Model save
Browse files- README.md +6 -20
- all_results.json +5 -5
- config.json +9 -12
- generation_config.json +2 -5
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- model.safetensors.index.json +292 -292
- special_tokens_map.json +21 -3
- tokenizer.json +0 -0
- tokenizer_config.json +22 -2039
- train_results.json +5 -5
- trainer_state.json +1098 -588
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- trl
|
4 |
- dpo
|
@@ -13,17 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# zephyr-7b-dpo-full
|
15 |
|
16 |
-
This model
|
17 |
-
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.0449
|
19 |
-
- Rewards/chosen: -0.6529
|
20 |
-
- Rewards/rejected: -1.2907
|
21 |
-
- Rewards/accuracies: 0.7383
|
22 |
-
- Rewards/margins: 0.6378
|
23 |
-
- Logps/rejected: -518.3444
|
24 |
-
- Logps/chosen: -448.4197
|
25 |
-
- Logits/rejected: 1.6154
|
26 |
-
- Logits/chosen: 1.4915
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -43,12 +35,12 @@ More information needed
|
|
43 |
|
44 |
The following hyperparameters were used during training:
|
45 |
- learning_rate: 5e-07
|
46 |
-
- train_batch_size:
|
47 |
- eval_batch_size: 8
|
48 |
-
- seed:
|
49 |
- distributed_type: multi-GPU
|
50 |
- num_devices: 8
|
51 |
-
- gradient_accumulation_steps:
|
52 |
- total_train_batch_size: 128
|
53 |
- total_eval_batch_size: 64
|
54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
@@ -58,12 +50,6 @@ The following hyperparameters were used during training:
|
|
58 |
|
59 |
### Training results
|
60 |
|
61 |
-
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
62 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
63 |
-
| 0.09 | 0.21 | 100 | 0.0844 | -0.0945 | -0.2957 | 0.6992 | 0.2012 | -418.8424 | -392.5748 | 0.5303 | 0.4926 |
|
64 |
-
| 0.0405 | 0.42 | 200 | 0.0452 | -0.6625 | -1.1657 | 0.7539 | 0.5032 | -505.8466 | -449.3789 | 1.2734 | 1.1859 |
|
65 |
-
| 0.0479 | 0.63 | 300 | 0.0477 | -0.5208 | -1.1204 | 0.7383 | 0.5995 | -501.3084 | -435.2133 | 1.4093 | 1.2982 |
|
66 |
-
| 0.0457 | 0.84 | 400 | 0.0449 | -0.6529 | -1.2907 | 0.7383 | 0.6378 | -518.3444 | -448.4197 | 1.6154 | 1.4915 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
base_model: HuggingFaceH4/mistral-7b-sft-beta
|
4 |
tags:
|
5 |
- trl
|
6 |
- dpo
|
|
|
15 |
|
16 |
# zephyr-7b-dpo-full
|
17 |
|
18 |
+
This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 5e-07
|
38 |
+
- train_batch_size: 8
|
39 |
- eval_batch_size: 8
|
40 |
+
- seed: 4
|
41 |
- distributed_type: multi-GPU
|
42 |
- num_devices: 8
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
- total_train_batch_size: 128
|
45 |
- total_eval_batch_size: 64
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
|
55 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.08422429972704783,
|
4 |
+
"train_runtime": 6988.5729,
|
5 |
+
"train_samples": 113028,
|
6 |
+
"train_samples_per_second": 16.173,
|
7 |
+
"train_steps_per_second": 0.126
|
8 |
}
|
config.json
CHANGED
@@ -1,28 +1,25 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"bos_token_id": 128000,
|
9 |
-
"eos_token_id": 128001,
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 14336,
|
14 |
-
"max_position_embeddings":
|
15 |
-
"model_type": "
|
16 |
"num_attention_heads": 32,
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 8,
|
19 |
-
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
-
"
|
22 |
-
"
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.35.2",
|
26 |
"use_cache": false,
|
27 |
-
"vocab_size":
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
|
3 |
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
|
|
|
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 14336,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"model_type": "mistral",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
16 |
"num_key_value_heads": 8,
|
|
|
17 |
"rms_norm_eps": 1e-05,
|
18 |
+
"rope_theta": 10000.0,
|
19 |
+
"sliding_window": 4096,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "bfloat16",
|
22 |
"transformers_version": "4.35.2",
|
23 |
"use_cache": false,
|
24 |
+
"vocab_size": 32000
|
25 |
}
|
generation_config.json
CHANGED
@@ -1,9 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"eos_token_id":
|
5 |
-
128001,
|
6 |
-
128009
|
7 |
-
],
|
8 |
"transformers_version": "4.35.2"
|
9 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
|
|
|
|
|
|
5 |
"transformers_version": "4.35.2"
|
6 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:830483ca7b1a7d164193ef40941fb8c1185bcbd9aea0f326fe666d87fc4f85db
|
3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49d1a3687da7a34f3a85bae6a2d6147ff1dc272d2dc3e7a2cf612e1866a1d34e
|
3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52e4d6b9a4cffb1d45574446b3bc4d5dbaee85c169802d75ec580a536037b327
|
3 |
size 4540516344
|
model.safetensors.index.json
CHANGED
@@ -1,298 +1,298 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
-
"lm_head.weight": "model-
|
7 |
-
"model.embed_tokens.weight": "model-00001-of-
|
8 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-
|
9 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-
|
10 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-
|
11 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-
|
12 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
13 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-
|
14 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-
|
15 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-
|
16 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-
|
17 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-
|
18 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-
|
19 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-
|
20 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-
|
21 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-
|
22 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-
|
23 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-
|
24 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-
|
25 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-
|
26 |
-
"model.layers.10.input_layernorm.weight": "model-00002-of-
|
27 |
-
"model.layers.10.mlp.down_proj.weight": "model-00002-of-
|
28 |
-
"model.layers.10.mlp.gate_proj.weight": "model-
|
29 |
-
"model.layers.10.mlp.up_proj.weight": "model-
|
30 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-
|
31 |
-
"model.layers.10.self_attn.k_proj.weight": "model-
|
32 |
-
"model.layers.10.self_attn.o_proj.weight": "model-
|
33 |
-
"model.layers.10.self_attn.q_proj.weight": "model-
|
34 |
-
"model.layers.10.self_attn.v_proj.weight": "model-
|
35 |
-
"model.layers.11.input_layernorm.weight": "model-00002-of-
|
36 |
-
"model.layers.11.mlp.down_proj.weight": "model-00002-of-
|
37 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-
|
38 |
-
"model.layers.11.mlp.up_proj.weight": "model-00002-of-
|
39 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-
|
40 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-
|
41 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-
|
42 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-
|
43 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-
|
44 |
-
"model.layers.12.input_layernorm.weight": "model-00002-of-
|
45 |
-
"model.layers.12.mlp.down_proj.weight": "model-00002-of-
|
46 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-
|
47 |
-
"model.layers.12.mlp.up_proj.weight": "model-00002-of-
|
48 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-
|
49 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-
|
50 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-
|
51 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-
|
52 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-
|
53 |
-
"model.layers.13.input_layernorm.weight": "model-00002-of-
|
54 |
-
"model.layers.13.mlp.down_proj.weight": "model-00002-of-
|
55 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-
|
56 |
-
"model.layers.13.mlp.up_proj.weight": "model-00002-of-
|
57 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-
|
58 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-
|
59 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-
|
60 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-
|
61 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-
|
62 |
-
"model.layers.14.input_layernorm.weight": "model-00002-of-
|
63 |
-
"model.layers.14.mlp.down_proj.weight": "model-00002-of-
|
64 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-
|
65 |
-
"model.layers.14.mlp.up_proj.weight": "model-00002-of-
|
66 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-
|
67 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-
|
68 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-
|
69 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-
|
70 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-
|
71 |
-
"model.layers.15.input_layernorm.weight": "model-00002-of-
|
72 |
-
"model.layers.15.mlp.down_proj.weight": "model-00002-of-
|
73 |
-
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-
|
74 |
-
"model.layers.15.mlp.up_proj.weight": "model-00002-of-
|
75 |
-
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-
|
76 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-
|
77 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-
|
78 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-
|
79 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-
|
80 |
-
"model.layers.16.input_layernorm.weight": "model-00002-of-
|
81 |
-
"model.layers.16.mlp.down_proj.weight": "model-00002-of-
|
82 |
-
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-
|
83 |
-
"model.layers.16.mlp.up_proj.weight": "model-00002-of-
|
84 |
-
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-
|
85 |
-
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-
|
86 |
-
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-
|
87 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-
|
88 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-
|
89 |
-
"model.layers.17.input_layernorm.weight": "model-00002-of-
|
90 |
-
"model.layers.17.mlp.down_proj.weight": "model-00002-of-
|
91 |
-
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-
|
92 |
-
"model.layers.17.mlp.up_proj.weight": "model-00002-of-
|
93 |
-
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-
|
94 |
-
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-
|
95 |
-
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-
|
96 |
-
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-
|
97 |
-
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-
|
98 |
-
"model.layers.18.input_layernorm.weight": "model-00002-of-
|
99 |
-
"model.layers.18.mlp.down_proj.weight": "model-00002-of-
|
100 |
-
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-
|
101 |
-
"model.layers.18.mlp.up_proj.weight": "model-00002-of-
|
102 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-
|
103 |
-
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-
|
104 |
-
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-
|
105 |
-
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-
|
106 |
-
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-
|
107 |
-
"model.layers.19.input_layernorm.weight": "model-00002-of-
|
108 |
-
"model.layers.19.mlp.down_proj.weight": "model-00002-of-
|
109 |
-
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-
|
110 |
-
"model.layers.19.mlp.up_proj.weight": "model-00002-of-
|
111 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-
|
112 |
-
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-
|
113 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-
|
114 |
-
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-
|
115 |
-
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-
|
116 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-
|
117 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-
|
118 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-
|
119 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-
|
120 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-
|
121 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-
|
122 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-
|
123 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-
|
124 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-
|
125 |
-
"model.layers.20.input_layernorm.weight": "model-
|
126 |
-
"model.layers.20.mlp.down_proj.weight": "model-
|
127 |
-
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-
|
128 |
-
"model.layers.20.mlp.up_proj.weight": "model-
|
129 |
-
"model.layers.20.post_attention_layernorm.weight": "model-
|
130 |
-
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-
|
131 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-
|
132 |
-
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-
|
133 |
-
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-
|
134 |
-
"model.layers.21.input_layernorm.weight": "model-
|
135 |
-
"model.layers.21.mlp.down_proj.weight": "model-
|
136 |
-
"model.layers.21.mlp.gate_proj.weight": "model-
|
137 |
-
"model.layers.21.mlp.up_proj.weight": "model-
|
138 |
-
"model.layers.21.post_attention_layernorm.weight": "model-
|
139 |
-
"model.layers.21.self_attn.k_proj.weight": "model-
|
140 |
-
"model.layers.21.self_attn.o_proj.weight": "model-
|
141 |
-
"model.layers.21.self_attn.q_proj.weight": "model-
|
142 |
-
"model.layers.21.self_attn.v_proj.weight": "model-
|
143 |
-
"model.layers.22.input_layernorm.weight": "model-00003-of-
|
144 |
-
"model.layers.22.mlp.down_proj.weight": "model-00003-of-
|
145 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-
|
146 |
-
"model.layers.22.mlp.up_proj.weight": "model-00003-of-
|
147 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-
|
148 |
-
"model.layers.22.self_attn.k_proj.weight": "model-
|
149 |
-
"model.layers.22.self_attn.o_proj.weight": "model-
|
150 |
-
"model.layers.22.self_attn.q_proj.weight": "model-
|
151 |
-
"model.layers.22.self_attn.v_proj.weight": "model-
|
152 |
-
"model.layers.23.input_layernorm.weight": "model-00003-of-
|
153 |
-
"model.layers.23.mlp.down_proj.weight": "model-00003-of-
|
154 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-
|
155 |
-
"model.layers.23.mlp.up_proj.weight": "model-00003-of-
|
156 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-
|
157 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-
|
158 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-
|
159 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-
|
160 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-
|
161 |
-
"model.layers.24.input_layernorm.weight": "model-00003-of-
|
162 |
-
"model.layers.24.mlp.down_proj.weight": "model-00003-of-
|
163 |
-
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-
|
164 |
-
"model.layers.24.mlp.up_proj.weight": "model-00003-of-
|
165 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-
|
166 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-
|
167 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-
|
168 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-
|
169 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-
|
170 |
-
"model.layers.25.input_layernorm.weight": "model-00003-of-
|
171 |
-
"model.layers.25.mlp.down_proj.weight": "model-00003-of-
|
172 |
-
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-
|
173 |
-
"model.layers.25.mlp.up_proj.weight": "model-00003-of-
|
174 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-
|
175 |
-
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-
|
176 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-
|
177 |
-
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-
|
178 |
-
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-
|
179 |
-
"model.layers.26.input_layernorm.weight": "model-00003-of-
|
180 |
-
"model.layers.26.mlp.down_proj.weight": "model-00003-of-
|
181 |
-
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-
|
182 |
-
"model.layers.26.mlp.up_proj.weight": "model-00003-of-
|
183 |
-
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-
|
184 |
-
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-
|
185 |
-
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-
|
186 |
-
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-
|
187 |
-
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-
|
188 |
-
"model.layers.27.input_layernorm.weight": "model-00003-of-
|
189 |
-
"model.layers.27.mlp.down_proj.weight": "model-00003-of-
|
190 |
-
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-
|
191 |
-
"model.layers.27.mlp.up_proj.weight": "model-00003-of-
|
192 |
-
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-
|
193 |
-
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-
|
194 |
-
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-
|
195 |
-
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-
|
196 |
-
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-
|
197 |
-
"model.layers.28.input_layernorm.weight": "model-00003-of-
|
198 |
-
"model.layers.28.mlp.down_proj.weight": "model-00003-of-
|
199 |
-
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-
|
200 |
-
"model.layers.28.mlp.up_proj.weight": "model-00003-of-
|
201 |
-
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-
|
202 |
-
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-
|
203 |
-
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-
|
204 |
-
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-
|
205 |
-
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-
|
206 |
-
"model.layers.29.input_layernorm.weight": "model-00003-of-
|
207 |
-
"model.layers.29.mlp.down_proj.weight": "model-00003-of-
|
208 |
-
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-
|
209 |
-
"model.layers.29.mlp.up_proj.weight": "model-00003-of-
|
210 |
-
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-
|
211 |
-
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-
|
212 |
-
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-
|
213 |
-
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-
|
214 |
-
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-
|
215 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-
|
216 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-
|
217 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-
|
218 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-
|
219 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-
|
220 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-
|
221 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-
|
222 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-
|
223 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-
|
224 |
-
"model.layers.30.input_layernorm.weight": "model-00003-of-
|
225 |
-
"model.layers.30.mlp.down_proj.weight": "model-00003-of-
|
226 |
-
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-
|
227 |
-
"model.layers.30.mlp.up_proj.weight": "model-00003-of-
|
228 |
-
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-
|
229 |
-
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-
|
230 |
-
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-
|
231 |
-
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-
|
232 |
-
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-
|
233 |
-
"model.layers.31.input_layernorm.weight": "model-
|
234 |
-
"model.layers.31.mlp.down_proj.weight": "model-
|
235 |
-
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-
|
236 |
-
"model.layers.31.mlp.up_proj.weight": "model-00003-of-
|
237 |
-
"model.layers.31.post_attention_layernorm.weight": "model-
|
238 |
-
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-
|
239 |
-
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-
|
240 |
-
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-
|
241 |
-
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-
|
242 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-
|
243 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-
|
244 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-
|
245 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-
|
246 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-
|
247 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-
|
248 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-
|
249 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-
|
250 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-
|
251 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-
|
252 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-
|
253 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-
|
254 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-
|
255 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-
|
256 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-
|
257 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-
|
258 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-
|
259 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-
|
260 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-
|
261 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-
|
262 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-
|
263 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-
|
264 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-
