202414989471436,
|
586 |
+
"logits/rejected": -1.956538200378418,
|
587 |
+
"logps/chosen": -628.9379272460938,
|
588 |
+
"logps/rejected": -831.4833984375,
|
589 |
+
"loss": 0.4385,
|
590 |
+
"rewards/accuracies": 0.768750011920929,
|
591 |
+
"rewards/chosen": -4.222132205963135,
|
592 |
+
"rewards/margins": 1.7108278274536133,
|
593 |
+
"rewards/rejected": -5.93295955657959,
|
594 |
+
"step": 190
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.3844731977818854,
|
598 |
+
"grad_norm": 17.956228351745885,
|
599 |
+
"learning_rate": 3.867370395306068e-07,
|
600 |
+
"logits/chosen": -1.974908471107483,
|
601 |
+
"logits/rejected": -1.9330415725708008,
|
602 |
+
"logps/chosen": -509.0133361816406,
|
603 |
+
"logps/rejected": -720.5633544921875,
|
604 |
+
"loss": 0.3801,
|
605 |
+
"rewards/accuracies": 0.8500000238418579,
|
606 |
+
"rewards/chosen": -2.9117178916931152,
|
607 |
+
"rewards/margins": 1.6813218593597412,
|
608 |
+
"rewards/rejected": -4.593040466308594,
|
609 |
+
"step": 195
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.3943314849044978,
|
613 |
+
"grad_norm": 24.48103397679138,
|
614 |
+
"learning_rate": 3.794478174686328e-07,
|
615 |
+
"logits/chosen": -1.9475266933441162,
|
616 |
+
"logits/rejected": -1.9687010049819946,
|
617 |
+
"logps/chosen": -549.758544921875,
|
618 |
+
"logps/rejected": -740.8396606445312,
|
619 |
+
"loss": 0.4111,
|
620 |
+
"rewards/accuracies": 0.793749988079071,
|
621 |
+
"rewards/chosen": -3.3982017040252686,
|
622 |
+
"rewards/margins": 1.5769809484481812,
|
623 |
+
"rewards/rejected": -4.97518253326416,
|
624 |
+
"step": 200
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.4041897720271103,
|
628 |
+
"grad_norm": 19.929793517914295,
|
629 |
+
"learning_rate": 3.720050057902495e-07,
|
630 |
+
"logits/chosen": -2.11773419380188,
|
631 |
+
"logits/rejected": -2.0510640144348145,
|
632 |
+
"logps/chosen": -678.2037353515625,
|
633 |
+
"logps/rejected": -897.92822265625,
|
634 |
+
"loss": 0.3989,
|
635 |
+
"rewards/accuracies": 0.768750011920929,
|
636 |
+
"rewards/chosen": -4.697990894317627,
|
637 |
+
"rewards/margins": 1.6948550939559937,
|
638 |
+
"rewards/rejected": -6.39284610748291,
|
639 |
+
"step": 205
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.41404805914972276,
|
643 |
+
"grad_norm": 19.138382009358025,
|
644 |
+
"learning_rate": 3.644174353789204e-07,
|
645 |
+
"logits/chosen": -1.96860671043396,
|
646 |
+
"logits/rejected": -1.9445680379867554,
|
647 |
+
"logps/chosen": -541.2803955078125,
|
648 |
+
"logps/rejected": -714.5045776367188,
|
649 |
+
"loss": 0.3758,
|
650 |
+
"rewards/accuracies": 0.831250011920929,
|
651 |
+
"rewards/chosen": -3.2117228507995605,
|
652 |
+
"rewards/margins": 1.4313344955444336,
|
653 |
+
"rewards/rejected": -4.643057346343994,
|
654 |
+
"step": 210
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.4239063462723352,
|
658 |
+
"grad_norm": 22.61062071667254,
|
659 |
+
"learning_rate": 3.566941088741009e-07,
|
660 |
+
"logits/chosen": -1.9290311336517334,
|
661 |
+
"logits/rejected": -1.9250952005386353,
|
662 |
+
"logps/chosen": -502.6095275878906,
|
663 |
+
"logps/rejected": -698.4926147460938,
|
664 |
+
"loss": 0.3967,
|
665 |
+
"rewards/accuracies": 0.8500000238418579,
|
666 |
+
"rewards/chosen": -2.9526402950286865,
|
667 |
+
"rewards/margins": 1.6423494815826416,
|
668 |
+
"rewards/rejected": -4.594989776611328,
|
669 |
+
"step": 215
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.43376463339494764,
|
673 |
+
"grad_norm": 28.506261562704676,
|
674 |
+
"learning_rate": 3.488441899896217e-07,
|
675 |
+
"logits/chosen": -2.1637561321258545,
|
676 |
+
"logits/rejected": -1.9638168811798096,
|
677 |
+
"logps/chosen": -579.2008056640625,
|
678 |
+
"logps/rejected": -836.2589111328125,
|
679 |
+
"loss": 0.3974,
|
680 |
+
"rewards/accuracies": 0.8500000238418579,
|
681 |
+
"rewards/chosen": -3.5565972328186035,
|
682 |
+
"rewards/margins": 2.140427589416504,
|
683 |
+
"rewards/rejected": -5.697024345397949,
|
684 |
+
"step": 220
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.4436229205175601,
|
688 |
+
"grad_norm": 22.104238159035294,
|
689 |
+
"learning_rate": 3.408769926409574e-07,
|
690 |
+
"logits/chosen": -1.9999799728393555,
|
691 |
+
"logits/rejected": -1.9067310094833374,
|
692 |
+
"logps/chosen": -533.4635009765625,
|
693 |
+
"logps/rejected": -767.3900146484375,
|
694 |
+
"loss": 0.3601,
|
695 |
+
"rewards/accuracies": 0.831250011920929,
|
696 |
+
"rewards/chosen": -3.1343350410461426,
|
697 |
+
"rewards/margins": 1.9703528881072998,
|
698 |
+
"rewards/rejected": -5.104687690734863,
|
699 |
+
"step": 225
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.4534812076401725,
|
703 |
+
"grad_norm": 21.86054071865173,
|
704 |
+
"learning_rate": 3.3280196989428263e-07,
|
705 |
+
"logits/chosen": -2.0549824237823486,
|
706 |
+
"logits/rejected": -2.079737424850464,
|
707 |
+
"logps/chosen": -571.4501342773438,
|
708 |
+
"logps/rejected": -805.6971435546875,
|
709 |
+
"loss": 0.3644,
|
710 |
+
"rewards/accuracies": 0.8187500238418579,
|
711 |
+
