xiyaowang96 commited on
Commit
5567f38
·
1 Parent(s): 4baff18

Initial commit of my model

Browse files
config.json ADDED
@@ -0,0 +1,253 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/blob/v-xiyaowang/v-xiyaowang/Video-Self-Rewarding-main/checkpoints/",
3
+ "architectures": [
4
+ "LlavaLlamaModel"
5
+ ],
6
+ "drop_path_rate": 0.0,
7
+ "hidden_size": 4096,
8
+ "image_aspect_ratio": "resize",
9
+ "interpolate_mode": "linear",
10
+ "llm_cfg": {
11
+ "_name_or_path": "/blob/v-xiyaowang/v-xiyaowang/Video-Self-Rewarding-main/checkpoints/llm",
12
+ "add_cross_attention": false,
13
+ "architectures": [
14
+ "LlamaForCausalLM"
15
+ ],
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "bad_words_ids": null,
19
+ "begin_suppress_tokens": null,
20
+ "bos_token_id": 128000,
21
+ "chunk_size_feed_forward": 0,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": 128001,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "hidden_act": "silu",
34
+ "hidden_size": 4096,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 14336,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 8192,
50
+ "min_length": 0,
51
+ "model_max_length": 4096,
52
+ "model_type": "llama",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 32,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 32,
58
+ "num_key_value_heads": 8,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": null,
64
+ "prefix": null,
65
+ "pretraining_tp": 1,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "rms_norm_eps": 1e-05,
73
+ "rope_scaling": null,
74
+ "rope_theta": 500000.0,
75
+ "sep_token_id": null,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": null,
78
+ "temperature": 1.0,
79
+ "tf_legacy_loss": false,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": false,
82
+ "tokenizer_class": null,
83
+ "tokenizer_model_max_length": 4096,
84
+ "tokenizer_padding_side": "right",
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": "bfloat16",
88
+ "torchscript": false,
89
+ "typical_p": 1.0,
90
+ "use_bfloat16": false,
91
+ "use_cache": true,
92
+ "vocab_size": 128257
93
+ },
94
+ "mm_hidden_size": 1152,
95
+ "mm_projector_cfg": {
96
+ "_name_or_path": "/blob/v-xiyaowang/v-xiyaowang/Video-Self-Rewarding-main/checkpoints/mm_projector",
97
+ "add_cross_attention": false,
98
+ "architectures": [
99
+ "MultimodalProjector"
100
+ ],
101
+ "bad_words_ids": null,
102
+ "begin_suppress_tokens": null,
103
+ "bos_token_id": null,
104
+ "chunk_size_feed_forward": 0,
105
+ "cross_attention_hidden_size": null,
106
+ "decoder_start_token_id": null,
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "id2label": {
117
+ "0": "LABEL_0",
118
+ "1": "LABEL_1"
119
+ },
120
+ "is_decoder": false,
121
+ "is_encoder_decoder": false,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "length_penalty": 1.0,
127
+ "max_length": 20,
128
+ "min_length": 0,
129
+ "mm_projector_type": "mlp_downsample",
130
+ "model_type": "v2l_projector",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_beam_groups": 1,
133
+ "num_beams": 1,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_scores": false,
138
+ "pad_token_id": null,
139
+ "prefix": null,
140
+ "problem_type": null,
141
+ "pruned_heads": {},
142
+ "remove_invalid_values": false,
143
+ "repetition_penalty": 1.0,
144
+ "return_dict": true,
145
+ "return_dict_in_generate": false,
146
+ "sep_token_id": null,
147
+ "suppress_tokens": null,
148
+ "task_specific_params": null,
149
+ "temperature": 1.0,
150
+ "tf_legacy_loss": false,
151
+ "tie_encoder_decoder": false,
152
+ "tie_word_embeddings": true,
153
+ "tokenizer_class": null,
154
+ "top_k": 50,
155
+ "top_p": 1.0,
156
+ "torch_dtype": "bfloat16",
157
+ "torchscript": false,
158
+ "typical_p": 1.0,
159
+ "use_bfloat16": false
160
+ },
161
+ "mm_projector_lr": null,
162
+ "mm_use_im_patch_token": false,
163
+ "mm_use_im_start_end": false,
164
+ "mm_vision_select_feature": "cls_patch",
165
+ "mm_vision_select_layer": -2,
166
+ "model_dtype": "torch.bfloat16",
167
+ "model_type": "llava_llama",
168
+ "num_video_frames": 8,
169
+ "resume_path": "/blob/v-xiyaowang/v-xiyaowang/Video-Self-Rewarding-main/checkpoints/",
170
+ "s2": false,
171
+ "s2_max_split_size": 336,
172
+ "s2_scales": "336,672,1008",
173
+ "transformers_version": "4.36.2",
174
+ "tune_language_model": true,
175
+ "tune_mm_projector": true,
176
+ "tune_vision_tower": true,
177
+ "vision_resolution": -1,
178
+ "vision_tower_cfg": {
179
+ "_name_or_path": "/blob/v-xiyaowang/v-xiyaowang/Video-Self-Rewarding-main/checkpoints/vision_tower",
180
+ "add_cross_attention": false,
181
+ "architectures": [
182
+ "SiglipVisionModel"
183
+ ],
184
+ "attention_dropout": 0.0,
185
+ "bad_words_ids": null,
186
+ "begin_suppress_tokens": null,
187
+ "bos_token_id": null,
188
+ "chunk_size_feed_forward": 0,
189
+ "cross_attention_hidden_size": null,
190
+ "decoder_start_token_id": null,
191
+ "diversity_penalty": 0.0,
192
+ "do_sample": false,
193
+ "early_stopping": false,
194
+ "encoder_no_repeat_ngram_size": 0,
195
+ "eos_token_id": null,
196
+ "exponential_decay_length_penalty": null,
197
+ "finetuning_task": null,
198
+ "forced_bos_token_id": null,
199
+ "forced_eos_token_id": null,
200
+ "hidden_act": "gelu_pytorch_tanh",
201
+ "hidden_size": 1152,
202
+ "id2label": {
203
+ "0": "LABEL_0",
204
+ "1": "LABEL_1"
205
+ },
206
+ "image_size": 384,
207
+ "intermediate_size": 4304,
208
+ "is_decoder": false,
209
+ "is_encoder_decoder": false,
210
+ "label2id": {
211
+ "LABEL_0": 0,
212
+ "LABEL_1": 1
213
+ },
214
+ "layer_norm_eps": 1e-06,
215
+ "length_penalty": 1.0,
216
+ "max_length": 20,
217
+ "min_length": 0,
218
+ "model_type": "siglip_vision_model",
219
+ "no_repeat_ngram_size": 0,
220
+ "num_attention_heads": 16,
221
+ "num_beam_groups": 1,
222
+ "num_beams": 1,
223
+ "num_channels": 3,
224
+ "num_hidden_layers": 27,
225
+ "num_return_sequences": 1,
226
+ "output_attentions": false,
227
+ "output_hidden_states": false,
228
+ "output_scores": false,
229
+ "pad_token_id": null,
230
+ "patch_size": 14,
231
+ "prefix": null,
232
+ "problem_type": null,
233
+ "pruned_heads": {},
234
+ "remove_invalid_values": false,
235
+ "repetition_penalty": 1.0,
236
+ "return_dict": true,
237
+ "return_dict_in_generate": false,
238
+ "sep_token_id": null,
239
+ "suppress_tokens": null,
240
+ "task_specific_params": null,
241
+ "temperature": 1.0,
242
+ "tf_legacy_loss": false,
243
+ "tie_encoder_decoder": false,
244
+ "tie_word_embeddings": true,
245
+ "tokenizer_class": null,
246
+ "top_k": 50,
247
+ "top_p": 1.0,
248
+ "torch_dtype": "bfloat16",
249
+ "torchscript": false,
250
+ "typical_p": 1.0,
251
+ "use_bfloat16": false
252
+ }
253
+ }
llm/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/blob/v-xiyaowang/v-xiyaowang/Video-Self-Rewarding-main/checkpoints/llm",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_max_length": 4096,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "tokenizer_model_max_length": 4096,
26
+ "tokenizer_padding_side": "right",
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.36.2",
29
+ "use_cache": true,
30
+ "vocab_size": 128257
31
+ }
llm/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128001,
5
+ "transformers_version": "4.36.2"
6
+ }
llm/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efa9aadfec724289b04bd111c88bfaed62705722586daf766f2694b1fd3ebbc2
3
+ size 4976706864
llm/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e455f9858a6170fb3cd6587ce9c1f9521aa226904cecee09effa0d7a68c155c0
3
+ size 4999802720
llm/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa51dfa0852907c635aa77d66715dbf4dbc1e48133e2c66c048deabcd80bd16
3
+ size 4915916176
llm/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c4522e96be02857b1240d1987b7b6cfb15ea25534eb56867d889770a603431
3
+ size 1168147000
llm/model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060538880
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
llm/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
llm/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
llm/tokenizer_config.json ADDED
@@ -0,0 +1,2073 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "[PAD]",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "bos_token": "<|begin_of_text|>",
2061
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2062
+ "clean_up_tokenization_spaces": true,
2063
+ "eos_token": "<|end_of_text|>",
2064
+ "legacy": false,
2065
+ "model_input_names": [
2066
+ "input_ids",
2067
+ "attention_mask"
2068
+ ],
2069
+ "model_max_length": 4096,
2070
+ "pad_token": "[PAD]",
2071
+ "padding_side": "right",
2072
+ "tokenizer_class": "PreTrainedTokenizerFast"
2073
+ }
mm_projector/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/blob/v-xiyaowang/v-xiyaowang/Video-Self-Rewarding-main/checkpoints/mm_projector",
3
+ "architectures": [
4
+ "MultimodalProjector"
5
+ ],
6
+ "mm_projector_type": "mlp_downsample",
7
+ "model_type": "v2l_projector",
8
+ "torch_dtype": "bfloat16",
9
+ "transformers_version": "4.36.2"
10
+ }
mm_projector/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79734f1751196d443717882f3c86cb27d3af144ee9b0b93b8110e8c102370b3d
3
+ size 71338512
trainer_state.json ADDED
@@ -0,0 +1,4284 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9992952783650458,
5
+ "eval_steps": 500,
6
+ "global_step": 709,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 4.5454545454545455e-06,
14
+ "loss": 1.019,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 9.090909090909091e-06,
20
+ "loss": 1.0036,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 1.3636363636363637e-05,
26
+ "loss": 0.9864,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 1.8181818181818182e-05,
32
+ "loss": 1.0294,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 2.272727272727273e-05,
38
+ "loss": 1.0158,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 2.7272727272727273e-05,
44
+ "loss": 1.005,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 3.181818181818182e-05,
50
+ "loss": 0.999,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "learning_rate": 3.6363636363636364e-05,
56
+ "loss": 1.1149,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.01,
61
+ "learning_rate": 4.0909090909090915e-05,
62
+ "loss": 1.1047,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.01,
67
+ "learning_rate": 4.545454545454546e-05,
68
+ "loss": 1.1206,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.02,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.1102,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.02,
79
+ "learning_rate": 5.4545454545454546e-05,
80
+ "loss": 1.1411,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.02,
85
+ "learning_rate": 5.90909090909091e-05,
86
+ "loss": 1.1526,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "learning_rate": 6.363636363636364e-05,
92
+ "loss": 1.1397,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.02,
97
+ "learning_rate": 6.818181818181818e-05,
98
+ "loss": 1.1834,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.02,
103
+ "learning_rate": 7.272727272727273e-05,
104
+ "loss": 1.2163,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.02,
109
+ "learning_rate": 7.727272727272727e-05,
110
+ "loss": 1.2801,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.03,
115
+ "learning_rate": 8.181818181818183e-05,
116
+ "loss": 1.2758,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.03,
121
+ "learning_rate": 8.636363636363637e-05,
122
+ "loss": 1.2541,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.03,
127
+ "learning_rate": 9.090909090909092e-05,
128
+ "loss": 1.2804,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.03,
133
+ "learning_rate": 9.545454545454546e-05,
134
+ "loss": 1.2869,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.03,
139
+ "learning_rate": 0.0001,
140
+ "loss": 1.261,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.03,
145
+ "learning_rate": 9.999947721210493e-05,
146
+ "loss": 1.2938,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.03,
151
+ "learning_rate": 9.999790885935198e-05,
152
+ "loss": 1.3089,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.04,
157
+ "learning_rate": 9.999529497453782e-05,
158
+ "loss": 1.3996,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.04,
163
+ "learning_rate": 9.999163561232272e-05,
164
+ "loss": 1.4033,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.04,
169
+ "learning_rate": 9.998693084922947e-05,
170
+ "loss": 1.4061,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.04,
175
+ "learning_rate": 9.998118078364184e-05,
176
+ "loss": 1.3929,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.04,
181
+ "learning_rate": 9.997438553580241e-05,
182