|
265 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-
|
266 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-
|
267 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-
|
268 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-
|
269 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-
|
270 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-
|
271 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-
|
272 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-
|
273 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-
|
274 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-
|
275 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-
|
276 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-
|
277 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-
|
278 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-
|
279 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-
|
280 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-
|
281 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-
|
282 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-
|
283 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-
|
284 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-
|
285 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-
|
286 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-
|
287 |
-
"model.layers.9.input_layernorm.weight": "model-
|
288 |
-
"model.layers.9.mlp.down_proj.weight": "model-
|
289 |
-
"model.layers.9.mlp.gate_proj.weight": "model-
|
290 |
-
"model.layers.9.mlp.up_proj.weight": "model-
|
291 |
-
"model.layers.9.post_attention_layernorm.weight": "model-
|
292 |
-
"model.layers.9.self_attn.k_proj.weight": "model-
|
293 |
-
"model.layers.9.self_attn.o_proj.weight": "model-
|
294 |
-
"model.layers.9.self_attn.q_proj.weight": "model-
|
295 |
-
"model.layers.9.self_attn.v_proj.weight": "model-
|
296 |
-
"model.norm.weight": "model-
|
297 |
}
|
298 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
},
|
5 |
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
297 |
}
|
298 |
}
|
special_tokens_map.json
CHANGED
@@ -1,17 +1,35 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
"lstrip": false,
|
10 |
"normalized": false,
|
11 |
"rstrip": false,
|
12 |
"single_word": false
|
13 |
},
|
14 |
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
"lstrip": false,
|
17 |
"normalized": false,
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,2047 +1,23 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"128003": {
|
28 |
-
"content": "<|reserved_special_token_1|>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"128004": {
|
36 |
-
"content": "<|reserved_special_token_2|>",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"128005": {
|
44 |
-
"content": "<|reserved_special_token_3|>",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
"128006": {
|
52 |
-
"content": "<|start_header_id|>",
|
53 |
-
"lstrip": false,
|
54 |
-
"normalized": false,
|
55 |
-
"rstrip": false,
|
56 |
-
"single_word": false,
|
57 |
-
"special": true
|
58 |
-
},
|
59 |
-
"128007": {
|
60 |
-
"content": "<|end_header_id|>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": false,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false,
|
65 |
-
"special": true
|
66 |
-
},
|
67 |
-
"128008": {
|
68 |
-
"content": "<|reserved_special_token_4|>",
|
69 |
-
"lstrip": false,
|
70 |
-
"normalized": false,
|
71 |
-
"rstrip": false,
|
72 |
-
"single_word": false,
|
73 |
-
"special": true
|
74 |
-
},
|
75 |
-
"128009": {
|
76 |
-
"content": "<|eot_id|>",
|
77 |
-
"lstrip": false,
|
78 |
-
"normalized": false,
|
79 |
-
"rstrip": false,
|
80 |
-
"single_word": false,
|
81 |
-
"special": true
|
82 |
-
},
|
83 |
-
"128010": {
|
84 |
-
"content": "<|reserved_special_token_5|>",
|
85 |
-
"lstrip": false,
|
86 |
-
"normalized": false,
|
87 |
-
"rstrip": false,
|
88 |
-
"single_word": false,
|
89 |
-
"special": true
|
90 |
-
},
|
91 |
-
"128011": {
|
92 |
-
"content": "<|reserved_special_token_6|>",
|
93 |
-
"lstrip": false,
|
94 |
-
"normalized": false,
|
95 |
-
"rstrip": false,
|
96 |
-
"single_word": false,
|
97 |
-
"special": true
|
98 |
-
},
|
99 |
-
"128012": {
|
100 |
-
"content": "<|reserved_special_token_7|>",
|
101 |
-
"lstrip": false,
|
102 |
-
"normalized": false,
|
103 |
-
"rstrip": false,
|
104 |
-
"single_word": false,
|
105 |
-
"special": true
|
106 |
-
},
|
107 |
-
"128013": {
|
108 |
-
"content": "<|reserved_special_token_8|>",
|
109 |
-
"lstrip": false,
|
110 |
-
"normalized": false,
|
111 |
-
"rstrip": false,
|
112 |
-
"single_word": false,
|
113 |
-
"special": true
|
114 |
-
},
|
115 |
-
"128014": {
|
116 |
-
"content": "<|reserved_special_token_9|>",
|
117 |
-
"lstrip": false,
|
118 |
-
"normalized": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"single_word": false,
|
121 |
-
"special": true
|
122 |
-
},
|
123 |
-
"128015": {
|
124 |
-
"content": "<|reserved_special_token_10|>",
|
125 |
-
"lstrip": false,
|
126 |
-
"normalized": false,
|
127 |
-
"rstrip": false,
|
128 |
-
"single_word": false,
|
129 |
-
"special": true
|
130 |
-
},
|
131 |
-
"128016": {
|
132 |
-
"content": "<|reserved_special_token_11|>",
|
133 |
-
"lstrip": false,
|
134 |
-
"normalized": false,
|
135 |
-
"rstrip": false,
|
136 |
-
"single_word": false,
|
137 |
-
"special": true
|
138 |
-
},
|
139 |
-
"128017": {
|
140 |
-
"content": "<|reserved_special_token_12|>",
|
141 |
-
"lstrip": false,
|
142 |
-
"normalized": false,
|
143 |
-
"rstrip": false,
|
144 |
-
"single_word": false,
|
145 |
-
"special": true
|
146 |
-
},
|
147 |
-
"128018": {
|
148 |
-
"content": "<|reserved_special_token_13|>",
|
149 |
-
"lstrip": false,
|
150 |
-
"normalized": false,
|
151 |
-
"rstrip": false,
|
152 |
-
"single_word": false,
|
153 |
-
"special": true
|
154 |
-
},
|
155 |
-
"128019": {
|
156 |
-
"content": "<|reserved_special_token_14|>",
|
157 |
-
"lstrip": false,
|
158 |
-
"normalized": false,
|
159 |
-
"rstrip": false,
|
160 |
-
"single_word": false,
|
161 |
-
"special": true
|
162 |
-
},
|
163 |
-
"128020": {
|
164 |
-
"content": "<|reserved_special_token_15|>",
|
165 |
-
"lstrip": false,
|
166 |
-
"normalized": false,
|
167 |
-
"rstrip": false,
|
168 |
-
"single_word": false,
|
169 |
-
"special": true
|
170 |
-
},
|
171 |
-
"128021": {
|
172 |
-
"content": "<|reserved_special_token_16|>",
|
173 |
-
"lstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"rstrip": false,
|
176 |
-
"single_word": false,
|
177 |
-
"special": true
|
178 |
-
},
|
179 |
-
"128022": {
|
180 |
-
"content": "<|reserved_special_token_17|>",
|
181 |
-
"lstrip": false,
|
182 |
-
"normalized": false,
|
183 |
-
"rstrip": false,
|
184 |
-
"single_word": false,
|
185 |
-
"special": true
|
186 |
-
},
|
187 |
-
"128023": {
|
188 |
-
"content": "<|reserved_special_token_18|>",
|
189 |
-
"lstrip": false,
|
190 |
-
"normalized": false,
|
191 |
-
"rstrip": false,
|
192 |
-
"single_word": false,
|
193 |
-
"special": true
|
194 |
-
},
|
195 |
-
"128024": {
|
196 |
-
"content": "<|reserved_special_token_19|>",
|
197 |
-
"lstrip": false,
|
198 |
-
"normalized": false,
|
199 |
-
"rstrip": false,
|
200 |
-
"single_word": false,
|
201 |
-
"special": true
|
202 |
-
},
|
203 |
-
"128025": {
|
204 |
-
"content": "<|reserved_special_token_20|>",
|
205 |
-
"lstrip": false,
|
206 |
-
"normalized": false,
|
207 |
-
"rstrip": false,
|
208 |
-
"single_word": false,
|
209 |
-
"special": true
|
210 |
-
},
|
211 |
-
"128026": {
|
212 |
-
"content": "<|reserved_special_token_21|>",
|
213 |
-
"lstrip": false,
|
214 |
-
"normalized": false,
|
215 |
-
"rstrip": false,
|
216 |
-
"single_word": false,
|
217 |
-
"special": true
|
218 |
-
},
|
219 |
-
"128027": {
|
220 |
-
"content": "<|reserved_special_token_22|>",
|
221 |
-
"lstrip": false,
|
222 |
-
"normalized": false,
|
223 |
-
"rstrip": false,
|
224 |
-
"single_word": false,
|
225 |
-
"special": true
|
226 |
-
},
|
227 |
-
"128028": {
|
228 |
-
"content": "<|reserved_special_token_23|>",
|
229 |
-
"lstrip": false,
|
230 |
-
"normalized": false,
|
231 |
-
"rstrip": false,
|
232 |
-
"single_word": false,
|
233 |
-
"special": true
|
234 |
-
},
|
235 |
-
"128029": {
|
236 |
-
"content": "<|reserved_special_token_24|>",
|
237 |
-
"lstrip": false,
|
238 |
-
"normalized": false,
|
239 |
-
"rstrip": false,
|
240 |
-
"single_word": false,
|
241 |
-
"special": true
|
242 |
-
},
|
243 |
-
"128030": {
|
244 |
-
"content": "<|reserved_special_token_25|>",
|
245 |
-
"lstrip": false,
|
246 |
-
"normalized": false,
|
247 |
-
"rstrip": false,
|
248 |
-
"single_word": false,
|
249 |
-
"special": true
|
250 |
-
},
|
251 |
-
"128031": {
|
252 |
-
"content": "<|reserved_special_token_26|>",
|
253 |
-
"lstrip": false,
|
254 |
-
"normalized": false,
|
255 |
-
"rstrip": false,
|
256 |
-
"single_word": false,
|
257 |
-
"special": true
|
258 |
-
},
|
259 |
-
"128032": {
|
260 |
-
"content": "<|reserved_special_token_27|>",
|
261 |
-
"lstrip": false,
|
262 |
-
"normalized": false,
|
263 |
-
"rstrip": false,
|
264 |
-
"single_word": false,
|
265 |
-
"special": true
|
266 |
-
},
|
267 |
-
"128033": {
|
268 |
-
"content": "<|reserved_special_token_28|>",
|
269 |
-
"lstrip": false,
|
270 |
-
"normalized": false,
|
271 |
-
"rstrip": false,
|
272 |
-
"single_word": false,
|
273 |
-
"special": true
|
274 |
-
},
|
275 |
-
"128034": {
|
276 |
-
"content": "<|reserved_special_token_29|>",
|
277 |
-
"lstrip": false,
|
278 |
-
"normalized": false,
|
279 |
-
"rstrip": false,
|
280 |
-
"single_word": false,
|
281 |
-
"special": true
|
282 |
-
},
|
283 |
-
"128035": {
|
284 |
-
"content": "<|reserved_special_token_30|>",
|
285 |
-
"lstrip": false,
|
286 |
-
"normalized": false,
|
287 |
-
"rstrip": false,
|
288 |
-
"single_word": false,
|
289 |
-
"special": true
|
290 |
-
},
|
291 |
-
"128036": {
|
292 |
-
"content": "<|reserved_special_token_31|>",
|
293 |
-
"lstrip": false,
|
294 |
-
"normalized": false,
|
295 |
-
"rstrip": false,
|
296 |
-
"single_word": false,
|
297 |
-
"special": true
|
298 |
-
},
|
299 |
-
"128037": {
|
300 |
-
"content": "<|reserved_special_token_32|>",
|
301 |
-
"lstrip": false,
|
302 |
-
"normalized": false,
|
303 |
-
"rstrip": false,
|
304 |
-
"single_word": false,
|
305 |
-
"special": true
|
306 |
-
},
|
307 |
-
"128038": {
|
308 |
-
"content": "<|reserved_special_token_33|>",
|
309 |
-
"lstrip": false,
|
310 |
-
"normalized": false,
|
311 |
-
"rstrip": false,
|
312 |
-
"single_word": false,
|
313 |
-
"special": true
|
314 |
-
},
|
315 |
-
"128039": {
|
316 |
-
"content": "<|reserved_special_token_34|>",
|
317 |
-
"lstrip": false,
|
318 |
-
"normalized": false,
|
319 |
-
"rstrip": false,
|
320 |
-
"single_word": false,
|
321 |
-
"special": true
|
322 |
-
},
|
323 |
-
"128040": {
|
324 |
-
"content": "<|reserved_special_token_35|>",
|
325 |
-
"lstrip": false,
|
326 |
-
"normalized": false,
|
327 |
-
"rstrip": false,
|
328 |
-
"single_word": false,
|
329 |
-
"special": true
|
330 |
-
},
|
331 |
-
"128041": {
|
332 |
-
"content": "<|reserved_special_token_36|>",
|
333 |
-
"lstrip": false,
|
334 |
-
"normalized": false,
|
335 |
-
"rstrip": false,
|
336 |
-
"single_word": false,
|
337 |
-
"special": true
|
338 |
-
},
|
339 |
-
"128042": {
|
340 |
-
"content": "<|reserved_special_token_37|>",
|
341 |
-
"lstrip": false,
|
342 |
-
"normalized": false,
|
343 |
-
"rstrip": false,
|
344 |
-
"single_word": false,
|
345 |
-
"special": true
|
346 |
-
},
|
347 |
-
"128043": {
|
348 |
-
"content": "<|reserved_special_token_38|>",
|
349 |
-
"lstrip": false,
|
350 |
-
"normalized": false,
|
351 |
-
"rstrip": false,
|
352 |
-
"single_word": false,
|
353 |
-
"special": true
|
354 |
-
},
|
355 |
-
"128044": {
|
356 |
-
"content": "<|reserved_special_token_39|>",
|
357 |
-
"lstrip": false,
|
358 |
-
"normalized": false,
|
359 |
-
"rstrip": false,
|
360 |
-
"single_word": false,
|
361 |
-
"special": true
|
362 |
-
},
|
363 |
-
"128045": {
|
364 |
-
"content": "<|reserved_special_token_40|>",
|
365 |
-
"lstrip": false,
|
366 |
-
"normalized": false,
|
367 |
-
"rstrip": false,
|
368 |
-
"single_word": false,
|
369 |
-
"special": true
|
370 |
-
},
|
371 |
-
"128046": {
|
372 |
-
"content": "<|reserved_special_token_41|>",
|
373 |
-
"lstrip": false,
|
374 |
-
"normalized": false,
|
375 |
-
"rstrip": false,
|
376 |
-
"single_word": false,
|
377 |
-
"special": true
|
378 |
-
},
|
379 |
-
"128047": {
|
380 |
-
"content": "<|reserved_special_token_42|>",
|
381 |
-
"lstrip": false,
|
382 |
-
"normalized": false,
|
383 |
-
"rstrip": false,
|
384 |
-
"single_word": false,
|
385 |
-
"special": true
|
386 |
-
},
|
387 |
-
"128048": {
|
388 |
-
"content": "<|reserved_special_token_43|>",
|
389 |
-
"lstrip": false,
|
390 |
-
"normalized": false,
|
391 |
-
"rstrip": false,
|
392 |
-
"single_word": false,
|
393 |
-
"special": true
|
394 |
-
},
|
395 |
-
"128049": {
|
396 |
-
"content": "<|reserved_special_token_44|>",
|
397 |
-
"lstrip": false,
|
398 |
-
"normalized": false,
|
399 |
-
"rstrip": false,
|
400 |
-
"single_word": false,
|
401 |
-
"special": true
|
402 |
-
},
|
403 |
-
"128050": {
|
404 |
-
"content": "<|reserved_special_token_45|>",
|
405 |
-
"lstrip": false,
|
406 |
-
"normalized": false,
|
407 |
-
"rstrip": false,
|
408 |
-
"single_word": false,
|
409 |
-
"special": true
|
410 |
-
},
|
411 |
-
"128051": {
|
412 |
-
"content": "<|reserved_special_token_46|>",
|
413 |
-
"lstrip": false,
|
414 |
-
"normalized": false,
|
415 |
-
"rstrip": false,
|
416 |
-
"single_word": false,
|
417 |
-
"special": true
|
418 |
-
},
|
419 |
-
"128052": {
|
420 |
-
"content": "<|reserved_special_token_47|>",
|
421 |
-
"lstrip": false,
|
422 |
-
"normalized": false,
|
423 |
-
"rstrip": false,
|
424 |
-
"single_word": false,
|
425 |
-
"special": true
|
426 |
-
},
|
427 |
-
"128053": {
|
428 |
-
"content": "<|reserved_special_token_48|>",
|
429 |
-
"lstrip": false,
|
430 |
-
"normalized": false,
|
431 |
-
"rstrip": false,
|
432 |
-
"single_word": false,
|
433 |
-
"special": true
|
434 |
-
},
|
435 |
-
"128054": {
|
436 |
-
"content": "<|reserved_special_token_49|>",
|
437 |
-
"lstrip": false,
|
438 |
-
"normalized": false,
|
439 |
-
"rstrip": false,
|
440 |
-
"single_word": false,
|
441 |
-
"special": true
|
442 |
-
},
|
443 |
-
"128055": {
|
444 |
-
"content": "<|reserved_special_token_50|>",
|
445 |
-
"lstrip": false,
|
446 |
-
"normalized": false,
|
447 |
-
"rstrip": false,
|
448 |
-
"single_word": false,
|
449 |
-
"special": true
|
450 |
-
},
|
451 |
-
"128056": {
|
452 |
-
"content": "<|reserved_special_token_51|>",
|
453 |
-
"lstrip": false,
|
454 |
-
"normalized": false,
|
455 |
-
"rstrip": false,
|
456 |
-
"single_word": false,
|
457 |
-
"special": true
|
458 |
-
},
|
459 |
-
"128057": {
|
460 |
-
"content": "<|reserved_special_token_52|>",
|
461 |
-
"lstrip": false,
|
462 |
-
"normalized": false,
|
463 |
-
"rstrip": false,
|
464 |
-
"single_word": false,
|
465 |
-
"special": true
|
466 |
-
},
|
467 |
-
"128058": {
|
468 |
-
"content": "<|reserved_special_token_53|>",
|
469 |
-
"lstrip": false,
|
470 |
-
"normalized": false,
|
471 |
-
"rstrip": false,
|
472 |
-
"single_word": false,
|
473 |
-
"special": true
|
474 |
-
},
|
475 |
-
"128059": {
|
476 |
-
"content": "<|reserved_special_token_54|>",
|
477 |
-
"lstrip": false,
|
478 |
-
"normalized": false,
|
479 |
-
"rstrip": false,
|
480 |
-
"single_word": false,
|
481 |
-
"special": true
|
482 |
-
},
|
483 |
-
"128060": {
|
484 |
-
"content": "<|reserved_special_token_55|>",
|
485 |
-
"lstrip": false,
|
486 |
-
"normalized": false,
|
487 |
-
"rstrip": false,
|
488 |
-
"single_word": false,
|
489 |
-
"special": true
|
490 |
-
},
|
491 |
-
"128061": {
|
492 |
-
"content": "<|reserved_special_token_56|>",
|
493 |
-
"lstrip": false,
|
494 |
-
"normalized": false,
|
495 |
-
"rstrip": false,
|
496 |
-
"single_word": false,
|
497 |
-
"special": true
|
498 |
-
},
|
499 |
-
"128062": {
|
500 |
-
"content": "<|reserved_special_token_57|>",
|
501 |
-
"lstrip": false,
|
502 |
-
"normalized": false,
|
503 |
-
"rstrip": false,
|
504 |
-
"single_word": false,
|
505 |
-
"special": true
|
506 |
-
},
|
507 |
-
"128063": {
|
508 |
-
"content": "<|reserved_special_token_58|>",
|
509 |
-
"lstrip": false,
|
510 |
-
"normalized": false,
|
511 |
-
"rstrip": false,
|
512 |
-
"single_word": false,
|
513 |
-
"special": true
|
514 |
-
},
|
515 |
-
"128064": {
|
516 |
-
"content": "<|reserved_special_token_59|>",
|
517 |
-
"lstrip": false,
|
518 |
-
"normalized": false,
|
519 |
-
"rstrip": false,
|
520 |
-
"single_word": false,
|
521 |
-
"special": true
|
522 |
-
},
|
523 |
-
"128065": {
|
524 |
-
"content": "<|reserved_special_token_60|>",
|
525 |
-
"lstrip": false,
|
526 |
-
"normalized": false,
|
527 |
-
"rstrip": false,
|
528 |
-
"single_word": false,
|
529 |
-
"special": true
|
530 |
-
},
|
531 |
-
"128066": {
|
532 |
-
"content": "<|reserved_special_token_61|>",
|
533 |
-
"lstrip": false,
|
534 |
-
"normalized": false,
|
535 |
-
"rstrip": false,
|
536 |
-
"single_word": false,
|
537 |
-
"special": true
|
538 |
-
},
|
539 |
-
"128067": {
|
540 |
-
"content": "<|reserved_special_token_62|>",
|
541 |
-
"lstrip": false,
|
542 |
-
"normalized": false,
|
543 |
-
"rstrip": false,
|
544 |
-
"single_word": false,
|
545 |
-
"special": true
|
546 |
-
},
|
547 |
-
"128068": {
|
548 |
-
"content": "<|reserved_special_token_63|>",
|
549 |
-
"lstrip": false,
|
550 |
-
"normalized": false,
|
551 |
-
"rstrip": false,
|
552 |
-
"single_word": false,
|
553 |
-
"special": true
|
554 |
-
},
|
555 |
-
"128069": {
|
556 |
-
"content": "<|reserved_special_token_64|>",
|
557 |
-
"lstrip": false,
|
558 |
-
"normalized": false,
|
559 |
-
"rstrip": false,
|
560 |
-
"single_word": false,
|
561 |
-
"special": true
|
562 |
-
},
|
563 |
-
"128070": {
|
564 |
-
"content": "<|reserved_special_token_65|>",
|
565 |
-
"lstrip": false,
|
566 |
-
"normalized": false,
|
567 |
-
"rstrip": false,
|
568 |
-
"single_word": false,
|
569 |
-
"special": true
|
570 |
-
},
|
571 |
-
"128071": {
|
572 |
-
"content": "<|reserved_special_token_66|>",
|
573 |
-
"lstrip": false,
|
574 |
-
"normalized": false,
|
575 |
-
"rstrip": false,
|
576 |
-
"single_word": false,
|
577 |
-
"special": true
|
578 |
-
},
|
579 |
-
"128072": {
|
580 |
-
"content": "<|reserved_special_token_67|>",
|
581 |
-
"lstrip": false,
|
582 |
-
"normalized": false,
|
583 |
-
"rstrip": false,
|
584 |
-
"single_word": false,
|
585 |
-
"special": true
|
586 |
-
},
|
587 |
-
"128073": {
|
588 |
-
"content": "<|reserved_special_token_68|>",
|
589 |
-
"lstrip": false,
|
590 |
-
"normalized": false,
|
591 |
-
"rstrip": false,
|
592 |
-
"single_word": false,
|
593 |
-
"special": true
|
594 |
-
},
|
595 |
-
"128074": {
|
596 |
-
"content": "<|reserved_special_token_69|>",
|
597 |
-
"lstrip": false,
|
598 |
-
"normalized": false,
|
599 |
-
"rstrip": false,
|
600 |
-
"single_word": false,
|
601 |
-
"special": true
|
602 |
-
},
|
603 |
-
"128075": {
|
604 |
-
"content": "<|reserved_special_token_70|>",
|
605 |
-
"lstrip": false,
|
606 |
-
"normalized": false,
|
607 |
-
"rstrip": false,
|
608 |
-
"single_word": false,
|
609 |
-
"special": true
|
610 |
-
},
|
611 |
-
"128076": {
|
612 |
-
"content": "<|reserved_special_token_71|>",
|
613 |
-
"lstrip": false,
|
614 |
-
"normalized": false,
|
615 |
-
"rstrip": false,
|
616 |
-
"single_word": false,
|
617 |
-
"special": true
|
618 |
-
},
|
619 |
-
"128077": {
|
620 |
-
"content": "<|reserved_special_token_72|>",
|
621 |
-
"lstrip": false,
|
622 |
-
"normalized": false,
|
623 |
-
"rstrip": false,
|
624 |
-
"single_word": false,
|
625 |
-
"special": true
|
626 |
-
},
|
627 |
-
"128078": {
|
628 |
-
"content": "<|reserved_special_token_73|>",
|
629 |
-
"lstrip": false,
|
630 |
-
"normalized": false,
|
631 |
-
"rstrip": false,
|
632 |
-
"single_word": false,
|
633 |
-
"special": true
|
634 |
-
},
|
635 |
-
"128079": {
|
636 |
-
"content": "<|reserved_special_token_74|>",
|
637 |
-
"lstrip": false,
|
638 |
-
"normalized": false,
|
639 |
-
"rstrip": false,
|
640 |
-
"single_word": false,
|
641 |
-
"special": true
|
642 |
-
},
|
643 |
-
"128080": {
|
644 |
-
"content": "<|reserved_special_token_75|>",
|
645 |
-
"lstrip": false,
|
646 |
-
"normalized": false,
|
647 |
-
"rstrip": false,
|
648 |
-
"single_word": false,
|
649 |
-
"special": true
|
650 |
-
},
|
651 |
-
"128081": {
|
652 |
-
"content": "<|reserved_special_token_76|>",
|
653 |
-
"lstrip": false,
|
654 |
-
"normalized": false,
|
655 |
-
"rstrip": false,
|
656 |
-
"single_word": false,
|
657 |
-
"special": true
|
658 |
-
},
|
659 |
-
"128082": {
|
660 |
-
"content": "<|reserved_special_token_77|>",
|
661 |
-
"lstrip": false,
|
662 |
-
"normalized": false,
|
663 |
-
"rstrip": false,
|
664 |
-
"single_word": false,
|
665 |
-
"special": true
|
666 |
-
},
|
667 |
-
"128083": {
|
668 |
-
"content": "<|reserved_special_token_78|>",
|
669 |
-
"lstrip": false,
|
670 |
-
"normalized": false,
|
671 |
-
"rstrip": false,
|
672 |
-
"single_word": false,
|
673 |
-
"special": true
|
674 |
-
},
|
675 |
-
"128084": {
|
676 |
-
"content": "<|reserved_special_token_79|>",
|
677 |
-
"lstrip": false,
|
678 |
-
"normalized": false,
|
679 |
-
"rstrip": false,
|
680 |
-
"single_word": false,
|
681 |
-
"special": true
|
682 |
-
},
|
683 |
-
