tcm03 commited on
Commit
f3d3de0
·
1 Parent(s): caa0952

cambrian_llama3_2 checkpoint after 1 epoch on EnTube_50m

Browse files
README.md ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ # LongVU Fine-tuned Checkpoint
2
+ This is a fine-tuned checkpoint of LongVU on Vast.ai after 1 epoch with 540 steps
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoints/longvu_llama3_2",
3
+ "architectures": [
4
+ "CambrianLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "connect_layer": 2,
10
+ "connector_depth": 3,
11
+ "connector_only": true,
12
+ "dino_threshold": 0.83,
13
+ "drop_threshold": 0.75,
14
+ "eos_token_id": [
15
+ 128001,
16
+ 128008,
17
+ 128009
18
+ ],
19
+ "frame_pos": false,
20
+ "freeze_mm_mlp_adapter": false,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 3072,
23
+ "highres": true,
24
+ "highres_connect": false,
25
+ "image_aspect_ratio": "pad",
26
+ "image_position": 91,
27
+ "image_token_len": 144,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 8192,
30
+ "is_image_newline": true,
31
+ "is_st_sampler": false,
32
+ "lowres_token": 8,
33
+ "max_position_embeddings": 131072,
34
+ "mlp_bias": false,
35
+ "mm_patch_merge_type": "flat",
36
+ "mm_projector_lr": null,
37
+ "mm_projector_type": "sva",
38
+ "mm_use_im_patch_token": false,
39
+ "mm_use_im_start_end": false,
40
+ "mm_vision_sampler_lr": null,
41
+ "mm_vision_select_feature": "patch",
42
+ "mm_vision_select_layer": -2,
43
+ "mm_vision_tower_aux_list": [
44
+ "siglip/CLIP-ViT-SO400M-14-384",
45
+ "facebook/dinov2-giant-res378"
46
+ ],
47
+ "mm_vision_tower_aux_token_len_list": [
48
+ 576,
49
+ 576
50
+ ],
51
+ "mm_vision_tower_lr": null,
52
+ "model_type": "cambrian_llama",
53
+ "num_attention_heads": 24,
54
+ "num_hidden_layers": 28,
55
+ "num_key_value_heads": 8,
56
+ "num_of_vision_sampler_layers": 10,
57
+ "num_query_group": 1,
58
+ "pretraining_tp": 1,
59
+ "query_num_list": [
60
+ 144
61
+ ],
62
+ "rms_norm_eps": 1e-05,
63
+ "rope_scaling": {
64
+ "factor": 32.0,
65
+ "high_freq_factor": 4.0,
66
+ "low_freq_factor": 1.0,
67
+ "original_max_position_embeddings": 8192,
68
+ "rope_type": "llama3"
69
+ },
70
+ "rope_theta": 500000.0,
71
+ "spmd_debug": null,
72
+ "spmd_fsdp_sharding": null,
73
+ "spmd_mesh": null,
74
+ "start_of_vision_sampler_layers": 0,
75
+ "stride_of_vision_sampler_layers": 3,
76
+ "tie_word_embeddings": false,
77
+ "tokenizer_model_max_length": 8192,
78
+ "tokenizer_padding_side": "right",
79
+ "torch_dtype": "bfloat16",
80
+ "transformers_version": "4.43.1",
81
+ "tune_mm_mlp_adapter": false,
82
+ "unfreeze_mm_vision_tower": false,
83
+ "use_cache": false,
84
+ "use_mm_proj": true,
85
+ "vision_hidden_size": 1024,
86
+ "vision_tower_aux_token_len_list": [
87
+ 576,
88
+ 576
89
+ ],
90
+ "vocab_size": 128256
91
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.43.1"
12
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1976f85aa2c26a35260ccc0aa399138cc7cb2a4d56d87234dca4571ad15343dc
3
+ size 4965807472
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21ee7e4b083a54c17a802f664a8afa3f5793a82df526e681e15ea219f3fc894
3
+ size 2351968856
model.safetensors.index.json ADDED
@@ -0,0 +1,352 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7317735424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.image_newline": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
262
+ "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
263
+ "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
264
+ "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
265
+ "model.mm_projector_aux_0.0.bias": "model-00002-of-00002.safetensors",
266
+ "model.mm_projector_aux_0.0.weight": "model-00002-of-00002.safetensors",
267
+ "model.mm_projector_aux_0.2.bias": "model-00002-of-00002.safetensors",
268
+ "model.mm_projector_aux_0.2.weight": "model-00002-of-00002.safetensors",
269
+ "model.mm_projector_aux_0.3.bias": "model-00002-of-00002.safetensors",
270
+ "model.mm_projector_aux_0.3.weight": "model-00002-of-00002.safetensors",
271
+ "model.mm_projector_aux_1.0.bias": "model-00002-of-00002.safetensors",
272
+ "model.mm_projector_aux_1.0.weight": "model-00002-of-00002.safetensors",
273
+ "model.mm_projector_aux_1.2.bias": "model-00002-of-00002.safetensors",
274
+ "model.mm_projector_aux_1.2.weight": "model-00002-of-00002.safetensors",
275
+ "model.mm_projector_aux_1.3.bias": "model-00002-of-00002.safetensors",
276
+ "model.mm_projector_aux_1.3.weight": "model-00002-of-00002.safetensors",
277
+ "model.norm.weight": "model-00002-of-00002.safetensors",
278
+ "model.vision_query": "model-00001-of-00002.safetensors",
279
+ "model.vision_sampler_0.layers.0.cross_attn.k_proj_0.0.bias": "model-00002-of-00002.safetensors",
280
+ "model.vision_sampler_0.layers.0.cross_attn.k_proj_0.0.weight": "model-00002-of-00002.safetensors",
281
+ "model.vision_sampler_0.layers.0.cross_attn.k_proj_0.1.weight": "model-00002-of-00002.safetensors",
282
+ "model.vision_sampler_0.layers.0.cross_attn.k_proj_1.0.bias": "model-00002-of-00002.safetensors",
283
+ "model.vision_sampler_0.layers.0.cross_attn.k_proj_1.0.weight": "model-00002-of-00002.safetensors",
284
+ "model.vision_sampler_0.layers.0.cross_attn.k_proj_1.1.weight": "model-00002-of-00002.safetensors",
285
+ "model.vision_sampler_0.layers.0.cross_attn.o_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.vision_sampler_0.layers.0.cross_attn.q_proj.0.bias": "model-00002-of-00002.safetensors",
287
+ "model.vision_sampler_0.layers.0.cross_attn.q_proj.0.weight": "model-00002-of-00002.safetensors",
288
+ "model.vision_sampler_0.layers.0.cross_attn.q_proj.1.weight": "model-00002-of-00002.safetensors",
289
+ "model.vision_sampler_0.layers.0.cross_attn.v_proj_0.0.bias": "model-00002-of-00002.safetensors",
290
+ "model.vision_sampler_0.layers.0.cross_attn.v_proj_0.0.weight": "model-00002-of-00002.safetensors",
291
+ "model.vision_sampler_0.layers.0.cross_attn.v_proj_0.1.weight": "model-00002-of-00002.safetensors",
292
+ "model.vision_sampler_0.layers.0.cross_attn.v_proj_1.0.bias": "model-00002-of-00002.safetensors",
293
+ "model.vision_sampler_0.layers.0.cross_attn.v_proj_1.0.weight": "model-00002-of-00002.safetensors",
294
+ "model.vision_sampler_0.layers.0.cross_attn.v_proj_1.1.weight": "model-00002-of-00002.safetensors",
295
+ "model.vision_sampler_0.layers.0.norm.bias": "model-00002-of-00002.safetensors",
296
+ "model.vision_sampler_0.layers.0.norm.weight": "model-00002-of-00002.safetensors",
297
+ "model.vision_sampler_0.layers.0.pos_embed_0": "model-00002-of-00002.safetensors",
298
+ "model.vision_sampler_0.layers.0.pos_embed_1": "model-00002-of-00002.safetensors",
299
+ "model.vision_sampler_0.layers.0.proj_context.weight": "model-00002-of-00002.safetensors",
300
+ "model.vision_sampler_0.layers.0.proj_in.weight": "model-00002-of-00002.safetensors",
301
+ "model.vision_sampler_0.layers.0.proj_out.linear_1.weight": "model-00002-of-00002.safetensors",
302
+ "model.vision_sampler_0.layers.0.proj_out.linear_2.weight": "model-00002-of-00002.safetensors",
303
+ "model.vision_sampler_0.layers.1.cross_attn.k_proj_0.0.bias": "model-00002-of-00002.safetensors",
304
+ "model.vision_sampler_0.layers.1.cross_attn.k_proj_0.0.weight": "model-00002-of-00002.safetensors",
305
+ "model.vision_sampler_0.layers.1.cross_attn.k_proj_0.1.weight": "model-00002-of-00002.safetensors",
