CodCodingCode commited on
Commit
149da00
·
verified ·
1 Parent(s): 39a8015

Delete checkpoint-2000

Browse files
checkpoint-2000/config.json DELETED
@@ -1,36 +0,0 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
- "eos_token_id": 128001,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 4096,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
- "max_position_embeddings": 131072,
15
- "mlp_bias": false,
16
- "model_type": "llama",
17
- "num_attention_heads": 32,
18
- "num_hidden_layers": 32,
19
- "num_key_value_heads": 8,
20
- "pad_token_id": 128001,
21
- "pretraining_tp": 1,
22
- "rms_norm_eps": 1e-05,
23
- "rope_scaling": {
24
- "factor": 8.0,
25
- "high_freq_factor": 4.0,
26
- "low_freq_factor": 1.0,
27
- "original_max_position_embeddings": 8192,
28
- "rope_type": "llama3"
29
- },
30
- "rope_theta": 500000.0,
31
- "tie_word_embeddings": false,
32
- "torch_dtype": "bfloat16",
33
- "transformers_version": "4.52.3",
34
- "use_cache": true,
35
- "vocab_size": 128256
36
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2000/generation_config.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 128000,
4
- "do_sample": true,
5
- "eos_token_id": 128001,
6
- "temperature": 0.6,
7
- "top_p": 0.9,
8
- "transformers_version": "4.52.3"
9
- }
 
 
 
 
 
 
 
 
 
 
checkpoint-2000/model-00001-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fe435e2c4bbca1269bc627240826023e18e4ad855772002e6a749f30697fb38
3
- size 4976698672
 
 
 
 
checkpoint-2000/model-00002-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:59b68beba1b4e324537a66eaf620ef1a176bbc344d7573b701b8d0702166843c
3
- size 4999802720
 
 
 
 
checkpoint-2000/model-00003-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfc74133728d3e1b75965131e44cbaf44f37cad4c502a69bda22faa6812f3167
3
- size 4915916176
 
 
 
 
checkpoint-2000/model-00004-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b68a26c009f6fb3ef08ffccf8708665772f795b84821421eeddbf7bd03b9307e
3
- size 1168138808
 
 
 
 
checkpoint-2000/model.safetensors.index.json DELETED
@@ -1,298 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 16060522496
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00004-of-00004.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
- "model.norm.weight": "model-00004-of-00004.safetensors"
297
- }
298
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c69047e52bec60fd8a4cb1e0b2b127ff6ec6ebd35f03273c04d8d4e065a0cda1
3
- size 32121300399
 
 
 
 
checkpoint-2000/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
- size 14645
 
 
 
 
checkpoint-2000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:32599b597ad95efbe0342d31cf37c19a12f3cbdfed5318ded837d873f234d1ae
3
- size 1465
 
 
 
 
checkpoint-2000/special_tokens_map.json DELETED
@@ -1,17 +0,0 @@
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": "<|end_of_text|>"
17
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2000/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
 
 
 