+ "loss": 1.4128,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.04,
187
+ "learning_rate": 9.996654524781009e-05,
188
+ "loss": 1.4063,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.04,
193
+ "learning_rate": 9.995766008361719e-05,
194
+ "loss": 1.4088,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.05,
199
+ "learning_rate": 9.994773022902597e-05,
200
+ "loss": 1.3899,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.05,
205
+ "learning_rate": 9.993675589168473e-05,
206
+ "loss": 1.3813,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.05,
211
+ "learning_rate": 9.992473730108354e-05,
212
+ "loss": 1.3964,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.05,
217
+ "learning_rate": 9.99116747085493e-05,
218
+ "loss": 1.3606,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.05,
223
+ "learning_rate": 9.989756838724064e-05,
224
+ "loss": 1.4069,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.05,
229
+ "learning_rate": 9.988241863214211e-05,
230
+ "loss": 1.4116,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.05,
235
+ "learning_rate": 9.986622576005806e-05,
236
+ "loss": 1.3307,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.05,
241
+ "learning_rate": 9.984899010960601e-05,
242
+ "loss": 1.3983,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.06,
247
+ "learning_rate": 9.983071204120951e-05,
248
+ "loss": 1.3725,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.06,
253
+ "learning_rate": 9.981139193709068e-05,
254
+ "loss": 1.4223,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.06,
259
+ "learning_rate": 9.979103020126218e-05,
260
+ "loss": 1.3844,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.06,
265
+ "learning_rate": 9.976962725951878e-05,
266
+ "loss": 1.4282,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.06,
271
+ "learning_rate": 9.974718355942843e-05,
272
+ "loss": 1.3989,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.06,
277
+ "learning_rate": 9.972369957032293e-05,
278
+ "loss": 1.393,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.06,
283
+ "learning_rate": 9.969917578328808e-05,
284
+ "loss": 1.4606,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.07,
289
+ "learning_rate": 9.967361271115343e-05,
290
+ "loss": 1.4384,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.07,
295
+ "learning_rate": 9.964701088848158e-05,
296
+ "loss": 1.478,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.07,
301
+ "learning_rate": 9.961937087155697e-05,
302
+ "loss": 1.4254,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.07,
307
+ "learning_rate": 9.959069323837424e-05,
308
+ "loss": 1.454,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.07,
313
+ "learning_rate": 9.956097858862619e-05,
314
+ "loss": 1.4448,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.07,
319
+ "learning_rate": 9.953022754369114e-05,
320
+ "loss": 1.4567,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.07,
325
+ "learning_rate": 9.94984407466201e-05,
326
+ "loss": 1.4563,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.08,
331
+ "learning_rate": 9.946561886212315e-05,
332
+ "loss": 1.438,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.08,
337
+ "learning_rate": 9.943176257655567e-05,
338
+ "loss": 1.4096,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.08,
343
+ "learning_rate": 9.93968725979039e-05,
344
+ "loss": 1.4472,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.08,
349
+ "learning_rate": 9.936094965577017e-05,
350
+ "loss": 1.4223,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.08,
355
+ "learning_rate": 9.932399450135766e-05,
356
+ "loss": 1.439,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.08,
361
+ "learning_rate": 9.928600790745466e-05,
362
+ "loss": 1.4606,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.08,
367
+ "learning_rate": 9.924699066841845e-05,
368
+ "loss": 1.5223,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.09,
373
+ "learning_rate": 9.920694360015863e-05,
374
+ "loss": 1.4791,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.09,
379
+ "learning_rate": 9.916586754012008e-05,
380
+ "loss": 1.4432,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.09,
385
+ "learning_rate": 9.91237633472655e-05,
386
+ "loss": 1.4596,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.09,
391
+ "learning_rate": 9.908063190205738e-05,
392
+ "loss": 1.4488,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.09,
397
+ "learning_rate": 9.903647410643963e-05,
398
+ "loss": 1.4542,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.09,
403
+ "learning_rate": 9.899129088381866e-05,
404
+ "loss": 1.443,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.09,
409
+ "learning_rate": 9.894508317904419e-05,
410
+ "loss": 1.5506,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.1,
415
+ "learning_rate": 9.88978519583893e-05,
416
+ "loss": 1.4963,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.1,
421
+ "learning_rate": 9.884959820953048e-05,
422
+ "loss": 1.4135,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.1,
427
+ "learning_rate": 9.880032294152673e-05,
428
+ "loss": 1.4813,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.1,
433
+ "learning_rate": 9.875002718479858e-05,
434
+ "loss": 1.4471,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.1,
439
+ "learning_rate": 9.869871199110656e-05,
440
+ "loss": 1.4165,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.1,
445
+ "learning_rate": 9.864637843352915e-05,
446
+ "loss": 1.4395,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.1,
451
+ "learning_rate": 9.859302760644036e-05,
452
+ "loss": 1.4375,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.11,
457
+ "learning_rate": 9.853866062548687e-05,
458
+ "loss": 1.4995,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.11,
463
+ "learning_rate": 9.848327862756466e-05,
464
+ "loss": 1.4465,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.11,
469
+ "learning_rate": 9.842688277079523e-05,
470
+ "loss": 1.4374,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.11,
475
+ "learning_rate": 9.836947423450147e-05,
476
+ "loss": 1.4476,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.11,
481
+ "learning_rate": 9.831105421918287e-05,
482
+ "loss": 1.437,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.11,
487
+ "learning_rate": 9.825162394649048e-05,
488
+ "loss": 1.41,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.11,
493
+ "learning_rate": 9.819118465920143e-05,
494
+ "loss": 1.469,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.12,
499
+ "learning_rate": 9.812973762119281e-05,
500
+ "loss": 1.4168,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.12,
505
+ "learning_rate": 9.806728411741533e-05,
506
+ "loss": 1.5309,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.12,
511
+ "learning_rate": 9.800382545386641e-05,
512
+ "loss": 1.4883,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.12,
517
+ "learning_rate": 9.79393629575629e-05,
518
+ "loss": 1.4679,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.12,
523
+ "learning_rate": 9.787389797651334e-05,
524
+ "loss": 1.5121,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.12,
529
+ "learning_rate": 9.780743187968968e-05,
530
+ "loss": 1.4483,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.12,
535
+ "learning_rate": 9.773996605699875e-05,
536
+ "loss": 1.4756,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.13,
541
+ "learning_rate": 9.767150191925321e-05,
542
+ "loss": 1.4383,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.13,
547
+ "learning_rate": 9.760204089814192e-05,
548
+ "loss": 1.4457,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.13,
553
+ "learning_rate": 9.753158444620013e-05,
554
+ "loss": 1.4332,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.13,
559
+ "learning_rate": 9.746013403677905e-05,
560
+ "loss": 1.4486,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.13,
565
+ "learning_rate": 9.738769116401505e-05,
566
+ "loss": 1.4434,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.13,
571
+ "learning_rate": 9.73142573427984e-05,
572
+ "loss": 1.4616,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.13,
577
+ "learning_rate": 9.723983410874163e-05,
578
+ "loss": 1.4519,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.14,
583
+ "learning_rate": 9.716442301814735e-05,
584
+ "loss": 1.4913,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.14,
589
+ "learning_rate": 9.708802564797578e-05,
590
+ "loss": 1.4632,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.14,
595
+ "learning_rate": 9.701064359581176e-05,
596
+ "loss": 1.4475,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.14,
601
+ "learning_rate": 9.693227847983126e-05,
602
+ "loss": 1.4445,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.14,
607
+ "learning_rate": 9.685293193876765e-05,
608
+ "loss": 1.458,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.14,
613
+ "learning_rate": 9.67726056318774e-05,
614
+ "loss": 1.4125,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.14,
619
+ "learning_rate": 9.669130123890533e-05,
620
+ "loss": 1.4348,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.15,
625
+ "learning_rate": 9.660902046004953e-05,
626
+ "loss": 1.4535,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.15,
631
+ "learning_rate": 9.652576501592583e-05,
632
+ "loss": 1.4669,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.15,
637
+ "learning_rate": 9.644153664753173e-05,
638
+ "loss": 1.4212,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.15,
643
+ "learning_rate": 9.635633711621012e-05,
644
+ "loss": 1.4407,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.15,
649
+ "learning_rate": 9.627016820361235e-05,
650
+ "loss": 1.4285,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.15,
655
+ "learning_rate": 9.618303171166094e-05,
656
+ "loss": 1.4433,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.15,
661
+ "learning_rate": 9.60949294625121e-05,
662
+ "loss": 1.4629,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.16,
667
+ "learning_rate": 9.600586329851735e-05,
668
+ "loss": 1.4309,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.16,
673
+ "learning_rate": 9.59158350821852e-05,
674
+ "loss": 1.4424,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.16,
679
+ "learning_rate": 9.582484669614211e-05,
680
+ "loss": 1.5388,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.16,
685
+ "learning_rate": 9.573290004309318e-05,
686
+ "loss": 1.4657,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.16,
691
+ "learning_rate": 9.563999704578226e-05,
692
+ "loss": 1.4654,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.16,
697
+ "learning_rate": 9.554613964695189e-05,
698
+ "loss": 1.4174,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.16,
703
+ "learning_rate": 9.545132980930251e-05,
704
+ "loss": 1.4004,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.16,
709
+ "learning_rate": 9.535556951545157e-05,
710
+ "loss": 1.4183,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.17,
715
+ "learning_rate": 9.525886076789194e-05,
716
+ "loss": 1.4468,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.17,
721
+ "learning_rate": 9.516120558895014e-05,
722
+ "loss": 1.429,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.17,
727
+ "learning_rate": 9.506260602074398e-05,
728
+ "loss": 1.3977,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.17,
733
+ "learning_rate": 9.496306412513988e-05,
734
+ "loss": 1.433,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.17,
739
+ "learning_rate": 9.486258198370981e-05,
740
+ "loss": 1.4687,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.17,
745
+ "learning_rate": 9.47611616976876e-05,
746
+ "loss": 1.4017,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.17,
751
+ "learning_rate": 9.465880538792518e-05,
752
+ "loss": 1.4283,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.18,
757
+ "learning_rate": 9.455551519484816e-05,
758
+ "loss": 1.4018,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.18,
763
+ "learning_rate": 9.445129327841102e-05,
764
+ "loss": 1.4522,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.18,
769
+ "learning_rate": 9.434614181805202e-05,
770
+ "loss": 1.4229,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.18,
775
+ "learning_rate": 9.424006301264761e-05,
776
+ "loss": 1.4334,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.18,
781
+ "learning_rate": 9.413305908046636e-05,
782
+ "loss": 1.4241,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.18,
787
+ "learning_rate": 9.402513225912273e-05,
788
+ "loss": 1.4142,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.18,
