weizhi.wang commited on
Commit
1e7c7fb
1 Parent(s): 80f96df

First model version

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/bn/datacompv6/weizhi_multimodal/models/vicuna-13b-v1.5",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "freeze_mm_mlp_adapter": false,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "image_aspect_ratio": "pad",
12
+ "image_grid_pinpoints": null,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 13824,
15
+ "max_length": 4096,
16
+ "max_position_embeddings": 4096,
17
+ "mm_hidden_size": 1024,
18
+ "mm_projector_type": "mlp2x_gelu",
19
+ "mm_use_im_patch_token": false,
20
+ "mm_use_im_start_end": false,
21
+ "mm_vision_select_feature": "patch",
22
+ "mm_vision_select_layer": -2,
23
+ "mm_vision_tower": "/mnt/bn/datacompv6/weizhi_multimodal/models/clip-vit-large-patch14-336",
24
+ "model_type": "llava",
25
+ "num_attention_heads": 40,
26
+ "num_hidden_layers": 40,
27
+ "num_key_value_heads": 40,
28
+ "pad_token_id": 0,
29
+ "pretraining_tp": 1,
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_scaling": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.31.0",
35
+ "tune_mm_mlp_adapter": false,
36
+ "use_cache": true,
37
+ "use_mm_proj": true,
38
+ "vocab_size": 32000
39
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.9,
8
+ "top_p": 0.6,
9
+ "transformers_version": "4.31.0"
10
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044f75614c3efeaa09b6cad962966767dcc764b8fe5da2c94b09afb77ce4f876
3
+ size 9948726510
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48e52d38e8e768f3452d3007d7752f4107d4515c90c9277d63e10478fadad61b
3
+ size 9904162976
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89d61b08b68239baea9ed6dd4e5caecb839204b7d810281b62ae1b93655cab1d
3
+ size 6849082169
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,805 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26701683712
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
358
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
359
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
360
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
361
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
362
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
363
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
364
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
365
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
367
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
368
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
369
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
370
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
371
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
372
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
373
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
374
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
375
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
377
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
378
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
379
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
380
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
381
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
382
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
383
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
384
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
385
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
387
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
388
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
389
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
390
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
391
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
392
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
393
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
394
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
395
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
397
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
398
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
399
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
400
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
401
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
402
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
403
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
404
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
405
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
407
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
408
+ "model.mm_projector.0.bias": "pytorch_model-00003-of-00003.bin",
409
+ "model.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin",
410
+ "model.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin",
411
+ "model.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin",
412
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin",
413
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin",
414
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin",
415
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
760
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
761
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
762
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
763
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
764
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
765
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
766
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
767
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
768
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
769
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
770
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
771
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
772
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
773
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
774
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
775
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
776
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
777
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
778
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
779
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
780
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
781
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
782
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
783
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
784
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
785
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
786
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
787
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
788
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
789
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
790
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
791
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
792
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
793
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
794
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
795
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
796
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
797
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
798
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
799
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
800
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin",
801
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin",
802
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin",
803
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin"
804
+ }
805
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 2048,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
@@ -0,0 +1,4717 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 782,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 8.333333333333333e-07,
13
+ "loss": 1.4219,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 1.6666666666666667e-06,
19
+ "loss": 1.3867,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 2.5e-06,
25
+ "loss": 1.3779,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 3.3333333333333333e-06,
31
+ "loss": 1.3799,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 4.166666666666667e-06,
37
+ "loss": 1.3516,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "learning_rate": 5e-06,
43
+ "loss": 1.292,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.02,
48
+ "learning_rate": 5.833333333333334e-06,
49
+ "loss": 1.252,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.02,
54
+ "learning_rate": 6.666666666666667e-06,
55
+ "loss": 1.2471,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.02,
60
+ "learning_rate": 7.500000000000001e-06,
61
+ "loss": 1.1914,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.03,
66
+ "learning_rate": 8.333333333333334e-06,
67
+ "loss": 1.1621,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.03,
72
+ "learning_rate": 9.166666666666666e-06,
73
+ "loss": 0.2146,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.03,
78
+ "learning_rate": 1e-05,
79
+ "loss": 1.1699,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.03,
84
+ "learning_rate": 1.0833333333333334e-05,
85
+ "loss": 0.238,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.04,
90
+ "learning_rate": 1.1666666666666668e-05,
91
+ "loss": 1.1445,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.04,
96
+ "learning_rate": 1.25e-05,
97
+ "loss": 1.1455,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.04,
102
+ "learning_rate": 1.3333333333333333e-05,
103
+ "loss": 1.1602,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.04,
108
+ "learning_rate": 1.416666666666667e-05,
109
+ "loss": 1.1348,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.05,
114
+ "learning_rate": 1.5000000000000002e-05,
115
+ "loss": 1.1416,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.05,
120
+ "learning_rate": 1.5833333333333333e-05,
121
+ "loss": 0.2249,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.05,
126
+ "learning_rate": 1.6666666666666667e-05,
127
+ "loss": 1.1328,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.05,
132
+ "learning_rate": 1.7500000000000002e-05,
133
+ "loss": 1.1143,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.06,
138
+ "learning_rate": 1.8333333333333333e-05,
139
+ "loss": 1.0884,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.06,
144
+ "learning_rate": 1.916666666666667e-05,
145
+ "loss": 0.2401,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.06,
150
+ "learning_rate": 2e-05,
151
+ "loss": 0.2283,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.06,
156
+ "learning_rate": 1.9999914112350643e-05,
157
+ "loss": 0.2246,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.07,
162
+ "learning_rate": 1.999965645087791e-05,
163
+ "loss": 1.0859,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.07,
168
+ "learning_rate": 1.9999227020007783e-05,
169
+ "loss": 1.0659,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.07,
174
+ "learning_rate": 1.9998625827116828e-05,
175
+ "loss": 1.125,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.07,
180
+ "learning_rate": 1.9997852882532053e-05,
181
+ "loss": 1.0503,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.08,
186
+ "learning_rate": 1.9996908199530737e-05,
187
+ "loss": 1.1279,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.08,
192
+ "learning_rate": 1.99957917943402e-05,
193
+ "loss": 1.0918,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.08,
198
+ "learning_rate": 1.9994503686137526e-05,
199
+ "loss": 1.0635,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.08,
204
+ "learning_rate": 1.999304389704923e-05,
205
+ "loss": 1.0664,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.09,
210
+ "learning_rate": 1.999141245215089e-05,
211
+ "loss": 0.2412,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.09,
216
+ "learning_rate": 1.9989609379466688e-05,
217
+ "loss": 1.0898,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.09,
222
+ "learning_rate": 1.998763470996897e-05,
223
+ "loss": 1.0425,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.09,
228
+ "learning_rate": 1.998548847757767e-05,
229
+ "loss": 1.0645,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.1,
234
+ "learning_rate": 1.998317071915977e-05,
235
+ "loss": 1.1016,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.1,
240
+ "learning_rate": 1.9980681474528624e-05,
241
+ "loss": 1.0645,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.1,
246
+ "learning_rate": 1.9978020786443314e-05,
247
+ "loss": 1.0908,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.1,
252
+ "learning_rate": 1.9975188700607885e-05,
253
+ "loss": 1.0361,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.11,
258
+ "learning_rate": 1.9972185265670573e-05,
259
+ "loss": 1.0918,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.11,
264
+ "learning_rate": 1.996901053322298e-05,
265
+ "loss": 1.0322,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.11,
270
+ "learning_rate": 1.9965664557799164e-05,
271
+ "loss": 1.0391,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.12,
276
+ "learning_rate": 1.996214739687471e-05,
277
+ "loss": 1.1465,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.12,
282
+ "learning_rate": 1.9958459110865767e-05,
283
+ "loss": 1.0503,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.12,
288
+ "learning_rate": 1.995459976312797e-05,
289
+ "loss": 1.0503,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.12,
294
+ "learning_rate": 1.995056941995538e-05,
295
+ "loss": 1.0981,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.13,