306
+ "model.vision_sampler_0.layers.1.cross_attn.k_proj_1.0.bias": "model-00002-of-00002.safetensors",
307
+ "model.vision_sampler_0.layers.1.cross_attn.k_proj_1.0.weight": "model-00002-of-00002.safetensors",
308
+ "model.vision_sampler_0.layers.1.cross_attn.k_proj_1.1.weight": "model-00002-of-00002.safetensors",
309
+ "model.vision_sampler_0.layers.1.cross_attn.o_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.vision_sampler_0.layers.1.cross_attn.q_proj.0.bias": "model-00002-of-00002.safetensors",
311
+ "model.vision_sampler_0.layers.1.cross_attn.q_proj.0.weight": "model-00002-of-00002.safetensors",
312
+ "model.vision_sampler_0.layers.1.cross_attn.q_proj.1.weight": "model-00002-of-00002.safetensors",
313
+ "model.vision_sampler_0.layers.1.cross_attn.v_proj_0.0.bias": "model-00002-of-00002.safetensors",
314
+ "model.vision_sampler_0.layers.1.cross_attn.v_proj_0.0.weight": "model-00002-of-00002.safetensors",
315
+ "model.vision_sampler_0.layers.1.cross_attn.v_proj_0.1.weight": "model-00002-of-00002.safetensors",
316
+ "model.vision_sampler_0.layers.1.cross_attn.v_proj_1.0.bias": "model-00002-of-00002.safetensors",
317
+ "model.vision_sampler_0.layers.1.cross_attn.v_proj_1.0.weight": "model-00002-of-00002.safetensors",
318
+ "model.vision_sampler_0.layers.1.cross_attn.v_proj_1.1.weight": "model-00002-of-00002.safetensors",
319
+ "model.vision_sampler_0.layers.1.norm.bias": "model-00002-of-00002.safetensors",
320
+ "model.vision_sampler_0.layers.1.norm.weight": "model-00002-of-00002.safetensors",
321
+ "model.vision_sampler_0.layers.1.pos_embed_0": "model-00002-of-00002.safetensors",
322
+ "model.vision_sampler_0.layers.1.pos_embed_1": "model-00002-of-00002.safetensors",
323
+ "model.vision_sampler_0.layers.1.proj_context.weight": "model-00002-of-00002.safetensors",
324
+ "model.vision_sampler_0.layers.1.proj_in.weight": "model-00002-of-00002.safetensors",
325
+ "model.vision_sampler_0.layers.1.proj_out.linear_1.weight": "model-00002-of-00002.safetensors",
326
+ "model.vision_sampler_0.layers.1.proj_out.linear_2.weight": "model-00002-of-00002.safetensors",
327
+ "model.vision_sampler_0.layers.2.cross_attn.k_proj_0.0.bias": "model-00002-of-00002.safetensors",
328
+ "model.vision_sampler_0.layers.2.cross_attn.k_proj_0.0.weight": "model-00002-of-00002.safetensors",
329
+ "model.vision_sampler_0.layers.2.cross_attn.k_proj_0.1.weight": "model-00002-of-00002.safetensors",
330
+ "model.vision_sampler_0.layers.2.cross_attn.k_proj_1.0.bias": "model-00002-of-00002.safetensors",
331
+ "model.vision_sampler_0.layers.2.cross_attn.k_proj_1.0.weight": "model-00002-of-00002.safetensors",
332
+ "model.vision_sampler_0.layers.2.cross_attn.k_proj_1.1.weight": "model-00002-of-00002.safetensors",
333
+ "model.vision_sampler_0.layers.2.cross_attn.o_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.vision_sampler_0.layers.2.cross_attn.q_proj.0.bias": "model-00002-of-00002.safetensors",
335
+ "model.vision_sampler_0.layers.2.cross_attn.q_proj.0.weight": "model-00002-of-00002.safetensors",
336
+ "model.vision_sampler_0.layers.2.cross_attn.q_proj.1.weight": "model-00002-of-00002.safetensors",
337
+ "model.vision_sampler_0.layers.2.cross_attn.v_proj_0.0.bias": "model-00002-of-00002.safetensors",
338
+ "model.vision_sampler_0.layers.2.cross_attn.v_proj_0.0.weight": "model-00002-of-00002.safetensors",
339
+ "model.vision_sampler_0.layers.2.cross_attn.v_proj_0.1.weight": "model-00002-of-00002.safetensors",
340
+ "model.vision_sampler_0.layers.2.cross_attn.v_proj_1.0.bias": "model-00002-of-00002.safetensors",
341
+ "model.vision_sampler_0.layers.2.cross_attn.v_proj_1.0.weight": "model-00002-of-00002.safetensors",
342
+ "model.vision_sampler_0.layers.2.cross_attn.v_proj_1.1.weight": "model-00002-of-00002.safetensors",
343
+ "model.vision_sampler_0.layers.2.norm.bias": "model-00002-of-00002.safetensors",
344
+ "model.vision_sampler_0.layers.2.norm.weight": "model-00002-of-00002.safetensors",
345
+ "model.vision_sampler_0.layers.2.pos_embed_0": "model-00002-of-00002.safetensors",
346
+ "model.vision_sampler_0.layers.2.pos_embed_1": "model-00002-of-00002.safetensors",
347
+ "model.vision_sampler_0.layers.2.proj_context.weight": "model-00002-of-00002.safetensors",
348
+ "model.vision_sampler_0.layers.2.proj_in.weight": "model-00002-of-00002.safetensors",
349
+ "model.vision_sampler_0.layers.2.proj_out.linear_1.weight": "model-00002-of-00002.safetensors",
350
+ "model.vision_sampler_0.layers.2.proj_out.linear_2.weight": "model-00002-of-00002.safetensors"
351
+ }
352
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0bff24ab47f3c682cb934cc5977eb64295818203a3a2ad6dd137a708f42ea19
3
+ size 1626371151
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b8f6500eb98748317efd17962c2a6f82705511e3f8832b13001dad309942fbe
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30a7501a8dbea3de989058ffdbe8ac592f04bac2c392daf9f2e2849eedb80b6e
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|reserved_special_token_0|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 8192,
2061
+ "pad_token": "<|reserved_special_token_0|>",
2062
+ "padding_side": "right",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,1923 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 540.0,
6
+ "global_step": 540,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.003703703703703704,
13
+ "grad_norm": 9.5,
14
+ "learning_rate": 2.787878787878788e-07,
15
+ "loss": 0.7464,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.007407407407407408,
20
+ "grad_norm": 9.6875,
21
+ "learning_rate": 5.575757575757576e-07,
22
+ "loss": 0.7497,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.011111111111111112,
27
+ "grad_norm": 9.6875,
28
+ "learning_rate": 8.363636363636364e-07,
29
+ "loss": 0.7544,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.014814814814814815,
34
+ "grad_norm": 9.375,
35
+ "learning_rate": 1.1151515151515153e-06,
36
+ "loss": 0.7549,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.018518518518518517,
41
+ "grad_norm": 9.6875,
42
+ "learning_rate": 1.393939393939394e-06,
43
+ "loss": 0.7816,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.022222222222222223,
48
+ "grad_norm": 9.5,
49
+ "learning_rate": 1.6727272727272728e-06,
50
+ "loss": 0.7629,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.025925925925925925,
55
+ "grad_norm": 9.375,
56
+ "learning_rate": 1.9515151515151518e-06,
57
+ "loss": 0.777,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.02962962962962963,
62
+ "grad_norm": 9.625,
63
+ "learning_rate": 2.2303030303030305e-06,
64
+ "loss": 0.7604,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.03333333333333333,
69
+ "grad_norm": 9.3125,
70
+ "learning_rate": 2.509090909090909e-06,
71
+ "loss": 0.7431,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.037037037037037035,
76
+ "grad_norm": 9.125,
77
+ "learning_rate": 2.787878787878788e-06,
78
+ "loss": 0.7333,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.040740740740740744,
83
+ "grad_norm": 9.875,
84
+ "learning_rate": 3.0666666666666664e-06,
85
+ "loss": 0.7854,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.044444444444444446,
90
+ "grad_norm": 9.5625,
91
+ "learning_rate": 3.3454545454545456e-06,
92
+ "loss": 0.7264,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.04814814814814815,