"rewards/chosen": -3.492208480834961,
|
712 |
+
"rewards/margins": 2.0622007846832275,
|
713 |
+
"rewards/rejected": -5.554409027099609,
|
714 |
+
"step": 230
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.46333949476278496,
|
718 |
+
"grad_norm": 28.670025336805338,
|
719 |
+
"learning_rate": 3.2462870275042367e-07,
|
720 |
+
"logits/chosen": -2.086364269256592,
|
721 |
+
"logits/rejected": -2.082109212875366,
|
722 |
+
"logps/chosen": -627.2444458007812,
|
723 |
+
"logps/rejected": -857.6990356445312,
|
724 |
+
"loss": 0.3692,
|
725 |
+
"rewards/accuracies": 0.8374999761581421,
|
726 |
+
"rewards/chosen": -3.9953174591064453,
|
727 |
+
"rewards/margins": 2.085484266281128,
|
728 |
+
"rewards/rejected": -6.080801963806152,
|
729 |
+
"step": 235
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.4731977818853974,
|
733 |
+
"grad_norm": 23.098928119258375,
|
734 |
+
"learning_rate": 3.1636688877701806e-07,
|
735 |
+
"logits/chosen": -1.9278815984725952,
|
736 |
+
"logits/rejected": -2.008877992630005,
|
737 |
+
"logps/chosen": -536.9634399414062,
|
738 |
+
"logps/rejected": -782.7907104492188,
|
739 |
+
"loss": 0.3307,
|
740 |
+
"rewards/accuracies": 0.831250011920929,
|
741 |
+
"rewards/chosen": -3.128661632537842,
|
742 |
+
"rewards/margins": 2.186957836151123,
|
743 |
+
"rewards/rejected": -5.315619468688965,
|
744 |
+
"step": 240
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.48305606900800985,
|
748 |
+
"grad_norm": 18.256316767301172,
|
749 |
+
"learning_rate": 3.080263306023669e-07,
|
750 |
+
"logits/chosen": -1.9272663593292236,
|
751 |
+
"logits/rejected": -1.9132862091064453,
|
752 |
+
"logps/chosen": -510.236328125,
|
753 |
+
"logps/rejected": -714.0992431640625,
|
754 |
+
"loss": 0.3866,
|
755 |
+
"rewards/accuracies": 0.8374999761581421,
|
756 |
+
"rewards/chosen": -3.079207420349121,
|
757 |
+
"rewards/margins": 1.7918453216552734,
|
758 |
+
"rewards/rejected": -4.8710527420043945,
|
759 |
+
"step": 245
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.4929143561306223,
|
763 |
+
"grad_norm": 21.751680260746046,
|
764 |
+
"learning_rate": 2.996169242846328e-07,
|
765 |
+
"logits/chosen": -1.8919010162353516,
|
766 |
+
"logits/rejected": -1.9492820501327515,
|
767 |
+
"logps/chosen": -575.5780029296875,
|
768 |
+
"logps/rejected": -819.9085693359375,
|
769 |
+
"loss": 0.3276,
|
770 |
+
"rewards/accuracies": 0.862500011920929,
|
771 |
+
"rewards/chosen": -3.592189311981201,
|
772 |
+
"rewards/margins": 2.1720731258392334,
|
773 |
+
"rewards/rejected": -5.764262676239014,
|
774 |
+
"step": 250
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.5027726432532348,
|
778 |
+
"grad_norm": 22.663811321818965,
|
779 |
+
"learning_rate": 2.911486475701835e-07,
|
780 |
+
"logits/chosen": -1.8436260223388672,
|
781 |
+
"logits/rejected": -1.8624000549316406,
|
782 |
+
"logps/chosen": -532.0939331054688,
|
783 |
+
"logps/rejected": -772.1865234375,
|
784 |
+
"loss": 0.3646,
|
785 |
+
"rewards/accuracies": 0.8687499761581421,
|
786 |
+
"rewards/chosen": -3.234412670135498,
|
787 |
+
"rewards/margins": 2.037332773208618,
|
788 |
+
"rewards/rejected": -5.271745681762695,
|
789 |
+
"step": 255
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.5126309303758472,
|
793 |
+
"grad_norm": 45.86539600331869,
|
794 |
+
"learning_rate": 2.826315480550129e-07,
|
795 |
+
"logits/chosen": -1.8276054859161377,
|
796 |
+
"logits/rejected": -1.944835901260376,
|
797 |
+
"logps/chosen": -522.5578002929688,
|
798 |
+
"logps/rejected": -729.6175537109375,
|
799 |
+
"loss": 0.3653,
|
800 |
+
"rewards/accuracies": 0.856249988079071,
|
801 |
+
"rewards/chosen": -3.1025471687316895,
|
802 |
+
"rewards/margins": 1.926390290260315,
|
803 |
+
"rewards/rejected": -5.028937339782715,
|
804 |
+
"step": 260
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.5224892174984597,
|
808 |
+
"grad_norm": 33.790931231853406,
|
809 |
+
"learning_rate": 2.740757312632854e-07,
|
810 |
+
"logits/chosen": -1.9260978698730469,
|
811 |
+
"logits/rejected": -1.8717044591903687,
|
812 |
+
"logps/chosen": -576.6935424804688,
|
813 |
+
"logps/rejected": -834.5701904296875,
|
814 |
+
"loss": 0.3316,
|
815 |
+
"rewards/accuracies": 0.8687499761581421,
|
816 |
+
"rewards/chosen": -3.7069427967071533,
|
817 |
+
"rewards/margins": 2.2525296211242676,
|
818 |
+
"rewards/rejected": -5.959472179412842,
|
819 |
+
"step": 265
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.532347504621072,
|
823 |
+
"grad_norm": 32.72135751726444,
|
824 |
+
"learning_rate": 2.654913486571487e-07,
|
825 |
+
"logits/chosen": -1.928877830505371,
|
826 |
+
"logits/rejected": -1.9832346439361572,
|
827 |
+
"logps/chosen": -580.7061767578125,
|
828 |
+
"logps/rejected": -821.77734375,
|
829 |
+
"loss": 0.3773,
|
830 |
+
"rewards/accuracies": 0.8374999761581421,
|
831 |
+
"rewards/chosen": -3.5770630836486816,
|
832 |
+
"rewards/margins": 2.1589841842651367,
|
833 |
+
"rewards/rejected": -5.73604679107666,
|
834 |
+
"step": 270
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.5422057917436846,
|
838 |
+
