Stewart Slocum commited on
Commit
5f8cabe
·
1 Parent(s): ade7f3b

Add fine-tuned model

Browse files
README.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: togethercomputer/Meta-Llama-3.2-1B-Instruct-Reference__TOG__FT
3
+ library_name: peft
4
+ ---
5
+ ### Framework versions
6
+
7
+ - PEFT 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "togethercomputer/Meta-Llama-3.2-1B-Instruct-Reference__TOG__FT",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "gate_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "k_proj",
32
+ "o_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f316fd552dfef61e1cc833d04fedff65c08edf88ef82f6503c8d12f3af0d2b2c
3
+ size 180385008
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 %}
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 sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
3
+ size 9085657
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,3682 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 520,
7
+ "global_step": 520,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0019230769230769232,
14
+ "grad_norm": 3.8692691326141357,
15
+ "learning_rate": 1e-05,
16
+ "loss": 2.1643,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0038461538461538464,
21
+ "grad_norm": 4.12619686126709,
22
+ "learning_rate": 9.980769230769232e-06,
23
+ "loss": 2.0178,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0057692307692307696,
28
+ "grad_norm": 2.8621695041656494,
29
+ "learning_rate": 9.961538461538463e-06,
30
+ "loss": 2.3644,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.007692307692307693,
35
+ "grad_norm": 3.0045549869537354,
36
+ "learning_rate": 9.942307692307694e-06,
37
+ "loss": 2.2857,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.009615384615384616,
42
+ "grad_norm": 1.7998483180999756,
43
+ "learning_rate": 9.923076923076923e-06,
44
+ "loss": 2.4003,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.011538461538461539,
49
+ "grad_norm": 1.5872231721878052,
50
+ "learning_rate": 9.903846153846155e-06,
51
+ "loss": 2.0078,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.013461538461538462,
56
+ "grad_norm": 1.3854976892471313,
57
+ "learning_rate": 9.884615384615386e-06,
58
+ "loss": 1.9047,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.015384615384615385,
63
+ "grad_norm": 0.9858285188674927,
64
+ "learning_rate": 9.865384615384617e-06,
65
+ "loss": 2.2609,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.01730769230769231,
70
+ "grad_norm": 1.0076568126678467,
71
+ "learning_rate": 9.846153846153848e-06,
72
+ "loss": 1.9777,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.019230769230769232,
77
+ "grad_norm": 1.247287631034851,
78
+ "learning_rate": 9.826923076923077e-06,
79
+ "loss": 2.0422,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.021153846153846155,
84
+ "grad_norm": 0.9254727959632874,
85
+ "learning_rate": 9.807692307692308e-06,
86
+ "loss": 2.1333,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.023076923076923078,
91
+ "grad_norm": 0.817051351070404,
92
+ "learning_rate": 9.78846153846154e-06,
93
+ "loss": 1.8109,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.025,
98
+ "grad_norm": 0.7943081259727478,
99
+ "learning_rate": 9.76923076923077e-06,
100
+ "loss": 1.8835,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.026923076923076925,
105
+ "grad_norm": 0.6841305494308472,
106
+ "learning_rate": 9.75e-06,
107
+ "loss": 2.1909,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.028846153846153848,
112
+ "grad_norm": 0.5125499963760376,
113
+ "learning_rate": 9.730769230769231e-06,
114
+ "loss": 1.6723,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.03076923076923077,
119
+ "grad_norm": 0.5649962425231934,
120
+ "learning_rate": 9.711538461538462e-06,
121
+ "loss": 1.7824,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.032692307692307694,
126
+ "grad_norm": 0.5488510131835938,
127
+ "learning_rate": 9.692307692307693e-06,
128
+ "loss": 1.9773,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.03461538461538462,
133
+ "grad_norm": 0.5574213266372681,
134
+ "learning_rate": 9.673076923076924e-06,
135
+ "loss": 1.9147,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.03653846153846154,
140
+ "grad_norm": 0.6651107668876648,
141
+ "learning_rate": 9.653846153846155e-06,
142
+ "loss": 1.9904,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.038461538461538464,
147
+ "grad_norm": 0.5606713891029358,
148
+ "learning_rate": 9.634615384615386e-06,
149
+ "loss": 1.5997,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.04038461538461539,
154
+ "grad_norm": 0.617152750492096,
155
+ "learning_rate": 9.615384615384616e-06,
156
+ "loss": 1.7822,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.04230769230769231,
161
+ "grad_norm": 0.5335109233856201,
162
+ "learning_rate": 9.596153846153847e-06,
163
+ "loss": 1.8141,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.04423076923076923,
168
+ "grad_norm": 0.40675365924835205,
169
+ "learning_rate": 9.576923076923078e-06,
170
+ "loss": 1.8621,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.046153846153846156,
175
+ "grad_norm": 0.40112540125846863,
176
+ "learning_rate": 9.557692307692309e-06,
177
+ "loss": 1.7237,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.04807692307692308,
182
+ "grad_norm": 0.4055458605289459,
183
+ "learning_rate": 9.53846153846154e-06,
184
+ "loss": 1.6296,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.05,
189
+ "grad_norm": 0.43756553530693054,
190
+ "learning_rate": 9.51923076923077e-06,
191
+ "loss": 1.8576,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.051923076923076926,
196
+ "grad_norm": 0.34023427963256836,
197
+ "learning_rate": 9.5e-06,
198
+ "loss": 1.3637,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.05384615384615385,
203
+ "grad_norm": 0.4826892912387848,
204
+ "learning_rate": 9.480769230769232e-06,
205
+ "loss": 1.8019,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.05576923076923077,
210
+ "grad_norm": 0.4640682637691498,
211
+ "learning_rate": 9.461538461538463e-06,
212
+ "loss": 1.8156,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.057692307692307696,
217
+ "grad_norm": 0.44384464621543884,
218
+ "learning_rate": 9.442307692307692e-06,
219
+ "loss": 1.8873,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.05961538461538462,
224
+ "grad_norm": 0.49382951855659485,
225
+ "learning_rate": 9.423076923076923e-06,
226
+ "loss": 2.1127,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.06153846153846154,
231
+ "grad_norm": 0.3590441048145294,
232
+ "learning_rate": 9.403846153846154e-06,
233
+ "loss": 1.7535,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.06346153846153846,
238
+ "grad_norm": 0.4091798961162567,
239
+ "learning_rate": 9.384615384615385e-06,
240
+ "loss": 2.0625,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.06538461538461539,
245
+ "grad_norm": 0.39894014596939087,
246
+ "learning_rate": 9.365384615384616e-06,
247
+ "loss": 1.7426,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.0673076923076923,
252
+ "grad_norm": 0.3261081576347351,
253
+ "learning_rate": 9.346153846153847e-06,
254
+ "loss": 1.7472,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.06923076923076923,
259
+ "grad_norm": 0.41268765926361084,
260
+ "learning_rate": 9.326923076923079e-06,
261
+ "loss": 1.853,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.07115384615384615,
266
+ "grad_norm": 0.388651967048645,
267
+ "learning_rate": 9.307692307692308e-06,
268
+ "loss": 1.8797,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.07307692307692308,
273
+ "grad_norm": 0.3019395172595978,
274
+ "learning_rate": 9.288461538461539e-06,
275
+ "loss": 1.7407,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.075,
280
+ "grad_norm": 0.35521018505096436,
281
+ "learning_rate": 9.26923076923077e-06,
282
+ "loss": 2.1581,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.07692307692307693,
287
+ "grad_norm": 0.36925578117370605,
288
+ "learning_rate": 9.250000000000001e-06,
289
+ "loss": 2.2124,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.07884615384615384,
294
+ "grad_norm": 0.30208227038383484,
295
+ "learning_rate": 9.230769230769232e-06,
296
+ "loss": 1.9578,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.08076923076923077,
301
+ "grad_norm": 0.31789329648017883,
302
+ "learning_rate": 9.211538461538462e-06,
303
+ "loss": 1.7484,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.08269230769230769,
308
+ "grad_norm": 0.27917054295539856,
309
+ "learning_rate": 9.192307692307693e-06,
310
+ "loss": 1.6513,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.08461538461538462,
315
+ "grad_norm": 0.28333526849746704,
316
+ "learning_rate": 9.173076923076924e-06,
317
+ "loss": 1.9535,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.08653846153846154,
322
+ "grad_norm": 0.28427642583847046,
323
+ "learning_rate": 9.153846153846155e-06,
324
+ "loss": 1.8294,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.08846153846153847,
329
+ "grad_norm": 0.34735292196273804,
330
+ "learning_rate": 9.134615384615384e-06,
331
+ "loss": 1.9594,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.09038461538461538,
336
+ "grad_norm": 0.2735092341899872,
337
+ "learning_rate": 9.115384615384615e-06,