97
+ "grad_norm": 9.5625,
98
+ "learning_rate": 3.624242424242424e-06,
99
+ "loss": 0.7634,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.05185185185185185,
104
+ "grad_norm": 9.4375,
105
+ "learning_rate": 3.9030303030303035e-06,
106
+ "loss": 0.7677,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.05555555555555555,
111
+ "grad_norm": 9.5,
112
+ "learning_rate": 4.1818181818181814e-06,
113
+ "loss": 0.76,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.05925925925925926,
118
+ "grad_norm": 9.625,
119
+ "learning_rate": 4.460606060606061e-06,
120
+ "loss": 0.7615,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.06296296296296296,
125
+ "grad_norm": 9.5,
126
+ "learning_rate": 4.59998964610166e-06,
127
+ "loss": 0.7493,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 0.06666666666666667,
132
+ "grad_norm": 9.4375,
133
+ "learning_rate": 4.599906815474259e-06,
134
+ "loss": 0.7541,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 0.07037037037037037,
139
+ "grad_norm": 9.5625,
140
+ "learning_rate": 4.599741157202478e-06,
141
+ "loss": 0.7721,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 0.07407407407407407,
146
+ "grad_norm": 9.125,
147
+ "learning_rate": 4.599492677252244e-06,
148
+ "loss": 0.7385,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 0.07777777777777778,
153
+ "grad_norm": 9.375,
154
+ "learning_rate": 4.599161384572187e-06,
155
+ "loss": 0.7255,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 0.08148148148148149,
160
+ "grad_norm": 9.375,
161
+ "learning_rate": 4.5987472910933085e-06,
162
+ "loss": 0.7548,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 0.08518518518518518,
167
+ "grad_norm": 9.3125,
168
+ "learning_rate": 4.598250411728554e-06,
169
+ "loss": 0.747,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 0.08888888888888889,
174
+ "grad_norm": 9.3125,
175
+ "learning_rate": 4.597670764372279e-06,
176
+ "loss": 0.7368,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 0.09259259259259259,
181
+ "grad_norm": 9.25,
182
+ "learning_rate": 4.5970083698996e-06,
183
+ "loss": 0.7536,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 0.0962962962962963,
188
+ "grad_norm": 9.3125,
189
+ "learning_rate": 4.596263252165647e-06,
190
+ "loss": 0.7242,
191
+ "step": 52
192
+ },
193
+ {
194
+ "epoch": 0.1,
195
+ "grad_norm": 9.375,
196
+ "learning_rate": 4.595435438004701e-06,
197
+ "loss": 0.7248,
198
+ "step": 54
199
+ },
200
+ {
201
+ "epoch": 0.1037037037037037,
202
+ "grad_norm": 9.1875,
203
+ "learning_rate": 4.594524957229229e-06,
204
+ "loss": 0.7113,
205
+ "step": 56
206
+ },
207
+ {
208
+ "epoch": 0.10740740740740741,
209
+ "grad_norm": 9.375,
210
+ "learning_rate": 4.593531842628811e-06,
211
+ "loss": 0.7352,
212
+ "step": 58
213
+ },
214
+ {
215
+ "epoch": 0.1111111111111111,
216
+ "grad_norm": 8.875,
217
+ "learning_rate": 4.592456129968958e-06,
218
+ "loss": 0.6914,
219
+ "step": 60
220
+ },
221
+ {
222
+ "epoch": 0.11481481481481481,
223
+ "grad_norm": 9.125,
224
+ "learning_rate": 4.591297857989825e-06,
225
+ "loss": 0.6962,
226
+ "step": 62
227
+ },
228
+ {
229
+ "epoch": 0.11851851851851852,
230
+ "grad_norm": 8.9375,
231
+ "learning_rate": 4.590057068404815e-06,
232
+ "loss": 0.7002,
233
+ "step": 64
234
+ },
235
+ {
236
+ "epoch": 0.12222222222222222,
237
+ "grad_norm": 9.1875,
238
+ "learning_rate": 4.588733805899076e-06,
239
+ "loss": 0.7196,
240
+ "step": 66
241
+ },
242
+ {
243
+ "epoch": 0.1259259259259259,
244
+ "grad_norm": 9.5625,
245
+ "learning_rate": 4.587328118127894e-06,
246
+ "loss": 0.7366,
247
+ "step": 68
248
+ },
249
+ {
250
+ "epoch": 0.12962962962962962,
251
+ "grad_norm": 9.0625,
252
+ "learning_rate": 4.585840055714976e-06,
253
+ "loss": 0.7042,
254
+ "step": 70
255
+ },
256
+ {
257
+ "epoch": 0.13333333333333333,
258
+ "grad_norm": 9.1875,
259
+ "learning_rate": 4.584269672250625e-06,
260
+ "loss": 0.6914,
261
+ "step": 72
262
+ },
263
+ {
264
+ "epoch": 0.13703703703703704,
265
+ "grad_norm": 9.1875,
266
+ "learning_rate": 4.582617024289811e-06,
267
+ "loss": 0.7045,
268
+ "step": 74
269
+ },
270
+ {
271
+ "epoch": 0.14074074074074075,
272
+ "grad_norm": 9.1875,
273
+ "learning_rate": 4.5808821713501374e-06,
274
+ "loss": 0.7275,
275
+ "step": 76
276
+ },
277
+ {
278
+ "epoch": 0.14444444444444443,
279
+ "grad_norm": 9.125,
280
+ "learning_rate": 4.579065175909692e-06,
281
+ "loss": 0.6943,
282
+ "step": 78
283
+ },
284
+ {
285
+ "epoch": 0.14814814814814814,
286
+ "grad_norm": 8.9375,
287
+ "learning_rate": 4.577166103404801e-06,
288
+ "loss": 0.6792,
289
+ "step": 80
290
+ },
291
+ {
292
+ "epoch": 0.15185185185185185,
293
+ "grad_norm": 9.1875,
294
+ "learning_rate": 4.5751850222276705e-06,
295
+ "loss": 0.6854,
296
+ "step": 82
297
+ },
298
+ {
299
+ "epoch": 0.15555555555555556,
300
+ "grad_norm": 8.875,
301
+ "learning_rate": 4.573122003723925e-06,
302
+ "loss": 0.6675,
303
+ "step": 84
304
+ },
305
+ {
306
+ "epoch": 0.15925925925925927,
307
+ "grad_norm": 9.625,
308
+ "learning_rate": 4.5709771221900375e-06,
309
+ "loss": 0.6882,
310
+ "step": 86
311
+ },
312
+ {
313
+ "epoch": 0.16296296296296298,
314
+ "grad_norm": 8.875,
315
+ "learning_rate": 4.568750454870651e-06,
316
+ "loss": 0.675,
317
+ "step": 88
318
+ },
319
+ {
320
+ "epoch": 0.16666666666666666,
321
+ "grad_norm": 9.0625,
322
+ "learning_rate": 4.5664420819558035e-06,
323
+ "loss": 0.6996,
324
+ "step": 90
325
+ },
326
+ {
327
+ "epoch": 0.17037037037037037,
328
+ "grad_norm": 9.375,
329
+ "learning_rate": 4.564052086578031e-06,
330
+ "loss": 0.7039,
331
+ "step": 92
332
+ },
333
+ {
334
+ "epoch": 0.17407407407407408,
335
+ "grad_norm": 8.8125,
336
+ "learning_rate": 4.561580554809381e-06,
337
+ "loss": 0.6587,
338
+ "step": 94
339
+ },
340
+ {
341
+ "epoch": 0.17777777777777778,
342
+ "grad_norm": 9.0,
343
+ "learning_rate": 4.559027575658309e-06,
344
+ "loss": 0.6556,
345
+ "step": 96
346
+ },
347
+ {
348
+ "epoch": 0.1814814814814815,
349
+ "grad_norm": 8.6875,
350
+ "learning_rate": 4.556393241066476e-06,
351
+ "loss": 0.6617,
352
+ "step": 98
353
+ },
354
+ {
355
+ "epoch": 0.18518518518518517,
356
+ "grad_norm": 9.375,
357
+ "learning_rate": 4.553677645905431e-06,
358
+ "loss": 0.6828,
359
+ "step": 100
360
+ },
361
+ {
362
+ "epoch": 0.18888888888888888,
363
+ "grad_norm": 8.625,
364
+ "learning_rate": 4.550880887973204e-06,
365
+ "loss": 0.6371,
366
+ "step": 102
367
+ },
368
+ {
369
+ "epoch": 0.1925925925925926,
370
+ "grad_norm": 8.8125,
371
+ "learning_rate": 4.548003067990776e-06,
372
+ "loss": 0.65,
373
+ "step": 104
374
+ },
375
+ {
376
+ "epoch": 0.1962962962962963,
377
+ "grad_norm": 8.875,
378
+ "learning_rate": 4.545044289598454e-06,
379
+ "loss": 0.6718,
380
+ "step": 106
381
+ },
382
+ {
383
+ "epoch": 0.2,
384
+ "grad_norm": 9.0625,
385
+ "learning_rate": 4.54200465935214e-06,
386
+ "loss": 0.6834,
387
+ "step": 108
388
+ },
389
+ {
390
+ "epoch": 0.2037037037037037,
391
+ "grad_norm": 8.9375,
392
+ "learning_rate": 4.5388842867194925e-06,
393
+ "loss": 0.6696,
394
+ "step": 110
395
+ },
396
+ {
397
+ "epoch": 0.2074074074074074,
398
+ "grad_norm": 8.8125,
399
+ "learning_rate": 4.535683284075984e-06,
400
+ "loss": 0.6811,
401
+ "step": 112
402
+ },
403
+ {
404
+ "epoch": 0.2111111111111111,
405
+ "grad_norm": 8.875,
406
+ "learning_rate": 4.5324017667008535e-06,
407