"grad_norm": 18.44880000765859,
|
839 |
+
"learning_rate": 2.5688858559204053e-07,
|
840 |
+
"logits/chosen": -1.8500230312347412,
|
841 |
+
"logits/rejected": -1.8931682109832764,
|
842 |
+
"logps/chosen": -484.74420166015625,
|
843 |
+
"logps/rejected": -701.5289916992188,
|
844 |
+
"loss": 0.3747,
|
845 |
+
"rewards/accuracies": 0.8374999761581421,
|
846 |
+
"rewards/chosen": -2.6471669673919678,
|
847 |
+
"rewards/margins": 1.9642257690429688,
|
848 |
+
"rewards/rejected": -4.611392974853516,
|
849 |
+
"step": 275
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.5520640788662969,
|
853 |
+
"grad_norm": 23.335141498824942,
|
854 |
+
"learning_rate": 2.4827764923178246e-07,
|
855 |
+
"logits/chosen": -1.8331562280654907,
|
856 |
+
"logits/rejected": -1.9513938426971436,
|
857 |
+
"logps/chosen": -470.59405517578125,
|
858 |
+
"logps/rejected": -660.6781005859375,
|
859 |
+
"loss": 0.3683,
|
860 |
+
"rewards/accuracies": 0.831250011920929,
|
861 |
+
"rewards/chosen": -2.504983901977539,
|
862 |
+
"rewards/margins": 1.7337911128997803,
|
863 |
+
"rewards/rejected": -4.23877477645874,
|
864 |
+
"step": 280
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.5619223659889094,
|
868 |
+
"grad_norm": 26.351304197321983,
|
869 |
+
"learning_rate": 2.3966875643779667e-07,
|
870 |
+
"logits/chosen": -2.0291342735290527,
|
871 |
+
"logits/rejected": -1.9187507629394531,
|
872 |
+
"logps/chosen": -495.74639892578125,
|
873 |
+
"logps/rejected": -760.9273681640625,
|
874 |
+
"loss": 0.3506,
|
875 |
+
"rewards/accuracies": 0.887499988079071,
|
876 |
+
"rewards/chosen": -2.894580125808716,
|
877 |
+
"rewards/margins": 2.167811632156372,
|
878 |
+
"rewards/rejected": -5.062391757965088,
|
879 |
+
"step": 285
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.5717806531115218,
|
883 |
+
"grad_norm": 21.633547530781627,
|
884 |
+
"learning_rate": 2.3107212164681774e-07,
|
885 |
+
"logits/chosen": -1.871260643005371,
|
886 |
+
"logits/rejected": -1.916135549545288,
|
887 |
+
"logps/chosen": -529.8262939453125,
|
888 |
+
"logps/rejected": -772.5482177734375,
|
889 |
+
"loss": 0.36,
|
890 |
+
"rewards/accuracies": 0.831250011920929,
|
891 |
+
"rewards/chosen": -3.0958144664764404,
|
892 |
+
"rewards/margins": 2.1699347496032715,
|
893 |
+
"rewards/rejected": -5.265749454498291,
|
894 |
+
"step": 290
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.5816389402341343,
|
898 |
+
"grad_norm": 28.65131510288306,
|
899 |
+
"learning_rate": 2.2249794475148019e-07,
|
900 |
+
"logits/chosen": -2.063917636871338,
|
901 |
+
"logits/rejected": -2.049710750579834,
|
902 |
+
"logps/chosen": -510.1465759277344,
|
903 |
+
"logps/rejected": -759.2296752929688,
|
904 |
+
"loss": 0.3827,
|
905 |
+
"rewards/accuracies": 0.893750011920929,
|
906 |
+
"rewards/chosen": -2.9606268405914307,
|
907 |
+
"rewards/margins": 2.110110282897949,
|
908 |
+
"rewards/rejected": -5.070736885070801,
|
909 |
+
"step": 295
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.5914972273567468,
|
913 |
+
"grad_norm": 23.359544656067033,
|
914 |
+
"learning_rate": 2.1395639899816332e-07,
|
915 |
+
"logits/chosen": -2.2645859718322754,
|
916 |
+
"logits/rejected": -1.9906375408172607,
|
917 |
+
"logps/chosen": -541.4847412109375,
|
918 |
+
"logps/rejected": -846.5947265625,
|
919 |
+
"loss": 0.3488,
|
920 |
+
"rewards/accuracies": 0.8374999761581421,
|
921 |
+
"rewards/chosen": -3.3356003761291504,
|
922 |
+
"rewards/margins": 2.4959442615509033,
|
923 |
+
"rewards/rejected": -5.831544399261475,
|
924 |
+
"step": 300
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.6013555144793592,
|
928 |
+
"grad_norm": 24.944829150573064,
|
929 |
+
"learning_rate": 2.0545761891645177e-07,
|
930 |
+
"logits/chosen": -2.0867130756378174,
|
931 |
+
"logits/rejected": -2.074833393096924,
|
932 |
+
"logps/chosen": -642.1096801757812,
|
933 |
+
"logps/rejected": -906.7780151367188,
|
934 |
+
"loss": 0.3502,
|
935 |
+
"rewards/accuracies": 0.8187500238418579,
|
936 |
+
"rewards/chosen": -4.175184726715088,
|
937 |
+
"rewards/margins": 2.322237253189087,
|
938 |
+
"rewards/rejected": -6.497422218322754,
|
939 |
+
"step": 305
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.6112138016019717,
|
943 |
+
"grad_norm": 24.979816541182146,
|
944 |
+
"learning_rate": 1.9701168829453305e-07,
|
945 |
+
"logits/chosen": -1.932847023010254,
|
946 |
+
"logits/rejected": -1.9259026050567627,
|
947 |
+
"logps/chosen": -570.7978515625,
|
948 |
+
"logps/rejected": -823.3259887695312,
|
949 |
+
"loss": 0.3411,
|
950 |
+
"rewards/accuracies": 0.8812500238418579,
|
951 |
+
"rewards/chosen": -3.579385757446289,
|
952 |
+
"rewards/margins": 2.1752305030822754,
|
953 |
+
"rewards/rejected": -5.7546162605285645,
|
954 |
+
"step": 310
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.6210720887245841,
|
958 |
+
"grad_norm": 24.585502500513254,
|
959 |
+
"learning_rate": 1.886286282148002e-07,
|
960 |
+
"logits/chosen": -2.069624662399292,
|
961 |
+
"logits/rejected": -1.978257179260254,
|
962 |
+
"logps/chosen": -547.39794921875,
|
963 |
+
"logps/rejected": -787.85302734375,