300
+ "learning_rate": 1.9946368150579343e-05,
301
+ "loss": 1.0264,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.13,
306
+ "learning_rate": 1.9941996027167286e-05,
307
+ "loss": 1.0332,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.13,
312
+ "learning_rate": 1.9937453124821487e-05,
313
+ "loss": 1.0415,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.13,
318
+ "learning_rate": 1.993273952157779e-05,
319
+ "loss": 1.0654,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.14,
324
+ "learning_rate": 1.9927855298404255e-05,
325
+ "loss": 1.0869,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.14,
330
+ "learning_rate": 1.992280053919977e-05,
331
+ "loss": 1.0278,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.14,
336
+ "learning_rate": 1.9917575330792616e-05,
337
+ "loss": 1.0078,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.14,
342
+ "learning_rate": 1.9912179762938962e-05,
343
+ "loss": 1.0771,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.15,
348
+ "learning_rate": 1.990661392832134e-05,
349
+ "loss": 0.2173,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.15,
354
+ "learning_rate": 1.9900877922547034e-05,
355
+ "loss": 0.2571,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.15,
360
+ "learning_rate": 1.989497184414646e-05,
361
+ "loss": 1.0537,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.15,
366
+ "learning_rate": 1.988889579457146e-05,
367
+ "loss": 1.0488,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.16,
372
+ "learning_rate": 1.9882649878193544e-05,
373
+ "loss": 1.0049,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.16,
378
+ "learning_rate": 1.987623420230214e-05,
379
+ "loss": 1.0474,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.16,
384
+ "learning_rate": 1.9869648877102707e-05,
385
+ "loss": 0.2599,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.16,
390
+ "learning_rate": 1.9862894015714866e-05,
391
+ "loss": 1.0967,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.17,
396
+ "learning_rate": 1.9855969734170448e-05,
397
+ "loss": 0.2701,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.17,
402
+ "learning_rate": 1.984887615141151e-05,
403
+ "loss": 1.0581,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.17,
408
+ "learning_rate": 1.9841613389288278e-05,
409
+ "loss": 0.2275,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.17,
414
+ "learning_rate": 1.9834181572557066e-05,
415
+ "loss": 1.0239,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.18,
420
+ "learning_rate": 1.9826580828878134e-05,
421
+ "loss": 1.021,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.18,
426
+ "learning_rate": 1.9818811288813475e-05,
427
+ "loss": 1.0571,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.18,
432
+ "learning_rate": 1.9810873085824604e-05,
433
+ "loss": 1.0356,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.18,
438
+ "learning_rate": 1.9802766356270226e-05,
439
+ "loss": 0.2253,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.19,
444
+ "learning_rate": 1.9794491239403946e-05,
445
+ "loss": 1.0308,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.19,
450
+ "learning_rate": 1.9786047877371823e-05,
451
+ "loss": 1.0127,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.19,
456
+ "learning_rate": 1.977743641520996e-05,
457
+ "loss": 1.0366,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.19,
462
+ "learning_rate": 1.976865700084201e-05,
463
+ "loss": 1.0146,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.2,
468
+ "learning_rate": 1.9759709785076622e-05,
469
+ "loss": 1.0229,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.2,
474
+ "learning_rate": 1.975059492160486e-05,
475
+ "loss": 1.0435,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.2,
480
+ "learning_rate": 1.9741312566997573e-05,
481
+ "loss": 1.0171,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.2,
486
+ "learning_rate": 1.9731862880702676e-05,
487
+ "loss": 1.0635,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.21,
492
+ "learning_rate": 1.972224602504244e-05,
493
+ "loss": 1.043,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.21,
498
+ "learning_rate": 1.9712462165210687e-05,
499
+ "loss": 1.0703,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.21,
504
+ "learning_rate": 1.9702511469269964e-05,
505
+ "loss": 1.0459,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.21,
510
+ "learning_rate": 1.969239410814865e-05,
511
+ "loss": 1.0405,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.22,
516
+ "learning_rate": 1.968211025563802e-05,
517
+ "loss": 1.0078,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.22,
522
+ "learning_rate": 1.967166008838925e-05,
523
+ "loss": 1.0068,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.22,
528
+ "learning_rate": 1.9661043785910404e-05,
529
+ "loss": 0.9854,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.23,
534
+ "learning_rate": 1.9650261530563336e-05,
535
+ "loss": 1.0029,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.23,
540
+ "learning_rate": 1.963931350756056e-05,
541
+ "loss": 1.0249,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.23,
546
+ "learning_rate": 1.9628199904962063e-05,
547
+ "loss": 0.2308,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.23,
552
+ "learning_rate": 1.9616920913672092e-05,
553
+ "loss": 1.0059,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.24,
558
+ "learning_rate": 1.9605476727435854e-05,
559
+ "loss": 1.0571,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.24,
564
+ "learning_rate": 1.9593867542836198e-05,
565
+ "loss": 1.0273,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.24,
570
+ "learning_rate": 1.9582093559290242e-05,
571
+ "loss": 1.0059,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.24,
576
+ "learning_rate": 1.9570154979045938e-05,
577
+ "loss": 1.0508,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.25,
582
+ "learning_rate": 1.9558052007178608e-05,
583
+ "loss": 0.9868,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.25,
588
+ "learning_rate": 1.954578485158741e-05,
589
+ "loss": 1.0259,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.25,
594
+ "learning_rate": 1.9533353722991775e-05,
595
+ "loss": 0.2211,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.25,
600
+ "learning_rate": 1.952075883492779e-05,
601
+ "loss": 1.0186,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.26,
606
+ "learning_rate": 1.9508000403744516e-05,
607
+ "loss": 1.04,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.26,
612
+ "learning_rate": 1.9495078648600286e-05,
613
+ "loss": 1.0645,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.26,
618
+ "learning_rate": 1.948199379145894e-05,
619
+ "loss": 0.2211,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.26,
624
+ "learning_rate": 1.9468746057086e-05,
625
+ "loss": 1.0908,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.27,
630
+ "learning_rate": 1.9455335673044817e-05,
631
+ "loss": 0.9873,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.27,
636
+ "learning_rate": 1.9441762869692664e-05,
637
+ "loss": 1.0615,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.27,
642
+ "learning_rate": 1.9428027880176775e-05,
643
+ "loss": 0.2557,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.27,
648
+ "learning_rate": 1.9414130940430347e-05,
649
+ "loss": 1.0874,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.28,
654
+ "learning_rate": 1.9400072289168474e-05,
655
+ "loss": 1.0845,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.28,
660
+ "learning_rate": 1.9385852167884057e-05,
661
+ "loss": 0.223,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.28,
666
+ "learning_rate": 1.937147082084366e-05,
667
+ "loss": 1.0464,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.28,
672
+ "learning_rate": 1.9356928495083295e-05,
673
+ "loss": 1.0068,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.29,
678
+ "learning_rate": 1.93422254404042e-05,
679
+ "loss": 1.0161,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.29,
684
+ "learning_rate": 1.9327361909368535e-05,
685
+ "loss": 1.0063,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.29,
690
+ "learning_rate": 1.931233815729505e-05,
691
+ "loss": 1.0117,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.29,
696
+ "learning_rate": 1.9297154442254692e-05,
697
+ "loss": 1.0371,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.3,
702
+ "learning_rate": 1.9281811025066184e-05,
703
+ "loss": 1.0044,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.3,
708
+ "learning_rate": 1.9266308169291533e-05,
709
+ "loss": 0.215,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.3,
714
+ "learning_rate": 1.9250646141231503e-05,
715
+ "loss": 1.0103,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.3,
720
+ "learning_rate": 1.9234825209921045e-05,
721
+ "loss": 0.2108,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.31,
726
+ "learning_rate": 1.921884564712469e-05,
727
+ "loss": 1.0479,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.31,
732
+ "learning_rate": 1.920270772733185e-05,
733
+ "loss": 1.084,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.31,
738
+ "learning_rate": 1.9186411727752124e-05,
739
+ "loss": 1.0229,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.31,
744
+ "learning_rate": 1.9169957928310533e-05,
745
+ "loss": 1.0728,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.32,
750
+ "learning_rate": 1.9153346611642706e-05,
751
+ "loss": 1.0684,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.32,
756
+ "learning_rate": 1.9136578063090035e-05,
757
+ "loss": 1.0376,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.32,
762
+ "learning_rate": 1.911965257069476e-05,
763
+ "loss": 1.0679,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.32,
768
+ "learning_rate": 1.9102570425195032e-05,
769
+ "loss": 1.0337,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.33,
774
+ "learning_rate": 1.908533192001992e-05,
775
+ "loss": 0.9604,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.33,
780
+ "learning_rate": 1.9067937351284355e-05,
781
+ "loss": 1.0098,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.33,
786
+ "learning_rate": 1.9050387017784067e-05,
787
+ "loss": 1.0693,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.34,
792
+ "learning_rate": 1.903268122099043e-05,
793
+ "loss": 0.27,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.34,
798
+ "learning_rate": 1.9014820265045304e-05,
799
+ "loss": 0.2208,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.34,
804
+ "learning_rate": 1.8996804456755783e-05,
805
+ "loss": 1.0479,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.34,
810
+ "learning_rate": 1.8978634105588963e-05,
811
+ "loss": 1.0605,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.35,
816
+ "learning_rate": 1.8960309523666583e-05,
817
+ "loss": 0.2468,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.35,
822
+ "learning_rate": 1.8941831025759705e-05,
823
+ "loss": 0.981,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.35,
828
+ "learning_rate": 1.8923198929283275e-05,
829
+ "loss": 1.0239,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.35,
834
+ "learning_rate": 1.8904413554290687e-05,
835
+ "loss": 1.0762,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.36,
840
+ "learning_rate": 1.888547522346828e-05,
841
+ "loss": 1.0532,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 0.36,
846
+ "learning_rate": 1.88663842621298e-05,
847
+ "loss": 1.0293,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 0.36,
852
+ "learning_rate": 1.8847140998210806e-05,
853
+ "loss": 0.2148,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 0.36,
858
+ "learning_rate": 1.8827745762263038e-05,
859
+ "loss": 1.0146,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 0.37,
864
+ "learning_rate": 1.8808198887448737e-05,
865
+ "loss": 0.9946,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 0.37,
870
+ "learning_rate": 1.8788500709534934e-05,
871
+ "loss": 1.0132,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 0.37,
876
+ "learning_rate": 1.8768651566887667e-05,
877
+ "loss": 1.0547,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 0.37,
882
+ "learning_rate": 1.8748651800466174e-05,
883
+ "loss": 0.2177,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 0.38,
888
+ "learning_rate": 1.8728501753817044e-05,
889
+ "loss": 1.0337,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 0.38,
894
+ "learning_rate": 1.8708201773068303e-05,
895
+ "loss": 0.2139,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 0.38,
900
+ "learning_rate": 1.868775220692348e-05,
901
+ "loss": 1.0161,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 0.38,
906
+ "learning_rate": 1.8667153406655606e-05,
907
+ "loss": 1.0059,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 0.39,
912
+ "learning_rate": 1.864640572610118e-05,
913
+ "loss": 0.2317,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 0.39,
918
+ "learning_rate": 1.8625509521654122e-05,
919
+ "loss": 1.0415,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 0.39,
924
+ "learning_rate": 1.8604465152259595e-05,
925
+ "loss": 1.0391,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 0.39,
930
+ "learning_rate": 1.8583272979407885e-05,
931
+ "loss": 0.2306,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 0.4,
936
+ "learning_rate": 1.8561933367128175e-05,
937
+ "loss": 1.0327,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 0.4,
942
+ "learning_rate": 1.8540446681982295e-05,
943
+ "loss": 0.2053,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 0.4,
948
+ "learning_rate": 1.851881329305842e-05,