+ "loss": 0.666,
408
+ "step": 114
409
+ },
410
+ {
411
+ "epoch": 0.21481481481481482,
412
+ "grad_norm": 9.125,
413
+ "learning_rate": 4.529039852772956e-06,
414
+ "loss": 0.6534,
415
+ "step": 116
416
+ },
417
+ {
418
+ "epoch": 0.21851851851851853,
419
+ "grad_norm": 9.0,
420
+ "learning_rate": 4.525597663366506e-06,
421
+ "loss": 0.66,
422
+ "step": 118
423
+ },
424
+ {
425
+ "epoch": 0.2222222222222222,
426
+ "grad_norm": 8.6875,
427
+ "learning_rate": 4.522075322446718e-06,
428
+ "loss": 0.6418,
429
+ "step": 120
430
+ },
431
+ {
432
+ "epoch": 0.22592592592592592,
433
+ "grad_norm": 9.125,
434
+ "learning_rate": 4.51847295686534e-06,
435
+ "loss": 0.6477,
436
+ "step": 122
437
+ },
438
+ {
439
+ "epoch": 0.22962962962962963,
440
+ "grad_norm": 8.75,
441
+ "learning_rate": 4.514790696356086e-06,
442
+ "loss": 0.6517,
443
+ "step": 124
444
+ },
445
+ {
446
+ "epoch": 0.23333333333333334,
447
+ "grad_norm": 9.125,
448
+ "learning_rate": 4.511028673529967e-06,
449
+ "loss": 0.6605,
450
+ "step": 126
451
+ },
452
+ {
453
+ "epoch": 0.23703703703703705,
454
+ "grad_norm": 8.75,
455
+ "learning_rate": 4.507187023870511e-06,
456
+ "loss": 0.6302,
457
+ "step": 128
458
+ },
459
+ {
460
+ "epoch": 0.24074074074074073,
461
+ "grad_norm": 8.75,
462
+ "learning_rate": 4.503265885728883e-06,
463
+ "loss": 0.6274,
464
+ "step": 130
465
+ },
466
+ {
467
+ "epoch": 0.24444444444444444,
468
+ "grad_norm": 8.625,
469
+ "learning_rate": 4.499265400318908e-06,
470
+ "loss": 0.6427,
471
+ "step": 132
472
+ },
473
+ {
474
+ "epoch": 0.24814814814814815,
475
+ "grad_norm": 8.5,
476
+ "learning_rate": 4.49518571171198e-06,
477
+ "loss": 0.6336,
478
+ "step": 134
479
+ },
480
+ {
481
+ "epoch": 0.2518518518518518,
482
+ "grad_norm": 9.0,
483
+ "learning_rate": 4.4910269668318775e-06,
484
+ "loss": 0.6704,
485
+ "step": 136
486
+ },
487
+ {
488
+ "epoch": 0.25555555555555554,
489
+ "grad_norm": 8.8125,
490
+ "learning_rate": 4.486789315449469e-06,
491
+ "loss": 0.6276,
492
+ "step": 138
493
+ },
494
+ {
495
+ "epoch": 0.25925925925925924,
496
+ "grad_norm": 8.875,
497
+ "learning_rate": 4.4824729101773205e-06,
498
+ "loss": 0.6456,
499
+ "step": 140
500
+ },
501
+ {
502
+ "epoch": 0.26296296296296295,
503
+ "grad_norm": 8.875,
504
+ "learning_rate": 4.4780779064642e-06,
505
+ "loss": 0.6438,
506
+ "step": 142
507
+ },
508
+ {
509
+ "epoch": 0.26666666666666666,
510
+ "grad_norm": 8.875,
511
+ "learning_rate": 4.473604462589479e-06,
512
+ "loss": 0.6319,
513
+ "step": 144
514
+ },
515
+ {
516
+ "epoch": 0.27037037037037037,
517
+ "grad_norm": 9.5625,
518
+ "learning_rate": 4.469052739657432e-06,
519
+ "loss": 0.6766,
520
+ "step": 146
521
+ },
522
+ {
523
+ "epoch": 0.2740740740740741,
524
+ "grad_norm": 8.875,
525
+ "learning_rate": 4.464422901591434e-06,
526
+ "loss": 0.6316,
527
+ "step": 148
528
+ },
529
+ {
530
+ "epoch": 0.2777777777777778,
531
+ "grad_norm": 8.6875,
532
+ "learning_rate": 4.459715115128058e-06,
533
+ "loss": 0.629,
534
+ "step": 150
535
+ },
536
+ {
537
+ "epoch": 0.2814814814814815,
538
+ "grad_norm": 8.9375,
539
+ "learning_rate": 4.454929549811071e-06,
540
+ "loss": 0.6362,
541
+ "step": 152
542
+ },
543
+ {
544
+ "epoch": 0.2851851851851852,
545
+ "grad_norm": 8.75,
546
+ "learning_rate": 4.450066377985326e-06,
547
+ "loss": 0.6216,
548
+ "step": 154
549
+ },
550
+ {
551
+ "epoch": 0.28888888888888886,
552
+ "grad_norm": 9.0625,
553
+ "learning_rate": 4.445125774790555e-06,
554
+ "loss": 0.6535,
555
+ "step": 156
556
+ },
557
+ {
558
+ "epoch": 0.29259259259259257,
559
+ "grad_norm": 8.8125,
560
+ "learning_rate": 4.440107918155065e-06,
561
+ "loss": 0.6278,
562
+ "step": 158
563
+ },
564
+ {
565
+ "epoch": 0.2962962962962963,
566
+ "grad_norm": 8.8125,
567
+ "learning_rate": 4.435012988789327e-06,
568
+ "loss": 0.6178,
569
+ "step": 160
570
+ },
571
+ {
572
+ "epoch": 0.3,
573
+ "grad_norm": 8.4375,
574
+ "learning_rate": 4.429841170179471e-06,
575
+ "loss": 0.6243,
576
+ "step": 162
577
+ },
578
+ {
579
+ "epoch": 0.3037037037037037,
580
+ "grad_norm": 8.875,
581
+ "learning_rate": 4.4245926485806745e-06,
582
+ "loss": 0.6201,
583
+ "step": 164
584
+ },
585
+ {
586
+ "epoch": 0.3074074074074074,
587
+ "grad_norm": 8.75,
588
+ "learning_rate": 4.419267613010454e-06,
589
+ "loss": 0.6267,
590
+ "step": 166
591
+ },
592
+ {
593
+ "epoch": 0.3111111111111111,
594
+ "grad_norm": 8.75,
595
+ "learning_rate": 4.413866255241867e-06,
596
+ "loss": 0.6474,
597
+ "step": 168
598
+ },
599
+ {
600
+ "epoch": 0.3148148148148148,
601
+ "grad_norm": 8.4375,
602
+ "learning_rate": 4.4083887697965915e-06,
603
+ "loss": 0.6021,
604
+ "step": 170
605
+ },
606
+ {
607
+ "epoch": 0.31851851851851853,
608
+ "grad_norm": 8.5625,
609
+ "learning_rate": 4.402835353937933e-06,
610
+ "loss": 0.6044,
611
+ "step": 172
612
+ },
613
+ {
614
+ "epoch": 0.32222222222222224,
615
+ "grad_norm": 8.9375,
616
+ "learning_rate": 4.397206207663713e-06,
617
+ "loss": 0.6293,
618
+ "step": 174
619
+ },
620
+ {
621
+ "epoch": 0.32592592592592595,
622
+ "grad_norm": 8.6875,
623
+ "learning_rate": 4.391501533699068e-06,
624
+ "loss": 0.6039,
625
+ "step": 176
626
+ },
627
+ {
628
+ "epoch": 0.3296296296296296,
629
+ "grad_norm": 8.875,
630
+ "learning_rate": 4.385721537489152e-06,
631
+ "loss": 0.6116,
632
+ "step": 178
633
+ },
634
+ {
635
+ "epoch": 0.3333333333333333,
636
+ "grad_norm": 8.4375,
637
+ "learning_rate": 4.379866427191734e-06,
638
+ "loss": 0.5855,
639
+ "step": 180
640
+ },
641
+ {
642
+ "epoch": 0.337037037037037,
643
+ "grad_norm": 8.625,
644
+ "learning_rate": 4.373936413669699e-06,
645
+ "loss": 0.5902,
646
+ "step": 182
647
+ },
648
+ {
649
+ "epoch": 0.34074074074074073,
650
+ "grad_norm": 8.25,
651
+ "learning_rate": 4.367931710483465e-06,
652
+ "loss": 0.6014,
653
+ "step": 184
654
+ },
655
+ {
656
+ "epoch": 0.34444444444444444,
657
+ "grad_norm": 8.625,
658
+ "learning_rate": 4.361852533883278e-06,
659
+ "loss": 0.6035,
660
+ "step": 186
661
+ },
662
+ {
663
+ "epoch": 0.34814814814814815,
664
+ "grad_norm": 8.3125,
665
+ "learning_rate": 4.355699102801434e-06,
666
+ "loss": 0.5791,
667
+ "step": 188
668
+ },
669
+ {
670
+ "epoch": 0.35185185185185186,
671
+ "grad_norm": 8.6875,
672
+ "learning_rate": 4.349471638844388e-06,
673
+ "loss": 0.5952,
674
+ "step": 190
675
+ },
676
+ {
677
+ "epoch": 0.35555555555555557,
678
+ "grad_norm": 8.9375,
679
+ "learning_rate": 4.3431703662847814e-06,
680
+ "loss": 0.6405,
681
+ "step": 192
682
+ },
683
+ {
684
+ "epoch": 0.3592592592592593,
685
+ "grad_norm": 8.375,
686
+ "learning_rate": 4.336795512053356e-06,
687
+ "loss": 0.5953,
688
+ "step": 194
689
+ },
690
+ {
691
+ "epoch": 0.362962962962963,
692
+ "grad_norm": 8.6875,
693
+ "learning_rate": 4.330347305730786e-06,
694
+ "loss": 0.6133,
695
+ "step": 196
696
+ },
697
+ {
698
+ "epoch": 0.36666666666666664,
699
+ "grad_norm": 8.6875,
700
+ "learning_rate": 4.323825979539413e-06,
701
+ "loss": 0.6232,
702
+ "step": 198
703
+ },
704
+ {
705
+ "epoch": 0.37037037037037035,
706
+ "grad_norm": 8.625,
707
+ "learning_rate": 4.317231768334875e-06,
708
+ "loss": 0.6017,
709
+ "step": 200
710
+ },
711
+ {
712
+ "epoch": 0.37407407407407406,
713
+ "grad_norm": 8.4375,
714
+ "learning_rate": 4.310564909597654e-06,
715
+ "loss": 0.5907,
716
+ "step": 202
717
+ },
718
+ {
719
+ "epoch": 0.37777777777777777,