checkpoint-2000/tokenizer_config.json DELETED
@@ -1,2063 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "128000": {
4
- "content": "<|begin_of_text|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "128001": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "128002": {
20
- "content": "<|reserved_special_token_0|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "128003": {
28
- "content": "<|reserved_special_token_1|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "128004": {
36
- "content": "<|finetune_right_pad_id|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "128005": {
44
- "content": "<|reserved_special_token_2|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "128006": {
52
- "content": "<|start_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "128007": {
60
- "content": "<|end_header_id|>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "128008": {
68
- "content": "<|eom_id|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "128009": {
76
- "content": "<|eot_id|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "128010": {
84
- "content": "<|python_tag|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "128011": {
92
- "content": "<|reserved_special_token_3|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "128012": {
100
- "content": "<|reserved_special_token_4|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "128013": {
108
- "content": "<|reserved_special_token_5|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_6|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_7|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_8|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_9|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_10|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_11|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_12|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_13|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_14|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_15|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_16|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_17|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_18|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_19|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_20|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_21|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_22|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_23|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_24|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_25|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_26|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_27|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_28|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_29|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_30|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_31|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_32|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_33|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_34|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_35|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_36|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_37|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_38|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_39|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_40|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_41|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_42|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_43|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_44|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_45|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_46|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_47|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_48|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_49|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_50|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_51|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_52|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_53|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_54|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_55|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_56|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_57|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_58|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_59|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_60|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_61|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_62|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_63|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_64|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_65|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_66|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_67|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_68|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_69|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_70|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_71|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_72|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_73|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_74|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_75|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_76|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_77|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_78|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_79|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_80|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_81|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_82|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_83|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_84|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_85|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_86|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_87|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_88|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_89|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_90|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_91|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_92|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_93|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_94|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_95|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_96|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_97|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_98|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_99|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_100|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_101|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_102|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_103|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_104|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_105|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_106|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