949
+ "loss": 1.0537,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 0.4,
954
+ "learning_rate": 1.849703357196473e-05,
955
+ "loss": 1.0469,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 0.41,
960
+ "learning_rate": 1.8475107892823038e-05,
961
+ "loss": 1.0034,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 0.41,
966
+ "learning_rate": 1.8453036632262352e-05,
967
+ "loss": 0.2062,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 0.41,
972
+ "learning_rate": 1.8430820169412415e-05,
973
+ "loss": 0.9941,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 0.41,
978
+ "learning_rate": 1.840845888589717e-05,
979
+ "loss": 0.9917,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 0.42,
984
+ "learning_rate": 1.8385953165828242e-05,
985
+ "loss": 1.0356,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 0.42,
990
+ "learning_rate": 1.8363303395798305e-05,
991
+ "loss": 1.0083,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 0.42,
996
+ "learning_rate": 1.834050996487446e-05,
997
+ "loss": 1.04,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 0.42,
1002
+ "learning_rate": 1.8317573264591553e-05,
1003
+ "loss": 1.0405,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 0.43,
1008
+ "learning_rate": 1.8294493688945435e-05,
1009
+ "loss": 1.0317,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 0.43,
1014
+ "learning_rate": 1.82712716343862e-05,
1015
+ "loss": 0.2234,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 0.43,
1020
+ "learning_rate": 1.8247907499811395e-05,
1021
+ "loss": 1.04,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 0.43,
1026
+ "learning_rate": 1.822440168655913e-05,
1027
+ "loss": 0.9971,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 0.44,
1032
+ "learning_rate": 1.8200754598401223e-05,
1033
+ "loss": 1.0503,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 0.44,
1038
+ "learning_rate": 1.8176966641536228e-05,
1039
+ "loss": 1.0439,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 0.44,
1044
+ "learning_rate": 1.8153038224582493e-05,
1045
+ "loss": 1.042,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 0.45,
1050
+ "learning_rate": 1.812896975857111e-05,
1051
+ "loss": 0.957,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 0.45,
1056
+ "learning_rate": 1.8104761656938872e-05,
1057
+ "loss": 0.2432,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 0.45,
1062
+ "learning_rate": 1.8080414335521174e-05,
1063
+ "loss": 1.0161,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 0.45,
1068
+ "learning_rate": 1.805592821254485e-05,
1069
+ "loss": 0.9922,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 0.46,
1074
+ "learning_rate": 1.803130370862101e-05,
1075
+ "loss": 1.0474,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 0.46,
1080
+ "learning_rate": 1.800654124673781e-05,
1081
+ "loss": 1.0347,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 0.46,
1086
+ "learning_rate": 1.798164125225318e-05,
1087
+ "loss": 1.0161,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 0.46,
1092
+ "learning_rate": 1.795660415288751e-05,
1093
+ "loss": 0.2272,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 0.47,
1098
+ "learning_rate": 1.793143037871633e-05,
1099
+ "loss": 0.2137,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 0.47,
1104
+ "learning_rate": 1.7906120362162895e-05,
1105
+ "loss": 1.0532,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 0.47,
1110
+ "learning_rate": 1.788067453799077e-05,
1111
+ "loss": 1.0166,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 0.47,
1116
+ "learning_rate": 1.785509334329636e-05,
1117
+ "loss": 1.0591,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 0.48,
1122
+ "learning_rate": 1.78293772175014e-05,
1123
+ "loss": 0.9902,
1124
+ "step": 186
1125
+ },
1126
+ {
1127
+ "epoch": 0.48,
1128
+ "learning_rate": 1.7803526602345415e-05,
1129
+ "loss": 0.2466,
1130
+ "step": 187
1131
+ },
1132
+ {
1133
+ "epoch": 0.48,
1134
+ "learning_rate": 1.7777541941878116e-05,
1135
+ "loss": 0.2354,
1136
+ "step": 188
1137
+ },
1138
+ {
1139
+ "epoch": 0.48,
1140
+ "learning_rate": 1.775142368245178e-05,
1141
+ "loss": 1.0044,
1142
+ "step": 189
1143
+ },
1144
+ {
1145
+ "epoch": 0.49,
1146
+ "learning_rate": 1.772517227271359e-05,
1147
+ "loss": 0.9844,
1148
+ "step": 190
1149
+ },
1150
+ {
1151
+ "epoch": 0.49,
1152
+ "learning_rate": 1.7698788163597923e-05,
1153
+ "loss": 1.0078,
1154
+ "step": 191
1155
+ },
1156
+ {
1157
+ "epoch": 0.49,
1158
+ "learning_rate": 1.7672271808318603e-05,
1159
+ "loss": 1.0312,
1160
+ "step": 192
1161
+ },
1162
+ {
1163
+ "epoch": 0.49,
1164
+ "learning_rate": 1.7645623662361112e-05,
1165
+ "loss": 0.2213,
1166
+ "step": 193
1167
+ },
1168
+ {
1169
+ "epoch": 0.5,
1170
+ "learning_rate": 1.7618844183474775e-05,
1171
+ "loss": 0.2122,
1172
+ "step": 194
1173
+ },
1174
+ {
1175
+ "epoch": 0.5,
1176
+ "learning_rate": 1.7591933831664887e-05,
1177
+ "loss": 1.0063,
1178
+ "step": 195
1179
+ },
1180
+ {
1181
+ "epoch": 0.5,
1182
+ "learning_rate": 1.7564893069184824e-05,
1183
+ "loss": 1.0625,
1184
+ "step": 196
1185
+ },
1186
+ {
1187
+ "epoch": 0.5,
1188
+ "learning_rate": 1.753772236052809e-05,
1189
+ "loss": 1.0342,
1190
+ "step": 197
1191
+ },
1192
+ {
1193
+ "epoch": 0.51,
1194
+ "learning_rate": 1.7510422172420344e-05,
1195
+ "loss": 0.9951,
1196
+ "step": 198
1197
+ },
1198
+ {
1199
+ "epoch": 0.51,
1200
+ "learning_rate": 1.7482992973811384e-05,
1201
+ "loss": 1.0166,
1202
+ "step": 199
1203
+ },
1204
+ {
1205
+ "epoch": 0.51,
1206
+ "learning_rate": 1.745543523586709e-05,
1207
+ "loss": 1.0083,
1208
+ "step": 200
1209
+ },
1210
+ {
1211
+ "epoch": 0.51,
1212
+ "learning_rate": 1.7427749431961324e-05,
1213
+ "loss": 1.019,
1214
+ "step": 201
1215
+ },
1216
+ {
1217
+ "epoch": 0.52,
1218
+ "learning_rate": 1.7399936037667807e-05,
1219
+ "loss": 1.0225,
1220
+ "step": 202
1221
+ },
1222
+ {
1223
+ "epoch": 0.52,
1224
+ "learning_rate": 1.737199553075196e-05,
1225
+ "loss": 1.0249,
1226
+ "step": 203
1227
+ },
1228
+ {
1229
+ "epoch": 0.52,
1230
+ "learning_rate": 1.7343928391162673e-05,
1231
+ "loss": 0.9858,
1232
+ "step": 204
1233
+ },
1234
+ {
1235
+ "epoch": 0.52,
1236
+ "learning_rate": 1.7315735101024068e-05,
1237
+ "loss": 0.2643,
1238
+ "step": 205
1239
+ },
1240
+ {
1241
+ "epoch": 0.53,
1242
+ "learning_rate": 1.7287416144627237e-05,
1243
+ "loss": 1.0249,
1244
+ "step": 206
1245
+ },
1246
+ {
1247
+ "epoch": 0.53,
1248
+ "learning_rate": 1.725897200842189e-05,
1249
+ "loss": 0.2609,
1250
+ "step": 207
1251
+ },
1252
+ {
1253
+ "epoch": 0.53,
1254
+ "learning_rate": 1.7230403181008032e-05,
1255
+ "loss": 1.0024,
1256
+ "step": 208
1257
+ },
1258
+ {
1259
+ "epoch": 0.53,
1260
+ "learning_rate": 1.7201710153127554e-05,
1261
+ "loss": 1.0186,
1262
+ "step": 209
1263
+ },
1264
+ {
1265
+ "epoch": 0.54,
1266
+ "learning_rate": 1.7172893417655792e-05,
1267
+ "loss": 0.2666,
1268
+ "step": 210
1269
+ },
1270
+ {
1271
+ "epoch": 0.54,
1272
+ "learning_rate": 1.714395346959308e-05,
1273
+ "loss": 1.002,
1274
+ "step": 211
1275
+ },
1276
+ {
1277
+ "epoch": 0.54,
1278
+ "learning_rate": 1.7114890806056245e-05,
1279
+ "loss": 0.244,
1280
+ "step": 212
1281
+ },
1282
+ {
1283
+ "epoch": 0.54,
1284
+ "learning_rate": 1.708570592627006e-05,
1285
+ "loss": 1.0571,
1286
+ "step": 213
1287
+ },
1288
+ {
1289
+ "epoch": 0.55,
1290
+ "learning_rate": 1.705639933155866e-05,
1291
+ "loss": 0.9575,
1292
+ "step": 214
1293
+ },
1294
+ {
1295
+ "epoch": 0.55,
1296
+ "learning_rate": 1.702697152533695e-05,
1297
+ "loss": 1.0552,
1298
+ "step": 215
1299
+ },
1300
+ {
1301
+ "epoch": 0.55,
1302
+ "learning_rate": 1.6997423013101967e-05,
1303
+ "loss": 0.2438,
1304
+ "step": 216
1305
+ },
1306
+ {
1307
+ "epoch": 0.55,
1308
+ "learning_rate": 1.6967754302424153e-05,
1309
+ "loss": 1.0049,
1310
+ "step": 217
1311
+ },
1312
+ {
1313
+ "epoch": 0.56,
1314
+ "learning_rate": 1.6937965902938667e-05,
1315
+ "loss": 1.0703,
1316
+ "step": 218
1317
+ },
1318
+ {
1319
+ "epoch": 0.56,
1320
+ "learning_rate": 1.6908058326336634e-05,
1321
+ "loss": 0.9165,
1322
+ "step": 219
1323
+ },
1324
+ {
1325
+ "epoch": 0.56,
1326
+ "learning_rate": 1.687803208635635e-05,
1327
+ "loss": 1.0137,
1328
+ "step": 220
1329
+ },
1330
+ {
1331
+ "epoch": 0.57,
1332
+ "learning_rate": 1.6847887698774446e-05,
1333
+ "loss": 1.0176,
1334
+ "step": 221
1335
+ },
1336
+ {
1337
+ "epoch": 0.57,
1338
+ "learning_rate": 1.6817625681397035e-05,
1339
+ "loss": 1.0308,
1340
+ "step": 222
1341
+ },
1342
+ {
1343
+ "epoch": 0.57,
1344
+ "learning_rate": 1.678724655405083e-05,
1345
+ "loss": 0.9995,
1346
+ "step": 223
1347
+ },
1348
+ {
1349
+ "epoch": 0.57,
1350
+ "learning_rate": 1.6756750838574197e-05,
1351
+ "loss": 0.981,
1352
+ "step": 224
1353
+ },
1354
+ {
1355
+ "epoch": 0.58,
1356
+ "learning_rate": 1.6726139058808206e-05,
1357
+ "loss": 1.0098,
1358
+ "step": 225
1359
+ },
1360
+ {
1361
+ "epoch": 0.58,
1362
+ "learning_rate": 1.66954117405876e-05,
1363
+ "loss": 1.0244,
1364
+ "step": 226
1365
+ },
1366
+ {
1367
+ "epoch": 0.58,
1368
+ "learning_rate": 1.6664569411731828e-05,
1369
+ "loss": 1.0166,
1370
+ "step": 227
1371
+ },
1372
+ {
1373
+ "epoch": 0.58,
1374
+ "learning_rate": 1.66336126020359e-05,
1375
+ "loss": 1.0117,
1376
+ "step": 228
1377
+ },
1378
+ {
1379
+ "epoch": 0.59,
1380
+ "learning_rate": 1.6602541843261345e-05,
1381
+ "loss": 1.0381,
1382
+ "step": 229
1383
+ },
1384
+ {
1385
+ "epoch": 0.59,
1386
+ "learning_rate": 1.6571357669127047e-05,
1387
+ "loss": 0.2267,
1388
+ "step": 230
1389
+ },
1390
+ {
1391
+ "epoch": 0.59,
1392
+ "learning_rate": 1.6540060615300096e-05,
1393
+ "loss": 0.2385,
1394
+ "step": 231
1395
+ },
1396
+ {
1397
+ "epoch": 0.59,
1398
+ "learning_rate": 1.650865121938656e-05,
1399
+ "loss": 0.269,
1400
+ "step": 232
1401
+ },
1402
+ {
1403
+ "epoch": 0.6,
1404
+ "learning_rate": 1.6477130020922277e-05,
1405
+ "loss": 0.2548,
1406
+ "step": 233
1407
+ },
1408
+ {
1409
+ "epoch": 0.6,
1410
+ "learning_rate": 1.644549756136358e-05,
1411
+ "loss": 1.0562,
1412
+ "step": 234
1413
+ },
1414
+ {
1415
+ "epoch": 0.6,
1416
+ "learning_rate": 1.6413754384077992e-05,
1417
+ "loss": 0.2437,
1418
+ "step": 235
1419
+ },
1420
+ {
1421
+ "epoch": 0.6,
1422
+ "learning_rate": 1.6381901034334876e-05,
1423
+ "loss": 1.0015,
1424
+ "step": 236
1425
+ },
1426
+ {
1427
+ "epoch": 0.61,
1428
+ "learning_rate": 1.6349938059296106e-05,
1429
+ "loss": 0.9893,
1430
+ "step": 237
1431
+ },
1432
+ {
1433
+ "epoch": 0.61,
1434
+ "learning_rate": 1.631786600800664e-05,
1435
+ "loss": 1.0459,
1436
+ "step": 238
1437
+ },
1438
+ {
1439
+ "epoch": 0.61,
1440
+ "learning_rate": 1.6285685431385096e-05,
1441
+ "loss": 1.0205,
1442
+ "step": 239
1443
+ },
1444
+ {
1445
+ "epoch": 0.61,
1446
+ "learning_rate": 1.6253396882214293e-05,
1447
+ "loss": 1.021,
1448
+ "step": 240
1449
+ },
1450
+ {
1451
+ "epoch": 0.62,
1452
+ "learning_rate": 1.6221000915131746e-05,
1453
+ "loss": 1.0552,
1454
+ "step": 241
1455
+ },
1456
+ {
1457
+ "epoch": 0.62,
1458
+ "learning_rate": 1.6188498086620148e-05,
1459
+ "loss": 0.9868,
1460
+ "step": 242
1461
+ },
1462
+ {
1463
+ "epoch": 0.62,
1464
+ "learning_rate": 1.615588895499781e-05,
1465
+ "loss": 1.0288,
1466
+ "step": 243
1467
+ },
1468
+ {
1469
+ "epoch": 0.62,
1470
+ "learning_rate": 1.6123174080409055e-05,
1471
+ "loss": 1.0645,
1472
+ "step": 244
1473
+ },
1474
+ {
1475
+ "epoch": 0.63,
1476
+ "learning_rate": 1.609035402481463e-05,
1477
+ "loss": 0.9839,
1478
+ "step": 245
1479
+ },
1480
+ {
1481
+ "epoch": 0.63,
1482
+ "learning_rate": 1.6057429351982016e-05,
1483
+ "loss": 1.0024,
1484
+ "step": 246
1485
+ },
1486
+ {
1487
+ "epoch": 0.63,
1488
+ "learning_rate": 1.602440062747576e-05,
1489
+ "loss": 1.0059,
1490
+ "step": 247
1491
+ },
1492
+ {
1493
+ "epoch": 0.63,
1494
+ "learning_rate": 1.5991268418647772e-05,
1495
+ "loss": 0.981,
1496
+ "step": 248
1497
+ },
1498
+ {
1499
+ "epoch": 0.64,
1500
+ "learning_rate": 1.595803329462755e-05,
1501
+ "loss": 1.0073,
1502
+ "step": 249
1503
+ },
1504
+ {
1505
+ "epoch": 0.64,
1506
+ "learning_rate": 1.5924695826312434e-05,
1507
+ "loss": 0.959,
1508
+ "step": 250
1509
+ },
1510
+ {
1511
+ "epoch": 0.64,
1512
+ "learning_rate": 1.5891256586357783e-05,
1513
+ "loss": 0.2305,
1514
+ "step": 251
1515
+ },
1516
+ {
1517
+ "epoch": 0.64,
1518
+ "learning_rate": 1.585771614916714e-05,
1519
+ "loss": 1.0049,
1520
+ "step": 252
1521
+ },
1522
+ {
1523
+ "epoch": 0.65,
1524
+ "learning_rate": 1.5824075090882364e-05,
1525
+ "loss": 0.9844,
1526
+ "step": 253
1527
+ },
1528
+ {
1529
+ "epoch": 0.65,
1530
+ "learning_rate": 1.5790333989373738e-05,
1531
+ "loss": 0.9756,
1532
+ "step": 254
1533
+ },
1534
+ {
1535
+ "epoch": 0.65,
1536
+ "learning_rate": 1.5756493424230046e-05,
1537
+ "loss": 0.9966,
1538
+ "step": 255
1539
+ },
1540
+ {
1541
+ "epoch": 0.65,
1542
+ "learning_rate": 1.5722553976748605e-05,
1543
+ "loss": 0.9961,
1544
+ "step": 256
1545
+ },
1546
+ {
1547
+ "epoch": 0.66,
1548
+ "learning_rate": 1.5688516229925282e-05,
1549
+ "loss": 0.9888,
1550
+ "step": 257
1551
+ },
1552
+ {
1553
+ "epoch": 0.66,
1554
+ "learning_rate": 1.5654380768444498e-05,
1555
+ "loss": 1.0127,
1556
+ "step": 258
1557
+ },
1558
+ {
1559
+ "epoch": 0.66,
1560
+ "learning_rate": 1.562014817866916e-05,
1561
+ "loss": 1.0337,
1562
+ "step": 259
1563
+ },
1564
+ {
1565
+ "epoch": 0.66,
1566
+ "learning_rate": 1.55858190486306e-05,
1567
+ "loss": 0.2548,
1568
+ "step": 260
1569
+ },
1570
+ {
1571
+ "epoch": 0.67,
1572
+ "learning_rate": 1.555139396801847e-05,
1573
+ "loss": 1.0171,
1574
+ "step": 261
1575
+ },
1576
+ {
1577
+ "epoch": 0.67,
1578
+ "learning_rate": 1.551687352817063e-05,
1579
