Divij commited on
Commit
67af8b2
·
verified ·
1 Parent(s): 51953b9

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
29
+ {%- if tools is not none %}
30
+ {{- "Environment: ipython\n" }}
31
+ {%- endif %}
32
+ {{- "Cutting Knowledge Date: December 2023\n" }}
33
+ {{- "Today Date: " + date_string + "\n\n" }}
34
+ {%- if tools is not none and not tools_in_user_message %}
35
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
36
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
37
+ {{- "Do not use variables.\n\n" }}
38
+ {%- for t in tools %}
39
+ {{- t | tojson(indent=4) }}
40
+ {{- "\n\n" }}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {{- system_message }}
44
+ {{- "<|eot_id|>" }}
45
+
46
+ {#- Custom tools are passed in a user message with some extra guidance #}
47
+ {%- if tools_in_user_message and not tools is none %}
48
+ {#- Extract the first user message so we can plug it in here #}
49
+ {%- if messages | length != 0 %}
50
+ {%- set first_user_message = messages[0]['content']|trim %}
51
+ {%- set messages = messages[1:] %}
52
+ {%- else %}
53
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
54
+ {%- endif %}
55
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
56
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
57
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
58
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
59
+ {{- "Do not use variables.\n\n" }}
60
+ {%- for t in tools %}
61
+ {{- t | tojson(indent=4) }}
62
+ {{- "\n\n" }}
63
+ {%- endfor %}
64
+ {{- first_user_message + "<|eot_id|>"}}
65
+ {%- endif %}
66
+
67
+ {%- for message in messages %}
68
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
69
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
70
+ {%- elif 'tool_calls' in message %}
71
+ {%- if not message.tool_calls|length == 1 %}
72
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
73
+ {%- endif %}
74
+ {%- set tool_call = message.tool_calls[0].function %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- '{"name": "' + tool_call.name + '", ' }}
77
+ {{- '"parameters": ' }}
78
+ {{- tool_call.arguments | tojson }}
79
+ {{- "}" }}
80
+ {{- "<|eot_id|>" }}
81
+ {%- elif message.role == "tool" or message.role == "ipython" %}
82
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
83
+ {%- if message.content is mapping or message.content is iterable %}
84
+ {{- message.content | tojson }}
85
+ {%- else %}
86
+ {{- message.content }}
87
+ {%- endif %}
88
+ {{- "<|eot_id|>" }}
89
+ {%- endif %}
90
+ {%- endfor %}
91
+ {%- if add_generation_prompt %}
92
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
93
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "float32",
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "transformers_version": "4.57.1",
37
+ "use_cache": true,
38
+ "vocab_size": 128256
39
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.57.1"
12
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0217bf40f05411fff88f38660de304bd14541b775f9ba03a89a3cf5540fa22d8
3
+ size 4998767360
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08dd632976b30b5c7dde8e11ec3796a1227a6469c93867571249ed0d5f48bf78
3
+ size 4932808968
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3fe746cfebc80fc8ffdd0fde708026af9cf47250c141c6aca567fff638c98b
3
+ size 2919452168
model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 3212749824,
4
+ "total_size": 12850999296
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
260
+ "model.norm.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62978368d134d651009b2ab98fc264152773b9ae224bd9e9a0fafe67055e9d80
3
+ size 25702221711
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ce66cbbb4d80808680a9a9eb511769ba2db3909d7f62993fb4e0ac84eefa9ad
3
+ size 14917
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56584a2ce2b67b560dbdca2a56519ad7e6aba8e34b3c8ae11350541319cdc5f6
3
+ size 14917
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad88a75cf868eb7ccab8ff3f5c00e8d0687e81c6e557ba22510a261e21e1f47
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a506fc5fe274b43aa8e389f830138bae677816c37d28186a15ac4071affdc0a
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051830f2f6c06d23b79bfeb1cb00c36ab32a29c2905e80e0b8e22148b654ec8b
3
+ size 17210197
tokenizer_config.json ADDED
@@ -0,0 +1,2067 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "added_tokens_decoder": {
5
+ "128000": {
6
+ "content": "<|begin_of_text|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "128001": {
14
+ "content": "<|end_of_text|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "128002": {
22
+ "content": "<|reserved_special_token_0|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "128003": {
30
+ "content": "<|reserved_special_token_1|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "128004": {
38
+ "content": "<|finetune_right_pad_id|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "128005": {
46
+ "content": "<|reserved_special_token_2|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "128006": {
54
+ "content": "<|start_header_id|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "128007": {
62
+ "content": "<|end_header_id|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "128008": {
70
+ "content": "<|eom_id|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "128009": {
78
+ "content": "<|eot_id|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "128010": {
86
+ "content": "<|python_tag|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "128011": {
94
+ "content": "<|reserved_special_token_3|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "128012": {
102
+ "content": "<|reserved_special_token_4|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "128013": {
110
+ "content": "<|reserved_special_token_5|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "128014": {
118
+ "content": "<|reserved_special_token_6|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "128015": {
126
+ "content": "<|reserved_special_token_7|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "128016": {
134
+ "content": "<|reserved_special_token_8|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "128017": {
142
+ "content": "<|reserved_special_token_9|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "128018": {
150
+ "content": "<|reserved_special_token_10|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "128019": {
158
+ "content": "<|reserved_special_token_11|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "128020": {
166
+ "content": "<|reserved_special_token_12|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "128021": {
174
+ "content": "<|reserved_special_token_13|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "128022": {
182
+ "content": "<|reserved_special_token_14|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "128023": {
190
+ "content": "<|reserved_special_token_15|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "128024": {
198
+ "content": "<|reserved_special_token_16|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "128025": {
206
+ "content": "<|reserved_special_token_17|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "128026": {
214
+ "content": "<|reserved_special_token_18|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "128027": {
222
+ "content": "<|reserved_special_token_19|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "128028": {
230
+ "content": "<|reserved_special_token_20|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "128029": {
238
+ "content": "<|reserved_special_token_21|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "128030": {
246
+ "content": "<|reserved_special_token_22|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "128031": {
254
+ "content": "<|reserved_special_token_23|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "128032": {
262
+ "content": "<|reserved_special_token_24|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "128033": {
270
+ "content": "<|reserved_special_token_25|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "128034": {
278
+ "content": "<|reserved_special_token_26|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "128035": {