|
964 |
+
"loss": 0.331,
|
965 |
+
"rewards/accuracies": 0.8374999761581421,
|
966 |
+
"rewards/chosen": -3.470412015914917,
|
967 |
+
"rewards/margins": 2.049595594406128,
|
968 |
+
"rewards/rejected": -5.520008087158203,
|
969 |
+
"step": 315
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.6309303758471966,
|
973 |
+
"grad_norm": 29.24520617120494,
|
974 |
+
"learning_rate": 1.8031838516385422e-07,
|
975 |
+
"logits/chosen": -2.089122772216797,
|
976 |
+
"logits/rejected": -2.0376973152160645,
|
977 |
+
"logps/chosen": -622.2824096679688,
|
978 |
+
"logps/rejected": -920.2009887695312,
|
979 |
+
"loss": 0.3733,
|
980 |
+
"rewards/accuracies": 0.856249988079071,
|
981 |
+
"rewards/chosen": -4.0230793952941895,
|
982 |
+
"rewards/margins": 2.4440813064575195,
|
983 |
+
"rewards/rejected": -6.467160701751709,
|
984 |
+
"step": 320
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.640788662969809,
|
988 |
+
"grad_norm": 20.742877534346576,
|
989 |
+
"learning_rate": 1.7209081923101472e-07,
|
990 |
+
"logits/chosen": -2.0211918354034424,
|
991 |
+
"logits/rejected": -2.014601230621338,
|
992 |
+
"logps/chosen": -589.6067504882812,
|
993 |
+
"logps/rejected": -773.7950439453125,
|
994 |
+
"loss": 0.3436,
|
995 |
+
"rewards/accuracies": 0.8125,
|
996 |
+
"rewards/chosen": -3.677738904953003,
|
997 |
+
"rewards/margins": 1.7034008502960205,
|
998 |
+
"rewards/rejected": -5.381140232086182,
|
999 |
+
"step": 325
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.6506469500924215,
|
1003 |
+
"grad_norm": 16.903001935618324,
|
1004 |
+
"learning_rate": 1.639556924093404e-07,
|
1005 |
+
"logits/chosen": -1.8897491693496704,
|
1006 |
+
"logits/rejected": -1.88128662109375,
|
1007 |
+
"logps/chosen": -517.2490844726562,
|
1008 |
+
"logps/rejected": -746.6140747070312,
|
1009 |
+
"loss": 0.3561,
|
1010 |
+
"rewards/accuracies": 0.856249988079071,
|
1011 |
+
"rewards/chosen": -3.064331531524658,
|
1012 |
+
"rewards/margins": 1.9852135181427002,
|
1013 |
+
"rewards/rejected": -5.0495452880859375,
|
1014 |
+
"step": 330
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.6605052372150338,
|
1018 |
+
"grad_norm": 19.809662336676986,
|
1019 |
+
"learning_rate": 1.5592265701304114e-07,
|
1020 |
+
"logits/chosen": -2.0255661010742188,
|
1021 |
+
"logits/rejected": -1.944502592086792,
|
1022 |
+
"logps/chosen": -566.5452270507812,
|
1023 |
+
"logps/rejected": -803.533203125,
|
1024 |
+
"loss": 0.3705,
|
1025 |
+
"rewards/accuracies": 0.8500000238418579,
|
1026 |
+
"rewards/chosen": -3.5436272621154785,
|
1027 |
+
"rewards/margins": 2.0192878246307373,
|
1028 |
+
"rewards/rejected": -5.562914848327637,
|
1029 |
+
"step": 335
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.6703635243376463,
|
1033 |
+
"grad_norm": 26.202979422607854,
|
1034 |
+
"learning_rate": 1.4800124422502334e-07,
|
1035 |
+
"logits/chosen": -1.918569803237915,
|
1036 |
+
"logits/rejected": -2.0119967460632324,
|
1037 |
+
"logps/chosen": -601.0817260742188,
|
1038 |
+
"logps/rejected": -845.7435302734375,
|
1039 |
+
"loss": 0.3597,
|
1040 |
+
"rewards/accuracies": 0.856249988079071,
|
1041 |
+
"rewards/chosen": -3.8363289833068848,
|
1042 |
+
"rewards/margins": 2.0620241165161133,
|
1043 |
+
"rewards/rejected": -5.89835262298584,
|
1044 |
+
"step": 340
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.6802218114602587,
|
1048 |
+
"grad_norm": 26.077309548266044,
|
1049 |
+
"learning_rate": 1.4020085278815743e-07,
|
1050 |
+
"logits/chosen": -2.0037617683410645,
|
1051 |
+
"logits/rejected": -1.8837954998016357,
|
1052 |
+
"logps/chosen": -645.288818359375,
|
1053 |
+
"logps/rejected": -909.7770385742188,
|
1054 |
+
"loss": 0.3434,
|
1055 |
+
"rewards/accuracies": 0.8374999761581421,
|
1056 |
+
"rewards/chosen": -4.325263500213623,
|
1057 |
+
"rewards/margins": 2.183290719985962,
|
1058 |
+
"rewards/rejected": -6.508553981781006,
|
1059 |
+
"step": 345
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.6900800985828712,
|
1063 |
+
"grad_norm": 20.206758195915803,
|
1064 |
+
"learning_rate": 1.3253073785368545e-07,
|
1065 |
+
"logits/chosen": -1.97844660282135,
|
1066 |
+
"logits/rejected": -1.9779163599014282,
|
1067 |
+
"logps/chosen": -656.6150512695312,
|
1068 |
+
"logps/rejected": -917.7893676757812,
|
1069 |
+
"loss": 0.3432,
|
1070 |
+
"rewards/accuracies": 0.856249988079071,
|
1071 |
+
"rewards/chosen": -4.431666374206543,
|
1072 |
+
"rewards/margins": 2.2607076168060303,
|
1073 |
+
"rewards/rejected": -6.692374229431152,
|
1074 |
+
"step": 350
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.6999383857054837,
|
1078 |
+
"grad_norm": 24.24143829005782,
|
1079 |
+
"learning_rate": 1.2500000000000005e-07,
|
1080 |
+
"logits/chosen": -2.066188335418701,
|
1081 |
+
"logits/rejected": -2.054232120513916,
|
1082 |
+
"logps/chosen": -643.3806762695312,
|
1083 |
+
"logps/rejected": -863.3739013671875,
|
1084 |
+
"loss": 0.3583,
|
1085 |
+
"rewards/accuracies": 0.78125,
|
1086 |
+
"rewards/chosen": -4.284465789794922,
|
1087 |
+
"rewards/margins": 1.9454777240753174,
|
1088 |
+