+ "loss": 0.9946,
1580
+ "step": 262
1581
+ },
1582
+ {
1583
+ "epoch": 0.67,
1584
+ "learning_rate": 1.548225832206296e-05,
1585
+ "loss": 0.2394,
1586
+ "step": 263
1587
+ },
1588
+ {
1589
+ "epoch": 0.68,
1590
+ "learning_rate": 1.5447548944299203e-05,
1591
+ "loss": 0.2191,
1592
+ "step": 264
1593
+ },
1594
+ {
1595
+ "epoch": 0.68,
1596
+ "learning_rate": 1.5412745991100724e-05,
1597
+ "loss": 1.0044,
1598
+ "step": 265
1599
+ },
1600
+ {
1601
+ "epoch": 0.68,
1602
+ "learning_rate": 1.53778500602963e-05,
1603
+ "loss": 1.0361,
1604
+ "step": 266
1605
+ },
1606
+ {
1607
+ "epoch": 0.68,
1608
+ "learning_rate": 1.5342861751311816e-05,
1609
+ "loss": 1.0474,
1610
+ "step": 267
1611
+ },
1612
+ {
1613
+ "epoch": 0.69,
1614
+ "learning_rate": 1.5307781665160005e-05,
1615
+ "loss": 1.0244,
1616
+ "step": 268
1617
+ },
1618
+ {
1619
+ "epoch": 0.69,
1620
+ "learning_rate": 1.527261040443008e-05,
1621
+ "loss": 1.0083,
1622
+ "step": 269
1623
+ },
1624
+ {
1625
+ "epoch": 0.69,
1626
+ "learning_rate": 1.523734857327744e-05,
1627
+ "loss": 1.0405,
1628
+ "step": 270
1629
+ },
1630
+ {
1631
+ "epoch": 0.69,
1632
+ "learning_rate": 1.5201996777413231e-05,
1633
+ "loss": 0.9678,
1634
+ "step": 271
1635
+ },
1636
+ {
1637
+ "epoch": 0.7,
1638
+ "learning_rate": 1.5166555624093986e-05,
1639
+ "loss": 1.02,
1640
+ "step": 272
1641
+ },
1642
+ {
1643
+ "epoch": 0.7,
1644
+ "learning_rate": 1.5131025722111176e-05,
1645
+ "loss": 1.0283,
1646
+ "step": 273
1647
+ },
1648
+ {
1649
+ "epoch": 0.7,
1650
+ "learning_rate": 1.5095407681780753e-05,
1651
+ "loss": 1.0171,
1652
+ "step": 274
1653
+ },
1654
+ {
1655
+ "epoch": 0.7,
1656
+ "learning_rate": 1.505970211493267e-05,
1657
+ "loss": 0.2305,
1658
+ "step": 275
1659
+ },
1660
+ {
1661
+ "epoch": 0.71,
1662
+ "learning_rate": 1.5023909634900362e-05,
1663
+ "loss": 0.2136,
1664
+ "step": 276
1665
+ },
1666
+ {
1667
+ "epoch": 0.71,
1668
+ "learning_rate": 1.4988030856510231e-05,
1669
+ "loss": 1.0059,
1670
+ "step": 277
1671
+ },
1672
+ {
1673
+ "epoch": 0.71,
1674
+ "learning_rate": 1.4952066396071064e-05,
1675
+ "loss": 0.9941,
1676
+ "step": 278
1677
+ },
1678
+ {
1679
+ "epoch": 0.71,
1680
+ "learning_rate": 1.491601687136345e-05,
1681
+ "loss": 1.042,
1682
+ "step": 279
1683
+ },
1684
+ {
1685
+ "epoch": 0.72,
1686
+ "learning_rate": 1.4879882901629181e-05,
1687
+ "loss": 0.9966,
1688
+ "step": 280
1689
+ },
1690
+ {
1691
+ "epoch": 0.72,
1692
+ "learning_rate": 1.4843665107560596e-05,
1693
+ "loss": 0.9966,
1694
+ "step": 281
1695
+ },
1696
+ {
1697
+ "epoch": 0.72,
1698
+ "learning_rate": 1.4807364111289941e-05,
1699
+ "loss": 1.0015,
1700
+ "step": 282
1701
+ },
1702
+ {
1703
+ "epoch": 0.72,
1704
+ "learning_rate": 1.477098053637866e-05,
1705
+ "loss": 0.9614,
1706
+ "step": 283
1707
+ },
1708
+ {
1709
+ "epoch": 0.73,
1710
+ "learning_rate": 1.4734515007806698e-05,
1711
+ "loss": 0.9648,
1712
+ "step": 284
1713
+ },
1714
+ {
1715
+ "epoch": 0.73,
1716
+ "learning_rate": 1.4697968151961763e-05,
1717
+ "loss": 1.0151,
1718
+ "step": 285
1719
+ },
1720
+ {
1721
+ "epoch": 0.73,
1722
+ "learning_rate": 1.4661340596628564e-05,
1723
+ "loss": 1.0171,
1724
+ "step": 286
1725
+ },
1726
+ {
1727
+ "epoch": 0.73,
1728
+ "learning_rate": 1.4624632970978021e-05,
1729
+ "loss": 0.2439,
1730
+ "step": 287
1731
+ },
1732
+ {
1733
+ "epoch": 0.74,
1734
+ "learning_rate": 1.4587845905556477e-05,
1735
+ "loss": 0.9878,
1736
+ "step": 288
1737
+ },
1738
+ {
1739
+ "epoch": 0.74,
1740
+ "learning_rate": 1.4550980032274842e-05,
1741
+ "loss": 0.2694,
1742
+ "step": 289
1743
+ },
1744
+ {
1745
+ "epoch": 0.74,
1746
+ "learning_rate": 1.4514035984397759e-05,
1747
+ "loss": 0.999,
1748
+ "step": 290
1749
+ },
1750
+ {
1751
+ "epoch": 0.74,
1752
+ "learning_rate": 1.4477014396532711e-05,
1753
+ "loss": 0.9946,
1754
+ "step": 291
1755
+ },
1756
+ {
1757
+ "epoch": 0.75,
1758
+ "learning_rate": 1.4439915904619136e-05,
1759
+ "loss": 0.2422,
1760
+ "step": 292
1761
+ },
1762
+ {
1763
+ "epoch": 0.75,
1764
+ "learning_rate": 1.4402741145917475e-05,
1765
+ "loss": 0.9565,
1766
+ "step": 293
1767
+ },
1768
+ {
1769
+ "epoch": 0.75,
1770
+ "learning_rate": 1.4365490758998268e-05,
1771
+ "loss": 0.9976,
1772
+ "step": 294
1773
+ },
1774
+ {
1775
+ "epoch": 0.75,
1776
+ "learning_rate": 1.4328165383731145e-05,
1777
+ "loss": 1.0088,
1778
+ "step": 295
1779
+ },
1780
+ {
1781
+ "epoch": 0.76,
1782
+ "learning_rate": 1.429076566127385e-05,
1783
+ "loss": 0.2537,
1784
+ "step": 296
1785
+ },
1786
+ {
1787
+ "epoch": 0.76,
1788
+ "learning_rate": 1.4253292234061237e-05,
1789
+ "loss": 1.0054,
1790
+ "step": 297
1791
+ },
1792
+ {
1793
+ "epoch": 0.76,
1794
+ "learning_rate": 1.4215745745794224e-05,
1795
+ "loss": 0.957,
1796
+ "step": 298
1797
+ },
1798
+ {
1799
+ "epoch": 0.76,
1800
+ "learning_rate": 1.4178126841428732e-05,
1801
+ "loss": 0.9761,
1802
+ "step": 299
1803
+ },
1804
+ {
1805
+ "epoch": 0.77,
1806
+ "learning_rate": 1.4140436167164611e-05,
1807
+ "loss": 0.9512,
1808
+ "step": 300
1809
+ },
1810
+ {
1811
+ "epoch": 0.77,
1812
+ "learning_rate": 1.4102674370434549e-05,
1813
+ "loss": 0.998,
1814
+ "step": 301
1815
+ },
1816
+ {
1817
+ "epoch": 0.77,
1818
+ "learning_rate": 1.4064842099892934e-05,
1819
+ "loss": 0.2422,
1820
+ "step": 302
1821
+ },
1822
+ {
1823
+ "epoch": 0.77,
1824
+ "learning_rate": 1.4026940005404726e-05,
1825
+ "loss": 1.0405,
1826
+ "step": 303
1827
+ },
1828
+ {
1829
+ "epoch": 0.78,
1830
+ "learning_rate": 1.3988968738034285e-05,
1831
+ "loss": 1.0464,
1832
+ "step": 304
1833
+ },
1834
+ {
1835
+ "epoch": 0.78,
1836
+ "learning_rate": 1.3950928950034189e-05,
1837
+ "loss": 1.0601,
1838
+ "step": 305
1839
+ },
1840
+ {
1841
+ "epoch": 0.78,
1842
+ "learning_rate": 1.3912821294834033e-05,
1843
+ "loss": 1.0049,
1844
+ "step": 306
1845
+ },
1846
+ {
1847
+ "epoch": 0.79,
1848
+ "learning_rate": 1.3874646427029204e-05,
1849
+ "loss": 1.0083,
1850
+ "step": 307
1851
+ },
1852
+ {
1853
+ "epoch": 0.79,
1854
+ "learning_rate": 1.3836405002369631e-05,
1855
+ "loss": 0.9946,
1856
+ "step": 308
1857
+ },
1858
+ {
1859
+ "epoch": 0.79,
1860
+ "learning_rate": 1.3798097677748535e-05,
1861
+ "loss": 0.9541,
1862
+ "step": 309
1863
+ },
1864
+ {
1865
+ "epoch": 0.79,
1866
+ "learning_rate": 1.3759725111191118e-05,
1867
+ "loss": 0.2429,
1868
+ "step": 310
1869
+ },
1870
+ {
1871
+ "epoch": 0.8,
1872
+ "learning_rate": 1.3721287961843298e-05,
1873
+ "loss": 1.0112,
1874
+ "step": 311
1875
+ },
1876
+ {
1877
+ "epoch": 0.8,
1878
+ "learning_rate": 1.3682786889960354e-05,
1879
+ "loss": 0.9995,
1880
+ "step": 312
1881
+ },
1882
+ {
1883
+ "epoch": 0.8,
1884
+ "learning_rate": 1.3644222556895591e-05,
1885
+ "loss": 1.001,
1886
+ "step": 313
1887
+ },
1888
+ {
1889
+ "epoch": 0.8,
1890
+ "learning_rate": 1.3605595625089006e-05,
1891
+ "loss": 0.9946,
1892
+ "step": 314
1893
+ },
1894
+ {
1895
+ "epoch": 0.81,
1896
+ "learning_rate": 1.3566906758055862e-05,
1897
+ "loss": 0.264,
1898
+ "step": 315
1899
+ },
1900
+ {
1901
+ "epoch": 0.81,
1902
+ "learning_rate": 1.3528156620375335e-05,
1903
+ "loss": 0.9922,
1904
+ "step": 316
1905
+ },
1906
+ {
1907
+ "epoch": 0.81,
1908
+ "learning_rate": 1.3489345877679068e-05,
1909
+ "loss": 0.9893,
1910
+ "step": 317
1911
+ },
1912
+ {
1913
+ "epoch": 0.81,
1914
+ "learning_rate": 1.3450475196639753e-05,
1915
+ "loss": 0.9927,
1916
+ "step": 318
1917
+ },
1918
+ {
1919
+ "epoch": 0.82,
1920
+ "learning_rate": 1.341154524495968e-05,
1921
+ "loss": 1.019,
1922
+ "step": 319
1923
+ },
1924
+ {
1925
+ "epoch": 0.82,
1926
+ "learning_rate": 1.3372556691359251e-05,
1927
+ "loss": 0.2389,
1928
+ "step": 320
1929
+ },
1930
+ {
1931
+ "epoch": 0.82,
1932
+ "learning_rate": 1.3333510205565516e-05,
1933
+ "loss": 0.2407,
1934
+ "step": 321
1935
+ },
1936
+ {
1937
+ "epoch": 0.82,
1938
+ "learning_rate": 1.3294406458300646e-05,
1939
+ "loss": 0.2081,
1940
+ "step": 322
1941
+ },
1942
+ {
1943
+ "epoch": 0.83,
1944
+ "learning_rate": 1.325524612127043e-05,
1945
+ "loss": 1.0029,
1946
+ "step": 323
1947
+ },
1948
+ {
1949
+ "epoch": 0.83,
1950
+ "learning_rate": 1.3216029867152724e-05,
1951
+ "loss": 0.9995,
1952
+ "step": 324
1953
+ },
1954
+ {
1955
+ "epoch": 0.83,
1956
+ "learning_rate": 1.3176758369585909e-05,
1957
+ "loss": 0.2625,
1958
+ "step": 325
1959
+ },
1960
+ {
1961
+ "epoch": 0.83,
1962
+ "learning_rate": 1.3137432303157306e-05,
1963
+ "loss": 0.2437,
1964
+ "step": 326
1965
+ },
1966
+ {
1967
+ "epoch": 0.84,
1968
+ "learning_rate": 1.3098052343391596e-05,
1969
+ "loss": 0.1965,
1970
+ "step": 327
1971
+ },
1972
+ {
1973
+ "epoch": 0.84,
1974
+ "learning_rate": 1.3058619166739212e-05,
1975
+ "loss": 1.0269,
1976
+ "step": 328
1977
+ },
1978
+ {
1979
+ "epoch": 0.84,
1980
+ "learning_rate": 1.3019133450564725e-05,
1981
+ "loss": 0.9941,
1982
+ "step": 329
1983
+ },
1984
+ {
1985
+ "epoch": 0.84,
1986
+ "learning_rate": 1.2979595873135208e-05,
1987
+ "loss": 0.939,
1988
+ "step": 330
1989
+ },
1990
+ {
1991
+ "epoch": 0.85,
1992
+ "learning_rate": 1.2940007113608572e-05,
1993
+ "loss": 0.9609,
1994
+ "step": 331
1995
+ },
1996
+ {
1997
+ "epoch": 0.85,
1998
+ "learning_rate": 1.290036785202192e-05,
1999
+ "loss": 1.0054,
2000
+ "step": 332
2001
+ },
2002
+ {
2003
+ "epoch": 0.85,
2004
+ "learning_rate": 1.2860678769279855e-05,
2005
+ "loss": 0.9839,
2006
+ "step": 333
2007
+ },
2008
+ {
2009
+ "epoch": 0.85,
2010
+ "learning_rate": 1.2820940547142773e-05,
2011
+ "loss": 0.9834,
2012
+ "step": 334
2013
+ },
2014
+ {
2015
+ "epoch": 0.86,
2016
+ "learning_rate": 1.278115386821518e-05,
2017
+ "loss": 0.9849,
2018
+ "step": 335
2019
+ },
2020
+ {
2021
+ "epoch": 0.86,
2022
+ "learning_rate": 1.2741319415933934e-05,
2023
+ "loss": 0.2257,
2024
+ "step": 336
2025
+ },
2026
+ {
2027
+ "epoch": 0.86,
2028
+ "learning_rate": 1.2701437874556537e-05,
2029
+ "loss": 0.2378,
2030
+ "step": 337
2031
+ },
2032
+ {
2033
+ "epoch": 0.86,
2034
+ "learning_rate": 1.2661509929149351e-05,
2035
+ "loss": 0.2456,
2036
+ "step": 338
2037
+ },
2038
+ {
2039
+ "epoch": 0.87,
2040
+ "learning_rate": 1.2621536265575855e-05,
2041
+ "loss": 0.2455,
2042
+ "step": 339
2043
+ },
2044
+ {
2045
+ "epoch": 0.87,
2046
+ "learning_rate": 1.258151757048485e-05,
2047
+ "loss": 0.9692,
2048
+ "step": 340
2049
+ },
2050
+ {
2051
+ "epoch": 0.87,
2052
+ "learning_rate": 1.2541454531298661e-05,
2053
+ "loss": 0.2754,
2054
+ "step": 341
2055
+ },
2056
+ {
2057
+ "epoch": 0.87,
2058
+ "learning_rate": 1.2501347836201343e-05,
2059
+ "loss": 1.0425,
2060
+ "step": 342
2061
+ },
2062
+ {
2063
+ "epoch": 0.88,
2064
+ "learning_rate": 1.2461198174126851e-05,
2065
+ "loss": 0.9878,
2066
+ "step": 343
2067
+ },
2068
+ {
2069
+ "epoch": 0.88,
2070
+ "learning_rate": 1.2421006234747202e-05,
2071
+ "loss": 0.9619,
2072
+ "step": 344
2073
+ },
2074
+ {
2075
+ "epoch": 0.88,
2076
+ "learning_rate": 1.238077270846064e-05,
2077
+ "loss": 0.2847,
2078
+ "step": 345
2079
+ },
2080
+ {
2081
+ "epoch": 0.88,
2082
+ "learning_rate": 1.2340498286379757e-05,
2083
+ "loss": 0.9648,
2084
+ "step": 346
2085
+ },
2086
+ {
2087
+ "epoch": 0.89,
2088
+ "learning_rate": 1.2300183660319647e-05,
2089
+ "loss": 1.0,
2090
+ "step": 347
2091
+ },
2092
+ {
2093
+ "epoch": 0.89,
2094
+ "learning_rate": 1.2259829522786003e-05,
2095
+ "loss": 1.0151,
2096
+ "step": 348
2097
+ },
2098
+ {
2099
+ "epoch": 0.89,
2100
+ "learning_rate": 1.2219436566963221e-05,
2101
+ "loss": 1.0244,
2102
+ "step": 349
2103
+ },
2104
+ {
2105
+ "epoch": 0.9,
2106
+ "learning_rate": 1.2179005486702518e-05,
2107
+ "loss": 1.0483,
2108
+ "step": 350
2109
+ },
2110
+ {
2111
+ "epoch": 0.9,
2112
+ "learning_rate": 1.2138536976509974e-05,
2113
+ "loss": 0.9966,
2114
+ "step": 351
2115
+ },
2116
+ {
2117
+ "epoch": 0.9,
2118
+ "learning_rate": 1.2098031731534636e-05,
2119
+ "loss": 1.0439,
2120
+ "step": 352
2121
+ },
2122
+ {
2123
+ "epoch": 0.9,
2124
+ "learning_rate": 1.2057490447556556e-05,
2125
+ "loss": 0.9907,
2126
+ "step": 353
2127
+ },
2128
+ {
2129
+ "epoch": 0.91,
2130
+ "learning_rate": 1.2016913820974855e-05,
2131
+ "loss": 1.0239,
2132
+ "step": 354
2133
+ },
2134
+ {
2135
+ "epoch": 0.91,
2136
+ "learning_rate": 1.1976302548795746e-05,
2137
+ "loss": 1.0059,
2138
+ "step": 355
2139
+ },
2140
+ {
2141
+ "epoch": 0.91,
2142
+ "learning_rate": 1.1935657328620566e-05,
2143
+ "loss": 0.9526,
2144
+ "step": 356
2145
+ },
2146
+ {
2147
+ "epoch": 0.91,
2148
+ "learning_rate": 1.1894978858633807e-05,
2149
+ "loss": 0.9561,
2150
+ "step": 357
2151
+ },
2152
+ {
2153
+ "epoch": 0.92,
2154
+ "learning_rate": 1.1854267837591095e-05,
2155
+ "loss": 1.0015,
2156
+ "step": 358
2157
+ },
2158
+ {
2159
+ "epoch": 0.92,
2160
+ "learning_rate": 1.1813524964807216e-05,
2161
+ "loss": 0.9756,
2162
+ "step": 359
2163
+ },
2164
+ {
2165
+ "epoch": 0.92,
2166
+ "learning_rate": 1.1772750940144079e-05,
2167
+ "loss": 0.9414,
2168
+ "step": 360
2169
+ },
2170
+ {
2171
+ "epoch": 0.92,
2172
+ "learning_rate": 1.1731946463998712e-05,
2173
+ "loss": 0.9839,
2174
+ "step": 361
2175
+ },
2176
+ {
2177
+ "epoch": 0.93,
2178
+ "learning_rate": 1.1691112237291225e-05,
2179
+ "loss": 0.2285,
2180
+ "step": 362
2181
+ },
2182
+ {
2183
+ "epoch": 0.93,
2184
+ "learning_rate": 1.1650248961452765e-05,
2185
+ "loss": 0.9873,
2186
+ "step": 363
2187
+ },
2188
+ {
2189
+ "epoch": 0.93,
2190
+ "learning_rate": 1.1609357338413476e-05,
2191
+ "loss": 1.0317,
2192
+ "step": 364
2193
+ },
2194
+ {
2195
+ "epoch": 0.93,
2196
+ "learning_rate": 1.1568438070590428e-05,
2197
+ "loss": 0.2444,
2198
+ "step": 365
2199
+ },
2200
+ {
2201
+ "epoch": 0.94,
2202
+ "learning_rate": 1.1527491860875574e-05,
2203
+ "loss": 0.9966,
2204
+ "step": 366
2205
+ },
2206
+ {
2207