_107|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_108|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_109|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_110|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_111|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_112|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_113|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_114|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_115|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_116|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_117|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_118|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_119|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_120|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_121|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_122|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_123|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_124|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_125|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_126|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_127|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_128|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_129|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_130|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_131|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_132|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_133|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_134|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_135|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_136|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_137|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_138|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_139|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_140|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_141|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_142|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_143|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_144|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_145|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_146|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_147|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_148|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_149|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_150|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_151|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_152|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_153|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_154|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_155|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_156|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_157|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_158|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_159|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_160|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_161|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_162|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_163|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_164|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_165|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_166|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_167|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_168|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_169|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_170|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_171|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_172|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_173|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_174|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_175|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_176|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_177|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_178|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_179|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_180|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_181|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_182|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_183|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_184|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_185|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_186|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_187|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_188|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_189|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_190|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_191|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_192|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_193|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_194|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_195|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_196|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_197|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_198|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_199|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_200|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_201|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_202|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_203|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_204|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_205|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_206|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_207|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_208|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_209|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_210|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_211|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_212|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_213|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_214|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_215|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_216|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_217|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_218|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_219|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_220|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_221|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_222|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_223|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_224|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_225|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_226|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_227|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_228|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_229|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_230|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_231|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_232|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_233|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_234|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_235|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_236|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_237|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_238|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_239|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_240|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_241|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_242|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_243|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_244|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_245|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_246|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_247|>",