720
+ "grad_norm": 8.4375,
721
+ "learning_rate": 4.303825643424525e-06,
722
+ "loss": 0.62,
723
+ "step": 204
724
+ },
725
+ {
726
+ "epoch": 0.3814814814814815,
727
+ "grad_norm": 8.375,
728
+ "learning_rate": 4.297014212519903e-06,
729
+ "loss": 0.5838,
730
+ "step": 206
731
+ },
732
+ {
733
+ "epoch": 0.3851851851851852,
734
+ "grad_norm": 8.25,
735
+ "learning_rate": 4.290130862187108e-06,
736
+ "loss": 0.5953,
737
+ "step": 208
738
+ },
739
+ {
740
+ "epoch": 0.3888888888888889,
741
+ "grad_norm": 9.0,
742
+ "learning_rate": 4.283175840319529e-06,
743
+ "loss": 0.6231,
744
+ "step": 210
745
+ },
746
+ {
747
+ "epoch": 0.3925925925925926,
748
+ "grad_norm": 8.375,
749
+ "learning_rate": 4.276149397391696e-06,
750
+ "loss": 0.6054,
751
+ "step": 212
752
+ },
753
+ {
754
+ "epoch": 0.3962962962962963,
755
+ "grad_norm": 8.4375,
756
+ "learning_rate": 4.269051786450258e-06,
757
+ "loss": 0.5715,
758
+ "step": 214
759
+ },
760
+ {
761
+ "epoch": 0.4,
762
+ "grad_norm": 8.1875,
763
+ "learning_rate": 4.261883263104874e-06,
764
+ "loss": 0.5643,
765
+ "step": 216
766
+ },
767
+ {
768
+ "epoch": 0.40370370370370373,
769
+ "grad_norm": 8.375,
770
+ "learning_rate": 4.2546440855190055e-06,
771
+ "loss": 0.5686,
772
+ "step": 218
773
+ },
774
+ {
775
+ "epoch": 0.4074074074074074,
776
+ "grad_norm": 8.875,
777
+ "learning_rate": 4.2473345144006165e-06,
778
+ "loss": 0.595,
779
+ "step": 220
780
+ },
781
+ {
782
+ "epoch": 0.4111111111111111,
783
+ "grad_norm": 8.8125,
784
+ "learning_rate": 4.239954812992789e-06,
785
+ "loss": 0.6095,
786
+ "step": 222
787
+ },
788
+ {
789
+ "epoch": 0.4148148148148148,
790
+ "grad_norm": 8.3125,
791
+ "learning_rate": 4.23250524706424e-06,
792
+ "loss": 0.554,
793
+ "step": 224
794
+ },
795
+ {
796
+ "epoch": 0.4185185185185185,
797
+ "grad_norm": 8.875,
798
+ "learning_rate": 4.224986084899751e-06,
799
+ "loss": 0.6128,
800
+ "step": 226
801
+ },
802
+ {
803
+ "epoch": 0.4222222222222222,
804
+ "grad_norm": 8.4375,
805
+ "learning_rate": 4.217397597290506e-06,
806
+ "loss": 0.5895,
807
+ "step": 228
808
+ },
809
+ {
810
+ "epoch": 0.42592592592592593,
811
+ "grad_norm": 8.6875,
812
+ "learning_rate": 4.20974005752434e-06,
813
+ "loss": 0.613,
814
+ "step": 230
815
+ },
816
+ {
817
+ "epoch": 0.42962962962962964,
818
+ "grad_norm": 8.625,
819
+ "learning_rate": 4.202013741375896e-06,
820
+ "loss": 0.5693,
821
+ "step": 232
822
+ },
823
+ {
824
+ "epoch": 0.43333333333333335,
825
+ "grad_norm": 8.0625,
826
+ "learning_rate": 4.194218927096692e-06,
827
+ "loss": 0.5706,
828
+ "step": 234
829
+ },
830
+ {
831
+ "epoch": 0.43703703703703706,
832
+ "grad_norm": 8.75,
833
+ "learning_rate": 4.186355895405106e-06,
834
+ "loss": 0.5816,
835
+ "step": 236
836
+ },
837
+ {
838
+ "epoch": 0.44074074074074077,
839
+ "grad_norm": 8.6875,
840
+ "learning_rate": 4.1784249294762585e-06,
841
+ "loss": 0.5983,
842
+ "step": 238
843
+ },
844
+ {
845
+ "epoch": 0.4444444444444444,
846
+ "grad_norm": 8.5625,
847
+ "learning_rate": 4.170426314931819e-06,
848
+ "loss": 0.5774,
849
+ "step": 240
850
+ },
851
+ {
852
+ "epoch": 0.44814814814814813,
853
+ "grad_norm": 8.8125,
854
+ "learning_rate": 4.16236033982972e-06,
855
+ "loss": 0.5933,
856
+ "step": 242
857
+ },
858
+ {
859
+ "epoch": 0.45185185185185184,
860
+ "grad_norm": 8.8125,
861
+ "learning_rate": 4.154227294653782e-06,
862
+ "loss": 0.5751,
863
+ "step": 244
864
+ },
865
+ {
866
+ "epoch": 0.45555555555555555,
867
+ "grad_norm": 8.0625,
868
+ "learning_rate": 4.146027472303251e-06,
869
+ "loss": 0.5488,
870
+ "step": 246
871
+ },
872
+ {
873
+ "epoch": 0.45925925925925926,
874
+ "grad_norm": 8.375,
875
+ "learning_rate": 4.137761168082251e-06,
876
+ "loss": 0.5881,
877
+ "step": 248
878
+ },
879
+ {
880
+ "epoch": 0.46296296296296297,
881
+ "grad_norm": 8.5625,
882
+ "learning_rate": 4.129428679689153e-06,
883
+ "loss": 0.5714,
884
+ "step": 250
885
+ },
886
+ {
887
+ "epoch": 0.4666666666666667,
888
+ "grad_norm": 8.4375,
889
+ "learning_rate": 4.121030307205846e-06,
890
+ "loss": 0.5852,
891
+ "step": 252
892
+ },
893
+ {
894
+ "epoch": 0.4703703703703704,
895
+ "grad_norm": 8.1875,
896
+ "learning_rate": 4.112566353086935e-06,
897
+ "loss": 0.5773,
898
+ "step": 254
899
+ },
900
+ {
901
+ "epoch": 0.4740740740740741,
902
+ "grad_norm": 8.3125,
903
+ "learning_rate": 4.1040371221488506e-06,
904
+ "loss": 0.5557,
905
+ "step": 256
906
+ },
907
+ {
908
+ "epoch": 0.4777777777777778,
909
+ "grad_norm": 8.5,
910
+ "learning_rate": 4.0954429215588655e-06,
911
+ "loss": 0.5793,
912
+ "step": 258
913
+ },
914
+ {
915
+ "epoch": 0.48148148148148145,
916
+ "grad_norm": 8.125,
917
+ "learning_rate": 4.086784060824037e-06,
918
+ "loss": 0.5691,
919
+ "step": 260
920
+ },
921
+ {
922
+ "epoch": 0.48518518518518516,
923
+ "grad_norm": 8.5,
924
+ "learning_rate": 4.078060851780059e-06,
925
+ "loss": 0.569,
926
+ "step": 262
927
+ },
928
+ {
929
+ "epoch": 0.4888888888888889,
930
+ "grad_norm": 8.5,
931
+ "learning_rate": 4.069273608580033e-06,
932
+ "loss": 0.5831,
933
+ "step": 264
934
+ },
935
+ {
936
+ "epoch": 0.4925925925925926,
937
+ "grad_norm": 8.8125,
938
+ "learning_rate": 4.060422647683151e-06,
939
+ "loss": 0.5827,
940
+ "step": 266
941
+ },
942
+ {
943
+ "epoch": 0.4962962962962963,
944
+ "grad_norm": 8.1875,
945
+ "learning_rate": 4.051508287843302e-06,
946
+ "loss": 0.5563,
947
+ "step": 268
948
+ },
949
+ {
950
+ "epoch": 0.5,
951
+ "grad_norm": 8.75,
952
+ "learning_rate": 4.042530850097591e-06,
953
+ "loss": 0.5807,
954
+ "step": 270
955
+ },
956
+ {
957
+ "epoch": 0.5037037037037037,
958
+ "grad_norm": 8.4375,
959
+ "learning_rate": 4.033490657754778e-06,
960
+ "loss": 0.5927,
961
+ "step": 272
962
+ },
963
+ {
964
+ "epoch": 0.5074074074074074,
965
+ "grad_norm": 8.75,
966
+ "learning_rate": 4.024388036383636e-06,
967
+ "loss": 0.5615,
968
+ "step": 274
969
+ },
970
+ {
971
+ "epoch": 0.5111111111111111,
972
+ "grad_norm": 8.625,
973
+ "learning_rate": 4.015223313801222e-06,
974
+ "loss": 0.5552,
975
+ "step": 276
976
+ },
977
+ {
978
+ "epoch": 0.5148148148148148,
979
+ "grad_norm": 8.25,
980
+ "learning_rate": 4.0059968200610755e-06,
981
+ "loss": 0.5492,
982
+ "step": 278
983
+ },
984
+ {
985
+ "epoch": 0.5185185185185185,
986
+ "grad_norm": 8.375,
987
+ "learning_rate": 3.996708887441328e-06,
988
+ "loss": 0.5802,
989
+ "step": 280
990
+ },
991
+ {
992
+ "epoch": 0.5222222222222223,
993
+ "grad_norm": 8.375,
994
+ "learning_rate": 3.98735985043274e-06,
995
+ "loss": 0.5961,
996
+ "step": 282
997
+ },
998
+ {
999
+ "epoch": 0.5259259259259259,
1000
+ "grad_norm": 8.6875,
1001
+ "learning_rate": 3.977950045726656e-06,
1002
+ "loss": 0.587,
1003
+ "step": 284
1004
+ },
1005
+ {
1006
+ "epoch": 0.5296296296296297,
1007
+ "grad_norm": 8.125,
1008
+ "learning_rate": 3.968479812202871e-06,
1009
+ "loss": 0.5425,
1010
+ "step": 286
1011
+ },
1012
+ {
1013
+ "epoch": 0.5333333333333333,
1014
+ "grad_norm": 8.5625,
1015
+ "learning_rate": 3.9589494909174376e-06,
1016
+ "loss": 0.5566,
1017
+ "step": 288
1018
+ },
1019
+ {
1020
+ "epoch": 0.5370370370370371,
1021
+ "grad_norm": 8.5625,
1022
+ "learning_rate": 3.949359425090375e-06,
1023
+ "loss": 0.5746,
1024
+ "step": 290
1025
+ },
1026
+ {
1027
+ "epoch": 0.5407407407407407,
1028
+ "grad_norm": 8.5625,
1029
+ "learning_rate": 3.939709960093312e-06,
1030