+ "epoch": 0.94,
2208
+ "learning_rate": 1.1486519412623653e-05,
2209
+ "loss": 0.2284,
2210
+ "step": 367
2211
+ },
2212
+ {
2213
+ "epoch": 0.94,
2214
+ "learning_rate": 1.1445521429640113e-05,
2215
+ "loss": 0.9277,
2216
+ "step": 368
2217
+ },
2218
+ {
2219
+ "epoch": 0.94,
2220
+ "learning_rate": 1.1404498616169039e-05,
2221
+ "loss": 0.9937,
2222
+ "step": 369
2223
+ },
2224
+ {
2225
+ "epoch": 0.95,
2226
+ "learning_rate": 1.136345167688103e-05,
2227
+ "loss": 0.9429,
2228
+ "step": 370
2229
+ },
2230
+ {
2231
+ "epoch": 0.95,
2232
+ "learning_rate": 1.1322381316861114e-05,
2233
+ "loss": 0.9268,
2234
+ "step": 371
2235
+ },
2236
+ {
2237
+ "epoch": 0.95,
2238
+ "learning_rate": 1.1281288241596624e-05,
2239
+ "loss": 0.9966,
2240
+ "step": 372
2241
+ },
2242
+ {
2243
+ "epoch": 0.95,
2244
+ "learning_rate": 1.1240173156965089e-05,
2245
+ "loss": 0.9653,
2246
+ "step": 373
2247
+ },
2248
+ {
2249
+ "epoch": 0.96,
2250
+ "learning_rate": 1.1199036769222104e-05,
2251
+ "loss": 0.24,
2252
+ "step": 374
2253
+ },
2254
+ {
2255
+ "epoch": 0.96,
2256
+ "learning_rate": 1.1157879784989203e-05,
2257
+ "loss": 1.0811,
2258
+ "step": 375
2259
+ },
2260
+ {
2261
+ "epoch": 0.96,
2262
+ "learning_rate": 1.1116702911241704e-05,
2263
+ "loss": 1.0024,
2264
+ "step": 376
2265
+ },
2266
+ {
2267
+ "epoch": 0.96,
2268
+ "learning_rate": 1.107550685529659e-05,
2269
+ "loss": 1.0449,
2270
+ "step": 377
2271
+ },
2272
+ {
2273
+ "epoch": 0.97,
2274
+ "learning_rate": 1.1034292324800342e-05,
2275
+ "loss": 0.9966,
2276
+ "step": 378
2277
+ },
2278
+ {
2279
+ "epoch": 0.97,
2280
+ "learning_rate": 1.099306002771679e-05,
2281
+ "loss": 1.0015,
2282
+ "step": 379
2283
+ },
2284
+ {
2285
+ "epoch": 0.97,
2286
+ "learning_rate": 1.0951810672314946e-05,
2287
+ "loss": 1.0112,
2288
+ "step": 380
2289
+ },
2290
+ {
2291
+ "epoch": 0.97,
2292
+ "learning_rate": 1.091054496715685e-05,
2293
+ "loss": 0.9658,
2294
+ "step": 381
2295
+ },
2296
+ {
2297
+ "epoch": 0.98,
2298
+ "learning_rate": 1.0869263621085375e-05,
2299
+ "loss": 1.0088,
2300
+ "step": 382
2301
+ },
2302
+ {
2303
+ "epoch": 0.98,
2304
+ "learning_rate": 1.0827967343212087e-05,
2305
+ "loss": 0.9927,
2306
+ "step": 383
2307
+ },
2308
+ {
2309
+ "epoch": 0.98,
2310
+ "learning_rate": 1.0786656842905028e-05,
2311
+ "loss": 1.0156,
2312
+ "step": 384
2313
+ },
2314
+ {
2315
+ "epoch": 0.98,
2316
+ "learning_rate": 1.074533282977655e-05,
2317
+ "loss": 0.23,
2318
+ "step": 385
2319
+ },
2320
+ {
2321
+ "epoch": 0.99,
2322
+ "learning_rate": 1.0703996013671126e-05,
2323
+ "loss": 0.9702,
2324
+ "step": 386
2325
+ },
2326
+ {
2327
+ "epoch": 0.99,
2328
+ "learning_rate": 1.0662647104653145e-05,
2329
+ "loss": 0.9653,
2330
+ "step": 387
2331
+ },
2332
+ {
2333
+ "epoch": 0.99,
2334
+ "learning_rate": 1.0621286812994733e-05,
2335
+ "loss": 1.0127,
2336
+ "step": 388
2337
+ },
2338
+ {
2339
+ "epoch": 0.99,
2340
+ "learning_rate": 1.057991584916353e-05,
2341
+ "loss": 0.9722,
2342
+ "step": 389
2343
+ },
2344
+ {
2345
+ "epoch": 1.0,
2346
+ "learning_rate": 1.0538534923810506e-05,
2347
+ "loss": 0.9731,
2348
+ "step": 390
2349
+ },
2350
+ {
2351
+ "epoch": 1.0,
2352
+ "learning_rate": 1.049714474775774e-05,
2353
+ "loss": 0.8088,
2354
+ "step": 391
2355
+ },
2356
+ {
2357
+ "epoch": 1.0,
2358
+ "learning_rate": 1.0455746031986215e-05,
2359
+ "loss": 0.1147,
2360
+ "step": 392
2361
+ },
2362
+ {
2363
+ "epoch": 1.01,
2364
+ "learning_rate": 1.041433948762362e-05,
2365
+ "loss": 0.7056,
2366
+ "step": 393
2367
+ },
2368
+ {
2369
+ "epoch": 1.01,
2370
+ "learning_rate": 1.0372925825932095e-05,
2371
+ "loss": 0.1289,
2372
+ "step": 394
2373
+ },
2374
+ {
2375
+ "epoch": 1.01,
2376
+ "learning_rate": 1.0331505758296054e-05,
2377
+ "loss": 0.0988,
2378
+ "step": 395
2379
+ },
2380
+ {
2381
+ "epoch": 1.01,
2382
+ "learning_rate": 1.029007999620995e-05,
2383
+ "loss": 0.6709,
2384
+ "step": 396
2385
+ },
2386
+ {
2387
+ "epoch": 1.02,
2388
+ "learning_rate": 1.0248649251266043e-05,
2389
+ "loss": 0.665,
2390
+ "step": 397
2391
+ },
2392
+ {
2393
+ "epoch": 1.02,
2394
+ "learning_rate": 1.0207214235142197e-05,
2395
+ "loss": 0.6655,
2396
+ "step": 398
2397
+ },
2398
+ {
2399
+ "epoch": 1.02,
2400
+ "learning_rate": 1.0165775659589638e-05,
2401
+ "loss": 0.1008,
2402
+ "step": 399
2403
+ },
2404
+ {
2405
+ "epoch": 1.02,
2406
+ "learning_rate": 1.0124334236420735e-05,
2407
+ "loss": 0.6792,
2408
+ "step": 400
2409
+ },
2410
+ {
2411
+ "epoch": 1.03,
2412
+ "learning_rate": 1.0082890677496766e-05,
2413
+ "loss": 0.1077,
2414
+ "step": 401
2415
+ },
2416
+ {
2417
+ "epoch": 1.03,
2418
+ "learning_rate": 1.0041445694715717e-05,
2419
+ "loss": 0.6846,
2420
+ "step": 402
2421
+ },
2422
+ {
2423
+ "epoch": 1.03,
2424
+ "learning_rate": 1e-05,
2425
+ "loss": 0.6353,
2426
+ "step": 403
2427
+ },
2428
+ {
2429
+ "epoch": 1.03,
2430
+ "learning_rate": 9.95855430528429e-06,
2431
+ "loss": 0.6665,
2432
+ "step": 404
2433
+ },
2434
+ {
2435
+ "epoch": 1.04,
2436
+ "learning_rate": 9.917109322503234e-06,
2437
+ "loss": 0.6421,
2438
+ "step": 405
2439
+ },
2440
+ {
2441
+ "epoch": 1.04,
2442
+ "learning_rate": 9.87566576357927e-06,
2443
+ "loss": 0.6406,
2444
+ "step": 406
2445
+ },
2446
+ {
2447
+ "epoch": 1.04,
2448
+ "learning_rate": 9.834224340410367e-06,
2449
+ "loss": 0.6113,
2450
+ "step": 407
2451
+ },
2452
+ {
2453
+ "epoch": 1.04,
2454
+ "learning_rate": 9.792785764857803e-06,
2455
+ "loss": 0.6248,
2456
+ "step": 408
2457
+ },
2458
+ {
2459
+ "epoch": 1.05,
2460
+ "learning_rate": 9.751350748733958e-06,
2461
+ "loss": 0.1197,
2462
+ "step": 409
2463
+ },
2464
+ {
2465
+ "epoch": 1.05,
2466
+ "learning_rate": 9.709920003790054e-06,
2467
+ "loss": 0.6689,
2468
+ "step": 410
2469
+ },
2470
+ {
2471
+ "epoch": 1.05,
2472
+ "learning_rate": 9.668494241703946e-06,
2473
+ "loss": 0.1241,
2474
+ "step": 411
2475
+ },
2476
+ {
2477
+ "epoch": 1.05,
2478
+ "learning_rate": 9.627074174067909e-06,
2479
+ "loss": 0.6055,
2480
+ "step": 412
2481
+ },
2482
+ {
2483
+ "epoch": 1.06,
2484
+ "learning_rate": 9.585660512376385e-06,
2485
+ "loss": 0.623,
2486
+ "step": 413
2487
+ },
2488
+ {
2489
+ "epoch": 1.06,
2490
+ "learning_rate": 9.544253968013785e-06,
2491
+ "loss": 0.6348,
2492
+ "step": 414
2493
+ },
2494
+ {
2495
+ "epoch": 1.06,
2496
+ "learning_rate": 9.502855252242265e-06,
2497
+ "loss": 0.6172,
2498
+ "step": 415
2499
+ },
2500
+ {
2501
+ "epoch": 1.06,
2502
+ "learning_rate": 9.461465076189499e-06,
2503
+ "loss": 0.6079,
2504
+ "step": 416
2505
+ },
2506
+ {
2507
+ "epoch": 1.07,
2508
+ "learning_rate": 9.420084150836472e-06,
2509
+ "loss": 0.6094,
2510
+ "step": 417
2511
+ },
2512
+ {
2513
+ "epoch": 1.07,
2514
+ "learning_rate": 9.37871318700527e-06,
2515
+ "loss": 0.6084,
2516
+ "step": 418
2517
+ },
2518
+ {
2519
+ "epoch": 1.07,
2520
+ "learning_rate": 9.337352895346858e-06,
2521
+ "loss": 0.6304,
2522
+ "step": 419
2523
+ },
2524
+ {
2525
+ "epoch": 1.07,
2526
+ "learning_rate": 9.296003986328876e-06,
2527
+ "loss": 0.6118,
2528
+ "step": 420
2529
+ },
2530
+ {
2531
+ "epoch": 1.08,
2532
+ "learning_rate": 9.254667170223454e-06,
2533
+ "loss": 0.5962,
2534
+ "step": 421
2535
+ },
2536
+ {
2537
+ "epoch": 1.08,
2538
+ "learning_rate": 9.213343157094975e-06,
2539
+ "loss": 0.5938,
2540
+ "step": 422
2541
+ },
2542
+ {
2543
+ "epoch": 1.08,
2544
+ "learning_rate": 9.172032656787913e-06,
2545
+ "loss": 0.6235,
2546
+ "step": 423
2547
+ },
2548
+ {
2549
+ "epoch": 1.08,
2550
+ "learning_rate": 9.130736378914626e-06,
2551
+ "loss": 0.6436,
2552
+ "step": 424
2553
+ },
2554
+ {
2555
+ "epoch": 1.09,
2556
+ "learning_rate": 9.089455032843156e-06,
2557
+ "loss": 0.5889,
2558
+ "step": 425
2559
+ },
2560
+ {
2561
+ "epoch": 1.09,
2562
+ "learning_rate": 9.048189327685056e-06,
2563
+ "loss": 0.1123,
2564
+ "step": 426
2565
+ },
2566
+ {
2567
+ "epoch": 1.09,
2568
+ "learning_rate": 9.006939972283213e-06,
2569
+ "loss": 0.6431,
2570
+ "step": 427
2571
+ },
2572
+ {
2573
+ "epoch": 1.09,
2574
+ "learning_rate": 8.965707675199661e-06,
2575
+ "loss": 0.1234,
2576
+ "step": 428
2577
+ },
2578
+ {
2579
+ "epoch": 1.1,
2580
+ "learning_rate": 8.92449314470341e-06,
2581
+ "loss": 0.5776,
2582
+ "step": 429
2583
+ },
2584
+ {
2585
+ "epoch": 1.1,
2586
+ "learning_rate": 8.883297088758298e-06,
2587
+ "loss": 0.1149,
2588
+ "step": 430
2589
+ },
2590
+ {
2591
+ "epoch": 1.1,
2592
+ "learning_rate": 8.842120215010804e-06,
2593
+ "loss": 0.6406,
2594
+ "step": 431
2595
+ },
2596
+ {
2597
+ "epoch": 1.1,
2598
+ "learning_rate": 8.800963230777895e-06,
2599
+ "loss": 0.6089,
2600
+ "step": 432
2601
+ },
2602
+ {
2603
+ "epoch": 1.11,
2604
+ "learning_rate": 8.759826843034916e-06,
2605
+ "loss": 0.5894,
2606
+ "step": 433
2607
+ },
2608
+ {
2609
+ "epoch": 1.11,
2610
+ "learning_rate": 8.718711758403382e-06,
2611
+ "loss": 0.0874,
2612
+ "step": 434
2613
+ },
2614
+ {
2615
+ "epoch": 1.11,
2616
+ "learning_rate": 8.677618683138888e-06,
2617
+ "loss": 0.6216,
2618
+ "step": 435
2619
+ },
2620
+ {
2621
+ "epoch": 1.12,
2622
+ "learning_rate": 8.636548323118974e-06,
2623
+ "loss": 0.117,
2624
+ "step": 436
2625
+ },
2626
+ {
2627
+ "epoch": 1.12,
2628
+ "learning_rate": 8.595501383830964e-06,
2629
+ "loss": 0.108,
2630
+ "step": 437
2631
+ },
2632
+ {
2633
+ "epoch": 1.12,
2634
+ "learning_rate": 8.554478570359888e-06,
2635
+ "loss": 0.644,
2636
+ "step": 438
2637
+ },
2638
+ {
2639
+ "epoch": 1.12,
2640
+ "learning_rate": 8.51348058737635e-06,
2641
+ "loss": 0.6006,
2642
+ "step": 439
2643
+ },
2644
+ {
2645
+ "epoch": 1.13,
2646
+ "learning_rate": 8.472508139124427e-06,
2647
+ "loss": 0.6157,
2648
+ "step": 440
2649
+ },
2650
+ {
2651
+ "epoch": 1.13,
2652
+ "learning_rate": 8.431561929409572e-06,
2653
+ "loss": 0.6616,
2654
+ "step": 441
2655
+ },
2656
+ {
2657
+ "epoch": 1.13,
2658
+ "learning_rate": 8.390642661586527e-06,
2659
+ "loss": 0.6138,
2660
+ "step": 442
2661
+ },
2662
+ {
2663
+ "epoch": 1.13,
2664
+ "learning_rate": 8.34975103854724e-06,
2665
+ "loss": 0.6567,
2666
+ "step": 443
2667
+ },
2668
+ {
2669
+ "epoch": 1.14,
2670
+ "learning_rate": 8.308887762708776e-06,
2671
+ "loss": 0.6221,
2672
+ "step": 444
2673
+ },
2674
+ {
2675
+ "epoch": 1.14,
2676
+ "learning_rate": 8.268053536001291e-06,
2677
+ "loss": 0.6123,
2678
+ "step": 445
2679
+ },
2680
+ {
2681
+ "epoch": 1.14,
2682
+ "learning_rate": 8.227249059855926e-06,
2683
+ "loss": 0.6064,
2684
+ "step": 446
2685
+ },
2686
+ {
2687
+ "epoch": 1.14,
2688
+ "learning_rate": 8.186475035192788e-06,
2689
+ "loss": 0.0959,
2690
+ "step": 447
2691
+ },
2692
+ {
2693
+ "epoch": 1.15,
2694
+ "learning_rate": 8.145732162408906e-06,
2695
+ "loss": 0.6082,
2696
+ "step": 448
2697
+ },
2698
+ {
2699
+ "epoch": 1.15,
2700
+ "learning_rate": 8.105021141366196e-06,
2701
+ "loss": 0.0883,
2702
+ "step": 449
2703
+ },
2704
+ {
2705
+ "epoch": 1.15,
2706
+ "learning_rate": 8.064342671379436e-06,
2707
+ "loss": 0.1067,
2708
+ "step": 450
2709
+ },
2710
+ {
2711
+ "epoch": 1.15,
2712
+ "learning_rate": 8.023697451204257e-06,
2713
+ "loss": 0.1097,
2714
+ "step": 451
2715
+ },
2716
+ {
2717
+ "epoch": 1.16,
2718
+ "learning_rate": 7.983086179025148e-06,
2719
+ "loss": 0.6636,
2720
+ "step": 452
2721
+ },
2722
+ {
2723
+ "epoch": 1.16,
2724
+ "learning_rate": 7.942509552443445e-06,
2725
+ "loss": 0.6729,
2726
+ "step": 453
2727
+ },
2728
+ {
2729
+ "epoch": 1.16,
2730
+ "learning_rate": 7.901968268465367e-06,
2731
+ "loss": 0.6558,
2732
+ "step": 454
2733
+ },
2734
+ {
2735
+ "epoch": 1.16,
2736
+ "learning_rate": 7.86146302349003e-06,
2737
+ "loss": 0.5608,
2738
+ "step": 455
2739
+ },
2740
+ {
2741
+ "epoch": 1.17,
2742
+ "learning_rate": 7.820994513297484e-06,
2743
+ "loss": 0.6401,
2744
+ "step": 456
2745
+ },
2746
+ {
2747
+ "epoch": 1.17,
2748
+ "learning_rate": 7.78056343303678e-06,
2749
+ "loss": 0.6196,
2750
+ "step": 457
2751
+ },
2752
+ {
2753
+ "epoch": 1.17,
2754
+ "learning_rate": 7.740170477214004e-06,
2755
+ "loss": 0.0937,
2756
+ "step": 458
2757
+ },
2758
+ {
2759
+ "epoch": 1.17,
2760
+ "learning_rate": 7.699816339680357e-06,
2761
+ "loss": 0.5903,
2762
+ "step": 459
2763
+ },
2764
+ {
2765
+ "epoch": 1.18,
2766
+ "learning_rate": 7.659501713620247e-06,
2767
+ "loss": 0.5938,
2768
+ "step": 460
2769
+ },
2770
+ {
2771
+ "epoch": 1.18,
2772
+ "learning_rate": 7.619227291539365e-06,
2773
+ "loss": 0.5625,
2774
+ "step": 461
2775
+ },
2776
+ {
2777
+ "epoch": 1.18,
2778
+ "learning_rate": 7.578993765252799e-06,
2779
+ "loss": 0.6348,
2780
+ "step": 462
2781
+ },
2782
+ {
2783
+ "epoch": 1.18,
2784
+ "learning_rate": 7.538801825873151e-06,
2785
+ "loss": 0.5894,
2786
+ "step": 463
2787
+ },
2788
+ {
2789
+ "epoch": 1.19,
2790
+ "learning_rate": 7.498652163798659e-06,
2791
+ "loss": 0.6079,
2792
+ "step": 464
2793
+ },
2794
+ {
2795
+ "epoch": 1.19,
2796
+ "learning_rate": 7.458545468701342e-06,
2797
+ "loss": 0.6187,
2798
+ "step": 465
2799
+ },
2800
+ {
2801
+ "epoch": 1.19,
2802
+ "learning_rate": 7.418482429515153e-06,
2803
+ "loss": 0.0979,
2804
+ "step": 466
2805
+ },
2806
+ {
2807
+ "epoch": 1.19,
2808
+ "learning_rate": 7.378463734424148e-06,
2809
+ "loss": 0.1021,
2810
+ "step": 467
2811
+ },
2812
+ {
2813
+ "epoch": 1.2,
2814
+ "learning_rate": 7.338490070850649e-06,
2815
+ "loss": 0.6431,
2816
+ "step": 468
2817
+ },
2818
+ {
2819
+ "epoch": 1.2,
2820
+ "learning_rate": 7.298562125443467e-06,
2821
+ "loss": 0.5703,
2822
+ "step": 469
2823
+ },
2824
+ {
2825
+ "epoch": 1.2,
2826
+ "learning_rate": 7.258680584066069e-06,
2827
+ "loss": 0.0981,
2828
+ "step": 470
2829
+ },
2830
+ {
2831
+ "epoch": 1.2,
2832
+ "learning_rate": 7.218846131784824e-06,
2833
+ "loss": 0.627,
2834
+ "step": 471
2835
+ },
2836
+ {
2837
+ "epoch": 1.21,
2838