2045
- "lstrip": false,
2046
- "normalized": false,
2047
- "rstrip": false,
2048
- "single_word": false,
2049
- "special": true
2050
- }
2051
- },
2052
- "bos_token": "<|begin_of_text|>",
2053
- "clean_up_tokenization_spaces": true,
2054
- "eos_token": "<|end_of_text|>",
2055
- "extra_special_tokens": {},
2056
- "model_input_names": [
2057
- "input_ids",
2058
- "attention_mask"
2059
- ],
2060
- "model_max_length": 131072,
2061
- "pad_token": "<|end_of_text|>",
2062
- "tokenizer_class": "PreTrainedTokenizer"
2063
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2000/trainer_state.json DELETED
@@ -1,1434 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 1.1481800559982769,
6
- "eval_steps": 500,
7
- "global_step": 2000,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.00574341302318903,
14
- "grad_norm": 3.515625,
15
- "learning_rate": 1.9920000000000002e-05,
16
- "loss": 1.3417,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.01148682604637806,
21
- "grad_norm": 2.609375,
22
- "learning_rate": 1.9831111111111113e-05,
23
- "loss": 0.654,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.01723023906956709,
28
- "grad_norm": 2.171875,
29
- "learning_rate": 1.9742222222222223e-05,
30
- "loss": 0.6043,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.02297365209275612,
35
- "grad_norm": 2.296875,
36
- "learning_rate": 1.9653333333333334e-05,
37
- "loss": 0.5744,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.02871706511594515,
42
- "grad_norm": 1.890625,
43
- "learning_rate": 1.9564444444444444e-05,
44
- "loss": 0.563,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.03446047813913418,
49
- "grad_norm": 2.3125,
50
- "learning_rate": 1.9475555555555558e-05,
51
- "loss": 0.5506,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.04020389116232321,
56
- "grad_norm": 1.984375,
57
- "learning_rate": 1.938666666666667e-05,
58
- "loss": 0.563,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.04594730418551224,
63
- "grad_norm": 2.125,
64
- "learning_rate": 1.929777777777778e-05,
65
- "loss": 0.561,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.05169071720870127,
70
- "grad_norm": 1.9765625,
71
- "learning_rate": 1.920888888888889e-05,
72
- "loss": 0.5288,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.0574341302318903,
77
- "grad_norm": 2.109375,
78
- "learning_rate": 1.912e-05,
79
- "loss": 0.5693,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.06317754325507934,
84
- "grad_norm": 2.21875,
85
- "learning_rate": 1.9031111111111114e-05,
86
- "loss": 0.5353,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 0.06892095627826836,
91
- "grad_norm": 1.9140625,
92
- "learning_rate": 1.8942222222222224e-05,
93
- "loss": 0.5383,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 0.0746643693014574,
98
- "grad_norm": 2.40625,
99
- "learning_rate": 1.8853333333333335e-05,
100
- "loss": 0.4849,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 0.08040778232464642,
105
- "grad_norm": 1.8671875,
106
- "learning_rate": 1.8764444444444445e-05,
107
- "loss": 0.5155,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 0.08615119534783545,
112
- "grad_norm": 2.265625,
113
- "learning_rate": 1.867555555555556e-05,
114
- "loss": 0.5071,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 0.09189460837102448,
119
- "grad_norm": 2.03125,
120
- "learning_rate": 1.858666666666667e-05,
121
- "loss": 0.5065,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 0.09763802139421351,
126
- "grad_norm": 1.84375,
127
- "learning_rate": 1.849777777777778e-05,
128
- "loss": 0.509,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 0.10338143441740254,
133
- "grad_norm": 1.703125,
134
- "learning_rate": 1.840888888888889e-05,
135
- "loss": 0.5076,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 0.10912484744059157,
140
- "grad_norm": 2.0,
141
- "learning_rate": 1.832e-05,
142
- "loss": 0.4804,
143
- "step": 190
144
- },
145
- {
146
- "epoch": 0.1148682604637806,
147
- "grad_norm": 1.8828125,
148
- "learning_rate": 1.823111111111111e-05,
149
- "loss": 0.4584,
150
- "step": 200
151
- },
152
- {
153
- "epoch": 0.12061167348696963,
154
- "grad_norm": 1.8046875,
155
- "learning_rate": 1.814222222222222e-05,
156
- "loss": 0.4951,
157
- "step": 210
158
- },
159
- {
160
- "epoch": 0.12635508651015867,
161
- "grad_norm": 1.7265625,
162
- "learning_rate": 1.8053333333333332e-05,
163
- "loss": 0.4758,
164
- "step": 220
165
- },
166
- {
167
- "epoch": 0.13209849953334768,
168
- "grad_norm": 2.1875,
169
- "learning_rate": 1.7964444444444446e-05,
170
- "loss": 0.5146,
171
- "step": 230
172
- },
173
- {
174
- "epoch": 0.13784191255653672,
175
- "grad_norm": 2.140625,
176
- "learning_rate": 1.7875555555555556e-05,
177
- "loss": 0.5004,
178
- "step": 240
179
- },
180
- {
181
- "epoch": 0.14358532557972575,
182
- "grad_norm": 2.234375,
183
- "learning_rate": 1.7786666666666667e-05,
184
- "loss": 0.4744,
185
- "step": 250
186
- },
187
- {
188
- "epoch": 0.1493287386029148,
189
- "grad_norm": 2.078125,
190
- "learning_rate": 1.7697777777777777e-05,
191
- "loss": 0.4943,
192
- "step": 260
193
- },
194
- {
195
- "epoch": 0.1550721516261038,
196
- "grad_norm": 2.046875,
197
- "learning_rate": 1.760888888888889e-05,
198
- "loss": 0.4751,
199
- "step": 270
200
- },
201
- {
202
- "epoch": 0.16081556464929284,
203
- "grad_norm": 2.09375,
204
- "learning_rate": 1.752e-05,
205
- "loss": 0.4599,
206
- "step": 280
207
- },
208
- {
209
- "epoch": 0.16655897767248187,
210
- "grad_norm": 1.8984375,
211
- "learning_rate": 1.7431111111111112e-05,
212
- "loss": 0.4656,
213
- "step": 290
214
- },
215
- {
216
- "epoch": 0.1723023906956709,
217
- "grad_norm": 1.9609375,
218
- "learning_rate": 1.7342222222222226e-05,
219
- "loss": 0.4242,
220
- "step": 300
221
- },
222
- {
223
- "epoch": 0.17804580371885995,
224
- "grad_norm": 2.0625,
225
- "learning_rate": 1.7253333333333336e-05,
226
- "loss": 0.4804,
227
- "step": 310
228
- },
229
- {
230
- "epoch": 0.18378921674204896,
231
- "grad_norm": 1.8046875,
232
- "learning_rate": 1.7164444444444447e-05,
233
- "loss": 0.4736,
234
- "step": 320
235
- },
236
- {
237
- "epoch": 0.189532629765238,
238
- "grad_norm": 2.0625,
239
- "learning_rate": 1.7075555555555557e-05,
240
- "loss": 0.4317,
241
- "step": 330
242
- },
243
- {
244
- "epoch": 0.19527604278842703,
245