"rewards/rejected": -6.22994327545166,
|
1089 |
+
"step": 355
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.7097966728280961,
|
1093 |
+
"grad_norm": 17.76728293699117,
|
1094 |
+
"learning_rate": 1.1761757443482285e-07,
|
1095 |
+
"logits/chosen": -1.8952592611312866,
|
1096 |
+
"logits/rejected": -1.8270065784454346,
|
1097 |
+
"logps/chosen": -567.1143798828125,
|
1098 |
+
"logps/rejected": -791.7889404296875,
|
1099 |
+
"loss": 0.3722,
|
1100 |
+
"rewards/accuracies": 0.8125,
|
1101 |
+
"rewards/chosen": -3.542332172393799,
|
1102 |
+
"rewards/margins": 1.8870967626571655,
|
1103 |
+
"rewards/rejected": -5.429428577423096,
|
1104 |
+
"step": 360
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.7196549599507086,
|
1108 |
+
"grad_norm": 25.546590661527123,
|
1109 |
+
"learning_rate": 1.1039222039359644e-07,
|
1110 |
+
"logits/chosen": -1.9491792917251587,
|
1111 |
+
"logits/rejected": -1.8340580463409424,
|
1112 |
+
"logps/chosen": -522.3615112304688,
|
1113 |
+
"logps/rejected": -782.1358032226562,
|
1114 |
+
"loss": 0.3194,
|
1115 |
+
"rewards/accuracies": 0.925000011920929,
|
1116 |
+
"rewards/chosen": -3.073195219039917,
|
1117 |
+
"rewards/margins": 2.195949077606201,
|
1118 |
+
"rewards/rejected": -5.269144535064697,
|
1119 |
+
"step": 365
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.729513247073321,
|
1123 |
+
"grad_norm": 25.390221264918292,
|
1124 |
+
"learning_rate": 1.0333251074666608e-07,
|
1125 |
+
"logits/chosen": -1.8948665857315063,
|
1126 |
+
"logits/rejected": -1.8821592330932617,
|
1127 |
+
"logps/chosen": -578.3306884765625,
|
1128 |
+
"logps/rejected": -830.9544677734375,
|
1129 |
+
"loss": 0.3285,
|
1130 |
+
"rewards/accuracies": 0.8687499761581421,
|
1131 |
+
"rewards/chosen": -3.6443309783935547,
|
1132 |
+
"rewards/margins": 2.2878963947296143,
|
1133 |
+
"rewards/rejected": -5.932227611541748,
|
1134 |
+
"step": 370
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.7393715341959335,
|
1138 |
+
"grad_norm": 23.32295380693496,
|
1139 |
+
"learning_rate": 9.644682182758304e-08,
|
1140 |
+
"logits/chosen": -1.8538382053375244,
|
1141 |
+
"logits/rejected": -1.8016763925552368,
|
1142 |
+
"logps/chosen": -604.1889038085938,
|
1143 |
+
"logps/rejected": -873.8849487304688,
|
1144 |
+
"loss": 0.3055,
|
1145 |
+
"rewards/accuracies": 0.862500011920929,
|
1146 |
+
"rewards/chosen": -3.8995869159698486,
|
1147 |
+
"rewards/margins": 2.3217251300811768,
|
1148 |
+
"rewards/rejected": -6.221312046051025,
|
1149 |
+
"step": 375
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.7492298213185459,
|
1153 |
+
"grad_norm": 23.34487045577994,
|
1154 |
+
"learning_rate": 8.974332349459992e-08,
|
1155 |
+
"logits/chosen": -1.913751244544983,
|
1156 |
+
"logits/rejected": -1.8759132623672485,
|
1157 |
+
"logps/chosen": -620.8341064453125,
|
1158 |
+
"logps/rejected": -879.5367431640625,
|
1159 |
+
"loss": 0.3497,
|
1160 |
+
"rewards/accuracies": 0.84375,
|
1161 |
+
"rewards/chosen": -3.9944968223571777,
|
1162 |
+
"rewards/margins": 2.277583360671997,
|
1163 |
+
"rewards/rejected": -6.272080421447754,
|
1164 |
+
"step": 380
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.7590881084411584,
|
1168 |
+
"grad_norm": 32.80860271044305,
|
1169 |
+
"learning_rate": 8.322996943714672e-08,
|
1170 |
+
"logits/chosen": -1.9127395153045654,
|
1171 |
+
"logits/rejected": -1.716653823852539,
|
1172 |
+
"logps/chosen": -559.0478515625,
|
1173 |
+
"logps/rejected": -869.8646240234375,
|
1174 |
+
"loss": 0.3553,
|
1175 |
+
"rewards/accuracies": 0.8500000238418579,
|
1176 |
+
"rewards/chosen": -3.513237714767456,
|
1177 |
+
"rewards/margins": 2.5553982257843018,
|
1178 |
+
"rewards/rejected": -6.068636894226074,
|
1179 |
+
"step": 385
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.7689463955637708,
|
1183 |
+
"grad_norm": 22.70407770691601,
|
1184 |
+
"learning_rate": 7.691448773879256e-08,
|
1185 |
+
"logits/chosen": -1.8521419763565063,
|
1186 |
+
"logits/rejected": -1.7435353994369507,
|
1187 |
+
"logps/chosen": -503.28369140625,
|
1188 |
+
"logps/rejected": -769.7913818359375,
|
1189 |
+
"loss": 0.3582,
|
1190 |
+
"rewards/accuracies": 0.8187500238418579,
|
1191 |
+
"rewards/chosen": -2.978849172592163,
|
1192 |
+
"rewards/margins": 2.2009291648864746,
|
1193 |
+
"rewards/rejected": -5.179778575897217,
|
1194 |
+
"step": 390
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.7788046826863833,
|
1198 |
+
"grad_norm": 26.31642324943315,
|
1199 |
+
"learning_rate": 7.080437170788722e-08,
|
1200 |
+
"logits/chosen": -1.9601354598999023,
|
1201 |
+
"logits/rejected": -1.8902816772460938,
|
1202 |
+
"logps/chosen": -511.15478515625,
|
1203 |
+
"logps/rejected": -765.9757690429688,
|
1204 |
+
"loss": 0.3126,
|
1205 |
+
"rewards/accuracies": 0.8812500238418579,
|
1206 |
+
"rewards/chosen": -3.040039539337158,
|
1207 |
+
"rewards/margins": 2.2116754055023193,
|
1208 |
+
"rewards/rejected": -5.251715183258057,
|
1209 |
+
"step": 395
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.7886629698089956,
|
1213 |
+
"grad_norm": 73.40724109949657,