+ "learning_rate": 7.17905945285723e-06,
2839
+ "loss": 0.0985,
2840
+ "step": 472
2841
+ },
2842
+ {
2843
+ "epoch": 1.21,
2844
+ "learning_rate": 7.139321230720151e-06,
2845
+ "loss": 0.6338,
2846
+ "step": 473
2847
+ },
2848
+ {
2849
+ "epoch": 1.21,
2850
+ "learning_rate": 7.09963214797808e-06,
2851
+ "loss": 0.6401,
2852
+ "step": 474
2853
+ },
2854
+ {
2855
+ "epoch": 1.21,
2856
+ "learning_rate": 7.059992886391429e-06,
2857
+ "loss": 0.5986,
2858
+ "step": 475
2859
+ },
2860
+ {
2861
+ "epoch": 1.22,
2862
+ "learning_rate": 7.020404126864795e-06,
2863
+ "loss": 0.573,
2864
+ "step": 476
2865
+ },
2866
+ {
2867
+ "epoch": 1.22,
2868
+ "learning_rate": 6.980866549435274e-06,
2869
+ "loss": 0.5938,
2870
+ "step": 477
2871
+ },
2872
+ {
2873
+ "epoch": 1.22,
2874
+ "learning_rate": 6.94138083326079e-06,
2875
+ "loss": 0.6157,
2876
+ "step": 478
2877
+ },
2878
+ {
2879
+ "epoch": 1.23,
2880
+ "learning_rate": 6.90194765660841e-06,
2881
+ "loss": 0.6167,
2882
+ "step": 479
2883
+ },
2884
+ {
2885
+ "epoch": 1.23,
2886
+ "learning_rate": 6.862567696842694e-06,
2887
+ "loss": 0.5967,
2888
+ "step": 480
2889
+ },
2890
+ {
2891
+ "epoch": 1.23,
2892
+ "learning_rate": 6.823241630414095e-06,
2893
+ "loss": 0.6318,
2894
+ "step": 481
2895
+ },
2896
+ {
2897
+ "epoch": 1.23,
2898
+ "learning_rate": 6.78397013284728e-06,
2899
+ "loss": 0.1078,
2900
+ "step": 482
2901
+ },
2902
+ {
2903
+ "epoch": 1.24,
2904
+ "learning_rate": 6.744753878729574e-06,
2905
+ "loss": 0.623,
2906
+ "step": 483
2907
+ },
2908
+ {
2909
+ "epoch": 1.24,
2910
+ "learning_rate": 6.705593541699358e-06,
2911
+ "loss": 0.6514,
2912
+ "step": 484
2913
+ },
2914
+ {
2915
+ "epoch": 1.24,
2916
+ "learning_rate": 6.666489794434488e-06,
2917
+ "loss": 0.603,
2918
+ "step": 485
2919
+ },
2920
+ {
2921
+ "epoch": 1.24,
2922
+ "learning_rate": 6.627443308640749e-06,
2923
+ "loss": 0.6182,
2924
+ "step": 486
2925
+ },
2926
+ {
2927
+ "epoch": 1.25,
2928
+ "learning_rate": 6.588454755040322e-06,
2929
+ "loss": 0.1431,
2930
+ "step": 487
2931
+ },
2932
+ {
2933
+ "epoch": 1.25,
2934
+ "learning_rate": 6.549524803360249e-06,
2935
+ "loss": 0.6558,
2936
+ "step": 488
2937
+ },
2938
+ {
2939
+ "epoch": 1.25,
2940
+ "learning_rate": 6.5106541223209344e-06,
2941
+ "loss": 0.6006,
2942
+ "step": 489
2943
+ },
2944
+ {
2945
+ "epoch": 1.25,
2946
+ "learning_rate": 6.4718433796246685e-06,
2947
+ "loss": 0.6191,
2948
+ "step": 490
2949
+ },
2950
+ {
2951
+ "epoch": 1.26,
2952
+ "learning_rate": 6.433093241944142e-06,
2953
+ "loss": 0.6362,
2954
+ "step": 491
2955
+ },
2956
+ {
2957
+ "epoch": 1.26,
2958
+ "learning_rate": 6.394404374910996e-06,
2959
+ "loss": 0.6396,
2960
+ "step": 492
2961
+ },
2962
+ {
2963
+ "epoch": 1.26,
2964
+ "learning_rate": 6.355777443104409e-06,
2965
+ "loss": 0.0875,
2966
+ "step": 493
2967
+ },
2968
+ {
2969
+ "epoch": 1.26,
2970
+ "learning_rate": 6.317213110039652e-06,
2971
+ "loss": 0.1085,
2972
+ "step": 494
2973
+ },
2974
+ {
2975
+ "epoch": 1.27,
2976
+ "learning_rate": 6.278712038156705e-06,
2977
+ "loss": 0.5989,
2978
+ "step": 495
2979
+ },
2980
+ {
2981
+ "epoch": 1.27,
2982
+ "learning_rate": 6.240274888808884e-06,
2983
+ "loss": 0.6021,
2984
+ "step": 496
2985
+ },
2986
+ {
2987
+ "epoch": 1.27,
2988
+ "learning_rate": 6.201902322251471e-06,
2989
+ "loss": 0.1126,
2990
+ "step": 497
2991
+ },
2992
+ {
2993
+ "epoch": 1.27,
2994
+ "learning_rate": 6.16359499763037e-06,
2995
+ "loss": 0.5835,
2996
+ "step": 498
2997
+ },
2998
+ {
2999
+ "epoch": 1.28,
3000
+ "learning_rate": 6.125353572970798e-06,
3001
+ "loss": 0.0947,
3002
+ "step": 499
3003
+ },
3004
+ {
3005
+ "epoch": 1.28,
3006
+ "learning_rate": 6.087178705165969e-06,
3007
+ "loss": 0.5996,
3008
+ "step": 500
3009
+ },
3010
+ {
3011
+ "epoch": 1.28,
3012
+ "learning_rate": 6.049071049965811e-06,
3013
+ "loss": 0.6362,
3014
+ "step": 501
3015
+ },
3016
+ {
3017
+ "epoch": 1.28,
3018
+ "learning_rate": 6.011031261965716e-06,
3019
+ "loss": 0.6187,
3020
+ "step": 502
3021
+ },
3022
+ {
3023
+ "epoch": 1.29,
3024
+ "learning_rate": 5.973059994595277e-06,
3025
+ "loss": 0.6245,
3026
+ "step": 503
3027
+ },
3028
+ {
3029
+ "epoch": 1.29,
3030
+ "learning_rate": 5.9351579001070655e-06,
3031
+ "loss": 0.6147,
3032
+ "step": 504
3033
+ },
3034
+ {
3035
+ "epoch": 1.29,
3036
+ "learning_rate": 5.897325629565455e-06,
3037
+ "loss": 0.6172,
3038
+ "step": 505
3039
+ },
3040
+ {
3041
+ "epoch": 1.29,
3042
+ "learning_rate": 5.859563832835393e-06,
3043
+ "loss": 0.6099,
3044
+ "step": 506
3045
+ },
3046
+ {
3047
+ "epoch": 1.3,
3048
+ "learning_rate": 5.8218731585712716e-06,
3049
+ "loss": 0.6348,
3050
+ "step": 507
3051
+ },
3052
+ {
3053
+ "epoch": 1.3,
3054
+ "learning_rate": 5.784254254205779e-06,
3055
+ "loss": 0.5654,
3056
+ "step": 508
3057
+ },
3058
+ {
3059
+ "epoch": 1.3,
3060
+ "learning_rate": 5.746707765938764e-06,
3061
+ "loss": 0.6802,
3062
+ "step": 509
3063
+ },
3064
+ {
3065
+ "epoch": 1.3,
3066
+ "learning_rate": 5.70923433872615e-06,
3067
+ "loss": 0.5708,
3068
+ "step": 510
3069
+ },
3070
+ {
3071
+ "epoch": 1.31,
3072
+ "learning_rate": 5.671834616268861e-06,
3073
+ "loss": 0.623,
3074
+ "step": 511
3075
+ },
3076
+ {
3077
+ "epoch": 1.31,
3078
+ "learning_rate": 5.634509241001736e-06,
3079
+ "loss": 0.5696,
3080
+ "step": 512
3081
+ },
3082
+ {
3083
+ "epoch": 1.31,
3084
+ "learning_rate": 5.5972588540825245e-06,
3085
+ "loss": 0.5947,
3086
+ "step": 513
3087
+ },
3088
+ {
3089
+ "epoch": 1.31,
3090
+ "learning_rate": 5.5600840953808675e-06,
3091
+ "loss": 0.624,
3092
+ "step": 514
3093
+ },
3094
+ {
3095
+ "epoch": 1.32,
3096
+ "learning_rate": 5.52298560346729e-06,
3097
+ "loss": 0.6475,
3098
+ "step": 515
3099
+ },
3100
+ {
3101
+ "epoch": 1.32,
3102
+ "learning_rate": 5.485964015602243e-06,
3103
+ "loss": 0.6123,
3104
+ "step": 516
3105
+ },
3106
+ {
3107
+ "epoch": 1.32,
3108
+ "learning_rate": 5.449019967725161e-06,
3109
+ "loss": 0.6323,
3110
+ "step": 517
3111
+ },
3112
+ {
3113
+ "epoch": 1.32,
3114
+ "learning_rate": 5.412154094443527e-06,
3115
+ "loss": 0.5957,
3116
+ "step": 518
3117
+ },
3118
+ {
3119
+ "epoch": 1.33,
3120
+ "learning_rate": 5.375367029021979e-06,
3121
+ "loss": 0.6182,
3122
+ "step": 519
3123
+ },
3124
+ {
3125
+ "epoch": 1.33,
3126
+ "learning_rate": 5.338659403371438e-06,
3127
+ "loss": 0.6128,
3128
+ "step": 520
3129
+ },
3130
+ {
3131
+ "epoch": 1.33,
3132
+ "learning_rate": 5.302031848038241e-06,
3133
+ "loss": 0.1093,
3134
+ "step": 521
3135
+ },
3136
+ {
3137
+ "epoch": 1.34,
3138
+ "learning_rate": 5.265484992193302e-06,
3139
+ "loss": 0.1129,
3140
+ "step": 522
3141
+ },
3142
+ {
3143
+ "epoch": 1.34,
3144
+ "learning_rate": 5.229019463621341e-06,
3145
+ "loss": 0.6431,
3146
+ "step": 523
3147
+ },
3148
+ {
3149
+ "epoch": 1.34,
3150
+ "learning_rate": 5.19263588871006e-06,
3151
+ "loss": 0.6279,
3152
+ "step": 524
3153
+ },
3154
+ {
3155
+ "epoch": 1.34,
3156
+ "learning_rate": 5.156334892439405e-06,
3157
+ "loss": 0.5752,
3158
+ "step": 525
3159
+ },
3160
+ {
3161
+ "epoch": 1.35,
3162
+ "learning_rate": 5.120117098370824e-06,
3163
+ "loss": 0.6372,
3164
+ "step": 526
3165
+ },
3166
+ {
3167
+ "epoch": 1.35,
3168
+ "learning_rate": 5.0839831286365535e-06,
3169
+ "loss": 0.625,
3170
+ "step": 527
3171
+ },
3172
+ {
3173
+ "epoch": 1.35,
3174
+ "learning_rate": 5.047933603928936e-06,
3175
+ "loss": 0.6133,
3176
+ "step": 528
3177
+ },
3178
+ {
3179
+ "epoch": 1.35,
3180
+ "learning_rate": 5.011969143489769e-06,
3181
+ "loss": 0.6143,
3182
+ "step": 529
3183
+ },
3184
+ {
3185
+ "epoch": 1.36,
3186
+ "learning_rate": 4.976090365099638e-06,
3187
+ "loss": 0.0949,
3188
+ "step": 530
3189
+ },
3190
+ {
3191
+ "epoch": 1.36,
3192
+ "learning_rate": 4.940297885067333e-06,
3193
+ "loss": 0.6445,
3194
+ "step": 531
3195
+ },
3196
+ {
3197
+ "epoch": 1.36,
3198
+ "learning_rate": 4.904592318219249e-06,
3199
+ "loss": 0.6138,
3200
+ "step": 532
3201
+ },
3202
+ {
3203
+ "epoch": 1.36,
3204
+ "learning_rate": 4.868974277888826e-06,
3205
+ "loss": 0.6323,
3206
+ "step": 533
3207
+ },
3208
+ {
3209
+ "epoch": 1.37,
3210
+ "learning_rate": 4.833444375906013e-06,
3211
+ "loss": 0.6084,
3212
+ "step": 534
3213
+ },
3214
+ {
3215
+ "epoch": 1.37,
3216
+ "learning_rate": 4.798003222586773e-06,
3217
+ "loss": 0.11,
3218
+ "step": 535
3219
+ },
3220
+ {
3221
+ "epoch": 1.37,
3222
+ "learning_rate": 4.762651426722566e-06,
3223
+ "loss": 0.6152,
3224
+ "step": 536
3225
+ },
3226
+ {
3227
+ "epoch": 1.37,
3228
+ "learning_rate": 4.727389595569919e-06,
3229
+ "loss": 0.624,
3230
+ "step": 537
3231
+ },
3232
+ {
3233
+ "epoch": 1.38,
3234
+ "learning_rate": 4.6922183348399996e-06,
3235
+ "loss": 0.6055,
3236
+ "step": 538
3237
+ },
3238
+ {
3239
+ "epoch": 1.38,
3240
+ "learning_rate": 4.657138248688185e-06,
3241
+ "loss": 0.6436,
3242
+ "step": 539
3243
+ },
3244
+ {
3245
+ "epoch": 1.38,
3246
+ "learning_rate": 4.622149939703704e-06,
3247
+ "loss": 0.5967,
3248
+ "step": 540
3249
+ },
3250
+ {
3251
+ "epoch": 1.38,
3252
+ "learning_rate": 4.587254008899278e-06,
3253
+ "loss": 0.6069,
3254
+ "step": 541
3255
+ },
3256
+ {
3257
+ "epoch": 1.39,
3258
+ "learning_rate": 4.552451055700802e-06,
3259
+ "loss": 0.6333,
3260
+ "step": 542
3261
+ },
3262
+ {
3263
+ "epoch": 1.39,
3264
+ "learning_rate": 4.517741677937039e-06,
3265
+ "loss": 0.604,
3266
+ "step": 543
3267
+ },
3268
+ {
3269
+ "epoch": 1.39,
3270
+ "learning_rate": 4.483126471829371e-06,
3271
+ "loss": 0.6045,
3272
+ "step": 544
3273
+ },
3274
+ {
3275
+ "epoch": 1.39,
3276
+ "learning_rate": 4.448606031981534e-06,
3277
+ "loss": 0.1033,
3278
+ "step": 545
3279
+ },
3280
+ {
3281
+ "epoch": 1.4,
3282
+ "learning_rate": 4.414180951369405e-06,
3283
+ "loss": 0.0998,
3284
+ "step": 546
3285
+ },
3286
+ {
3287
+ "epoch": 1.4,
3288
+ "learning_rate": 4.379851821330842e-06,
3289
+ "loss": 0.6001,
3290
+ "step": 547
3291
+ },
3292
+ {
3293
+ "epoch": 1.4,
3294
+ "learning_rate": 4.345619231555503e-06,
3295
+ "loss": 0.624,
3296
+ "step": 548
3297
+ },
3298
+ {
3299
+ "epoch": 1.4,
3300
+ "learning_rate": 4.3114837700747205e-06,
3301
+ "loss": 0.0993,
3302
+ "step": 549
3303
+ },
3304
+ {
3305
+ "epoch": 1.41,
3306
+ "learning_rate": 4.277446023251401e-06,
3307
+ "loss": 0.0955,
3308
+ "step": 550
3309
+ },
3310
+ {
3311
+ "epoch": 1.41,
3312
+ "learning_rate": 4.243506575769958e-06,
3313
+ "loss": 0.1053,
3314
+ "step": 551
3315
+ },
3316
+ {
3317
+ "epoch": 1.41,
3318
+ "learning_rate": 4.209666010626262e-06,
3319
+ "loss": 0.5942,
3320
+ "step": 552
3321
+ },
3322
+ {
3323
+ "epoch": 1.41,
3324
+ "learning_rate": 4.175924909117638e-06,
3325
+ "loss": 0.5886,
3326
+ "step": 553
3327
+ },
3328
+ {
3329
+ "epoch": 1.42,
3330
+ "learning_rate": 4.142283850832862e-06,
3331
+ "loss": 0.6709,
3332
+ "step": 554
3333
+ },
3334
+ {
3335
+ "epoch": 1.42,
3336
+ "learning_rate": 4.108743413642219e-06,
3337
+ "loss": 0.0912,
3338
+ "step": 555
3339
+ },
3340
+ {
3341
+ "epoch": 1.42,
3342
+ "learning_rate": 4.0753041736875675e-06,
3343
+ "loss": 0.603,
3344
+ "step": 556
3345
+ },
3346
+ {
3347
+ "epoch": 1.42,
3348
+ "learning_rate": 4.041966705372453e-06,
3349
+ "loss": 0.5723,
3350
+ "step": 557
3351
+ },
3352
+ {
3353
+ "epoch": 1.43,
3354
+ "learning_rate": 4.008731581352229e-06,
3355
+ "loss": 0.645,
3356
+ "step": 558
3357
+ },
3358
+ {
3359
+ "epoch": 1.43,
3360
+ "learning_rate": 3.975599372524242e-06,
3361
+ "loss": 0.6177,
3362
+ "step": 559
3363
+ },
3364
+ {
3365
+ "epoch": 1.43,
3366
+ "learning_rate": 3.942570648017988e-06,
3367
+ "loss": 0.627,
3368
+ "step": 560
3369
+ },
3370
+ {
3371
+ "epoch": 1.43,
3372
+ "learning_rate": 3.90964597518537e-06,
3373
+ "loss": 0.5889,
3374
+ "step": 561
3375
+ },
3376
+ {
3377
+ "epoch": 1.44,
3378
+ "learning_rate": 3.876825919590944e-06,
3379
+ "loss": 0.1072,
3380
+ "step": 562
3381
+ },
3382
+ {
3383
+ "epoch": 1.44,
3384
+ "learning_rate": 3.844111045002193e-06,
3385
+ "loss": 0.1013,
3386
+ "step": 563
3387
+ },
3388
+ {
3389
+ "epoch": 1.44,
3390
+ "learning_rate": 3.8115019133798535e-06,
3391
+ "loss": 0.0995,
3392
+ "step": 564
3393
+ },
3394
+ {
3395
+ "epoch": 1.45,
3396
+ "learning_rate": 3.778999084868257e-06,
3397
+ "loss": 0.625,
3398
+ "step": 565
3399
+ },
3400
+ {
3401
+ "epoch": 1.45,
3402
+ "learning_rate": 3.74660311778571e-06,
3403
+ "loss": 0.6201,
3404
+ "step": 566
3405
+ },
3406
+ {
3407
+ "epoch": 1.45,
3408
+ "learning_rate": 3.714314568614904e-06,
3409
+ "loss": 0.6113,
3410
+ "step": 567
3411
+ },
3412
+ {
3413
+ "epoch": 1.45,
3414
+ "learning_rate": 3.682133991993361e-06,
3415
+ "loss": 0.6152,
3416
+ "step": 568
3417
+ },
3418
+ {
3419
+ "epoch": 1.46,
3420
+ "learning_rate": 3.6500619407038996e-06,
3421
+ "loss": 0.5557,
3422
+ "step": 569
3423
+ },
3424
+ {
3425
+ "epoch": 1.46,
3426
+ "learning_rate": 3.6180989656651268e-06,
3427
+ "loss": 0.5977,
3428
+ "step": 570
3429
+ },
3430
+ {
3431
+ "epoch": 1.46,
3432
+ "learning_rate": 3.5862456159220115e-06,
3433
+ "loss": 0.5938,
3434
+ "step": 571
3435
+ },
3436
+ {
3437
+ "epoch": 1.46,
3438
+ "learning_rate": 3.5545024386364192e-06,
3439
+ "loss": 0.5635,
3440
+ "step": 572
3441
+ },
3442
+ {
3443
+ "epoch": 1.47,
3444
+ "learning_rate": 3.522869979077723e-06,
3445
+ "loss": 0.6167,
3446
+ "step": 573
3447
+ },
3448
+ {
3449
+ "epoch": 1.47,
3450
+ "learning_rate": 3.491348780613444e-06,
3451
+ "loss": 0.1184,
3452
+ "step": 574
3453
+ },
3454
+ {
3455
+ "epoch": 1.47,
3456
+ "learning_rate": 3.4599393846999087e-06,
3457
+ "loss": 0.6538,
3458
+ "step": 575
3459
+ },
3460
+ {
3461
+ "epoch": 1.47,
3462
+ "learning_rate": 3.4286423308729523e-06,
3463
+ "loss": 0.6182,
3464
+ "step": 576
3465
+ },
3466
+ {
3467
+ "epoch": 1.48,
3468
+ "learning_rate": 3.3974581567386567e-06,