793
+ "learning_rate": 9.391628480553013e-05,
794
+ "loss": 1.4467,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.19,
799
+ "learning_rate": 9.38065189958538e-05,
800
+ "loss": 1.4676,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.19,
805
+ "learning_rate": 9.369583712546322e-05,
806
+ "loss": 1.4513,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.19,
811
+ "learning_rate": 9.358424150888405e-05,
812
+ "loss": 1.4245,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.19,
817
+ "learning_rate": 9.347173447974982e-05,
818
+ "loss": 1.406,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.19,
823
+ "learning_rate": 9.335831839075304e-05,
824
+ "loss": 1.3876,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.19,
829
+ "learning_rate": 9.324399561359602e-05,
830
+ "loss": 1.352,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.19,
835
+ "learning_rate": 9.312876853894134e-05,
836
+ "loss": 1.4428,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.2,
841
+ "learning_rate": 9.30126395763618e-05,
842
+ "loss": 1.4213,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.2,
847
+ "learning_rate": 9.289561115429004e-05,
848
+ "loss": 1.3948,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.2,
853
+ "learning_rate": 9.277768571996772e-05,
854
+ "loss": 1.4475,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.2,
859
+ "learning_rate": 9.265886573939447e-05,
860
+ "loss": 1.4342,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.2,
865
+ "learning_rate": 9.253915369727617e-05,
866
+ "loss": 1.3901,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.2,
871
+ "learning_rate": 9.241855209697307e-05,
872
+ "loss": 1.4319,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.2,
877
+ "learning_rate": 9.229706346044747e-05,
878
+ "loss": 1.4263,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.21,
883
+ "learning_rate": 9.217469032821088e-05,
884
+ "loss": 1.3893,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.21,
889
+ "learning_rate": 9.205143525927103e-05,
890
+ "loss": 1.4633,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.21,
895
+ "learning_rate": 9.192730083107819e-05,
896
+ "loss": 1.4429,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.21,
901
+ "learning_rate": 9.180228963947144e-05,
902
+ "loss": 1.3981,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.21,
907
+ "learning_rate": 9.167640429862429e-05,
908
+ "loss": 1.441,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.21,
913
+ "learning_rate": 9.154964744099006e-05,
914
+ "loss": 1.4101,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.21,
919
+ "learning_rate": 9.142202171724674e-05,
920
+ "loss": 1.4725,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.22,
925
+ "learning_rate": 9.129352979624169e-05,
926
+ "loss": 1.3903,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.22,
931
+ "learning_rate": 9.116417436493574e-05,
932
+ "loss": 1.4252,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.22,
937
+ "learning_rate": 9.103395812834705e-05,
938
+ "loss": 1.4432,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.22,
943
+ "learning_rate": 9.09028838094945e-05,
944
+ "loss": 1.4416,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.22,
949
+ "learning_rate": 9.077095414934075e-05,
950
+ "loss": 1.3401,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.22,
955
+ "learning_rate": 9.063817190673503e-05,
956
+ "loss": 1.4355,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.22,
961
+ "learning_rate": 9.050453985835527e-05,
962
+ "loss": 1.4083,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.23,
967
+ "learning_rate": 9.037006079865016e-05,
968
+ "loss": 1.4175,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.23,
973
+ "learning_rate": 9.023473753978069e-05,
974
+ "loss": 1.4193,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.23,
979
+ "learning_rate": 9.009857291156134e-05,
980
+ "loss": 1.4148,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.23,
985
+ "learning_rate": 8.996156976140086e-05,
986
+ "loss": 1.4227,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.23,
991
+ "learning_rate": 8.98237309542428e-05,
992
+ "loss": 1.3991,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.23,
997
+ "learning_rate": 8.968505937250555e-05,
998
+ "loss": 1.4063,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.23,
1003
+ "learning_rate": 8.954555791602211e-05,
1004
+ "loss": 1.4072,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.24,
1009
+ "learning_rate": 8.940522950197935e-05,
1010
+ "loss": 1.4471,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.24,
1015
+ "learning_rate": 8.926407706485713e-05,
1016
+ "loss": 1.3875,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.24,
1021
+ "learning_rate": 8.91221035563669e-05,
1022
+ "loss": 1.469,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.24,
1027
+ "learning_rate": 8.897931194538989e-05,
1028
+ "loss": 1.4398,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.24,
1033
+ "learning_rate": 8.883570521791514e-05,
1034
+ "loss": 1.436,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.24,
1039
+ "learning_rate": 8.869128637697702e-05,
1040
+ "loss": 1.4175,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.24,
1045
+ "learning_rate": 8.854605844259237e-05,
1046
+ "loss": 1.3957,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.25,
1051
+ "learning_rate": 8.840002445169746e-05,
1052
+ "loss": 1.4846,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.25,
1057
+ "learning_rate": 8.82531874580844e-05,
1058
+ "loss": 1.3793,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.25,
1063
+ "learning_rate": 8.810555053233729e-05,
1064
+ "loss": 1.4326,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.25,
1069
+ "learning_rate": 8.795711676176803e-05,
1070
+ "loss": 1.4546,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.25,
1075
+ "learning_rate": 8.780788925035178e-05,
1076
+ "loss": 1.4048,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.25,
1081
+ "learning_rate": 8.765787111866198e-05,
1082
+ "loss": 1.3985,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.25,
1087
+ "learning_rate": 8.750706550380518e-05,
1088
+ "loss": 1.3538,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.26,
1093
+ "learning_rate": 8.735547555935537e-05,
1094
+ "loss": 1.402,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.26,
1099
+ "learning_rate": 8.720310445528807e-05,
1100
+ "loss": 1.3701,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.26,
1105
+ "learning_rate": 8.704995537791405e-05,
1106
+ "loss": 1.3698,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.26,
1111
+ "learning_rate": 8.689603152981263e-05,
1112
+ "loss": 1.3827,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.26,
1117
+ "learning_rate": 8.674133612976481e-05,
1118
+ "loss": 1.463,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.26,
1123
+ "learning_rate": 8.658587241268587e-05,
1124
+ "loss": 1.363,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.26,
1129
+ "learning_rate": 8.642964362955781e-05,
1130
+ "loss": 1.4031,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.26,
1135
+ "learning_rate": 8.627265304736131e-05,
1136
+ "loss": 1.4026,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.27,
1141
+ "learning_rate": 8.611490394900739e-05,
1142
+ "loss": 1.45,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.27,
1147
+ "learning_rate": 8.595639963326881e-05,
1148
+ "loss": 1.3965,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.27,
1153
+ "learning_rate": 8.579714341471106e-05,
1154
+ "loss": 1.4117,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.27,
1159
+ "learning_rate": 8.56371386236231e-05,
1160
+ "loss": 1.3525,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.27,
1165
+ "learning_rate": 8.547638860594764e-05,
1166
+ "loss": 1.4094,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.27,
1171
+ "learning_rate": 8.531489672321122e-05,
1172
+ "loss": 1.3721,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.27,
1177
+ "learning_rate": 8.515266635245389e-05,
1178
+ "loss": 1.3894,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.28,
1183
+ "learning_rate": 8.498970088615861e-05,
1184
+ "loss": 1.3716,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.28,
1189
+ "learning_rate": 8.48260037321803e-05,
1190
+ "loss": 1.4026,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.28,
1195
+ "learning_rate": 8.46615783136746e-05,
1196
+ "loss": 1.3507,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.28,
1201
+ "learning_rate": 8.449642806902623e-05,
1202
+ "loss": 1.3839,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.28,
1207
+ "learning_rate": 8.433055645177714e-05,
1208
+ "loss": 1.3451,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.28,
1213
+ "learning_rate": 8.416396693055429e-05,
1214
+ "loss": 1.3518,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.28,
1219
+ "learning_rate": 8.399666298899706e-05,
1220
+ "loss": 1.3893,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.29,
1225
+ "learning_rate": 8.382864812568452e-05,
1226
+ "loss": 1.3508,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.29,
1231
+ "learning_rate": 8.365992585406207e-05,
1232
+ "loss": 1.335,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.29,
1237
+ "learning_rate": 8.34904997023682e-05,
1238
+ "loss": 1.3734,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.29,
1243
+ "learning_rate": 8.332037321356057e-05,
1244
+ "loss": 1.3876,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.29,
1249
+ "learning_rate": 8.31495499452419e-05,
1250
+ "loss": 1.398,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.29,
1255
+ "learning_rate": 8.297803346958571e-05,
1256
+ "loss": 1.4288,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.29,
1261
+ "learning_rate": 8.280582737326146e-05,
1262
+ "loss": 1.389,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.3,
1267
+ "learning_rate": 8.263293525735967e-05,
1268
+ "loss": 1.3819,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.3,
1273
+ "learning_rate": 8.245936073731653e-05,
1274
+ "loss": 1.3584,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.3,
1279
+ "learning_rate": 8.228510744283837e-05,
1280
+ "loss": 1.3803,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.3,
1285
+ "learning_rate": 8.211017901782574e-05,
1286
+ "loss": 1.4161,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.3,
1291
+ "learning_rate": 8.193457912029713e-05,
1292
+ "loss": 1.3701,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.3,
1297
+ "learning_rate": 8.175831142231258e-05,
1298
+ "loss": 1.4184,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.3,
1303
+ "learning_rate": 8.158137960989685e-05,
1304
+ "loss": 1.4,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.31,
1309
+ "learning_rate": 8.140378738296233e-05,
1310
+ "loss": 1.3785,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.31,
1315
+ "learning_rate": 8.122553845523166e-05,
1316
+ "loss": 1.4217,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.31,
1321
+ "learning_rate": 8.104663655416014e-05,
1322
+ "loss": 1.3014,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.31,
1327
+ "learning_rate": 8.086708542085768e-05,
1328
+ "loss": 1.3709,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.31,
1333
+ "learning_rate": 8.068688881001065e-05,
1334
+ "loss": 1.3432,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.31,
1339
+ "learning_rate": 8.050605048980333e-05,
1340
+ "loss": 1.3728,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.31,
1345
+ "learning_rate": 8.03245742418391e-05,
1346
+ "loss": 1.4366,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.32,
1351
+ "learning_rate": 8.014246386106138e-05,
1352
+ "loss": 1.3944,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.32,
1357
+ "learning_rate": 7.995972315567431e-05,
1358
+ "loss": 1.4022,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.32,
1363
+ "learning_rate": 7.977635594706299e-05,
1364
+ "loss": 1.3549,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.32,
1369
+ "learning_rate": 7.959236606971375e-05,
1370
+ "loss": 1.4002,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.32,
1375
+ "learning_rate": 7.940775737113378e-05,
1376
+ "loss": 1.3788,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.32,
1381
+ "learning_rate": 7.922253371177082e-05,
1382
+ "loss": 1.3339,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.32,
1387
+ "learning_rate": 7.903669896493233e-05,
1388
+ "loss": 1.3297,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.33,
1393