"128085": {
|
684 |
-
"content": "<|reserved_special_token_80|>",
|
685 |
-
"lstrip": false,
|
686 |
-
"normalized": false,
|
687 |
-
"rstrip": false,
|
688 |
-
"single_word": false,
|
689 |
-
"special": true
|
690 |
-
},
|
691 |
-
"128086": {
|
692 |
-
"content": "<|reserved_special_token_81|>",
|
693 |
-
"lstrip": false,
|
694 |
-
"normalized": false,
|
695 |
-
"rstrip": false,
|
696 |
-
"single_word": false,
|
697 |
-
"special": true
|
698 |
-
},
|
699 |
-
"128087": {
|
700 |
-
"content": "<|reserved_special_token_82|>",
|
701 |
-
"lstrip": false,
|
702 |
-
"normalized": false,
|
703 |
-
"rstrip": false,
|
704 |
-
"single_word": false,
|
705 |
-
"special": true
|
706 |
-
},
|
707 |
-
"128088": {
|
708 |
-
"content": "<|reserved_special_token_83|>",
|
709 |
-
"lstrip": false,
|
710 |
-
"normalized": false,
|
711 |
-
"rstrip": false,
|
712 |
-
"single_word": false,
|
713 |
-
"special": true
|
714 |
-
},
|
715 |
-
"128089": {
|
716 |
-
"content": "<|reserved_special_token_84|>",
|
717 |
-
"lstrip": false,
|
718 |
-
"normalized": false,
|
719 |
-
"rstrip": false,
|
720 |
-
"single_word": false,
|
721 |
-
"special": true
|
722 |
-
},
|
723 |
-
"128090": {
|
724 |
-
"content": "<|reserved_special_token_85|>",
|
725 |
-
"lstrip": false,
|
726 |
-
"normalized": false,
|
727 |
-
"rstrip": false,
|
728 |
-
"single_word": false,
|
729 |
-
"special": true
|
730 |
-
},
|
731 |
-
"128091": {
|
732 |
-
"content": "<|reserved_special_token_86|>",
|
733 |
-
"lstrip": false,
|
734 |
-
"normalized": false,
|
735 |
-
"rstrip": false,
|
736 |
-
"single_word": false,
|
737 |
-
"special": true
|
738 |
-
},
|
739 |
-
"128092": {
|
740 |
-
"content": "<|reserved_special_token_87|>",
|
741 |
-
"lstrip": false,
|
742 |
-
"normalized": false,
|
743 |
-
"rstrip": false,
|
744 |
-
"single_word": false,
|
745 |
-
"special": true
|
746 |
-
},
|
747 |
-
"128093": {
|
748 |
-
"content": "<|reserved_special_token_88|>",
|
749 |
-
"lstrip": false,
|
750 |
-
"normalized": false,
|
751 |
-
"rstrip": false,
|
752 |
-
"single_word": false,
|
753 |
-
"special": true
|
754 |
-
},
|
755 |
-
"128094": {
|
756 |
-
"content": "<|reserved_special_token_89|>",
|
757 |
-
"lstrip": false,
|
758 |
-
"normalized": false,
|
759 |
-
"rstrip": false,
|
760 |
-
"single_word": false,
|
761 |
-
"special": true
|
762 |
-
},
|
763 |
-
"128095": {
|
764 |
-
"content": "<|reserved_special_token_90|>",
|
765 |
-
"lstrip": false,
|
766 |
-
"normalized": false,
|
767 |
-
"rstrip": false,
|
768 |
-
"single_word": false,
|
769 |
-
"special": true
|
770 |
-
},
|
771 |
-
"128096": {
|
772 |
-
"content": "<|reserved_special_token_91|>",
|
773 |
-
"lstrip": false,
|
774 |
-
"normalized": false,
|
775 |
-
"rstrip": false,
|
776 |
-
"single_word": false,
|
777 |
-
"special": true
|
778 |
-
},
|
779 |
-
"128097": {
|
780 |
-
"content": "<|reserved_special_token_92|>",
|
781 |
-
"lstrip": false,
|
782 |
-
"normalized": false,
|
783 |
-
"rstrip": false,
|
784 |
-
"single_word": false,
|
785 |
-
"special": true
|
786 |
-
},
|
787 |
-
"128098": {
|
788 |
-
"content": "<|reserved_special_token_93|>",
|
789 |
-
"lstrip": false,
|
790 |
-
"normalized": false,
|
791 |
-
"rstrip": false,
|
792 |
-
"single_word": false,
|
793 |
-
"special": true
|
794 |
-
},
|
795 |
-
"128099": {
|
796 |
-
"content": "<|reserved_special_token_94|>",
|
797 |
-
"lstrip": false,
|
798 |
-
"normalized": false,
|
799 |
-
"rstrip": false,
|
800 |
-
"single_word": false,
|
801 |
-
"special": true
|
802 |
-
},
|
803 |
-
"128100": {
|
804 |
-
"content": "<|reserved_special_token_95|>",
|
805 |
-
"lstrip": false,
|
806 |
-
"normalized": false,
|
807 |
-
"rstrip": false,
|
808 |
-
"single_word": false,
|
809 |
-
"special": true
|
810 |
-
},
|
811 |
-
"128101": {
|
812 |
-
"content": "<|reserved_special_token_96|>",
|
813 |
-
"lstrip": false,
|
814 |
-
"normalized": false,
|
815 |
-
"rstrip": false,
|
816 |
-
"single_word": false,
|
817 |
-
"special": true
|
818 |
-
},
|
819 |
-
"128102": {
|
820 |
-
"content": "<|reserved_special_token_97|>",
|
821 |
-
"lstrip": false,
|
822 |
-
"normalized": false,
|
823 |
-
"rstrip": false,
|
824 |
-
"single_word": false,
|
825 |
-
"special": true
|
826 |
-
},
|
827 |
-
"128103": {
|
828 |
-
"content": "<|reserved_special_token_98|>",
|
829 |
-
"lstrip": false,
|
830 |
-
"normalized": false,
|
831 |
-
"rstrip": false,
|
832 |
-
"single_word": false,
|
833 |
-
"special": true
|
834 |
-
},
|
835 |
-
"128104": {
|
836 |
-
"content": "<|reserved_special_token_99|>",
|
837 |
-
"lstrip": false,
|
838 |
-
"normalized": false,
|
839 |
-
"rstrip": false,
|
840 |
-
"single_word": false,
|
841 |
-
"special": true
|
842 |
-
},
|
843 |
-
"128105": {
|
844 |
-
"content": "<|reserved_special_token_100|>",
|
845 |
-
"lstrip": false,
|
846 |
-
"normalized": false,
|
847 |
-
"rstrip": false,
|
848 |
-
"single_word": false,
|
849 |
-
"special": true
|
850 |
-
},
|
851 |
-
"128106": {
|
852 |
-
"content": "<|reserved_special_token_101|>",
|
853 |
-
"lstrip": false,
|
854 |
-
"normalized": false,
|
855 |
-
"rstrip": false,
|
856 |
-
"single_word": false,
|
857 |
-
"special": true
|
858 |
-
},
|
859 |
-
"128107": {
|
860 |
-
"content": "<|reserved_special_token_102|>",
|
861 |
-
"lstrip": false,
|
862 |
-
"normalized": false,
|
863 |
-
"rstrip": false,
|
864 |
-
"single_word": false,
|
865 |
-
"special": true
|
866 |
-
},
|
867 |
-
"128108": {
|
868 |
-
"content": "<|reserved_special_token_103|>",
|
869 |
-
"lstrip": false,
|
870 |
-
"normalized": false,
|
871 |
-
"rstrip": false,
|
872 |
-
"single_word": false,
|
873 |
-
"special": true
|
874 |
-
},
|
875 |
-
"128109": {
|
876 |
-
"content": "<|reserved_special_token_104|>",
|
877 |
-
"lstrip": false,
|
878 |
-
"normalized": false,
|
879 |
-
"rstrip": false,
|
880 |
-
"single_word": false,
|
881 |
-
"special": true
|
882 |
-
},
|
883 |
-
"128110": {
|
884 |
-
"content": "<|reserved_special_token_105|>",
|
885 |
-
"lstrip": false,
|
886 |
-
"normalized": false,
|
887 |
-
"rstrip": false,
|
888 |
-
"single_word": false,
|
889 |
-
"special": true
|
890 |
-
},
|
891 |
-
"128111": {
|
892 |
-
"content": "<|reserved_special_token_106|>",
|
893 |
-
"lstrip": false,
|
894 |
-
"normalized": false,
|
895 |
-
"rstrip": false,
|
896 |
-
"single_word": false,
|
897 |
-
"special": true
|
898 |
-
},
|
899 |
-
"128112": {
|
900 |
-
"content": "<|reserved_special_token_107|>",
|
901 |
-
"lstrip": false,
|
902 |
-
"normalized": false,
|
903 |
-
"rstrip": false,
|
904 |
-
"single_word": false,
|
905 |
-
"special": true
|
906 |
-
},
|
907 |
-
"128113": {
|
908 |
-
"content": "<|reserved_special_token_108|>",
|
909 |
-
"lstrip": false,
|
910 |
-
"normalized": false,
|
911 |
-
"rstrip": false,
|
912 |
-
"single_word": false,
|
913 |
-
"special": true
|
914 |
-
},
|
915 |
-
"128114": {
|
916 |
-
"content": "<|reserved_special_token_109|>",
|
917 |
-
"lstrip": false,
|
918 |
-
"normalized": false,
|
919 |
-
"rstrip": false,
|
920 |
-
"single_word": false,
|
921 |
-
"special": true
|
922 |
-
},
|
923 |
-
"128115": {
|
924 |
-
"content": "<|reserved_special_token_110|>",
|
925 |
-
"lstrip": false,
|
926 |
-
"normalized": false,
|
927 |
-
"rstrip": false,
|
928 |
-
"single_word": false,
|
929 |
-
"special": true
|
930 |
-
},
|
931 |
-
"128116": {
|
932 |
-
"content": "<|reserved_special_token_111|>",
|
933 |
-
"lstrip": false,
|
934 |
-
"normalized": false,
|
935 |
-
"rstrip": false,
|
936 |
-
"single_word": false,
|
937 |
-
"special": true
|
938 |
-
},
|
939 |
-
"128117": {
|
940 |
-
"content": "<|reserved_special_token_112|>",
|
941 |
-
"lstrip": false,
|
942 |
-
"normalized": false,
|
943 |
-
"rstrip": false,
|
944 |
-
"single_word": false,
|
945 |
-
"special": true
|
946 |
-
},
|
947 |
-
"128118": {
|
948 |
-
"content": "<|reserved_special_token_113|>",
|
949 |
-
"lstrip": false,
|
950 |
-
"normalized": false,
|
951 |
-
"rstrip": false,
|
952 |
-
"single_word": false,
|
953 |
-
"special": true
|
954 |
-
},
|
955 |
-
"128119": {
|
956 |
-
"content": "<|reserved_special_token_114|>",
|
957 |
-
"lstrip": false,
|
958 |
-
"normalized": false,
|
959 |
-
"rstrip": false,
|
960 |
-
"single_word": false,
|
961 |
-
"special": true
|
962 |
-
},
|
963 |
-
"128120": {
|
964 |
-
"content": "<|reserved_special_token_115|>",
|
965 |
-
"lstrip": false,
|
966 |
-
"normalized": false,
|
967 |
-
"rstrip": false,
|
968 |
-
"single_word": false,
|
969 |
-
"special": true
|
970 |
-
},
|
971 |
-
"128121": {
|
972 |
-
"content": "<|reserved_special_token_116|>",
|
973 |
-
"lstrip": false,
|
974 |
-
"normalized": false,
|
975 |
-
"rstrip": false,
|
976 |
-
"single_word": false,
|
977 |
-
"special": true
|
978 |
-
},
|
979 |
-
"128122": {
|
980 |
-
"content": "<|reserved_special_token_117|>",
|
981 |
-
"lstrip": false,
|
982 |
-
"normalized": false,
|
983 |
-
"rstrip": false,
|
984 |
-
"single_word": false,
|
985 |
-
"special": true
|
986 |
-
},
|
987 |
-
"128123": {
|
988 |
-
"content": "<|reserved_special_token_118|>",
|
989 |
-
"lstrip": false,
|
990 |
-
"normalized": false,
|
991 |
-
"rstrip": false,
|
992 |
-
"single_word": false,
|
993 |
-
"special": true
|
994 |
-
},
|
995 |
-
"128124": {
|
996 |
-
"content": "<|reserved_special_token_119|>",
|
997 |
-
"lstrip": false,
|
998 |
-
"normalized": false,
|
999 |
-
"rstrip": false,
|
1000 |
-
"single_word": false,
|
1001 |
-
"special": true
|
1002 |
-
},
|
1003 |
-
"128125": {
|
1004 |
-
"content": "<|reserved_special_token_120|>",
|
1005 |
-
"lstrip": false,
|
1006 |
-
"normalized": false,
|
1007 |
-
"rstrip": false,
|
1008 |
-
"single_word": false,
|
1009 |
-
"special": true
|
1010 |
-
},
|
1011 |
-
"128126": {
|
1012 |
-
"content": "<|reserved_special_token_121|>",
|
1013 |
-
"lstrip": false,
|
1014 |
-
"normalized": false,
|
1015 |
-
"rstrip": false,
|
1016 |
-
"single_word": false,
|
1017 |
-
"special": true
|
1018 |
-
},
|
1019 |
-
"128127": {
|
1020 |
-
"content": "<|reserved_special_token_122|>",
|
1021 |
-
"lstrip": false,
|
1022 |
-
"normalized": false,
|
1023 |
-
"rstrip": false,
|
1024 |
-
"single_word": false,
|
1025 |
-
"special": true
|
1026 |
-
},
|
1027 |
-
"128128": {
|
1028 |
-
"content": "<|reserved_special_token_123|>",
|
1029 |
-
"lstrip": false,
|
1030 |
-
"normalized": false,
|
1031 |
-
"rstrip": false,
|
1032 |
-
"single_word": false,
|
1033 |
-
"special": true
|
1034 |
-
},
|
1035 |
-
"128129": {
|
1036 |
-
"content": "<|reserved_special_token_124|>",
|
1037 |
-
"lstrip": false,
|
1038 |
-
"normalized": false,
|
1039 |
-
"rstrip": false,
|
1040 |
-
"single_word": false,
|
1041 |
-
"special": true
|
1042 |
-
},
|
1043 |
-
"128130": {
|
1044 |
-
"content": "<|reserved_special_token_125|>",
|
1045 |
-
"lstrip": false,
|
1046 |
-
"normalized": false,
|
1047 |
-
"rstrip": false,
|
1048 |
-
"single_word": false,
|
1049 |
-
"special": true
|
1050 |
-
},
|
1051 |
-
"128131": {
|
1052 |
-
"content": "<|reserved_special_token_126|>",
|
1053 |
-
"lstrip": false,
|
1054 |
-
"normalized": false,
|
1055 |
-
"rstrip": false,
|
1056 |
-
"single_word": false,
|
1057 |
-
"special": true
|
1058 |
-
},
|
1059 |
-
"128132": {
|
1060 |
-
"content": "<|reserved_special_token_127|>",
|
1061 |
-
"lstrip": false,
|
1062 |
-
"normalized": false,
|
1063 |
-
"rstrip": false,
|
1064 |
-
"single_word": false,
|
1065 |
-
"special": true
|
1066 |
-
},
|
1067 |
-
"128133": {
|
1068 |
-
"content": "<|reserved_special_token_128|>",
|
1069 |
-
"lstrip": false,
|
1070 |
-
"normalized": false,
|
1071 |
-
"rstrip": false,
|
1072 |
-
"single_word": false,
|
1073 |
-
"special": true
|
1074 |
-
},
|
1075 |
-
"128134": {
|
1076 |
-
"content": "<|reserved_special_token_129|>",
|
1077 |
-
"lstrip": false,
|
1078 |
-
"normalized": false,
|
1079 |
-
"rstrip": false,
|
1080 |
-
"single_word": false,
|
1081 |
-
"special": true
|
1082 |
-
},
|
1083 |
-
"128135": {
|
1084 |
-
"content": "<|reserved_special_token_130|>",
|
1085 |
-
"lstrip": false,
|
1086 |
-
"normalized": false,
|
1087 |
-
"rstrip": false,
|
1088 |
-
"single_word": false,
|
1089 |
-
"special": true
|
1090 |
-
},
|
1091 |
-
"128136": {
|
1092 |
-
"content": "<|reserved_special_token_131|>",
|
1093 |
-
"lstrip": false,
|
1094 |
-
"normalized": false,
|
1095 |
-
"rstrip": false,
|
1096 |
-
"single_word": false,
|
1097 |
-
"special": true
|
1098 |
-
},
|
1099 |
-
"128137": {
|
1100 |
-
"content": "<|reserved_special_token_132|>",
|
1101 |
-
"lstrip": false,
|
1102 |
-
"normalized": false,
|
1103 |
-
"rstrip": false,
|
1104 |
-
"single_word": false,
|
1105 |
-
"special": true
|
1106 |
-
},
|
1107 |
-
"128138": {
|
1108 |
-
"content": "<|reserved_special_token_133|>",
|
1109 |
-
"lstrip": false,
|
1110 |
-
"normalized": false,
|
1111 |
-
"rstrip": false,
|
1112 |
-
"single_word": false,
|
1113 |
-
"special": true
|
1114 |
-
},
|
1115 |
-
"128139": {
|
1116 |
-
"content": "<|reserved_special_token_134|>",
|
1117 |
-
"lstrip": false,
|
1118 |
-
"normalized": false,
|
1119 |
-
"rstrip": false,
|
1120 |
-
"single_word": false,
|
1121 |
-
"special": true
|
1122 |
-
},
|
1123 |
-
"128140": {
|
1124 |
-
"content": "<|reserved_special_token_135|>",
|
1125 |
-
"lstrip": false,
|
1126 |
-
"normalized": false,
|
1127 |
-
"rstrip": false,
|
1128 |
-
"single_word": false,
|
1129 |
-
"special": true
|
1130 |
-
},
|
1131 |
-
"128141": {
|
1132 |
-
"content": "<|reserved_special_token_136|>",
|
1133 |
-
"lstrip": false,
|
1134 |
-
"normalized": false,
|
1135 |
-
"rstrip": false,
|
1136 |
-
"single_word": false,
|
1137 |
-
"special": true
|
1138 |
-
},
|
1139 |
-
"128142": {
|
1140 |
-
"content": "<|reserved_special_token_137|>",
|
1141 |
-
"lstrip": false,
|
1142 |
-
"normalized": false,
|
1143 |
-
"rstrip": false,
|
1144 |
-
"single_word": false,
|
1145 |
-
"special": true
|
1146 |
-
},
|
1147 |
-
"128143": {
|
1148 |
-
"content": "<|reserved_special_token_138|>",
|
1149 |
-
"lstrip": false,
|
1150 |
-
"normalized": false,
|
1151 |
-
"rstrip": false,
|
1152 |
-
"single_word": false,
|
1153 |
-
"special": true
|
1154 |
-
},
|
1155 |
-
"128144": {
|
1156 |
-
"content": "<|reserved_special_token_139|>",
|
1157 |
-
"lstrip": false,
|
1158 |
-
"normalized": false,
|
1159 |
-
"rstrip": false,
|
1160 |
-
"single_word": false,
|
1161 |
-
"special": true
|
1162 |
-
},
|
1163 |
-
"128145": {
|
1164 |
-
"content": "<|reserved_special_token_140|>",
|
1165 |
-
"lstrip": false,
|
1166 |
-
"normalized": false,
|
1167 |
-
"rstrip": false,
|
1168 |
-
"single_word": false,
|
1169 |
-
"special": true
|
1170 |
-
},
|
1171 |
-
"128146": {
|
1172 |
-
"content": "<|reserved_special_token_141|>",
|
1173 |
-
"lstrip": false,
|
1174 |
-
"normalized": false,
|
1175 |
-
"rstrip": false,
|
1176 |
-
"single_word": false,
|
1177 |
-
"special": true
|
1178 |
-
},
|
1179 |
-
"128147": {
|
1180 |
-
"content": "<|reserved_special_token_142|>",
|
1181 |
-
"lstrip": false,
|
1182 |
-
"normalized": false,
|
1183 |
-
"rstrip": false,
|
1184 |
-
"single_word": false,
|
1185 |
-
"special": true
|
1186 |
-
},
|
1187 |
-
"128148": {
|
1188 |
-
"content": "<|reserved_special_token_143|>",
|
1189 |
-
"lstrip": false,
|
1190 |
-
"normalized": false,
|
1191 |
-
"rstrip": false,
|
1192 |
-
"single_word": false,
|
1193 |
-
"special": true
|
1194 |
-
},
|
1195 |
-
"128149": {
|
1196 |
-
"content": "<|reserved_special_token_144|>",
|
1197 |
-
"lstrip": false,
|
1198 |
-
"normalized": false,
|
1199 |
-
"rstrip": false,
|
1200 |
-
"single_word": false,
|
1201 |
-
"special": true
|
1202 |
-
},
|
1203 |
-
"128150": {
|
1204 |
-
"content": "<|reserved_special_token_145|>",
|
1205 |
-
"lstrip": false,
|
1206 |
-
"normalized": false,
|
1207 |
-
"rstrip": false,
|
1208 |
-
"single_word": false,
|
1209 |
-
"special": true
|
1210 |
-
},
|
1211 |
-
"128151": {
|
1212 |
-
"content": "<|reserved_special_token_146|>",
|
1213 |
-
"lstrip": false,
|
1214 |
-
"normalized": false,
|
1215 |
-
"rstrip": false,
|
1216 |
-
"single_word": false,
|
1217 |
-
"special": true
|
1218 |
-
},
|
1219 |
-
"128152": {
|
1220 |
-
"content": "<|reserved_special_token_147|>",
|
1221 |
-
"lstrip": false,
|
1222 |
-
"normalized": false,
|
1223 |
-
"rstrip": false,
|
1224 |
-
"single_word": false,
|
1225 |
-
"special": true
|
1226 |
-
},
|
1227 |
-
"128153": {
|
1228 |
-
"content": "<|reserved_special_token_148|>",
|
1229 |
-
"lstrip": false,
|
1230 |
-
"normalized": false,
|
1231 |
-
"rstrip": false,
|
1232 |
-
"single_word": false,
|
1233 |
-
"special": true
|
1234 |
-
},
|
1235 |
-
"128154": {
|
1236 |
-
"content": "<|reserved_special_token_149|>",
|
1237 |
-
"lstrip": false,
|
1238 |
-
"normalized": false,
|
1239 |
-
"rstrip": false,
|
1240 |
-
"single_word": false,
|
1241 |
-
"special": true
|
1242 |
-
},
|
1243 |
-
"128155": {
|
1244 |
-
"content": "<|reserved_special_token_150|>",
|
1245 |
-
"lstrip": false,
|
1246 |
-
"normalized": false,
|
1247 |
-
"rstrip": false,
|
1248 |
-
"single_word": false,
|
1249 |
-
"special": true
|
1250 |
-
},
|
1251 |
-
"128156": {
|
1252 |
-
"content": "<|reserved_special_token_151|>",
|
1253 |
-
"lstrip": false,
|
1254 |
-
"normalized": false,
|
1255 |
-
"rstrip": false,
|
1256 |
-
"single_word": false,
|
1257 |
-
"special": true
|
1258 |
-
},
|
1259 |
-
"128157": {
|
1260 |
-
"content": "<|reserved_special_token_152|>",
|
1261 |
-
"lstrip": false,
|
1262 |
-
"normalized": false,
|
1263 |
-
"rstrip": false,
|
1264 |
-
"single_word": false,
|
1265 |
-
"special": true
|
1266 |
-
},
|
1267 |
-
"128158": {
|
1268 |
-
"content": "<|reserved_special_token_153|>",
|
1269 |
-
"lstrip": false,
|
1270 |
-
"normalized": false,
|
1271 |
-
"rstrip": false,
|
1272 |
-
"single_word": false,
|
1273 |
-
"special": true
|
1274 |
-
},
|
1275 |
-
"128159": {
|
1276 |
-
"content": "<|reserved_special_token_154|>",
|
1277 |
-
"lstrip": false,
|
1278 |
-
"normalized": false,
|
1279 |
-
"rstrip": false,
|
1280 |
-
"single_word": false,
|
1281 |
-
"special": true
|
1282 |
-
},
|
1283 |
-
"128160": {
|
1284 |
-
"content": "<|reserved_special_token_155|>",
|
1285 |
-
"lstrip": false,
|
1286 |
-
"normalized": false,
|
1287 |
-
"rstrip": false,
|
1288 |
-
"single_word": false,
|
1289 |
-
"special": true
|
1290 |
-
},
|
1291 |
-
"128161": {
|
1292 |
-
"content": "<|reserved_special_token_156|>",
|
1293 |
-
"lstrip": false,
|
1294 |
-
"normalized": false,
|
1295 |
-
"rstrip": false,
|
1296 |
-
"single_word": false,
|
1297 |
-
"special": true
|
1298 |
-
},
|
1299 |
-
"128162": {
|
1300 |
-
"content": "<|reserved_special_token_157|>",
|
1301 |
-
"lstrip": false,
|
1302 |
-
"normalized": false,
|
1303 |
-
"rstrip": false,
|
1304 |
-
"single_word": false,
|
1305 |
-
"special": true
|
1306 |
-
},
|
1307 |
-
"128163": {
|
1308 |
-
"content": "<|reserved_special_token_158|>",
|
1309 |
-
"lstrip": false,
|
1310 |
-
"normalized": false,
|
1311 |
-
"rstrip": false,
|
1312 |
-
"single_word": false,
|
1313 |
-
"special": true
|
1314 |
-
},
|
1315 |
-
"128164": {
|
1316 |
-
"content": "<|reserved_special_token_159|>",
|
1317 |
-
"lstrip": false,
|
1318 |
-
"normalized": false,
|
1319 |
-
"rstrip": false,
|
1320 |
-
"single_word": false,
|
1321 |
-
"special": true
|
1322 |
-
},
|
1323 |
-
"128165": {
|
1324 |
-
"content": "<|reserved_special_token_160|>",
|
1325 |
-
"lstrip": false,
|
1326 |
-
"normalized": false,
|
1327 |
-
"rstrip": false,
|
1328 |
-
"single_word": false,
|
1329 |
-
"special": true
|
1330 |
-
},
|
1331 |
-
"128166": {
|
1332 |
-
"content": "<|reserved_special_token_161|>",
|
1333 |
-
"lstrip": false,
|
1334 |
-
"normalized": false,
|
1335 |
-
"rstrip": false,
|
1336 |
-
"single_word": false,
|
1337 |
-
"special": true
|
1338 |
-
},
|
1339 |
-
"128167": {
|
1340 |
-
"content": "<|reserved_special_token_162|>",
|
1341 |
-
"lstrip": false,
|
1342 |
-
"normalized": false,
|
1343 |
-
"rstrip": false,
|
1344 |
-
"single_word": false,
|
1345 |
-
"special": true
|
1346 |
-
},
|
1347 |
-
"128168": {
|
1348 |
-
"content": "<|reserved_special_token_163|>",
|
1349 |
-
"lstrip": false,
|
1350 |
-
"normalized": false,
|
1351 |
-
"rstrip": false,
|
1352 |
-
"single_word": false,
|
1353 |
-
"special": true
|
1354 |
-
},
|
1355 |
-
"128169": {
|
1356 |
-
"content": "<|reserved_special_token_164|>",
|
1357 |
-
"lstrip": false,
|
1358 |
-
"normalized": false,
|
1359 |
-
"rstrip": false,
|
1360 |
-
"single_word": false,
|
1361 |
-
"special": true
|
1362 |
-
},
|
1363 |
-
"128170": {
|
1364 |
-
"content": "<|reserved_special_token_165|>",
|
1365 |
-
"lstrip": false,
|
1366 |
-
"normalized": false,
|
1367 |
-
"rstrip": false,
|
1368 |
-
"single_word": false,
|
1369 |
-
"special": true
|
1370 |
-
},
|
1371 |
-
"128171": {
|
1372 |
-
"content": "<|reserved_special_token_166|>",
|
1373 |
-
"lstrip": false,
|
1374 |
-
"normalized": false,
|
1375 |
-
"rstrip": false,
|
1376 |
-
"single_word": false,
|
1377 |
-
"special": true
|
1378 |
-
},
|
1379 |
-
"128172": {
|
1380 |
-
"content": "<|reserved_special_token_167|>",
|
1381 |
-
"lstrip": false,
|
1382 |
-
"normalized": false,
|
1383 |
-
"rstrip": false,
|
1384 |
-
"single_word": false,
|
1385 |
-
"special": true
|
1386 |
-
},
|
1387 |
-
"128173": {
|
1388 |
-
"content": "<|reserved_special_token_168|>",
|
1389 |
-
"lstrip": false,
|
1390 |
-
"normalized": false,
|
1391 |
-
"rstrip": false,
|
1392 |
-
"single_word": false,
|
1393 |
-
"special": true
|
1394 |
-
},
|
1395 |
-
"128174": {