286
+ "content": "<|reserved_special_token_27|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "128036": {
294
+ "content": "<|reserved_special_token_28|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "128037": {
302
+ "content": "<|reserved_special_token_29|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "128038": {
310
+ "content": "<|reserved_special_token_30|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "128039": {
318
+ "content": "<|reserved_special_token_31|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "128040": {
326
+ "content": "<|reserved_special_token_32|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "128041": {
334
+ "content": "<|reserved_special_token_33|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "128042": {
342
+ "content": "<|reserved_special_token_34|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "128043": {
350
+ "content": "<|reserved_special_token_35|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "128044": {
358
+ "content": "<|reserved_special_token_36|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "128045": {
366
+ "content": "<|reserved_special_token_37|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "128046": {
374
+ "content": "<|reserved_special_token_38|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "128047": {
382
+ "content": "<|reserved_special_token_39|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "128048": {
390
+ "content": "<|reserved_special_token_40|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "128049": {
398
+ "content": "<|reserved_special_token_41|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "128050": {
406
+ "content": "<|reserved_special_token_42|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "128051": {
414
+ "content": "<|reserved_special_token_43|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "128052": {
422
+ "content": "<|reserved_special_token_44|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "128053": {
430
+ "content": "<|reserved_special_token_45|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "128054": {
438
+ "content": "<|reserved_special_token_46|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "128055": {
446
+ "content": "<|reserved_special_token_47|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "128056": {
454
+ "content": "<|reserved_special_token_48|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "128057": {
462
+ "content": "<|reserved_special_token_49|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "128058": {
470
+ "content": "<|reserved_special_token_50|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "128059": {
478
+ "content": "<|reserved_special_token_51|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "128060": {
486
+ "content": "<|reserved_special_token_52|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "128061": {
494
+ "content": "<|reserved_special_token_53|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "128062": {
502
+ "content": "<|reserved_special_token_54|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "128063": {
510
+ "content": "<|reserved_special_token_55|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "128064": {
518
+ "content": "<|reserved_special_token_56|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "128065": {
526
+ "content": "<|reserved_special_token_57|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "128066": {
534
+ "content": "<|reserved_special_token_58|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "128067": {
542
+ "content": "<|reserved_special_token_59|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "128068": {
550
+ "content": "<|reserved_special_token_60|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "128069": {
558
+ "content": "<|reserved_special_token_61|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "128070": {
566
+ "content": "<|reserved_special_token_62|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "128071": {
574
+ "content": "<|reserved_special_token_63|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "128072": {
582
+ "content": "<|reserved_special_token_64|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "128073": {
590
+ "content": "<|reserved_special_token_65|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "128074": {
598
+ "content": "<|reserved_special_token_66|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "128075": {
606
+ "content": "<|reserved_special_token_67|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "128076": {
614
+ "content": "<|reserved_special_token_68|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "128077": {
622
+ "content": "<|reserved_special_token_69|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "128078": {
630
+ "content": "<|reserved_special_token_70|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "128079": {
638
+ "content": "<|reserved_special_token_71|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "128080": {
646
+ "content": "<|reserved_special_token_72|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "128081": {
654
+ "content": "<|reserved_special_token_73|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "128082": {
662
+ "content": "<|reserved_special_token_74|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "128083": {
670
+ "content": "<|reserved_special_token_75|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "128084": {
678
+ "content": "<|reserved_special_token_76|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "128085": {
686
+ "content": "<|reserved_special_token_77|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "128086": {
694
+ "content": "<|reserved_special_token_78|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "128087": {
702
+ "content": "<|reserved_special_token_79|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "128088": {
710
+ "content": "<|reserved_special_token_80|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "128089": {
718
+ "content": "<|reserved_special_token_81|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "128090": {
726
+ "content": "<|reserved_special_token_82|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "128091": {
734
+ "content": "<|reserved_special_token_83|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "128092": {
742
+ "content": "<|reserved_special_token_84|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "128093": {
750
+ "content": "<|reserved_special_token_85|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "128094": {
758
+ "content": "<|reserved_special_token_86|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "128095": {
766
+ "content": "<|reserved_special_token_87|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "128096": {
774
+ "content": "<|reserved_special_token_88|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "128097": {
782
+ "content": "<|reserved_special_token_89|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "128098": {
790
+ "content": "<|reserved_special_token_90|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "128099": {
798
+ "content": "<|reserved_special_token_91|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "128100": {
806
+ "content": "<|reserved_special_token_92|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "128101": {
814
+ "content": "<|reserved_special_token_93|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "128102": {
822
+ "content": "<|reserved_special_token_94|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "128103": {
830
+ "content": "<|reserved_special_token_95|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "128104": {
838
+ "content": "<|reserved_special_token_96|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "128105": {
846
+ "content": "<|reserved_special_token_97|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "128106": {
854
+ "content": "<|reserved_special_token_98|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "128107": {
862
+ "content": "<|reserved_special_token_99|>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "128108": {