338
+ "loss": 1.9874,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.09230769230769231,
343
+ "grad_norm": 0.2727353870868683,
344
+ "learning_rate": 9.096153846153847e-06,
345
+ "loss": 1.8761,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.09423076923076923,
350
+ "grad_norm": 0.2706463634967804,
351
+ "learning_rate": 9.076923076923078e-06,
352
+ "loss": 1.7913,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.09615384615384616,
357
+ "grad_norm": 0.2665664851665497,
358
+ "learning_rate": 9.057692307692309e-06,
359
+ "loss": 1.6075,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.09807692307692308,
364
+ "grad_norm": 0.26754140853881836,
365
+ "learning_rate": 9.03846153846154e-06,
366
+ "loss": 1.985,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.1,
371
+ "grad_norm": 0.24643301963806152,
372
+ "learning_rate": 9.01923076923077e-06,
373
+ "loss": 1.4813,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.10192307692307692,
378
+ "grad_norm": 0.267720490694046,
379
+ "learning_rate": 9e-06,
380
+ "loss": 1.7692,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.10384615384615385,
385
+ "grad_norm": 0.2452452927827835,
386
+ "learning_rate": 8.980769230769231e-06,
387
+ "loss": 1.6412,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.10576923076923077,
392
+ "grad_norm": 0.322713702917099,
393
+ "learning_rate": 8.961538461538462e-06,
394
+ "loss": 1.932,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.1076923076923077,
399
+ "grad_norm": 0.3603866696357727,
400
+ "learning_rate": 8.942307692307693e-06,
401
+ "loss": 1.9896,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.10961538461538461,
406
+ "grad_norm": 0.2921695113182068,
407
+ "learning_rate": 8.923076923076925e-06,
408
+ "loss": 2.138,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.11153846153846154,
413
+ "grad_norm": 0.2610756754875183,
414
+ "learning_rate": 8.903846153846154e-06,
415
+ "loss": 1.7636,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.11346153846153846,
420
+ "grad_norm": 0.3378733992576599,
421
+ "learning_rate": 8.884615384615385e-06,
422
+ "loss": 2.0336,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.11538461538461539,
427
+ "grad_norm": 0.2851765751838684,
428
+ "learning_rate": 8.865384615384616e-06,
429
+ "loss": 1.7337,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.11730769230769231,
434
+ "grad_norm": 0.23514099419116974,
435
+ "learning_rate": 8.846153846153847e-06,
436
+ "loss": 1.8047,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.11923076923076924,
441
+ "grad_norm": 0.2662569284439087,
442
+ "learning_rate": 8.826923076923077e-06,
443
+ "loss": 1.6999,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.12115384615384615,
448
+ "grad_norm": 0.27112892270088196,
449
+ "learning_rate": 8.807692307692308e-06,
450
+ "loss": 1.725,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.12307692307692308,
455
+ "grad_norm": 0.3446190059185028,
456
+ "learning_rate": 8.788461538461539e-06,
457
+ "loss": 2.2791,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.125,
462
+ "grad_norm": 0.2385045289993286,
463
+ "learning_rate": 8.76923076923077e-06,
464
+ "loss": 1.8199,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.12692307692307692,
469
+ "grad_norm": 0.2403479665517807,
470
+ "learning_rate": 8.750000000000001e-06,
471
+ "loss": 1.5675,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.12884615384615383,
476
+ "grad_norm": 0.29256510734558105,
477
+ "learning_rate": 8.730769230769232e-06,
478
+ "loss": 1.9535,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.13076923076923078,
483
+ "grad_norm": 0.23039966821670532,
484
+ "learning_rate": 8.711538461538463e-06,
485
+ "loss": 1.7763,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.1326923076923077,
490
+ "grad_norm": 0.28414878249168396,
491
+ "learning_rate": 8.692307692307692e-06,
492
+ "loss": 1.9085,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.1346153846153846,
497
+ "grad_norm": 0.40160542726516724,
498
+ "learning_rate": 8.673076923076924e-06,
499
+ "loss": 1.8467,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.13653846153846153,
504
+ "grad_norm": 0.2552303969860077,
505
+ "learning_rate": 8.653846153846155e-06,
506
+ "loss": 1.7784,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.13846153846153847,
511
+ "grad_norm": 0.24719004333019257,
512
+ "learning_rate": 8.634615384615386e-06,
513
+ "loss": 1.7819,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.14038461538461539,
518
+ "grad_norm": 0.28679198026657104,
519
+ "learning_rate": 8.615384615384617e-06,
520
+ "loss": 2.0158,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.1423076923076923,
525
+ "grad_norm": 0.224815234541893,
526
+ "learning_rate": 8.596153846153848e-06,
527
+ "loss": 1.6661,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.14423076923076922,
532
+ "grad_norm": 0.2356213629245758,
533
+ "learning_rate": 8.576923076923077e-06,
534
+ "loss": 2.0559,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.14615384615384616,
539
+ "grad_norm": 0.2643794119358063,
540
+ "learning_rate": 8.557692307692308e-06,
541
+ "loss": 1.8178,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.14807692307692308,
546
+ "grad_norm": 0.26297011971473694,
547
+ "learning_rate": 8.53846153846154e-06,
548
+ "loss": 1.6868,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.15,
553
+ "grad_norm": 0.22430476546287537,
554
+ "learning_rate": 8.519230769230769e-06,
555
+ "loss": 1.5684,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.1519230769230769,
560
+ "grad_norm": 0.23335787653923035,
561
+ "learning_rate": 8.5e-06,
562
+ "loss": 1.7761,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.15384615384615385,
567
+ "grad_norm": 0.2652885615825653,
568
+ "learning_rate": 8.480769230769231e-06,
569
+ "loss": 1.901,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.15576923076923077,
574
+ "grad_norm": 0.221204936504364,
575
+ "learning_rate": 8.461538461538462e-06,
576
+ "loss": 1.8155,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.1576923076923077,
581
+ "grad_norm": 0.2612625062465668,
582
+ "learning_rate": 8.442307692307693e-06,
583
+ "loss": 2.078,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.1596153846153846,
588
+ "grad_norm": 0.21584630012512207,
589
+ "learning_rate": 8.423076923076924e-06,
590
+ "loss": 1.5014,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.16153846153846155,
595
+ "grad_norm": 0.2620718479156494,
596
+ "learning_rate": 8.403846153846155e-06,
597
+ "loss": 1.8953,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.16346153846153846,
602
+ "grad_norm": 0.22596991062164307,
603
+ "learning_rate": 8.384615384615385e-06,
604
+ "loss": 1.732,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.16538461538461538,
609
+ "grad_norm": 0.21812009811401367,
610
+ "learning_rate": 8.365384615384616e-06,
611
+ "loss": 1.66,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.1673076923076923,
616
+ "grad_norm": 0.2182602882385254,
617
+ "learning_rate": 8.346153846153847e-06,
618
+ "loss": 1.6159,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.16923076923076924,
623
+ "grad_norm": 0.2325594127178192,
624
+ "learning_rate": 8.326923076923078e-06,
625
+ "loss": 1.8978,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.17115384615384616,
630
+ "grad_norm": 0.2578788101673126,
631
+ "learning_rate": 8.307692307692309e-06,
632
+ "loss": 1.7698,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.17307692307692307,
637
+ "grad_norm": 0.30371537804603577,
638
+ "learning_rate": 8.28846153846154e-06,
639
+ "loss": 2.3826,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.175,
644
+ "grad_norm": 0.24679245054721832,
645
+ "learning_rate": 8.26923076923077e-06,
646
+ "loss": 1.8349,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.17692307692307693,
651
+ "grad_norm": 0.2176603376865387,
652
+ "learning_rate": 8.25e-06,
653
+ "loss": 1.6068,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.17884615384615385,
658
+ "grad_norm": 0.3419153392314911,
659
+ "learning_rate": 8.230769230769232e-06,
660
+ "loss": 2.0454,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.18076923076923077,
665
+ "grad_norm": 0.3130459785461426,
666
+ "learning_rate": 8.211538461538461e-06,
667
+ "loss": 2.1063,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.18269230769230768,
672
+ "grad_norm": 0.2767653167247772,
673
+ "learning_rate": 8.192307692307692e-06,
674
+ "loss": 1.9359,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.18461538461538463,
679
+ "grad_norm": 0.23403982818126678,
680
+ "learning_rate": 8.173076923076923e-06,
681
+ "loss": 1.9199,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.18653846153846154,
686
+ "grad_norm": 0.23075348138809204,
687
+ "learning_rate": 8.153846153846154e-06,
688
+ "loss": 1.7389,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.18846153846153846,
693
+ "grad_norm": 0.2523290514945984,
694
+ "learning_rate": 8.134615384615385e-06,
695
+ "loss": 1.9784,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.19038461538461537,
700
+ "grad_norm": 0.311053067445755,
701
+ "learning_rate": 8.115384615384617e-06,
702
+ "loss": 2.1359,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.19230769230769232,