+ "learning_rate": 7.885025701670457e-05,
1394
+ "loss": 1.2987,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.33,
1399
+ "learning_rate": 7.866321176587129e-05,
1400
+ "loss": 1.4247,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.33,
1405
+ "learning_rate": 7.84755671238322e-05,
1406
+ "loss": 1.3754,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.33,
1411
+ "learning_rate": 7.828732701452119e-05,
1412
+ "loss": 1.3807,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.33,
1417
+ "learning_rate": 7.809849537432432e-05,
1418
+ "loss": 1.3654,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.33,
1423
+ "learning_rate": 7.790907615199736e-05,
1424
+ "loss": 1.3311,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.33,
1429
+ "learning_rate": 7.771907330858341e-05,
1430
+ "loss": 1.3283,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.34,
1435
+ "learning_rate": 7.752849081732993e-05,
1436
+ "loss": 1.3423,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.34,
1441
+ "learning_rate": 7.733733266360568e-05,
1442
+ "loss": 1.37,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.34,
1447
+ "learning_rate": 7.714560284481742e-05,
1448
+ "loss": 1.355,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.34,
1453
+ "learning_rate": 7.695330537032628e-05,
1454
+ "loss": 1.397,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.34,
1459
+ "learning_rate": 7.676044426136397e-05,
1460
+ "loss": 1.3589,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.34,
1465
+ "learning_rate": 7.656702355094859e-05,
1466
+ "loss": 1.3804,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.34,
1471
+ "learning_rate": 7.637304728380036e-05,
1472
+ "loss": 1.3695,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.35,
1477
+ "learning_rate": 7.61785195162571e-05,
1478
+ "loss": 1.3546,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.35,
1483
+ "learning_rate": 7.598344431618926e-05,
1484
+ "loss": 1.33,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.35,
1489
+ "learning_rate": 7.578782576291501e-05,
1490
+ "loss": 1.3519,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.35,
1495
+ "learning_rate": 7.559166794711476e-05,
1496
+ "loss": 1.3526,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.35,
1501
+ "learning_rate": 7.539497497074584e-05,
1502
+ "loss": 1.37,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.35,
1507
+ "learning_rate": 7.519775094695649e-05,
1508
+ "loss": 1.343,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.35,
1513
+ "learning_rate": 7.500000000000001e-05,
1514
+ "loss": 1.3729,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.36,
1519
+ "learning_rate": 7.480172626514845e-05,
1520
+ "loss": 1.344,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.36,
1525
+ "learning_rate": 7.460293388860615e-05,
1526
+ "loss": 1.3071,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.36,
1531
+ "learning_rate": 7.440362702742305e-05,
1532
+ "loss": 1.3789,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.36,
1537
+ "learning_rate": 7.420380984940773e-05,
1538
+ "loss": 1.3207,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.36,
1543
+ "learning_rate": 7.400348653304022e-05,
1544
+ "loss": 1.3365,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.36,
1549
+ "learning_rate": 7.380266126738476e-05,
1550
+ "loss": 1.3616,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.36,
1555
+ "learning_rate": 7.360133825200205e-05,
1556
+ "loss": 1.3094,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.37,
1561
+ "learning_rate": 7.339952169686151e-05,
1562
+ "loss": 1.3491,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.37,
1567
+ "learning_rate": 7.319721582225323e-05,
1568
+ "loss": 1.3591,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.37,
1573
+ "learning_rate": 7.29944248586997e-05,
1574
+ "loss": 1.336,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.37,
1579
+ "learning_rate": 7.279115304686735e-05,
1580
+ "loss": 1.3376,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.37,
1585
+ "learning_rate": 7.258740463747788e-05,
1586
+ "loss": 1.3373,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.37,
1591
+ "learning_rate": 7.238318389121939e-05,
1592
+ "loss": 1.3632,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.37,
1597
+ "learning_rate": 7.217849507865724e-05,
1598
+ "loss": 1.3784,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.37,
1603
+ "learning_rate": 7.197334248014477e-05,
1604
+ "loss": 1.3099,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.38,
1609
+ "learning_rate": 7.176773038573377e-05,
1610
+ "loss": 1.3208,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.38,
1615
+ "learning_rate": 7.156166309508482e-05,
1616
+ "loss": 1.3293,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.38,
1621
+ "learning_rate": 7.13551449173773e-05,
1622
+ "loss": 1.3885,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.38,
1627
+ "learning_rate": 7.114818017121939e-05,
1628
+ "loss": 1.354,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.38,
1633
+ "learning_rate": 7.094077318455762e-05,
1634
+ "loss": 1.3362,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.38,
1639
+ "learning_rate": 7.073292829458645e-05,
1640
+ "loss": 1.3203,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.38,
1645
+ "learning_rate": 7.052464984765764e-05,
1646
+ "loss": 1.3777,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.39,
1651
+ "learning_rate": 7.031594219918916e-05,
1652
+ "loss": 1.3297,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.39,
1657
+ "learning_rate": 7.010680971357434e-05,
1658
+ "loss": 1.3249,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.39,
1663
+ "learning_rate": 6.989725676409044e-05,
1664
+ "loss": 1.3271,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.39,
1669
+ "learning_rate": 6.96872877328073e-05,
1670
+ "loss": 1.3234,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.39,
1675
+ "learning_rate": 6.94769070104956e-05,
1676
+ "loss": 1.3597,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.39,
1681
+ "learning_rate": 6.926611899653516e-05,
1682
+ "loss": 1.3421,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.39,
1687
+ "learning_rate": 6.905492809882286e-05,
1688
+ "loss": 1.3048,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.4,
1693
+ "learning_rate": 6.88433387336805e-05,
1694
+ "loss": 1.3737,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.4,
1699
+ "learning_rate": 6.863135532576241e-05,
1700
+ "loss": 1.3015,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.4,
1705
+ "learning_rate": 6.841898230796302e-05,
1706
+ "loss": 1.325,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.4,
1711
+ "learning_rate": 6.820622412132402e-05,
1712
+ "loss": 1.3183,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.4,
1717
+ "learning_rate": 6.799308521494156e-05,
1718
+ "loss": 1.3447,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.4,
1723
+ "learning_rate": 6.777957004587331e-05,
1724
+ "loss": 1.2967,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.4,
1729
+ "learning_rate": 6.756568307904508e-05,
1730
+ "loss": 1.3522,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.41,
1735
+ "learning_rate": 6.735142878715754e-05,
1736
+ "loss": 1.3333,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.41,
1741
+ "learning_rate": 6.713681165059271e-05,
1742
+ "loss": 1.4079,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.41,
1747
+ "learning_rate": 6.692183615732025e-05,
1748
+ "loss": 1.2946,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.41,
1753
+ "learning_rate": 6.670650680280358e-05,
1754
+ "loss": 1.3045,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.41,
1759
+ "learning_rate": 6.649082808990586e-05,
1760
+ "loss": 1.358,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.41,
1765
+ "learning_rate": 6.627480452879593e-05,
1766
+ "loss": 1.2442,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.41,
1771
+ "learning_rate": 6.605844063685392e-05,
1772
+ "loss": 1.3063,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.42,
1777
+ "learning_rate": 6.584174093857675e-05,
1778
+ "loss": 1.3009,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.42,
1783
+ "learning_rate": 6.562470996548361e-05,
1784
+ "loss": 1.2866,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.42,
1789
+ "learning_rate": 6.54073522560211e-05,
1790
+ "loss": 1.3432,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.42,
1795
+ "learning_rate": 6.518967235546841e-05,
1796
+ "loss": 1.363,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.42,
1801
+ "learning_rate": 6.497167481584221e-05,
1802
+ "loss": 1.3525,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.42,
1807
+ "learning_rate": 6.475336419580151e-05,
1808
+ "loss": 1.3155,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.42,
1813
+ "learning_rate": 6.453474506055228e-05,
1814
+ "loss": 1.3143,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.43,
1819
+ "learning_rate": 6.431582198175203e-05,
1820
+ "loss": 1.3338,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.43,
1825
+ "learning_rate": 6.409659953741416e-05,
1826
+ "loss": 1.3271,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.43,
1831
+ "learning_rate": 6.387708231181229e-05,
1832
+ "loss": 1.2591,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.43,
1837
+ "learning_rate": 6.365727489538437e-05,
1838
+ "loss": 1.2911,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.43,
1843
+ "learning_rate": 6.343718188463663e-05,
1844
+ "loss": 1.2664,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.43,
1849
+ "learning_rate": 6.321680788204758e-05,
1850
+ "loss": 1.2654,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.43,
1855
+ "learning_rate": 6.299615749597165e-05,
1856
+ "loss": 1.256,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.44,
1861
+ "learning_rate": 6.277523534054284e-05,
1862
+ "loss": 1.2852,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.44,
1867
+ "learning_rate": 6.255404603557833e-05,
1868
+ "loss": 1.2917,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.44,
1873
+ "learning_rate": 6.233259420648175e-05,
1874
+ "loss": 1.2603,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.44,
1879
+ "learning_rate": 6.211088448414653e-05,
1880
+ "loss": 1.324,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.44,
1885
+ "learning_rate": 6.188892150485903e-05,
1886
+ "loss": 1.3535,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.44,
1891
+ "learning_rate": 6.166670991020162e-05,
1892
+ "loss": 1.2928,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.44,
1897
+ "learning_rate": 6.144425434695551e-05,
1898
+ "loss": 1.3231,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.45,
1903
+ "learning_rate": 6.122155946700381e-05,
1904
+ "loss": 1.313,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.45,
1909
+ "learning_rate": 6.099862992723397e-05,
1910
+ "loss": 1.3226,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.45,
1915
+ "learning_rate": 6.077547038944058e-05,
1916
+ "loss": 1.3328,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.45,
1921
+ "learning_rate": 6.0552085520227875e-05,
1922
+ "loss": 1.2803,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.45,
1927
+ "learning_rate": 6.032847999091206e-05,
1928
+ "loss": 1.3747,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.45,
1933
+ "learning_rate": 6.010465847742368e-05,
1934
+ "loss": 1.2863,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.45,
1939
+ "learning_rate": 5.988062566020987e-05,
1940
+ "loss": 1.3153,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.46,
1945
+ "learning_rate": 5.9656386224136426e-05,
1946
+ "loss": 1.2917,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.46,
1951
+ "learning_rate": 5.943194485838985e-05,
1952
+ "loss": 1.2688,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.46,
1957
+ "learning_rate": 5.920730625637934e-05,
1958
+ "loss": 1.3114,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.46,
1963
+ "learning_rate": 5.8982475115638515e-05,
1964
+ "loss": 1.3089,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.46,
1969
+ "learning_rate": 5.875745613772736e-05,
1970
+ "loss": 1.3035,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.46,
1975
+ "learning_rate": 5.85322540281338e-05,
1976
+ "loss": 1.3158,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.46,
1981
+ "learning_rate": 5.830687349617529e-05,
1982
+ "loss": 1.2819,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.47,
1987
+ "learning_rate": 5.808131925490039e-05,
1988
+ "loss": 1.3261,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.47,