- "grad_norm": 2.46875,
246
- "learning_rate": 1.6986666666666668e-05,
247
- "loss": 0.4752,
248
- "step": 340
249
- },
250
- {
251
- "epoch": 0.20101945581161607,
252
- "grad_norm": 1.8359375,
253
- "learning_rate": 1.6897777777777778e-05,
254
- "loss": 0.3932,
255
- "step": 350
256
- },
257
- {
258
- "epoch": 0.20676286883480507,
259
- "grad_norm": 2.109375,
260
- "learning_rate": 1.680888888888889e-05,
261
- "loss": 0.4742,
262
- "step": 360
263
- },
264
- {
265
- "epoch": 0.2125062818579941,
266
- "grad_norm": 2.34375,
267
- "learning_rate": 1.672e-05,
268
- "loss": 0.4542,
269
- "step": 370
270
- },
271
- {
272
- "epoch": 0.21824969488118315,
273
- "grad_norm": 1.9140625,
274
- "learning_rate": 1.6631111111111113e-05,
275
- "loss": 0.4284,
276
- "step": 380
277
- },
278
- {
279
- "epoch": 0.22399310790437219,
280
- "grad_norm": 1.90625,
281
- "learning_rate": 1.6542222222222223e-05,
282
- "loss": 0.4232,
283
- "step": 390
284
- },
285
- {
286
- "epoch": 0.2297365209275612,
287
- "grad_norm": 1.890625,
288
- "learning_rate": 1.6453333333333334e-05,
289
- "loss": 0.4299,
290
- "step": 400
291
- },
292
- {
293
- "epoch": 0.23547993395075023,
294
- "grad_norm": 2.375,
295
- "learning_rate": 1.6364444444444444e-05,
296
- "loss": 0.4246,
297
- "step": 410
298
- },
299
- {
300
- "epoch": 0.24122334697393927,
301
- "grad_norm": 2.015625,
302
- "learning_rate": 1.6275555555555558e-05,
303
- "loss": 0.4215,
304
- "step": 420
305
- },
306
- {
307
- "epoch": 0.2469667599971283,
308
- "grad_norm": 1.9375,
309
- "learning_rate": 1.618666666666667e-05,
310
- "loss": 0.4398,
311
- "step": 430
312
- },
313
- {
314
- "epoch": 0.25271017302031734,
315
- "grad_norm": 2.1875,
316
- "learning_rate": 1.609777777777778e-05,
317
- "loss": 0.4319,
318
- "step": 440
319
- },
320
- {
321
- "epoch": 0.2584535860435064,
322
- "grad_norm": 2.109375,
323
- "learning_rate": 1.600888888888889e-05,
324
- "loss": 0.4227,
325
- "step": 450
326
- },
327
- {
328
- "epoch": 0.26419699906669536,
329
- "grad_norm": 2.390625,
330
- "learning_rate": 1.5920000000000003e-05,
331
- "loss": 0.431,
332
- "step": 460
333
- },
334
- {
335
- "epoch": 0.2699404120898844,
336
- "grad_norm": 2.421875,
337
- "learning_rate": 1.5831111111111114e-05,
338
- "loss": 0.4323,
339
- "step": 470
340
- },
341
- {
342
- "epoch": 0.27568382511307343,
343
- "grad_norm": 2.15625,
344
- "learning_rate": 1.5742222222222224e-05,
345
- "loss": 0.4417,
346
- "step": 480
347
- },
348
- {
349
- "epoch": 0.28142723813626247,
350
- "grad_norm": 1.8984375,
351
- "learning_rate": 1.5653333333333335e-05,
352
- "loss": 0.3823,
353
- "step": 490
354
- },
355
- {
356
- "epoch": 0.2871706511594515,
357
- "grad_norm": 1.9140625,
358
- "learning_rate": 1.5564444444444445e-05,
359
- "loss": 0.394,
360
- "step": 500
361
- },
362
- {
363
- "epoch": 0.29291406418264054,
364
- "grad_norm": 2.171875,
365
- "learning_rate": 1.5475555555555556e-05,
366
- "loss": 0.4017,
367
- "step": 510
368
- },
369
- {
370
- "epoch": 0.2986574772058296,
371
- "grad_norm": 2.4375,
372
- "learning_rate": 1.5386666666666666e-05,
373
- "loss": 0.4121,
374
- "step": 520
375
- },
376
- {
377
- "epoch": 0.3044008902290186,
378
- "grad_norm": 2.078125,
379
- "learning_rate": 1.5297777777777777e-05,
380
- "loss": 0.3843,
381
- "step": 530
382
- },
383
- {
384
- "epoch": 0.3101443032522076,
385
- "grad_norm": 2.34375,
386
- "learning_rate": 1.520888888888889e-05,
387
- "loss": 0.4395,
388
- "step": 540
389
- },
390
- {
391
- "epoch": 0.31588771627539664,
392
- "grad_norm": 2.25,
393
- "learning_rate": 1.5120000000000001e-05,
394
- "loss": 0.3883,
395
- "step": 550
396
- },
397
- {
398
- "epoch": 0.32163112929858567,
399
- "grad_norm": 1.6171875,
400
- "learning_rate": 1.5031111111111111e-05,
401
- "loss": 0.4089,
402
- "step": 560
403
- },
404
- {
405
- "epoch": 0.3273745423217747,
406
- "grad_norm": 1.734375,
407
- "learning_rate": 1.4942222222222222e-05,
408
- "loss": 0.3895,
409
- "step": 570
410
- },
411
- {
412
- "epoch": 0.33311795534496375,
413
- "grad_norm": 1.9453125,
414
- "learning_rate": 1.4853333333333336e-05,
415
- "loss": 0.4084,
416
- "step": 580
417
- },
418
- {
419
- "epoch": 0.3388613683681528,
420
- "grad_norm": 2.171875,
421
- "learning_rate": 1.4764444444444446e-05,
422
- "loss": 0.4083,
423
- "step": 590
424
- },
425
- {
426
- "epoch": 0.3446047813913418,
427
- "grad_norm": 2.109375,
428
- "learning_rate": 1.4675555555555557e-05,
429
- "loss": 0.4037,
430
- "step": 600
431
- },
432
- {
433
- "epoch": 0.35034819441453086,
434
- "grad_norm": 2.53125,
435
- "learning_rate": 1.4586666666666667e-05,
436
- "loss": 0.3538,
437
- "step": 610
438
- },
439
- {
440
- "epoch": 0.3560916074377199,
441
- "grad_norm": 2.015625,
442
- "learning_rate": 1.449777777777778e-05,
443
- "loss": 0.3661,
444
- "step": 620
445
- },
446
- {
447
- "epoch": 0.3618350204609089,
448
- "grad_norm": 1.984375,
449
- "learning_rate": 1.440888888888889e-05,
450
- "loss": 0.3992,
451
- "step": 630
452
- },
453
- {
454
- "epoch": 0.3675784334840979,
455
- "grad_norm": 2.328125,
456
- "learning_rate": 1.432e-05,
457
- "loss": 0.3721,
458
- "step": 640
459
- },
460
- {
461
- "epoch": 0.37332184650728695,
462
- "grad_norm": 2.453125,
463
- "learning_rate": 1.4231111111111114e-05,
464
- "loss": 0.4009,
465
- "step": 650
466
- },
467
- {
468
- "epoch": 0.379065259530476,
469
- "grad_norm": 2.25,
470
- "learning_rate": 1.4142222222222224e-05,
471
- "loss": 0.401,
472
- "step": 660
473
- },
474
- {
475
- "epoch": 0.384808672553665,
476
- "grad_norm": 2.46875,
477
- "learning_rate": 1.4053333333333335e-05,
478
- "loss": 0.3783,
479
- "step": 670
480
- },
481
- {
482
- "epoch": 0.39055208557685406,
483
- "grad_norm": 2.234375,
484
- "learning_rate": 1.3964444444444445e-05,
485
- "loss": 0.4021,
486
- "step": 680
487
- },
488
- {
489
- "epoch": 0.3962954986000431,
490
- "grad_norm": 2.15625,
491
- "learning_rate": 1.3875555555555557e-05,
492
- "loss": 0.3713,
493
- "step": 690
494
- },
495
- {
496
- "epoch": 0.40203891162323213,
497
- "grad_norm": 2.125,
498
- "learning_rate": 1.3786666666666668e-05,
499
- "loss": 0.4036,
500
- "step": 700
501
- },
502
- {
503
- "epoch": 0.4077823246464211,
504
- "grad_norm": 2.03125,
505
- "learning_rate": 1.3697777777777778e-05,
506
- "loss": 0.368,
507
- "step": 710
508
- },
509
- {
510
- "epoch": 0.41352573766961015,
511
- "grad_norm": 2.5625,
512
- "learning_rate": 1.3608888888888889e-05,
513
- "loss": 0.3578,
514
- "step": 720
515
- },
516
- {
517
- "epoch": 0.4192691506927992,
518
- "grad_norm": 2.390625,
519
- "learning_rate": 1.3520000000000003e-05,
520
- "loss": 0.3731,
521
- "step": 730
522
- },
523
- {
524
- "epoch": 0.4250125637159882,
525
- "grad_norm": 2.5,
526
- "learning_rate": 1.3431111111111113e-05,
527
- "loss": 0.3817,
528
- "step": 740
529
- },
530
- {
531
- "epoch": 0.43075597673917726,
532
- "grad_norm": 2.515625,
533
- "learning_rate": 1.3342222222222224e-05,
534
- "loss": 0.3717,
535
- "step": 750
536
- },
537
- {
538
- "epoch": 0.4364993897623663,
539
- "grad_norm": 2.203125,
540
- "learning_rate": 1.3253333333333334e-05,
541
- "loss": 0.3629,
542
- "step": 760
543
- },
544
- {
545
- "epoch": 0.44224280278555533,
546
- "grad_norm": 2.625,
547
- "learning_rate": 1.3164444444444446e-05,