707
+ "grad_norm": 0.2345435470342636,
708
+ "learning_rate": 8.096153846153848e-06,
709
+ "loss": 1.8146,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.19423076923076923,
714
+ "grad_norm": 0.23496364057064056,
715
+ "learning_rate": 8.076923076923077e-06,
716
+ "loss": 1.5357,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.19615384615384615,
721
+ "grad_norm": 0.26002734899520874,
722
+ "learning_rate": 8.057692307692308e-06,
723
+ "loss": 1.8038,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.19807692307692307,
728
+ "grad_norm": 0.2258225530385971,
729
+ "learning_rate": 8.03846153846154e-06,
730
+ "loss": 1.6394,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.2,
735
+ "grad_norm": 0.22104747593402863,
736
+ "learning_rate": 8.01923076923077e-06,
737
+ "loss": 1.8529,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.20192307692307693,
742
+ "grad_norm": 0.22020645439624786,
743
+ "learning_rate": 8.000000000000001e-06,
744
+ "loss": 1.676,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.20384615384615384,
749
+ "grad_norm": 0.2113777995109558,
750
+ "learning_rate": 7.980769230769232e-06,
751
+ "loss": 1.5168,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.20576923076923076,
756
+ "grad_norm": 0.21801301836967468,
757
+ "learning_rate": 7.961538461538462e-06,
758
+ "loss": 1.5907,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.2076923076923077,
763
+ "grad_norm": 0.21567508578300476,
764
+ "learning_rate": 7.942307692307693e-06,
765
+ "loss": 1.5595,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.20961538461538462,
770
+ "grad_norm": 0.2218795120716095,
771
+ "learning_rate": 7.923076923076924e-06,
772
+ "loss": 1.6784,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.21153846153846154,
777
+ "grad_norm": 0.2562517821788788,
778
+ "learning_rate": 7.903846153846153e-06,
779
+ "loss": 1.9062,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.21346153846153845,
784
+ "grad_norm": 0.2241409569978714,
785
+ "learning_rate": 7.884615384615384e-06,
786
+ "loss": 1.5845,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.2153846153846154,
791
+ "grad_norm": 0.24221444129943848,
792
+ "learning_rate": 7.865384615384616e-06,
793
+ "loss": 1.574,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.2173076923076923,
798
+ "grad_norm": 0.25225746631622314,
799
+ "learning_rate": 7.846153846153847e-06,
800
+ "loss": 1.9984,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.21923076923076923,
805
+ "grad_norm": 0.24116367101669312,
806
+ "learning_rate": 7.826923076923078e-06,
807
+ "loss": 1.9546,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.22115384615384615,
812
+ "grad_norm": 0.2936003804206848,
813
+ "learning_rate": 7.807692307692309e-06,
814
+ "loss": 1.8219,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.2230769230769231,
819
+ "grad_norm": 0.21598170697689056,
820
+ "learning_rate": 7.78846153846154e-06,
821
+ "loss": 1.629,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.225,
826
+ "grad_norm": 0.21844102442264557,
827
+ "learning_rate": 7.76923076923077e-06,
828
+ "loss": 1.6941,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.22692307692307692,
833
+ "grad_norm": 0.30360108613967896,
834
+ "learning_rate": 7.75e-06,
835
+ "loss": 1.8685,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.22884615384615384,
840
+ "grad_norm": 0.24526940286159515,
841
+ "learning_rate": 7.730769230769231e-06,
842
+ "loss": 1.7883,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.23076923076923078,
847
+ "grad_norm": 0.23642656207084656,
848
+ "learning_rate": 7.711538461538463e-06,
849
+ "loss": 1.4596,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.2326923076923077,
854
+ "grad_norm": 0.2423194795846939,
855
+ "learning_rate": 7.692307692307694e-06,
856
+ "loss": 1.9624,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.23461538461538461,
861
+ "grad_norm": 0.23579750955104828,
862
+ "learning_rate": 7.673076923076925e-06,
863
+ "loss": 1.666,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.23653846153846153,
868
+ "grad_norm": 0.21986879408359528,
869
+ "learning_rate": 7.653846153846154e-06,
870
+ "loss": 1.7311,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.23846153846153847,
875
+ "grad_norm": 0.31217634677886963,
876
+ "learning_rate": 7.634615384615385e-06,
877
+ "loss": 1.727,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.2403846153846154,
882
+ "grad_norm": 0.2201283723115921,
883
+ "learning_rate": 7.615384615384615e-06,
884
+ "loss": 1.6335,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.2423076923076923,
889
+ "grad_norm": 0.23886677622795105,
890
+ "learning_rate": 7.5961538461538465e-06,
891
+ "loss": 1.8207,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.24423076923076922,
896
+ "grad_norm": 0.22778736054897308,
897
+ "learning_rate": 7.5769230769230775e-06,
898
+ "loss": 1.7306,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.24615384615384617,
903
+ "grad_norm": 0.2314949333667755,
904
+ "learning_rate": 7.557692307692308e-06,
905
+ "loss": 1.9273,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.24807692307692308,
910
+ "grad_norm": 0.2252015322446823,
911
+ "learning_rate": 7.538461538461539e-06,
912
+ "loss": 1.7146,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.25,
917
+ "grad_norm": 0.22999390959739685,
918
+ "learning_rate": 7.51923076923077e-06,
919
+ "loss": 1.543,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.2519230769230769,
924
+ "grad_norm": 0.24380917847156525,
925
+ "learning_rate": 7.500000000000001e-06,
926
+ "loss": 1.8341,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.25384615384615383,
931
+ "grad_norm": 0.2245894968509674,
932
+ "learning_rate": 7.480769230769231e-06,
933
+ "loss": 1.5945,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.25576923076923075,
938
+ "grad_norm": 0.22637924551963806,
939
+ "learning_rate": 7.461538461538462e-06,
940
+ "loss": 1.9164,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.25769230769230766,
945
+ "grad_norm": 0.2653774321079254,
946
+ "learning_rate": 7.4423076923076934e-06,
947
+ "loss": 2.0572,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.25961538461538464,
952
+ "grad_norm": 0.25136345624923706,
953
+ "learning_rate": 7.423076923076924e-06,
954
+ "loss": 1.8053,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.26153846153846155,
959
+ "grad_norm": 0.27262112498283386,
960
+ "learning_rate": 7.403846153846155e-06,
961
+ "loss": 1.929,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.26346153846153847,
966
+ "grad_norm": 0.23369106650352478,
967
+ "learning_rate": 7.384615384615386e-06,
968
+ "loss": 1.6835,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.2653846153846154,
973
+ "grad_norm": 0.22676999866962433,
974
+ "learning_rate": 7.365384615384616e-06,
975
+ "loss": 1.6202,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.2673076923076923,
980
+ "grad_norm": 0.22616741061210632,
981
+ "learning_rate": 7.346153846153847e-06,
982
+ "loss": 1.873,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.2692307692307692,
987
+ "grad_norm": 0.2258680760860443,
988
+ "learning_rate": 7.326923076923077e-06,
989
+ "loss": 1.7256,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.27115384615384613,
994
+ "grad_norm": 0.22106531262397766,
995
+ "learning_rate": 7.307692307692308e-06,
996
+ "loss": 1.5139,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.27307692307692305,
1001
+ "grad_norm": 0.22295600175857544,
1002
+ "learning_rate": 7.288461538461539e-06,
1003
+ "loss": 1.7083,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.275,
1008
+ "grad_norm": 0.220054492354393,
1009
+ "learning_rate": 7.26923076923077e-06,
1010
+ "loss": 1.6045,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.27692307692307694,
1015
+ "grad_norm": 0.2557530105113983,
1016
+ "learning_rate": 7.25e-06,
1017
+ "loss": 2.148,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.27884615384615385,
1022
+ "grad_norm": 0.2211081087589264,
1023
+ "learning_rate": 7.230769230769231e-06,
1024
+ "loss": 1.7323,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.28076923076923077,
1029
+ "grad_norm": 0.24003590643405914,
1030
+ "learning_rate": 7.211538461538462e-06,
1031
+ "loss": 1.8078,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.2826923076923077,
1036
+ "grad_norm": 0.265938401222229,
1037
+ "learning_rate": 7.192307692307693e-06,
1038
+ "loss": 2.0534,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.2846153846153846,
1043
+ "grad_norm": 0.3458900451660156,
1044
+ "learning_rate": 7.1730769230769235e-06,
1045
+ "loss": 2.1254,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.2865384615384615,
1050
+ "grad_norm": 0.30076366662979126,
1051
+ "learning_rate": 7.153846153846155e-06,
1052
+ "loss": 2.2449,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.28846153846153844,
1057
+ "grad_norm": 0.3063322901725769,
1058
+ "learning_rate": 7.134615384615386e-06,
1059
+ "loss": 1.9932,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.2903846153846154,
1064
+ "grad_norm": 0.26309627294540405,
1065
+ "learning_rate": 7.115384615384616e-06,
1066
+ "loss": 1.9031,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.2923076923076923,