|
1214 |
+
"learning_rate": 6.490687098676332e-08,
|
1215 |
+
"logits/chosen": -1.776098608970642,
|
1216 |
+
"logits/rejected": -1.7230415344238281,
|
1217 |
+
"logps/chosen": -568.650634765625,
|
1218 |
+
"logps/rejected": -813.4503173828125,
|
1219 |
+
"loss": 0.347,
|
1220 |
+
"rewards/accuracies": 0.793749988079071,
|
1221 |
+
"rewards/chosen": -3.520684003829956,
|
1222 |
+
"rewards/margins": 2.105372190475464,
|
1223 |
+
"rewards/rejected": -5.626055717468262,
|
1224 |
+
"step": 400
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.7886629698089956,
|
1228 |
+
"eval_logits/chosen": -2.5592944622039795,
|
1229 |
+
"eval_logits/rejected": -2.4283623695373535,
|
1230 |
+
"eval_logps/chosen": -432.9762878417969,
|
1231 |
+
"eval_logps/rejected": -481.0541076660156,
|
1232 |
+
"eval_loss": 0.5772423148155212,
|
1233 |
+
"eval_rewards/accuracies": 0.6794354915618896,
|
1234 |
+
"eval_rewards/chosen": -1.7008415460586548,
|
1235 |
+
"eval_rewards/margins": 0.37072598934173584,
|
1236 |
+
"eval_rewards/rejected": -2.0715677738189697,
|
1237 |
+
"eval_runtime": 324.936,
|
1238 |
+
"eval_samples_per_second": 6.081,
|
1239 |
+
"eval_steps_per_second": 0.382,
|
1240 |
+
"step": 400
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 0.7985212569316081,
|
1244 |
+
"grad_norm": 33.809746730746596,
|
1245 |
+
"learning_rate": 5.9228982950048414e-08,
|
1246 |
+
"logits/chosen": -1.7156673669815063,
|
1247 |
+
"logits/rejected": -1.7448875904083252,
|
1248 |
+
"logps/chosen": -582.68603515625,
|
1249 |
+
"logps/rejected": -882.1572265625,
|
1250 |
+
"loss": 0.3578,
|
1251 |
+
"rewards/accuracies": 0.893750011920929,
|
1252 |
+
"rewards/chosen": -3.6797871589660645,
|
1253 |
+
"rewards/margins": 2.6076254844665527,
|
1254 |
+
"rewards/rejected": -6.287413120269775,
|
1255 |
+
"step": 405
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.8083795440542206,
|
1259 |
+
"grad_norm": 23.982039805708112,
|
1260 |
+
"learning_rate": 5.3777444402291345e-08,
|
1261 |
+
"logits/chosen": -1.9656894207000732,
|
1262 |
+
"logits/rejected": -1.7757899761199951,
|
1263 |
+
"logps/chosen": -602.1336059570312,
|
1264 |
+
"logps/rejected": -914.3304443359375,
|
1265 |
+
"loss": 0.2749,
|
1266 |
+
"rewards/accuracies": 0.887499988079071,
|
1267 |
+
"rewards/chosen": -3.811291456222534,
|
1268 |
+
"rewards/margins": 2.5836830139160156,
|
1269 |
+
"rewards/rejected": -6.394974708557129,
|
1270 |
+
"step": 410
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.818237831176833,
|
1274 |
+
"grad_norm": 21.999889032487328,
|
1275 |
+
"learning_rate": 4.855872358475546e-08,
|
1276 |
+
"logits/chosen": -1.883536696434021,
|
1277 |
+
"logits/rejected": -1.8990424871444702,
|
1278 |
+
"logps/chosen": -593.3975219726562,
|
1279 |
+
"logps/rejected": -852.3743896484375,
|
1280 |
+
"loss": 0.3421,
|
1281 |
+
"rewards/accuracies": 0.8500000238418579,
|
1282 |
+
"rewards/chosen": -3.749640941619873,
|
1283 |
+
"rewards/margins": 2.2763512134552,
|
1284 |
+
"rewards/rejected": -6.025992393493652,
|
1285 |
+
"step": 415
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.8280961182994455,
|
1289 |
+
"grad_norm": 22.43509931864549,
|
1290 |
+
"learning_rate": 4.357901250086107e-08,
|
1291 |
+
"logits/chosen": -1.9897289276123047,
|
1292 |
+
"logits/rejected": -1.8019778728485107,
|
1293 |
+
"logps/chosen": -604.5925903320312,
|
1294 |
+
"logps/rejected": -907.0695190429688,
|
1295 |
+
"loss": 0.34,
|
1296 |
+
"rewards/accuracies": 0.8687499761581421,
|
1297 |
+
"rewards/chosen": -3.7366394996643066,
|
1298 |
+
"rewards/margins": 2.591937303543091,
|
1299 |
+
"rewards/rejected": -6.328576564788818,
|
1300 |
+
"step": 420
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 0.8379544054220579,
|
1304 |
+
"grad_norm": 24.272876807226076,
|
1305 |
+
"learning_rate": 3.884421956938377e-08,
|
1306 |
+
"logits/chosen": -1.7035375833511353,
|
1307 |
+
"logits/rejected": -1.8067095279693604,
|
1308 |
+
"logps/chosen": -621.3763427734375,
|
1309 |
+
"logps/rejected": -809.0113525390625,
|
1310 |
+
"loss": 0.3274,
|
1311 |
+
"rewards/accuracies": 0.8687499761581421,
|
1312 |
+
"rewards/chosen": -3.943162441253662,
|
1313 |
+
"rewards/margins": 1.8734540939331055,
|
1314 |
+
"rewards/rejected": -5.816616535186768,
|
1315 |
+
"step": 425
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 0.8478126925446704,
|
1319 |
+
"grad_norm": 20.673588966056126,
|
1320 |
+
"learning_rate": 3.435996261412591e-08,
|
1321 |
+
"logits/chosen": -1.7106269598007202,
|
1322 |
+
"logits/rejected": -1.7173693180084229,
|
1323 |
+
"logps/chosen": -582.3190307617188,
|
1324 |
+
"logps/rejected": -837.8707275390625,
|
1325 |
+
"loss": 0.3204,
|
1326 |
+
"rewards/accuracies": 0.862500011920929,
|
1327 |
+
"rewards/chosen": -3.7369446754455566,
|
1328 |
+
"rewards/margins": 2.223895311355591,
|
1329 |
+
"rewards/rejected": -5.960839748382568,
|
1330 |
+
"step": 430
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 0.8576709796672828,
|
1334 |
+
"grad_norm": 21.70614636700232,
|
1335 |
+
"learning_rate": 3.013156219837776e-08,
|
1336 |