3469
+ "loss": 0.6304,
3470
+ "step": 577
3471
+ },
3472
+ {
3473
+ "epoch": 1.48,
3474
+ "learning_rate": 3.3663873979641014e-06,
3475
+ "loss": 0.6016,
3476
+ "step": 578
3477
+ },
3478
+ {
3479
+ "epoch": 1.48,
3480
+ "learning_rate": 3.3354305882681747e-06,
3481
+ "loss": 0.6646,
3482
+ "step": 579
3483
+ },
3484
+ {
3485
+ "epoch": 1.48,
3486
+ "learning_rate": 3.304588259412399e-06,
3487
+ "loss": 0.6001,
3488
+ "step": 580
3489
+ },
3490
+ {
3491
+ "epoch": 1.49,
3492
+ "learning_rate": 3.2738609411918e-06,
3493
+ "loss": 0.613,
3494
+ "step": 581
3495
+ },
3496
+ {
3497
+ "epoch": 1.49,
3498
+ "learning_rate": 3.243249161425801e-06,
3499
+ "loss": 0.5913,
3500
+ "step": 582
3501
+ },
3502
+ {
3503
+ "epoch": 1.49,
3504
+ "learning_rate": 3.2127534459491715e-06,
3505
+ "loss": 0.6362,
3506
+ "step": 583
3507
+ },
3508
+ {
3509
+ "epoch": 1.49,
3510
+ "learning_rate": 3.1823743186029676e-06,
3511
+ "loss": 0.6099,
3512
+ "step": 584
3513
+ },
3514
+ {
3515
+ "epoch": 1.5,
3516
+ "learning_rate": 3.1521123012255563e-06,
3517
+ "loss": 0.6162,
3518
+ "step": 585
3519
+ },
3520
+ {
3521
+ "epoch": 1.5,
3522
+ "learning_rate": 3.1219679136436496e-06,
3523
+ "loss": 0.6211,
3524
+ "step": 586
3525
+ },
3526
+ {
3527
+ "epoch": 1.5,
3528
+ "learning_rate": 3.0919416736633643e-06,
3529
+ "loss": 0.6226,
3530
+ "step": 587
3531
+ },
3532
+ {
3533
+ "epoch": 1.5,
3534
+ "learning_rate": 3.062034097061335e-06,
3535
+ "loss": 0.091,
3536
+ "step": 588
3537
+ },
3538
+ {
3539
+ "epoch": 1.51,
3540
+ "learning_rate": 3.0322456975758507e-06,
3541
+ "loss": 0.6191,
3542
+ "step": 589
3543
+ },
3544
+ {
3545
+ "epoch": 1.51,
3546
+ "learning_rate": 3.0025769868980337e-06,
3547
+ "loss": 0.6123,
3548
+ "step": 590
3549
+ },
3550
+ {
3551
+ "epoch": 1.51,
3552
+ "learning_rate": 2.9730284746630454e-06,
3553
+ "loss": 0.5996,
3554
+ "step": 591
3555
+ },
3556
+ {
3557
+ "epoch": 1.51,
3558
+ "learning_rate": 2.9436006684413444e-06,
3559
+ "loss": 0.6406,
3560
+ "step": 592
3561
+ },
3562
+ {
3563
+ "epoch": 1.52,
3564
+ "learning_rate": 2.9142940737299486e-06,
3565
+ "loss": 0.1161,
3566
+ "step": 593
3567
+ },
3568
+ {
3569
+ "epoch": 1.52,
3570
+ "learning_rate": 2.88510919394376e-06,
3571
+ "loss": 0.1031,
3572
+ "step": 594
3573
+ },
3574
+ {
3575
+ "epoch": 1.52,
3576
+ "learning_rate": 2.8560465304069217e-06,
3577
+ "loss": 0.6021,
3578
+ "step": 595
3579
+ },
3580
+ {
3581
+ "epoch": 1.52,
3582
+ "learning_rate": 2.827106582344212e-06,
3583
+ "loss": 0.6138,
3584
+ "step": 596
3585
+ },
3586
+ {
3587
+ "epoch": 1.53,
3588
+ "learning_rate": 2.7982898468724496e-06,
3589
+ "loss": 0.6128,
3590
+ "step": 597
3591
+ },
3592
+ {
3593
+ "epoch": 1.53,
3594
+ "learning_rate": 2.7695968189919686e-06,
3595
+ "loss": 0.0927,
3596
+ "step": 598
3597
+ },
3598
+ {
3599
+ "epoch": 1.53,
3600
+ "learning_rate": 2.7410279915781124e-06,
3601
+ "loss": 0.6274,
3602
+ "step": 599
3603
+ },
3604
+ {
3605
+ "epoch": 1.53,
3606
+ "learning_rate": 2.712583855372769e-06,
3607
+ "loss": 0.5781,
3608
+ "step": 600
3609
+ },
3610
+ {
3611
+ "epoch": 1.54,
3612
+ "learning_rate": 2.6842648989759325e-06,
3613
+ "loss": 0.6211,
3614
+ "step": 601
3615
+ },
3616
+ {
3617
+ "epoch": 1.54,
3618
+ "learning_rate": 2.6560716088373295e-06,
3619
+ "loss": 0.625,
3620
+ "step": 602
3621
+ },
3622
+ {
3623
+ "epoch": 1.54,
3624
+ "learning_rate": 2.628004469248043e-06,
3625
+ "loss": 0.5903,
3626
+ "step": 603
3627
+ },
3628
+ {
3629
+ "epoch": 1.54,
3630
+ "learning_rate": 2.6000639623321934e-06,
3631
+ "loss": 0.6143,
3632
+ "step": 604
3633
+ },
3634
+ {
3635
+ "epoch": 1.55,
3636
+ "learning_rate": 2.572250568038681e-06,
3637
+ "loss": 0.6152,
3638
+ "step": 605
3639
+ },
3640
+ {
3641
+ "epoch": 1.55,
3642
+ "learning_rate": 2.5445647641329154e-06,
3643
+ "loss": 0.5664,
3644
+ "step": 606
3645
+ },
3646
+ {
3647
+ "epoch": 1.55,
3648
+ "learning_rate": 2.517007026188619e-06,
3649
+ "loss": 0.6284,
3650
+ "step": 607
3651
+ },
3652
+ {
3653
+ "epoch": 1.55,
3654
+ "learning_rate": 2.489577827579659e-06,
3655
+ "loss": 0.6401,
3656
+ "step": 608
3657
+ },
3658
+ {
3659
+ "epoch": 1.56,
3660
+ "learning_rate": 2.462277639471914e-06,
3661
+ "loss": 0.644,
3662
+ "step": 609
3663
+ },
3664
+ {
3665
+ "epoch": 1.56,
3666
+ "learning_rate": 2.4351069308151774e-06,
3667
+ "loss": 0.613,
3668
+ "step": 610
3669
+ },
3670
+ {
3671
+ "epoch": 1.56,
3672
+ "learning_rate": 2.4080661683351146e-06,
3673
+ "loss": 0.5991,
3674
+ "step": 611
3675
+ },
3676
+ {
3677
+ "epoch": 1.57,
3678
+ "learning_rate": 2.381155816525228e-06,
3679
+ "loss": 0.584,
3680
+ "step": 612
3681
+ },
3682
+ {
3683
+ "epoch": 1.57,
3684
+ "learning_rate": 2.3543763376388906e-06,
3685
+ "loss": 0.605,
3686
+ "step": 613
3687
+ },
3688
+ {
3689
+ "epoch": 1.57,
3690
+ "learning_rate": 2.3277281916814e-06,
3691
+ "loss": 0.5823,
3692
+ "step": 614
3693
+ },
3694
+ {
3695
+ "epoch": 1.57,
3696
+ "learning_rate": 2.3012118364020787e-06,
3697
+ "loss": 0.625,
3698
+ "step": 615
3699
+ },
3700
+ {
3701
+ "epoch": 1.58,
3702
+ "learning_rate": 2.2748277272864108e-06,
3703
+ "loss": 0.5996,
3704
+ "step": 616
3705
+ },
3706
+ {
3707
+ "epoch": 1.58,
3708
+ "learning_rate": 2.2485763175482255e-06,
3709
+ "loss": 0.5596,
3710
+ "step": 617
3711
+ },
3712
+ {
3713
+ "epoch": 1.58,
3714
+ "learning_rate": 2.222458058121889e-06,
3715
+ "loss": 0.6191,
3716
+ "step": 618
3717
+ },
3718
+ {
3719
+ "epoch": 1.58,
3720
+ "learning_rate": 2.196473397654585e-06,
3721
+ "loss": 0.5542,
3722
+ "step": 619
3723
+ },
3724
+ {
3725
+ "epoch": 1.59,
3726
+ "learning_rate": 2.170622782498598e-06,
3727
+ "loss": 0.5752,
3728
+ "step": 620
3729
+ },
3730
+ {
3731
+ "epoch": 1.59,
3732
+ "learning_rate": 2.1449066567036413e-06,
3733
+ "loss": 0.6426,
3734
+ "step": 621
3735
+ },
3736
+ {
3737
+ "epoch": 1.59,
3738
+ "learning_rate": 2.119325462009233e-06,
3739
+ "loss": 0.5957,
3740
+ "step": 622
3741
+ },
3742
+ {
3743
+ "epoch": 1.59,
3744
+ "learning_rate": 2.0938796378371084e-06,
3745
+ "loss": 0.5688,
3746
+ "step": 623
3747
+ },
3748
+ {
3749
+ "epoch": 1.6,
3750
+ "learning_rate": 2.0685696212836737e-06,
3751
+ "loss": 0.0952,
3752
+ "step": 624
3753
+ },
3754
+ {
3755
+ "epoch": 1.6,
3756
+ "learning_rate": 2.0433958471124903e-06,
3757
+ "loss": 0.5864,
3758
+ "step": 625
3759
+ },
3760
+ {
3761
+ "epoch": 1.6,
3762
+ "learning_rate": 2.0183587477468226e-06,
3763
+ "loss": 0.6099,
3764
+ "step": 626
3765
+ },
3766
+ {
3767
+ "epoch": 1.6,
3768
+ "learning_rate": 1.9934587532621917e-06,
3769
+ "loss": 0.5986,
3770
+ "step": 627
3771
+ },
3772
+ {
3773
+ "epoch": 1.61,
3774
+ "learning_rate": 1.9686962913789897e-06,
3775
+ "loss": 0.5869,
3776
+ "step": 628
3777
+ },
3778
+ {
3779
+ "epoch": 1.61,
3780
+ "learning_rate": 1.9440717874551527e-06,
3781
+ "loss": 0.1058,
3782
+ "step": 629
3783
+ },
3784
+ {
3785
+ "epoch": 1.61,
3786
+ "learning_rate": 1.91958566447883e-06,
3787
+ "loss": 0.5723,
3788
+ "step": 630
3789
+ },
3790
+ {
3791
+ "epoch": 1.61,
3792
+ "learning_rate": 1.8952383430611299e-06,
3793
+ "loss": 0.5918,
3794
+ "step": 631
3795
+ },
3796
+ {
3797
+ "epoch": 1.62,
3798
+ "learning_rate": 1.871030241428894e-06,
3799
+ "loss": 0.5747,
3800
+ "step": 632
3801
+ },
3802
+ {
3803
+ "epoch": 1.62,
3804
+ "learning_rate": 1.8469617754175106e-06,
3805
+ "loss": 0.5981,
3806
+ "step": 633
3807
+ },
3808
+ {
3809
+ "epoch": 1.62,
3810
+ "learning_rate": 1.8230333584637715e-06,
3811
+ "loss": 0.604,
3812
+ "step": 634
3813
+ },
3814
+ {
3815
+ "epoch": 1.62,
3816
+ "learning_rate": 1.7992454015987791e-06,
3817
+ "loss": 0.106,
3818
+ "step": 635
3819
+ },
3820
+ {
3821
+ "epoch": 1.63,
3822
+ "learning_rate": 1.7755983134408706e-06,
3823
+ "loss": 0.5962,
3824
+ "step": 636
3825
+ },
3826
+ {
3827
+ "epoch": 1.63,
3828
+ "learning_rate": 1.752092500188608e-06,
3829
+ "loss": 0.1136,
3830
+ "step": 637
3831
+ },
3832
+ {
3833
+ "epoch": 1.63,
3834
+ "learning_rate": 1.7287283656138009e-06,
3835
+ "loss": 0.6311,
3836
+ "step": 638
3837
+ },
3838
+ {
3839
+ "epoch": 1.63,
3840
+ "learning_rate": 1.70550631105457e-06,
3841
+ "loss": 0.6108,
3842
+ "step": 639
3843
+ },
3844
+ {
3845
+ "epoch": 1.64,
3846
+ "learning_rate": 1.6824267354084478e-06,
3847
+ "loss": 0.6206,
3848
+ "step": 640
3849
+ },
3850
+ {
3851
+ "epoch": 1.64,
3852
+ "learning_rate": 1.6594900351255427e-06,
3853
+ "loss": 0.6021,
3854
+ "step": 641
3855
+ },
3856
+ {
3857
+ "epoch": 1.64,
3858
+ "learning_rate": 1.6366966042016996e-06,
3859
+ "loss": 0.6143,
3860
+ "step": 642
3861
+ },
3862
+ {
3863
+ "epoch": 1.64,
3864
+ "learning_rate": 1.6140468341717607e-06,
3865
+ "loss": 0.5967,
3866
+ "step": 643
3867
+ },
3868
+ {
3869
+ "epoch": 1.65,
3870
+ "learning_rate": 1.5915411141028325e-06,
3871
+ "loss": 0.6333,
3872
+ "step": 644
3873
+ },
3874
+ {
3875
+ "epoch": 1.65,
3876
+ "learning_rate": 1.5691798305875893e-06,
3877
+ "loss": 0.6016,
3878
+ "step": 645
3879
+ },
3880
+ {
3881
+ "epoch": 1.65,
3882
+ "learning_rate": 1.5469633677376494e-06,
3883
+ "loss": 0.6108,
3884
+ "step": 646
3885
+ },
3886
+ {
3887
+ "epoch": 1.65,
3888
+ "learning_rate": 1.524892107176964e-06,
3889
+ "loss": 0.0956,
3890
+ "step": 647
3891
+ },
3892
+ {
3893
+ "epoch": 1.66,
3894
+ "learning_rate": 1.502966428035274e-06,
3895
+ "loss": 0.6152,
3896
+ "step": 648
3897
+ },
3898
+ {
3899
+ "epoch": 1.66,
3900
+ "learning_rate": 1.4811867069415832e-06,
3901
+ "loss": 0.6001,
3902
+ "step": 649
3903
+ },
3904
+ {
3905
+ "epoch": 1.66,
3906
+ "learning_rate": 1.4595533180177058e-06,
3907
+ "loss": 0.5847,
3908
+ "step": 650
3909
+ },
3910
+ {
3911
+ "epoch": 1.66,
3912
+ "learning_rate": 1.4380666328718274e-06,
3913
+ "loss": 0.6084,
3914
+ "step": 651
3915
+ },
3916
+ {
3917
+ "epoch": 1.67,
3918
+ "learning_rate": 1.4167270205921168e-06,
3919
+ "loss": 0.5581,
3920
+ "step": 652
3921
+ },
3922
+ {
3923
+ "epoch": 1.67,
3924
+ "learning_rate": 1.3955348477404073e-06,
3925
+ "loss": 0.6079,
3926
+ "step": 653
3927
+ },
3928
+ {
3929
+ "epoch": 1.67,
3930
+ "learning_rate": 1.37449047834588e-06,
3931
+ "loss": 0.6348,
3932
+ "step": 654
3933
+ },
3934
+ {
3935
+ "epoch": 1.68,
3936
+ "learning_rate": 1.3535942738988194e-06,
3937
+ "loss": 0.5818,
3938
+ "step": 655
3939
+ },
3940
+ {
3941
+ "epoch": 1.68,
3942
+ "learning_rate": 1.332846593344399e-06,
3943
+ "loss": 0.6045,
3944
+ "step": 656
3945
+ },
3946
+ {
3947
+ "epoch": 1.68,
3948
+ "learning_rate": 1.3122477930765243e-06,
3949
+ "loss": 0.6196,
3950
+ "step": 657
3951
+ },
3952
+ {
3953
+ "epoch": 1.68,
3954
+ "learning_rate": 1.2917982269316975e-06,
3955
+ "loss": 0.5854,
3956
+ "step": 658
3957
+ },
3958
+ {
3959
+ "epoch": 1.69,
3960
+ "learning_rate": 1.2714982461829572e-06,
3961
+ "loss": 0.5547,
3962
+ "step": 659
3963
+ },
3964
+ {
3965
+ "epoch": 1.69,
3966
+ "learning_rate": 1.2513481995338284e-06,
3967
+ "loss": 0.5737,
3968
+ "step": 660
3969
+ },
3970
+ {
3971
+ "epoch": 1.69,
3972
+ "learning_rate": 1.2313484331123371e-06,
3973
+ "loss": 0.6182,
3974
+ "step": 661
3975
+ },
3976
+ {
3977
+ "epoch": 1.69,
3978
+ "learning_rate": 1.211499290465069e-06,
3979
+ "loss": 0.5972,
3980
+ "step": 662
3981
+ },
3982
+ {
3983
+ "epoch": 1.7,
3984
+ "learning_rate": 1.1918011125512651e-06,
3985
+ "loss": 0.6479,
3986
+ "step": 663
3987
+ },
3988
+ {
3989
+ "epoch": 1.7,
3990
+ "learning_rate": 1.1722542377369639e-06,
3991
+ "loss": 0.6177,
3992
+ "step": 664
3993
+ },
3994
+ {
3995
+ "epoch": 1.7,
3996
+ "learning_rate": 1.152859001789196e-06,
3997
+ "loss": 0.5579,
3998
+ "step": 665
3999
+ },
4000
+ {
4001
+ "epoch": 1.7,
4002
+ "learning_rate": 1.1336157378702017e-06,
4003
+ "loss": 0.1103,
4004
+ "step": 666
4005
+ },
4006
+ {
4007
+ "epoch": 1.71,
4008
+ "learning_rate": 1.1145247765317192e-06,
4009
+ "loss": 0.0921,
4010
+ "step": 667
4011
+ },
4012
+ {
4013
+ "epoch": 1.71,
4014
+ "learning_rate": 1.0955864457093147e-06,
4015
+ "loss": 0.1014,
4016
+ "step": 668
4017
+ },
4018
+ {
4019
+ "epoch": 1.71,
4020
+ "learning_rate": 1.0768010707167265e-06,
4021
+ "loss": 0.6294,
4022
+ "step": 669
4023
+ },
4024
+ {
4025
+ "epoch": 1.71,
4026
+ "learning_rate": 1.0581689742402967e-06,
4027
+ "loss": 0.6328,
4028
+ "step": 670
4029
+ },
4030
+ {
4031
+ "epoch": 1.72,
4032
+ "learning_rate": 1.0396904763334182e-06,
4033
+ "loss": 0.5898,
4034
+ "step": 671
4035
+ },
4036
+ {
4037
+ "epoch": 1.72,
4038
+ "learning_rate": 1.0213658944110406e-06,
4039
+ "loss": 0.0984,
4040
+ "step": 672
4041
+ },
4042
+ {
4043
+ "epoch": 1.72,
4044
+ "learning_rate": 1.0031955432442153e-06,
4045
+ "loss": 0.5884,
4046
+ "step": 673
4047
+ },
4048
+ {
4049
+ "epoch": 1.72,
4050
+ "learning_rate": 9.851797349546977e-07,
4051
+ "loss": 0.6187,
4052
+ "step": 674
4053
+ },
4054
+ {
4055
+ "epoch": 1.73,
4056
+ "learning_rate": 9.673187790095707e-07,
4057
+ "loss": 0.5806,
4058
+ "step": 675
4059
+ },
4060
+ {
4061
+ "epoch": 1.73,
4062
+ "learning_rate": 9.496129822159339e-07,
4063
+ "loss": 0.6357,
4064
+ "step": 676
4065
+ },
4066
+ {
4067
+ "epoch": 1.73,
4068
+ "learning_rate": 9.320626487156459e-07,
4069
+ "loss": 0.5703,
4070
+ "step": 677
4071
+ },
4072
+ {
4073
+ "epoch": 1.73,
4074
+ "learning_rate": 9.146680799800833e-07,
4075
+ "loss": 0.6267,
4076
+ "step": 678
4077
+ },
4078
+ {
4079
+ "epoch": 1.74,
4080
+ "learning_rate": 8.974295748049711e-07,
4081
+ "loss": 0.6074,
4082
+ "step": 679
4083
+ },
4084
+ {
4085
+ "epoch": 1.74,
4086
+ "learning_rate": 8.803474293052438e-07,
4087
+ "loss": 0.6182,
4088
+ "step": 680
4089
+ },
4090
+ {
4091
+ "epoch": 1.74,
4092
+ "learning_rate": 8.634219369099694e-07,
4093
+ "loss": 0.5918,
4094
+ "step": 681
4095
+ },
4096
+ {
4097