1993
+ "learning_rate": 5.7855596020990186e-05,
1994
+ "loss": 1.2925,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.47,
1999
+ "learning_rate": 5.7629708514659655e-05,
2000
+ "loss": 1.2977,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.47,
2005
+ "learning_rate": 5.740366145955893e-05,
2006
+ "loss": 1.2672,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.47,
2011
+ "learning_rate": 5.7177459582674595e-05,
2012
+ "loss": 1.2812,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.47,
2017
+ "learning_rate": 5.6951107614230783e-05,
2018
+ "loss": 1.343,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.47,
2023
+ "learning_rate": 5.672461028759024e-05,
2024
+ "loss": 1.2741,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.47,
2029
+ "learning_rate": 5.649797233915539e-05,
2030
+ "loss": 1.2426,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.48,
2035
+ "learning_rate": 5.627119850826931e-05,
2036
+ "loss": 1.2673,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.48,
2041
+ "learning_rate": 5.6044293537116496e-05,
2042
+ "loss": 1.2921,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.48,
2047
+ "learning_rate": 5.5817262170623865e-05,
2048
+ "loss": 1.3118,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.48,
2053
+ "learning_rate": 5.559010915636143e-05,
2054
+ "loss": 1.2766,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.48,
2059
+ "learning_rate": 5.5362839244443034e-05,
2060
+ "loss": 1.311,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.48,
2065
+ "learning_rate": 5.513545718742702e-05,
2066
+ "loss": 1.327,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.48,
2071
+ "learning_rate": 5.490796774021687e-05,
2072
+ "loss": 1.3586,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.49,
2077
+ "learning_rate": 5.468037565996177e-05,
2078
+ "loss": 1.3274,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.49,
2083
+ "learning_rate": 5.445268570595708e-05,
2084
+ "loss": 1.2875,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.49,
2089
+ "learning_rate": 5.42249026395449e-05,
2090
+ "loss": 1.2926,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.49,
2095
+ "learning_rate": 5.399703122401441e-05,
2096
+ "loss": 1.3126,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.49,
2101
+ "learning_rate": 5.376907622450229e-05,
2102
+ "loss": 1.3025,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.49,
2107
+ "learning_rate": 5.3541042407893164e-05,
2108
+ "loss": 1.3226,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 0.49,
2113
+ "learning_rate": 5.331293454271974e-05,
2114
+ "loss": 1.3268,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 0.5,
2119
+ "learning_rate": 5.308475739906329e-05,
2120
+ "loss": 1.328,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 0.5,
2125
+ "learning_rate": 5.285651574845374e-05,
2126
+ "loss": 1.3183,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 0.5,
2131
+ "learning_rate": 5.262821436376998e-05,
2132
+ "loss": 1.2694,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 0.5,
2137
+ "learning_rate": 5.239985801914e-05,
2138
+ "loss": 1.3136,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 0.5,
2143
+ "learning_rate": 5.217145148984114e-05,
2144
+ "loss": 1.2293,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 0.5,
2149
+ "learning_rate": 5.1942999552200136e-05,
2150
+ "loss": 1.2772,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 0.5,
2155
+ "learning_rate": 5.171450698349329e-05,
2156
+ "loss": 1.3034,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 0.51,
2161
+ "learning_rate": 5.148597856184656e-05,
2162
+ "loss": 1.3186,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 0.51,
2167
+ "learning_rate": 5.125741906613565e-05,
2168
+ "loss": 1.2917,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 0.51,
2173
+ "learning_rate": 5.102883327588608e-05,
2174
+ "loss": 1.2597,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 0.51,
2179
+ "learning_rate": 5.080022597117318e-05,
2180
+ "loss": 1.2747,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 0.51,
2185
+ "learning_rate": 5.057160193252225e-05,
2186
+ "loss": 1.3008,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 0.51,
2191
+ "learning_rate": 5.0342965940808486e-05,
2192
+ "loss": 1.3098,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 0.51,
2197
+ "learning_rate": 5.011432277715702e-05,
2198
+ "loss": 1.2622,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 0.52,
2203
+ "learning_rate": 4.9885677222842984e-05,
2204
+ "loss": 1.2856,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 0.52,
2209
+ "learning_rate": 4.965703405919154e-05,
2210
+ "loss": 1.2775,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 0.52,
2215
+ "learning_rate": 4.942839806747775e-05,
2216
+ "loss": 1.2891,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 0.52,
2221
+ "learning_rate": 4.919977402882682e-05,
2222
+ "loss": 1.3406,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 0.52,
2227
+ "learning_rate": 4.897116672411395e-05,
2228
+ "loss": 1.302,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 0.52,
2233
+ "learning_rate": 4.8742580933864356e-05,
2234
+ "loss": 1.3238,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 0.52,
2239
+ "learning_rate": 4.851402143815345e-05,
2240
+ "loss": 1.2748,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 0.53,
2245
+ "learning_rate": 4.828549301650673e-05,
2246
+ "loss": 1.2535,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 0.53,
2251
+ "learning_rate": 4.8057000447799876e-05,
2252
+ "loss": 1.26,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 0.53,
2257
+ "learning_rate": 4.782854851015886e-05,
2258
+ "loss": 1.2667,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 0.53,
2263
+ "learning_rate": 4.760014198086002e-05,
2264
+ "loss": 1.2761,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 0.53,
2269
+ "learning_rate": 4.737178563623004e-05,
2270
+ "loss": 1.2922,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 0.53,
2275
+ "learning_rate": 4.714348425154627e-05,
2276
+ "loss": 1.2724,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 0.53,
2281
+ "learning_rate": 4.691524260093672e-05,
2282
+ "loss": 1.2786,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 0.54,
2287
+ "learning_rate": 4.668706545728026e-05,
2288
+ "loss": 1.3129,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 0.54,
2293
+ "learning_rate": 4.6458957592106855e-05,
2294
+ "loss": 1.2888,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 0.54,
2299
+ "learning_rate": 4.623092377549772e-05,
2300
+ "loss": 1.2741,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 0.54,
2305
+ "learning_rate": 4.600296877598561e-05,
2306
+ "loss": 1.2683,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 0.54,
2311
+ "learning_rate": 4.577509736045511e-05,
2312
+ "loss": 1.2782,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 0.54,
2317
+ "learning_rate": 4.554731429404293e-05,
2318
+ "loss": 1.2592,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 0.54,
2323
+ "learning_rate": 4.5319624340038244e-05,
2324
+ "loss": 1.3419,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 0.55,
2329
+ "learning_rate": 4.509203225978314e-05,
2330
+ "loss": 1.2586,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 0.55,
2335
+ "learning_rate": 4.486454281257299e-05,
2336
+ "loss": 1.3275,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 0.55,
2341
+ "learning_rate": 4.4637160755557e-05,
2342
+ "loss": 1.2152,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 0.55,
2347
+ "learning_rate": 4.4409890843638584e-05,
2348
+ "loss": 1.3169,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 0.55,
2353
+ "learning_rate": 4.418273782937613e-05,
2354
+ "loss": 1.2855,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 0.55,
2359
+ "learning_rate": 4.395570646288352e-05,
2360
+ "loss": 1.2351,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 0.55,
2365
+ "learning_rate": 4.372880149173071e-05,
2366
+ "loss": 1.3066,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 0.56,
2371
+ "learning_rate": 4.35020276608446e-05,
2372
+ "loss": 1.2788,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 0.56,
2377
+ "learning_rate": 4.327538971240978e-05,
2378
+ "loss": 1.3019,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 0.56,
2383
+ "learning_rate": 4.304889238576922e-05,
2384
+ "loss": 1.2754,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 0.56,
2389
+ "learning_rate": 4.2822540417325396e-05,
2390
+ "loss": 1.2644,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 0.56,
2395
+ "learning_rate": 4.2596338540441086e-05,
2396
+ "loss": 1.2097,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 0.56,
2401
+ "learning_rate": 4.237029148534036e-05,
2402
+ "loss": 1.2849,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 0.56,
2407
+ "learning_rate": 4.2144403979009826e-05,
2408
+ "loss": 1.2622,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 0.57,
2413
+ "learning_rate": 4.1918680745099614e-05,
2414
+ "loss": 1.2837,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 0.57,
2419
+ "learning_rate": 4.169312650382471e-05,
2420
+ "loss": 1.2705,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 0.57,
2425
+ "learning_rate": 4.1467745971866216e-05,
2426
+ "loss": 1.274,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 0.57,
2431
+ "learning_rate": 4.124254386227264e-05,
2432
+ "loss": 1.2877,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 0.57,
2437
+ "learning_rate": 4.101752488436149e-05,
2438
+ "loss": 1.2715,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 0.57,
2443
+ "learning_rate": 4.0792693743620695e-05,
2444
+ "loss": 1.2333,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 0.57,
2449
+ "learning_rate": 4.056805514161015e-05,
2450
+ "loss": 1.3097,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 0.58,
2455
+ "learning_rate": 4.034361377586357e-05,
2456
+ "loss": 1.3334,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 0.58,
2461
+ "learning_rate": 4.0119374339790136e-05,
2462
+ "loss": 1.2569,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 0.58,
2467
+ "learning_rate": 3.989534152257632e-05,
2468
+ "loss": 1.2795,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 0.58,
2473
+ "learning_rate": 3.967152000908796e-05,
2474
+ "loss": 1.3314,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 0.58,
2479
+ "learning_rate": 3.944791447977214e-05,
2480
+ "loss": 1.3027,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 0.58,
2485
+ "learning_rate": 3.922452961055941e-05,
2486
+ "loss": 1.2614,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 0.58,
2491
+ "learning_rate": 3.900137007276605e-05,
2492
+ "loss": 1.2581,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 0.58,
2497
+ "learning_rate": 3.8778440532996204e-05,
2498
+ "loss": 1.2899,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 0.59,
2503
+ "learning_rate": 3.855574565304448e-05,
2504
+ "loss": 1.2968,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 0.59,
2509
+ "learning_rate": 3.8333290089798415e-05,
2510
+ "loss": 1.2594,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 0.59,
2515
+ "learning_rate": 3.811107849514098e-05,
2516
+ "loss": 1.2745,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 0.59,
2521
+ "learning_rate": 3.788911551585348e-05,
2522
+ "loss": 1.2817,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 0.59,
2527
+ "learning_rate": 3.7667405793518264e-05,
2528
+ "loss": 1.2884,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 0.59,
2533
+ "learning_rate": 3.744595396442169e-05,
2534
+ "loss": 1.2748,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 0.59,
2539
+ "learning_rate": 3.722476465945718e-05,
2540
+ "loss": 1.309,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 0.6,
2545
+ "learning_rate": 3.7003842504028366e-05,
2546
+ "loss": 1.3223,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 0.6,
2551
+ "learning_rate": 3.678319211795242e-05,
2552
+ "loss": 1.3418,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 0.6,
2557
+ "learning_rate": 3.656281811536337e-05,
2558
+ "loss": 1.274,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 0.6,
2563
+ "learning_rate": 3.634272510461564e-05,
2564
+ "loss": 1.2765,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 0.6,
2569
+ "learning_rate": 3.612291768818772e-05,
2570
+ "loss": 1.2968,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 0.6,
2575
+ "learning_rate": 3.590340046258586e-05,
2576
+ "loss": 1.2538,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 0.6,
2581