548
- "loss": 0.3698,
549
- "step": 770
550
- },
551
- {
552
- "epoch": 0.44798621580874437,
553
- "grad_norm": 2.0,
554
- "learning_rate": 1.3075555555555557e-05,
555
- "loss": 0.3661,
556
- "step": 780
557
- },
558
- {
559
- "epoch": 0.45372962883193335,
560
- "grad_norm": 2.5,
561
- "learning_rate": 1.2986666666666667e-05,
562
- "loss": 0.342,
563
- "step": 790
564
- },
565
- {
566
- "epoch": 0.4594730418551224,
567
- "grad_norm": 2.046875,
568
- "learning_rate": 1.2897777777777778e-05,
569
- "loss": 0.3862,
570
- "step": 800
571
- },
572
- {
573
- "epoch": 0.4652164548783114,
574
- "grad_norm": 2.40625,
575
- "learning_rate": 1.2808888888888891e-05,
576
- "loss": 0.3436,
577
- "step": 810
578
- },
579
- {
580
- "epoch": 0.47095986790150046,
581
- "grad_norm": 2.3125,
582
- "learning_rate": 1.2720000000000002e-05,
583
- "loss": 0.3374,
584
- "step": 820
585
- },
586
- {
587
- "epoch": 0.4767032809246895,
588
- "grad_norm": 2.15625,
589
- "learning_rate": 1.2631111111111112e-05,
590
- "loss": 0.3648,
591
- "step": 830
592
- },
593
- {
594
- "epoch": 0.48244669394787854,
595
- "grad_norm": 2.25,
596
- "learning_rate": 1.2542222222222223e-05,
597
- "loss": 0.327,
598
- "step": 840
599
- },
600
- {
601
- "epoch": 0.48819010697106757,
602
- "grad_norm": 2.3125,
603
- "learning_rate": 1.2453333333333335e-05,
604
- "loss": 0.3406,
605
- "step": 850
606
- },
607
- {
608
- "epoch": 0.4939335199942566,
609
- "grad_norm": 2.03125,
610
- "learning_rate": 1.2364444444444445e-05,
611
- "loss": 0.3441,
612
- "step": 860
613
- },
614
- {
615
- "epoch": 0.4996769330174456,
616
- "grad_norm": 2.609375,
617
- "learning_rate": 1.2275555555555556e-05,
618
- "loss": 0.3695,
619
- "step": 870
620
- },
621
- {
622
- "epoch": 0.5054203460406347,
623
- "grad_norm": 2.359375,
624
- "learning_rate": 1.2186666666666666e-05,
625
- "loss": 0.3386,
626
- "step": 880
627
- },
628
- {
629
- "epoch": 0.5111637590638237,
630
- "grad_norm": 2.328125,
631
- "learning_rate": 1.209777777777778e-05,
632
- "loss": 0.3478,
633
- "step": 890
634
- },
635
- {
636
- "epoch": 0.5169071720870128,
637
- "grad_norm": 2.078125,
638
- "learning_rate": 1.200888888888889e-05,
639
- "loss": 0.3274,
640
- "step": 900
641
- },
642
- {
643
- "epoch": 0.5226505851102017,
644
- "grad_norm": 2.3125,
645
- "learning_rate": 1.1920000000000001e-05,
646
- "loss": 0.3381,
647
- "step": 910
648
- },
649
- {
650
- "epoch": 0.5283939981333907,
651
- "grad_norm": 2.359375,
652
- "learning_rate": 1.1831111111111112e-05,
653
- "loss": 0.3438,
654
- "step": 920
655
- },
656
- {
657
- "epoch": 0.5341374111565798,
658
- "grad_norm": 2.390625,
659
- "learning_rate": 1.1742222222222224e-05,
660
- "loss": 0.3655,
661
- "step": 930
662
- },
663
- {
664
- "epoch": 0.5398808241797688,
665
- "grad_norm": 2.203125,
666
- "learning_rate": 1.1653333333333334e-05,
667
- "loss": 0.3219,
668
- "step": 940
669
- },
670
- {
671
- "epoch": 0.5456242372029578,
672
- "grad_norm": 2.453125,
673
- "learning_rate": 1.1564444444444445e-05,
674
- "loss": 0.3286,
675
- "step": 950
676
- },
677
- {
678
- "epoch": 0.5513676502261469,
679
- "grad_norm": 2.34375,
680
- "learning_rate": 1.1475555555555557e-05,
681
- "loss": 0.3547,
682
- "step": 960
683
- },
684
- {
685
- "epoch": 0.5571110632493359,
686
- "grad_norm": 2.578125,
687
- "learning_rate": 1.1386666666666669e-05,
688
- "loss": 0.3325,
689
- "step": 970
690
- },
691
- {
692
- "epoch": 0.5628544762725249,
693
- "grad_norm": 2.375,
694
- "learning_rate": 1.129777777777778e-05,
695
- "loss": 0.3711,
696
- "step": 980
697
- },
698
- {
699
- "epoch": 0.568597889295714,
700
- "grad_norm": 2.234375,
701
- "learning_rate": 1.120888888888889e-05,
702
- "loss": 0.3124,
703
- "step": 990
704
- },
705
- {
706
- "epoch": 0.574341302318903,
707
- "grad_norm": 2.234375,
708
- "learning_rate": 1.1120000000000002e-05,
709
- "loss": 0.3289,
710
- "step": 1000
711
- },
712
- {
713
- "epoch": 0.580084715342092,
714
- "grad_norm": 2.234375,
715
- "learning_rate": 1.1031111111111112e-05,
716
- "loss": 0.3218,
717
- "step": 1010
718
- },
719
- {
720
- "epoch": 0.5858281283652811,
721
- "grad_norm": 2.515625,
722
- "learning_rate": 1.0942222222222223e-05,
723
- "loss": 0.3503,
724
- "step": 1020
725
- },
726
- {
727
- "epoch": 0.5915715413884701,
728
- "grad_norm": 2.328125,
729
- "learning_rate": 1.0853333333333333e-05,
730
- "loss": 0.3551,
731
- "step": 1030
732
- },
733
- {
734
- "epoch": 0.5973149544116592,
735
- "grad_norm": 2.453125,
736
- "learning_rate": 1.0764444444444445e-05,
737
- "loss": 0.3194,
738
- "step": 1040
739
- },
740
- {
741
- "epoch": 0.6030583674348482,
742
- "grad_norm": 2.1875,
743
- "learning_rate": 1.0675555555555558e-05,
744
- "loss": 0.3478,
745
- "step": 1050
746
- },
747
- {
748
- "epoch": 0.6088017804580372,
749
- "grad_norm": 2.265625,
750
- "learning_rate": 1.0586666666666668e-05,
751
- "loss": 0.3202,
752
- "step": 1060
753
- },
754
- {
755
- "epoch": 0.6145451934812263,
756
- "grad_norm": 1.9140625,
757
- "learning_rate": 1.0497777777777779e-05,
758
- "loss": 0.3095,
759
- "step": 1070
760
- },
761
- {
762
- "epoch": 0.6202886065044152,
763
- "grad_norm": 2.71875,
764
- "learning_rate": 1.040888888888889e-05,
765
- "loss": 0.3112,
766
- "step": 1080
767
- },
768
- {
769
- "epoch": 0.6260320195276042,
770
- "grad_norm": 2.359375,
771
- "learning_rate": 1.0320000000000001e-05,
772
- "loss": 0.3115,
773
- "step": 1090
774
- },
775
- {
776
- "epoch": 0.6317754325507933,
777
- "grad_norm": 2.296875,
778
- "learning_rate": 1.0231111111111112e-05,
779
- "loss": 0.3296,
780
- "step": 1100
781
- },
782
- {
783
- "epoch": 0.6375188455739823,
784
- "grad_norm": 2.703125,
785
- "learning_rate": 1.0142222222222222e-05,
786
- "loss": 0.279,
787
- "step": 1110
788
- },
789
- {
790
- "epoch": 0.6432622585971713,
791
- "grad_norm": 2.71875,
792
- "learning_rate": 1.0053333333333334e-05,
793
- "loss": 0.3153,
794
- "step": 1120
795
- },
796
- {
797
- "epoch": 0.6490056716203604,
798
- "grad_norm": 1.953125,
799
- "learning_rate": 9.964444444444445e-06,
800
- "loss": 0.3039,
801
- "step": 1130
802
- },
803
- {
804
- "epoch": 0.6547490846435494,
805
- "grad_norm": 2.140625,
806
- "learning_rate": 9.875555555555557e-06,
807
- "loss": 0.3238,
808
- "step": 1140
809
- },
810
- {
811
- "epoch": 0.6604924976667385,
812
- "grad_norm": 2.25,
813
- "learning_rate": 9.786666666666667e-06,
814
- "loss": 0.3143,
815
- "step": 1150
816
- },
817
- {
818
- "epoch": 0.6662359106899275,
819
- "grad_norm": 2.546875,
820
- "learning_rate": 9.697777777777778e-06,
821
- "loss": 0.3145,
822
- "step": 1160
823
- },
824
- {
825
- "epoch": 0.6719793237131165,
826
- "grad_norm": 2.15625,
827
- "learning_rate": 9.60888888888889e-06,
828
- "loss": 0.3034,
829
- "step": 1170
830
- },
831
- {
832
- "epoch": 0.6777227367363056,
833
- "grad_norm": 3.875,
834
- "learning_rate": 9.52e-06,
835
- "loss": 0.2813,
836
- "step": 1180
837
- },
838
- {
839
- "epoch": 0.6834661497594946,
840
- "grad_norm": 2.046875,
841
- "learning_rate": 9.431111111111112e-06,
842
- "loss": 0.3211,
843
- "step": 1190
844
- },
845
- {
846
- "epoch": 0.6892095627826836,
847
- "grad_norm": 2.515625,
848
- "learning_rate": 9.342222222222223e-06,
849
- "loss": 0.2954,
850
- "step": 1200
851
- },
852