+
"logits/chosen": -2.0358176231384277,
|
1337 |
+
"logits/rejected": -1.7434278726577759,
|
1338 |
+
"logps/chosen": -567.6253662109375,
|
1339 |
+
"logps/rejected": -890.8966674804688,
|
1340 |
+
"loss": 0.3264,
|
1341 |
+
"rewards/accuracies": 0.8812500238418579,
|
1342 |
+
"rewards/chosen": -3.516098737716675,
|
1343 |
+
"rewards/margins": 2.7037405967712402,
|
1344 |
+
"rewards/rejected": -6.219839096069336,
|
1345 |
+
"step": 435
|
1346 |
+
},
|
1347 |
+
{
|
1348 |
+
"epoch": 0.8675292667898953,
|
1349 |
+
"grad_norm": 32.0982872650184,
|
1350 |
+
"learning_rate": 2.6164035312078447e-08,
|
1351 |
+
"logits/chosen": -1.87311589717865,
|
1352 |
+
"logits/rejected": -1.8581056594848633,
|
1353 |
+
"logps/chosen": -588.0389404296875,
|
1354 |
+
"logps/rejected": -895.1696166992188,
|
1355 |
+
"loss": 0.3188,
|
1356 |
+
"rewards/accuracies": 0.8812500238418579,
|
1357 |
+
"rewards/chosen": -3.7721753120422363,
|
1358 |
+
"rewards/margins": 2.676305055618286,
|
1359 |
+
"rewards/rejected": -6.448480129241943,
|
1360 |
+
"step": 440
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.8773875539125077,
|
1364 |
+
"grad_norm": 21.51066896519883,
|
1365 |
+
"learning_rate": 2.2462089419165776e-08,
|
1366 |
+
"logits/chosen": -1.8648655414581299,
|
1367 |
+
"logits/rejected": -1.7761850357055664,
|
1368 |
+
"logps/chosen": -582.1537475585938,
|
1369 |
+
"logps/rejected": -876.07080078125,
|
1370 |
+
"loss": 0.3584,
|
1371 |
+
"rewards/accuracies": 0.8500000238418579,
|
1372 |
+
"rewards/chosen": -3.821885347366333,
|
1373 |
+
"rewards/margins": 2.4609155654907227,
|
1374 |
+
"rewards/rejected": -6.282800197601318,
|
1375 |
+
"step": 445
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.8872458410351202,
|
1379 |
+
"grad_norm": 23.61458187816769,
|
1380 |
+
"learning_rate": 1.9030116872178314e-08,
|
1381 |
+
"logits/chosen": -1.8204158544540405,
|
1382 |
+
"logits/rejected": -1.798825979232788,
|
1383 |
+
"logps/chosen": -608.7778930664062,
|
1384 |
+
"logps/rejected": -842.8968505859375,
|
1385 |
+
"loss": 0.355,
|
1386 |
+
"rewards/accuracies": 0.8500000238418579,
|
1387 |
+
"rewards/chosen": -3.7794837951660156,
|
1388 |
+
"rewards/margins": 2.1480660438537598,
|
1389 |
+
"rewards/rejected": -5.927549839019775,
|
1390 |
+
"step": 450
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 0.8971041281577325,
|
1394 |
+
"grad_norm": 19.975596086165712,
|
1395 |
+
"learning_rate": 1.5872189700736337e-08,
|
1396 |
+
"logits/chosen": -1.7636759281158447,
|
1397 |
+
"logits/rejected": -1.8992855548858643,
|
1398 |
+
"logps/chosen": -585.3933715820312,
|
1399 |
+
"logps/rejected": -801.01025390625,
|
1400 |
+
"loss": 0.3525,
|
1401 |
+
"rewards/accuracies": 0.8125,
|
1402 |
+
"rewards/chosen": -3.633349657058716,
|
1403 |
+
"rewards/margins": 1.9284839630126953,
|
1404 |
+
"rewards/rejected": -5.561833381652832,
|
1405 |
+
"step": 455
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 0.906962415280345,
|
1409 |
+
"grad_norm": 24.116575473235745,
|
1410 |
+
"learning_rate": 1.2992054780085692e-08,
|
1411 |
+
"logits/chosen": -1.6149314641952515,
|
1412 |
+
"logits/rejected": -1.6830947399139404,
|
1413 |
+
"logps/chosen": -552.21728515625,
|
1414 |
+
"logps/rejected": -793.0897216796875,
|
1415 |
+
"loss": 0.3263,
|
1416 |
+
"rewards/accuracies": 0.862500011920929,
|
1417 |
+
"rewards/chosen": -3.4062886238098145,
|
1418 |
+
"rewards/margins": 2.0678482055664062,
|
1419 |
+
"rewards/rejected": -5.474137306213379,
|
1420 |
+
"step": 460
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.9168207024029574,
|
1424 |
+
"grad_norm": 20.57194341940523,
|
1425 |
+
"learning_rate": 1.0393129385436823e-08,
|
1426 |
+
"logits/chosen": -1.9199676513671875,
|
1427 |
+
"logits/rejected": -1.8623239994049072,
|
1428 |
+
"logps/chosen": -570.3748779296875,
|
1429 |
+
"logps/rejected": -817.0477294921875,
|
1430 |
+
"loss": 0.3323,
|
1431 |
+
"rewards/accuracies": 0.8687499761581421,
|
1432 |
+
"rewards/chosen": -3.562505006790161,
|
1433 |
+
"rewards/margins": 2.1840949058532715,
|
1434 |
+
"rewards/rejected": -5.7465996742248535,
|
1435 |
+
"step": 465
|
1436 |
+
},
|
1437 |
+
{
|
1438 |
+
"epoch": 0.9266789895255699,
|
1439 |
+
"grad_norm": 23.30110640610616,
|
1440 |
+
"learning_rate": 8.078497137373242e-09,
|
1441 |
+
"logits/chosen": -1.7810325622558594,
|
1442 |
+
"logits/rejected": -1.7818634510040283,
|
1443 |
+
"logps/chosen": -555.9640502929688,
|
1444 |
+
"logps/rejected": -835.23876953125,
|
1445 |
+
"loss": 0.3237,
|
1446 |
+
"rewards/accuracies": 0.887499988079071,
|
1447 |
+
"rewards/chosen": -3.4883415699005127,
|
1448 |
+
"rewards/margins": 2.179206609725952,
|
1449 |
+
"rewards/rejected": -5.667548179626465,
|
1450 |
+
"step": 470
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 0.9365372766481824,
|
1454 |
+
"grad_norm": 21.422635902068766,
|
1455 |
+
"learning_rate": 6.0509043431410945e-09,
|
1456 |
+
"logits/chosen": -1.7087141275405884,
|
1457 |
+
"logits/rejected": -1.772657036781311,
|
1458 |
+
"logps/chosen": -568.8113403320312,
|
1459 |
+