+ "loss": 0.5679,
1031
+ "step": 292
1032
+ },
1033
+ {
1034
+ "epoch": 0.5444444444444444,
1035
+ "grad_norm": 8.125,
1036
+ "learning_rate": 3.930001443437046e-06,
1037
+ "loss": 0.5553,
1038
+ "step": 294
1039
+ },
1040
+ {
1041
+ "epoch": 0.5481481481481482,
1042
+ "grad_norm": 8.75,
1043
+ "learning_rate": 3.920234224759034e-06,
1044
+ "loss": 0.578,
1045
+ "step": 296
1046
+ },
1047
+ {
1048
+ "epoch": 0.5518518518518518,
1049
+ "grad_norm": 8.625,
1050
+ "learning_rate": 3.910408655810793e-06,
1051
+ "loss": 0.5866,
1052
+ "step": 298
1053
+ },
1054
+ {
1055
+ "epoch": 0.5555555555555556,
1056
+ "grad_norm": 8.625,
1057
+ "learning_rate": 3.900525090445238e-06,
1058
+ "loss": 0.5767,
1059
+ "step": 300
1060
+ },
1061
+ {
1062
+ "epoch": 0.5592592592592592,
1063
+ "grad_norm": 8.5,
1064
+ "learning_rate": 3.890583884603937e-06,
1065
+ "loss": 0.5557,
1066
+ "step": 302
1067
+ },
1068
+ {
1069
+ "epoch": 0.562962962962963,
1070
+ "grad_norm": 8.625,
1071
+ "learning_rate": 3.880585396304293e-06,
1072
+ "loss": 0.5618,
1073
+ "step": 304
1074
+ },
1075
+ {
1076
+ "epoch": 0.5666666666666667,
1077
+ "grad_norm": 8.0625,
1078
+ "learning_rate": 3.870529985626646e-06,
1079
+ "loss": 0.5323,
1080
+ "step": 306
1081
+ },
1082
+ {
1083
+ "epoch": 0.5703703703703704,
1084
+ "grad_norm": 8.8125,
1085
+ "learning_rate": 3.860418014701313e-06,
1086
+ "loss": 0.5737,
1087
+ "step": 308
1088
+ },
1089
+ {
1090
+ "epoch": 0.5740740740740741,
1091
+ "grad_norm": 8.125,
1092
+ "learning_rate": 3.850249847695538e-06,
1093
+ "loss": 0.5486,
1094
+ "step": 310
1095
+ },
1096
+ {
1097
+ "epoch": 0.5777777777777777,
1098
+ "grad_norm": 8.125,
1099
+ "learning_rate": 3.840025850800386e-06,
1100
+ "loss": 0.5394,
1101
+ "step": 312
1102
+ },
1103
+ {
1104
+ "epoch": 0.5814814814814815,
1105
+ "grad_norm": 8.125,
1106
+ "learning_rate": 3.8297463922175465e-06,
1107
+ "loss": 0.5573,
1108
+ "step": 314
1109
+ },
1110
+ {
1111
+ "epoch": 0.5851851851851851,
1112
+ "grad_norm": 8.5625,
1113
+ "learning_rate": 3.81941184214608e-06,
1114
+ "loss": 0.5522,
1115
+ "step": 316
1116
+ },
1117
+ {
1118
+ "epoch": 0.5888888888888889,
1119
+ "grad_norm": 8.625,
1120
+ "learning_rate": 3.8090225727690826e-06,
1121
+ "loss": 0.5727,
1122
+ "step": 318
1123
+ },
1124
+ {
1125
+ "epoch": 0.5925925925925926,
1126
+ "grad_norm": 8.125,
1127
+ "learning_rate": 3.798578958240281e-06,
1128
+ "loss": 0.5549,
1129
+ "step": 320
1130
+ },
1131
+ {
1132
+ "epoch": 0.5962962962962963,
1133
+ "grad_norm": 8.1875,
1134
+ "learning_rate": 3.7880813746705614e-06,
1135
+ "loss": 0.5452,
1136
+ "step": 322
1137
+ },
1138
+ {
1139
+ "epoch": 0.6,
1140
+ "grad_norm": 8.0625,
1141
+ "learning_rate": 3.7775302001144237e-06,
1142
+ "loss": 0.5246,
1143
+ "step": 324
1144
+ },
1145
+ {
1146
+ "epoch": 0.6037037037037037,
1147
+ "grad_norm": 8.6875,
1148
+ "learning_rate": 3.7669258145563636e-06,
1149
+ "loss": 0.5316,
1150
+ "step": 326
1151
+ },
1152
+ {
1153
+ "epoch": 0.6074074074074074,
1154
+ "grad_norm": 8.5625,
1155
+ "learning_rate": 3.756268599897193e-06,
1156
+ "loss": 0.5523,
1157
+ "step": 328
1158
+ },
1159
+ {
1160
+ "epoch": 0.6111111111111112,
1161
+ "grad_norm": 8.375,
1162
+ "learning_rate": 3.74555893994028e-06,
1163
+ "loss": 0.5412,
1164
+ "step": 330
1165
+ },
1166
+ {
1167
+ "epoch": 0.6148148148148148,
1168
+ "grad_norm": 8.4375,
1169
+ "learning_rate": 3.7347972203777317e-06,
1170
+ "loss": 0.5598,
1171
+ "step": 332
1172
+ },
1173
+ {
1174
+ "epoch": 0.6185185185185185,
1175
+ "grad_norm": 7.96875,
1176
+ "learning_rate": 3.7239838287765044e-06,
1177
+ "loss": 0.5334,
1178
+ "step": 334
1179
+ },
1180
+ {
1181
+ "epoch": 0.6222222222222222,
1182
+ "grad_norm": 8.1875,
1183
+ "learning_rate": 3.7131191545644415e-06,
1184
+ "loss": 0.5353,
1185
+ "step": 336
1186
+ },
1187
+ {
1188
+ "epoch": 0.6259259259259259,
1189
+ "grad_norm": 8.375,
1190
+ "learning_rate": 3.702203589016253e-06,
1191
+ "loss": 0.5547,
1192
+ "step": 338
1193
+ },
1194
+ {
1195
+ "epoch": 0.6296296296296297,
1196
+ "grad_norm": 8.625,
1197
+ "learning_rate": 3.691237525239424e-06,
1198
+ "loss": 0.5703,
1199
+ "step": 340
1200
+ },
1201
+ {
1202
+ "epoch": 0.6333333333333333,
1203
+ "grad_norm": 8.5,
1204
+ "learning_rate": 3.6802213581600538e-06,
1205
+ "loss": 0.5669,
1206
+ "step": 342
1207
+ },
1208
+ {
1209
+ "epoch": 0.6370370370370371,
1210
+ "grad_norm": 8.6875,
1211
+ "learning_rate": 3.669155484508639e-06,
1212
+ "loss": 0.5535,
1213
+ "step": 344
1214
+ },
1215
+ {
1216
+ "epoch": 0.6407407407407407,
1217
+ "grad_norm": 8.125,
1218
+ "learning_rate": 3.6580403028057785e-06,
1219
+ "loss": 0.544,
1220
+ "step": 346
1221
+ },
1222
+ {
1223
+ "epoch": 0.6444444444444445,
1224
+ "grad_norm": 8.375,
1225
+ "learning_rate": 3.6468762133478317e-06,
1226
+ "loss": 0.5295,
1227
+ "step": 348
1228
+ },
1229
+ {
1230
+ "epoch": 0.6481481481481481,
1231
+ "grad_norm": 8.625,
1232
+ "learning_rate": 3.6356636181924892e-06,
1233
+ "loss": 0.5698,
1234
+ "step": 350
1235
+ },
1236
+ {
1237
+ "epoch": 0.6518518518518519,
1238
+ "grad_norm": 7.9375,
1239
+ "learning_rate": 3.6244029211443076e-06,
1240
+ "loss": 0.5422,
1241
+ "step": 352
1242
+ },
1243
+ {
1244
+ "epoch": 0.6555555555555556,
1245
+ "grad_norm": 8.6875,
1246
+ "learning_rate": 3.613094527740155e-06,
1247
+ "loss": 0.5365,
1248
+ "step": 354
1249
+ },
1250
+ {
1251
+ "epoch": 0.6592592592592592,
1252
+ "grad_norm": 8.5625,
1253
+ "learning_rate": 3.601738845234613e-06,
1254
+ "loss": 0.5389,
1255
+ "step": 356
1256
+ },
1257
+ {
1258
+ "epoch": 0.662962962962963,
1259
+ "grad_norm": 8.625,
1260
+ "learning_rate": 3.5903362825853077e-06,
1261
+ "loss": 0.5571,
1262
+ "step": 358
1263
+ },
1264
+ {
1265
+ "epoch": 0.6666666666666666,
1266
+ "grad_norm": 8.0625,
1267
+ "learning_rate": 3.5788872504381836e-06,
1268
+ "loss": 0.5259,
1269
+ "step": 360
1270
+ },
1271
+ {
1272
+ "epoch": 0.6703703703703704,
1273
+ "grad_norm": 8.375,
1274
+ "learning_rate": 3.5673921611127115e-06,
1275
+ "loss": 0.557,
1276
+ "step": 362
1277
+ },
1278
+ {
1279
+ "epoch": 0.674074074074074,
1280
+ "grad_norm": 8.0625,
1281
+ "learning_rate": 3.5558514285870426e-06,
1282
+ "loss": 0.5442,
1283
+ "step": 364
1284
+ },
1285
+ {
1286
+ "epoch": 0.6777777777777778,
1287
+ "grad_norm": 8.0625,
1288
+ "learning_rate": 3.5442654684830982e-06,
1289
+ "loss": 0.5267,
1290
+ "step": 366
1291
+ },
1292
+ {
1293
+ "epoch": 0.6814814814814815,
1294
+ "grad_norm": 8.5,
1295
+ "learning_rate": 3.5326346980516022e-06,
1296
+ "loss": 0.5572,
1297
+ "step": 368
1298
+ },
1299
+ {
1300
+ "epoch": 0.6851851851851852,
1301
+ "grad_norm": 8.375,
1302
+ "learning_rate": 3.520959536157054e-06,
1303
+ "loss": 0.5482,
1304
+ "step": 370
1305
+ },
1306
+ {
1307
+ "epoch": 0.6888888888888889,
1308
+ "grad_norm": 8.4375,
1309
+ "learning_rate": 3.5092404032626437e-06,
1310
+ "loss": 0.5537,
1311
+ "step": 372
1312
+ },
1313
+ {
1314
+ "epoch": 0.6925925925925925,
1315
+ "grad_norm": 8.0625,
1316
+ "learning_rate": 3.4974777214151117e-06,
1317
+ "loss": 0.5388,
1318
+ "step": 374
1319
+ },
1320
+ {
1321
+ "epoch": 0.6962962962962963,
1322
+ "grad_norm": 8.5,
1323
+ "learning_rate": 3.4856719142295446e-06,
1324
+ "loss": 0.5352,
1325
+ "step": 376
1326
+ },
1327
+ {
1328
+ "epoch": 0.7,
1329
+ "grad_norm": 8.375,
1330