870
+ "content": "<|reserved_special_token_100|>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "128109": {
878
+ "content": "<|reserved_special_token_101|>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "128110": {
886
+ "content": "<|reserved_special_token_102|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "128111": {
894
+ "content": "<|reserved_special_token_103|>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "128112": {
902
+ "content": "<|reserved_special_token_104|>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "128113": {
910
+ "content": "<|reserved_special_token_105|>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "128114": {
918
+ "content": "<|reserved_special_token_106|>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "128115": {
926
+ "content": "<|reserved_special_token_107|>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "128116": {
934
+ "content": "<|reserved_special_token_108|>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "128117": {
942
+ "content": "<|reserved_special_token_109|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "128118": {
950
+ "content": "<|reserved_special_token_110|>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "128119": {
958
+ "content": "<|reserved_special_token_111|>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "128120": {
966
+ "content": "<|reserved_special_token_112|>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "128121": {
974
+ "content": "<|reserved_special_token_113|>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "128122": {
982
+ "content": "<|reserved_special_token_114|>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "128123": {
990
+ "content": "<|reserved_special_token_115|>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "128124": {
998
+ "content": "<|reserved_special_token_116|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "128125": {
1006
+ "content": "<|reserved_special_token_117|>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "128126": {
1014
+ "content": "<|reserved_special_token_118|>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "128127": {
1022
+ "content": "<|reserved_special_token_119|>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "128128": {
1030
+ "content": "<|reserved_special_token_120|>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "128129": {
1038
+ "content": "<|reserved_special_token_121|>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "128130": {
1046
+ "content": "<|reserved_special_token_122|>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "128131": {
1054
+ "content": "<|reserved_special_token_123|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "128132": {
1062
+ "content": "<|reserved_special_token_124|>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "128133": {
1070
+ "content": "<|reserved_special_token_125|>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "128134": {
1078
+ "content": "<|reserved_special_token_126|>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "128135": {
1086
+ "content": "<|reserved_special_token_127|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "128136": {
1094
+ "content": "<|reserved_special_token_128|>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "128137": {
1102
+ "content": "<|reserved_special_token_129|>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "128138": {
1110
+ "content": "<|reserved_special_token_130|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "128139": {
1118
+ "content": "<|reserved_special_token_131|>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "128140": {
1126
+ "content": "<|reserved_special_token_132|>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "128141": {
1134
+ "content": "<|reserved_special_token_133|>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "128142": {
1142
+ "content": "<|reserved_special_token_134|>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "128143": {
1150
+ "content": "<|reserved_special_token_135|>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "128144": {
1158
+ "content": "<|reserved_special_token_136|>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "128145": {
1166
+ "content": "<|reserved_special_token_137|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "128146": {
1174
+ "content": "<|reserved_special_token_138|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "128147": {
1182
+ "content": "<|reserved_special_token_139|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "128148": {
1190
+ "content": "<|reserved_special_token_140|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "128149": {
1198
+ "content": "<|reserved_special_token_141|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "128150": {
1206
+ "content": "<|reserved_special_token_142|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "128151": {
1214
+ "content": "<|reserved_special_token_143|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "128152": {
1222
+ "content": "<|reserved_special_token_144|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "128153": {
1230
+ "content": "<|reserved_special_token_145|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "128154": {
1238
+ "content": "<|reserved_special_token_146|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "128155": {
1246
+ "content": "<|reserved_special_token_147|>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "128156": {
1254
+ "content": "<|reserved_special_token_148|>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "128157": {
1262
+ "content": "<|reserved_special_token_149|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "128158": {
1270
+ "content": "<|reserved_special_token_150|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "128159": {
1278
+ "content": "<|reserved_special_token_151|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "128160": {
1286
+ "content": "<|reserved_special_token_152|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "128161": {
1294
+ "content": "<|reserved_special_token_153|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "128162": {
1302
+ "content": "<|reserved_special_token_154|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "128163": {
1310
+ "content": "<|reserved_special_token_155|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "128164": {
1318
+ "content": "<|reserved_special_token_156|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "128165": {
1326
+ "content": "<|reserved_special_token_157|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "128166": {
1334
+ "content": "<|reserved_special_token_158|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "128167": {
1342
+ "content": "<|reserved_special_token_159|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "128168": {
1350
+ "content": "<|reserved_special_token_160|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "128169": {
1358
+ "content": "<|reserved_special_token_161|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "128170": {
1366
+ "content": "<|reserved_special_token_162|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "128171": {
1374
+ "content": "<|reserved_special_token_163|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "128172": {
1382
+ "content": "<|reserved_special_token_164|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "128173": {
1390
+ "content": "<|reserved_special_token_165|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "128174": {
1398
+ "content": "<|reserved_special_token_166|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "128175": {
1406
+ "content": "<|reserved_special_token_167|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "128176": {
1414
+ "content": "<|reserved_special_token_168|>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "128177": {
1422
+ "content": "<|reserved_special_token_169|>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "128178": {
1430
+ "content": "<|reserved_special_token_170|>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "128179": {
1438