|
1396 |
-
"content": "<|reserved_special_token_169|>",
|
1397 |
-
"lstrip": false,
|
1398 |
-
"normalized": false,
|
1399 |
-
"rstrip": false,
|
1400 |
-
"single_word": false,
|
1401 |
-
"special": true
|
1402 |
-
},
|
1403 |
-
"128175": {
|
1404 |
-
"content": "<|reserved_special_token_170|>",
|
1405 |
-
"lstrip": false,
|
1406 |
-
"normalized": false,
|
1407 |
-
"rstrip": false,
|
1408 |
-
"single_word": false,
|
1409 |
-
"special": true
|
1410 |
-
},
|
1411 |
-
"128176": {
|
1412 |
-
"content": "<|reserved_special_token_171|>",
|
1413 |
-
"lstrip": false,
|
1414 |
-
"normalized": false,
|
1415 |
-
"rstrip": false,
|
1416 |
-
"single_word": false,
|
1417 |
-
"special": true
|
1418 |
-
},
|
1419 |
-
"128177": {
|
1420 |
-
"content": "<|reserved_special_token_172|>",
|
1421 |
-
"lstrip": false,
|
1422 |
-
"normalized": false,
|
1423 |
-
"rstrip": false,
|
1424 |
-
"single_word": false,
|
1425 |
-
"special": true
|
1426 |
-
},
|
1427 |
-
"128178": {
|
1428 |
-
"content": "<|reserved_special_token_173|>",
|
1429 |
-
"lstrip": false,
|
1430 |
-
"normalized": false,
|
1431 |
-
"rstrip": false,
|
1432 |
-
"single_word": false,
|
1433 |
-
"special": true
|
1434 |
-
},
|
1435 |
-
"128179": {
|
1436 |
-
"content": "<|reserved_special_token_174|>",
|
1437 |
-
"lstrip": false,
|
1438 |
-
"normalized": false,
|
1439 |
-
"rstrip": false,
|
1440 |
-
"single_word": false,
|
1441 |
-
"special": true
|
1442 |
-
},
|
1443 |
-
"128180": {
|
1444 |
-
"content": "<|reserved_special_token_175|>",
|
1445 |
-
"lstrip": false,
|
1446 |
-
"normalized": false,
|
1447 |
-
"rstrip": false,
|
1448 |
-
"single_word": false,
|
1449 |
-
"special": true
|
1450 |
-
},
|
1451 |
-
"128181": {
|
1452 |
-
"content": "<|reserved_special_token_176|>",
|
1453 |
-
"lstrip": false,
|
1454 |
-
"normalized": false,
|
1455 |
-
"rstrip": false,
|
1456 |
-
"single_word": false,
|
1457 |
-
"special": true
|
1458 |
-
},
|
1459 |
-
"128182": {
|
1460 |
-
"content": "<|reserved_special_token_177|>",
|
1461 |
-
"lstrip": false,
|
1462 |
-
"normalized": false,
|
1463 |
-
"rstrip": false,
|
1464 |
-
"single_word": false,
|
1465 |
-
"special": true
|
1466 |
-
},
|
1467 |
-
"128183": {
|
1468 |
-
"content": "<|reserved_special_token_178|>",
|
1469 |
-
"lstrip": false,
|
1470 |
-
"normalized": false,
|
1471 |
-
"rstrip": false,
|
1472 |
-
"single_word": false,
|
1473 |
-
"special": true
|
1474 |
-
},
|
1475 |
-
"128184": {
|
1476 |
-
"content": "<|reserved_special_token_179|>",
|
1477 |
-
"lstrip": false,
|
1478 |
-
"normalized": false,
|
1479 |
-
"rstrip": false,
|
1480 |
-
"single_word": false,
|
1481 |
-
"special": true
|
1482 |
-
},
|
1483 |
-
"128185": {
|
1484 |
-
"content": "<|reserved_special_token_180|>",
|
1485 |
-
"lstrip": false,
|
1486 |
-
"normalized": false,
|
1487 |
-
"rstrip": false,
|
1488 |
-
"single_word": false,
|
1489 |
-
"special": true
|
1490 |
-
},
|
1491 |
-
"128186": {
|
1492 |
-
"content": "<|reserved_special_token_181|>",
|
1493 |
-
"lstrip": false,
|
1494 |
-
"normalized": false,
|
1495 |
-
"rstrip": false,
|
1496 |
-
"single_word": false,
|
1497 |
-
"special": true
|
1498 |
-
},
|
1499 |
-
"128187": {
|
1500 |
-
"content": "<|reserved_special_token_182|>",
|
1501 |
-
"lstrip": false,
|
1502 |
-
"normalized": false,
|
1503 |
-
"rstrip": false,
|
1504 |
-
"single_word": false,
|
1505 |
-
"special": true
|
1506 |
-
},
|
1507 |
-
"128188": {
|
1508 |
-
"content": "<|reserved_special_token_183|>",
|
1509 |
-
"lstrip": false,
|
1510 |
-
"normalized": false,
|
1511 |
-
"rstrip": false,
|
1512 |
-
"single_word": false,
|
1513 |
-
"special": true
|
1514 |
-
},
|
1515 |
-
"128189": {
|
1516 |
-
"content": "<|reserved_special_token_184|>",
|
1517 |
-
"lstrip": false,
|
1518 |
-
"normalized": false,
|
1519 |
-
"rstrip": false,
|
1520 |
-
"single_word": false,
|
1521 |
-
"special": true
|
1522 |
-
},
|
1523 |
-
"128190": {
|
1524 |
-
"content": "<|reserved_special_token_185|>",
|
1525 |
-
"lstrip": false,
|
1526 |
-
"normalized": false,
|
1527 |
-
"rstrip": false,
|
1528 |
-
"single_word": false,
|
1529 |
-
"special": true
|
1530 |
-
},
|
1531 |
-
"128191": {
|
1532 |
-
"content": "<|reserved_special_token_186|>",
|
1533 |
-
"lstrip": false,
|
1534 |
-
"normalized": false,
|
1535 |
-
"rstrip": false,
|
1536 |
-
"single_word": false,
|
1537 |
-
"special": true
|
1538 |
-
},
|
1539 |
-
"128192": {
|
1540 |
-
"content": "<|reserved_special_token_187|>",
|
1541 |
-
"lstrip": false,
|
1542 |
-
"normalized": false,
|
1543 |
-
"rstrip": false,
|
1544 |
-
"single_word": false,
|
1545 |
-
"special": true
|
1546 |
-
},
|
1547 |
-
"128193": {
|
1548 |
-
"content": "<|reserved_special_token_188|>",
|
1549 |
-
"lstrip": false,
|
1550 |
-
"normalized": false,
|
1551 |
-
"rstrip": false,
|
1552 |
-
"single_word": false,
|
1553 |
-
"special": true
|
1554 |
-
},
|
1555 |
-
"128194": {
|
1556 |
-
"content": "<|reserved_special_token_189|>",
|
1557 |
-
"lstrip": false,
|
1558 |
-
"normalized": false,
|
1559 |
-
"rstrip": false,
|
1560 |
-
"single_word": false,
|
1561 |
-
"special": true
|
1562 |
-
},
|
1563 |
-
"128195": {
|
1564 |
-
"content": "<|reserved_special_token_190|>",
|
1565 |
-
"lstrip": false,
|
1566 |
-
"normalized": false,
|
1567 |
-
"rstrip": false,
|
1568 |
-
"single_word": false,
|
1569 |
-
"special": true
|
1570 |
-
},
|
1571 |
-
"128196": {
|
1572 |
-
"content": "<|reserved_special_token_191|>",
|
1573 |
-
"lstrip": false,
|
1574 |
-
"normalized": false,
|
1575 |
-
"rstrip": false,
|
1576 |
-
"single_word": false,
|
1577 |
-
"special": true
|
1578 |
-
},
|
1579 |
-
"128197": {
|
1580 |
-
"content": "<|reserved_special_token_192|>",
|
1581 |
-
"lstrip": false,
|
1582 |
-
"normalized": false,
|
1583 |
-
"rstrip": false,
|
1584 |
-
"single_word": false,
|
1585 |
-
"special": true
|
1586 |
-
},
|
1587 |
-
"128198": {
|
1588 |
-
"content": "<|reserved_special_token_193|>",
|
1589 |
-
"lstrip": false,
|
1590 |
-
"normalized": false,
|
1591 |
-
"rstrip": false,
|
1592 |
-
"single_word": false,
|
1593 |
-
"special": true
|
1594 |
-
},
|
1595 |
-
"128199": {
|
1596 |
-
"content": "<|reserved_special_token_194|>",
|
1597 |
-
"lstrip": false,
|
1598 |
-
"normalized": false,
|
1599 |
-
"rstrip": false,
|
1600 |
-
"single_word": false,
|
1601 |
-
"special": true
|
1602 |
-
},
|
1603 |
-
"128200": {
|
1604 |
-
"content": "<|reserved_special_token_195|>",
|
1605 |
-
"lstrip": false,
|
1606 |
-
"normalized": false,
|
1607 |
-
"rstrip": false,
|
1608 |
-
"single_word": false,
|
1609 |
-
"special": true
|
1610 |
-
},
|
1611 |
-
"128201": {
|
1612 |
-
"content": "<|reserved_special_token_196|>",
|
1613 |
-
"lstrip": false,
|
1614 |
-
"normalized": false,
|
1615 |
-
"rstrip": false,
|
1616 |
-
"single_word": false,
|
1617 |
-
"special": true
|
1618 |
-
},
|
1619 |
-
"128202": {
|
1620 |
-
"content": "<|reserved_special_token_197|>",
|
1621 |
-
"lstrip": false,
|
1622 |
-
"normalized": false,
|
1623 |
-
"rstrip": false,
|
1624 |
-
"single_word": false,
|
1625 |
-
"special": true
|
1626 |
-
},
|
1627 |
-
"128203": {
|
1628 |
-
"content": "<|reserved_special_token_198|>",
|
1629 |
-
"lstrip": false,
|
1630 |
-
"normalized": false,
|
1631 |
-
"rstrip": false,
|
1632 |
-
"single_word": false,
|
1633 |
-
"special": true
|
1634 |
-
},
|
1635 |
-
"128204": {
|
1636 |
-
"content": "<|reserved_special_token_199|>",
|
1637 |
-
"lstrip": false,
|
1638 |
-
"normalized": false,
|
1639 |
-
"rstrip": false,
|
1640 |
-
"single_word": false,
|
1641 |
-
"special": true
|
1642 |
-
},
|
1643 |
-
"128205": {
|
1644 |
-
"content": "<|reserved_special_token_200|>",
|
1645 |
-
"lstrip": false,
|
1646 |
-
"normalized": false,
|
1647 |
-
"rstrip": false,
|
1648 |
-
"single_word": false,
|
1649 |
-
"special": true
|
1650 |
-
},
|
1651 |
-
"128206": {
|
1652 |
-
"content": "<|reserved_special_token_201|>",
|
1653 |
-
"lstrip": false,
|
1654 |
-
"normalized": false,
|
1655 |
-
"rstrip": false,
|
1656 |
-
"single_word": false,
|
1657 |
-
"special": true
|
1658 |
-
},
|
1659 |
-
"128207": {
|
1660 |
-
"content": "<|reserved_special_token_202|>",
|
1661 |
-
"lstrip": false,
|
1662 |
-
"normalized": false,
|
1663 |
-
"rstrip": false,
|
1664 |
-
"single_word": false,
|
1665 |
-
"special": true
|
1666 |
-
},
|
1667 |
-
"128208": {
|
1668 |
-
"content": "<|reserved_special_token_203|>",
|
1669 |
-
"lstrip": false,
|
1670 |
-
"normalized": false,
|
1671 |
-
"rstrip": false,
|
1672 |
-
"single_word": false,
|
1673 |
-
"special": true
|
1674 |
-
},
|
1675 |
-
"128209": {
|
1676 |
-
"content": "<|reserved_special_token_204|>",
|
1677 |
-
"lstrip": false,
|
1678 |
-
"normalized": false,
|
1679 |
-
"rstrip": false,
|
1680 |
-
"single_word": false,
|
1681 |
-
"special": true
|
1682 |
-
},
|
1683 |
-
"128210": {
|
1684 |
-
"content": "<|reserved_special_token_205|>",
|
1685 |
-
"lstrip": false,
|
1686 |
-
"normalized": false,
|
1687 |
-
"rstrip": false,
|
1688 |
-
"single_word": false,
|
1689 |
-
"special": true
|
1690 |
-
},
|
1691 |
-
"128211": {
|
1692 |
-
"content": "<|reserved_special_token_206|>",
|
1693 |
-
"lstrip": false,
|
1694 |
-
"normalized": false,
|
1695 |
-
"rstrip": false,
|
1696 |
-
"single_word": false,
|
1697 |
-
"special": true
|
1698 |
-
},
|
1699 |
-
"128212": {
|
1700 |
-
"content": "<|reserved_special_token_207|>",
|
1701 |
-
"lstrip": false,
|
1702 |
-
"normalized": false,
|
1703 |
-
"rstrip": false,
|
1704 |
-
"single_word": false,
|
1705 |
-
"special": true
|
1706 |
-
},
|
1707 |
-
"128213": {
|
1708 |
-
"content": "<|reserved_special_token_208|>",
|
1709 |
-
"lstrip": false,
|
1710 |
-
"normalized": false,
|
1711 |
-
"rstrip": false,
|
1712 |
-
"single_word": false,
|
1713 |
-
"special": true
|
1714 |
-
},
|
1715 |
-
"128214": {
|
1716 |
-
"content": "<|reserved_special_token_209|>",
|
1717 |
-
"lstrip": false,
|
1718 |
-
"normalized": false,
|
1719 |
-
"rstrip": false,
|
1720 |
-
"single_word": false,
|
1721 |
-
"special": true
|
1722 |
-
},
|
1723 |
-
"128215": {
|
1724 |
-
"content": "<|reserved_special_token_210|>",
|
1725 |
-
"lstrip": false,
|
1726 |
-
"normalized": false,
|
1727 |
-
"rstrip": false,
|
1728 |
-
"single_word": false,
|
1729 |
-
"special": true
|
1730 |
-
},
|
1731 |
-
"128216": {
|
1732 |
-
"content": "<|reserved_special_token_211|>",
|
1733 |
-
"lstrip": false,
|
1734 |
-
"normalized": false,
|
1735 |
-
"rstrip": false,
|
1736 |
-
"single_word": false,
|
1737 |
-
"special": true
|
1738 |
-
},
|
1739 |
-
"128217": {
|
1740 |
-
"content": "<|reserved_special_token_212|>",
|
1741 |
-
"lstrip": false,
|
1742 |
-
"normalized": false,
|
1743 |
-
"rstrip": false,
|
1744 |
-
"single_word": false,
|
1745 |
-
"special": true
|
1746 |
-
},
|
1747 |
-
"128218": {
|
1748 |
-
"content": "<|reserved_special_token_213|>",
|
1749 |
-
"lstrip": false,
|
1750 |
-
"normalized": false,
|
1751 |
-
"rstrip": false,
|
1752 |
-
"single_word": false,
|
1753 |
-
"special": true
|
1754 |
-
},
|
1755 |
-
"128219": {
|
1756 |
-
"content": "<|reserved_special_token_214|>",
|
1757 |
-
"lstrip": false,
|
1758 |
-
"normalized": false,
|
1759 |
-
"rstrip": false,
|
1760 |
-
"single_word": false,
|
1761 |
-
"special": true
|
1762 |
-
},
|
1763 |
-
"128220": {
|
1764 |
-
"content": "<|reserved_special_token_215|>",
|
1765 |
-
"lstrip": false,
|
1766 |
-
"normalized": false,
|
1767 |
-
"rstrip": false,
|
1768 |
-
"single_word": false,
|
1769 |
-
"special": true
|
1770 |
-
},
|
1771 |
-
"128221": {
|
1772 |
-
"content": "<|reserved_special_token_216|>",
|
1773 |
-
"lstrip": false,
|
1774 |
-
"normalized": false,
|
1775 |
-
"rstrip": false,
|
1776 |
-
"single_word": false,
|
1777 |
-
"special": true
|
1778 |
-
},
|
1779 |
-
"128222": {
|
1780 |
-
"content": "<|reserved_special_token_217|>",
|
1781 |
-
"lstrip": false,
|
1782 |
-
"normalized": false,
|
1783 |
-
"rstrip": false,
|
1784 |
-
"single_word": false,
|
1785 |
-
"special": true
|
1786 |
-
},
|
1787 |
-
"128223": {
|
1788 |
-
"content": "<|reserved_special_token_218|>",
|
1789 |
-
"lstrip": false,
|
1790 |
-
"normalized": false,
|
1791 |
-
"rstrip": false,
|
1792 |
-
"single_word": false,
|
1793 |
-
"special": true
|
1794 |
-
},
|
1795 |
-
"128224": {
|
1796 |
-
"content": "<|reserved_special_token_219|>",
|
1797 |
-
"lstrip": false,
|
1798 |
-
"normalized": false,
|
1799 |
-
"rstrip": false,
|
1800 |
-
"single_word": false,
|
1801 |
-
"special": true
|
1802 |
-
},
|
1803 |
-
"128225": {
|
1804 |
-
"content": "<|reserved_special_token_220|>",
|
1805 |
-
"lstrip": false,
|
1806 |
-
"normalized": false,
|
1807 |
-
"rstrip": false,
|
1808 |
-
"single_word": false,
|
1809 |
-
"special": true
|
1810 |
-
},
|
1811 |
-
"128226": {
|
1812 |
-
"content": "<|reserved_special_token_221|>",
|
1813 |
-
"lstrip": false,
|
1814 |
-
"normalized": false,
|
1815 |
-
"rstrip": false,
|
1816 |
-
"single_word": false,
|
1817 |
-
"special": true
|
1818 |
-
},
|
1819 |
-
"128227": {
|
1820 |
-
"content": "<|reserved_special_token_222|>",
|
1821 |
-
"lstrip": false,
|
1822 |
-
"normalized": false,
|
1823 |
-
"rstrip": false,
|
1824 |
-
"single_word": false,
|
1825 |
-
"special": true
|
1826 |
-
},
|
1827 |
-
"128228": {
|
1828 |
-
"content": "<|reserved_special_token_223|>",
|
1829 |
-
"lstrip": false,
|
1830 |
-
"normalized": false,
|
1831 |
-
"rstrip": false,
|
1832 |
-
"single_word": false,
|
1833 |
-
"special": true
|
1834 |
-
},
|
1835 |
-
"128229": {
|
1836 |
-
"content": "<|reserved_special_token_224|>",
|
1837 |
-
"lstrip": false,
|
1838 |
-
"normalized": false,
|
1839 |
-
"rstrip": false,
|
1840 |
-
"single_word": false,
|
1841 |
-
"special": true
|
1842 |
-
},
|
1843 |
-
"128230": {
|
1844 |
-
"content": "<|reserved_special_token_225|>",
|
1845 |
-
"lstrip": false,
|
1846 |
-
"normalized": false,
|
1847 |
-
"rstrip": false,
|
1848 |
-
"single_word": false,
|
1849 |
-
"special": true
|
1850 |
-
},
|
1851 |
-
"128231": {
|
1852 |
-
"content": "<|reserved_special_token_226|>",
|
1853 |
-
"lstrip": false,
|
1854 |
-
"normalized": false,
|
1855 |
-
"rstrip": false,
|
1856 |
-
"single_word": false,
|
1857 |
-
"special": true
|
1858 |
-
},
|
1859 |
-
"128232": {
|
1860 |
-
"content": "<|reserved_special_token_227|>",
|
1861 |
-
"lstrip": false,
|
1862 |
-
"normalized": false,
|
1863 |
-
"rstrip": false,
|
1864 |
-
"single_word": false,
|
1865 |
-
"special": true
|
1866 |
-
},
|
1867 |
-
"128233": {
|
1868 |
-
"content": "<|reserved_special_token_228|>",
|
1869 |
-
"lstrip": false,
|
1870 |
-
"normalized": false,
|
1871 |
-
"rstrip": false,
|
1872 |
-
"single_word": false,
|
1873 |
-
"special": true
|
1874 |
-
},
|
1875 |
-
"128234": {
|
1876 |
-
"content": "<|reserved_special_token_229|>",
|
1877 |
-
"lstrip": false,
|
1878 |
-
"normalized": false,
|
1879 |
-
"rstrip": false,
|
1880 |
-
"single_word": false,
|
1881 |
-
"special": true
|
1882 |
-
},
|
1883 |
-
"128235": {
|
1884 |
-
"content": "<|reserved_special_token_230|>",
|
1885 |
-
"lstrip": false,
|
1886 |
-
"normalized": false,
|
1887 |
-
"rstrip": false,
|
1888 |
-
"single_word": false,
|
1889 |
-
"special": true
|
1890 |
-
},
|
1891 |
-
"128236": {
|
1892 |
-
"content": "<|reserved_special_token_231|>",
|
1893 |
-
"lstrip": false,
|
1894 |
-
"normalized": false,
|
1895 |
-
"rstrip": false,
|
1896 |
-
"single_word": false,
|
1897 |
-
"special": true
|
1898 |
-
},
|
1899 |
-
"128237": {
|
1900 |
-
"content": "<|reserved_special_token_232|>",
|
1901 |
-
"lstrip": false,
|
1902 |
-
"normalized": false,
|
1903 |
-
"rstrip": false,
|
1904 |
-
"single_word": false,
|
1905 |
-
"special": true
|
1906 |
-
},
|
1907 |
-
"128238": {
|
1908 |
-
"content": "<|reserved_special_token_233|>",
|
1909 |
-
"lstrip": false,
|
1910 |
-
"normalized": false,
|
1911 |
-
"rstrip": false,
|
1912 |
-
"single_word": false,
|
1913 |
-
"special": true
|
1914 |
-
},
|
1915 |
-
"128239": {
|
1916 |
-
"content": "<|reserved_special_token_234|>",
|
1917 |
-
"lstrip": false,
|
1918 |
-
"normalized": false,
|
1919 |
-
"rstrip": false,
|
1920 |
-
"single_word": false,
|
1921 |
-
"special": true
|
1922 |
-
},
|
1923 |
-
"128240": {
|
1924 |
-
"content": "<|reserved_special_token_235|>",
|
1925 |
-
"lstrip": false,
|
1926 |
-
"normalized": false,
|
1927 |
-
"rstrip": false,
|
1928 |
-
"single_word": false,
|
1929 |
-
"special": true
|
1930 |
-
},
|
1931 |
-
"128241": {
|
1932 |
-
"content": "<|reserved_special_token_236|>",
|
1933 |
-
"lstrip": false,
|
1934 |
-
"normalized": false,
|
1935 |
-
"rstrip": false,
|
1936 |
-
"single_word": false,
|
1937 |
-
"special": true
|
1938 |
-
},
|
1939 |
-
"128242": {
|
1940 |
-
"content": "<|reserved_special_token_237|>",
|
1941 |
-
"lstrip": false,
|
1942 |
-
"normalized": false,
|
1943 |
-
"rstrip": false,
|
1944 |
-
"single_word": false,
|
1945 |
-
"special": true
|
1946 |
-
},
|
1947 |
-
"128243": {
|
1948 |
-
"content": "<|reserved_special_token_238|>",
|
1949 |
-
"lstrip": false,
|
1950 |
-
"normalized": false,
|
1951 |
-
"rstrip": false,
|
1952 |
-
"single_word": false,
|
1953 |
-
"special": true
|
1954 |
-
},
|
1955 |
-
"128244": {
|
1956 |
-
"content": "<|reserved_special_token_239|>",
|
1957 |
-
"lstrip": false,
|
1958 |
-
"normalized": false,
|
1959 |
-
"rstrip": false,
|
1960 |
-
"single_word": false,
|
1961 |
-
"special": true
|
1962 |
-
},
|
1963 |
-
"128245": {
|
1964 |
-
"content": "<|reserved_special_token_240|>",
|
1965 |
-
"lstrip": false,
|
1966 |
-
"normalized": false,
|
1967 |
-
"rstrip": false,
|
1968 |
-
"single_word": false,
|
1969 |
-
"special": true
|
1970 |
-
},
|
1971 |
-
"128246": {
|
1972 |
-
"content": "<|reserved_special_token_241|>",
|
1973 |
-
"lstrip": false,
|
1974 |
-
"normalized": false,
|
1975 |
-
"rstrip": false,
|
1976 |
-
"single_word": false,
|
1977 |
-
"special": true
|
1978 |
-
},
|
1979 |
-
"128247": {
|
1980 |
-
"content": "<|reserved_special_token_242|>",
|
1981 |
-
"lstrip": false,
|
1982 |
-
"normalized": false,
|
1983 |
-
"rstrip": false,
|
1984 |
-
"single_word": false,
|
1985 |
-
"special": true
|
1986 |
-
},
|
1987 |
-
"128248": {
|
1988 |
-
"content": "<|reserved_special_token_243|>",
|
1989 |
-
"lstrip": false,
|
1990 |
-
"normalized": false,
|
1991 |
-
"rstrip": false,
|
1992 |
-
"single_word": false,
|
1993 |
-
"special": true
|
1994 |
-
},
|
1995 |
-
"128249": {
|
1996 |
-
"content": "<|reserved_special_token_244|>",
|
1997 |
-
"lstrip": false,
|
1998 |
-
"normalized": false,
|
1999 |
-
"rstrip": false,
|
2000 |
-
"single_word": false,
|
2001 |
-
"special": true
|
2002 |
-
},
|
2003 |
-
"128250": {
|
2004 |
-
"content": "<|reserved_special_token_245|>",
|
2005 |
-
"lstrip": false,
|
2006 |
-
"normalized": false,
|
2007 |
-
"rstrip": false,
|
2008 |
-
"single_word": false,
|
2009 |
-
"special": true
|
2010 |
-
},
|
2011 |
-
"128251": {
|
2012 |
-
"content": "<|reserved_special_token_246|>",
|
2013 |
-
"lstrip": false,
|
2014 |
-
"normalized": false,
|
2015 |
-
"rstrip": false,
|
2016 |
-
"single_word": false,
|
2017 |
-
"special": true
|
2018 |
-
},
|
2019 |
-
"128252": {
|
2020 |
-
"content": "<|reserved_special_token_247|>",
|
2021 |
-
"lstrip": false,
|
2022 |
-
"normalized": false,
|
2023 |
-
"rstrip": false,
|
2024 |
-
"single_word": false,
|
2025 |
-
"special": true
|
2026 |
-
},
|
2027 |
-
"128253": {
|
2028 |
-
"content": "<|reserved_special_token_248|>",
|
2029 |
-
"lstrip": false,
|
2030 |
-
"normalized": false,
|
2031 |
-
"rstrip": false,
|
2032 |
-
"single_word": false,
|
2033 |
-
"special": true
|
2034 |
-
},
|
2035 |
-
"128254": {
|
2036 |
-
"content": "<|reserved_special_token_249|>",
|
2037 |
-
"lstrip": false,
|
2038 |
-
"normalized": false,
|
2039 |
-
"rstrip": false,
|
2040 |
-
"single_word": false,
|
2041 |
-
"special": true
|
2042 |
-
},
|
2043 |
-
"128255": {
|
2044 |
-
"content": "<|reserved_special_token_250|>",
|
2045 |
"lstrip": false,
|
2046 |
"normalized": false,
|
2047 |
"rstrip": false,
|
@@ -2049,15 +25,22 @@
|
|
2049 |
"special": true
|
2050 |
}
|
2051 |
},
|
2052 |
-
"
|
2053 |
-
|
2054 |
-
|
2055 |
-
|
2056 |
-
"model_input_names": [
|
2057 |
-
"input_ids",
|
2058 |
-
"attention_mask"
|
2059 |
],
|
|
|
|
|
|
|
|
|
|
|
2060 |
"model_max_length": 2048,
|
2061 |
-
"pad_token": "
|
2062 |
-
"
|
|
|
|
|
|
|
|
|
|
|
2063 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
+
"additional_special_tokens": [
|
29 |
+
"<unk>",
|
30 |
+
"<s>",
|
31 |
+
"</s>"
|
|
|
|
|
|
|
32 |
],
|
33 |
+
"bos_token": "<s>",
|
34 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "</s>",
|
37 |
+
"legacy": true,
|
38 |
"model_max_length": 2048,
|
39 |
+
"pad_token": "</s>",
|
40 |
+
"sp_model_kwargs": {},
|
41 |
+
"spaces_between_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"truncation_side": "left",
|
44 |
+
"unk_token": "<unk>",
|
45 |
+
"use_default_system_prompt": true
|
46 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.08422429972704783,
|
4 |
+
"train_runtime": 6988.5729,
|
5 |
+
"train_samples": 113028,
|
6 |
+
"train_samples_per_second": 16.173,
|
7 |
+
"train_steps_per_second": 0.126
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,21 +1,21 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"eval_steps":
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
-
"learning_rate":
|
14 |
-
"logits/chosen":
|
15 |
-
"logits/rejected":
|
16 |
-
"logps/chosen": -
|
17 |
-
"logps/rejected": -
|
18 |
-
"loss": 0.