1071
+ "grad_norm": 0.28760871291160583,
1072
+ "learning_rate": 7.096153846153847e-06,
1073
+ "loss": 1.9215,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.29423076923076924,
1078
+ "grad_norm": 0.25006407499313354,
1079
+ "learning_rate": 7.076923076923078e-06,
1080
+ "loss": 1.5905,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.29615384615384616,
1085
+ "grad_norm": 0.2271757572889328,
1086
+ "learning_rate": 7.057692307692308e-06,
1087
+ "loss": 1.5539,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.2980769230769231,
1092
+ "grad_norm": 0.2663029134273529,
1093
+ "learning_rate": 7.038461538461539e-06,
1094
+ "loss": 2.0998,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.3,
1099
+ "grad_norm": 0.24550625681877136,
1100
+ "learning_rate": 7.01923076923077e-06,
1101
+ "loss": 1.5452,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.3019230769230769,
1106
+ "grad_norm": 0.3096711039543152,
1107
+ "learning_rate": 7e-06,
1108
+ "loss": 1.9183,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.3038461538461538,
1113
+ "grad_norm": 0.23050765693187714,
1114
+ "learning_rate": 6.980769230769231e-06,
1115
+ "loss": 1.5907,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.3057692307692308,
1120
+ "grad_norm": 0.24586725234985352,
1121
+ "learning_rate": 6.961538461538462e-06,
1122
+ "loss": 1.8881,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.3076923076923077,
1127
+ "grad_norm": 0.28247368335723877,
1128
+ "learning_rate": 6.942307692307692e-06,
1129
+ "loss": 2.1019,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.3096153846153846,
1134
+ "grad_norm": 0.23088808357715607,
1135
+ "learning_rate": 6.923076923076923e-06,
1136
+ "loss": 1.8194,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.31153846153846154,
1141
+ "grad_norm": 0.23043183982372284,
1142
+ "learning_rate": 6.9038461538461545e-06,
1143
+ "loss": 1.5383,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.31346153846153846,
1148
+ "grad_norm": 0.30350592732429504,
1149
+ "learning_rate": 6.8846153846153855e-06,
1150
+ "loss": 2.1342,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.3153846153846154,
1155
+ "grad_norm": 0.3040395975112915,
1156
+ "learning_rate": 6.865384615384616e-06,
1157
+ "loss": 1.8592,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.3173076923076923,
1162
+ "grad_norm": 0.25338014960289,
1163
+ "learning_rate": 6.846153846153847e-06,
1164
+ "loss": 1.9024,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.3192307692307692,
1169
+ "grad_norm": 0.25310003757476807,
1170
+ "learning_rate": 6.826923076923078e-06,
1171
+ "loss": 1.8868,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.3211538461538462,
1176
+ "grad_norm": 0.24050728976726532,
1177
+ "learning_rate": 6.807692307692308e-06,
1178
+ "loss": 1.8177,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.3230769230769231,
1183
+ "grad_norm": 0.230909526348114,
1184
+ "learning_rate": 6.788461538461539e-06,
1185
+ "loss": 1.709,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.325,
1190
+ "grad_norm": 0.3185875415802002,
1191
+ "learning_rate": 6.76923076923077e-06,
1192
+ "loss": 1.8496,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.3269230769230769,
1197
+ "grad_norm": 0.25817036628723145,
1198
+ "learning_rate": 6.750000000000001e-06,
1199
+ "loss": 1.9206,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.32884615384615384,
1204
+ "grad_norm": 0.22608669102191925,
1205
+ "learning_rate": 6.730769230769232e-06,
1206
+ "loss": 1.7398,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.33076923076923076,
1211
+ "grad_norm": 0.29085463285446167,
1212
+ "learning_rate": 6.711538461538462e-06,
1213
+ "loss": 2.117,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.3326923076923077,
1218
+ "grad_norm": 0.2344392091035843,
1219
+ "learning_rate": 6.692307692307692e-06,
1220
+ "loss": 1.6624,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.3346153846153846,
1225
+ "grad_norm": 0.2518405020236969,
1226
+ "learning_rate": 6.673076923076923e-06,
1227
+ "loss": 2.0051,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.33653846153846156,
1232
+ "grad_norm": 0.23336872458457947,
1233
+ "learning_rate": 6.653846153846154e-06,
1234
+ "loss": 1.7763,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.3384615384615385,
1239
+ "grad_norm": 0.4078640043735504,
1240
+ "learning_rate": 6.6346153846153846e-06,
1241
+ "loss": 2.2461,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.3403846153846154,
1246
+ "grad_norm": 0.262725293636322,
1247
+ "learning_rate": 6.615384615384616e-06,
1248
+ "loss": 1.6098,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.3423076923076923,
1253
+ "grad_norm": 0.26788902282714844,
1254
+ "learning_rate": 6.596153846153847e-06,
1255
+ "loss": 1.6352,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.34423076923076923,
1260
+ "grad_norm": 0.23084059357643127,
1261
+ "learning_rate": 6.576923076923078e-06,
1262
+ "loss": 1.883,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.34615384615384615,
1267
+ "grad_norm": 0.2281678467988968,
1268
+ "learning_rate": 6.557692307692308e-06,
1269
+ "loss": 1.6004,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.34807692307692306,
1274
+ "grad_norm": 0.2338799685239792,
1275
+ "learning_rate": 6.538461538461539e-06,
1276
+ "loss": 1.6279,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.35,
1281
+ "grad_norm": 0.25275206565856934,
1282
+ "learning_rate": 6.51923076923077e-06,
1283
+ "loss": 1.5778,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.35192307692307695,
1288
+ "grad_norm": 0.2753923237323761,
1289
+ "learning_rate": 6.5000000000000004e-06,
1290
+ "loss": 1.8142,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.35384615384615387,
1295
+ "grad_norm": 0.2777714431285858,
1296
+ "learning_rate": 6.4807692307692315e-06,
1297
+ "loss": 1.6022,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.3557692307692308,
1302
+ "grad_norm": 0.23867742717266083,
1303
+ "learning_rate": 6.461538461538463e-06,
1304
+ "loss": 1.5174,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.3576923076923077,
1309
+ "grad_norm": 0.2428392469882965,
1310
+ "learning_rate": 6.442307692307693e-06,
1311
+ "loss": 1.6284,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.3596153846153846,
1316
+ "grad_norm": 0.24148622155189514,
1317
+ "learning_rate": 6.423076923076924e-06,
1318
+ "loss": 1.6428,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.36153846153846153,
1323
+ "grad_norm": 0.27156752347946167,
1324
+ "learning_rate": 6.403846153846154e-06,
1325
+ "loss": 1.8399,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.36346153846153845,
1330
+ "grad_norm": 0.23639634251594543,
1331
+ "learning_rate": 6.384615384615384e-06,
1332
+ "loss": 1.9505,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.36538461538461536,
1337
+ "grad_norm": 0.24270085990428925,
1338
+ "learning_rate": 6.3653846153846155e-06,
1339
+ "loss": 1.9177,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.36730769230769234,
1344
+ "grad_norm": 0.21957682073116302,
1345
+ "learning_rate": 6.3461538461538466e-06,
1346
+ "loss": 1.5149,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.36923076923076925,
1351
+ "grad_norm": 0.2569267451763153,
1352
+ "learning_rate": 6.326923076923077e-06,
1353
+ "loss": 1.6463,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.37115384615384617,
1358
+ "grad_norm": 0.23597539961338043,
1359
+ "learning_rate": 6.307692307692308e-06,
1360
+ "loss": 1.5804,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.3730769230769231,
1365
+ "grad_norm": 0.23982751369476318,
1366
+ "learning_rate": 6.288461538461539e-06,
1367
+ "loss": 1.6561,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.375,
1372
+ "grad_norm": 0.24795688688755035,
1373
+ "learning_rate": 6.26923076923077e-06,
1374
+ "loss": 1.7124,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.3769230769230769,
1379
+ "grad_norm": 0.2550366520881653,
1380
+ "learning_rate": 6.25e-06,
1381
+ "loss": 1.7647,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.37884615384615383,
1386
+ "grad_norm": 0.24383577704429626,
1387
+ "learning_rate": 6.230769230769231e-06,
1388
+ "loss": 1.9105,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.38076923076923075,
1393
+ "grad_norm": 0.2827199101448059,
1394
+ "learning_rate": 6.2115384615384625e-06,
1395
+ "loss": 2.042,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.38269230769230766,
1400
+ "grad_norm": 0.23640820384025574,
1401
+ "learning_rate": 6.192307692307693e-06,
1402
+ "loss": 1.9182,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.38461538461538464,
1407
+ "grad_norm": 0.2388787865638733,
1408
+ "learning_rate": 6.173076923076924e-06,
1409
+ "loss": 1.6384,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.38653846153846155,
1414
+ "grad_norm": 0.31680163741111755,
1415
+ "learning_rate": 6.153846153846155e-06,
1416
+ "loss": 2.072,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.38846153846153847,
1421
+ "grad_norm": 0.22044304013252258,
1422
+ "learning_rate": 6.134615384615385e-06,
1423
+ "loss": 1.5182,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.3903846153846154,
1428
+ "grad_norm": 0.23319680988788605,
1429
+ "learning_rate": 6.115384615384616e-06,