+ "content": "<|reserved_special_token_171|>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "128180": {
1446
+ "content": "<|reserved_special_token_172|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "128181": {
1454
+ "content": "<|reserved_special_token_173|>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "128182": {
1462
+ "content": "<|reserved_special_token_174|>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "128183": {
1470
+ "content": "<|reserved_special_token_175|>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "128184": {
1478
+ "content": "<|reserved_special_token_176|>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "128185": {
1486
+ "content": "<|reserved_special_token_177|>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "128186": {
1494
+ "content": "<|reserved_special_token_178|>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "128187": {
1502
+ "content": "<|reserved_special_token_179|>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "128188": {
1510
+ "content": "<|reserved_special_token_180|>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "128189": {
1518
+ "content": "<|reserved_special_token_181|>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "128190": {
1526
+ "content": "<|reserved_special_token_182|>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "128191": {
1534
+ "content": "<|reserved_special_token_183|>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "128192": {
1542
+ "content": "<|reserved_special_token_184|>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "128193": {
1550
+ "content": "<|reserved_special_token_185|>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "128194": {
1558
+ "content": "<|reserved_special_token_186|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "128195": {
1566
+ "content": "<|reserved_special_token_187|>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "128196": {
1574
+ "content": "<|reserved_special_token_188|>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "128197": {
1582
+ "content": "<|reserved_special_token_189|>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "128198": {
1590
+ "content": "<|reserved_special_token_190|>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "128199": {
1598
+ "content": "<|reserved_special_token_191|>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "128200": {
1606
+ "content": "<|reserved_special_token_192|>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "128201": {
1614
+ "content": "<|reserved_special_token_193|>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "128202": {
1622
+ "content": "<|reserved_special_token_194|>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "128203": {
1630
+ "content": "<|reserved_special_token_195|>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "128204": {
1638
+ "content": "<|reserved_special_token_196|>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "128205": {
1646
+ "content": "<|reserved_special_token_197|>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "128206": {
1654
+ "content": "<|reserved_special_token_198|>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "128207": {
1662
+ "content": "<|reserved_special_token_199|>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ },
1669
+ "128208": {
1670
+ "content": "<|reserved_special_token_200|>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": true
1676
+ },
1677
+ "128209": {
1678
+ "content": "<|reserved_special_token_201|>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": true
1684
+ },
1685
+ "128210": {
1686
+ "content": "<|reserved_special_token_202|>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": true
1692
+ },
1693
+ "128211": {
1694
+ "content": "<|reserved_special_token_203|>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": true
1700
+ },
1701
+ "128212": {
1702
+ "content": "<|reserved_special_token_204|>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": true
1708
+ },
1709
+ "128213": {
1710
+ "content": "<|reserved_special_token_205|>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": true
1716
+ },
1717
+ "128214": {
1718
+ "content": "<|reserved_special_token_206|>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": true
1724
+ },
1725
+ "128215": {
1726
+ "content": "<|reserved_special_token_207|>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": true
1732
+ },
1733
+ "128216": {
1734
+ "content": "<|reserved_special_token_208|>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": true
1740
+ },
1741
+ "128217": {
1742
+ "content": "<|reserved_special_token_209|>",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": true
1748
+ },
1749
+ "128218": {
1750
+ "content": "<|reserved_special_token_210|>",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": true
1756
+ },
1757
+ "128219": {
1758
+ "content": "<|reserved_special_token_211|>",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": true
1764
+ },
1765
+ "128220": {
1766
+ "content": "<|reserved_special_token_212|>",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": true
1772
+ },
1773
+ "128221": {
1774
+ "content": "<|reserved_special_token_213|>",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": true
1780
+ },
1781
+ "128222": {
1782
+ "content": "<|reserved_special_token_214|>",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": true
1788
+ },
1789
+ "128223": {
1790
+ "content": "<|reserved_special_token_215|>",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": true
1796
+ },
1797
+ "128224": {
1798
+ "content": "<|reserved_special_token_216|>",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": true
1804
+ },
1805
+ "128225": {
1806
+ "content": "<|reserved_special_token_217|>",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": true
1812
+ },
1813
+ "128226": {
1814
+ "content": "<|reserved_special_token_218|>",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": true
1820
+ },
1821
+ "128227": {
1822
+ "content": "<|reserved_special_token_219|>",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": true
1828
+ },
1829
+ "128228": {
1830
+ "content": "<|reserved_special_token_220|>",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": true
1836
+ },
1837
+ "128229": {
1838
+ "content": "<|reserved_special_token_221|>",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": true
1844
+ },
1845
+ "128230": {
1846
+ "content": "<|reserved_special_token_222|>",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": true
1852
+ },
1853
+ "128231": {
1854
+ "content": "<|reserved_special_token_223|>",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": true
1860
+ },
1861
+ "128232": {
1862
+ "content": "<|reserved_special_token_224|>",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": true
1868
+ },
1869
+ "128233": {
1870
+ "content": "<|reserved_special_token_225|>",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": true
1876
+ },
1877
+ "128234": {
1878
+ "content": "<|reserved_special_token_226|>",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": true
1884
+ },
1885
+ "128235": {
1886
+ "content": "<|reserved_special_token_227|>",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": true
1892
+ },
1893
+ "128236": {
1894
+ "content": "<|reserved_special_token_228|>",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": true
1900
+ },
1901
+ "128237": {
1902
+ "content": "<|reserved_special_token_229|>",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": true
1908
+ },
1909
+ "128238": {
1910
+ "content": "<|reserved_special_token_230|>",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": true
1916
+ },
1917
+ "128239": {
1918
+ "content": "<|reserved_special_token_231|>",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": true
1924
+ },
1925
+ "128240": {
1926
+ "content": "<|reserved_special_token_232|>",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": true
1932
+ },
1933
+ "128241": {
1934
+ "content": "<|reserved_special_token_233|>",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": true
1940
+ },
1941
+ "128242": {
1942