+ "learning_rate": 3.5684178018247996e-05,
2582
+ "loss": 1.3016,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 0.61,
2587
+ "learning_rate": 3.546525493944773e-05,
2588
+ "loss": 1.287,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 0.61,
2593
+ "learning_rate": 3.52466358041985e-05,
2594
+ "loss": 1.2595,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 0.61,
2599
+ "learning_rate": 3.502832518415778e-05,
2600
+ "loss": 1.2606,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 0.61,
2605
+ "learning_rate": 3.48103276445316e-05,
2606
+ "loss": 1.2743,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 0.61,
2611
+ "learning_rate": 3.459264774397891e-05,
2612
+ "loss": 1.2596,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 0.61,
2617
+ "learning_rate": 3.437529003451639e-05,
2618
+ "loss": 1.2515,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 0.61,
2623
+ "learning_rate": 3.415825906142326e-05,
2624
+ "loss": 1.2812,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 0.62,
2629
+ "learning_rate": 3.394155936314609e-05,
2630
+ "loss": 1.3057,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 0.62,
2635
+ "learning_rate": 3.372519547120407e-05,
2636
+ "loss": 1.2646,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 0.62,
2641
+ "learning_rate": 3.350917191009416e-05,
2642
+ "loss": 1.2425,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 0.62,
2647
+ "learning_rate": 3.329349319719644e-05,
2648
+ "loss": 1.2911,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 0.62,
2653
+ "learning_rate": 3.307816384267975e-05,
2654
+ "loss": 1.2944,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 0.62,
2659
+ "learning_rate": 3.286318834940729e-05,
2660
+ "loss": 1.2845,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 0.62,
2665
+ "learning_rate": 3.264857121284246e-05,
2666
+ "loss": 1.2854,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 0.63,
2671
+ "learning_rate": 3.2434316920954935e-05,
2672
+ "loss": 1.2476,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 0.63,
2677
+ "learning_rate": 3.222042995412669e-05,
2678
+ "loss": 1.3087,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 0.63,
2683
+ "learning_rate": 3.200691478505843e-05,
2684
+ "loss": 1.2395,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 0.63,
2689
+ "learning_rate": 3.1793775878676e-05,
2690
+ "loss": 1.2305,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 0.63,
2695
+ "learning_rate": 3.1581017692036985e-05,
2696
+ "loss": 1.2651,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 0.63,
2701
+ "learning_rate": 3.136864467423758e-05,
2702
+ "loss": 1.2375,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 0.63,
2707
+ "learning_rate": 3.115666126631952e-05,
2708
+ "loss": 1.2829,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 0.64,
2713
+ "learning_rate": 3.094507190117715e-05,
2714
+ "loss": 1.3191,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 0.64,
2719
+ "learning_rate": 3.073388100346484e-05,
2720
+ "loss": 1.2975,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 0.64,
2725
+ "learning_rate": 3.0523092989504415e-05,
2726
+ "loss": 1.2755,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 0.64,
2731
+ "learning_rate": 3.0312712267192713e-05,
2732
+ "loss": 1.2873,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 0.64,
2737
+ "learning_rate": 3.010274323590956e-05,
2738
+ "loss": 1.2662,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 0.64,
2743
+ "learning_rate": 2.989319028642567e-05,
2744
+ "loss": 1.3002,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 0.64,
2749
+ "learning_rate": 2.9684057800810845e-05,
2750
+ "loss": 1.2369,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 0.65,
2755
+ "learning_rate": 2.9475350152342378e-05,
2756
+ "loss": 1.2125,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 0.65,
2761
+ "learning_rate": 2.9267071705413552e-05,
2762
+ "loss": 1.296,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 0.65,
2767
+ "learning_rate": 2.9059226815442385e-05,
2768
+ "loss": 1.2878,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 0.65,
2773
+ "learning_rate": 2.8851819828780623e-05,
2774
+ "loss": 1.308,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 0.65,
2779
+ "learning_rate": 2.8644855082622695e-05,
2780
+ "loss": 1.2083,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 0.65,
2785
+ "learning_rate": 2.8438336904915185e-05,
2786
+ "loss": 1.2431,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 0.65,
2791
+ "learning_rate": 2.823226961426625e-05,
2792
+ "loss": 1.2315,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 0.66,
2797
+ "learning_rate": 2.802665751985525e-05,
2798
+ "loss": 1.3051,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 0.66,
2803
+ "learning_rate": 2.7821504921342777e-05,
2804
+ "loss": 1.2527,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 0.66,
2809
+ "learning_rate": 2.7616816108780623e-05,
2810
+ "loss": 1.295,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 0.66,
2815
+ "learning_rate": 2.741259536252213e-05,
2816
+ "loss": 1.2856,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 0.66,
2821
+ "learning_rate": 2.7208846953132682e-05,
2822
+ "loss": 1.28,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 0.66,
2827
+ "learning_rate": 2.700557514130032e-05,
2828
+ "loss": 1.2658,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 0.66,
2833
+ "learning_rate": 2.6802784177746777e-05,
2834
+ "loss": 1.2511,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 0.67,
2839
+ "learning_rate": 2.6600478303138503e-05,
2840
+ "loss": 1.3012,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 0.67,
2845
+ "learning_rate": 2.6398661747997955e-05,
2846
+ "loss": 1.2492,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 0.67,
2851
+ "learning_rate": 2.619733873261524e-05,
2852
+ "loss": 1.2535,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 0.67,
2857
+ "learning_rate": 2.5996513466959794e-05,
2858
+ "loss": 1.261,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 0.67,
2863
+ "learning_rate": 2.579619015059229e-05,
2864
+ "loss": 1.2847,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 0.67,
2869
+ "learning_rate": 2.5596372972576967e-05,
2870
+ "loss": 1.2955,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 0.67,
2875
+ "learning_rate": 2.5397066111393853e-05,
2876
+ "loss": 1.2465,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 0.68,
2881
+ "learning_rate": 2.5198273734851553e-05,
2882
+ "loss": 1.2523,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 0.68,
2887
+ "learning_rate": 2.500000000000001e-05,
2888
+ "loss": 1.3038,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 0.68,
2893
+ "learning_rate": 2.4802249053043526e-05,
2894
+ "loss": 1.3138,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 0.68,
2899
+ "learning_rate": 2.4605025029254164e-05,
2900
+ "loss": 1.2282,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 0.68,
2905
+ "learning_rate": 2.4408332052885246e-05,
2906
+ "loss": 1.2731,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 0.68,
2911
+ "learning_rate": 2.4212174237085007e-05,
2912
+ "loss": 1.3086,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 0.68,
2917
+ "learning_rate": 2.401655568381074e-05,
2918
+ "loss": 1.3227,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 0.68,
2923
+ "learning_rate": 2.382148048374292e-05,
2924
+ "loss": 1.2396,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 0.69,
2929
+ "learning_rate": 2.3626952716199647e-05,
2930
+ "loss": 1.2487,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 0.69,
2935
+ "learning_rate": 2.3432976449051442e-05,
2936
+ "loss": 1.2149,
2937
+ "step": 488
2938
+ },
2939
+ {
2940
+ "epoch": 0.69,
2941
+ "learning_rate": 2.3239555738636044e-05,
2942
+ "loss": 1.2986,
2943
+ "step": 489
2944
+ },
2945
+ {
2946
+ "epoch": 0.69,
2947
+ "learning_rate": 2.3046694629673716e-05,
2948
+ "loss": 1.2814,
2949
+ "step": 490
2950
+ },
2951
+ {
2952
+ "epoch": 0.69,
2953
+ "learning_rate": 2.28543971551826e-05,
2954
+ "loss": 1.2465,
2955
+ "step": 491
2956
+ },
2957
+ {
2958
+ "epoch": 0.69,
2959
+ "learning_rate": 2.266266733639434e-05,
2960
+ "loss": 1.307,
2961
+ "step": 492
2962
+ },
2963
+ {
2964
+ "epoch": 0.69,
2965
+ "learning_rate": 2.247150918267008e-05,
2966
+ "loss": 1.2532,
2967
+ "step": 493
2968
+ },
2969
+ {
2970
+ "epoch": 0.7,
2971
+ "learning_rate": 2.2280926691416603e-05,
2972
+ "loss": 1.261,
2973
+ "step": 494
2974
+ },
2975
+ {
2976
+ "epoch": 0.7,
2977
+ "learning_rate": 2.209092384800265e-05,
2978
+ "loss": 1.2771,
2979
+ "step": 495
2980
+ },
2981
+ {
2982
+ "epoch": 0.7,
2983
+ "learning_rate": 2.190150462567569e-05,
2984
+ "loss": 1.2589,
2985
+ "step": 496
2986
+ },
2987
+ {
2988
+ "epoch": 0.7,
2989
+ "learning_rate": 2.1712672985478815e-05,
2990
+ "loss": 1.278,
2991
+ "step": 497
2992
+ },
2993
+ {
2994
+ "epoch": 0.7,
2995
+ "learning_rate": 2.1524432876167812e-05,
2996
+ "loss": 1.2595,
2997
+ "step": 498
2998
+ },
2999
+ {
3000
+ "epoch": 0.7,
3001
+ "learning_rate": 2.133678823412873e-05,
3002
+ "loss": 1.299,
3003
+ "step": 499
3004
+ },
3005
+ {
3006
+ "epoch": 0.7,
3007
+ "learning_rate": 2.1149742983295446e-05,
3008
+ "loss": 1.3015,
3009
+ "step": 500
3010
+ },
3011
+ {
3012
+ "epoch": 0.71,
3013
+ "learning_rate": 2.0963301035067685e-05,
3014
+ "loss": 1.2777,
3015
+ "step": 501
3016
+ },
3017
+ {
3018
+ "epoch": 0.71,
3019
+ "learning_rate": 2.0777466288229207e-05,
3020
+ "loss": 1.2536,
3021
+ "step": 502
3022
+ },
3023
+ {
3024
+ "epoch": 0.71,
3025
+ "learning_rate": 2.0592242628866236e-05,
3026
+ "loss": 1.2498,
3027
+ "step": 503
3028
+ },
3029
+ {
3030
+ "epoch": 0.71,
3031
+ "learning_rate": 2.040763393028627e-05,
3032
+ "loss": 1.2639,
3033
+ "step": 504
3034
+ },
3035
+ {
3036
+ "epoch": 0.71,
3037
+ "learning_rate": 2.022364405293703e-05,
3038
+ "loss": 1.2522,
3039
+ "step": 505
3040
+ },
3041
+ {
3042
+ "epoch": 0.71,
3043
+ "learning_rate": 2.0040276844325718e-05,
3044
+ "loss": 1.263,
3045
+ "step": 506
3046
+ },
3047
+ {
3048
+ "epoch": 0.71,
3049
+ "learning_rate": 1.9857536138938627e-05,
3050
+ "loss": 1.2423,
3051
+ "step": 507
3052
+ },
3053
+ {
3054
+ "epoch": 0.72,
3055
+ "learning_rate": 1.9675425758160925e-05,
3056
+ "loss": 1.2513,
3057
+ "step": 508
3058
+ },
3059
+ {
3060
+ "epoch": 0.72,
3061
+ "learning_rate": 1.949394951019669e-05,
3062
+ "loss": 1.2495,
3063
+ "step": 509
3064
+ },
3065
+ {
3066
+ "epoch": 0.72,
3067
+ "learning_rate": 1.9313111189989375e-05,
3068
+ "loss": 1.2178,
3069
+ "step": 510
3070
+ },
3071
+ {
3072
+ "epoch": 0.72,
3073
+ "learning_rate": 1.913291457914234e-05,
3074
+ "loss": 1.2509,
3075
+ "step": 511
3076
+ },
3077
+ {
3078
+ "epoch": 0.72,
3079
+ "learning_rate": 1.8953363445839877e-05,
3080
+ "loss": 1.2768,
3081
+ "step": 512
3082
+ },
3083
+ {
3084
+ "epoch": 0.72,
3085
+ "learning_rate": 1.8774461544768347e-05,
3086
+ "loss": 1.2517,
3087
+ "step": 513
3088
+ },
3089
+ {
3090
+ "epoch": 0.72,
3091
+ "learning_rate": 1.8596212617037694e-05,
3092
+ "loss": 1.2702,
3093
+ "step": 514
3094
+ },
3095
+ {
3096
+ "epoch": 0.73,
3097
+ "learning_rate": 1.8418620390103163e-05,
3098
+ "loss": 1.2566,
3099
+ "step": 515
3100
+ },
3101
+ {
3102
+ "epoch": 0.73,
3103
+ "learning_rate": 1.8241688577687426e-05,
3104
+ "loss": 1.2464,
3105
+ "step": 516
3106
+ },
3107
+ {
3108
+ "epoch": 0.73,
3109
+ "learning_rate": 1.806542087970289e-05,
3110
+ "loss": 1.2356,
3111
+ "step": 517
3112
+ },
3113
+ {
3114
+ "epoch": 0.73,
3115
+ "learning_rate": 1.788982098217427e-05,
3116
+ "loss": 1.2719,
3117
+ "step": 518
3118
+ },
3119
+ {
3120
+ "epoch": 0.73,
3121
+ "learning_rate": 1.7714892557161624e-05,
3122
+ "loss": 1.2667,
3123
+ "step": 519
3124
+ },
3125
+ {
3126
+ "epoch": 0.73,
3127
+ "learning_rate": 1.754063926268349e-05,
3128
+ "loss": 1.2486,
3129
+ "step": 520
3130
+ },
3131
+ {
3132
+ "epoch": 0.73,
3133
+ "learning_rate": 1.7367064742640348e-05,
3134
+ "loss": 1.2685,
3135
+ "step": 521
3136
+ },
3137
+ {
3138
+ "epoch": 0.74,
3139
+ "learning_rate": 1.719417262673854e-05,
3140
+ "loss": 1.3077,
3141
+ "step": 522
3142
+ },
3143
+ {
3144
+ "epoch": 0.74,
3145
+ "learning_rate": 1.7021966530414303e-05,
3146
+ "loss": 1.2647,
3147
+ "step": 523
3148
+ },
3149
+ {
3150
+ "epoch": 0.74,
3151
+ "learning_rate": 1.6850450054758092e-05,
3152
+ "loss": 1.2924,
3153
+ "step": 524
3154
+ },
3155
+ {
3156
+ "epoch": 0.74,
3157
+ "learning_rate": 1.667962678643943e-05,
3158
+ "loss": 1.2512,
3159
+ "step": 525
3160
+ },
3161
+ {
3162
+ "epoch": 0.74,
3163
+ "learning_rate": 1.6509500297631787e-05,
3164
+ "loss": 1.2396,
3165