- {
853
- "epoch": 0.6949529758058727,
854
- "grad_norm": 2.34375,
855
- "learning_rate": 9.253333333333333e-06,
856
- "loss": 0.2969,
857
- "step": 1210
858
- },
859
- {
860
- "epoch": 0.7006963888290617,
861
- "grad_norm": 2.171875,
862
- "learning_rate": 9.164444444444446e-06,
863
- "loss": 0.2942,
864
- "step": 1220
865
- },
866
- {
867
- "epoch": 0.7064398018522507,
868
- "grad_norm": 2.0,
869
- "learning_rate": 9.075555555555556e-06,
870
- "loss": 0.321,
871
- "step": 1230
872
- },
873
- {
874
- "epoch": 0.7121832148754398,
875
- "grad_norm": 2.171875,
876
- "learning_rate": 8.986666666666666e-06,
877
- "loss": 0.2949,
878
- "step": 1240
879
- },
880
- {
881
- "epoch": 0.7179266278986287,
882
- "grad_norm": 2.609375,
883
- "learning_rate": 8.897777777777779e-06,
884
- "loss": 0.3111,
885
- "step": 1250
886
- },
887
- {
888
- "epoch": 0.7236700409218177,
889
- "grad_norm": 2.234375,
890
- "learning_rate": 8.80888888888889e-06,
891
- "loss": 0.3199,
892
- "step": 1260
893
- },
894
- {
895
- "epoch": 0.7294134539450068,
896
- "grad_norm": 3.171875,
897
- "learning_rate": 8.720000000000001e-06,
898
- "loss": 0.3239,
899
- "step": 1270
900
- },
901
- {
902
- "epoch": 0.7351568669681958,
903
- "grad_norm": 2.640625,
904
- "learning_rate": 8.631111111111112e-06,
905
- "loss": 0.3203,
906
- "step": 1280
907
- },
908
- {
909
- "epoch": 0.7409002799913849,
910
- "grad_norm": 2.3125,
911
- "learning_rate": 8.542222222222222e-06,
912
- "loss": 0.3071,
913
- "step": 1290
914
- },
915
- {
916
- "epoch": 0.7466436930145739,
917
- "grad_norm": 2.328125,
918
- "learning_rate": 8.453333333333334e-06,
919
- "loss": 0.3296,
920
- "step": 1300
921
- },
922
- {
923
- "epoch": 0.7523871060377629,
924
- "grad_norm": 2.296875,
925
- "learning_rate": 8.364444444444445e-06,
926
- "loss": 0.2994,
927
- "step": 1310
928
- },
929
- {
930
- "epoch": 0.758130519060952,
931
- "grad_norm": 2.390625,
932
- "learning_rate": 8.275555555555557e-06,
933
- "loss": 0.2661,
934
- "step": 1320
935
- },
936
- {
937
- "epoch": 0.763873932084141,
938
- "grad_norm": 2.34375,
939
- "learning_rate": 8.186666666666667e-06,
940
- "loss": 0.3194,
941
- "step": 1330
942
- },
943
- {
944
- "epoch": 0.76961734510733,
945
- "grad_norm": 2.28125,
946
- "learning_rate": 8.09777777777778e-06,
947
- "loss": 0.283,
948
- "step": 1340
949
- },
950
- {
951
- "epoch": 0.7753607581305191,
952
- "grad_norm": 2.734375,
953
- "learning_rate": 8.00888888888889e-06,
954
- "loss": 0.3358,
955
- "step": 1350
956
- },
957
- {
958
- "epoch": 0.7811041711537081,
959
- "grad_norm": 2.53125,
960
- "learning_rate": 7.92e-06,
961
- "loss": 0.3041,
962
- "step": 1360
963
- },
964
- {
965
- "epoch": 0.7868475841768972,
966
- "grad_norm": 2.671875,
967
- "learning_rate": 7.831111111111111e-06,
968
- "loss": 0.2701,
969
- "step": 1370
970
- },
971
- {
972
- "epoch": 0.7925909972000862,
973
- "grad_norm": 2.53125,
974
- "learning_rate": 7.742222222222223e-06,
975
- "loss": 0.2783,
976
- "step": 1380
977
- },
978
- {
979
- "epoch": 0.7983344102232752,
980
- "grad_norm": 2.296875,
981
- "learning_rate": 7.653333333333333e-06,
982
- "loss": 0.2989,
983
- "step": 1390
984
- },
985
- {
986
- "epoch": 0.8040778232464643,
987
- "grad_norm": 3.09375,
988
- "learning_rate": 7.564444444444446e-06,
989
- "loss": 0.2711,
990
- "step": 1400
991
- },
992
- {
993
- "epoch": 0.8098212362696532,
994
- "grad_norm": 2.21875,
995
- "learning_rate": 7.475555555555556e-06,
996
- "loss": 0.29,
997
- "step": 1410
998
- },
999
- {
1000
- "epoch": 0.8155646492928422,
1001
- "grad_norm": 2.359375,
1002
- "learning_rate": 7.386666666666667e-06,
1003
- "loss": 0.3208,
1004
- "step": 1420
1005
- },
1006
- {
1007
- "epoch": 0.8213080623160313,
1008
- "grad_norm": 2.21875,
1009
- "learning_rate": 7.297777777777778e-06,
1010
- "loss": 0.2838,
1011
- "step": 1430
1012
- },
1013
- {
1014
- "epoch": 0.8270514753392203,
1015
- "grad_norm": 2.828125,
1016
- "learning_rate": 7.20888888888889e-06,
1017
- "loss": 0.3104,
1018
- "step": 1440
1019
- },
1020
- {
1021
- "epoch": 0.8327948883624093,
1022
- "grad_norm": 2.3125,
1023
- "learning_rate": 7.1200000000000004e-06,
1024
- "loss": 0.2805,
1025
- "step": 1450
1026
- },
1027
- {
1028
- "epoch": 0.8385383013855984,
1029
- "grad_norm": 1.71875,
1030
- "learning_rate": 7.031111111111112e-06,
1031
- "loss": 0.2542,
1032
- "step": 1460
1033
- },
1034
- {
1035
- "epoch": 0.8442817144087874,
1036
- "grad_norm": 2.1875,
1037
- "learning_rate": 6.942222222222222e-06,
1038
- "loss": 0.2698,
1039
- "step": 1470
1040
- },
1041
- {
1042
- "epoch": 0.8500251274319764,
1043
- "grad_norm": 2.671875,
1044
- "learning_rate": 6.853333333333334e-06,
1045
- "loss": 0.2938,
1046
- "step": 1480
1047
- },
1048
- {
1049
- "epoch": 0.8557685404551655,
1050
- "grad_norm": 2.484375,
1051
- "learning_rate": 6.764444444444445e-06,
1052
- "loss": 0.2657,
1053
- "step": 1490
1054
- },
1055
- {
1056
- "epoch": 0.8615119534783545,
1057
- "grad_norm": 2.125,
1058
- "learning_rate": 6.675555555555556e-06,
1059
- "loss": 0.3194,
1060
- "step": 1500
1061
- },
1062
- {
1063
- "epoch": 0.8672553665015436,
1064
- "grad_norm": 3.0,
1065
- "learning_rate": 6.5866666666666666e-06,
1066
- "loss": 0.2863,
1067
- "step": 1510
1068
- },
1069
- {
1070
- "epoch": 0.8729987795247326,
1071
- "grad_norm": 2.640625,
1072
- "learning_rate": 6.497777777777779e-06,
1073
- "loss": 0.2636,
1074
- "step": 1520
1075
- },
1076
- {
1077
- "epoch": 0.8787421925479216,
1078
- "grad_norm": 2.1875,
1079
- "learning_rate": 6.408888888888889e-06,
1080
- "loss": 0.2537,
1081
- "step": 1530
1082
- },
1083
- {
1084
- "epoch": 0.8844856055711107,
1085
- "grad_norm": 2.265625,
1086
- "learning_rate": 6.3200000000000005e-06,
1087
- "loss": 0.2915,
1088
- "step": 1540
1089
- },
1090
- {
1091
- "epoch": 0.8902290185942997,
1092
- "grad_norm": 2.53125,
1093
- "learning_rate": 6.231111111111111e-06,
1094
- "loss": 0.2814,
1095
- "step": 1550
1096
- },
1097
- {
1098
- "epoch": 0.8959724316174887,
1099
- "grad_norm": 2.421875,
1100
- "learning_rate": 6.142222222222223e-06,
1101
- "loss": 0.2508,
1102
- "step": 1560
1103
- },
1104
- {
1105
- "epoch": 0.9017158446406778,
1106
- "grad_norm": 1.8984375,
1107
- "learning_rate": 6.0533333333333335e-06,
1108
- "loss": 0.2499,
1109
- "step": 1570
1110
- },
1111
- {
1112
- "epoch": 0.9074592576638667,
1113
- "grad_norm": 3.515625,
1114
- "learning_rate": 5.964444444444445e-06,
1115
- "loss": 0.2779,
1116
- "step": 1580
1117
- },
1118
- {
1119
- "epoch": 0.9132026706870557,
1120
- "grad_norm": 2.09375,
1121
- "learning_rate": 5.875555555555556e-06,
1122
- "loss": 0.2703,
1123
- "step": 1590
1124
- },
1125
- {
1126
- "epoch": 0.9189460837102448,
1127
- "grad_norm": 2.515625,
1128
- "learning_rate": 5.7866666666666674e-06,
1129
- "loss": 0.2851,
1130
- "step": 1600
1131
- },
1132
- {
1133
- "epoch": 0.9246894967334338,
1134
- "grad_norm": 2.53125,
1135
- "learning_rate": 5.697777777777779e-06,
1136
- "loss": 0.2771,
1137
- "step": 1610
1138
- },
1139
- {
1140
- "epoch": 0.9304329097566229,
1141
- "grad_norm": 2.515625,
1142
- "learning_rate": 5.608888888888889e-06,
1143
- "loss": 0.2545,
1144
- "step": 1620
1145
- },
1146
- {
1147
- "epoch": 0.9361763227798119,
1148
- "grad_norm": 2.171875,
1149