+ "learning_rate": 3.4738234068741254e-06,
1331
+ "loss": 0.5161,
1332
+ "step": 378
1333
+ },
1334
+ {
1335
+ "epoch": 0.7037037037037037,
1336
+ "grad_norm": 7.96875,
1337
+ "learning_rate": 3.4619326260548185e-06,
1338
+ "loss": 0.544,
1339
+ "step": 380
1340
+ },
1341
+ {
1342
+ "epoch": 0.7074074074074074,
1343
+ "grad_norm": 7.9375,
1344
+ "learning_rate": 3.45e-06,
1345
+ "loss": 0.5386,
1346
+ "step": 382
1347
+ },
1348
+ {
1349
+ "epoch": 0.7111111111111111,
1350
+ "grad_norm": 8.375,
1351
+ "learning_rate": 3.438025958445042e-06,
1352
+ "loss": 0.5254,
1353
+ "step": 384
1354
+ },
1355
+ {
1356
+ "epoch": 0.7148148148148148,
1357
+ "grad_norm": 8.375,
1358
+ "learning_rate": 3.4260109326168295e-06,
1359
+ "loss": 0.5373,
1360
+ "step": 386
1361
+ },
1362
+ {
1363
+ "epoch": 0.7185185185185186,
1364
+ "grad_norm": 8.0625,
1365
+ "learning_rate": 3.413955355218237e-06,
1366
+ "loss": 0.5188,
1367
+ "step": 388
1368
+ },
1369
+ {
1370
+ "epoch": 0.7222222222222222,
1371
+ "grad_norm": 8.0625,
1372
+ "learning_rate": 3.40185966041254e-06,
1373
+ "loss": 0.5286,
1374
+ "step": 390
1375
+ },
1376
+ {
1377
+ "epoch": 0.725925925925926,
1378
+ "grad_norm": 8.3125,
1379
+ "learning_rate": 3.3897242838077815e-06,
1380
+ "loss": 0.5281,
1381
+ "step": 392
1382
+ },
1383
+ {
1384
+ "epoch": 0.7296296296296296,
1385
+ "grad_norm": 8.5,
1386
+ "learning_rate": 3.3775496624410846e-06,
1387
+ "loss": 0.5568,
1388
+ "step": 394
1389
+ },
1390
+ {
1391
+ "epoch": 0.7333333333333333,
1392
+ "grad_norm": 7.90625,
1393
+ "learning_rate": 3.365336234762914e-06,
1394
+ "loss": 0.5025,
1395
+ "step": 396
1396
+ },
1397
+ {
1398
+ "epoch": 0.737037037037037,
1399
+ "grad_norm": 7.9375,
1400
+ "learning_rate": 3.3530844406212813e-06,
1401
+ "loss": 0.5306,
1402
+ "step": 398
1403
+ },
1404
+ {
1405
+ "epoch": 0.7407407407407407,
1406
+ "grad_norm": 8.125,
1407
+ "learning_rate": 3.340794721245911e-06,
1408
+ "loss": 0.5232,
1409
+ "step": 400
1410
+ },
1411
+ {
1412
+ "epoch": 0.7444444444444445,
1413
+ "grad_norm": 8.4375,
1414
+ "learning_rate": 3.3284675192323466e-06,
1415
+ "loss": 0.5402,
1416
+ "step": 402
1417
+ },
1418
+ {
1419
+ "epoch": 0.7481481481481481,
1420
+ "grad_norm": 8.625,
1421
+ "learning_rate": 3.3161032785260114e-06,
1422
+ "loss": 0.5587,
1423
+ "step": 404
1424
+ },
1425
+ {
1426
+ "epoch": 0.7518518518518519,
1427
+ "grad_norm": 7.875,
1428
+ "learning_rate": 3.30370244440622e-06,
1429
+ "loss": 0.5217,
1430
+ "step": 406
1431
+ },
1432
+ {
1433
+ "epoch": 0.7555555555555555,
1434
+ "grad_norm": 8.125,
1435
+ "learning_rate": 3.291265463470143e-06,
1436
+ "loss": 0.5097,
1437
+ "step": 408
1438
+ },
1439
+ {
1440
+ "epoch": 0.7592592592592593,
1441
+ "grad_norm": 7.90625,
1442
+ "learning_rate": 3.2787927836167273e-06,
1443
+ "loss": 0.5301,
1444
+ "step": 410
1445
+ },
1446
+ {
1447
+ "epoch": 0.762962962962963,
1448
+ "grad_norm": 7.875,
1449
+ "learning_rate": 3.2662848540305566e-06,
1450
+ "loss": 0.515,
1451
+ "step": 412
1452
+ },
1453
+ {
1454
+ "epoch": 0.7666666666666667,
1455
+ "grad_norm": 8.1875,
1456
+ "learning_rate": 3.253742125165684e-06,
1457
+ "loss": 0.5769,
1458
+ "step": 414
1459
+ },
1460
+ {
1461
+ "epoch": 0.7703703703703704,
1462
+ "grad_norm": 8.0625,
1463
+ "learning_rate": 3.241165048729404e-06,
1464
+ "loss": 0.5125,
1465
+ "step": 416
1466
+ },
1467
+ {
1468
+ "epoch": 0.774074074074074,
1469
+ "grad_norm": 7.96875,
1470
+ "learning_rate": 3.2285540776659865e-06,
1471
+ "loss": 0.5187,
1472
+ "step": 418
1473
+ },
1474
+ {
1475
+ "epoch": 0.7777777777777778,
1476
+ "grad_norm": 7.96875,
1477
+ "learning_rate": 3.215909666140367e-06,
1478
+ "loss": 0.5163,
1479
+ "step": 420
1480
+ },
1481
+ {
1482
+ "epoch": 0.7814814814814814,
1483
+ "grad_norm": 8.4375,
1484
+ "learning_rate": 3.2032322695217835e-06,
1485
+ "loss": 0.5378,
1486
+ "step": 422
1487
+ },
1488
+ {
1489
+ "epoch": 0.7851851851851852,
1490
+ "grad_norm": 8.1875,
1491
+ "learning_rate": 3.1905223443673878e-06,
1492
+ "loss": 0.5254,
1493
+ "step": 424
1494
+ },
1495
+ {
1496
+ "epoch": 0.7888888888888889,
1497
+ "grad_norm": 8.1875,
1498
+ "learning_rate": 3.1777803484057937e-06,
1499
+ "loss": 0.5277,
1500
+ "step": 426
1501
+ },
1502
+ {
1503
+ "epoch": 0.7925925925925926,
1504
+ "grad_norm": 7.90625,
1505
+ "learning_rate": 3.165006740520598e-06,
1506
+ "loss": 0.514,
1507
+ "step": 428
1508
+ },
1509
+ {
1510
+ "epoch": 0.7962962962962963,
1511
+ "grad_norm": 8.0625,
1512
+ "learning_rate": 3.1522019807338508e-06,
1513
+ "loss": 0.5231,
1514
+ "step": 430
1515
+ },
1516
+ {
1517
+ "epoch": 0.8,
1518
+ "grad_norm": 8.25,
1519
+ "learning_rate": 3.1393665301894926e-06,
1520
+ "loss": 0.5135,
1521
+ "step": 432
1522
+ },
1523
+ {
1524
+ "epoch": 0.8037037037037037,
1525
+ "grad_norm": 8.0,
1526
+ "learning_rate": 3.126500851136745e-06,
1527
+ "loss": 0.5319,
1528
+ "step": 434
1529
+ },
1530
+ {
1531
+ "epoch": 0.8074074074074075,
1532
+ "grad_norm": 8.0625,
1533
+ "learning_rate": 3.1136054069134607e-06,
1534
+ "loss": 0.53,
1535
+ "step": 436
1536
+ },
1537
+ {
1538
+ "epoch": 0.8111111111111111,
1539
+ "grad_norm": 8.5,
1540
+ "learning_rate": 3.1006806619294428e-06,
1541
+ "loss": 0.5229,
1542
+ "step": 438
1543
+ },
1544
+ {
1545
+ "epoch": 0.8148148148148148,
1546
+ "grad_norm": 8.5625,
1547
+ "learning_rate": 3.087727081649715e-06,
1548
+ "loss": 0.5429,
1549
+ "step": 440
1550
+ },
1551
+ {
1552
+ "epoch": 0.8185185185185185,
1553
+ "grad_norm": 8.0625,
1554
+ "learning_rate": 3.0747451325777605e-06,
1555
+ "loss": 0.5103,
1556
+ "step": 442
1557
+ },
1558
+ {
1559
+ "epoch": 0.8222222222222222,
1560
+ "grad_norm": 8.5625,
1561
+ "learning_rate": 3.061735282238722e-06,
1562
+ "loss": 0.5541,
1563
+ "step": 444
1564
+ },
1565
+ {
1566
+ "epoch": 0.825925925925926,
1567
+ "grad_norm": 7.90625,
1568
+ "learning_rate": 3.0486979991625627e-06,
1569
+ "loss": 0.5284,
1570
+ "step": 446
1571
+ },
1572
+ {
1573
+ "epoch": 0.8296296296296296,
1574
+ "grad_norm": 8.375,
1575
+ "learning_rate": 3.035633752867196e-06,
1576
+ "loss": 0.5209,
1577
+ "step": 448
1578
+ },
1579
+ {
1580
+ "epoch": 0.8333333333333334,
1581
+ "grad_norm": 8.375,
1582
+ "learning_rate": 3.022543013841572e-06,
1583
+ "loss": 0.53,
1584
+ "step": 450
1585
+ },
1586
+ {
1587
+ "epoch": 0.837037037037037,
1588
+ "grad_norm": 7.8125,
1589
+ "learning_rate": 3.0094262535287385e-06,
1590
+ "loss": 0.5104,
1591
+ "step": 452
1592
+ },
1593
+ {
1594
+ "epoch": 0.8407407407407408,
1595
+ "grad_norm": 7.78125,
1596
+ "learning_rate": 2.99628394430886e-06,
1597
+ "loss": 0.4987,
1598
+ "step": 454
1599
+ },
1600
+ {
1601
+ "epoch": 0.8444444444444444,
1602
+ "grad_norm": 7.875,
1603
+ "learning_rate": 2.9831165594822035e-06,
1604
+ "loss": 0.5181,
1605
+ "step": 456
1606
+ },
1607
+ {
1608
+ "epoch": 0.8481481481481481,
1609
+ "grad_norm": 7.90625,
1610
+ "learning_rate": 2.9699245732521005e-06,
1611
+ "loss": 0.5204,
1612
+ "step": 458
1613
+ },
1614
+ {
1615
+ "epoch": 0.8518518518518519,
1616
+ "grad_norm": 8.3125,
1617
+ "learning_rate": 2.95670846070786e-06,
1618
+ "loss": 0.5254,
1619
+ "step": 460
1620
+ },
1621
+ {
1622
+ "epoch": 0.8555555555555555,
1623
+ "grad_norm": 8.5,
1624
+ "learning_rate": 2.943468697807666e-06,
1625
+ "loss": 0.5233,
1626
+ "step": 462
1627
+ },
1628
+ {
1629
+ "epoch": 0.8592592592592593,
1630