|
19 |
"rewards/accuracies": 0.0,
|
20 |
"rewards/chosen": 0.0,
|
21 |
"rewards/margins": 0.0,
|
@@ -23,739 +23,1249 @@
|
|
23 |
"step": 1
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"learning_rate":
|
28 |
-
"logits/chosen":
|
29 |
-
"logits/rejected":
|
30 |
-
"logps/chosen": -
|
31 |
-
"logps/rejected": -
|
32 |
-
"loss": 0.
|
33 |
-
"rewards/accuracies": 0.
|
34 |
-
"rewards/chosen":
|
35 |
-
"rewards/margins": 0.
|
36 |
-
"rewards/rejected":
|
37 |
"step": 10
|
38 |
},
|
39 |
{
|
40 |
-
"epoch": 0.
|
41 |
-
"learning_rate":
|
42 |
-
"logits/chosen": -
|
43 |
-
"logits/rejected":
|
44 |
-
"logps/chosen": -
|
45 |
-
"logps/rejected": -
|
46 |
-
"loss": 0.
|
47 |
-
"rewards/accuracies": 0.
|
48 |
-
"rewards/chosen": 0.
|
49 |
-
"rewards/margins": 0.
|
50 |
-
"rewards/rejected": -0.
|
51 |
"step": 20
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 0.
|
55 |
-
"learning_rate":
|
56 |
-
"logits/chosen":
|
57 |
-
"logits/rejected":
|
58 |
-
"logps/chosen": -
|
59 |
-
"logps/rejected": -
|
60 |
-
"loss": 0.
|
61 |
-
"rewards/accuracies": 0.
|
62 |
-
"rewards/chosen":
|
63 |
-
"rewards/margins": 0.
|
64 |
-
"rewards/rejected": -0.
|
65 |
"step": 30
|
66 |
},
|
67 |
{
|
68 |
-
"epoch": 0.
|
69 |
-
"learning_rate":
|
70 |
-
"logits/chosen": -
|
71 |
-
"logits/rejected":
|
72 |
-
"logps/chosen": -
|
73 |
-
"logps/rejected": -
|
74 |
-
"loss": 0.
|
75 |
-
"rewards/accuracies": 0.
|
76 |
-
"rewards/chosen":
|
77 |
-
"rewards/margins": 0.
|
78 |
-
"rewards/rejected": -0.
|
79 |
"step": 40
|
80 |
},
|
81 |
{
|
82 |
-
"epoch": 0.
|
83 |
-
"learning_rate":
|
84 |
-
"logits/chosen":
|
85 |
-
"logits/rejected":
|
86 |
-
"logps/chosen": -
|
87 |
-
"logps/rejected": -
|
88 |
-
"loss": 0.
|
89 |
-
"rewards/accuracies": 0.
|
90 |
-
"rewards/chosen": -0.
|
91 |
-
"rewards/margins": 0.
|
92 |
-
"rewards/rejected": -0.
|
93 |
"step": 50
|
94 |
},
|
95 |
{
|
96 |
-
"epoch": 0.
|
97 |
-
"learning_rate":
|
98 |
-
"logits/chosen":
|
99 |
-
"logits/rejected":
|
100 |
-
"logps/chosen": -
|
101 |
-
"logps/rejected": -
|
102 |
-
"loss": 0.
|
103 |
-
"rewards/accuracies": 0.
|
104 |
-
"rewards/chosen": -0.
|
105 |
-
"rewards/margins": 0.
|
106 |
-
"rewards/rejected": -0.
|
107 |
"step": 60
|
108 |
},
|
109 |
{
|
110 |
-
"epoch": 0.
|
111 |
-
"learning_rate":
|
112 |
-
"logits/chosen":
|
113 |
-
"logits/rejected":
|
114 |
-
"logps/chosen": -
|
115 |
-
"logps/rejected": -
|
116 |
-
"loss": 0.
|
117 |
-
"rewards/accuracies": 0.
|
118 |
-
"rewards/chosen": -0.
|
119 |
-
"rewards/margins": 0.
|
120 |
-
"rewards/rejected": -0.
|
121 |
"step": 70
|
122 |
},
|
123 |
{
|
124 |
-
"epoch": 0.
|
125 |
-
"learning_rate": 4.
|
126 |
-
"logits/chosen":
|
127 |
-
"logits/rejected":
|
128 |
-
"logps/chosen": -
|
129 |
-
"logps/rejected": -
|
130 |
-
"loss": 0.
|
131 |
-
"rewards/accuracies": 0.
|
132 |
-
"rewards/chosen": -0.
|
133 |
-
"rewards/margins": 0.
|
134 |
-
"rewards/rejected": -0.
|
135 |
"step": 80
|
136 |
},
|
137 |
{
|
138 |
-
"epoch": 0.
|
139 |
-
"learning_rate": 4.
|
140 |
-
"logits/chosen":
|
141 |
-
"logits/rejected":
|
142 |
-
"logps/chosen": -
|
143 |
-
"logps/rejected": -
|
144 |
-
"loss": 0.
|
145 |
-
"rewards/accuracies": 0.
|
146 |
-
"rewards/chosen": -0.
|
147 |
-
"rewards/margins": 0.
|
148 |
-
"rewards/rejected": -0.
|
149 |
"step": 90
|
150 |
},
|
151 |
{
|
152 |
-
"epoch": 0.
|
153 |
-
"learning_rate": 4.
|
154 |
-
"logits/chosen":
|
155 |
-
"logits/rejected":
|
156 |
-
"logps/chosen": -
|
157 |
-
"logps/rejected": -
|
158 |
-
"loss": 0.
|
159 |
"rewards/accuracies": 0.7250000238418579,
|
160 |
-
"rewards/chosen": -0.
|
161 |
-
"rewards/margins": 0.
|
162 |
-
"rewards/rejected": -
|
163 |
"step": 100
|
164 |
},
|
165 |
{
|
166 |
-
"epoch": 0.
|
167 |
-
"
|
168 |
-
"
|
169 |
-
"
|
170 |
-
"
|
171 |
-
"
|
172 |
-
"
|
173 |
-
"
|
174 |
-
"
|
175 |
-
"
|
176 |
-
"
|
177 |
-
"
|
178 |
-
"eval_steps_per_second": 0.424,
|
179 |
-
"step": 100
|
180 |
},
|
181 |
{
|
182 |
-
"epoch": 0.
|
183 |
-
"learning_rate": 4.
|
184 |
-
"logits/chosen":
|
185 |
-
"logits/rejected":
|
186 |
-
"logps/chosen": -
|
187 |
-
"logps/rejected": -
|
188 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
189 |
"rewards/accuracies": 0.699999988079071,
|
190 |
-
"rewards/chosen": -
|
191 |
-
"rewards/margins":
|
192 |
-
"rewards/rejected": -
|
193 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
194 |
},
|
195 |
{
|
196 |
"epoch": 0.25,
|
197 |
-
"learning_rate": 4.
|
198 |
-
"logits/chosen":
|
199 |
-
"logits/rejected":
|
200 |
-
"logps/chosen": -
|
201 |
-
"logps/rejected": -
|
202 |
-
"loss": 0.
|
203 |
"rewards/accuracies": 0.762499988079071,
|
204 |
-
"rewards/chosen": -
|
205 |
-
"rewards/margins":
|
206 |
-
"rewards/rejected": -
|
207 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
208 |
},
|
209 |
{
|
210 |
"epoch": 0.27,
|
211 |
-
"learning_rate": 4.
|
212 |
-
"logits/chosen":
|
213 |
-
"logits/rejected":
|
214 |
-
"logps/chosen": -
|
215 |
-
"logps/rejected": -
|
216 |
-
"loss": 0.
|
217 |
-
"rewards/accuracies": 0.
|
218 |
-
"rewards/chosen": -
|
219 |
-
"rewards/margins":
|
220 |
-
"rewards/rejected": -
|
221 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
222 |
},
|
223 |
{
|
224 |
"epoch": 0.29,
|
225 |
-
"learning_rate": 4.
|
226 |
-
"logits/chosen":
|
227 |
-
"logits/rejected":
|
228 |
-
"logps/chosen": -
|
229 |
-
"logps/rejected": -
|
230 |
-
"loss": 0.
|
231 |
-
"rewards/accuracies": 0.
|
232 |
-
"rewards/chosen": -
|
233 |
-
"rewards/margins": 0.
|
234 |
-
"rewards/rejected": -
|
235 |
-
"step":
|
236 |
},
|
237 |
{
|
238 |
"epoch": 0.31,
|
239 |
-
"learning_rate": 4.
|
240 |
-
"logits/chosen":
|
241 |
-
"logits/rejected":
|
242 |
-
"logps/chosen": -
|
243 |
-
"logps/rejected": -
|
244 |
-
"loss": 0.
|
245 |
-
"rewards/accuracies": 0.
|
246 |
-
"rewards/chosen": -
|
247 |
-
"rewards/margins":
|
248 |
-
"rewards/rejected": -
|
249 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
},
|
251 |
{
|
252 |
"epoch": 0.33,
|
253 |
-
"learning_rate": 4.
|
254 |
-
"logits/chosen":
|
255 |
-
"logits/rejected":
|
256 |
-
"logps/chosen": -
|
257 |
-
"logps/rejected": -
|
258 |
-
"loss": 0.
|
259 |
-
"rewards/accuracies": 0.
|
260 |
-
"rewards/chosen": -
|
261 |
-
"rewards/margins":
|
262 |
-
"rewards/rejected": -
|
263 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
264 |
},
|
265 |
{
|
266 |
"epoch": 0.36,
|
267 |
-
"learning_rate": 4.
|
268 |
-
"logits/chosen":
|
269 |
-
"logits/rejected":
|
270 |
-
"logps/chosen": -
|
271 |
-
"logps/rejected": -
|
272 |
-
"loss": 0.
|
273 |
-
"rewards/accuracies": 0.
|
274 |
-
"rewards/chosen": -
|
275 |
-
"rewards/margins":
|
276 |
-
"rewards/rejected": -
|
277 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
278 |
},
|
279 |
{
|
280 |
"epoch": 0.38,
|
281 |
-
"learning_rate": 3.
|
282 |
-
"logits/chosen":
|
283 |
-
"logits/rejected":
|
284 |
-
"logps/chosen": -
|
285 |
-
"logps/rejected": -
|
286 |
-
"loss": 0.
|
287 |
-
"rewards/accuracies": 0.
|
288 |
-
"rewards/chosen": -
|
289 |
-
"rewards/margins":
|
290 |
-
"rewards/rejected": -
|
291 |
-
"step":
|
292 |
},
|
293 |
{
|
294 |
"epoch": 0.4,
|
295 |
-
"learning_rate": 3.
|
296 |
-
"logits/chosen":
|
297 |
-
"logits/rejected":
|
298 |
-
"logps/chosen": -
|
299 |
-
"logps/rejected": -
|
300 |
-
"loss": 0.
|
301 |
-
"rewards/accuracies": 0.
|
302 |
-
"rewards/chosen": -
|
303 |
-
"rewards/margins":
|
304 |
-
"rewards/rejected": -
|
305 |
-
"step":
|
306 |
},
|
307 |
{
|
308 |
-
"epoch": 0.
|
309 |
-
"learning_rate": 3.
|
310 |
-
"logits/chosen":
|
311 |
-
"logits/rejected":
|
312 |
-
"logps/chosen": -
|
313 |
-
"logps/rejected": -
|
314 |
-
"loss": 0.
|
315 |
-
"rewards/accuracies": 0.
|
316 |
-
"rewards/chosen": -
|
317 |
-
"rewards/margins":
|
318 |
-
"rewards/rejected": -
|
319 |
-
"step":
|
320 |
},
|
321 |
{
|
322 |
"epoch": 0.42,
|
323 |
-
"
|
324 |
-
"
|
325 |
-
"
|
326 |
-
"
|
327 |
-
"
|
328 |
-
"
|
329 |
-
"
|
330 |
-
"
|
331 |
-
"
|
332 |
-
"
|
333 |
-
"
|
334 |
-
"eval_steps_per_second": 0.426,
|
335 |
-
"step": 200
|
336 |
},
|
337 |
{
|
338 |
-
"epoch": 0.
|
339 |
-
"learning_rate": 3.
|
340 |
-
"logits/chosen":
|
341 |
-
"logits/rejected":
|
342 |
-
"logps/chosen": -
|
343 |
-
"logps/rejected": -
|
344 |
-
"loss": 0.
|
345 |
"rewards/accuracies": 0.7250000238418579,
|
346 |
-
"rewards/chosen": -
|
347 |
-
"rewards/margins":
|
348 |
-
"rewards/rejected": -
|
349 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
350 |
},
|
351 |
{
|
352 |
"epoch": 0.46,
|
353 |
-
"learning_rate": 3.
|
354 |
-
"logits/chosen":
|
355 |
-
"logits/rejected":
|
356 |
-
"logps/chosen": -
|
357 |
-
"logps/rejected": -
|
358 |
-
"loss": 0.
|
359 |
-
"rewards/accuracies": 0.
|
360 |
-
"rewards/chosen": -
|
361 |
-
"rewards/margins":
|
362 |
-
"rewards/rejected": -
|
363 |
-
"step":
|
364 |
},
|
365 |
{
|
366 |
"epoch": 0.48,
|
367 |
-
"learning_rate": 3.
|
368 |
-
"logits/chosen":
|
369 |
-
"logits/rejected":
|
370 |
-
"logps/chosen": -
|
371 |
-
"logps/rejected": -
|
372 |
-
"loss": 0.
|
373 |
-
"rewards/accuracies": 0.
|
374 |
-
"rewards/chosen": -
|
375 |
-
"rewards/margins":
|
376 |
-
"rewards/rejected": -
|
377 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
378 |
},
|
379 |
{
|
380 |
"epoch": 0.5,
|
381 |
-
"learning_rate": 2.
|
382 |
-
"logits/chosen":
|
383 |
-
"logits/rejected":
|
384 |
-
"logps/chosen": -
|
385 |
-
"logps/rejected": -
|
386 |
-
"loss": 0.
|
387 |
-
"rewards/accuracies": 0.
|
388 |
-
"rewards/chosen": -
|
389 |
-
"rewards/margins": 0.
|
390 |
-
"rewards/rejected": -
|
391 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
392 |
},
|
393 |
{
|
394 |
"epoch": 0.52,
|
395 |
-
"learning_rate": 2.
|
396 |
-
"logits/chosen":
|
397 |
-
"logits/rejected":
|
398 |
-
"logps/chosen": -
|
399 |
-
"logps/rejected": -
|
400 |
-
"loss": 0.
|
401 |
-
"rewards/accuracies": 0.
|
402 |
-
"rewards/chosen": -
|
403 |
-
"rewards/margins":
|
404 |
-
"rewards/rejected": -
|
405 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
406 |
},
|
407 |
{
|
408 |
"epoch": 0.54,
|
409 |
-
"learning_rate": 2.
|
410 |
-
"logits/chosen":
|
411 |
-
"logits/rejected":
|
412 |
-
"logps/chosen": -
|
413 |
-
"logps/rejected": -
|
414 |
-
"loss": 0.
|
415 |
-
"rewards/accuracies": 0.
|
416 |
-
"rewards/chosen": -
|
417 |
-
"rewards/margins": 0.
|
418 |
-
"rewards/rejected": -
|
419 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
420 |
},
|
421 |
{
|
422 |
"epoch": 0.57,
|
423 |
-
"learning_rate": 2.
|
424 |
-
"logits/chosen":
|
425 |
-
"logits/rejected":
|
426 |
-
"logps/chosen": -
|
427 |
-
"logps/rejected": -
|
428 |
-
"loss": 0.
|
429 |
-
"rewards/accuracies": 0.
|
430 |
-
"rewards/chosen": -
|
431 |
-
"rewards/margins":
|
432 |
-
"rewards/rejected": -
|
433 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
434 |
},
|
435 |
{
|
436 |
"epoch": 0.59,
|
437 |
-
"learning_rate": 2.
|
438 |
-
"logits/chosen":
|
439 |
-
"logits/rejected":
|
440 |
-
"logps/chosen": -
|
441 |
-
"logps/rejected": -
|
442 |
-
"loss": 0.
|
443 |
-
"rewards/accuracies": 0.
|
444 |
-
"rewards/chosen": -
|
445 |
-
"rewards/margins":
|
446 |
-
"rewards/rejected": -
|
447 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
448 |
},
|
449 |
{
|
450 |
"epoch": 0.61,
|
451 |
-
"learning_rate": 1.
|
452 |
-
"logits/chosen":
|
453 |
-
"logits/rejected":
|
454 |
-
"logps/chosen": -
|
455 |
-
"logps/rejected": -
|
456 |
-
"loss": 0.
|
457 |
-
"rewards/accuracies": 0.
|
458 |
-
"rewards/chosen": -
|
459 |
-
"rewards/margins":
|
460 |
-
"rewards/rejected": -
|
461 |
-
"step":
|
462 |
},
|
463 |
{
|
464 |
-
"epoch": 0.
|
465 |
-
"learning_rate": 1.
|
466 |
-
"logits/chosen":
|
467 |
-
"logits/rejected": 1.
|
468 |
-
"logps/chosen": -
|
469 |
-
"logps/rejected": -
|
470 |
-
"loss": 0.
|
471 |
-
"rewards/accuracies": 0.
|
472 |
-
"rewards/chosen": -
|
473 |
-
"rewards/margins":
|
474 |
-
"rewards/rejected": -
|
475 |
-
"step":
|
476 |
},
|
477 |
{
|
478 |
"epoch": 0.63,
|
479 |
-
"
|
480 |
-
"
|
481 |
-
"
|
482 |
-
"
|
483 |
-
"
|
484 |
-
"
|
485 |
-
"
|
486 |
-
"
|
487 |
-
"
|
488 |
-
"
|
489 |
-
"
|
490 |
-
"eval_steps_per_second": 0.425,
|
491 |
-
"step": 300
|
492 |
},
|
493 |
{
|
494 |
"epoch": 0.65,
|
495 |
-
"learning_rate": 1.
|
496 |
-
"logits/chosen":
|
497 |
-
"logits/rejected":
|
498 |
-
"logps/chosen": -
|
499 |
-
"logps/rejected": -
|
500 |
-
"loss": 0.
|
501 |
-
"rewards/accuracies": 0.
|
502 |
-
"rewards/chosen": -
|
503 |
-
"rewards/margins":
|
504 |
-
"rewards/rejected": -
|
505 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
506 |
},
|
507 |
{
|
508 |
"epoch": 0.67,
|
509 |
-
"learning_rate": 1.
|
510 |
-
"logits/chosen":
|
511 |
-
"logits/rejected":
|
512 |
-
"logps/chosen": -
|
513 |
-
"logps/rejected": -
|
514 |
-
"loss": 0.
|
515 |
-
"rewards/accuracies": 0.
|
516 |
-
"rewards/chosen": -
|
517 |
-
"rewards/margins":
|
518 |
-
"rewards/rejected": -
|
519 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
520 |
},
|
521 |
{
|
522 |
"epoch": 0.69,
|
523 |
-
"learning_rate": 1.
|
524 |
-
"logits/chosen":
|
525 |
-
"logits/rejected":
|
526 |
-
"logps/chosen": -
|
527 |
-
"logps/rejected": -533.
|
528 |
-
"loss": 0.
|
529 |
-
"rewards/accuracies": 0.
|
530 |
-
"rewards/chosen": -
|
531 |
-
"rewards/margins":
|
532 |
-
"rewards/rejected": -
|
533 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
534 |
},
|
535 |
{
|
536 |
"epoch": 0.71,
|
537 |
-
"learning_rate": 1.
|
538 |
-
"logits/chosen":
|
539 |
-
"logits/rejected":
|
540 |
-
"logps/chosen": -
|
541 |
-
"logps/rejected": -
|
542 |
-
"loss": 0.
|
543 |
-
"rewards/accuracies": 0.
|
544 |
-
"rewards/chosen": -
|
545 |
-
"rewards/margins":
|
546 |
-
"rewards/rejected": -
|
547 |
-
"step":
|
548 |
},
|
549 |
{
|
550 |
-
"epoch": 0.
|
551 |
-
"learning_rate": 1.
|
552 |
-
"logits/chosen":
|
553 |
-
"logits/rejected": 1.
|
554 |
-
"logps/chosen": -
|
555 |
-
"logps/rejected": -
|
556 |
-
"loss": 0.
|
557 |
-
"rewards/accuracies": 0.