- "learning_rate": 5.5200000000000005e-06,
1150
- "loss": 0.2534,
1151
- "step": 1630
1152
- },
1153
- {
1154
- "epoch": 0.9419197358030009,
1155
- "grad_norm": 2.65625,
1156
- "learning_rate": 5.431111111111112e-06,
1157
- "loss": 0.2851,
1158
- "step": 1640
1159
- },
1160
- {
1161
- "epoch": 0.94766314882619,
1162
- "grad_norm": 2.109375,
1163
- "learning_rate": 5.342222222222223e-06,
1164
- "loss": 0.3072,
1165
- "step": 1650
1166
- },
1167
- {
1168
- "epoch": 0.953406561849379,
1169
- "grad_norm": 2.171875,
1170
- "learning_rate": 5.2533333333333336e-06,
1171
- "loss": 0.2709,
1172
- "step": 1660
1173
- },
1174
- {
1175
- "epoch": 0.959149974872568,
1176
- "grad_norm": 2.359375,
1177
- "learning_rate": 5.164444444444445e-06,
1178
- "loss": 0.2876,
1179
- "step": 1670
1180
- },
1181
- {
1182
- "epoch": 0.9648933878957571,
1183
- "grad_norm": 2.015625,
1184
- "learning_rate": 5.075555555555556e-06,
1185
- "loss": 0.2824,
1186
- "step": 1680
1187
- },
1188
- {
1189
- "epoch": 0.9706368009189461,
1190
- "grad_norm": 2.515625,
1191
- "learning_rate": 4.986666666666667e-06,
1192
- "loss": 0.2867,
1193
- "step": 1690
1194
- },
1195
- {
1196
- "epoch": 0.9763802139421351,
1197
- "grad_norm": 2.421875,
1198
- "learning_rate": 4.897777777777778e-06,
1199
- "loss": 0.2711,
1200
- "step": 1700
1201
- },
1202
- {
1203
- "epoch": 0.9821236269653242,
1204
- "grad_norm": 2.375,
1205
- "learning_rate": 4.808888888888889e-06,
1206
- "loss": 0.3008,
1207
- "step": 1710
1208
- },
1209
- {
1210
- "epoch": 0.9878670399885132,
1211
- "grad_norm": 1.9296875,
1212
- "learning_rate": 4.7200000000000005e-06,
1213
- "loss": 0.2649,
1214
- "step": 1720
1215
- },
1216
- {
1217
- "epoch": 0.9936104530117023,
1218
- "grad_norm": 1.9296875,
1219
- "learning_rate": 4.631111111111111e-06,
1220
- "loss": 0.2625,
1221
- "step": 1730
1222
- },
1223
- {
1224
- "epoch": 0.9993538660348912,
1225
- "grad_norm": 2.359375,
1226
- "learning_rate": 4.542222222222223e-06,
1227
- "loss": 0.2995,
1228
- "step": 1740
1229
- },
1230
- {
1231
- "epoch": 1.0045947304185512,
1232
- "grad_norm": 2.078125,
1233
- "learning_rate": 4.453333333333334e-06,
1234
- "loss": 0.2862,
1235
- "step": 1750
1236
- },
1237
- {
1238
- "epoch": 1.0103381434417402,
1239
- "grad_norm": 1.953125,
1240
- "learning_rate": 4.364444444444445e-06,
1241
- "loss": 0.24,
1242
- "step": 1760
1243
- },
1244
- {
1245
- "epoch": 1.0160815564649293,
1246
- "grad_norm": 2.28125,
1247
- "learning_rate": 4.275555555555556e-06,
1248
- "loss": 0.2394,
1249
- "step": 1770
1250
- },
1251
- {
1252
- "epoch": 1.0218249694881183,
1253
- "grad_norm": 1.796875,
1254
- "learning_rate": 4.1866666666666675e-06,
1255
- "loss": 0.2177,
1256
- "step": 1780
1257
- },
1258
- {
1259
- "epoch": 1.0275683825113073,
1260
- "grad_norm": 2.28125,
1261
- "learning_rate": 4.097777777777778e-06,
1262
- "loss": 0.2514,
1263
- "step": 1790
1264
- },
1265
- {
1266
- "epoch": 1.0333117955344964,
1267
- "grad_norm": 1.890625,
1268
- "learning_rate": 4.008888888888889e-06,
1269
- "loss": 0.2158,
1270
- "step": 1800
1271
- },
1272
- {
1273
- "epoch": 1.0390552085576854,
1274
- "grad_norm": 2.015625,
1275
- "learning_rate": 3.920000000000001e-06,
1276
- "loss": 0.2377,
1277
- "step": 1810
1278
- },
1279
- {
1280
- "epoch": 1.0447986215808744,
1281
- "grad_norm": 2.5,
1282
- "learning_rate": 3.831111111111112e-06,
1283
- "loss": 0.2193,
1284
- "step": 1820
1285
- },
1286
- {
1287
- "epoch": 1.0505420346040635,
1288
- "grad_norm": 2.40625,
1289
- "learning_rate": 3.7422222222222228e-06,
1290
- "loss": 0.2354,
1291
- "step": 1830
1292
- },
1293
- {
1294
- "epoch": 1.0562854476272525,
1295
- "grad_norm": 1.8984375,
1296
- "learning_rate": 3.6533333333333336e-06,
1297
- "loss": 0.2315,
1298
- "step": 1840
1299
- },
1300
- {
1301
- "epoch": 1.0620288606504416,
1302
- "grad_norm": 2.484375,
1303
- "learning_rate": 3.564444444444445e-06,
1304
- "loss": 0.1987,
1305
- "step": 1850
1306
- },
1307
- {
1308
- "epoch": 1.0677722736736306,
1309
- "grad_norm": 2.5,
1310
- "learning_rate": 3.475555555555556e-06,
1311
- "loss": 0.2276,
1312
- "step": 1860
1313
- },
1314
- {
1315
- "epoch": 1.0735156866968196,
1316
- "grad_norm": 2.90625,
1317
- "learning_rate": 3.386666666666667e-06,
1318
- "loss": 0.225,
1319
- "step": 1870
1320
- },
1321
- {
1322
- "epoch": 1.0792590997200087,
1323
- "grad_norm": 1.8046875,
1324
- "learning_rate": 3.297777777777778e-06,
1325
- "loss": 0.1992,
1326
- "step": 1880
1327
- },
1328
- {
1329
- "epoch": 1.0850025127431977,
1330
- "grad_norm": 2.265625,
1331
- "learning_rate": 3.2088888888888893e-06,
1332
- "loss": 0.2068,
1333
- "step": 1890
1334
- },
1335
- {
1336
- "epoch": 1.0907459257663867,
1337
- "grad_norm": 2.296875,
1338
- "learning_rate": 3.12e-06,
1339
- "loss": 0.225,
1340
- "step": 1900
1341
- },
1342
- {
1343
- "epoch": 1.0964893387895758,
1344
- "grad_norm": 2.703125,
1345
- "learning_rate": 3.0311111111111115e-06,
1346
- "loss": 0.2173,
1347
- "step": 1910
1348
- },
1349
- {
1350
- "epoch": 1.1022327518127648,
1351
- "grad_norm": 2.625,
1352
- "learning_rate": 2.9422222222222224e-06,
1353
- "loss": 0.2348,
1354
- "step": 1920
1355
- },
1356
- {
1357
- "epoch": 1.1079761648359538,
1358
- "grad_norm": 1.796875,
1359
- "learning_rate": 2.8533333333333337e-06,
1360
- "loss": 0.2427,
1361
- "step": 1930
1362
- },
1363
- {
1364
- "epoch": 1.1137195778591429,
1365
- "grad_norm": 2.0625,
1366
- "learning_rate": 2.7644444444444446e-06,
1367
- "loss": 0.2386,
1368
- "step": 1940
1369
- },
1370
- {
1371
- "epoch": 1.119462990882332,
1372
- "grad_norm": 2.140625,
1373
- "learning_rate": 2.675555555555556e-06,
1374
- "loss": 0.2433,
1375
- "step": 1950
1376
- },
1377
- {
1378
- "epoch": 1.125206403905521,
1379
- "grad_norm": 2.25,
1380
- "learning_rate": 2.5866666666666667e-06,
1381
- "loss": 0.2448,
1382
- "step": 1960
1383
- },
1384
- {
1385
- "epoch": 1.1309498169287098,
1386
- "grad_norm": 2.140625,
1387
- "learning_rate": 2.497777777777778e-06,
1388
- "loss": 0.2304,
1389
- "step": 1970
1390
- },
1391
- {
1392
- "epoch": 1.136693229951899,
1393
- "grad_norm": 2.09375,
1394
- "learning_rate": 2.4088888888888894e-06,
1395
- "loss": 0.2304,
1396
- "step": 1980
1397
- },
1398
- {
1399
- "epoch": 1.1424366429750878,
1400
- "grad_norm": 2.515625,
1401
- "learning_rate": 2.3200000000000002e-06,
1402
- "loss": 0.236,
1403
- "step": 1990
1404
- },
1405
- {
1406
- "epoch": 1.1481800559982769,
1407
- "grad_norm": 2.125,
1408
- "learning_rate": 2.2311111111111115e-06,
1409
- "loss": 0.2367,
1410
- "step": 2000
1411
- }
1412
- ],
1413
- "logging_steps": 10,
1414
- "max_steps": 2250,
1415
- "num_input_tokens_seen": 0,
1416
- "num_train_epochs": 2,
1417
- "save_steps": 500,
1418
- "stateful_callbacks": {
1419
- "TrainerControl": {
1420
- "args": {
1421
- "should_epoch_stop": false,
1422
- "should_evaluate": false,
1423
- "should_log": false,
1424
- "should_save": true,
1425
- "should_training_stop": false
1426
- },
1427
- "attributes": {}
1428
- }
1429
- },
1430
- "total_flos": 9.552945667120988e+17,
1431
- "train_batch_size": 1,
1432
- "trial_name": null,
1433
- "trial_params": null
1434
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:361125642ad5db12b2d31389eb95ab5f48a61f1b57295a045caaee9962562ff5
3
- size 5713