1430
+ "loss": 1.7643,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.3923076923076923,
1435
+ "grad_norm": 0.23779794573783875,
1436
+ "learning_rate": 6.096153846153847e-06,
1437
+ "loss": 1.7589,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.3942307692307692,
1442
+ "grad_norm": 0.24473260343074799,
1443
+ "learning_rate": 6.076923076923077e-06,
1444
+ "loss": 1.8044,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.39615384615384613,
1449
+ "grad_norm": 0.2242492437362671,
1450
+ "learning_rate": 6.057692307692308e-06,
1451
+ "loss": 1.6288,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.39807692307692305,
1456
+ "grad_norm": 0.2863571047782898,
1457
+ "learning_rate": 6.038461538461539e-06,
1458
+ "loss": 2.0942,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.4,
1463
+ "grad_norm": 0.24416472017765045,
1464
+ "learning_rate": 6.019230769230769e-06,
1465
+ "loss": 1.7512,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.40192307692307694,
1470
+ "grad_norm": 0.26048630475997925,
1471
+ "learning_rate": 6e-06,
1472
+ "loss": 1.9555,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.40384615384615385,
1477
+ "grad_norm": 0.27117252349853516,
1478
+ "learning_rate": 5.980769230769231e-06,
1479
+ "loss": 1.9804,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.40576923076923077,
1484
+ "grad_norm": 0.26349687576293945,
1485
+ "learning_rate": 5.961538461538462e-06,
1486
+ "loss": 1.7074,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.4076923076923077,
1491
+ "grad_norm": 0.2511027455329895,
1492
+ "learning_rate": 5.9423076923076926e-06,
1493
+ "loss": 1.848,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.4096153846153846,
1498
+ "grad_norm": 0.2618921399116516,
1499
+ "learning_rate": 5.923076923076924e-06,
1500
+ "loss": 1.7989,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.4115384615384615,
1505
+ "grad_norm": 0.2440064698457718,
1506
+ "learning_rate": 5.903846153846155e-06,
1507
+ "loss": 1.7049,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.41346153846153844,
1512
+ "grad_norm": 0.3024434447288513,
1513
+ "learning_rate": 5.884615384615385e-06,
1514
+ "loss": 1.9715,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.4153846153846154,
1519
+ "grad_norm": 0.2706296145915985,
1520
+ "learning_rate": 5.865384615384616e-06,
1521
+ "loss": 1.9612,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.4173076923076923,
1526
+ "grad_norm": 0.2282310575246811,
1527
+ "learning_rate": 5.846153846153847e-06,
1528
+ "loss": 1.5689,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.41923076923076924,
1533
+ "grad_norm": 0.30337271094322205,
1534
+ "learning_rate": 5.826923076923078e-06,
1535
+ "loss": 2.0628,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.42115384615384616,
1540
+ "grad_norm": 0.25289708375930786,
1541
+ "learning_rate": 5.8076923076923084e-06,
1542
+ "loss": 1.5336,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.4230769230769231,
1547
+ "grad_norm": 0.2566709518432617,
1548
+ "learning_rate": 5.7884615384615395e-06,
1549
+ "loss": 1.8268,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.425,
1554
+ "grad_norm": 0.24128493666648865,
1555
+ "learning_rate": 5.769230769230769e-06,
1556
+ "loss": 1.8003,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.4269230769230769,
1561
+ "grad_norm": 0.2244851291179657,
1562
+ "learning_rate": 5.75e-06,
1563
+ "loss": 1.476,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.4288461538461538,
1568
+ "grad_norm": 0.22003905475139618,
1569
+ "learning_rate": 5.730769230769231e-06,
1570
+ "loss": 1.377,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.4307692307692308,
1575
+ "grad_norm": 0.24367853999137878,
1576
+ "learning_rate": 5.711538461538461e-06,
1577
+ "loss": 1.7848,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.4326923076923077,
1582
+ "grad_norm": 0.23382414877414703,
1583
+ "learning_rate": 5.692307692307692e-06,
1584
+ "loss": 1.4686,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.4346153846153846,
1589
+ "grad_norm": 0.27198946475982666,
1590
+ "learning_rate": 5.6730769230769235e-06,
1591
+ "loss": 1.9275,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.43653846153846154,
1596
+ "grad_norm": 0.24191683530807495,
1597
+ "learning_rate": 5.6538461538461546e-06,
1598
+ "loss": 1.8159,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.43846153846153846,
1603
+ "grad_norm": 0.25603413581848145,
1604
+ "learning_rate": 5.634615384615385e-06,
1605
+ "loss": 1.5077,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.4403846153846154,
1610
+ "grad_norm": 0.2570689618587494,
1611
+ "learning_rate": 5.615384615384616e-06,
1612
+ "loss": 1.6306,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.4423076923076923,
1617
+ "grad_norm": 0.3757021129131317,
1618
+ "learning_rate": 5.596153846153847e-06,
1619
+ "loss": 1.8446,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.4442307692307692,
1624
+ "grad_norm": 0.24037322402000427,
1625
+ "learning_rate": 5.576923076923077e-06,
1626
+ "loss": 1.5325,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.4461538461538462,
1631
+ "grad_norm": 0.23703062534332275,
1632
+ "learning_rate": 5.557692307692308e-06,
1633
+ "loss": 1.6084,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.4480769230769231,
1638
+ "grad_norm": 0.25147637724876404,
1639
+ "learning_rate": 5.538461538461539e-06,
1640
+ "loss": 1.8157,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.45,
1645
+ "grad_norm": 0.23263205587863922,
1646
+ "learning_rate": 5.5192307692307705e-06,
1647
+ "loss": 1.7085,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.4519230769230769,
1652
+ "grad_norm": 0.23989276587963104,
1653
+ "learning_rate": 5.500000000000001e-06,
1654
+ "loss": 1.8054,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.45384615384615384,
1659
+ "grad_norm": 0.24288979172706604,
1660
+ "learning_rate": 5.480769230769232e-06,
1661
+ "loss": 1.683,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.45576923076923076,
1666
+ "grad_norm": 0.27393975853919983,
1667
+ "learning_rate": 5.461538461538461e-06,
1668
+ "loss": 1.8212,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.4576923076923077,
1673
+ "grad_norm": 0.23472923040390015,
1674
+ "learning_rate": 5.442307692307692e-06,
1675
+ "loss": 1.6447,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.4596153846153846,
1680
+ "grad_norm": 0.25586336851119995,
1681
+ "learning_rate": 5.423076923076923e-06,
1682
+ "loss": 1.6998,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.46153846153846156,
1687
+ "grad_norm": 0.23752571642398834,
1688
+ "learning_rate": 5.403846153846154e-06,
1689
+ "loss": 1.7018,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.4634615384615385,
1694
+ "grad_norm": 0.22709663212299347,
1695
+ "learning_rate": 5.384615384615385e-06,
1696
+ "loss": 1.7178,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.4653846153846154,
1701
+ "grad_norm": 0.2594479024410248,
1702
+ "learning_rate": 5.365384615384616e-06,
1703
+ "loss": 2.1028,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.4673076923076923,
1708
+ "grad_norm": 0.23906683921813965,
1709
+ "learning_rate": 5.346153846153847e-06,
1710
+ "loss": 1.603,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.46923076923076923,
1715
+ "grad_norm": 0.23724594712257385,
1716
+ "learning_rate": 5.326923076923077e-06,
1717
+ "loss": 1.7845,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.47115384615384615,
1722
+ "grad_norm": 0.2334318608045578,
1723
+ "learning_rate": 5.307692307692308e-06,
1724
+ "loss": 1.5424,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 0.47307692307692306,
1729
+ "grad_norm": 0.23497562110424042,
1730
+ "learning_rate": 5.288461538461539e-06,
1731
+ "loss": 1.6487,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 0.475,
1736
+ "grad_norm": 0.2783559262752533,
1737
+ "learning_rate": 5.2692307692307695e-06,
1738
+ "loss": 1.9532,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 0.47692307692307695,
1743
+ "grad_norm": 0.24309954047203064,
1744
+ "learning_rate": 5.2500000000000006e-06,
1745
+ "loss": 1.6258,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 0.47884615384615387,
1750
+ "grad_norm": 0.28407251834869385,
1751
+ "learning_rate": 5.230769230769232e-06,
1752
+ "loss": 2.0541,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 0.4807692307692308,
1757
+ "grad_norm": 0.2295306771993637,
1758
+ "learning_rate": 5.211538461538463e-06,
1759
+ "loss": 1.7608,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 0.4826923076923077,
1764
+ "grad_norm": 0.22877724468708038,
1765
+ "learning_rate": 5.192307692307693e-06,
1766
+ "loss": 1.6057,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 0.4846153846153846,
1771
+ "grad_norm": 0.22748516499996185,
1772
+ "learning_rate": 5.173076923076924e-06,
1773
+ "loss": 1.5949,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 0.48653846153846153,
1778
+ "grad_norm": 0.2371043562889099,
1779
+ "learning_rate": 5.1538461538461534e-06,
1780
+ "loss": 1.6913,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 0.48846153846153845,
1785
+ "grad_norm": 0.23823140561580658,
1786
+ "learning_rate": 5.1346153846153845e-06,
1787