|
558 |
-
"rewards/chosen": -
|
559 |
-
"rewards/margins":
|
560 |
-
"rewards/rejected": -
|
561 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
562 |
},
|
563 |
{
|
564 |
"epoch": 0.75,
|
565 |
-
"learning_rate":
|
566 |
-
"logits/chosen":
|
567 |
-
"logits/rejected":
|
568 |
-
"logps/chosen": -
|
569 |
-
"logps/rejected": -
|
570 |
-
"loss": 0.
|
571 |
-
"rewards/accuracies": 0.
|
572 |
-
"rewards/chosen": -
|
573 |
-
"rewards/margins":
|
574 |
-
"rewards/rejected": -
|
575 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
576 |
},
|
577 |
{
|
578 |
"epoch": 0.77,
|
579 |
-
"learning_rate": 7.
|
580 |
-
"logits/chosen":
|
581 |
-
"logits/rejected":
|
582 |
-
"logps/chosen": -
|
583 |
-
"logps/rejected": -
|
584 |
-
"loss": 0.
|
585 |
-
"rewards/accuracies": 0.
|
586 |
-
"rewards/chosen": -
|
587 |
-
"rewards/margins":
|
588 |
-
"rewards/rejected": -
|
589 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
590 |
},
|
591 |
{
|
592 |
"epoch": 0.8,
|
593 |
-
"learning_rate":
|
594 |
-
"logits/chosen":
|
595 |
-
"logits/rejected":
|
596 |
-
"logps/chosen": -
|
597 |
-
"logps/rejected": -
|
598 |
-
"loss": 0.
|
599 |
-
"rewards/accuracies": 0.
|
600 |
-
"rewards/chosen": -
|
601 |
-
"rewards/margins":
|
602 |
-
"rewards/rejected": -
|
603 |
-
"step":
|
604 |
},
|
605 |
{
|
606 |
-
"epoch": 0.
|
607 |
-
"learning_rate":
|
608 |
-
"logits/chosen":
|
609 |
-
"logits/rejected":
|
610 |
-
"logps/chosen": -
|
611 |
-
"logps/rejected": -
|
612 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
613 |
"rewards/accuracies": 0.7437499761581421,
|
614 |
-
"rewards/chosen": -
|
615 |
-
"rewards/margins":
|
616 |
-
"rewards/rejected": -
|
617 |
-
"step":
|
618 |
},
|
619 |
{
|
620 |
"epoch": 0.84,
|
621 |
-
"learning_rate": 3.
|
622 |
-
"logits/chosen":
|
623 |
-
"logits/rejected":
|
624 |
-
"logps/chosen": -
|
625 |
-
"logps/rejected": -
|
626 |
-
"loss": 0.
|
627 |
-
"rewards/accuracies": 0.
|
628 |
-
"rewards/chosen": -
|
629 |
-
"rewards/margins":
|
630 |
-
"rewards/rejected": -
|
631 |
-
"step":
|
632 |
},
|
633 |
{
|
634 |
-
"epoch": 0.
|
635 |
-
"
|
636 |
-
"
|
637 |
-
"
|
638 |
-
"
|
639 |
-
"
|
640 |
-
"
|
641 |
-
"
|
642 |
-
"
|
643 |
-
"
|
644 |
-
"
|
645 |
-
"
|
646 |
-
"eval_steps_per_second": 0.428,
|
647 |
-
"step": 400
|
648 |
},
|
649 |
{
|
650 |
"epoch": 0.86,
|
651 |
-
"learning_rate": 2.
|
652 |
-
"logits/chosen":
|
653 |
-
"logits/rejected":
|
654 |
-
"logps/chosen": -
|
655 |
-
"logps/rejected": -
|
656 |
-
"loss": 0.
|
657 |
-
"rewards/accuracies": 0.
|
658 |
-
"rewards/chosen": -
|
659 |
-
"rewards/margins":
|
660 |
-
"rewards/rejected": -
|
661 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
662 |
},
|
663 |
{
|
664 |
"epoch": 0.88,
|
665 |
-
"learning_rate": 2.
|
666 |
-
"logits/chosen":
|
667 |
-
"logits/rejected":
|
668 |
-
"logps/chosen": -
|
669 |
-
"logps/rejected": -
|
670 |
-
"loss": 0.
|
671 |
-
"rewards/accuracies": 0.
|
672 |
-
"rewards/chosen": -
|
673 |
-
"rewards/margins":
|
674 |
-
"rewards/rejected": -
|
675 |
-
"step":
|
676 |
},
|
677 |
{
|
678 |
-
"epoch": 0.
|
679 |
-
"learning_rate": 1.
|
680 |
-
"logits/chosen":
|
681 |
-
"logits/rejected":
|
682 |
-
"logps/chosen": -
|
683 |
-
"logps/rejected": -
|
684 |
-
"loss": 0.
|
685 |
-
"rewards/accuracies": 0.
|
686 |
-
"rewards/chosen": -
|
687 |
-
"rewards/margins":
|
688 |
-
"rewards/rejected": -
|
689 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
690 |
},
|
691 |
{
|
692 |
"epoch": 0.92,
|
693 |
-
"learning_rate":
|
694 |
-
"logits/chosen":
|
695 |
-
"logits/rejected":
|
696 |
-
"logps/chosen": -
|
697 |
-
"logps/rejected": -
|
698 |
-
"loss": 0.
|
699 |
-
"rewards/accuracies": 0.
|
700 |
-
"rewards/chosen": -
|
701 |
-
"rewards/margins":
|
702 |
-
"rewards/rejected": -
|
703 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
704 |
},
|
705 |
{
|
706 |
"epoch": 0.94,
|
707 |
-
"learning_rate":
|
708 |
-
"logits/chosen":
|
709 |
-
"logits/rejected":
|
710 |
-
"logps/chosen": -
|
711 |
-
"logps/rejected": -
|
712 |
-
"loss": 0.
|
713 |
-
"rewards/accuracies": 0.
|
714 |
-
"rewards/chosen": -
|
715 |
-
"rewards/margins":
|
716 |
-
"rewards/rejected": -
|
717 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
718 |
},
|
719 |
{
|
720 |
"epoch": 0.96,
|
721 |
-
"learning_rate":
|
722 |
-
"logits/chosen":
|
723 |
-
"logits/rejected":
|
724 |
-
"logps/chosen": -
|
725 |
-
"logps/rejected": -
|
726 |
-
"loss": 0.
|
727 |
-
"rewards/accuracies": 0.
|
728 |
-
"rewards/chosen": -
|
729 |
-
"rewards/margins":
|
730 |
-
"rewards/rejected": -
|
731 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
732 |
},
|
733 |
{
|
734 |
"epoch": 0.98,
|
735 |
-
"learning_rate": 3.
|
736 |
-
"logits/chosen":
|
737 |
-
"logits/rejected":
|
738 |
-
"logps/chosen": -
|
739 |
-
"logps/rejected": -
|
740 |
-
"loss": 0.
|
741 |
-
"rewards/accuracies": 0.
|
742 |
-
"rewards/chosen": -
|
743 |
-
"rewards/margins":
|
744 |
-
"rewards/rejected": -
|
745 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
746 |
},
|
747 |
{
|
748 |
"epoch": 1.0,
|
749 |
-
"step":
|
750 |
"total_flos": 0.0,
|
751 |
-
"train_loss": 0.
|
752 |
-
"train_runtime":
|
753 |
-
"train_samples_per_second":
|
754 |
-
"train_steps_per_second": 0.
|
755 |
}
|
756 |
],
|
757 |
"logging_steps": 10,
|
758 |
-
"max_steps":
|
759 |
"num_train_epochs": 1,
|
760 |
"save_steps": 1000,
|
761 |
"total_flos": 0.0,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9994340690435767,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 883,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
+
"learning_rate": 5.617977528089887e-09,
|
14 |
+
"logits/chosen": -2.8445301055908203,
|
15 |
+
"logits/rejected": -2.814356565475464,
|
16 |
+
"logps/chosen": -319.6065979003906,
|
17 |
+
"logps/rejected": -174.94183349609375,
|
18 |
+
"loss": 0.3715,
|
19 |
"rewards/accuracies": 0.0,
|
20 |
"rewards/chosen": 0.0,
|
21 |
"rewards/margins": 0.0,
|
|
|
23 |
"step": 1
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.01,
|
27 |
+
"learning_rate": 5.617977528089887e-08,
|
28 |
+
"logits/chosen": -2.8251900672912598,
|
29 |
+
"logits/rejected": -2.789383888244629,
|
30 |
+
"logps/chosen": -309.8087463378906,
|
31 |
+
"logps/rejected": -215.91148376464844,
|
32 |
+
"loss": 0.3422,
|
33 |
+
"rewards/accuracies": 0.3472222089767456,
|
34 |
+
"rewards/chosen": -1.3414668501354754e-05,
|
35 |
+
"rewards/margins": -0.0010301731526851654,
|
36 |
+
"rewards/rejected": 0.001016758382320404,
|
37 |
"step": 10
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 0.02,
|
41 |
+
"learning_rate": 1.1235955056179774e-07,
|
42 |
+
"logits/chosen": -2.7988970279693604,
|
43 |
+
"logits/rejected": -2.761237382888794,
|
44 |
+
"logps/chosen": -393.90570068359375,
|
45 |
+
"logps/rejected": -215.60818481445312,
|
46 |
+
"loss": 0.3403,
|
47 |
+
"rewards/accuracies": 0.6499999761581421,
|
48 |
+
"rewards/chosen": 0.0024659852497279644,
|
49 |
+
"rewards/margins": 0.003918920643627644,
|
50 |
+
"rewards/rejected": -0.001452935510315001,
|
51 |
"step": 20
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.03,
|
55 |
+
"learning_rate": 1.6853932584269663e-07,
|
56 |
+
"logits/chosen": -2.758561611175537,
|
57 |
+
"logits/rejected": -2.7206640243530273,
|
58 |
+
"logps/chosen": -338.9088134765625,
|
59 |
+
"logps/rejected": -169.10595703125,
|
60 |
+
"loss": 0.3345,
|
61 |
+
"rewards/accuracies": 0.7250000238418579,
|
62 |
+
"rewards/chosen": 0.010817291215062141,
|
63 |
+
"rewards/margins": 0.01906611956655979,
|
64 |
+
"rewards/rejected": -0.0082488302141428,
|
65 |
"step": 30
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 0.05,
|
69 |
+
"learning_rate": 2.2471910112359549e-07,
|
70 |
+
"logits/chosen": -2.7481541633605957,
|
71 |
+
"logits/rejected": -2.725372076034546,
|
72 |
+
"logps/chosen": -380.46087646484375,
|
73 |
+
"logps/rejected": -190.8077392578125,
|
74 |
+
"loss": 0.3464,
|
75 |
+
"rewards/accuracies": 0.7437499761581421,
|
76 |
+
"rewards/chosen": 0.03875667601823807,
|
77 |
+
"rewards/margins": 0.07445183396339417,
|
78 |
+
"rewards/rejected": -0.035695165395736694,
|
79 |
"step": 40
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 0.06,
|
83 |
+
"learning_rate": 2.8089887640449437e-07,
|
84 |
+
"logits/chosen": -2.6264801025390625,
|
85 |
+
"logits/rejected": -2.6301627159118652,
|
86 |
+
"logps/chosen": -317.04522705078125,
|
87 |
+
"logps/rejected": -220.34957885742188,
|
88 |
+
"loss": 0.3512,
|
89 |
+
"rewards/accuracies": 0.5687500238418579,
|
90 |
+
"rewards/chosen": -0.008213408291339874,
|
91 |
+
"rewards/margins": 0.0798892229795456,
|
92 |
+
"rewards/rejected": -0.08810263872146606,
|
93 |
"step": 50
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 0.07,
|
97 |
+
"learning_rate": 3.3707865168539325e-07,
|
98 |
+
"logits/chosen": -2.611682653427124,
|
99 |
+
"logits/rejected": -2.590343475341797,
|
100 |
+
"logps/chosen": -311.91217041015625,
|
101 |
+
"logps/rejected": -191.47933959960938,
|
102 |
+
"loss": 0.3306,
|
103 |
+
"rewards/accuracies": 0.6937500238418579,
|
104 |
+
"rewards/chosen": -0.010586333461105824,
|
105 |
+
"rewards/margins": 0.19717885553836823,
|
106 |
+
"rewards/rejected": -0.20776517689228058,
|
107 |
"step": 60
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 0.08,
|
111 |
+
"learning_rate": 3.9325842696629214e-07,
|
112 |
+
"logits/chosen": -2.523609161376953,
|
113 |
+
"logits/rejected": -2.4986379146575928,
|
114 |
+
"logps/chosen": -387.2811279296875,
|
115 |
+
"logps/rejected": -237.1663818359375,
|
116 |
+
"loss": 0.2949,
|
117 |
+
"rewards/accuracies": 0.699999988079071,
|
118 |
+
"rewards/chosen": -0.10780398547649384,
|
119 |
+
"rewards/margins": 0.32766008377075195,
|
120 |
+
"rewards/rejected": -0.4354640543460846,
|
121 |
"step": 70
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 0.09,
|
125 |
+
"learning_rate": 4.4943820224719097e-07,
|
126 |
+
"logits/chosen": -2.5573625564575195,
|
127 |
+
"logits/rejected": -2.5448756217956543,
|
128 |
+
"logps/chosen": -370.834228515625,
|
129 |
+
"logps/rejected": -265.3526611328125,
|
130 |
+
"loss": 0.2472,
|
131 |
+
"rewards/accuracies": 0.612500011920929,
|
132 |
+
"rewards/chosen": -0.2603791356086731,
|
133 |
+
"rewards/margins": 0.3768497407436371,
|
134 |
+
"rewards/rejected": -0.6372288465499878,
|
135 |
"step": 80
|
136 |
},
|
137 |
{
|
138 |
+
"epoch": 0.1,
|
139 |
+
"learning_rate": 4.999980431020109e-07,
|
140 |
+
"logits/chosen": -2.5590720176696777,
|
141 |
+
"logits/rejected": -2.5129566192626953,
|
142 |
+
"logps/chosen": -386.1466064453125,
|
143 |
+
"logps/rejected": -303.9127197265625,
|
144 |
+
"loss": 0.1973,
|
145 |
+
"rewards/accuracies": 0.768750011920929,
|
146 |
+
"rewards/chosen": -0.5000510215759277,
|
147 |
+
"rewards/margins": 0.4384336471557617,
|
148 |
+
"rewards/rejected": -0.938484787940979,
|
149 |
"step": 90
|
150 |
},
|
151 |
{
|
152 |
+
"epoch": 0.11,
|
153 |
+
"learning_rate": 4.997632524101301e-07,
|
154 |
+
"logits/chosen": -2.4931159019470215,
|
155 |
+
"logits/rejected": -2.468529224395752,
|
156 |
+
"logps/chosen": -443.2901306152344,
|
157 |
+
"logps/rejected": -325.82012939453125,
|
158 |
+
"loss": 0.1395,
|
159 |
"rewards/accuracies": 0.7250000238418579,
|
160 |
+
"rewards/chosen": -0.6497722864151001,
|
161 |
+
"rewards/margins": 0.7651033997535706,
|
162 |
+
"rewards/rejected": -1.4148756265640259,
|
163 |
"step": 100
|
164 |
},
|
165 |
{
|
166 |
+
"epoch": 0.12,
|
167 |
+
"learning_rate": 4.991375032514749e-07,
|
168 |
+
"logits/chosen": -2.4719808101654053,
|
169 |
+
"logits/rejected": -2.42130708694458,
|
170 |
+
"logps/chosen": -444.5228576660156,
|
171 |
+
"logps/rejected": -351.6055603027344,
|
172 |
+
"loss": 0.1286,
|
173 |
+
"rewards/accuracies": 0.6812499761581421,
|
174 |
+
"rewards/chosen": -0.9098852276802063,
|
175 |
+
"rewards/margins": 0.6541920900344849,
|
176 |
+
"rewards/rejected": -1.5640771389007568,
|
177 |
+
"step": 110
|
|
|
|
|
178 |
},
|
179 |
{
|
180 |
+
"epoch": 0.14,
|
181 |
+
"learning_rate": 4.98121775121344e-07,
|
182 |
+
"logits/chosen": -2.4348862171173096,
|
183 |
+
"logits/rejected": -2.4189703464508057,
|
184 |
+
"logps/chosen": -401.9959716796875,
|
185 |
+
"logps/rejected": -356.4914245605469,
|
186 |
+
"loss": 0.1242,
|
187 |
+
"rewards/accuracies": 0.731249988079071,
|
188 |
+
"rewards/chosen": -0.8814595937728882,
|
189 |
+
"rewards/margins": 0.7036622762680054,
|
190 |
+
"rewards/rejected": -1.5851218700408936,
|
191 |
+
"step": 120
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.15,
|
195 |
+
"learning_rate": 4.96717657955441e-07,
|
196 |
+
"logits/chosen": -2.432359218597412,
|
197 |
+
"logits/rejected": -2.3951916694641113,
|
198 |
+
"logps/chosen": -467.46258544921875,
|
199 |
+
"logps/rejected": -365.39935302734375,
|
200 |
+
"loss": 0.1171,
|
201 |
+
"rewards/accuracies": 0.7250000238418579,
|
202 |
+
"rewards/chosen": -0.7459506988525391,
|
203 |
+
"rewards/margins": 0.9494789242744446,
|
204 |
+
"rewards/rejected": -1.6954295635223389,
|
205 |
+
"step": 130
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.16,
|
209 |
+
"learning_rate": 4.949273496411216e-07,
|
210 |
+
"logits/chosen": -2.4169604778289795,
|
211 |
+
"logits/rejected": -2.3435044288635254,
|
212 |
+
"logps/chosen": -457.04315185546875,
|
213 |
+
"logps/rejected": -351.8127136230469,
|
214 |
+
"loss": 0.1122,
|
215 |
+
"rewards/accuracies": 0.768750011920929,
|
216 |
+
"rewards/chosen": -0.8486078381538391,
|
217 |
+
"rewards/margins": 0.9041606783866882,
|
218 |
+
"rewards/rejected": -1.7527685165405273,
|
219 |
+
"step": 140
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.17,
|
223 |
+
"learning_rate": 4.927536525770046e-07,
|
224 |
+
"logits/chosen": -2.3999485969543457,
|
225 |
+
"logits/rejected": -2.3312039375305176,
|
226 |
+
"logps/chosen": -469.7005310058594,
|
227 |
+
"logps/rejected": -392.58245849609375,
|
228 |
+
"loss": 0.0875,
|
229 |
+
"rewards/accuracies": 0.6937500238418579,
|
230 |
+
"rewards/chosen": -1.270356297492981,
|
231 |
+
"rewards/margins": 0.873481273651123,
|
232 |
+
"rewards/rejected": -2.1438372135162354,
|
233 |
+
"step": 150
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.18,
|
237 |
+
"learning_rate": 4.901999692863326e-07,
|
238 |
+
"logits/chosen": -2.3253886699676514,
|
239 |
+
"logits/rejected": -2.282778263092041,
|
240 |
+
"logps/chosen": -426.901611328125,
|
241 |
+
"logps/rejected": -402.61676025390625,
|
242 |
+
"loss": 0.0988,
|
243 |
+
"rewards/accuracies": 0.6875,
|
244 |
+
"rewards/chosen": -0.9533098936080933,
|
245 |
+
"rewards/margins": 1.0418169498443604,
|
246 |
+
"rewards/rejected": -1.995126724243164,
|
247 |
+
"step": 160
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.19,
|
251 |
+
"learning_rate": 4.872702970909464e-07,
|
252 |
+
"logits/chosen": -2.2736876010894775,
|
253 |
+
"logits/rejected": -2.252612352371216,
|
254 |
+
"logps/chosen": -419.8299255371094,
|
255 |
+
"logps/rejected": -376.61456298828125,
|
256 |
+
"loss": 0.1007,
|
257 |
+
"rewards/accuracies": 0.737500011920929,
|
258 |
+
"rewards/chosen": -1.1481902599334717,
|
259 |
+
"rewards/margins": 0.816639244556427,
|
260 |
+
"rewards/rejected": -1.964829444885254,
|
261 |
+
"step": 170
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.2,
|
265 |
+
"learning_rate": 4.839692218542131e-07,
|
266 |
+
"logits/chosen": -2.3057937622070312,
|
267 |
+
"logits/rejected": -2.2593424320220947,
|
268 |
+
"logps/chosen": -515.2421264648438,
|
269 |
+
"logps/rejected": -416.0797424316406,
|
270 |
+
"loss": 0.0914,
|
271 |
"rewards/accuracies": 0.699999988079071,
|
272 |
+
"rewards/chosen": -1.2467437982559204,
|
273 |
+
"rewards/margins": 1.0007789134979248,
|
274 |
+
"rewards/rejected": -2.2475228309631348,
|
275 |
+
"step": 180
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.22,
|
279 |
+
"learning_rate": 4.803019108026997e-07,
|
280 |
+
"logits/chosen": -2.3358588218688965,
|
281 |
+
"logits/rejected": -2.2952218055725098,
|
282 |
+
"logps/chosen": -413.60198974609375,
|
283 |
+
"logps/rejected": -376.8982849121094,
|
284 |
+
"loss": 0.1101,
|
285 |
+
"rewards/accuracies": 0.768750011920929,
|
286 |
+
"rewards/chosen": -0.8951161503791809,
|
287 |
+
"rewards/margins": 0.9150535464286804,
|
288 |
+
"rewards/rejected": -1.8101698160171509,
|
289 |
+
"step": 190
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.23,
|
293 |
+
"learning_rate": 4.7627410443782887e-07,
|
294 |
+
"logits/chosen": -2.278486490249634,
|
295 |
+
"logits/rejected": -2.231799364089966,
|
296 |
+
"logps/chosen": -481.43267822265625,
|
297 |
+
"logps/rejected": -418.29400634765625,
|
298 |
+
"loss": 0.088,
|
299 |
+
"rewards/accuracies": 0.706250011920929,
|
300 |
+
"rewards/chosen": -1.1549925804138184,
|
301 |
+
"rewards/margins": 0.9669499397277832,
|
302 |
+
"rewards/rejected": -2.1219422817230225,
|
303 |
+
"step": 200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.24,
|
307 |
+
"learning_rate": 4.7189210755018034e-07,
|
308 |
+
"logits/chosen": -2.2762014865875244,
|
309 |
+
"logits/rejected": -2.2429184913635254,
|
310 |
+
"logps/chosen": -479.207763671875,
|
311 |
+
"logps/rejected": -468.08319091796875,
|
312 |
+
"loss": 0.0741,
|
313 |
+
"rewards/accuracies": 0.7875000238418579,
|
314 |
+
"rewards/chosen": -1.3922666311264038,
|
315 |
+
"rewards/margins": 1.2790825366973877,
|
316 |
+
"rewards/rejected": -2.671349048614502,
|
317 |
+
"step": 210
|
318 |
},
|
319 |
{
|
320 |
"epoch": 0.25,
|
321 |
+
"learning_rate": 4.671627793504988e-07,
|
322 |
+
"logits/chosen": -2.2565343379974365,
|
323 |
+
"logits/rejected": -2.201573610305786,
|
324 |
+
"logps/chosen": -496.92071533203125,
|
325 |
+
"logps/rejected": -468.92767333984375,
|
326 |
+
"loss": 0.0725,
|
327 |
"rewards/accuracies": 0.762499988079071,
|
328 |
+
"rewards/chosen": -1.47738778591156,
|
329 |
+
"rewards/margins": 1.299922227859497,
|
330 |
+
"rewards/rejected": -2.7773098945617676,
|
331 |
+
"step": 220
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.26,
|
335 |
+
"learning_rate": 4.6209352273286095e-07,
|
336 |
+
"logits/chosen": -2.2663636207580566,
|
337 |
+