+ "content": "<|reserved_special_token_234|>",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": true
1948
+ },
1949
+ "128243": {
1950
+ "content": "<|reserved_special_token_235|>",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": true
1956
+ },
1957
+ "128244": {
1958
+ "content": "<|reserved_special_token_236|>",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": true
1964
+ },
1965
+ "128245": {
1966
+ "content": "<|reserved_special_token_237|>",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": true
1972
+ },
1973
+ "128246": {
1974
+ "content": "<|reserved_special_token_238|>",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": true
1980
+ },
1981
+ "128247": {
1982
+ "content": "<|reserved_special_token_239|>",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": true
1988
+ },
1989
+ "128248": {
1990
+ "content": "<|reserved_special_token_240|>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": true
1996
+ },
1997
+ "128249": {
1998
+ "content": "<|reserved_special_token_241|>",
1999
+ "lstrip": false,
2000
+ "normalized": false,
2001
+ "rstrip": false,
2002
+ "single_word": false,
2003
+ "special": true
2004
+ },
2005
+ "128250": {
2006
+ "content": "<|reserved_special_token_242|>",
2007
+ "lstrip": false,
2008
+ "normalized": false,
2009
+ "rstrip": false,
2010
+ "single_word": false,
2011
+ "special": true
2012
+ },
2013
+ "128251": {
2014
+ "content": "<|reserved_special_token_243|>",
2015
+ "lstrip": false,
2016
+ "normalized": false,
2017
+ "rstrip": false,
2018
+ "single_word": false,
2019
+ "special": true
2020
+ },
2021
+ "128252": {
2022
+ "content": "<|reserved_special_token_244|>",
2023
+ "lstrip": false,
2024
+ "normalized": false,
2025
+ "rstrip": false,
2026
+ "single_word": false,
2027
+ "special": true
2028
+ },
2029
+ "128253": {
2030
+ "content": "<|reserved_special_token_245|>",
2031
+ "lstrip": false,
2032
+ "normalized": false,
2033
+ "rstrip": false,
2034
+ "single_word": false,
2035
+ "special": true
2036
+ },
2037
+ "128254": {
2038
+ "content": "<|reserved_special_token_246|>",
2039
+ "lstrip": false,
2040
+ "normalized": false,
2041
+ "rstrip": false,
2042
+ "single_word": false,
2043
+ "special": true
2044
+ },
2045
+ "128255": {
2046
+ "content": "<|reserved_special_token_247|>",
2047
+ "lstrip": false,
2048
+ "normalized": false,
2049
+ "rstrip": false,
2050
+ "single_word": false,
2051
+ "special": true
2052
+ }
2053
+ },
2054
+ "bos_token": "<|begin_of_text|>",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|eot_id|>",
2064
+ "padding_side": "right",
2065
+ "tokenizer_class": "PreTrainedTokenizerFast",
2066
+ "use_multiprocessing": false
2067
+ }
trainer_state.json ADDED
@@ -0,0 +1,1154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1400,
3
+ "best_metric": 0.6364541053771973,
4
+ "best_model_checkpoint": "/scr/dhanda/projects/sampling_inference/trained_models/aswin_llama_star/checkpoint-1400",
5
+ "epoch": 1.0,
6
+ "eval_steps": 100,
7
+ "global_step": 1441,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.006939625260235947,
14
+ "grad_norm": 8.436548233032227,
15
+ "learning_rate": 2.7586206896551725e-06,
16
+ "loss": 0.8313,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.013879250520471894,
21
+ "grad_norm": 5.655324935913086,
22
+ "learning_rate": 6.206896551724138e-06,
23
+ "loss": 0.5995,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.020818875780707843,
28
+ "grad_norm": 6.097832202911377,
29
+ "learning_rate": 9.655172413793103e-06,
30
+ "loss": 0.5897,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.027758501040943788,
35
+ "grad_norm": 5.244992256164551,
36
+ "learning_rate": 1.310344827586207e-05,
37
+ "loss": 0.5975,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.03469812630117974,
42
+ "grad_norm": 5.82904577255249,
43
+ "learning_rate": 1.6551724137931037e-05,
44
+ "loss": 0.5866,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.041637751561415685,
49
+ "grad_norm": 4.755958557128906,
50
+ "learning_rate": 2e-05,
51
+ "loss": 0.6143,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.048577376821651634,
56
+ "grad_norm": 4.591907024383545,
57
+ "learning_rate": 2.3448275862068967e-05,
58
+ "loss": 0.6709,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.055517002081887576,
63
+ "grad_norm": 5.520663738250732,
64
+ "learning_rate": 2.689655172413793e-05,
65
+ "loss": 0.6815,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.062456627342123525,
70
+ "grad_norm": 5.258326530456543,
71
+ "learning_rate": 3.0344827586206897e-05,
72
+ "loss": 0.7171,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.06939625260235947,
77
+ "grad_norm": 4.56249475479126,
78
+ "learning_rate": 3.3793103448275865e-05,
79
+ "loss": 0.7289,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.06939625260235947,
84
+ "eval_loss": 0.7279375195503235,
85
+ "eval_runtime": 49.9788,
86
+ "eval_samples_per_second": 28.832,
87
+ "eval_steps_per_second": 7.223,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 0.07633587786259542,
92
+ "grad_norm": 3.349087715148926,
93
+ "learning_rate": 3.724137931034483e-05,
94
+ "loss": 0.7553,
95
+ "step": 110
96
+ },
97
+ {
98
+ "epoch": 0.08327550312283137,
99
+ "grad_norm": 3.4430437088012695,
100
+ "learning_rate": 4.0689655172413795e-05,
101
+ "loss": 0.7228,
102
+ "step": 120
103
+ },
104
+ {
105
+ "epoch": 0.09021512838306732,
106
+ "grad_norm": 4.375394821166992,
107
+ "learning_rate": 4.413793103448276e-05,
108
+ "loss": 0.8678,
109
+ "step": 130
110
+ },
111
+ {
112
+ "epoch": 0.09715475364330327,
113
+ "grad_norm": 4.496102333068848,
114
+ "learning_rate": 4.7586206896551725e-05,
115
+ "loss": 0.8478,
116
+ "step": 140
117
+ },
118
+ {
119
+ "epoch": 0.1040943789035392,
120
+ "grad_norm": 4.770753383636475,
121
+ "learning_rate": 4.988425925925926e-05,
122
+ "loss": 0.824,
123
+ "step": 150
124
+ },
125
+ {
126
+ "epoch": 0.11103400416377515,
127
+ "grad_norm": 4.819082260131836,
128
+ "learning_rate": 4.949845679012346e-05,
129
+ "loss": 0.8833,
130
+ "step": 160
131
+ },
132
+ {
133
+ "epoch": 0.1179736294240111,
134
+ "grad_norm": 5.851232528686523,
135
+ "learning_rate": 4.911265432098766e-05,
136
+ "loss": 0.8861,
137
+ "step": 170
138
+ },
139
+ {
140
+ "epoch": 0.12491325468424705,
141
+ "grad_norm": 3.9091575145721436,
142
+ "learning_rate": 4.8726851851851855e-05,
143
+ "loss": 0.9043,
144
+ "step": 180
145
+ },
146
+ {
147
+ "epoch": 0.131852879944483,
148
+ "grad_norm": 4.504231929779053,
149
+ "learning_rate": 4.834104938271605e-05,
150
+ "loss": 0.909,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 0.13879250520471895,
155
+ "grad_norm": 5.178035259246826,
156
+ "learning_rate": 4.795524691358025e-05,
157
+ "loss": 0.8768,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 0.13879250520471895,
162
+ "eval_loss": 0.8475821018218994,
163
+ "eval_runtime": 49.8841,
164
+ "eval_samples_per_second": 28.887,
165
+ "eval_steps_per_second": 7.237,
166
+ "step": 200
167
+ },
168
+ {
169
+ "epoch": 0.1457321304649549,
170
+ "grad_norm": 4.2687907218933105,
171
+ "learning_rate": 4.756944444444444e-05,
172
+ "loss": 0.7687,
173
+ "step": 210
174
+ },
175
+ {
176
+ "epoch": 0.15267175572519084,
177
+ "grad_norm": 3.8715438842773438,
178
+ "learning_rate": 4.7183641975308646e-05,
179
+ "loss": 0.8323,
180
+ "step": 220
181
+ },
182
+ {
183
+ "epoch": 0.1596113809854268,
184
+ "grad_norm": 5.992573261260986,
185
+ "learning_rate": 4.679783950617284e-05,
186
+ "loss": 0.829,
187
+ "step": 230
188
+ },
189
+ {
190
+ "epoch": 0.16655100624566274,
191
+ "grad_norm": 3.7021474838256836,
192
+ "learning_rate": 4.6412037037037034e-05,
193
+ "loss": 0.8627,
194
+ "step": 240
195
+ },
196
+ {
197
+ "epoch": 0.1734906315058987,
198
+ "grad_norm": 3.4208054542541504,
199
+ "learning_rate": 4.602623456790124e-05,
200
+ "loss": 0.9109,
201
+ "step": 250
202
+ },
203
+ {
204
+ "epoch": 0.18043025676613464,
205
+ "grad_norm": 3.720872163772583,
206
+ "learning_rate": 4.5640432098765436e-05,
207
+ "loss": 0.8255,
208
+ "step": 260
209
+ },
210
+ {
211
+ "epoch": 0.1873698820263706,
212
+ "grad_norm": 3.8880999088287354,
213