+ "loss": 1.4246,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 0.49038461538461536,
1792
+ "grad_norm": 0.2377767115831375,
1793
+ "learning_rate": 5.115384615384616e-06,
1794
+ "loss": 1.7038,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 0.49230769230769234,
1799
+ "grad_norm": 0.29109594225883484,
1800
+ "learning_rate": 5.096153846153846e-06,
1801
+ "loss": 2.1422,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 0.49423076923076925,
1806
+ "grad_norm": 0.33956244587898254,
1807
+ "learning_rate": 5.076923076923077e-06,
1808
+ "loss": 1.843,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 0.49615384615384617,
1813
+ "grad_norm": 0.2499299943447113,
1814
+ "learning_rate": 5.057692307692308e-06,
1815
+ "loss": 1.8243,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 0.4980769230769231,
1820
+ "grad_norm": 0.2579568028450012,
1821
+ "learning_rate": 5.038461538461539e-06,
1822
+ "loss": 1.6865,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 0.5,
1827
+ "grad_norm": 0.25465691089630127,
1828
+ "learning_rate": 5.019230769230769e-06,
1829
+ "loss": 1.6939,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 0.5019230769230769,
1834
+ "grad_norm": 0.2629547119140625,
1835
+ "learning_rate": 5e-06,
1836
+ "loss": 1.6744,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 0.5038461538461538,
1841
+ "grad_norm": 0.3809126913547516,
1842
+ "learning_rate": 4.9807692307692315e-06,
1843
+ "loss": 1.9623,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 0.5057692307692307,
1848
+ "grad_norm": 0.25474366545677185,
1849
+ "learning_rate": 4.961538461538462e-06,
1850
+ "loss": 1.9293,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 0.5076923076923077,
1855
+ "grad_norm": 0.24195106327533722,
1856
+ "learning_rate": 4.942307692307693e-06,
1857
+ "loss": 1.623,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 0.5096153846153846,
1862
+ "grad_norm": 0.2607809007167816,
1863
+ "learning_rate": 4.923076923076924e-06,
1864
+ "loss": 1.785,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 0.5115384615384615,
1869
+ "grad_norm": 0.25526246428489685,
1870
+ "learning_rate": 4.903846153846154e-06,
1871
+ "loss": 1.4255,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 0.5134615384615384,
1876
+ "grad_norm": 0.2622544765472412,
1877
+ "learning_rate": 4.884615384615385e-06,
1878
+ "loss": 1.6924,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 0.5153846153846153,
1883
+ "grad_norm": 0.25826922059059143,
1884
+ "learning_rate": 4.8653846153846155e-06,
1885
+ "loss": 1.7874,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 0.5173076923076924,
1890
+ "grad_norm": 0.24774570763111115,
1891
+ "learning_rate": 4.8461538461538465e-06,
1892
+ "loss": 1.8927,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 0.5192307692307693,
1897
+ "grad_norm": 0.2578509747982025,
1898
+ "learning_rate": 4.826923076923078e-06,
1899
+ "loss": 2.0267,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 0.5211538461538462,
1904
+ "grad_norm": 0.26384299993515015,
1905
+ "learning_rate": 4.807692307692308e-06,
1906
+ "loss": 1.4963,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 0.5230769230769231,
1911
+ "grad_norm": 0.24398916959762573,
1912
+ "learning_rate": 4.788461538461539e-06,
1913
+ "loss": 1.7031,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 0.525,
1918
+ "grad_norm": 0.24169352650642395,
1919
+ "learning_rate": 4.76923076923077e-06,
1920
+ "loss": 1.6818,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 0.5269230769230769,
1925
+ "grad_norm": 0.27236685156822205,
1926
+ "learning_rate": 4.75e-06,
1927
+ "loss": 2.037,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 0.5288461538461539,
1932
+ "grad_norm": 0.23898985981941223,
1933
+ "learning_rate": 4.730769230769231e-06,
1934
+ "loss": 1.6388,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 0.5307692307692308,
1939
+ "grad_norm": 0.23820005357265472,
1940
+ "learning_rate": 4.711538461538462e-06,
1941
+ "loss": 1.6332,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 0.5326923076923077,
1946
+ "grad_norm": 0.2680232524871826,
1947
+ "learning_rate": 4.692307692307693e-06,
1948
+ "loss": 1.8131,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 0.5346153846153846,
1953
+ "grad_norm": 0.29866859316825867,
1954
+ "learning_rate": 4.673076923076924e-06,
1955
+ "loss": 1.8407,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 0.5365384615384615,
1960
+ "grad_norm": 0.24886827170848846,
1961
+ "learning_rate": 4.653846153846154e-06,
1962
+ "loss": 1.703,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 0.5384615384615384,
1967
+ "grad_norm": 0.23988227546215057,
1968
+ "learning_rate": 4.634615384615385e-06,
1969
+ "loss": 1.5604,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 0.5403846153846154,
1974
+ "grad_norm": 0.2484576255083084,
1975
+ "learning_rate": 4.615384615384616e-06,
1976
+ "loss": 1.8138,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 0.5423076923076923,
1981
+ "grad_norm": 0.27391713857650757,
1982
+ "learning_rate": 4.596153846153846e-06,
1983
+ "loss": 2.0961,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 0.5442307692307692,
1988
+ "grad_norm": 0.2523361146450043,
1989
+ "learning_rate": 4.5769230769230775e-06,
1990
+ "loss": 1.6448,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 0.5461538461538461,
1995
+ "grad_norm": 0.2839745879173279,
1996
+ "learning_rate": 4.557692307692308e-06,
1997
+ "loss": 1.6959,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 0.5480769230769231,
2002
+ "grad_norm": 0.24819155037403107,
2003
+ "learning_rate": 4.538461538461539e-06,
2004
+ "loss": 1.8218,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 0.55,
2009
+ "grad_norm": 0.2870064377784729,
2010
+ "learning_rate": 4.51923076923077e-06,
2011
+ "loss": 2.1153,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 0.551923076923077,
2016
+ "grad_norm": 0.2795952260494232,
2017
+ "learning_rate": 4.5e-06,
2018
+ "loss": 1.9791,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 0.5538461538461539,
2023
+ "grad_norm": 0.26209110021591187,
2024
+ "learning_rate": 4.480769230769231e-06,
2025
+ "loss": 1.7019,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 0.5557692307692308,
2030
+ "grad_norm": 0.24958765506744385,
2031
+ "learning_rate": 4.461538461538462e-06,
2032
+ "loss": 1.6907,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 0.5576923076923077,
2037
+ "grad_norm": 0.24778376519680023,
2038
+ "learning_rate": 4.4423076923076925e-06,
2039
+ "loss": 1.7051,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 0.5596153846153846,
2044
+ "grad_norm": 0.25688597559928894,
2045
+ "learning_rate": 4.423076923076924e-06,
2046
+ "loss": 1.506,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 0.5615384615384615,
2051
+ "grad_norm": 0.27464303374290466,
2052
+ "learning_rate": 4.403846153846154e-06,
2053
+ "loss": 1.872,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 0.5634615384615385,
2058
+ "grad_norm": 0.27473941445350647,
2059
+ "learning_rate": 4.384615384615385e-06,
2060
+ "loss": 1.8974,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 0.5653846153846154,
2065
+ "grad_norm": 0.27038097381591797,
2066
+ "learning_rate": 4.365384615384616e-06,
2067
+ "loss": 1.8278,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 0.5673076923076923,
2072
+ "grad_norm": 0.2503652572631836,
2073
+ "learning_rate": 4.346153846153846e-06,
2074
+ "loss": 1.6871,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 0.5692307692307692,
2079
+ "grad_norm": 0.24866697192192078,
2080
+ "learning_rate": 4.326923076923077e-06,
2081
+ "loss": 1.6712,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 0.5711538461538461,
2086
+ "grad_norm": 0.2415498048067093,
2087
+ "learning_rate": 4.307692307692308e-06,
2088
+ "loss": 1.6487,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 0.573076923076923,
2093
+ "grad_norm": 0.2505098581314087,
2094
+ "learning_rate": 4.288461538461539e-06,
2095
+ "loss": 1.5942,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 0.575,
2100
+ "grad_norm": 0.26868870854377747,
2101
+ "learning_rate": 4.26923076923077e-06,
2102
+ "loss": 1.7665,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 0.5769230769230769,
2107
+ "grad_norm": 0.24033549427986145,
2108
+ "learning_rate": 4.25e-06,
2109
+ "loss": 1.5891,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 0.5788461538461539,
2114
+ "grad_norm": 0.24726857244968414,
2115
+ "learning_rate": 4.230769230769231e-06,
2116
+ "loss": 1.6395,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 0.5807692307692308,
2121
+ "grad_norm": 0.23964416980743408,
2122
+ "learning_rate": 4.211538461538462e-06,
2123
+ "loss": 1.5237,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 0.5826923076923077,
2128
+ "grad_norm": 0.2671034336090088,
2129
+ "learning_rate": 4.192307692307692e-06,
2130
+ "loss": 1.8635,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 0.5846153846153846,
2135
+ "grad_norm": 0.22949711978435516,
2136
+ "learning_rate": 4.1730769230769235e-06,
2137
+ "loss": 1.5451,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 0.5865384615384616,
2142
+ "grad_norm": 0.2626548111438751,
2143
+ "learning_rate": 4.1538461538461545e-06,
2144
+ "loss": 1.931,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 0.5884615384615385,