+ "grad_norm": 8.25,
1631
+ "learning_rate": 2.930205761361434e-06,
1632
+ "loss": 0.5238,
1633
+ "step": 464
1634
+ },
1635
+ {
1636
+ "epoch": 0.8629629629629629,
1637
+ "grad_norm": 8.5,
1638
+ "learning_rate": 2.9169201290136377e-06,
1639
+ "loss": 0.5196,
1640
+ "step": 466
1641
+ },
1642
+ {
1643
+ "epoch": 0.8666666666666667,
1644
+ "grad_norm": 8.3125,
1645
+ "learning_rate": 2.903612279226112e-06,
1646
+ "loss": 0.5359,
1647
+ "step": 468
1648
+ },
1649
+ {
1650
+ "epoch": 0.8703703703703703,
1651
+ "grad_norm": 7.6875,
1652
+ "learning_rate": 2.8902826912608155e-06,
1653
+ "loss": 0.5168,
1654
+ "step": 470
1655
+ },
1656
+ {
1657
+ "epoch": 0.8740740740740741,
1658
+ "grad_norm": 8.0625,
1659
+ "learning_rate": 2.8769318451625792e-06,
1660
+ "loss": 0.5393,
1661
+ "step": 472
1662
+ },
1663
+ {
1664
+ "epoch": 0.8777777777777778,
1665
+ "grad_norm": 7.75,
1666
+ "learning_rate": 2.8635602217418073e-06,
1667
+ "loss": 0.5155,
1668
+ "step": 474
1669
+ },
1670
+ {
1671
+ "epoch": 0.8814814814814815,
1672
+ "grad_norm": 7.75,
1673
+ "learning_rate": 2.850168302557173e-06,
1674
+ "loss": 0.4892,
1675
+ "step": 476
1676
+ },
1677
+ {
1678
+ "epoch": 0.8851851851851852,
1679
+ "grad_norm": 7.8125,
1680
+ "learning_rate": 2.8367565698982674e-06,
1681
+ "loss": 0.5184,
1682
+ "step": 478
1683
+ },
1684
+ {
1685
+ "epoch": 0.8888888888888888,
1686
+ "grad_norm": 8.4375,
1687
+ "learning_rate": 2.8233255067682357e-06,
1688
+ "loss": 0.526,
1689
+ "step": 480
1690
+ },
1691
+ {
1692
+ "epoch": 0.8925925925925926,
1693
+ "grad_norm": 8.4375,
1694
+ "learning_rate": 2.8098755968663775e-06,
1695
+ "loss": 0.5202,
1696
+ "step": 482
1697
+ },
1698
+ {
1699
+ "epoch": 0.8962962962962963,
1700
+ "grad_norm": 8.25,
1701
+ "learning_rate": 2.7964073245707345e-06,
1702
+ "loss": 0.5124,
1703
+ "step": 484
1704
+ },
1705
+ {
1706
+ "epoch": 0.9,
1707
+ "grad_norm": 8.375,
1708
+ "learning_rate": 2.7829211749206393e-06,
1709
+ "loss": 0.5341,
1710
+ "step": 486
1711
+ },
1712
+ {
1713
+ "epoch": 0.9037037037037037,
1714
+ "grad_norm": 8.25,
1715
+ "learning_rate": 2.76941763359925e-06,
1716
+ "loss": 0.5118,
1717
+ "step": 488
1718
+ },
1719
+ {
1720
+ "epoch": 0.9074074074074074,
1721
+ "grad_norm": 8.3125,
1722
+ "learning_rate": 2.7558971869160605e-06,
1723
+ "loss": 0.5252,
1724
+ "step": 490
1725
+ },
1726
+ {
1727
+ "epoch": 0.9111111111111111,
1728
+ "grad_norm": 7.6875,
1729
+ "learning_rate": 2.7423603217893853e-06,
1730
+ "loss": 0.5061,
1731
+ "step": 492
1732
+ },
1733
+ {
1734
+ "epoch": 0.9148148148148149,
1735
+ "grad_norm": 8.375,
1736
+ "learning_rate": 2.7288075257288237e-06,
1737
+ "loss": 0.5002,
1738
+ "step": 494
1739
+ },
1740
+ {
1741
+ "epoch": 0.9185185185185185,
1742
+ "grad_norm": 8.5625,
1743
+ "learning_rate": 2.7152392868177043e-06,
1744
+ "loss": 0.542,
1745
+ "step": 496
1746
+ },
1747
+ {
1748
+ "epoch": 0.9222222222222223,
1749
+ "grad_norm": 7.78125,
1750
+ "learning_rate": 2.7016560936955053e-06,
1751
+ "loss": 0.5133,
1752
+ "step": 498
1753
+ },
1754
+ {
1755
+ "epoch": 0.9259259259259259,
1756
+ "grad_norm": 8.0,
1757
+ "learning_rate": 2.6880584355402586e-06,
1758
+ "loss": 0.524,
1759
+ "step": 500
1760
+ },
1761
+ {
1762
+ "epoch": 0.9296296296296296,
1763
+ "grad_norm": 7.8125,
1764
+ "learning_rate": 2.6744468020509324e-06,
1765
+ "loss": 0.5031,
1766
+ "step": 502
1767
+ },
1768
+ {
1769
+ "epoch": 0.9333333333333333,
1770
+ "grad_norm": 8.375,
1771
+ "learning_rate": 2.6608216834297947e-06,
1772
+ "loss": 0.5137,
1773
+ "step": 504
1774
+ },
1775
+ {
1776
+ "epoch": 0.937037037037037,
1777
+ "grad_norm": 7.8125,
1778
+ "learning_rate": 2.647183570364761e-06,
1779
+ "loss": 0.5095,
1780
+ "step": 506
1781
+ },
1782
+ {
1783
+ "epoch": 0.9407407407407408,
1784
+ "grad_norm": 8.25,
1785
+ "learning_rate": 2.633532954011721e-06,
1786
+ "loss": 0.5195,
1787
+ "step": 508
1788
+ },
1789
+ {
1790
+ "epoch": 0.9444444444444444,
1791
+ "grad_norm": 8.375,
1792
+ "learning_rate": 2.6198703259768517e-06,
1793
+ "loss": 0.5133,
1794
+ "step": 510
1795
+ },
1796
+ {
1797
+ "epoch": 0.9481481481481482,
1798
+ "grad_norm": 7.84375,
1799
+ "learning_rate": 2.606196178298913e-06,
1800
+ "loss": 0.4951,
1801
+ "step": 512
1802
+ },
1803
+ {
1804
+ "epoch": 0.9518518518518518,
1805
+ "grad_norm": 8.5,
1806
+ "learning_rate": 2.592511003431526e-06,
1807
+ "loss": 0.5214,
1808
+ "step": 514
1809
+ },
1810
+ {
1811
+ "epoch": 0.9555555555555556,
1812
+ "grad_norm": 8.5,
1813
+ "learning_rate": 2.5788152942254395e-06,
1814
+ "loss": 0.5309,
1815
+ "step": 516
1816
+ },
1817
+ {
1818
+ "epoch": 0.9592592592592593,
1819
+ "grad_norm": 7.78125,
1820
+ "learning_rate": 2.5651095439107826e-06,
1821
+ "loss": 0.5009,
1822
+ "step": 518
1823
+ },
1824
+ {
1825
+ "epoch": 0.9629629629629629,
1826
+ "grad_norm": 8.375,
1827
+ "learning_rate": 2.5513942460792966e-06,
1828
+ "loss": 0.503,
1829
+ "step": 520
1830
+ },
1831
+ {
1832
+ "epoch": 0.9666666666666667,
1833
+ "grad_norm": 8.25,
1834
+ "learning_rate": 2.5376698946665634e-06,
1835
+ "loss": 0.5223,
1836
+ "step": 522
1837
+ },
1838
+ {
1839
+ "epoch": 0.9703703703703703,
1840
+ "grad_norm": 8.4375,
1841
+ "learning_rate": 2.523936983934217e-06,
1842
+ "loss": 0.5341,
1843
+ "step": 524
1844
+ },
1845
+ {
1846
+ "epoch": 0.9740740740740741,
1847
+ "grad_norm": 8.375,
1848
+ "learning_rate": 2.5101960084521407e-06,
1849
+ "loss": 0.5507,
1850
+ "step": 526
1851
+ },
1852
+ {
1853
+ "epoch": 0.9777777777777777,
1854
+ "grad_norm": 8.3125,
1855
+ "learning_rate": 2.4964474630806573e-06,
1856
+ "loss": 0.5107,
1857
+ "step": 528
1858
+ },
1859
+ {
1860
+ "epoch": 0.9814814814814815,
1861
+ "grad_norm": 8.25,
1862
+ "learning_rate": 2.482691842952709e-06,
1863
+ "loss": 0.5035,
1864
+ "step": 530
1865
+ },
1866
+ {
1867
+ "epoch": 0.9851851851851852,
1868
+ "grad_norm": 8.5,
1869
+ "learning_rate": 2.468929643456024e-06,
1870
+ "loss": 0.5083,
1871
+ "step": 532
1872
+ },
1873
+ {
1874
+ "epoch": 0.9888888888888889,
1875
+ "grad_norm": 8.25,
1876
+ "learning_rate": 2.4551613602152758e-06,
1877
+ "loss": 0.5121,
1878
+ "step": 534
1879
+ },
1880
+ {
1881
+ "epoch": 0.9925925925925926,
1882
+ "grad_norm": 8.3125,
1883
+ "learning_rate": 2.4413874890742364e-06,
1884
+ "loss": 0.535,
1885
+ "step": 536
1886
+ },
1887
+ {
1888
+ "epoch": 0.9962962962962963,
1889
+ "grad_norm": 8.1875,
1890
+ "learning_rate": 2.427608526077915e-06,
1891
+ "loss": 0.5184,
1892
+ "step": 538
1893
+ },
1894
+ {
1895
+ "epoch": 1.0,
1896
+ "grad_norm": 7.6875,
1897
+ "learning_rate": 2.413824967454698e-06,
1898
+ "loss": 0.4873,
1899
+ "step": 540
1900
+ }
1901
+ ],
1902
+ "logging_steps": 2,
1903
+ "max_steps": 1080,
1904
+ "num_input_tokens_seen": 0,
1905
+ "num_train_epochs": 2,
1906
+ "save_steps": 540,
1907
+ "stateful_callbacks": {
1908
+ "TrainerControl": {
1909
+ "args": {
1910
+ "should_epoch_stop": false,
1911
+ "should_evaluate": false,
1912
+ "should_log": false,
1913
+ "should_save": true,
1914
+ "should_training_stop": false
1915
+ },
1916
+ "attributes": {}
1917
+ }
1918
+ },
1919
+ "total_flos": 8.66563154509824e+16,
1920
+ "train_batch_size": 1,
1921
+ "trial_name": null,
1922
+ "trial_params": null
1923
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ceda14221168e4fb77e9aea4392d1633c8c539de803e81e9912a66ddc7f917
3
+ size 5688