+ "step": 526
3166
+ },
3167
+ {
3168
+ "epoch": 0.74,
3169
+ "learning_rate": 1.6340074145937934e-05,
3170
+ "loss": 1.2432,
3171
+ "step": 527
3172
+ },
3173
+ {
3174
+ "epoch": 0.74,
3175
+ "learning_rate": 1.6171351874315494e-05,
3176
+ "loss": 1.2462,
3177
+ "step": 528
3178
+ },
3179
+ {
3180
+ "epoch": 0.75,
3181
+ "learning_rate": 1.600333701100293e-05,
3182
+ "loss": 1.2697,
3183
+ "step": 529
3184
+ },
3185
+ {
3186
+ "epoch": 0.75,
3187
+ "learning_rate": 1.583603306944572e-05,
3188
+ "loss": 1.2251,
3189
+ "step": 530
3190
+ },
3191
+ {
3192
+ "epoch": 0.75,
3193
+ "learning_rate": 1.566944354822286e-05,
3194
+ "loss": 1.2481,
3195
+ "step": 531
3196
+ },
3197
+ {
3198
+ "epoch": 0.75,
3199
+ "learning_rate": 1.5503571930973786e-05,
3200
+ "loss": 1.2048,
3201
+ "step": 532
3202
+ },
3203
+ {
3204
+ "epoch": 0.75,
3205
+ "learning_rate": 1.533842168632541e-05,
3206
+ "loss": 1.277,
3207
+ "step": 533
3208
+ },
3209
+ {
3210
+ "epoch": 0.75,
3211
+ "learning_rate": 1.5173996267819695e-05,
3212
+ "loss": 1.2525,
3213
+ "step": 534
3214
+ },
3215
+ {
3216
+ "epoch": 0.75,
3217
+ "learning_rate": 1.5010299113841397e-05,
3218
+ "loss": 1.2449,
3219
+ "step": 535
3220
+ },
3221
+ {
3222
+ "epoch": 0.76,
3223
+ "learning_rate": 1.4847333647546113e-05,
3224
+ "loss": 1.2571,
3225
+ "step": 536
3226
+ },
3227
+ {
3228
+ "epoch": 0.76,
3229
+ "learning_rate": 1.468510327678877e-05,
3230
+ "loss": 1.2618,
3231
+ "step": 537
3232
+ },
3233
+ {
3234
+ "epoch": 0.76,
3235
+ "learning_rate": 1.4523611394052356e-05,
3236
+ "loss": 1.2877,
3237
+ "step": 538
3238
+ },
3239
+ {
3240
+ "epoch": 0.76,
3241
+ "learning_rate": 1.4362861376376896e-05,
3242
+ "loss": 1.2563,
3243
+ "step": 539
3244
+ },
3245
+ {
3246
+ "epoch": 0.76,
3247
+ "learning_rate": 1.4202856585288954e-05,
3248
+ "loss": 1.3038,
3249
+ "step": 540
3250
+ },
3251
+ {
3252
+ "epoch": 0.76,
3253
+ "learning_rate": 1.4043600366731213e-05,
3254
+ "loss": 1.2746,
3255
+ "step": 541
3256
+ },
3257
+ {
3258
+ "epoch": 0.76,
3259
+ "learning_rate": 1.3885096050992624e-05,
3260
+ "loss": 1.2297,
3261
+ "step": 542
3262
+ },
3263
+ {
3264
+ "epoch": 0.77,
3265
+ "learning_rate": 1.3727346952638703e-05,
3266
+ "loss": 1.2217,
3267
+ "step": 543
3268
+ },
3269
+ {
3270
+ "epoch": 0.77,
3271
+ "learning_rate": 1.3570356370442188e-05,
3272
+ "loss": 1.2506,
3273
+ "step": 544
3274
+ },
3275
+ {
3276
+ "epoch": 0.77,
3277
+ "learning_rate": 1.341412758731413e-05,
3278
+ "loss": 1.2465,
3279
+ "step": 545
3280
+ },
3281
+ {
3282
+ "epoch": 0.77,
3283
+ "learning_rate": 1.325866387023521e-05,
3284
+ "loss": 1.2689,
3285
+ "step": 546
3286
+ },
3287
+ {
3288
+ "epoch": 0.77,
3289
+ "learning_rate": 1.3103968470187384e-05,
3290
+ "loss": 1.235,
3291
+ "step": 547
3292
+ },
3293
+ {
3294
+ "epoch": 0.77,
3295
+ "learning_rate": 1.2950044622085955e-05,
3296
+ "loss": 1.2777,
3297
+ "step": 548
3298
+ },
3299
+ {
3300
+ "epoch": 0.77,
3301
+ "learning_rate": 1.2796895544711929e-05,
3302
+ "loss": 1.2638,
3303
+ "step": 549
3304
+ },
3305
+ {
3306
+ "epoch": 0.78,
3307
+ "learning_rate": 1.2644524440644628e-05,
3308
+ "loss": 1.2612,
3309
+ "step": 550
3310
+ },
3311
+ {
3312
+ "epoch": 0.78,
3313
+ "learning_rate": 1.249293449619483e-05,
3314
+ "loss": 1.269,
3315
+ "step": 551
3316
+ },
3317
+ {
3318
+ "epoch": 0.78,
3319
+ "learning_rate": 1.2342128881338027e-05,
3320
+ "loss": 1.2453,
3321
+ "step": 552
3322
+ },
3323
+ {
3324
+ "epoch": 0.78,
3325
+ "learning_rate": 1.2192110749648233e-05,
3326
+ "loss": 1.2294,
3327
+ "step": 553
3328
+ },
3329
+ {
3330
+ "epoch": 0.78,
3331
+ "learning_rate": 1.2042883238231984e-05,
3332
+ "loss": 1.2449,
3333
+ "step": 554
3334
+ },
3335
+ {
3336
+ "epoch": 0.78,
3337
+ "learning_rate": 1.1894449467662728e-05,
3338
+ "loss": 1.2523,
3339
+ "step": 555
3340
+ },
3341
+ {
3342
+ "epoch": 0.78,
3343
+ "learning_rate": 1.1746812541915608e-05,
3344
+ "loss": 1.2162,
3345
+ "step": 556
3346
+ },
3347
+ {
3348
+ "epoch": 0.79,
3349
+ "learning_rate": 1.1599975548302549e-05,
3350
+ "loss": 1.2533,
3351
+ "step": 557
3352
+ },
3353
+ {
3354
+ "epoch": 0.79,
3355
+ "learning_rate": 1.1453941557407638e-05,
3356
+ "loss": 1.2307,
3357
+ "step": 558
3358
+ },
3359
+ {
3360
+ "epoch": 0.79,
3361
+ "learning_rate": 1.1308713623022987e-05,
3362
+ "loss": 1.2713,
3363
+ "step": 559
3364
+ },
3365
+ {
3366
+ "epoch": 0.79,
3367
+ "learning_rate": 1.1164294782084866e-05,
3368
+ "loss": 1.2636,
3369
+ "step": 560
3370
+ },
3371
+ {
3372
+ "epoch": 0.79,
3373
+ "learning_rate": 1.1020688054610118e-05,
3374
+ "loss": 1.2408,
3375
+ "step": 561
3376
+ },
3377
+ {
3378
+ "epoch": 0.79,
3379
+ "learning_rate": 1.0877896443633117e-05,
3380
+ "loss": 1.2865,
3381
+ "step": 562
3382
+ },
3383
+ {
3384
+ "epoch": 0.79,
3385
+ "learning_rate": 1.0735922935142873e-05,
3386
+ "loss": 1.2493,
3387
+ "step": 563
3388
+ },
3389
+ {
3390
+ "epoch": 0.79,
3391
+ "learning_rate": 1.0594770498020657e-05,
3392
+ "loss": 1.2406,
3393
+ "step": 564
3394
+ },
3395
+ {
3396
+ "epoch": 0.8,
3397
+ "learning_rate": 1.0454442083977912e-05,
3398
+ "loss": 1.263,
3399
+ "step": 565
3400
+ },
3401
+ {
3402
+ "epoch": 0.8,
3403
+ "learning_rate": 1.0314940627494451e-05,
3404
+ "loss": 1.2701,
3405
+ "step": 566
3406
+ },
3407
+ {
3408
+ "epoch": 0.8,
3409
+ "learning_rate": 1.0176269045757202e-05,
3410
+ "loss": 1.2196,
3411
+ "step": 567
3412
+ },
3413
+ {
3414
+ "epoch": 0.8,
3415
+ "learning_rate": 1.0038430238599156e-05,
3416
+ "loss": 1.2103,
3417
+ "step": 568
3418
+ },
3419
+ {
3420
+ "epoch": 0.8,
3421
+ "learning_rate": 9.901427088438675e-06,
3422
+ "loss": 1.2255,
3423
+ "step": 569
3424
+ },
3425
+ {
3426
+ "epoch": 0.8,
3427
+ "learning_rate": 9.76526246021931e-06,
3428
+ "loss": 1.2491,
3429
+ "step": 570
3430
+ },
3431
+ {
3432
+ "epoch": 0.8,
3433
+ "learning_rate": 9.629939201349853e-06,
3434
+ "loss": 1.2494,
3435
+ "step": 571
3436
+ },
3437
+ {
3438
+ "epoch": 0.81,
3439
+ "learning_rate": 9.49546014164474e-06,
3440
+ "loss": 1.2868,
3441
+ "step": 572
3442
+ },
3443
+ {
3444
+ "epoch": 0.81,
3445
+ "learning_rate": 9.361828093264984e-06,
3446
+ "loss": 1.2383,
3447
+ "step": 573
3448
+ },
3449
+ {
3450
+ "epoch": 0.81,
3451
+ "learning_rate": 9.229045850659252e-06,
3452
+ "loss": 1.2227,
3453
+ "step": 574
3454
+ },
3455
+ {
3456
+ "epoch": 0.81,
3457
+ "learning_rate": 9.097116190505516e-06,
3458
+ "loss": 1.2423,
3459
+ "step": 575
3460
+ },
3461
+ {
3462
+ "epoch": 0.81,
3463
+ "learning_rate": 8.966041871652969e-06,
3464
+ "loss": 1.233,
3465
+ "step": 576
3466
+ },
3467
+ {
3468
+ "epoch": 0.81,
3469
+ "learning_rate": 8.835825635064266e-06,
3470
+ "loss": 1.2144,
3471
+ "step": 577
3472
+ },
3473
+ {
3474
+ "epoch": 0.81,
3475
+ "learning_rate": 8.706470203758316e-06,
3476
+ "loss": 1.2529,
3477
+ "step": 578
3478
+ },
3479
+ {
3480
+ "epoch": 0.82,
3481
+ "learning_rate": 8.577978282753274e-06,
3482
+ "loss": 1.2622,
3483
+ "step": 579
3484
+ },
3485
+ {
3486
+ "epoch": 0.82,
3487
+ "learning_rate": 8.45035255900995e-06,
3488
+ "loss": 1.2398,
3489
+ "step": 580
3490
+ },
3491
+ {
3492
+ "epoch": 0.82,
3493
+ "learning_rate": 8.323595701375702e-06,
3494
+ "loss": 1.2622,
3495
+ "step": 581
3496
+ },
3497
+ {
3498
+ "epoch": 0.82,
3499
+ "learning_rate": 8.197710360528571e-06,
3500
+ "loss": 1.2585,
3501
+ "step": 582
3502
+ },
3503
+ {
3504
+ "epoch": 0.82,
3505
+ "learning_rate": 8.072699168921826e-06,
3506
+ "loss": 1.2459,
3507
+ "step": 583
3508
+ },
3509
+ {
3510
+ "epoch": 0.82,
3511
+ "learning_rate": 7.948564740728998e-06,
3512
+ "loss": 1.2625,
3513
+ "step": 584
3514
+ },
3515
+ {
3516
+ "epoch": 0.82,
3517
+ "learning_rate": 7.825309671789128e-06,
3518
+ "loss": 1.2628,
3519
+ "step": 585
3520
+ },
3521
+ {
3522
+ "epoch": 0.83,
3523
+ "learning_rate": 7.70293653955254e-06,
3524
+ "loss": 1.2116,
3525
+ "step": 586
3526
+ },
3527
+ {
3528
+ "epoch": 0.83,
3529
+ "learning_rate": 7.581447903026939e-06,
3530
+ "loss": 1.2787,
3531
+ "step": 587
3532
+ },
3533
+ {
3534
+ "epoch": 0.83,
3535
+ "learning_rate": 7.460846302723845e-06,
3536
+ "loss": 1.2558,
3537
+ "step": 588
3538
+ },
3539
+ {
3540
+ "epoch": 0.83,
3541
+ "learning_rate": 7.341134260605536e-06,
3542
+ "loss": 1.2558,
3543
+ "step": 589
3544
+ },
3545
+ {
3546
+ "epoch": 0.83,
3547
+ "learning_rate": 7.2223142800322775e-06,
3548
+ "loss": 1.2198,
3549
+ "step": 590
3550
+ },
3551
+ {
3552
+ "epoch": 0.83,
3553
+ "learning_rate": 7.104388845709981e-06,
3554
+ "loss": 1.2856,
3555
+ "step": 591
3556
+ },
3557
+ {
3558
+ "epoch": 0.83,
3559
+ "learning_rate": 6.987360423638206e-06,
3560
+ "loss": 1.1944,
3561
+ "step": 592
3562
+ },
3563
+ {
3564
+ "epoch": 0.84,
3565
+ "learning_rate": 6.871231461058658e-06,
3566
+ "loss": 1.2197,
3567
+ "step": 593
3568
+ },
3569
+ {
3570
+ "epoch": 0.84,
3571
+ "learning_rate": 6.756004386403996e-06,
3572
+ "loss": 1.2229,
3573
+ "step": 594
3574
+ },
3575
+ {
3576
+ "epoch": 0.84,
3577
+ "learning_rate": 6.64168160924698e-06,
3578
+ "loss": 1.2093,
3579
+ "step": 595
3580
+ },
3581
+ {
3582
+ "epoch": 0.84,
3583
+ "learning_rate": 6.528265520250182e-06,
3584
+ "loss": 1.2403,
3585
+ "step": 596
3586
+ },
3587
+ {
3588
+ "epoch": 0.84,
3589
+ "learning_rate": 6.415758491115953e-06,
3590
+ "loss": 1.2749,
3591
+ "step": 597
3592
+ },
3593
+ {
3594
+ "epoch": 0.84,
3595
+ "learning_rate": 6.304162874536796e-06,
3596
+ "loss": 1.2668,
3597
+ "step": 598
3598
+ },
3599
+ {
3600
+ "epoch": 0.84,
3601
+ "learning_rate": 6.1934810041462066e-06,
3602
+ "loss": 1.2744,
3603
+ "step": 599
3604
+ },
3605
+ {
3606
+ "epoch": 0.85,
3607
+ "learning_rate": 6.08371519446988e-06,
3608
+ "loss": 1.2197,
3609
+ "step": 600
3610
+ },
3611
+ {
3612
+ "epoch": 0.85,
3613
+ "learning_rate": 5.974867740877283e-06,
3614
+ "loss": 1.248,
3615
+ "step": 601
3616
+ },
3617
+ {
3618
+ "epoch": 0.85,
3619
+ "learning_rate": 5.866940919533642e-06,
3620
+ "loss": 1.227,
3621
+ "step": 602
3622
+ },
3623
+ {
3624
+ "epoch": 0.85,
3625
+ "learning_rate": 5.759936987352399e-06,
3626
+ "loss": 1.2888,
3627
+ "step": 603
3628
+ },
3629
+ {
3630
+ "epoch": 0.85,
3631
+ "learning_rate": 5.65385818194798e-06,
3632
+ "loss": 1.2776,
3633
+ "step": 604
3634
+ },
3635
+ {
3636
+ "epoch": 0.85,
3637
+ "learning_rate": 5.548706721588986e-06,
3638
+ "loss": 1.2825,
3639
+ "step": 605
3640
+ },
3641
+ {
3642
+ "epoch": 0.85,
3643
+ "learning_rate": 5.444484805151856e-06,
3644
+ "loss": 1.2633,
3645
+ "step": 606
3646
+ },
3647
+ {
3648
+ "epoch": 0.86,
3649
+ "learning_rate": 5.341194612074824e-06,
3650
+ "loss": 1.2443,
3651
+ "step": 607
3652
+ },
3653
+ {
3654
+ "epoch": 0.86,
3655
+ "learning_rate": 5.23883830231241e-06,
3656
+ "loss": 1.247,
3657
+ "step": 608
3658
+ },
3659
+ {
3660
+ "epoch": 0.86,
3661
+ "learning_rate": 5.137418016290207e-06,
3662
+ "loss": 1.2748,
3663
+ "step": 609
3664
+ },
3665
+ {
3666
+ "epoch": 0.86,
3667
+ "learning_rate": 5.036935874860111e-06,
3668
+ "loss": 1.2337,
3669
+ "step": 610
3670
+ },
3671
+ {
3672
+ "epoch": 0.86,
3673
+ "learning_rate": 4.937393979256016e-06,
3674
+ "loss": 1.2413,
3675
+ "step": 611
3676
+ },
3677
+ {
3678
+ "epoch": 0.86,
3679
+ "learning_rate": 4.8387944110498685e-06,
3680
+ "loss": 1.2295,
3681
+ "step": 612
3682
+ },
3683
+ {
3684
+ "epoch": 0.86,
3685
+ "learning_rate": 4.7411392321080605e-06,
3686
+ "loss": 1.2466,
3687
+ "step": 613
3688
+ },
3689
+ {
3690
+ "epoch": 0.87,
3691
+ "learning_rate": 4.644430484548428e-06,
3692
+ "loss": 1.247,
3693
+ "step": 614
3694
+ },
3695
+ {
3696
+ "epoch": 0.87,
3697
+ "learning_rate": 4.548670190697485e-06,
3698
+ "loss": 1.2306,
3699
+ "step": 615
3700
+ },
3701
+ {
3702
+ "epoch": 0.87,
3703
+ "learning_rate": 4.453860353048112e-06,
3704
+ "loss": 1.2751,
3705
+ "step": 616
3706
+ },
3707
+ {
3708
+ "epoch": 0.87,
3709
+ "learning_rate": 4.360002954217734e-06,
3710
+ "loss": 1.2279,
3711
+ "step": 617
3712
+ },
3713
+ {
3714
+ "epoch": 0.87,
3715
+ "learning_rate": 4.267099956906828e-06,
3716
+ "loss": 1.2359,
3717
+ "step": 618
3718
+ },
3719
+ {
3720
+ "epoch": 0.87,
3721
+ "learning_rate": 4.175153303857887e-06,
3722
+ "loss": 1.2383,
3723
+ "step": 619
3724
+ },
3725
+ {
3726
+ "epoch": 0.87,
3727
+ "learning_rate": 4.084164917814815e-06,
3728
+ "loss": 1.2658,
3729
+ "step": 620
3730
+ },
3731
+ {
3732
+ "epoch": 0.88,
3733
+ "learning_rate": 3.994136701482659e-06,
3734
+ "loss": 1.2115,
3735
+ "step": 621
3736
+ },
3737
+ {
3738
+ "epoch": 0.88,
3739
+ "learning_rate": 3.905070537487909e-06,
3740
+ "loss": 1.2615,
3741
+ "step": 622
3742
+ },
3743
+ {
3744
+ "epoch": 0.88,
3745
+ "learning_rate": 3.8169682883390565e-06,
3746
+ "loss": 1.1924,
3747
+ "step": 623