2149
+ "grad_norm": 0.3223446011543274,
2150
+ "learning_rate": 4.134615384615385e-06,
2151
+ "loss": 1.8154,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 0.5903846153846154,
2156
+ "grad_norm": 0.25602713227272034,
2157
+ "learning_rate": 4.115384615384616e-06,
2158
+ "loss": 1.9264,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 0.5923076923076923,
2163
+ "grad_norm": 0.23411142826080322,
2164
+ "learning_rate": 4.096153846153846e-06,
2165
+ "loss": 1.7772,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 0.5942307692307692,
2170
+ "grad_norm": 0.24739161133766174,
2171
+ "learning_rate": 4.076923076923077e-06,
2172
+ "loss": 1.8269,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 0.5961538461538461,
2177
+ "grad_norm": 0.2461506873369217,
2178
+ "learning_rate": 4.057692307692308e-06,
2179
+ "loss": 1.6308,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 0.5980769230769231,
2184
+ "grad_norm": 0.24289779365062714,
2185
+ "learning_rate": 4.0384615384615385e-06,
2186
+ "loss": 1.6079,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 0.6,
2191
+ "grad_norm": 0.23565930128097534,
2192
+ "learning_rate": 4.01923076923077e-06,
2193
+ "loss": 1.5903,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 0.6019230769230769,
2198
+ "grad_norm": 0.28295522928237915,
2199
+ "learning_rate": 4.000000000000001e-06,
2200
+ "loss": 1.7925,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 0.6038461538461538,
2205
+ "grad_norm": 0.23887692391872406,
2206
+ "learning_rate": 3.980769230769231e-06,
2207
+ "loss": 1.6514,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 0.6057692307692307,
2212
+ "grad_norm": 0.2427336424589157,
2213
+ "learning_rate": 3.961538461538462e-06,
2214
+ "loss": 1.8173,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 0.6076923076923076,
2219
+ "grad_norm": 0.2524043619632721,
2220
+ "learning_rate": 3.942307692307692e-06,
2221
+ "loss": 1.6093,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 0.6096153846153847,
2226
+ "grad_norm": 0.26615944504737854,
2227
+ "learning_rate": 3.923076923076923e-06,
2228
+ "loss": 1.9504,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 0.6115384615384616,
2233
+ "grad_norm": 0.24780301749706268,
2234
+ "learning_rate": 3.903846153846154e-06,
2235
+ "loss": 1.5564,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 0.6134615384615385,
2240
+ "grad_norm": 0.2689846158027649,
2241
+ "learning_rate": 3.884615384615385e-06,
2242
+ "loss": 1.6757,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 0.6153846153846154,
2247
+ "grad_norm": 0.2715066969394684,
2248
+ "learning_rate": 3.865384615384616e-06,
2249
+ "loss": 1.6226,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 0.6173076923076923,
2254
+ "grad_norm": 0.2660449147224426,
2255
+ "learning_rate": 3.846153846153847e-06,
2256
+ "loss": 1.7564,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 0.6192307692307693,
2261
+ "grad_norm": 0.28160029649734497,
2262
+ "learning_rate": 3.826923076923077e-06,
2263
+ "loss": 1.8733,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 0.6211538461538462,
2268
+ "grad_norm": 0.2656888961791992,
2269
+ "learning_rate": 3.8076923076923077e-06,
2270
+ "loss": 1.7778,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 0.6230769230769231,
2275
+ "grad_norm": 0.31719696521759033,
2276
+ "learning_rate": 3.7884615384615388e-06,
2277
+ "loss": 1.6981,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 0.625,
2282
+ "grad_norm": 0.2793767750263214,
2283
+ "learning_rate": 3.7692307692307694e-06,
2284
+ "loss": 1.8359,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 0.6269230769230769,
2289
+ "grad_norm": 0.2439165562391281,
2290
+ "learning_rate": 3.7500000000000005e-06,
2291
+ "loss": 1.5793,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 0.6288461538461538,
2296
+ "grad_norm": 0.2448013722896576,
2297
+ "learning_rate": 3.730769230769231e-06,
2298
+ "loss": 1.8272,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 0.6307692307692307,
2303
+ "grad_norm": 0.28000980615615845,
2304
+ "learning_rate": 3.711538461538462e-06,
2305
+ "loss": 1.7879,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 0.6326923076923077,
2310
+ "grad_norm": 0.23256851732730865,
2311
+ "learning_rate": 3.692307692307693e-06,
2312
+ "loss": 1.4326,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 0.6346153846153846,
2317
+ "grad_norm": 0.3126485347747803,
2318
+ "learning_rate": 3.6730769230769236e-06,
2319
+ "loss": 2.0227,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 0.6365384615384615,
2324
+ "grad_norm": 0.22934819757938385,
2325
+ "learning_rate": 3.653846153846154e-06,
2326
+ "loss": 1.3916,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 0.6384615384615384,
2331
+ "grad_norm": 0.2432371973991394,
2332
+ "learning_rate": 3.634615384615385e-06,
2333
+ "loss": 1.682,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 0.6403846153846153,
2338
+ "grad_norm": 0.26585835218429565,
2339
+ "learning_rate": 3.6153846153846156e-06,
2340
+ "loss": 1.7519,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 0.6423076923076924,
2345
+ "grad_norm": 0.2541634440422058,
2346
+ "learning_rate": 3.5961538461538466e-06,
2347
+ "loss": 1.6093,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 0.6442307692307693,
2352
+ "grad_norm": 0.2718803584575653,
2353
+ "learning_rate": 3.5769230769230773e-06,
2354
+ "loss": 1.5575,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 0.6461538461538462,
2359
+ "grad_norm": 0.24795065820217133,
2360
+ "learning_rate": 3.557692307692308e-06,
2361
+ "loss": 1.8081,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 0.6480769230769231,
2366
+ "grad_norm": 0.25796961784362793,
2367
+ "learning_rate": 3.538461538461539e-06,
2368
+ "loss": 1.8205,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 0.65,
2373
+ "grad_norm": 0.28369465470314026,
2374
+ "learning_rate": 3.5192307692307697e-06,
2375
+ "loss": 1.9473,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 0.6519230769230769,
2380
+ "grad_norm": 0.300689697265625,
2381
+ "learning_rate": 3.5e-06,
2382
+ "loss": 2.0075,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 0.6538461538461539,
2387
+ "grad_norm": 0.2581382989883423,
2388
+ "learning_rate": 3.480769230769231e-06,
2389
+ "loss": 1.6992,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 0.6557692307692308,
2394
+ "grad_norm": 0.24735523760318756,
2395
+ "learning_rate": 3.4615384615384617e-06,
2396
+ "loss": 1.6095,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 0.6576923076923077,
2401
+ "grad_norm": 0.2518751323223114,
2402
+ "learning_rate": 3.4423076923076928e-06,
2403
+ "loss": 1.7043,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 0.6596153846153846,
2408
+ "grad_norm": 0.24945800006389618,
2409
+ "learning_rate": 3.4230769230769234e-06,
2410
+ "loss": 1.6327,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 0.6615384615384615,
2415
+ "grad_norm": 0.2738107144832611,
2416
+ "learning_rate": 3.403846153846154e-06,
2417
+ "loss": 1.9886,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 0.6634615384615384,
2422
+ "grad_norm": 0.25639379024505615,
2423
+ "learning_rate": 3.384615384615385e-06,
2424
+ "loss": 1.8663,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 0.6653846153846154,
2429
+ "grad_norm": 0.2627631425857544,
2430
+ "learning_rate": 3.365384615384616e-06,
2431
+ "loss": 2.0097,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 0.6673076923076923,
2436
+ "grad_norm": 0.46703851222991943,
2437
+ "learning_rate": 3.346153846153846e-06,
2438
+ "loss": 1.6617,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 0.6692307692307692,
2443
+ "grad_norm": 0.2513875663280487,
2444
+ "learning_rate": 3.326923076923077e-06,
2445
+ "loss": 1.5083,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 0.6711538461538461,
2450
+ "grad_norm": 0.24889354407787323,
2451
+ "learning_rate": 3.307692307692308e-06,
2452
+ "loss": 1.6616,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 0.6730769230769231,
2457
+ "grad_norm": 0.265433669090271,
2458
+ "learning_rate": 3.288461538461539e-06,
2459
+ "loss": 1.8974,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 0.675,
2464
+ "grad_norm": 0.31281140446662903,
2465
+ "learning_rate": 3.2692307692307696e-06,
2466
+ "loss": 1.6919,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 0.676923076923077,
2471
+ "grad_norm": 0.3091296851634979,
2472
+ "learning_rate": 3.2500000000000002e-06,
2473
+ "loss": 2.0115,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 0.6788461538461539,
2478
+ "grad_norm": 0.2759809195995331,
2479
+ "learning_rate": 3.2307692307692313e-06,
2480
+ "loss": 1.7599,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 0.6807692307692308,
2485
+ "grad_norm": 0.25779569149017334,
2486
+ "learning_rate": 3.211538461538462e-06,
2487
+ "loss": 1.6681,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 0.6826923076923077,
2492
+ "grad_norm": 0.2611697316169739,
2493
+ "learning_rate": 3.192307692307692e-06,
2494
+ "loss": 1.8169,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 0.6846153846153846,
2499
+ "grad_norm": 0.24831156432628632,
2500
+ "learning_rate": 3.1730769230769233e-06,
2501