"logps/rejected": -804.4452514648438,
|
1460 |
+
"loss": 0.3425,
|
1461 |
+
"rewards/accuracies": 0.862500011920929,
|
1462 |
+
"rewards/chosen": -3.5404930114746094,
|
1463 |
+
"rewards/margins": 2.15417742729187,
|
1464 |
+
"rewards/rejected": -5.694670677185059,
|
1465 |
+
"step": 475
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.9463955637707948,
|
1469 |
+
"grad_norm": 22.24576845817703,
|
1470 |
+
"learning_rate": 4.312756738160145e-09,
|
1471 |
+
"logits/chosen": -1.8130733966827393,
|
1472 |
+
"logits/rejected": -1.7939121723175049,
|
1473 |
+
"logps/chosen": -561.7185668945312,
|
1474 |
+
"logps/rejected": -826.4733276367188,
|
1475 |
+
"loss": 0.3187,
|
1476 |
+
"rewards/accuracies": 0.8687499761581421,
|
1477 |
+
"rewards/chosen": -3.5638492107391357,
|
1478 |
+
"rewards/margins": 2.2962565422058105,
|
1479 |
+
"rewards/rejected": -5.860105991363525,
|
1480 |
+
"step": 480
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 0.9562538508934073,
|
1484 |
+
"grad_norm": 20.818504977861426,
|
1485 |
+
"learning_rate": 2.8661166316229223e-09,
|
1486 |
+
"logits/chosen": -1.7990143299102783,
|
1487 |
+
"logits/rejected": -1.7799808979034424,
|
1488 |
+
"logps/chosen": -545.7501220703125,
|
1489 |
+
"logps/rejected": -777.5648193359375,
|
1490 |
+
"loss": 0.338,
|
1491 |
+
"rewards/accuracies": 0.8687499761581421,
|
1492 |
+
"rewards/chosen": -3.4501044750213623,
|
1493 |
+
"rewards/margins": 1.9422149658203125,
|
1494 |
+
"rewards/rejected": -5.392319202423096,
|
1495 |
+
"step": 485
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 0.9661121380160197,
|
1499 |
+
"grad_norm": 21.367843020001658,
|
1500 |
+
"learning_rate": 1.7127004595681727e-09,
|
1501 |
+
"logits/chosen": -1.8907989263534546,
|
1502 |
+
"logits/rejected": -1.803995132446289,
|
1503 |
+
"logps/chosen": -572.9863891601562,
|
1504 |
+
"logps/rejected": -869.6575317382812,
|
1505 |
+
"loss": 0.3514,
|
1506 |
+
"rewards/accuracies": 0.856249988079071,
|
1507 |
+
"rewards/chosen": -3.549314498901367,
|
1508 |
+
"rewards/margins": 2.517167568206787,
|
1509 |
+
"rewards/rejected": -6.066482067108154,
|
1510 |
+
"step": 490
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 0.9759704251386322,
|
1514 |
+
"grad_norm": 26.301841729679015,
|
1515 |
+
"learning_rate": 8.538767483325383e-10,
|
1516 |
+
"logits/chosen": -1.6898645162582397,
|
1517 |
+
"logits/rejected": -1.872666597366333,
|
1518 |
+
"logps/chosen": -564.5504760742188,
|
1519 |
+
"logps/rejected": -813.0301513671875,
|
1520 |
+
"loss": 0.3249,
|
1521 |
+
"rewards/accuracies": 0.887499988079071,
|
1522 |
+
"rewards/chosen": -3.5329060554504395,
|
1523 |
+
"rewards/margins": 2.330728054046631,
|
1524 |
+
"rewards/rejected": -5.863633632659912,
|
1525 |
+
"step": 495
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 0.9858287122612446,
|
1529 |
+
"grad_norm": 28.33067138539654,
|
1530 |
+
"learning_rate": 2.9066449079634404e-10,
|
1531 |
+
"logits/chosen": -1.81964910030365,
|
1532 |
+
"logits/rejected": -1.7677667140960693,
|
1533 |
+
"logps/chosen": -553.2039184570312,
|
1534 |
+
"logps/rejected": -806.8800048828125,
|
1535 |
+
"loss": 0.3026,
|
1536 |
+
"rewards/accuracies": 0.887499988079071,
|
1537 |
+
"rewards/chosen": -3.421668291091919,
|
1538 |
+
"rewards/margins": 2.2354369163513184,
|
1539 |
+
"rewards/rejected": -5.657104969024658,
|
1540 |
+
"step": 500
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 0.9956869993838571,
|
1544 |
+
"grad_norm": 23.713797105940532,
|
1545 |
+
"learning_rate": 2.3731937350224273e-11,
|
1546 |
+
"logits/chosen": -1.9265756607055664,
|
1547 |
+
"logits/rejected": -1.8447071313858032,
|
1548 |
+
"logps/chosen": -565.0730590820312,
|
1549 |
+
"logps/rejected": -841.3292236328125,
|
1550 |
+
"loss": 0.3122,
|
1551 |
+
"rewards/accuracies": 0.875,
|
1552 |
+
"rewards/chosen": -3.6411995887756348,
|
1553 |
+
"rewards/margins": 2.3857717514038086,
|
1554 |
+
"rewards/rejected": -6.026970863342285,
|
1555 |
+
"step": 505
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 0.999630314232902,
|
1559 |
+
"step": 507,
|
1560 |
+
"total_flos": 0.0,
|
1561 |
+
"train_loss": 0.41502543125867375,
|
1562 |
+
"train_runtime": 18234.8908,
|
1563 |
+
"train_samples_per_second": 3.56,
|
1564 |
+
"train_steps_per_second": 0.028
|
1565 |
+
}
|
1566 |
+
],
|
1567 |
+
"logging_steps": 5,
|
1568 |
+
"max_steps": 507,
|
1569 |
+
"num_input_tokens_seen": 0,
|
1570 |
+
"num_train_epochs": 1,
|
1571 |
+
"save_steps": 1000000,
|
1572 |
+
"stateful_callbacks": {
|
1573 |
+
"TrainerControl": {
|
1574 |
+
"args": {
|
1575 |
+
"should_epoch_stop": false,
|
1576 |
+
"should_evaluate": false,
|
1577 |
+
"should_log": false,
|
1578 |
+
"should_save": true,
|
1579 |
+
"should_training_stop": true
|
1580 |
+
},
|
1581 |
+
"attributes": {}
|
1582 |
+
}
|
1583 |
+
},
|
1584 |
+
"total_flos": 0.0,
|
1585 |
+
"train_batch_size": 2,
|
1586 |
+
"trial_name": null,
|
1587 |
+
"trial_params": null
|
1588 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ba6041847709d39bc52f2a755bc9830a7ea045ea36ce8708be2d504af7e0601
|
3 |
+
size 7608
|