+ "epoch": 1.74,
4098
+ "learning_rate": 8.466533883572947e-07,
4099
+ "loss": 0.5854,
4100
+ "step": 682
4101
+ },
4102
+ {
4103
+ "epoch": 1.75,
4104
+ "learning_rate": 8.300420716894685e-07,
4105
+ "loss": 0.5869,
4106
+ "step": 683
4107
+ },
4108
+ {
4109
+ "epoch": 1.75,
4110
+ "learning_rate": 8.135882722478772e-07,
4111
+ "loss": 0.1112,
4112
+ "step": 684
4113
+ },
4114
+ {
4115
+ "epoch": 1.75,
4116
+ "learning_rate": 7.972922726681509e-07,
4117
+ "loss": 0.626,
4118
+ "step": 685
4119
+ },
4120
+ {
4121
+ "epoch": 1.75,
4122
+ "learning_rate": 7.811543528753108e-07,
4123
+ "loss": 0.6582,
4124
+ "step": 686
4125
+ },
4126
+ {
4127
+ "epoch": 1.76,
4128
+ "learning_rate": 7.651747900789552e-07,
4129
+ "loss": 0.5686,
4130
+ "step": 687
4131
+ },
4132
+ {
4133
+ "epoch": 1.76,
4134
+ "learning_rate": 7.493538587685012e-07,
4135
+ "loss": 0.5515,
4136
+ "step": 688
4137
+ },
4138
+ {
4139
+ "epoch": 1.76,
4140
+ "learning_rate": 7.336918307084718e-07,
4141
+ "loss": 0.6455,
4142
+ "step": 689
4143
+ },
4144
+ {
4145
+ "epoch": 1.76,
4146
+ "learning_rate": 7.181889749338178e-07,
4147
+ "loss": 0.5854,
4148
+ "step": 690
4149
+ },
4150
+ {
4151
+ "epoch": 1.77,
4152
+ "learning_rate": 7.028455577453075e-07,
4153
+ "loss": 0.6216,
4154
+ "step": 691
4155
+ },
4156
+ {
4157
+ "epoch": 1.77,
4158
+ "learning_rate": 6.876618427049509e-07,
4159
+ "loss": 0.6499,
4160
+ "step": 692
4161
+ },
4162
+ {
4163
+ "epoch": 1.77,
4164
+ "learning_rate": 6.726380906314655e-07,
4165
+ "loss": 0.6499,
4166
+ "step": 693
4167
+ },
4168
+ {
4169
+ "epoch": 1.77,
4170
+ "learning_rate": 6.577745595958018e-07,
4171
+ "loss": 0.5977,
4172
+ "step": 694
4173
+ },
4174
+ {
4175
+ "epoch": 1.78,
4176
+ "learning_rate": 6.430715049167069e-07,
4177
+ "loss": 0.1055,
4178
+ "step": 695
4179
+ },
4180
+ {
4181
+ "epoch": 1.78,
4182
+ "learning_rate": 6.285291791563431e-07,
4183
+ "loss": 0.6255,
4184
+ "step": 696
4185
+ },
4186
+ {
4187
+ "epoch": 1.78,
4188
+ "learning_rate": 6.141478321159422e-07,
4189
+ "loss": 0.5654,
4190
+ "step": 697
4191
+ },
4192
+ {
4193
+ "epoch": 1.79,
4194
+ "learning_rate": 5.999277108315272e-07,
4195
+ "loss": 0.0991,
4196
+ "step": 698
4197
+ },
4198
+ {
4199
+ "epoch": 1.79,
4200
+ "learning_rate": 5.858690595696559e-07,
4201
+ "loss": 0.625,
4202
+ "step": 699
4203
+ },
4204
+ {
4205
+ "epoch": 1.79,
4206
+ "learning_rate": 5.719721198232254e-07,
4207
+ "loss": 0.0953,
4208
+ "step": 700
4209
+ },
4210
+ {
4211
+ "epoch": 1.79,
4212
+ "learning_rate": 5.582371303073386e-07,
4213
+ "loss": 0.5994,
4214
+ "step": 701
4215
+ },
4216
+ {
4217
+ "epoch": 1.8,
4218
+ "learning_rate": 5.446643269551854e-07,
4219
+ "loss": 0.1088,
4220
+ "step": 702
4221
+ },
4222
+ {
4223
+ "epoch": 1.8,
4224
+ "learning_rate": 5.312539429140018e-07,
4225
+ "loss": 0.1089,
4226
+ "step": 703
4227
+ },
4228
+ {
4229
+ "epoch": 1.8,
4230
+ "learning_rate": 5.180062085410609e-07,
4231
+ "loss": 0.6082,
4232
+ "step": 704
4233
+ },
4234
+ {
4235
+ "epoch": 1.8,
4236
+ "learning_rate": 5.049213513997142e-07,
4237
+ "loss": 0.5894,
4238
+ "step": 705
4239
+ },
4240
+ {
4241
+ "epoch": 1.81,
4242
+ "learning_rate": 4.919995962554846e-07,
4243
+ "loss": 0.5762,
4244
+ "step": 706
4245
+ },
4246
+ {
4247
+ "epoch": 1.81,
4248
+ "learning_rate": 4.792411650722117e-07,
4249
+ "loss": 0.0939,
4250
+ "step": 707
4251
+ },
4252
+ {
4253
+ "epoch": 1.81,
4254
+ "learning_rate": 4.6664627700822475e-07,
4255
+ "loss": 0.5874,
4256
+ "step": 708
4257
+ },
4258
+ {
4259
+ "epoch": 1.81,
4260
+ "learning_rate": 4.5421514841259115e-07,
4261
+ "loss": 0.6123,
4262
+ "step": 709
4263
+ },
4264
+ {
4265
+ "epoch": 1.82,
4266
+ "learning_rate": 4.4194799282139324e-07,
4267
+ "loss": 0.5859,
4268
+ "step": 710
4269
+ },
4270
+ {
4271
+ "epoch": 1.82,
4272
+ "learning_rate": 4.298450209540628e-07,
4273
+ "loss": 0.0967,
4274
+ "step": 711
4275
+ },
4276
+ {
4277
+ "epoch": 1.82,
4278
+ "learning_rate": 4.1790644070975884e-07,
4279
+ "loss": 0.6067,
4280
+ "step": 712
4281
+ },
4282
+ {
4283
+ "epoch": 1.82,
4284
+ "learning_rate": 4.061324571638048e-07,
4285
+ "loss": 0.1036,
4286
+ "step": 713
4287
+ },
4288
+ {
4289
+ "epoch": 1.83,
4290
+ "learning_rate": 3.94523272564149e-07,
4291
+ "loss": 0.6001,
4292
+ "step": 714
4293
+ },
4294
+ {
4295
+ "epoch": 1.83,
4296
+ "learning_rate": 3.830790863279088e-07,
4297
+ "loss": 0.6313,
4298
+ "step": 715
4299
+ },
4300
+ {
4301
+ "epoch": 1.83,
4302
+ "learning_rate": 3.7180009503793745e-07,
4303
+ "loss": 0.5474,
4304
+ "step": 716
4305
+ },
4306
+ {
4307
+ "epoch": 1.83,
4308
+ "learning_rate": 3.6068649243944267e-07,
4309
+ "loss": 0.6123,
4310
+ "step": 717
4311
+ },
4312
+ {
4313
+ "epoch": 1.84,
4314
+ "learning_rate": 3.4973846943666567e-07,
4315
+ "loss": 0.6108,
4316
+ "step": 718
4317
+ },
4318
+ {
4319
+ "epoch": 1.84,
4320
+ "learning_rate": 3.3895621408959744e-07,
4321
+ "loss": 0.5747,
4322
+ "step": 719
4323
+ },
4324
+ {
4325
+ "epoch": 1.84,
4326
+ "learning_rate": 3.283399116107533e-07,
4327
+ "loss": 0.5728,
4328
+ "step": 720
4329
+ },
4330
+ {
4331
+ "epoch": 1.84,
4332
+ "learning_rate": 3.1788974436198326e-07,
4333
+ "loss": 0.6055,
4334
+ "step": 721
4335
+ },
4336
+ {
4337
+ "epoch": 1.85,
4338
+ "learning_rate": 3.076058918513503e-07,
4339
+ "loss": 0.0818,
4340
+ "step": 722
4341
+ },
4342
+ {
4343
+ "epoch": 1.85,
4344
+ "learning_rate": 2.974885307300379e-07,
4345
+ "loss": 0.1096,
4346
+ "step": 723
4347
+ },
4348
+ {
4349
+ "epoch": 1.85,
4350
+ "learning_rate": 2.875378347893165e-07,
4351
+ "loss": 0.6123,
4352
+ "step": 724
4353
+ },
4354
+ {
4355
+ "epoch": 1.85,
4356
+ "learning_rate": 2.7775397495756527e-07,
4357
+ "loss": 0.5845,
4358
+ "step": 725
4359
+ },
4360
+ {
4361
+ "epoch": 1.86,
4362
+ "learning_rate": 2.681371192973281e-07,
4363
+ "loss": 0.6021,
4364
+ "step": 726
4365
+ },
4366
+ {
4367
+ "epoch": 1.86,
4368
+ "learning_rate": 2.5868743300242913e-07,
4369
+ "loss": 0.092,
4370
+ "step": 727
4371
+ },
4372
+ {
4373
+ "epoch": 1.86,
4374
+ "learning_rate": 2.494050783951396e-07,
4375
+ "loss": 0.6196,
4376
+ "step": 728
4377
+ },
4378
+ {
4379
+ "epoch": 1.86,
4380
+ "learning_rate": 2.402902149233799e-07,
4381
+ "loss": 0.6021,
4382
+ "step": 729
4383
+ },
4384
+ {
4385
+ "epoch": 1.87,
4386
+ "learning_rate": 2.3134299915799185e-07,
4387
+ "loss": 0.6143,
4388
+ "step": 730
4389
+ },
4390
+ {
4391
+ "epoch": 1.87,
4392
+ "learning_rate": 2.2256358479004092e-07,
4393
+ "loss": 0.603,
4394
+ "step": 731
4395
+ },
4396
+ {
4397
+ "epoch": 1.87,
4398
+ "learning_rate": 2.1395212262817933e-07,
4399
+ "loss": 0.5972,
4400
+ "step": 732
4401
+ },
4402
+ {
4403
+ "epoch": 1.87,
4404
+ "learning_rate": 2.0550876059605597e-07,
4405
+ "loss": 0.573,
4406
+ "step": 733
4407
+ },
4408
+ {
4409
+ "epoch": 1.88,
4410
+ "learning_rate": 1.9723364372977395e-07,
4411
+ "loss": 0.6191,
4412
+ "step": 734
4413
+ },
4414
+ {
4415
+ "epoch": 1.88,
4416
+ "learning_rate": 1.8912691417540152e-07,
4417
+ "loss": 0.6084,
4418
+ "step": 735
4419
+ },
4420
+ {
4421
+ "epoch": 1.88,
4422
+ "learning_rate": 1.8118871118652516e-07,
4423
+ "loss": 0.5981,
4424
+ "step": 736
4425
+ },
4426
+ {
4427
+ "epoch": 1.88,
4428
+ "learning_rate": 1.7341917112186801e-07,
4429
+ "loss": 0.1162,
4430
+ "step": 737
4431
+ },
4432
+ {
4433
+ "epoch": 1.89,
4434
+ "learning_rate": 1.6581842744293309e-07,
4435
+ "loss": 0.6016,
4436
+ "step": 738
4437
+ },
4438
+ {
4439
+ "epoch": 1.89,
4440
+ "learning_rate": 1.5838661071172268e-07,
4441
+ "loss": 0.5901,
4442
+ "step": 739
4443
+ },
4444
+ {
4445
+ "epoch": 1.89,
4446
+ "learning_rate": 1.511238485884914e-07,
4447
+ "loss": 0.5793,
4448
+ "step": 740
4449
+ },
4450
+ {
4451
+ "epoch": 1.9,
4452
+ "learning_rate": 1.4403026582955337e-07,
4453
+ "loss": 0.1075,
4454
+ "step": 741
4455
+ },
4456
+ {
4457
+ "epoch": 1.9,
4458
+ "learning_rate": 1.3710598428513634e-07,
4459
+ "loss": 0.5742,
4460
+ "step": 742
4461
+ },
4462
+ {
4463
+ "epoch": 1.9,
4464
+ "learning_rate": 1.3035112289729423e-07,
4465
+ "loss": 0.604,
4466
+ "step": 743
4467
+ },
4468
+ {
4469
+ "epoch": 1.9,
4470
+ "learning_rate": 1.2376579769786124e-07,
4471
+ "loss": 0.1082,
4472
+ "step": 744
4473
+ },
4474
+ {
4475
+ "epoch": 1.91,
4476
+ "learning_rate": 1.1735012180645544e-07,
4477
+ "loss": 0.6028,
4478
+ "step": 745
4479
+ },
4480
+ {
4481
+ "epoch": 1.91,
4482
+ "learning_rate": 1.1110420542854383e-07,
4483
+ "loss": 0.605,
4484
+ "step": 746
4485
+ },
4486
+ {
4487
+ "epoch": 1.91,
4488
+ "learning_rate": 1.0502815585354042e-07,
4489
+ "loss": 0.6184,
4490
+ "step": 747
4491
+ },
4492
+ {
4493
+ "epoch": 1.91,
4494
+ "learning_rate": 9.912207745296665e-08,
4495
+ "loss": 0.5801,
4496
+ "step": 748
4497
+ },
4498
+ {
4499
+ "epoch": 1.92,
4500
+ "learning_rate": 9.338607167866276e-08,
4501
+ "loss": 0.0825,
4502
+ "step": 749
4503
+ },
4504
+ {
4505
+ "epoch": 1.92,
4506
+ "learning_rate": 8.782023706103926e-08,
4507
+ "loss": 0.1002,
4508
+ "step": 750
4509
+ },
4510
+ {
4511
+ "epoch": 1.92,
4512
+ "learning_rate": 8.242466920738601e-08,
4513
+ "loss": 0.1,
4514
+ "step": 751
4515
+ },
4516
+ {
4517
+ "epoch": 1.92,
4518
+ "learning_rate": 7.719946080023022e-08,
4519
+ "loss": 0.1301,
4520
+ "step": 752
4521
+ },
4522
+ {
4523
+ "epoch": 1.93,
4524
+ "learning_rate": 7.21447015957466e-08,
4525
+ "loss": 0.647,
4526
+ "step": 753
4527
+ },
4528
+ {
4529
+ "epoch": 1.93,
4530
+ "learning_rate": 6.726047842221083e-08,
4531
+ "loss": 0.5725,
4532
+ "step": 754
4533
+ },
4534
+ {
4535
+ "epoch": 1.93,
4536
+ "learning_rate": 6.25468751785141e-08,
4537
+ "loss": 0.6299,
4538
+ "step": 755
4539
+ },
4540
+ {
4541
+ "epoch": 1.93,
4542
+ "learning_rate": 5.800397283271753e-08,
4543
+ "loss": 0.6025,
4544
+ "step": 756
4545
+ },
4546
+ {
4547
+ "epoch": 1.94,
4548
+ "learning_rate": 5.363184942065891e-08,
4549
+ "loss": 0.6348,
4550
+ "step": 757
4551
+ },
4552
+ {
4553
+ "epoch": 1.94,
4554
+ "learning_rate": 4.9430580044620425e-08,
4555
+ "loss": 0.592,
4556
+ "step": 758
4557
+ },
4558
+ {
4559
+ "epoch": 1.94,
4560
+ "learning_rate": 4.540023687203299e-08,
4561
+ "loss": 0.1055,
4562
+ "step": 759
4563
+ },
4564
+ {
4565
+ "epoch": 1.94,
4566
+ "learning_rate": 4.154088913423615e-08,
4567
+ "loss": 0.6128,
4568
+ "step": 760
4569
+ },
4570
+ {
4571
+ "epoch": 1.95,
4572
+ "learning_rate": 3.7852603125291265e-08,
4573
+ "loss": 0.606,
4574
+ "step": 761
4575
+ },
4576
+ {
4577
+ "epoch": 1.95,
4578
+ "learning_rate": 3.433544220084017e-08,
4579
+ "loss": 0.5698,
4580
+ "step": 762
4581
+ },
4582
+ {
4583
+ "epoch": 1.95,
4584
+ "learning_rate": 3.0989466777021634e-08,
4585
+ "loss": 0.6084,
4586
+ "step": 763
4587
+ },
4588
+ {
4589
+ "epoch": 1.95,
4590
+ "learning_rate": 2.7814734329426607e-08,
4591
+ "loss": 0.0991,
4592
+ "step": 764
4593
+ },
4594
+ {
4595
+ "epoch": 1.96,
4596
+ "learning_rate": 2.4811299392117904e-08,
4597
+ "loss": 0.1006,
4598
+ "step": 765
4599
+ },
4600
+ {
4601
+ "epoch": 1.96,
4602
+ "learning_rate": 2.197921355668875e-08,
4603
+ "loss": 0.6377,
4604
+ "step": 766
4605
+ },
4606
+ {
4607
+ "epoch": 1.96,
4608
+ "learning_rate": 1.9318525471376803e-08,
4609
+ "loss": 0.5952,
4610
+ "step": 767
4611
+ },
4612
+ {
4613
+ "epoch": 1.96,
4614
+ "learning_rate": 1.682928084023261e-08,
4615
+ "loss": 0.592,
4616
+ "step": 768
4617
+ },
4618
+ {
4619
+ "epoch": 1.97,
4620
+ "learning_rate": 1.4511522422330226e-08,
4621
+ "loss": 0.5645,
4622
+ "step": 769
4623
+ },
4624
+ {
4625
+ "epoch": 1.97,
4626
+ "learning_rate": 1.2365290031032261e-08,
4627
+ "loss": 0.6289,
4628
+ "step": 770
4629
+ },
4630
+ {
4631
+ "epoch": 1.97,
4632
+ "learning_rate": 1.0390620533312635e-08,
4633
+ "loss": 0.5986,
4634
+ "step": 771
4635
+ },
4636
+ {
4637
+ "epoch": 1.97,
4638
+ "learning_rate": 8.587547849112643e-09,
4639
+ "loss": 0.1176,
4640
+ "step": 772
4641
+ },
4642
+ {
4643
+ "epoch": 1.98,
4644
+ "learning_rate": 6.956102950770316e-09,
4645
+ "loss": 0.6133,
4646
+ "step": 773
4647
+ },
4648
+ {
4649
+ "epoch": 1.98,
4650
+ "learning_rate": 5.496313862476399e-09,
4651
+ "loss": 0.6133,
4652
+ "step": 774
4653
+ },
4654
+ {
4655
+ "epoch": 1.98,
4656
+ "learning_rate": 4.208205659802511e-09,
4657
+ "loss": 0.5889,
4658
+ "step": 775
4659
+ },
4660
+ {
4661
+ "epoch": 1.98,
4662
+ "learning_rate": 3.0918004692648273e-09,
4663
+ "loss": 0.5986,
4664
+ "step": 776
4665
+ },
4666
+ {
4667
+ "epoch": 1.99,
4668
+ "learning_rate": 2.147117467949933e-09,
4669
+ "loss": 0.6084,
4670
+ "step": 777
4671
+ },
4672
+ {
4673
+ "epoch": 1.99,
4674
+ "learning_rate": 1.3741728831750956e-09,
4675
+ "loss": 0.604,
4676
+ "step": 778
4677
+ },
4678
+ {
4679
+ "epoch": 1.99,
4680
+ "learning_rate": 7.729799922195913e-10,
4681
+ "loss": 0.603,
4682
+ "step": 779
4683
+ },
4684
+ {
4685
+ "epoch": 1.99,
4686
+ "learning_rate": 3.435491220937781e-10,
4687
+ "loss": 0.6011,
4688
+ "step": 780
4689
+ },
4690
+ {
4691
+ "epoch": 2.0,
4692
+ "learning_rate": 8.588764935812955e-11,
4693
+ "loss": 0.6123,
4694
+ "step": 781
4695
+ },
4696
+ {
4697
+ "epoch": 2.0,
4698
+ "learning_rate": 0.0,
4699
+ "loss": 0.2844,
4700
+ "step": 782
4701
+ },
4702
+ {
4703
+ "epoch": 2.0,
4704
+ "step": 782,
4705
+ "total_flos": 393855144689664.0,
4706
+ "train_loss": 0.6908293428933224,
4707
+ "train_runtime": 11146.7695,
4708
+ "train_samples_per_second": 8.971,
4709
+ "train_steps_per_second": 0.07
4710
+ }
4711
+ ],
4712
+ "max_steps": 782,
4713
+ "num_train_epochs": 2,
4714
+ "total_flos": 393855144689664.0,
4715
+ "trial_name": null,
4716
+ "trial_params": null
4717
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21851d9c02e675878855011ad6ad8e61ee0bc9b5ece9a5b3cbfd602e0edfdc22
3
+ size 5883