+ "learning_rate": 4.525462962962963e-05,
214
+ "loss": 0.8802,
215
+ "step": 270
216
+ },
217
+ {
218
+ "epoch": 0.19430950728660654,
219
+ "grad_norm": 3.356327772140503,
220
+ "learning_rate": 4.486882716049383e-05,
221
+ "loss": 0.9039,
222
+ "step": 280
223
+ },
224
+ {
225
+ "epoch": 0.20124913254684246,
226
+ "grad_norm": 3.6388580799102783,
227
+ "learning_rate": 4.448302469135803e-05,
228
+ "loss": 0.8776,
229
+ "step": 290
230
+ },
231
+ {
232
+ "epoch": 0.2081887578070784,
233
+ "grad_norm": 4.57245397567749,
234
+ "learning_rate": 4.4097222222222226e-05,
235
+ "loss": 0.8568,
236
+ "step": 300
237
+ },
238
+ {
239
+ "epoch": 0.2081887578070784,
240
+ "eval_loss": 0.8598970770835876,
241
+ "eval_runtime": 50.2014,
242
+ "eval_samples_per_second": 28.704,
243
+ "eval_steps_per_second": 7.191,
244
+ "step": 300
245
+ },
246
+ {
247
+ "epoch": 0.21512838306731435,
248
+ "grad_norm": 3.0655972957611084,
249
+ "learning_rate": 4.3711419753086424e-05,
250
+ "loss": 0.8248,
251
+ "step": 310
252
+ },
253
+ {
254
+ "epoch": 0.2220680083275503,
255
+ "grad_norm": 3.4082236289978027,
256
+ "learning_rate": 4.332561728395062e-05,
257
+ "loss": 0.8737,
258
+ "step": 320
259
+ },
260
+ {
261
+ "epoch": 0.22900763358778625,
262
+ "grad_norm": 4.789612770080566,
263
+ "learning_rate": 4.293981481481482e-05,
264
+ "loss": 0.8218,
265
+ "step": 330
266
+ },
267
+ {
268
+ "epoch": 0.2359472588480222,
269
+ "grad_norm": 3.7866945266723633,
270
+ "learning_rate": 4.255401234567901e-05,
271
+ "loss": 0.8208,
272
+ "step": 340
273
+ },
274
+ {
275
+ "epoch": 0.24288688410825815,
276
+ "grad_norm": 4.31322717666626,
277
+ "learning_rate": 4.2168209876543214e-05,
278
+ "loss": 0.7825,
279
+ "step": 350
280
+ },
281
+ {
282
+ "epoch": 0.2498265093684941,
283
+ "grad_norm": 3.4791786670684814,
284
+ "learning_rate": 4.178240740740741e-05,
285
+ "loss": 0.8161,
286
+ "step": 360
287
+ },
288
+ {
289
+ "epoch": 0.25676613462873005,
290
+ "grad_norm": 4.521151542663574,
291
+ "learning_rate": 4.13966049382716e-05,
292
+ "loss": 0.7744,
293
+ "step": 370
294
+ },
295
+ {
296
+ "epoch": 0.263705759888966,
297
+ "grad_norm": 2.1991310119628906,
298
+ "learning_rate": 4.104938271604938e-05,
299
+ "loss": 0.8381,
300
+ "step": 380
301
+ },
302
+ {
303
+ "epoch": 0.27064538514920194,
304
+ "grad_norm": 3.745811939239502,
305
+ "learning_rate": 4.066358024691358e-05,
306
+ "loss": 0.9447,
307
+ "step": 390
308
+ },
309
+ {
310
+ "epoch": 0.2775850104094379,
311
+ "grad_norm": 3.5998716354370117,
312
+ "learning_rate": 4.027777777777778e-05,
313
+ "loss": 0.8452,
314
+ "step": 400
315
+ },
316
+ {
317
+ "epoch": 0.2775850104094379,
318
+ "eval_loss": 0.8371486067771912,
319
+ "eval_runtime": 50.1497,
320
+ "eval_samples_per_second": 28.734,
321
+ "eval_steps_per_second": 7.198,
322
+ "step": 400
323
+ },
324
+ {
325
+ "epoch": 0.28452463566967384,
326
+ "grad_norm": 4.008808612823486,
327
+ "learning_rate": 3.9891975308641976e-05,
328
+ "loss": 0.8101,
329
+ "step": 410
330
+ },
331
+ {
332
+ "epoch": 0.2914642609299098,
333
+ "grad_norm": 4.993364334106445,
334
+ "learning_rate": 3.950617283950617e-05,
335
+ "loss": 0.9292,
336
+ "step": 420
337
+ },
338
+ {
339
+ "epoch": 0.29840388619014574,
340
+ "grad_norm": 3.597254514694214,
341
+ "learning_rate": 3.912037037037037e-05,
342
+ "loss": 0.8176,
343
+ "step": 430
344
+ },
345
+ {
346
+ "epoch": 0.3053435114503817,
347
+ "grad_norm": 4.86491584777832,
348
+ "learning_rate": 3.873456790123457e-05,
349
+ "loss": 0.7595,
350
+ "step": 440
351
+ },
352
+ {
353
+ "epoch": 0.31228313671061764,
354
+ "grad_norm": 4.191522121429443,
355
+ "learning_rate": 3.8348765432098766e-05,
356
+ "loss": 0.8463,
357
+ "step": 450
358
+ },
359
+ {
360
+ "epoch": 0.3192227619708536,
361
+ "grad_norm": 3.8313114643096924,
362
+ "learning_rate": 3.7962962962962964e-05,
363
+ "loss": 0.815,
364
+ "step": 460
365
+ },
366
+ {
367
+ "epoch": 0.32616238723108953,
368
+ "grad_norm": 2.289886951446533,
369
+ "learning_rate": 3.757716049382716e-05,
370
+ "loss": 0.7598,
371
+ "step": 470
372
+ },
373
+ {
374
+ "epoch": 0.3331020124913255,
375
+ "grad_norm": 3.6466236114501953,
376
+ "learning_rate": 3.719135802469136e-05,
377
+ "loss": 0.7771,
378
+ "step": 480
379
+ },
380
+ {
381
+ "epoch": 0.34004163775156143,
382
+ "grad_norm": 3.2481741905212402,
383
+ "learning_rate": 3.6805555555555556e-05,
384
+ "loss": 0.7833,
385
+ "step": 490
386
+ },
387
+ {
388
+ "epoch": 0.3469812630117974,
389
+ "grad_norm": 5.6007208824157715,
390
+ "learning_rate": 3.6419753086419754e-05,
391
+ "loss": 0.8243,
392
+ "step": 500
393
+ },
394
+ {
395
+ "epoch": 0.3469812630117974,
396
+ "eval_loss": 0.8030129671096802,
397
+ "eval_runtime": 50.3084,
398
+ "eval_samples_per_second": 28.643,
399
+ "eval_steps_per_second": 7.176,
400
+ "step": 500
401
+ },
402
+ {
403
+ "epoch": 0.35392088827203333,
404
+ "grad_norm": 4.155673503875732,
405
+ "learning_rate": 3.603395061728395e-05,
406
+ "loss": 0.7968,
407
+ "step": 510
408
+ },
409
+ {
410
+ "epoch": 0.3608605135322693,
411
+ "grad_norm": 3.114962577819824,
412
+ "learning_rate": 3.564814814814815e-05,
413
+ "loss": 0.815,
414
+ "step": 520
415
+ },
416
+ {
417
+ "epoch": 0.3678001387925052,
418
+ "grad_norm": 4.049103736877441,
419
+ "learning_rate": 3.526234567901235e-05,
420
+ "loss": 0.8768,
421
+ "step": 530
422
+ },
423
+ {
424
+ "epoch": 0.3747397640527412,
425
+ "grad_norm": 3.64631724357605,
426
+ "learning_rate": 3.4876543209876545e-05,
427
+ "loss": 0.7909,
428
+ "step": 540
429
+ },
430
+ {
431
+ "epoch": 0.3816793893129771,
432
+ "grad_norm": 3.093494176864624,
433
+ "learning_rate": 3.449074074074074e-05,
434
+ "loss": 0.7576,
435
+ "step": 550
436
+ },
437
+ {
438
+ "epoch": 0.3886190145732131,
439
+ "grad_norm": 3.2251219749450684,
440
+ "learning_rate": 3.410493827160494e-05,
441
+ "loss": 0.813,
442
+ "step": 560
443
+ },
444
+ {
445
+ "epoch": 0.39555863983344897,
446
+ "grad_norm": 2.702892303466797,
447
+ "learning_rate": 3.371913580246914e-05,
448
+ "loss": 0.7765,
449
+ "step": 570
450
+ },
451
+ {
452
+ "epoch": 0.4024982650936849,
453
+ "grad_norm": 3.3482439517974854,
454
+ "learning_rate": 3.3333333333333335e-05,
455
+ "loss": 0.8653,
456
+ "step": 580
457
+ },
458
+ {
459
+ "epoch": 0.40943789035392086,
460
+ "grad_norm": 2.537188768386841,
461
+ "learning_rate": 3.294753086419753e-05,
462
+ "loss": 0.7409,
463
+ "step": 590
464
+ },
465
+ {
466
+ "epoch": 0.4163775156141568,
467
+ "grad_norm": 3.178288459777832,
468
+ "learning_rate": 3.256172839506173e-05,
469
+ "loss": 0.7191,
470
+ "step": 600
471
+ },
472
+ {
473
+ "epoch": 0.4163775156141568,
474
+ "eval_loss": 0.7933737635612488,
475
+ "eval_runtime": 50.9506,
476
+ "eval_samples_per_second": 28.282,
477
+ "eval_steps_per_second": 7.085,
478
+ "step": 600
479
+ },
480
+ {
481
+ "epoch": 0.42331714087439276,
482
+ "grad_norm": 3.4489400386810303,
483
+ "learning_rate": 3.221450617283951e-05,
484
+ "loss": 0.8456,
485
+ "step": 610
486
+ },
487
+ {
488
+ "epoch": 0.4302567661346287,
489
+ "grad_norm": 3.6795783042907715,
490
+ "learning_rate": 3.182870370370371e-05,
491
+ "loss": 0.8392,
492
+ "step": 620
493
+ },
494
+ {
495
+ "epoch": 0.43719639139486466,
496
+ "grad_norm": 2.7610459327697754,
497
+ "learning_rate": 3.14429012345679e-05,
498
+ "loss": 0.7238,
499
+ "step": 630
500
+ },
501
+ {
502
+ "epoch": 0.4441360166551006,
503
+ "grad_norm": 3.525322675704956,
504
+ "learning_rate": 3.10570987654321e-05,
505
+ "loss": 0.8437,
506
+ "step": 640
507
+ },
508
+ {
509
+ "epoch": 0.45107564191533656,
510
+ "grad_norm": 4.020907402038574,
511
+ "learning_rate": 3.06712962962963e-05,
512
+ "loss": 0.8097,
513
+ "step": 650
514
+ },
515
+ {
516
+ "epoch": 0.4580152671755725,
517
+ "grad_norm": 4.816994667053223,
518
+ "learning_rate": 3.0285493827160495e-05,
519
+ "loss": 0.7754,
520
+ "step": 660
521
+ },
522
+ {
523
+ "epoch": 0.46495489243580845,
524
+ "grad_norm": 2.7212016582489014,
525
+ "learning_rate": 2.9899691358024696e-05,
526
+ "loss": 0.7264,
527
+ "step": 670
528
+ },
529
+ {
530
+ "epoch": 0.4718945176960444,
531