"logits/rejected": -2.2125396728515625,
|
338 |
+
"logps/chosen": -488.028076171875,
|
339 |
+
"logps/rejected": -457.62615966796875,
|
340 |
+
"loss": 0.0718,
|
341 |
+
"rewards/accuracies": 0.7124999761581421,
|
342 |
+
"rewards/chosen": -1.5378353595733643,
|
343 |
+
"rewards/margins": 1.093570351600647,
|
344 |
+
"rewards/rejected": -2.6314055919647217,
|
345 |
+
"step": 230
|
346 |
},
|
347 |
{
|
348 |
"epoch": 0.27,
|
349 |
+
"learning_rate": 4.56692272686805e-07,
|
350 |
+
"logits/chosen": -2.222353219985962,
|
351 |
+
"logits/rejected": -2.175215244293213,
|
352 |
+
"logps/chosen": -495.33294677734375,
|
353 |
+
"logps/rejected": -462.1837463378906,
|
354 |
+
"loss": 0.0534,
|
355 |
+
"rewards/accuracies": 0.75,
|
356 |
+
"rewards/chosen": -1.8188711404800415,
|
357 |
+
"rewards/margins": 1.0099431276321411,
|
358 |
+
"rewards/rejected": -2.8288140296936035,
|
359 |
+
"step": 240
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.28,
|
363 |
+
"learning_rate": 4.5096748387656326e-07,
|
364 |
+
"logits/chosen": -2.1846108436584473,
|
365 |
+
"logits/rejected": -2.120591402053833,
|
366 |
+
"logps/chosen": -542.7911376953125,
|
367 |
+
"logps/rejected": -492.59613037109375,
|
368 |
+
"loss": 0.0444,
|
369 |
+
"rewards/accuracies": 0.731249988079071,
|
370 |
+
"rewards/chosen": -2.2211267948150635,
|
371 |
+
"rewards/margins": 1.0178402662277222,
|
372 |
+
"rewards/rejected": -3.238966703414917,
|
373 |
+
"step": 250
|
374 |
},
|
375 |
{
|
376 |
"epoch": 0.29,
|
377 |
+
"learning_rate": 4.4492811740683877e-07,
|
378 |
+
"logits/chosen": -2.1908137798309326,
|
379 |
+
"logits/rejected": -2.134983777999878,
|
380 |
+
"logps/chosen": -579.2075805664062,
|
381 |
+
"logps/rejected": -490.6512756347656,
|
382 |
+
"loss": 0.0416,
|
383 |
+
"rewards/accuracies": 0.6875,
|
384 |
+
"rewards/chosen": -2.233696460723877,
|
385 |
+
"rewards/margins": 0.9735918045043945,
|
386 |
+
"rewards/rejected": -3.2072887420654297,
|
387 |
+
"step": 260
|
388 |
},
|
389 |
{
|
390 |
"epoch": 0.31,
|
391 |
+
"learning_rate": 4.3858362679584354e-07,
|
392 |
+
"logits/chosen": -2.219695568084717,
|
393 |
+
"logits/rejected": -2.162471294403076,
|
394 |
+
"logps/chosen": -540.0610961914062,
|
395 |
+
"logps/rejected": -505.3155822753906,
|
396 |
+
"loss": 0.0501,
|
397 |
+
"rewards/accuracies": 0.7124999761581421,
|
398 |
+
"rewards/chosen": -2.0654993057250977,
|
399 |
+
"rewards/margins": 1.0172322988510132,
|
400 |
+
"rewards/rejected": -3.082731246948242,
|
401 |
+
"step": 270
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.32,
|
405 |
+
"learning_rate": 4.3194394317755245e-07,
|
406 |
+
"logits/chosen": -2.1336846351623535,
|
407 |
+
"logits/rejected": -2.112194538116455,
|
408 |
+
"logps/chosen": -507.14862060546875,
|
409 |
+
"logps/rejected": -446.50244140625,
|
410 |
+
"loss": 0.0488,
|
411 |
+
"rewards/accuracies": 0.699999988079071,
|
412 |
+
"rewards/chosen": -1.9484211206436157,
|
413 |
+
"rewards/margins": 0.8502570986747742,
|
414 |
+
"rewards/rejected": -2.798678159713745,
|
415 |
+
"step": 280
|
416 |
},
|
417 |
{
|
418 |
"epoch": 0.33,
|
419 |
+
"learning_rate": 4.2501945975633914e-07,
|
420 |
+
"logits/chosen": -2.2120940685272217,
|
421 |
+
"logits/rejected": -2.1599128246307373,
|
422 |
+
"logps/chosen": -565.96923828125,
|
423 |
+
"logps/rejected": -511.15875244140625,
|
424 |
+
"loss": 0.0673,
|
425 |
+
"rewards/accuracies": 0.731249988079071,
|
426 |
+
"rewards/chosen": -1.7033636569976807,
|
427 |
+
"rewards/margins": 1.2502896785736084,
|
428 |
+
"rewards/rejected": -2.95365309715271,
|
429 |
+
"step": 290
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.34,
|
433 |
+
"learning_rate": 4.1782101553832405e-07,
|
434 |
+
"logits/chosen": -2.229743480682373,
|
435 |
+
"logits/rejected": -2.16943621635437,
|
436 |
+
"logps/chosen": -531.8292846679688,
|
437 |
+
"logps/rejected": -456.9198303222656,
|
438 |
+
"loss": 0.0744,
|
439 |
+
"rewards/accuracies": 0.768750011920929,
|
440 |
+
"rewards/chosen": -1.5255606174468994,
|
441 |
+
"rewards/margins": 1.3379647731781006,
|
442 |
+
"rewards/rejected": -2.863525867462158,
|
443 |
+
"step": 300
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.35,
|
447 |
+
"learning_rate": 4.103598783649029e-07,
|
448 |
+
"logits/chosen": -2.1273748874664307,
|
449 |
+
"logits/rejected": -2.0621378421783447,
|
450 |
+
"logps/chosen": -449.0135803222656,
|
451 |
+
"logps/rejected": -464.1368103027344,
|
452 |
+
"loss": 0.0535,
|
453 |
+
"rewards/accuracies": 0.7437499761581421,
|
454 |
+
"rewards/chosen": -1.700299859046936,
|
455 |
+
"rewards/margins": 1.344228982925415,
|
456 |
+
"rewards/rejected": -3.0445287227630615,
|
457 |
+
"step": 310
|
458 |
},
|
459 |
{
|
460 |
"epoch": 0.36,
|
461 |
+
"learning_rate": 4.026477272750119e-07,
|
462 |
+
"logits/chosen": -2.1758084297180176,
|
463 |
+
"logits/rejected": -2.1122355461120605,
|
464 |
+
"logps/chosen": -523.4859008789062,
|
465 |
+
"logps/rejected": -473.9483947753906,
|
466 |
+
"loss": 0.0521,
|
467 |
+
"rewards/accuracies": 0.7250000238418579,
|
468 |
+
"rewards/chosen": -1.8398901224136353,
|
469 |
+
"rewards/margins": 1.2361342906951904,
|
470 |
+
"rewards/rejected": -3.0760245323181152,
|
471 |
+
"step": 320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.37,
|
475 |
+
"learning_rate": 3.9469663422373864e-07,
|
476 |
+
"logits/chosen": -2.1758205890655518,
|
477 |
+
"logits/rejected": -2.1095774173736572,
|
478 |
+
"logps/chosen": -526.5242919921875,
|
479 |
+
"logps/rejected": -537.9935302734375,
|
480 |
+
"loss": 0.0567,
|
481 |
+
"rewards/accuracies": 0.706250011920929,
|
482 |
+
"rewards/chosen": -2.1948952674865723,
|
483 |
+
"rewards/margins": 1.110154390335083,
|
484 |
+
"rewards/rejected": -3.3050498962402344,
|
485 |
+
"step": 330
|
486 |
},
|
487 |
{
|
488 |
"epoch": 0.38,
|
489 |
+
"learning_rate": 3.865190451858954e-07,
|
490 |
+
"logits/chosen": -2.1651651859283447,
|
491 |
+
"logits/rejected": -2.1235530376434326,
|
492 |
+
"logps/chosen": -530.256103515625,
|
493 |
+
"logps/rejected": -508.19073486328125,
|
494 |
+
"loss": 0.0525,
|
495 |
+
"rewards/accuracies": 0.762499988079071,
|
496 |
+
"rewards/chosen": -2.0087122917175293,
|
497 |
+
"rewards/margins": 1.3509318828582764,
|
498 |
+
"rewards/rejected": -3.3596444129943848,
|
499 |
+
"step": 340
|
500 |
},
|
501 |
{
|
502 |
"epoch": 0.4,
|
503 |
+
"learning_rate": 3.781277606741327e-07,
|
504 |
+
"logits/chosen": -2.174168825149536,
|
505 |
+
"logits/rejected": -2.1008687019348145,
|
506 |
+
"logps/chosen": -523.4888916015625,
|
507 |
+
"logps/rejected": -506.63909912109375,
|
508 |
+
"loss": 0.0449,
|
509 |
+
"rewards/accuracies": 0.737500011920929,
|
510 |
+
"rewards/chosen": -2.164114475250244,
|
511 |
+
"rewards/margins": 1.164854884147644,
|
512 |
+
"rewards/rejected": -3.3289694786071777,
|
513 |
+
"step": 350
|
514 |
},
|
515 |
{
|
516 |
+
"epoch": 0.41,
|
517 |
+
"learning_rate": 3.6953591570208996e-07,
|
518 |
+
"logits/chosen": -2.13757586479187,
|
519 |
+
"logits/rejected": -2.0624773502349854,
|
520 |
+
"logps/chosen": -568.0411376953125,
|
521 |
+
"logps/rejected": -503.7386169433594,
|
522 |
+
"loss": 0.0426,
|
523 |
+
"rewards/accuracies": 0.65625,
|
524 |
+
"rewards/chosen": -2.1451027393341064,
|
525 |
+
"rewards/margins": 1.2416441440582275,
|
526 |
+
"rewards/rejected": -3.386746883392334,
|
527 |
+
"step": 360
|
528 |
},
|
529 |
{
|
530 |
"epoch": 0.42,
|
531 |
+
"learning_rate": 3.607569592239452e-07,
|
532 |
+
"logits/chosen": -2.1109542846679688,
|
533 |
+
"logits/rejected": -2.0401806831359863,
|
534 |
+
"logps/chosen": -550.1793212890625,
|
535 |
+
"logps/rejected": -503.6466369628906,
|
536 |
+
"loss": 0.0482,
|
537 |
+
"rewards/accuracies": 0.768750011920929,
|
538 |
+
"rewards/chosen": -1.9328603744506836,
|
539 |
+
"rewards/margins": 1.231170892715454,
|
540 |
+
"rewards/rejected": -3.1640312671661377,
|
541 |
+
"step": 370
|
|
|
|
|
542 |
},
|
543 |
{
|
544 |
+
"epoch": 0.43,
|
545 |
+
"learning_rate": 3.518046330825494e-07,
|
546 |
+
"logits/chosen": -2.1060791015625,
|
547 |
+
"logits/rejected": -2.041074514389038,
|
548 |
+
"logps/chosen": -535.5892944335938,
|
549 |
+
"logps/rejected": -487.30352783203125,
|
550 |
+
"loss": 0.0552,
|
551 |
"rewards/accuracies": 0.7250000238418579,
|
552 |
+
"rewards/chosen": -1.9271209239959717,
|
553 |
+
"rewards/margins": 1.0428855419158936,
|
554 |
+
"rewards/rejected": -2.9700064659118652,
|
555 |
+
"step": 380
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.44,
|
559 |
+
"learning_rate": 3.4269295049909713e-07,
|
560 |
+
"logits/chosen": -2.175748109817505,
|
561 |
+
"logits/rejected": -2.112736701965332,
|
562 |
+
"logps/chosen": -584.9471435546875,
|
563 |
+
"logps/rejected": -521.4114379882812,
|
564 |
+
"loss": 0.0535,
|
565 |
+
"rewards/accuracies": 0.6937500238418579,
|
566 |
+
"rewards/chosen": -1.8646738529205322,
|
567 |
+
"rewards/margins": 1.4181945323944092,
|
568 |
+
"rewards/rejected": -3.2828681468963623,
|
569 |
+
"step": 390
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.45,
|
573 |
+
"learning_rate": 3.3343617413800453e-07,
|
574 |
+
"logits/chosen": -2.0954391956329346,
|
575 |
+
"logits/rejected": -2.029520034790039,
|
576 |
+
"logps/chosen": -522.0698852539062,
|
577 |
+
"logps/rejected": -517.2570190429688,
|
578 |
+
"loss": 0.0433,
|
579 |
+
"rewards/accuracies": 0.8187500238418579,
|
580 |
+
"rewards/chosen": -2.0321173667907715,
|
581 |
+
"rewards/margins": 1.4304258823394775,
|
582 |
+
"rewards/rejected": -3.46254301071167,
|
583 |
+
"step": 400
|
584 |
},
|
585 |
{
|
586 |
"epoch": 0.46,
|
587 |
+
"learning_rate": 3.2404879378132893e-07,
|
588 |
+
"logits/chosen": -2.101567029953003,
|
589 |
+
"logits/rejected": -2.044337511062622,
|
590 |
+
"logps/chosen": -559.70458984375,
|
591 |
+
"logps/rejected": -565.7550048828125,
|
592 |
+
"loss": 0.0561,
|
593 |
+
"rewards/accuracies": 0.7562500238418579,
|
594 |
+
"rewards/chosen": -2.1665139198303223,
|
595 |
+
"rewards/margins": 1.347381591796875,
|
596 |
+
"rewards/rejected": -3.5138955116271973,
|
597 |
+
"step": 410
|
598 |
},
|
599 |
{
|
600 |
"epoch": 0.48,
|
601 |
+
"learning_rate": 3.1454550364767894e-07,
|
602 |
+
"logits/chosen": -2.1945436000823975,
|
603 |
+
"logits/rejected": -2.108241558074951,
|
604 |
+
"logps/chosen": -547.8588256835938,
|
605 |
+
"logps/rejected": -472.13055419921875,
|
606 |
+
"loss": 0.0682,
|
607 |
+
"rewards/accuracies": 0.8125,
|
608 |
+
"rewards/chosen": -1.5657107830047607,
|
609 |
+
"rewards/margins": 1.3424267768859863,
|
610 |
+
"rewards/rejected": -2.908137798309326,
|
611 |
+
"step": 420
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.49,
|
615 |
+
"learning_rate": 3.049411793911154e-07,
|
616 |
+
"logits/chosen": -2.200591564178467,
|
617 |
+
"logits/rejected": -2.147153615951538,
|
618 |
+
"logps/chosen": -558.2203369140625,
|
619 |
+
"logps/rejected": -518.0502319335938,
|
620 |
+
"loss": 0.0599,
|
621 |
+
"rewards/accuracies": 0.8125,
|
622 |
+
"rewards/chosen": -1.8033355474472046,
|
623 |
+
"rewards/margins": 1.3239552974700928,
|
624 |
+
"rewards/rejected": -3.127290725708008,
|
625 |
+
"step": 430
|
626 |
},
|
627 |
{
|
628 |
"epoch": 0.5,
|
629 |
+
"learning_rate": 2.9525085481604914e-07,
|
630 |
+
"logits/chosen": -2.055802345275879,
|
631 |
+
"logits/rejected": -2.034162998199463,
|
632 |
+
"logps/chosen": -532.451416015625,
|
633 |
+
"logps/rejected": -547.7064819335938,
|
634 |
+
"loss": 0.0414,
|
635 |
+
"rewards/accuracies": 0.71875,
|
636 |
+
"rewards/chosen": -2.4992823600769043,
|
637 |
+
"rewards/margins": 0.9650812149047852,
|
638 |
+
"rewards/rejected": -3.4643635749816895,
|
639 |
+
"step": 440
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.51,
|
643 |
+
"learning_rate": 2.854896983445833e-07,
|
644 |
+
"logits/chosen": -2.0957014560699463,
|
645 |
+
"logits/rejected": -2.0423591136932373,
|
646 |
+
"logps/chosen": -601.10302734375,
|
647 |
+
"logps/rejected": -567.8006591796875,
|
648 |
+
"loss": 0.0359,
|
649 |
+
"rewards/accuracies": 0.699999988079071,
|
650 |
+
"rewards/chosen": -2.637305736541748,
|
651 |
+
"rewards/margins": 1.1463762521743774,
|
652 |
+
"rewards/rejected": -3.783681869506836,
|
653 |
+
"step": 450
|
654 |
},
|
655 |
{
|
656 |
"epoch": 0.52,
|
657 |
+
"learning_rate": 2.7567298927313654e-07,
|
658 |
+
"logits/chosen": -2.131615400314331,
|
659 |
+
"logits/rejected": -2.082598924636841,
|
660 |
+
"logps/chosen": -597.11474609375,
|
661 |
+
"logps/rejected": -561.5462646484375,
|
662 |
+
"loss": 0.043,
|
663 |
+
"rewards/accuracies": 0.731249988079071,
|
664 |
+
"rewards/chosen": -2.3780384063720703,
|
665 |
+
"rewards/margins": 1.2381227016448975,
|
666 |
+
"rewards/rejected": -3.6161608695983887,
|
667 |
+
"step": 460
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.53,
|
671 |
+
"learning_rate": 2.658160938555123e-07,
|
672 |
+
"logits/chosen": -2.093458890914917,
|
673 |
+
"logits/rejected": -2.061420440673828,
|
674 |
+
"logps/chosen": -515.4798583984375,
|
675 |
+
"logps/rejected": -517.3043212890625,
|
676 |
+
"loss": 0.0434,
|
677 |
+
"rewards/accuracies": 0.762499988079071,
|
678 |
+
"rewards/chosen": -2.0862958431243896,
|
679 |
+
"rewards/margins": 1.3371632099151611,
|
680 |
+
"rewards/rejected": -3.42345929145813,
|
681 |
+
"step": 470
|
682 |
},
|
683 |
{
|
684 |
"epoch": 0.54,
|
685 |
+
"learning_rate": 2.559344412498532e-07,
|
686 |
+
"logits/chosen": -2.1327083110809326,
|
687 |
+
"logits/rejected": -2.0735764503479004,
|
688 |
+
"logps/chosen": -521.3518676757812,
|
689 |
+
"logps/rejected": -507.07940673828125,
|
690 |
+
"loss": 0.0493,
|
691 |
+
"rewards/accuracies": 0.706250011920929,
|
692 |
+
"rewards/chosen": -2.167259931564331,
|
693 |
+
"rewards/margins": 0.961189866065979,
|
694 |
+
"rewards/rejected": -3.1284494400024414,
|
695 |
+
"step": 480
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.55,
|
699 |
+
"learning_rate": 2.460434993671294e-07,
|
700 |
+
"logits/chosen": -2.1041388511657715,
|
701 |
+
"logits/rejected": -2.0494048595428467,
|
702 |
+
"logps/chosen": -468.25286865234375,
|
703 |
+
"logps/rejected": -456.40069580078125,
|
704 |
+
"loss": 0.0565,
|
705 |
+
"rewards/accuracies": 0.78125,
|
706 |
+
"rewards/chosen": -1.6431152820587158,
|
707 |
+
"rewards/margins": 1.1550475358963013,
|
708 |
+
"rewards/rejected": -2.7981629371643066,
|
709 |
+
"step": 490
|
710 |
},
|
711 |
{
|
712 |
"epoch": 0.57,
|
713 |
+
"learning_rate": 2.361587506589672e-07,
|
714 |
+
"logits/chosen": -2.136615514755249,
|
715 |
+
"logits/rejected": -2.0756921768188477,
|
716 |
+
"logps/chosen": -559.8421630859375,
|
717 |
+
"logps/rejected": -500.45416259765625,
|
718 |
+
"loss": 0.0555,
|
719 |
+
"rewards/accuracies": 0.731249988079071,
|
720 |
+
"rewards/chosen": -2.011848211288452,
|
721 |
+
"rewards/margins": 1.14077889919281,
|
722 |
+
"rewards/rejected": -3.1526272296905518,
|
723 |
+
"step": 500
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.58,
|
727 |
+
"learning_rate": 2.2629566788271613e-07,
|
728 |
+
"logits/chosen": -2.1114137172698975,
|
729 |
+
"logits/rejected": -2.0390002727508545,
|
730 |
+
"logps/chosen": -583.687255859375,
|
731 |
+
"logps/rejected": -564.6419067382812,
|
732 |
+
"loss": 0.0469,
|
733 |
+
"rewards/accuracies": 0.75,
|
734 |
+
"rewards/chosen": -2.1826224327087402,
|
735 |
+
"rewards/margins": 1.3830513954162598,
|
736 |
+
"rewards/rejected": -3.565673828125,
|
737 |
+
"step": 510
|
738 |
},
|
739 |
{
|
740 |
"epoch": 0.59,
|
741 |
+
"learning_rate": 2.1646968988169135e-07,
|
742 |
+
"logits/chosen": -2.100142240524292,
|
743 |
+
"logits/rejected": -2.0500102043151855,
|
744 |
+
"logps/chosen": -592.74755859375,
|
745 |
+
"logps/rejected": -565.3260498046875,
|
746 |
+
"loss": 0.0453,
|
747 |
+
"rewards/accuracies": 0.768750011920929,
|
748 |
+
"rewards/chosen": -2.248453378677368,
|
749 |
+
"rewards/margins": 1.5243793725967407,
|
750 |
+
"rewards/rejected": -3.7728323936462402,
|
751 |
+
"step": 520
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.6,
|
755 |
+
"learning_rate": 2.0669619741850232e-07,
|
756 |
+
"logits/chosen": -2.0300328731536865,
|
757 |
+
"logits/rejected": -1.9945085048675537,
|
758 |
+
"logps/chosen": -557.4923095703125,
|
759 |
+
"logps/rejected": -565.3587646484375,
|
760 |
+
"loss": 0.0414,
|
761 |
+
"rewards/accuracies": 0.75,
|
762 |
+
"rewards/chosen": -2.316817045211792,
|
763 |
+
"rewards/margins": 1.3874229192733765,
|
764 |
+
"rewards/rejected": -3.704240083694458,
|
765 |
+
"step": 530
|
766 |
},
|
767 |
{
|
768 |
"epoch": 0.61,
|
769 |
+
"learning_rate": 1.9699048909929518e-07,
|
770 |
+
"logits/chosen": -2.041743040084839,
|
771 |
+
"logits/rejected": -2.026899814605713,
|
772 |
+
"logps/chosen": -549.0650634765625,
|
773 |
+
"logps/rejected": -553.6836547851562,
|
774 |
+
"loss": 0.0385,
|
775 |
+
"rewards/accuracies": 0.78125,
|
776 |
+
"rewards/chosen": -2.206735134124756,
|
777 |
+
"rewards/margins": 1.487671136856079,
|
778 |
+
"rewards/rejected": -3.6944069862365723,
|
779 |
+
"step": 540
|
780 |
},
|
781 |
{
|
782 |
+
"epoch": 0.62,
|
783 |
+
"learning_rate": 1.8736775742659732e-07,
|
784 |
+
"logits/chosen": -2.042382001876831,
|
785 |
+
"logits/rejected": -1.9802138805389404,
|
786 |
+
"logps/chosen": -505.1175842285156,
|
787 |
+
"logps/rejected": -516.2354736328125,
|
788 |
+
"loss": 0.0492,
|
789 |
+
"rewards/accuracies": 0.731249988079071,
|
790 |
+
"rewards/chosen": -2.0931038856506348,
|
791 |
+
"rewards/margins": 1.3815913200378418,
|
792 |
+
"rewards/rejected": -3.4746952056884766,
|
793 |
+
"step": 550
|
794 |
},
|
795 |
{
|
796 |
"epoch": 0.63,
|
797 |
+
"learning_rate": 1.7784306501824616e-07,
|
798 |
+
"logits/chosen": -2.0194315910339355,
|
799 |
+
"logits/rejected": -1.9467071294784546,
|
800 |
+
"logps/chosen": -560.6709594726562,
|
801 |
+
"logps/rejected": -534.3895874023438,
|
802 |
+
"loss": 0.0542,
|
803 |
+
"rewards/accuracies": 0.768750011920929,
|
804 |
+
"rewards/chosen": -2.101309299468994,
|
805 |
+
"rewards/margins": 1.3114370107650757,
|
806 |
+
"rewards/rejected": -3.412745952606201,
|
807 |
+
"step": 560