3748
+ },
3749
+ {
3750
+ "epoch": 0.88,
3751
+ "learning_rate": 3.729831796387667e-06,
3752
+ "loss": 1.2593,
3753
+ "step": 624
3754
+ },
3755
+ {
3756
+ "epoch": 0.88,
3757
+ "learning_rate": 3.643662883789878e-06,
3758
+ "loss": 1.2781,
3759
+ "step": 625
3760
+ },
3761
+ {
3762
+ "epoch": 0.88,
3763
+ "learning_rate": 3.558463352468272e-06,
3764
+ "loss": 1.1864,
3765
+ "step": 626
3766
+ },
3767
+ {
3768
+ "epoch": 0.88,
3769
+ "learning_rate": 3.474234984074182e-06,
3770
+ "loss": 1.2902,
3771
+ "step": 627
3772
+ },
3773
+ {
3774
+ "epoch": 0.89,
3775
+ "learning_rate": 3.3909795399504783e-06,
3776
+ "loss": 1.2285,
3777
+ "step": 628
3778
+ },
3779
+ {
3780
+ "epoch": 0.89,
3781
+ "learning_rate": 3.3086987610946807e-06,
3782
+ "loss": 1.2597,
3783
+ "step": 629
3784
+ },
3785
+ {
3786
+ "epoch": 0.89,
3787
+ "learning_rate": 3.2273943681225992e-06,
3788
+ "loss": 1.2546,
3789
+ "step": 630
3790
+ },
3791
+ {
3792
+ "epoch": 0.89,
3793
+ "learning_rate": 3.14706806123235e-06,
3794
+ "loss": 1.2337,
3795
+ "step": 631
3796
+ },
3797
+ {
3798
+ "epoch": 0.89,
3799
+ "learning_rate": 3.067721520168748e-06,
3800
+ "loss": 1.214,
3801
+ "step": 632
3802
+ },
3803
+ {
3804
+ "epoch": 0.89,
3805
+ "learning_rate": 2.9893564041882484e-06,
3806
+ "loss": 1.2604,
3807
+ "step": 633
3808
+ },
3809
+ {
3810
+ "epoch": 0.89,
3811
+ "learning_rate": 2.9119743520242217e-06,
3812
+ "loss": 1.2261,
3813
+ "step": 634
3814
+ },
3815
+ {
3816
+ "epoch": 0.89,
3817
+ "learning_rate": 2.835576981852656e-06,
3818
+ "loss": 1.2825,
3819
+ "step": 635
3820
+ },
3821
+ {
3822
+ "epoch": 0.9,
3823
+ "learning_rate": 2.7601658912583763e-06,
3824
+ "loss": 1.2606,
3825
+ "step": 636
3826
+ },
3827
+ {
3828
+ "epoch": 0.9,
3829
+ "learning_rate": 2.685742657201601e-06,
3830
+ "loss": 1.2474,
3831
+ "step": 637
3832
+ },
3833
+ {
3834
+ "epoch": 0.9,
3835
+ "learning_rate": 2.61230883598495e-06,
3836
+ "loss": 1.2088,
3837
+ "step": 638
3838
+ },
3839
+ {
3840
+ "epoch": 0.9,
3841
+ "learning_rate": 2.5398659632209552e-06,
3842
+ "loss": 1.2612,
3843
+ "step": 639
3844
+ },
3845
+ {
3846
+ "epoch": 0.9,
3847
+ "learning_rate": 2.4684155537998743e-06,
3848
+ "loss": 1.2175,
3849
+ "step": 640
3850
+ },
3851
+ {
3852
+ "epoch": 0.9,
3853
+ "learning_rate": 2.397959101858083e-06,
3854
+ "loss": 1.2022,
3855
+ "step": 641
3856
+ },
3857
+ {
3858
+ "epoch": 0.9,
3859
+ "learning_rate": 2.3284980807467994e-06,
3860
+ "loss": 1.219,
3861
+ "step": 642
3862
+ },
3863
+ {
3864
+ "epoch": 0.91,
3865
+ "learning_rate": 2.2600339430012442e-06,
3866
+ "loss": 1.2495,
3867
+ "step": 643
3868
+ },
3869
+ {
3870
+ "epoch": 0.91,
3871
+ "learning_rate": 2.1925681203103287e-06,
3872
+ "loss": 1.2155,
3873
+ "step": 644
3874
+ },
3875
+ {
3876
+ "epoch": 0.91,
3877
+ "learning_rate": 2.12610202348667e-06,
3878
+ "loss": 1.2359,
3879
+ "step": 645
3880
+ },
3881
+ {
3882
+ "epoch": 0.91,
3883
+ "learning_rate": 2.060637042437097e-06,
3884
+ "loss": 1.2291,
3885
+ "step": 646
3886
+ },
3887
+ {
3888
+ "epoch": 0.91,
3889
+ "learning_rate": 1.9961745461335947e-06,
3890
+ "loss": 1.2033,
3891
+ "step": 647
3892
+ },
3893
+ {
3894
+ "epoch": 0.91,
3895
+ "learning_rate": 1.9327158825846848e-06,
3896
+ "loss": 1.2563,
3897
+ "step": 648
3898
+ },
3899
+ {
3900
+ "epoch": 0.91,
3901
+ "learning_rate": 1.8702623788072027e-06,
3902
+ "loss": 1.2112,
3903
+ "step": 649
3904
+ },
3905
+ {
3906
+ "epoch": 0.92,
3907
+ "learning_rate": 1.8088153407985809e-06,
3908
+ "loss": 1.2475,
3909
+ "step": 650
3910
+ },
3911
+ {
3912
+ "epoch": 0.92,
3913
+ "learning_rate": 1.7483760535095262e-06,
3914
+ "loss": 1.2246,
3915
+ "step": 651
3916
+ },
3917
+ {
3918
+ "epoch": 0.92,
3919
+ "learning_rate": 1.6889457808171472e-06,
3920
+ "loss": 1.2597,
3921
+ "step": 652
3922
+ },
3923
+ {
3924
+ "epoch": 0.92,
3925
+ "learning_rate": 1.6305257654985361e-06,
3926
+ "loss": 1.2363,
3927
+ "step": 653
3928
+ },
3929
+ {
3930
+ "epoch": 0.92,
3931
+ "learning_rate": 1.5731172292047625e-06,
3932
+ "loss": 1.2366,
3933
+ "step": 654
3934
+ },
3935
+ {
3936
+ "epoch": 0.92,
3937
+ "learning_rate": 1.5167213724353424e-06,
3938
+ "loss": 1.2134,
3939
+ "step": 655
3940
+ },
3941
+ {
3942
+ "epoch": 0.92,
3943
+ "learning_rate": 1.4613393745131321e-06,
3944
+ "loss": 1.2548,
3945
+ "step": 656
3946
+ },
3947
+ {
3948
+ "epoch": 0.93,
3949
+ "learning_rate": 1.4069723935596412e-06,
3950
+ "loss": 1.2399,
3951
+ "step": 657
3952
+ },
3953
+ {
3954
+ "epoch": 0.93,
3955
+ "learning_rate": 1.3536215664708586e-06,
3956
+ "loss": 1.242,
3957
+ "step": 658
3958
+ },
3959
+ {
3960
+ "epoch": 0.93,
3961
+ "learning_rate": 1.3012880088934532e-06,
3962
+ "loss": 1.2886,
3963
+ "step": 659
3964
+ },
3965
+ {
3966
+ "epoch": 0.93,
3967
+ "learning_rate": 1.2499728152014334e-06,
3968
+ "loss": 1.2667,
3969
+ "step": 660
3970
+ },
3971
+ {
3972
+ "epoch": 0.93,
3973
+ "learning_rate": 1.1996770584732919e-06,
3974
+ "loss": 1.28,
3975
+ "step": 661
3976
+ },
3977
+ {
3978
+ "epoch": 0.93,
3979
+ "learning_rate": 1.1504017904695296e-06,
3980
+ "loss": 1.2598,
3981
+ "step": 662
3982
+ },
3983
+ {
3984
+ "epoch": 0.93,
3985
+ "learning_rate": 1.1021480416106956e-06,
3986
+ "loss": 1.2444,
3987
+ "step": 663
3988
+ },
3989
+ {
3990
+ "epoch": 0.94,
3991
+ "learning_rate": 1.0549168209558312e-06,
3992
+ "loss": 1.2365,
3993
+ "step": 664
3994
+ },
3995
+ {
3996
+ "epoch": 0.94,
3997
+ "learning_rate": 1.008709116181339e-06,
3998
+ "loss": 1.235,
3999
+ "step": 665
4000
+ },
4001
+ {
4002
+ "epoch": 0.94,
4003
+ "learning_rate": 9.635258935603796e-07,
4004
+ "loss": 1.2456,
4005
+ "step": 666
4006
+ },
4007
+ {
4008
+ "epoch": 0.94,
4009
+ "learning_rate": 9.19368097942619e-07,
4010
+ "loss": 1.2448,
4011
+ "step": 667
4012
+ },
4013
+ {
4014
+ "epoch": 0.94,
4015
+ "learning_rate": 8.762366527345022e-07,
4016
+ "loss": 1.284,
4017
+ "step": 668
4018
+ },
4019
+ {
4020
+ "epoch": 0.94,
4021
+ "learning_rate": 8.341324598799216e-07,
4022
+ "loss": 1.2056,
4023
+ "step": 669
4024
+ },
4025
+ {
4026
+ "epoch": 0.94,
4027
+ "learning_rate": 7.930563998413798e-07,
4028
+ "loss": 1.175,
4029
+ "step": 670
4030
+ },
4031
+ {
4032
+ "epoch": 0.95,
4033
+ "learning_rate": 7.530093315815557e-07,
4034
+ "loss": 1.2085,
4035
+ "step": 671
4036
+ },
4037
+ {
4038
+ "epoch": 0.95,
4039
+ "learning_rate": 7.139920925453347e-07,
4040
+ "loss": 1.2548,
4041
+ "step": 672
4042
+ },
4043
+ {
4044
+ "epoch": 0.95,
4045
+ "learning_rate": 6.760054986423459e-07,
4046
+ "loss": 1.1877,
4047
+ "step": 673
4048
+ },
4049
+ {
4050
+ "epoch": 0.95,
4051
+ "learning_rate": 6.390503442298413e-07,
4052
+ "loss": 1.2495,
4053
+ "step": 674
4054
+ },
4055
+ {
4056
+ "epoch": 0.95,
4057
+ "learning_rate": 6.031274020961152e-07,
4058
+ "loss": 1.2678,
4059
+ "step": 675
4060
+ },
4061
+ {
4062
+ "epoch": 0.95,
4063
+ "learning_rate": 5.682374234443344e-07,
4064
+ "loss": 1.2285,
4065
+ "step": 676
4066
+ },
4067
+ {
4068
+ "epoch": 0.95,
4069
+ "learning_rate": 5.343811378768492e-07,
4070
+ "loss": 1.2401,
4071
+ "step": 677
4072
+ },
4073
+ {
4074
+ "epoch": 0.96,
4075
+ "learning_rate": 5.015592533799074e-07,
4076
+ "loss": 1.1871,
4077
+ "step": 678
4078
+ },
4079
+ {
4080
+ "epoch": 0.96,
4081
+ "learning_rate": 4.6977245630886455e-07,
4082
+ "loss": 1.2252,
4083
+ "step": 679
4084
+ },
4085
+ {
4086
+ "epoch": 0.96,
4087
+ "learning_rate": 4.3902141137382444e-07,
4088
+ "loss": 1.2074,
4089
+ "step": 680
4090
+ },
4091
+ {
4092
+ "epoch": 0.96,
4093
+ "learning_rate": 4.0930676162576063e-07,
4094
+ "loss": 1.2778,
4095
+ "step": 681
4096
+ },
4097
+ {
4098
+ "epoch": 0.96,
4099
+ "learning_rate": 3.8062912844302746e-07,
4100
+ "loss": 1.2601,
4101
+ "step": 682
4102
+ },
4103
+ {
4104
+ "epoch": 0.96,
4105
+ "learning_rate": 3.5298911151841475e-07,
4106
+ "loss": 1.239,
4107
+ "step": 683
4108
+ },
4109
+ {
4110
+ "epoch": 0.96,
4111
+ "learning_rate": 3.263872888465691e-07,
4112
+ "loss": 1.231,
4113
+ "step": 684
4114
+ },
4115
+ {
4116
+ "epoch": 0.97,
4117
+ "learning_rate": 3.0082421671192575e-07,
4118
+ "loss": 1.2737,
4119
+ "step": 685
4120
+ },
4121
+ {
4122
+ "epoch": 0.97,
4123
+ "learning_rate": 2.7630042967707327e-07,
4124
+ "loss": 1.29,
4125
+ "step": 686
4126
+ },
4127
+ {
4128
+ "epoch": 0.97,
4129
+ "learning_rate": 2.5281644057156826e-07,
4130
+ "loss": 1.248,
4131
+ "step": 687
4132
+ },
4133
+ {
4134
+ "epoch": 0.97,
4135
+ "learning_rate": 2.303727404812217e-07,
4136
+ "loss": 1.2008,
4137
+ "step": 688
4138
+ },
4139
+ {
4140
+ "epoch": 0.97,
4141
+ "learning_rate": 2.0896979873782918e-07,
4142
+ "loss": 1.1855,
4143
+ "step": 689
4144
+ },
4145
+ {
4146
+ "epoch": 0.97,
4147
+ "learning_rate": 1.8860806290932897e-07,
4148
+ "loss": 1.1995,
4149
+ "step": 690
4150
+ },
4151
+ {
4152
+ "epoch": 0.97,
4153
+ "learning_rate": 1.692879587904983e-07,
4154
+ "loss": 1.245,
4155
+ "step": 691
4156
+ },
4157
+ {
4158
+ "epoch": 0.98,
4159
+ "learning_rate": 1.5100989039399939e-07,
4160
+ "loss": 1.2523,
4161
+ "step": 692
4162
+ },
4163
+ {
4164
+ "epoch": 0.98,
4165
+ "learning_rate": 1.337742399419306e-07,
4166
+ "loss": 1.2624,
4167
+ "step": 693
4168
+ },
4169
+ {
4170
+ "epoch": 0.98,
4171
+ "learning_rate": 1.1758136785788854e-07,
4172
+ "loss": 1.2609,
4173
+ "step": 694
4174
+ },
4175
+ {
4176
+ "epoch": 0.98,
4177
+ "learning_rate": 1.0243161275936274e-07,
4178
+ "loss": 1.2369,
4179
+ "step": 695
4180
+ },
4181
+ {
4182
+ "epoch": 0.98,
4183
+ "learning_rate": 8.832529145070267e-08,
4184
+ "loss": 1.2945,
4185
+ "step": 696
4186
+ },
4187
+ {
4188
+ "epoch": 0.98,
4189
+ "learning_rate": 7.526269891646176e-08,
4190
+ "loss": 1.2309,
4191
+ "step": 697
4192
+ },
4193
+ {
4194
+ "epoch": 0.98,
4195
+ "learning_rate": 6.324410831525795e-08,
4196
+ "loss": 1.2671,
4197
+ "step": 698
4198
+ },
4199
+ {
4200
+ "epoch": 0.99,
4201
+ "learning_rate": 5.226977097403385e-08,
4202
+ "loss": 1.2309,
4203
+ "step": 699
4204
+ },
4205
+ {
4206
+ "epoch": 0.99,
4207
+ "learning_rate": 4.233991638281642e-08,
4208
+ "loss": 1.1994,
4209
+ "step": 700
4210
+ },
4211
+ {
4212
+ "epoch": 0.99,
4213
+ "learning_rate": 3.3454752189926444e-08,
4214
+ "loss": 1.234,
4215
+ "step": 701
4216
+ },
4217
+ {
4218
+ "epoch": 0.99,
4219
+ "learning_rate": 2.561446419760416e-08,
4220
+ "loss": 1.2064,
4221
+ "step": 702
4222
+ },
4223
+ {
4224
+ "epoch": 0.99,
4225
+ "learning_rate": 1.8819216358156864e-08,
4226
+ "loss": 1.1986,
4227
+ "step": 703
4228
+ },
4229
+ {
4230
+ "epoch": 0.99,
4231
+ "learning_rate": 1.3069150770528282e-08,
4232
+ "loss": 1.2388,
4233
+ "step": 704
4234
+ },
4235
+ {
4236
+ "epoch": 0.99,
4237
+ "learning_rate": 8.364387677295415e-09,
4238
+ "loss": 1.2003,
4239
+ "step": 705
4240
+ },
4241
+ {
4242
+ "epoch": 1.0,
4243
+ "learning_rate": 4.705025462187207e-09,
4244
+ "loss": 1.2338,
4245
+ "step": 706
4246
+ },
4247
+ {
4248
+ "epoch": 1.0,
4249
+ "learning_rate": 2.091140648013967e-09,
4250
+ "loss": 1.264,
4251
+ "step": 707
4252
+ },
4253
+ {
4254
+ "epoch": 1.0,
4255
+ "learning_rate": 5.22787895074206e-10,
4256
+ "loss": 1.2477,
4257
+ "step": 708
4258
+ },
4259
+ {
4260
+ "epoch": 1.0,
4261
+ "learning_rate": 0.0,
4262
+ "loss": 1.208,
4263
+ "step": 709
4264
+ },
4265
+ {
4266
+ "epoch": 1.0,
4267
+ "step": 709,
4268
+ "total_flos": 0.0,
4269
+ "train_loss": 0.7294200115714995,
4270
+ "train_runtime": 11040.3966,
4271
+ "train_samples_per_second": 7.201,
4272
+ "train_steps_per_second": 0.064
4273
+ }
4274
+ ],
4275
+ "logging_steps": 1.0,
4276
+ "max_steps": 709,
4277
+ "num_input_tokens_seen": 0,
4278
+ "num_train_epochs": 1,
4279
+ "save_steps": 100,
4280
+ "total_flos": 0.0,
4281
+ "train_batch_size": 8,
4282
+ "trial_name": null,
4283
+ "trial_params": null
4284
+ }
vision_tower/config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/blob/v-xiyaowang/v-xiyaowang/Video-Self-Rewarding-main/checkpoints/vision_tower",
3
+ "architectures": [
4
+ "SiglipVisionModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "hidden_act": "gelu_pytorch_tanh",
8
+ "hidden_size": 1152,
9
+ "image_size": 384,
10
+ "intermediate_size": 4304,
11
+ "layer_norm_eps": 1e-06,
12
+ "model_type": "siglip_vision_model",
13
+ "num_attention_heads": 16,
14
+ "num_channels": 3,
15
+ "num_hidden_layers": 27,
16
+ "patch_size": 14,
17
+ "torch_dtype": "bfloat16",
18
+ "transformers_version": "4.36.2"
19
+ }
vision_tower/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b226be7791c114dc110669ee9af1c44a38484ab78b62c0a9058555313b500cf8
3
+ size 856506120
vision_tower/preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 3,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 384,
22
+ "width": 384
23
+ }
24
+ }