+ "grad_norm": 2.6413140296936035,
532
+ "learning_rate": 2.951388888888889e-05,
533
+ "loss": 0.7636,
534
+ "step": 680
535
+ },
536
+ {
537
+ "epoch": 0.47883414295628035,
538
+ "grad_norm": 3.3349661827087402,
539
+ "learning_rate": 2.9128086419753087e-05,
540
+ "loss": 0.7971,
541
+ "step": 690
542
+ },
543
+ {
544
+ "epoch": 0.4857737682165163,
545
+ "grad_norm": 3.037588119506836,
546
+ "learning_rate": 2.8780864197530867e-05,
547
+ "loss": 0.7778,
548
+ "step": 700
549
+ },
550
+ {
551
+ "epoch": 0.4857737682165163,
552
+ "eval_loss": 0.7744709849357605,
553
+ "eval_runtime": 50.6673,
554
+ "eval_samples_per_second": 28.44,
555
+ "eval_steps_per_second": 7.125,
556
+ "step": 700
557
+ },
558
+ {
559
+ "epoch": 0.49271339347675225,
560
+ "grad_norm": 3.02775239944458,
561
+ "learning_rate": 2.839506172839506e-05,
562
+ "loss": 0.7377,
563
+ "step": 710
564
+ },
565
+ {
566
+ "epoch": 0.4996530187369882,
567
+ "grad_norm": 3.7178709506988525,
568
+ "learning_rate": 2.8009259259259263e-05,
569
+ "loss": 0.7315,
570
+ "step": 720
571
+ },
572
+ {
573
+ "epoch": 0.5065926439972241,
574
+ "grad_norm": 2.3943405151367188,
575
+ "learning_rate": 2.762345679012346e-05,
576
+ "loss": 0.6843,
577
+ "step": 730
578
+ },
579
+ {
580
+ "epoch": 0.5135322692574601,
581
+ "grad_norm": 3.1974751949310303,
582
+ "learning_rate": 2.7237654320987654e-05,
583
+ "loss": 0.7292,
584
+ "step": 740
585
+ },
586
+ {
587
+ "epoch": 0.520471894517696,
588
+ "grad_norm": 2.935885429382324,
589
+ "learning_rate": 2.6851851851851855e-05,
590
+ "loss": 0.8194,
591
+ "step": 750
592
+ },
593
+ {
594
+ "epoch": 0.527411519777932,
595
+ "grad_norm": 6.58482027053833,
596
+ "learning_rate": 2.6466049382716053e-05,
597
+ "loss": 0.6681,
598
+ "step": 760
599
+ },
600
+ {
601
+ "epoch": 0.5343511450381679,
602
+ "grad_norm": 2.9752790927886963,
603
+ "learning_rate": 2.6080246913580247e-05,
604
+ "loss": 0.8489,
605
+ "step": 770
606
+ },
607
+ {
608
+ "epoch": 0.5412907702984039,
609
+ "grad_norm": 3.415062427520752,
610
+ "learning_rate": 2.5694444444444445e-05,
611
+ "loss": 0.7535,
612
+ "step": 780
613
+ },
614
+ {
615
+ "epoch": 0.5482303955586398,
616
+ "grad_norm": 2.9602854251861572,
617
+ "learning_rate": 2.5308641975308646e-05,
618
+ "loss": 0.7386,
619
+ "step": 790
620
+ },
621
+ {
622
+ "epoch": 0.5551700208188758,
623
+ "grad_norm": 2.3397035598754883,
624
+ "learning_rate": 2.492283950617284e-05,
625
+ "loss": 0.6889,
626
+ "step": 800
627
+ },
628
+ {
629
+ "epoch": 0.5551700208188758,
630
+ "eval_loss": 0.7451881766319275,
631
+ "eval_runtime": 50.5382,
632
+ "eval_samples_per_second": 28.513,
633
+ "eval_steps_per_second": 7.143,
634
+ "step": 800
635
+ },
636
+ {
637
+ "epoch": 0.5621096460791117,
638
+ "grad_norm": 1.889366626739502,
639
+ "learning_rate": 2.4537037037037038e-05,
640
+ "loss": 0.7376,
641
+ "step": 810
642
+ },
643
+ {
644
+ "epoch": 0.5690492713393477,
645
+ "grad_norm": 3.3545074462890625,
646
+ "learning_rate": 2.4151234567901235e-05,
647
+ "loss": 0.7324,
648
+ "step": 820
649
+ },
650
+ {
651
+ "epoch": 0.5759888965995836,
652
+ "grad_norm": 3.243748426437378,
653
+ "learning_rate": 2.3765432098765433e-05,
654
+ "loss": 0.7056,
655
+ "step": 830
656
+ },
657
+ {
658
+ "epoch": 0.5829285218598196,
659
+ "grad_norm": 1.6572705507278442,
660
+ "learning_rate": 2.337962962962963e-05,
661
+ "loss": 0.7623,
662
+ "step": 840
663
+ },
664
+ {
665
+ "epoch": 0.5898681471200555,
666
+ "grad_norm": 3.6564319133758545,
667
+ "learning_rate": 2.2993827160493828e-05,
668
+ "loss": 0.8021,
669
+ "step": 850
670
+ },
671
+ {
672
+ "epoch": 0.5968077723802915,
673
+ "grad_norm": 2.7752833366394043,
674
+ "learning_rate": 2.2608024691358026e-05,
675
+ "loss": 0.6935,
676
+ "step": 860
677
+ },
678
+ {
679
+ "epoch": 0.6037473976405274,
680
+ "grad_norm": 4.253413677215576,
681
+ "learning_rate": 2.2222222222222223e-05,
682
+ "loss": 0.762,
683
+ "step": 870
684
+ },
685
+ {
686
+ "epoch": 0.6106870229007634,
687
+ "grad_norm": 2.7186923027038574,
688
+ "learning_rate": 2.183641975308642e-05,
689
+ "loss": 0.7403,
690
+ "step": 880
691
+ },
692
+ {
693
+ "epoch": 0.6176266481609993,
694
+ "grad_norm": 2.6007790565490723,
695
+ "learning_rate": 2.145061728395062e-05,
696
+ "loss": 0.7119,
697
+ "step": 890
698
+ },
699
+ {
700
+ "epoch": 0.6245662734212353,
701
+ "grad_norm": 3.293909788131714,
702
+ "learning_rate": 2.1064814814814816e-05,
703
+ "loss": 0.6942,
704
+ "step": 900
705
+ },
706
+ {
707
+ "epoch": 0.6245662734212353,
708
+ "eval_loss": 0.7264400720596313,
709
+ "eval_runtime": 50.4954,
710
+ "eval_samples_per_second": 28.537,
711
+ "eval_steps_per_second": 7.149,
712
+ "step": 900
713
+ },
714
+ {
715
+ "epoch": 0.6315058986814712,
716
+ "grad_norm": 3.3802788257598877,
717
+ "learning_rate": 2.0679012345679014e-05,
718
+ "loss": 0.7141,
719
+ "step": 910
720
+ },
721
+ {
722
+ "epoch": 0.6384455239417072,
723
+ "grad_norm": 2.965416669845581,
724
+ "learning_rate": 2.029320987654321e-05,
725
+ "loss": 0.7806,
726
+ "step": 920
727
+ },
728
+ {
729
+ "epoch": 0.6453851492019431,
730
+ "grad_norm": 3.0134222507476807,
731
+ "learning_rate": 1.990740740740741e-05,
732
+ "loss": 0.6889,
733
+ "step": 930
734
+ },
735
+ {
736
+ "epoch": 0.6523247744621791,
737
+ "grad_norm": 3.078749895095825,
738
+ "learning_rate": 1.9521604938271607e-05,
739
+ "loss": 0.753,
740
+ "step": 940
741
+ },
742
+ {
743
+ "epoch": 0.659264399722415,
744
+ "grad_norm": 2.0064494609832764,
745
+ "learning_rate": 1.91358024691358e-05,
746
+ "loss": 0.6586,
747
+ "step": 950
748
+ },
749
+ {
750
+ "epoch": 0.666204024982651,
751
+ "grad_norm": 3.144228458404541,
752
+ "learning_rate": 1.8750000000000002e-05,
753
+ "loss": 0.7233,
754
+ "step": 960
755
+ },
756
+ {
757
+ "epoch": 0.6731436502428869,
758
+ "grad_norm": 3.3552615642547607,
759
+ "learning_rate": 1.83641975308642e-05,
760
+ "loss": 0.6848,
761
+ "step": 970
762
+ },
763
+ {
764
+ "epoch": 0.6800832755031229,
765
+ "grad_norm": 2.424555540084839,
766
+ "learning_rate": 1.7978395061728397e-05,
767
+ "loss": 0.711,
768
+ "step": 980
769
+ },
770
+ {
771
+ "epoch": 0.6870229007633588,
772
+ "grad_norm": 3.5036256313323975,
773
+ "learning_rate": 1.7592592592592595e-05,
774
+ "loss": 0.7794,
775
+ "step": 990
776
+ },
777
+ {
778
+ "epoch": 0.6939625260235948,
779
+ "grad_norm": 3.1521127223968506,
780
+ "learning_rate": 1.720679012345679e-05,
781
+ "loss": 0.7769,
782
+ "step": 1000
783
+ },
784
+ {
785
+ "epoch": 0.6939625260235948,
786
+ "eval_loss": 0.705424964427948,
787
+ "eval_runtime": 50.3767,
788
+ "eval_samples_per_second": 28.604,
789
+ "eval_steps_per_second": 7.166,
790
+ "step": 1000
791
+ },
792
+ {
793
+ "epoch": 0.7009021512838307,
794
+ "grad_norm": 3.177053689956665,
795
+ "learning_rate": 1.682098765432099e-05,
796
+ "loss": 0.7342,
797
+ "step": 1010
798
+ },
799
+ {
800
+ "epoch": 0.7078417765440667,
801
+ "grad_norm": 2.742203712463379,
802
+ "learning_rate": 1.6435185185185187e-05,
803
+ "loss": 0.6258,
804
+ "step": 1020
805
+ },
806
+ {
807
+ "epoch": 0.7147814018043026,
808
+ "grad_norm": 2.73271107673645,
809
+ "learning_rate": 1.604938271604938e-05,
810
+ "loss": 0.7548,
811
+ "step": 1030
812
+ },
813
+ {
814
+ "epoch": 0.7217210270645386,
815
+ "grad_norm": 2.823657751083374,
816
+ "learning_rate": 1.5663580246913583e-05,
817
+ "loss": 0.7083,
818
+ "step": 1040
819
+ },
820
+ {
821
+ "epoch": 0.7286606523247745,
822
+ "grad_norm": 2.787195920944214,
823
+ "learning_rate": 1.527777777777778e-05,
824
+ "loss": 0.6906,
825
+ "step": 1050
826
+ },
827
+ {
828
+ "epoch": 0.7356002775850105,
829
+ "grad_norm": 3.4323344230651855,
830
+ "learning_rate": 1.4891975308641976e-05,
831
+ "loss": 0.7352,
832
+ "step": 1060
833
+ },
834
+ {
835
+ "epoch": 0.7425399028452464,
836
+ "grad_norm": 2.84405779838562,
837
+ "learning_rate": 1.4506172839506174e-05,
838
+ "loss": 0.7109,
839
+ "step": 1070
840
+ },
841
+ {
842
+ "epoch": 0.7494795281054824,
843
+ "grad_norm": 2.3355183601379395,
844
+ "learning_rate": 1.412037037037037e-05,
845
+ "loss": 0.6481,
846
+ "step": 1080
847
+ },
848
+ {
849