|
|
|
|
|
808 |
},
|
809 |
{
|
810 |
"epoch": 0.65,
|
811 |
+
"learning_rate": 1.6843132102963025e-07,
|
812 |
+
"logits/chosen": -2.1281192302703857,
|
813 |
+
"logits/rejected": -2.0448033809661865,
|
814 |
+
"logps/chosen": -538.1578369140625,
|
815 |
+
"logps/rejected": -523.7766723632812,
|
816 |
+
"loss": 0.0553,
|
817 |
+
"rewards/accuracies": 0.824999988079071,
|
818 |
+
"rewards/chosen": -1.8923267126083374,
|
819 |
+
"rewards/margins": 1.5170024633407593,
|
820 |
+
"rewards/rejected": -3.4093291759490967,
|
821 |
+
"step": 570
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.66,
|
825 |
+
"learning_rate": 1.591472578161458e-07,
|
826 |
+
"logits/chosen": -2.052722454071045,
|
827 |
+
"logits/rejected": -2.037425994873047,
|
828 |
+
"logps/chosen": -544.02197265625,
|
829 |
+
"logps/rejected": -537.7569580078125,
|
830 |
+
"loss": 0.0538,
|
831 |
+
"rewards/accuracies": 0.7749999761581421,
|
832 |
+
"rewards/chosen": -2.122720241546631,
|
833 |
+
"rewards/margins": 1.2477385997772217,
|
834 |
+
"rewards/rejected": -3.3704590797424316,
|
835 |
+
"step": 580
|
836 |
},
|
837 |
{
|
838 |
"epoch": 0.67,
|
839 |
+
"learning_rate": 1.5000540787240274e-07,
|
840 |
+
"logits/chosen": -2.1312813758850098,
|
841 |
+
"logits/rejected": -2.0585029125213623,
|
842 |
+
"logps/chosen": -578.3094482421875,
|
843 |
+
"logps/rejected": -522.5347900390625,
|
844 |
+
"loss": 0.0505,
|
845 |
+
"rewards/accuracies": 0.699999988079071,
|
846 |
+
"rewards/chosen": -2.313297986984253,
|
847 |
+
"rewards/margins": 1.069830298423767,
|
848 |
+
"rewards/rejected": -3.3831279277801514,
|
849 |
+
"step": 590
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.68,
|
853 |
+
"learning_rate": 1.410200810842749e-07,
|
854 |
+
"logits/chosen": -2.0706946849823,
|
855 |
+
"logits/rejected": -2.0253984928131104,
|
856 |
+
"logps/chosen": -567.4093627929688,
|
857 |
+
"logps/rejected": -551.6956787109375,
|
858 |
+
"loss": 0.0423,
|
859 |
+
"rewards/accuracies": 0.793749988079071,
|
860 |
+
"rewards/chosen": -2.204864025115967,
|
861 |
+
"rewards/margins": 1.2818561792373657,
|
862 |
+
"rewards/rejected": -3.486720561981201,
|
863 |
+
"step": 600
|
864 |
},
|
865 |
{
|
866 |
"epoch": 0.69,
|
867 |
+
"learning_rate": 1.322053423294041e-07,
|
868 |
+
"logits/chosen": -2.1002461910247803,
|
869 |
+
"logits/rejected": -2.0568830966949463,
|
870 |
+
"logps/chosen": -551.1517333984375,
|
871 |
+
"logps/rejected": -533.7266235351562,
|
872 |
+
"loss": 0.049,
|
873 |
+
"rewards/accuracies": 0.6937500238418579,
|
874 |
+
"rewards/chosen": -2.393352746963501,
|
875 |
+
"rewards/margins": 1.0419074296951294,
|
876 |
+
"rewards/rejected": -3.4352595806121826,
|
877 |
+
"step": 610
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.7,
|
881 |
+
"learning_rate": 1.2357498946121905e-07,
|
882 |
+
"logits/chosen": -2.088925838470459,
|
883 |
+
"logits/rejected": -2.03609037399292,
|
884 |
+
"logps/chosen": -612.4100952148438,
|
885 |
+
"logps/rejected": -554.9931640625,
|
886 |
+
"loss": 0.047,
|
887 |
+
"rewards/accuracies": 0.768750011920929,
|
888 |
+
"rewards/chosen": -2.3001351356506348,
|
889 |
+
"rewards/margins": 1.3683874607086182,
|
890 |
+
"rewards/rejected": -3.668523073196411,
|
891 |
+
"step": 620
|
892 |
},
|
893 |
{
|
894 |
"epoch": 0.71,
|
895 |
+
"learning_rate": 1.1514253171093161e-07,
|
896 |
+
"logits/chosen": -2.1326541900634766,
|
897 |
+
"logits/rejected": -2.0758585929870605,
|
898 |
+
"logps/chosen": -570.8392333984375,
|
899 |
+
"logps/rejected": -574.4908447265625,
|
900 |
+
"loss": 0.0533,
|
901 |
+
"rewards/accuracies": 0.768750011920929,
|
902 |
+
"rewards/chosen": -2.2075510025024414,
|
903 |
+
"rewards/margins": 1.380297064781189,
|
904 |
+
"rewards/rejected": -3.587847948074341,
|
905 |
+
"step": 630
|
906 |
},
|
907 |
{
|
908 |
+
"epoch": 0.72,
|
909 |
+
"learning_rate": 1.0692116854131883e-07,
|
910 |
+
"logits/chosen": -2.0427284240722656,
|
911 |
+
"logits/rejected": -1.9922561645507812,
|
912 |
+
"logps/chosen": -528.8707275390625,
|
913 |
+
"logps/rejected": -516.8524169921875,
|
914 |
+
"loss": 0.0486,
|
915 |
+
"rewards/accuracies": 0.768750011920929,
|
916 |
+
"rewards/chosen": -2.0978333950042725,
|
917 |
+
"rewards/margins": 1.2833999395370483,
|
918 |
+
"rewards/rejected": -3.3812332153320312,
|
919 |
+
"step": 640
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.74,
|
923 |
+
"learning_rate": 9.89237689853889e-08,
|
924 |
+
"logits/chosen": -2.1081204414367676,
|
925 |
+
"logits/rejected": -2.0486502647399902,
|
926 |
+
"logps/chosen": -574.6364135742188,
|
927 |
+
"logps/rejected": -567.418212890625,
|
928 |
+
"loss": 0.0473,
|
929 |
+
"rewards/accuracies": 0.800000011920929,
|
930 |
+
"rewards/chosen": -2.1617255210876465,
|
931 |
+
"rewards/margins": 1.530967354774475,
|
932 |
+
"rewards/rejected": -3.692692995071411,
|
933 |
+
"step": 650
|
934 |
},
|
935 |
{
|
936 |
"epoch": 0.75,
|
937 |
+
"learning_rate": 9.11628515022765e-08,
|
938 |
+
"logits/chosen": -2.0846991539001465,
|
939 |
+
"logits/rejected": -2.0398693084716797,
|
940 |
+
"logps/chosen": -597.761962890625,
|
941 |
+
"logps/rejected": -579.8795166015625,
|
942 |
+
"loss": 0.0522,
|
943 |
+
"rewards/accuracies": 0.78125,
|
944 |
+
"rewards/chosen": -2.5013487339019775,
|
945 |
+
"rewards/margins": 1.258310079574585,
|
946 |
+
"rewards/rejected": -3.7596592903137207,
|
947 |
+
"step": 660
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.76,
|
951 |
+
"learning_rate": 8.365056438189486e-08,
|
952 |
+
"logits/chosen": -2.1001641750335693,
|
953 |
+
"logits/rejected": -2.0509486198425293,
|
954 |
+
"logps/chosen": -590.825439453125,
|
955 |
+
"logps/rejected": -565.3231201171875,
|
956 |
+
"loss": 0.0481,
|
957 |
+
"rewards/accuracies": 0.7124999761581421,
|
958 |
+
"rewards/chosen": -2.456451654434204,
|
959 |
+
"rewards/margins": 1.0512244701385498,
|
960 |
+
"rewards/rejected": -3.507675886154175,
|
961 |
+
"step": 670
|
962 |
},
|
963 |
{
|
964 |
"epoch": 0.77,
|
965 |
+
"learning_rate": 7.639866672902101e-08,
|
966 |
+
"logits/chosen": -2.059082269668579,
|
967 |
+
"logits/rejected": -2.0069167613983154,
|
968 |
+
"logps/chosen": -529.4530029296875,
|
969 |
+
"logps/rejected": -553.0791015625,
|
970 |
+
"loss": 0.0537,
|
971 |
+
"rewards/accuracies": 0.8125,
|
972 |
+
"rewards/chosen": -2.3729891777038574,
|
973 |
+
"rewards/margins": 1.3166040182113647,
|
974 |
+
"rewards/rejected": -3.6895930767059326,
|
975 |
+
"step": 680
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.78,
|
979 |
+
"learning_rate": 6.941851005657851e-08,
|
980 |
+
"logits/chosen": -2.059549570083618,
|
981 |
+
"logits/rejected": -1.993088722229004,
|
982 |
+
"logps/chosen": -531.9309692382812,
|
983 |
+
"logps/rejected": -547.8716430664062,
|
984 |
+
"loss": 0.0507,
|
985 |
+
"rewards/accuracies": 0.78125,
|
986 |
+
"rewards/chosen": -2.190737247467041,
|
987 |
+
"rewards/margins": 1.2514276504516602,
|
988 |
+
"rewards/rejected": -3.442164897918701,
|
989 |
+
"step": 690
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.79,
|
993 |
+
"learning_rate": 6.272102051693051e-08,
|
994 |
+
"logits/chosen": -2.078123092651367,
|
995 |
+
"logits/rejected": -2.0465798377990723,
|
996 |
+
"logps/chosen": -528.0089721679688,
|
997 |
+
"logps/rejected": -525.1822509765625,
|
998 |
+
"loss": 0.0489,
|
999 |
+
"rewards/accuracies": 0.7437499761581421,
|
1000 |
+
"rewards/chosen": -2.0736889839172363,
|
1001 |
+
"rewards/margins": 1.2697416543960571,
|
1002 |
+
"rewards/rejected": -3.343430995941162,
|
1003 |
+
"step": 700
|
1004 |
},
|
1005 |
{
|
1006 |
"epoch": 0.8,
|
1007 |
+
"learning_rate": 5.6316681798995844e-08,
|
1008 |
+
"logits/chosen": -2.1082401275634766,
|
1009 |
+
"logits/rejected": -2.036336898803711,
|
1010 |
+
"logps/chosen": -535.8514404296875,
|
1011 |
+
"logps/rejected": -538.2098388671875,
|
1012 |
+
"loss": 0.0525,
|
1013 |
+
"rewards/accuracies": 0.800000011920929,
|
1014 |
+
"rewards/chosen": -2.207425594329834,
|
1015 |
+
"rewards/margins": 1.2546026706695557,
|
1016 |
+
"rewards/rejected": -3.4620280265808105,
|
1017 |
+
"step": 710
|
1018 |
},
|
1019 |
{
|
1020 |
+
"epoch": 0.81,
|
1021 |
+
"learning_rate": 5.0215518717961256e-08,
|
1022 |
+
"logits/chosen": -2.0293445587158203,
|
1023 |
+
"logits/rejected": -2.0118401050567627,
|
1024 |
+
"logps/chosen": -534.4603271484375,
|
1025 |
+
"logps/rejected": -497.52862548828125,
|
1026 |
+
"loss": 0.0513,
|
1027 |
+
"rewards/accuracies": 0.831250011920929,
|
1028 |
+
"rewards/chosen": -1.9929277896881104,
|
1029 |
+
"rewards/margins": 1.2197530269622803,
|
1030 |
+
"rewards/rejected": -3.2126808166503906,
|
1031 |
+
"step": 720
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.83,
|
1035 |
+
"learning_rate": 4.4427081523275925e-08,
|
1036 |
+
"logits/chosen": -2.111539363861084,
|
1037 |
+
"logits/rejected": -2.0251288414001465,
|
1038 |
+
"logps/chosen": -571.8197021484375,
|
1039 |
+
"logps/rejected": -563.7077026367188,
|
1040 |
+
"loss": 0.0537,
|
1041 |
"rewards/accuracies": 0.7437499761581421,
|
1042 |
+
"rewards/chosen": -2.099212646484375,
|
1043 |
+
"rewards/margins": 1.648705244064331,
|
1044 |
+
"rewards/rejected": -3.747917890548706,
|
1045 |
+
"step": 730
|
1046 |
},
|
1047 |
{
|
1048 |
"epoch": 0.84,
|
1049 |
+
"learning_rate": 3.896043094949061e-08,
|
1050 |
+
"logits/chosen": -2.112701654434204,
|
1051 |
+
"logits/rejected": -2.0454134941101074,
|
1052 |
+
"logps/chosen": -555.4544067382812,
|
1053 |
+
"logps/rejected": -528.0631713867188,
|
1054 |
+
"loss": 0.0544,
|
1055 |
+
"rewards/accuracies": 0.75,
|
1056 |
+
"rewards/chosen": -2.158057451248169,
|
1057 |
+
"rewards/margins": 1.1910467147827148,
|
1058 |
+
"rewards/rejected": -3.3491039276123047,
|
1059 |
+
"step": 740
|
1060 |
},
|
1061 |
{
|
1062 |
+
"epoch": 0.85,
|
1063 |
+
"learning_rate": 3.3824124033343557e-08,
|
1064 |
+
"logits/chosen": -2.101064682006836,
|
1065 |
+
"logits/rejected": -2.035494089126587,
|
1066 |
+
"logps/chosen": -523.05517578125,
|
1067 |
+
"logps/rejected": -508.50653076171875,
|
1068 |
+
"loss": 0.0473,
|
1069 |
+
"rewards/accuracies": 0.7562500238418579,
|
1070 |
+
"rewards/chosen": -2.1078267097473145,
|
1071 |
+
"rewards/margins": 1.258143424987793,
|
1072 |
+
"rewards/rejected": -3.3659701347351074,
|
1073 |
+
"step": 750
|
|
|
|
|
1074 |
},
|
1075 |
{
|
1076 |
"epoch": 0.86,
|
1077 |
+
"learning_rate": 2.9026200719291904e-08,
|
1078 |
+
"logits/chosen": -2.0927655696868896,
|
1079 |
+
"logits/rejected": -2.014799118041992,
|
1080 |
+
"logps/chosen": -526.6090087890625,
|
1081 |
+
"logps/rejected": -510.7976989746094,
|
1082 |
+
"loss": 0.0476,
|
1083 |
+
"rewards/accuracies": 0.8187500238418579,
|
1084 |
+
"rewards/chosen": -2.0697100162506104,
|
1085 |
+
"rewards/margins": 1.2819905281066895,
|
1086 |
+
"rewards/rejected": -3.3517003059387207,
|
1087 |
+
"step": 760
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.87,
|
1091 |
+
"learning_rate": 2.4574171274456433e-08,
|
1092 |
+
"logits/chosen": -2.127093553543091,
|
1093 |
+
"logits/rejected": -2.072615146636963,
|
1094 |
+
"logps/chosen": -579.9869995117188,
|
1095 |
+
"logps/rejected": -531.943359375,
|
1096 |
+
"loss": 0.0517,
|
1097 |
+
"rewards/accuracies": 0.7562500238418579,
|
1098 |
+
"rewards/chosen": -2.103449583053589,
|
1099 |
+
"rewards/margins": 1.3205053806304932,
|
1100 |
+
"rewards/rejected": -3.423954725265503,
|
1101 |
+
"step": 770
|
1102 |
},
|
1103 |
{
|
1104 |
"epoch": 0.88,
|
1105 |
+
"learning_rate": 2.047500453267881e-08,
|
1106 |
+
"logits/chosen": -2.0992608070373535,
|
1107 |
+
"logits/rejected": -2.035027265548706,
|
1108 |
+
"logps/chosen": -576.8822021484375,
|
1109 |
+
"logps/rejected": -549.5172119140625,
|
1110 |
+
"loss": 0.0442,
|
1111 |
+
"rewards/accuracies": 0.7437499761581421,
|
1112 |
+
"rewards/chosen": -2.2390971183776855,
|
1113 |
+
"rewards/margins": 1.385114073753357,
|
1114 |
+
"rewards/rejected": -3.624211072921753,
|
1115 |
+
"step": 780
|
1116 |
},
|
1117 |
{
|
1118 |
+
"epoch": 0.89,
|
1119 |
+
"learning_rate": 1.673511698609292e-08,
|
1120 |
+
"logits/chosen": -2.1341183185577393,
|
1121 |
+
"logits/rejected": -2.060023784637451,
|
1122 |
+
"logps/chosen": -565.7227172851562,
|
1123 |
+
"logps/rejected": -535.3021850585938,
|
1124 |
+
"loss": 0.0475,
|
1125 |
+
"rewards/accuracies": 0.75,
|
1126 |
+
"rewards/chosen": -2.2470290660858154,
|
1127 |
+
"rewards/margins": 1.2771549224853516,
|
1128 |
+
"rewards/rejected": -3.524184465408325,
|
1129 |
+
"step": 790
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.91,
|
1133 |
+
"learning_rate": 1.3360362741285769e-08,
|
1134 |
+
"logits/chosen": -2.0838260650634766,
|
1135 |
+
"logits/rejected": -2.0251381397247314,
|
1136 |
+
"logps/chosen": -578.9539794921875,
|
1137 |
+
"logps/rejected": -542.1248779296875,
|
1138 |
+
"loss": 0.0468,
|
1139 |
+
"rewards/accuracies": 0.6875,
|
1140 |
+
"rewards/chosen": -2.277639865875244,
|
1141 |
+
"rewards/margins": 1.2334930896759033,
|
1142 |
+
"rewards/rejected": -3.5111324787139893,
|
1143 |
+
"step": 800
|
1144 |
},
|
1145 |
{
|
1146 |
"epoch": 0.92,
|
1147 |
+
"learning_rate": 1.0356024355769433e-08,
|
1148 |
+
"logits/chosen": -2.093954086303711,
|
1149 |
+
"logits/rejected": -2.043708324432373,
|
1150 |
+
"logps/chosen": -584.259521484375,
|
1151 |
+
"logps/rejected": -580.5767211914062,
|
1152 |
+
"loss": 0.0458,
|
1153 |
+
"rewards/accuracies": 0.768750011920929,
|
1154 |
+
"rewards/chosen": -2.1630260944366455,
|
1155 |
+
"rewards/margins": 1.6276559829711914,
|
1156 |
+
"rewards/rejected": -3.790682315826416,
|
1157 |
+
"step": 810
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.93,
|
1161 |
+
"learning_rate": 7.726804569108597e-09,
|
1162 |
+
"logits/chosen": -2.112128973007202,
|
1163 |
+
"logits/rejected": -2.0508077144622803,
|
1164 |
+
"logps/chosen": -558.3360595703125,
|
1165 |
+
"logps/rejected": -544.3916015625,
|
1166 |
+
"loss": 0.0469,
|
1167 |
+
"rewards/accuracies": 0.793749988079071,
|
1168 |
+
"rewards/chosen": -2.1536641120910645,
|
1169 |
+
"rewards/margins": 1.3970838785171509,
|
1170 |
+
"rewards/rejected": -3.5507476329803467,
|
1171 |
+
"step": 820
|
1172 |
},
|
1173 |
{
|
1174 |
"epoch": 0.94,
|
1175 |
+
"learning_rate": 5.476818941645561e-09,
|
1176 |
+
"logits/chosen": -2.100653648376465,
|
1177 |
+
"logits/rejected": -2.021291732788086,
|
1178 |
+
"logps/chosen": -588.8988037109375,
|
1179 |
+
"logps/rejected": -540.7061767578125,
|
1180 |
+
"loss": 0.0429,
|
1181 |
+
"rewards/accuracies": 0.7437499761581421,
|
1182 |
+
"rewards/chosen": -2.19673490524292,
|
1183 |
+
"rewards/margins": 1.4355782270431519,
|
1184 |
+
"rewards/rejected": -3.632312774658203,
|
1185 |
+
"step": 830
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.95,
|
1189 |
+
"learning_rate": 3.609589412347347e-09,
|
1190 |
+
"logits/chosen": -2.109170913696289,
|
1191 |
+
"logits/rejected": -2.0334959030151367,
|
1192 |
+
"logps/chosen": -578.6869506835938,
|
1193 |
+
"logps/rejected": -536.8270263671875,
|
1194 |
+
"loss": 0.0477,
|
1195 |
+
"rewards/accuracies": 0.737500011920929,
|
1196 |
+
"rewards/chosen": -2.1644272804260254,
|
1197 |
+
"rewards/margins": 1.3395423889160156,
|
1198 |
+
"rewards/rejected": -3.50396990776062,
|
1199 |
+
"step": 840
|
1200 |
},
|
1201 |
{
|
1202 |
"epoch": 0.96,
|
1203 |
+
"learning_rate": 2.1280387858572667e-09,
|
1204 |
+
"logits/chosen": -2.0832810401916504,
|
1205 |
+
"logits/rejected": -2.0087838172912598,
|
1206 |
+
"logps/chosen": -581.9695434570312,
|
1207 |
+
"logps/rejected": -542.6390380859375,
|
1208 |
+
"loss": 0.0409,
|
1209 |
+
"rewards/accuracies": 0.75,
|
1210 |
+
"rewards/chosen": -2.3538167476654053,
|
1211 |
+
"rewards/margins": 1.3839699029922485,
|
1212 |
+
"rewards/rejected": -3.737786054611206,
|
1213 |
+
"step": 850
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.97,
|
1217 |
+
"learning_rate": 1.03448615738172e-09,
|
1218 |
+
"logits/chosen": -2.070016384124756,
|
1219 |
+
"logits/rejected": -1.9977195262908936,
|
1220 |
+
"logps/chosen": -577.4140625,
|
1221 |
+
"logps/rejected": -548.4049682617188,
|
1222 |
+
"loss": 0.0434,
|
1223 |
+
"rewards/accuracies": 0.7437499761581421,
|
1224 |
+
"rewards/chosen": -2.305614709854126,
|
1225 |
+
"rewards/margins": 1.2134736776351929,
|
1226 |
+
"rewards/rejected": -3.51908802986145,
|
1227 |
+
"step": 860
|
1228 |
},
|
1229 |
{
|
1230 |
"epoch": 0.98,
|
1231 |
+
"learning_rate": 3.3064328257259575e-10,
|
1232 |
+
"logits/chosen": -2.05591082572937,
|
1233 |
+
"logits/rejected": -2.0076966285705566,
|
1234 |
+
"logps/chosen": -535.1695556640625,
|
1235 |
+
"logps/rejected": -527.5564575195312,
|
1236 |
+
"loss": 0.0505,
|
1237 |
+
"rewards/accuracies": 0.706250011920929,
|
1238 |
+
"rewards/chosen": -2.3522868156433105,
|
1239 |
+
"rewards/margins": 1.0536117553710938,
|
1240 |
+
"rewards/rejected": -3.4058985710144043,
|
1241 |
+
"step": 870
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 1.0,
|
1245 |
+
"learning_rate": 1.7611898088715216e-11,
|
1246 |
+
"logits/chosen": -2.0798163414001465,
|
1247 |
+
"logits/rejected": -2.035545825958252,
|
1248 |
+
"logps/chosen": -553.0671997070312,
|
1249 |
+
"logps/rejected": -526.8216552734375,
|
1250 |
+
"loss": 0.0432,
|
1251 |
+
"rewards/accuracies": 0.737500011920929,
|
1252 |
+
"rewards/chosen": -2.1250925064086914,
|
1253 |
+
"rewards/margins": 1.3694770336151123,
|
1254 |
+
"rewards/rejected": -3.4945693016052246,
|
1255 |
+
"step": 880
|
1256 |
},
|
1257 |
{
|
1258 |
"epoch": 1.0,
|
1259 |
+
"step": 883,
|
1260 |
"total_flos": 0.0,
|
1261 |
+
"train_loss": 0.08422429972704783,
|
1262 |
+
"train_runtime": 6988.5729,
|
1263 |
+
"train_samples_per_second": 16.173,
|
1264 |
+
"train_steps_per_second": 0.126
|
1265 |
}
|
1266 |
],
|
1267 |
"logging_steps": 10,
|
1268 |
+
"max_steps": 883,
|
1269 |
"num_train_epochs": 1,
|
1270 |
"save_steps": 1000,
|
1271 |
"total_flos": 0.0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5944
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d532f4704c9f808c3ea9e327a50c66a63a95927fe15fa88c50065901d0980f26
|
3 |
size 5944
|