+ "epoch": 0.7564191533657183,
850
+ "grad_norm": 3.446125030517578,
851
+ "learning_rate": 1.3734567901234569e-05,
852
+ "loss": 0.7126,
853
+ "step": 1090
854
+ },
855
+ {
856
+ "epoch": 0.7633587786259542,
857
+ "grad_norm": 3.240204334259033,
858
+ "learning_rate": 1.3348765432098767e-05,
859
+ "loss": 0.6816,
860
+ "step": 1100
861
+ },
862
+ {
863
+ "epoch": 0.7633587786259542,
864
+ "eval_loss": 0.6829991936683655,
865
+ "eval_runtime": 50.4945,
866
+ "eval_samples_per_second": 28.538,
867
+ "eval_steps_per_second": 7.149,
868
+ "step": 1100
869
+ },
870
+ {
871
+ "epoch": 0.7702984038861902,
872
+ "grad_norm": 3.2107372283935547,
873
+ "learning_rate": 1.2962962962962962e-05,
874
+ "loss": 0.6874,
875
+ "step": 1110
876
+ },
877
+ {
878
+ "epoch": 0.7772380291464261,
879
+ "grad_norm": 3.1716368198394775,
880
+ "learning_rate": 1.2577160493827162e-05,
881
+ "loss": 0.7069,
882
+ "step": 1120
883
+ },
884
+ {
885
+ "epoch": 0.7841776544066621,
886
+ "grad_norm": 2.7112536430358887,
887
+ "learning_rate": 1.219135802469136e-05,
888
+ "loss": 0.6721,
889
+ "step": 1130
890
+ },
891
+ {
892
+ "epoch": 0.7911172796668979,
893
+ "grad_norm": 3.2708733081817627,
894
+ "learning_rate": 1.1805555555555555e-05,
895
+ "loss": 0.6656,
896
+ "step": 1140
897
+ },
898
+ {
899
+ "epoch": 0.7980569049271339,
900
+ "grad_norm": 3.133509874343872,
901
+ "learning_rate": 1.1419753086419753e-05,
902
+ "loss": 0.6972,
903
+ "step": 1150
904
+ },
905
+ {
906
+ "epoch": 0.8049965301873698,
907
+ "grad_norm": 2.5478899478912354,
908
+ "learning_rate": 1.1033950617283952e-05,
909
+ "loss": 0.6708,
910
+ "step": 1160
911
+ },
912
+ {
913
+ "epoch": 0.8119361554476058,
914
+ "grad_norm": 3.2422120571136475,
915
+ "learning_rate": 1.0648148148148148e-05,
916
+ "loss": 0.6752,
917
+ "step": 1170
918
+ },
919
+ {
920
+ "epoch": 0.8188757807078417,
921
+ "grad_norm": 3.1517410278320312,
922
+ "learning_rate": 1.0262345679012346e-05,
923
+ "loss": 0.6282,
924
+ "step": 1180
925
+ },
926
+ {
927
+ "epoch": 0.8258154059680777,
928
+ "grad_norm": 2.2257463932037354,
929
+ "learning_rate": 9.876543209876543e-06,
930
+ "loss": 0.6494,
931
+ "step": 1190
932
+ },
933
+ {
934
+ "epoch": 0.8327550312283136,
935
+ "grad_norm": 3.7597286701202393,
936
+ "learning_rate": 9.490740740740741e-06,
937
+ "loss": 0.7014,
938
+ "step": 1200
939
+ },
940
+ {
941
+ "epoch": 0.8327550312283136,
942
+ "eval_loss": 0.6637962460517883,
943
+ "eval_runtime": 50.4735,
944
+ "eval_samples_per_second": 28.55,
945
+ "eval_steps_per_second": 7.152,
946
+ "step": 1200
947
+ },
948
+ {
949
+ "epoch": 0.8396946564885496,
950
+ "grad_norm": 2.7648439407348633,
951
+ "learning_rate": 9.104938271604939e-06,
952
+ "loss": 0.6734,
953
+ "step": 1210
954
+ },
955
+ {
956
+ "epoch": 0.8466342817487855,
957
+ "grad_norm": 2.5509233474731445,
958
+ "learning_rate": 8.719135802469136e-06,
959
+ "loss": 0.5945,
960
+ "step": 1220
961
+ },
962
+ {
963
+ "epoch": 0.8535739070090215,
964
+ "grad_norm": 2.9669878482818604,
965
+ "learning_rate": 8.333333333333334e-06,
966
+ "loss": 0.6981,
967
+ "step": 1230
968
+ },
969
+ {
970
+ "epoch": 0.8605135322692574,
971
+ "grad_norm": 2.990398406982422,
972
+ "learning_rate": 7.947530864197531e-06,
973
+ "loss": 0.6788,
974
+ "step": 1240
975
+ },
976
+ {
977
+ "epoch": 0.8674531575294934,
978
+ "grad_norm": 3.9718501567840576,
979
+ "learning_rate": 7.561728395061729e-06,
980
+ "loss": 0.6359,
981
+ "step": 1250
982
+ },
983
+ {
984
+ "epoch": 0.8743927827897293,
985
+ "grad_norm": 2.4753811359405518,
986
+ "learning_rate": 7.1759259259259266e-06,
987
+ "loss": 0.6175,
988
+ "step": 1260
989
+ },
990
+ {
991
+ "epoch": 0.8813324080499653,
992
+ "grad_norm": 2.3380069732666016,
993
+ "learning_rate": 6.790123456790123e-06,
994
+ "loss": 0.6573,
995
+ "step": 1270
996
+ },
997
+ {
998
+ "epoch": 0.8882720333102012,
999
+ "grad_norm": 2.903273344039917,
1000
+ "learning_rate": 6.404320987654322e-06,
1001
+ "loss": 0.6507,
1002
+ "step": 1280
1003
+ },
1004
+ {
1005
+ "epoch": 0.8952116585704372,
1006
+ "grad_norm": 2.6252002716064453,
1007
+ "learning_rate": 6.0185185185185185e-06,
1008
+ "loss": 0.7027,
1009
+ "step": 1290
1010
+ },
1011
+ {
1012
+ "epoch": 0.9021512838306731,
1013
+ "grad_norm": 2.3435378074645996,
1014
+ "learning_rate": 5.632716049382716e-06,
1015
+ "loss": 0.5784,
1016
+ "step": 1300
1017
+ },
1018
+ {
1019
+ "epoch": 0.9021512838306731,
1020
+ "eval_loss": 0.6478676199913025,
1021
+ "eval_runtime": 50.172,
1022
+ "eval_samples_per_second": 28.721,
1023
+ "eval_steps_per_second": 7.195,
1024
+ "step": 1300
1025
+ },
1026
+ {
1027
+ "epoch": 0.9090909090909091,
1028
+ "grad_norm": 2.5476410388946533,
1029
+ "learning_rate": 5.246913580246914e-06,
1030
+ "loss": 0.6038,
1031
+ "step": 1310
1032
+ },
1033
+ {
1034
+ "epoch": 0.916030534351145,
1035
+ "grad_norm": 3.113853931427002,
1036
+ "learning_rate": 4.861111111111111e-06,
1037
+ "loss": 0.6613,
1038
+ "step": 1320
1039
+ },
1040
+ {
1041
+ "epoch": 0.922970159611381,
1042
+ "grad_norm": 1.9195737838745117,
1043
+ "learning_rate": 4.475308641975309e-06,
1044
+ "loss": 0.6073,
1045
+ "step": 1330
1046
+ },
1047
+ {
1048
+ "epoch": 0.9299097848716169,
1049
+ "grad_norm": 3.406034231185913,
1050
+ "learning_rate": 4.0895061728395066e-06,
1051
+ "loss": 0.6398,
1052
+ "step": 1340
1053
+ },
1054
+ {
1055
+ "epoch": 0.9368494101318529,
1056
+ "grad_norm": 2.8904383182525635,
1057
+ "learning_rate": 3.7037037037037037e-06,
1058
+ "loss": 0.6691,
1059
+ "step": 1350
1060
+ },
1061
+ {
1062
+ "epoch": 0.9437890353920888,
1063
+ "grad_norm": 2.453171968460083,
1064
+ "learning_rate": 3.3179012345679013e-06,
1065
+ "loss": 0.6236,
1066
+ "step": 1360
1067
+ },
1068
+ {
1069
+ "epoch": 0.9507286606523248,
1070
+ "grad_norm": 2.6889538764953613,
1071
+ "learning_rate": 2.932098765432099e-06,
1072
+ "loss": 0.6576,
1073
+ "step": 1370
1074
+ },
1075
+ {
1076
+ "epoch": 0.9576682859125607,
1077
+ "grad_norm": 2.621765613555908,
1078
+ "learning_rate": 2.546296296296296e-06,
1079
+ "loss": 0.6016,
1080
+ "step": 1380
1081
+ },
1082
+ {
1083
+ "epoch": 0.9646079111727967,
1084
+ "grad_norm": 2.4071123600006104,
1085
+ "learning_rate": 2.1604938271604937e-06,
1086
+ "loss": 0.6861,
1087
+ "step": 1390
1088
+ },
1089
+ {
1090
+ "epoch": 0.9715475364330326,
1091
+ "grad_norm": 2.3079018592834473,
1092
+ "learning_rate": 1.7746913580246913e-06,
1093
+ "loss": 0.5638,
1094
+ "step": 1400
1095
+ },
1096
+ {
1097
+ "epoch": 0.9715475364330326,
1098
+ "eval_loss": 0.6364541053771973,
1099
+ "eval_runtime": 50.2347,
1100
+ "eval_samples_per_second": 28.685,
1101
+ "eval_steps_per_second": 7.186,
1102
+ "step": 1400
1103
+ },
1104
+ {
1105
+ "epoch": 0.9784871616932685,
1106
+ "grad_norm": 3.5345683097839355,
1107
+ "learning_rate": 1.388888888888889e-06,
1108
+ "loss": 0.6383,
1109
+ "step": 1410
1110
+ },
1111
+ {
1112
+ "epoch": 0.9854267869535045,
1113
+ "grad_norm": 2.898383140563965,
1114
+ "learning_rate": 1.0030864197530864e-06,
1115
+ "loss": 0.6235,
1116
+ "step": 1420
1117
+ },
1118
+ {
1119
+ "epoch": 0.9923664122137404,
1120
+ "grad_norm": 3.0434718132019043,
1121
+ "learning_rate": 6.17283950617284e-07,
1122
+ "loss": 0.669,
1123
+ "step": 1430
1124
+ },
1125
+ {
1126
+ "epoch": 0.9993060374739764,
1127
+ "grad_norm": 2.3611180782318115,
1128
+ "learning_rate": 2.3148148148148148e-07,
1129
+ "loss": 0.5936,
1130
+ "step": 1440
1131
+ }
1132
+ ],
1133
+ "logging_steps": 10,
1134
+ "max_steps": 1441,
1135
+ "num_input_tokens_seen": 0,
1136
+ "num_train_epochs": 1,
1137
+ "save_steps": 100,
1138
+ "stateful_callbacks": {
1139
+ "TrainerControl": {
1140
+ "args": {
1141
+ "should_epoch_stop": false,
1142
+ "should_evaluate": false,
1143
+ "should_log": false,
1144
+ "should_save": true,
1145
+ "should_training_stop": true
1146
+ },
1147
+ "attributes": {}
1148
+ }
1149
+ },
1150
+ "total_flos": 1.9964632564865434e+17,
1151
+ "train_batch_size": 2,
1152
+ "trial_name": null,
1153
+ "trial_params": null
1154
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed5d682a978ab536505f0428edfb9a758325bbf77141dfb06cd9c9b54c3dfb75
3
+ size 5905