+ "loss": 1.6432,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 0.6865384615384615,
2506
+ "grad_norm": 0.25252771377563477,
2507
+ "learning_rate": 3.153846153846154e-06,
2508
+ "loss": 1.5363,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 0.6884615384615385,
2513
+ "grad_norm": 0.266879141330719,
2514
+ "learning_rate": 3.134615384615385e-06,
2515
+ "loss": 1.9388,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 0.6903846153846154,
2520
+ "grad_norm": 0.24888667464256287,
2521
+ "learning_rate": 3.1153846153846157e-06,
2522
+ "loss": 1.6614,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 0.6923076923076923,
2527
+ "grad_norm": 0.2969956398010254,
2528
+ "learning_rate": 3.0961538461538464e-06,
2529
+ "loss": 2.1946,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 0.6942307692307692,
2534
+ "grad_norm": 0.2996269464492798,
2535
+ "learning_rate": 3.0769230769230774e-06,
2536
+ "loss": 2.1553,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 0.6961538461538461,
2541
+ "grad_norm": 0.24327410757541656,
2542
+ "learning_rate": 3.057692307692308e-06,
2543
+ "loss": 1.6482,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 0.698076923076923,
2548
+ "grad_norm": 0.32169681787490845,
2549
+ "learning_rate": 3.0384615384615383e-06,
2550
+ "loss": 1.6264,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 0.7,
2555
+ "grad_norm": 0.24536465108394623,
2556
+ "learning_rate": 3.0192307692307694e-06,
2557
+ "loss": 1.6291,
2558
+ "step": 364
2559
+ },
2560
+ {
2561
+ "epoch": 0.7019230769230769,
2562
+ "grad_norm": 0.2459547221660614,
2563
+ "learning_rate": 3e-06,
2564
+ "loss": 1.6067,
2565
+ "step": 365
2566
+ },
2567
+ {
2568
+ "epoch": 0.7038461538461539,
2569
+ "grad_norm": 0.26628872752189636,
2570
+ "learning_rate": 2.980769230769231e-06,
2571
+ "loss": 1.7971,
2572
+ "step": 366
2573
+ },
2574
+ {
2575
+ "epoch": 0.7057692307692308,
2576
+ "grad_norm": 0.2480877786874771,
2577
+ "learning_rate": 2.961538461538462e-06,
2578
+ "loss": 1.679,
2579
+ "step": 367
2580
+ },
2581
+ {
2582
+ "epoch": 0.7076923076923077,
2583
+ "grad_norm": 0.25840988755226135,
2584
+ "learning_rate": 2.9423076923076925e-06,
2585
+ "loss": 1.9267,
2586
+ "step": 368
2587
+ },
2588
+ {
2589
+ "epoch": 0.7096153846153846,
2590
+ "grad_norm": 0.22647550702095032,
2591
+ "learning_rate": 2.9230769230769236e-06,
2592
+ "loss": 1.3319,
2593
+ "step": 369
2594
+ },
2595
+ {
2596
+ "epoch": 0.7115384615384616,
2597
+ "grad_norm": 0.24305392801761627,
2598
+ "learning_rate": 2.9038461538461542e-06,
2599
+ "loss": 1.5368,
2600
+ "step": 370
2601
+ },
2602
+ {
2603
+ "epoch": 0.7134615384615385,
2604
+ "grad_norm": 0.26097992062568665,
2605
+ "learning_rate": 2.8846153846153845e-06,
2606
+ "loss": 1.7886,
2607
+ "step": 371
2608
+ },
2609
+ {
2610
+ "epoch": 0.7153846153846154,
2611
+ "grad_norm": 0.2853803038597107,
2612
+ "learning_rate": 2.8653846153846155e-06,
2613
+ "loss": 1.7891,
2614
+ "step": 372
2615
+ },
2616
+ {
2617
+ "epoch": 0.7173076923076923,
2618
+ "grad_norm": 0.24426959455013275,
2619
+ "learning_rate": 2.846153846153846e-06,
2620
+ "loss": 1.7191,
2621
+ "step": 373
2622
+ },
2623
+ {
2624
+ "epoch": 0.7192307692307692,
2625
+ "grad_norm": 0.27378132939338684,
2626
+ "learning_rate": 2.8269230769230773e-06,
2627
+ "loss": 1.6646,
2628
+ "step": 374
2629
+ },
2630
+ {
2631
+ "epoch": 0.7211538461538461,
2632
+ "grad_norm": 0.245508074760437,
2633
+ "learning_rate": 2.807692307692308e-06,
2634
+ "loss": 1.522,
2635
+ "step": 375
2636
+ },
2637
+ {
2638
+ "epoch": 0.7230769230769231,
2639
+ "grad_norm": 0.2848544120788574,
2640
+ "learning_rate": 2.7884615384615386e-06,
2641
+ "loss": 1.8397,
2642
+ "step": 376
2643
+ },
2644
+ {
2645
+ "epoch": 0.725,
2646
+ "grad_norm": 0.3340882658958435,
2647
+ "learning_rate": 2.7692307692307697e-06,
2648
+ "loss": 1.8823,
2649
+ "step": 377
2650
+ },
2651
+ {
2652
+ "epoch": 0.7269230769230769,
2653
+ "grad_norm": 0.2577882707118988,
2654
+ "learning_rate": 2.7500000000000004e-06,
2655
+ "loss": 1.7244,
2656
+ "step": 378
2657
+ },
2658
+ {
2659
+ "epoch": 0.7288461538461538,
2660
+ "grad_norm": 0.25997602939605713,
2661
+ "learning_rate": 2.7307692307692306e-06,
2662
+ "loss": 1.8059,
2663
+ "step": 379
2664
+ },
2665
+ {
2666
+ "epoch": 0.7307692307692307,
2667
+ "grad_norm": 0.2765803635120392,
2668
+ "learning_rate": 2.7115384615384617e-06,
2669
+ "loss": 1.996,
2670
+ "step": 380
2671
+ },
2672
+ {
2673
+ "epoch": 0.7326923076923076,
2674
+ "grad_norm": 0.2528791129589081,
2675
+ "learning_rate": 2.6923076923076923e-06,
2676
+ "loss": 1.5255,
2677
+ "step": 381
2678
+ },
2679
+ {
2680
+ "epoch": 0.7346153846153847,
2681
+ "grad_norm": 0.4214087724685669,
2682
+ "learning_rate": 2.6730769230769234e-06,
2683
+ "loss": 1.8193,
2684
+ "step": 382
2685
+ },
2686
+ {
2687
+ "epoch": 0.7365384615384616,
2688
+ "grad_norm": 0.25269967317581177,
2689
+ "learning_rate": 2.653846153846154e-06,
2690
+ "loss": 1.6907,
2691
+ "step": 383
2692
+ },
2693
+ {
2694
+ "epoch": 0.7384615384615385,
2695
+ "grad_norm": 0.23778170347213745,
2696
+ "learning_rate": 2.6346153846153847e-06,
2697
+ "loss": 1.6785,
2698
+ "step": 384
2699
+ },
2700
+ {
2701
+ "epoch": 0.7403846153846154,
2702
+ "grad_norm": 0.2538526952266693,
2703
+ "learning_rate": 2.615384615384616e-06,
2704
+ "loss": 1.7631,
2705
+ "step": 385
2706
+ },
2707
+ {
2708
+ "epoch": 0.7423076923076923,
2709
+ "grad_norm": 0.2979341149330139,
2710
+ "learning_rate": 2.5961538461538465e-06,
2711
+ "loss": 1.742,
2712
+ "step": 386
2713
+ },
2714
+ {
2715
+ "epoch": 0.7442307692307693,
2716
+ "grad_norm": 0.25184565782546997,
2717
+ "learning_rate": 2.5769230769230767e-06,
2718
+ "loss": 1.4643,
2719
+ "step": 387
2720
+ },
2721
+ {
2722
+ "epoch": 0.7461538461538462,
2723
+ "grad_norm": 0.27387166023254395,
2724
+ "learning_rate": 2.557692307692308e-06,
2725
+ "loss": 1.6691,
2726
+ "step": 388
2727
+ },
2728
+ {
2729
+ "epoch": 0.7480769230769231,
2730
+ "grad_norm": 0.2717282474040985,
2731
+ "learning_rate": 2.5384615384615385e-06,
2732
+ "loss": 1.8296,
2733
+ "step": 389
2734
+ },
2735
+ {
2736
+ "epoch": 0.75,
2737
+ "grad_norm": 0.25921329855918884,
2738
+ "learning_rate": 2.5192307692307695e-06,
2739
+ "loss": 1.6836,
2740
+ "step": 390
2741
+ },
2742
+ {
2743
+ "epoch": 0.7519230769230769,
2744
+ "grad_norm": 0.25560587644577026,
2745
+ "learning_rate": 2.5e-06,
2746
+ "loss": 1.5991,
2747
+ "step": 391
2748
+ },
2749
+ {
2750
+ "epoch": 0.7538461538461538,
2751
+ "grad_norm": 0.26660940051078796,
2752
+ "learning_rate": 2.480769230769231e-06,
2753
+ "loss": 1.567,
2754
+ "step": 392
2755
+ },
2756
+ {
2757
+ "epoch": 0.7557692307692307,
2758
+ "grad_norm": 0.25358498096466064,
2759
+ "learning_rate": 2.461538461538462e-06,
2760
+ "loss": 1.4709,
2761
+ "step": 393
2762
+ },
2763
+ {
2764
+ "epoch": 0.7576923076923077,
2765
+ "grad_norm": 0.25442802906036377,
2766
+ "learning_rate": 2.4423076923076926e-06,
2767
+ "loss": 1.6581,
2768
+ "step": 394
2769
+ },
2770
+ {
2771
+ "epoch": 0.7596153846153846,
2772
+ "grad_norm": 0.3973132073879242,
2773
+ "learning_rate": 2.4230769230769233e-06,
2774
+ "loss": 1.5558,
2775
+ "step": 395
2776
+ },
2777
+ {
2778
+ "epoch": 0.7615384615384615,
2779
+ "grad_norm": 0.23773129284381866,
2780
+ "learning_rate": 2.403846153846154e-06,
2781
+ "loss": 1.6702,
2782
+ "step": 396
2783
+ },
2784
+ {
2785
+ "epoch": 0.7634615384615384,
2786
+ "grad_norm": 0.24875624477863312,
2787
+ "learning_rate": 2.384615384615385e-06,
2788
+ "loss": 1.4193,
2789
+ "step": 397
2790
+ },
2791
+ {
2792
+ "epoch": 0.7653846153846153,
2793
+ "grad_norm": 0.26100465655326843,
2794
+ "learning_rate": 2.3653846153846157e-06,
2795
+ "loss": 1.6245,
2796
+ "step": 398
2797
+ },
2798
+ {
2799
+ "epoch": 0.7673076923076924,
2800
+ "grad_norm": 0.26141950488090515,
2801
+ "learning_rate": 2.3461538461538463e-06,
2802
+ "loss": 1.782,
2803
+ "step": 399
2804
+ },
2805
+ {
2806
+ "epoch": 0.7692307692307693,
2807
+ "grad_norm": 0.2312656044960022,
2808
+ "learning_rate": 2.326923076923077e-06,
2809
+ "loss": 1.567,
2810
+ "step": 400
2811
+ },
2812
+ {
2813
+ "epoch": 0.7711538461538462,
2814
+ "grad_norm": 0.23716554045677185,
2815
+ "learning_rate": 2.307692307692308e-06,
2816
+ "loss": 1.4983,
2817
+ "step": 401
2818
+ },
2819
+ {
2820
+ "epoch": 0.7730769230769231,
2821
+ "grad_norm": 0.24115121364593506,
2822
+ "learning_rate": 2.2884615384615387e-06,
2823
+ "loss": 1.5522,
2824
+ "step": 402
2825
+ },
2826
+ {
2827
+ "epoch": 0.775,
2828
+ "grad_norm": 0.25047433376312256,
2829
+ "learning_rate": 2.2692307692307694e-06,
2830
+ "loss": 1.6842,
2831
+ "step": 403
2832
+ },
2833
+ {
2834
+ "epoch": 0.7769230769230769,
2835
+ "grad_norm": 0.26907241344451904,
2836
+ "learning_rate": 2.25e-06,
2837
+ "loss": 1.8948,
2838
+ "step": 404
2839
+ },
2840
+ {
2841
+ "epoch": 0.7788461538461539,
2842
+ "grad_norm": 0.26408788561820984,
2843
+ "learning_rate": 2.230769230769231e-06,
2844
+ "loss": 1.7583,
2845
+ "step": 405
2846
+ },
2847
+ {
2848
+ "epoch": 0.7807692307692308,
2849
+ "grad_norm": 0.3124351501464844,
2850
+ "learning_rate": 2.211538461538462e-06,
2851
+ "loss": 2.3,
2852
+ "step": 406
2853
+ },
2854
+ {
2855
+ "epoch": 0.7826923076923077,
2856
+ "grad_norm": 0.32905814051628113,
2857
+ "learning_rate": 2.1923076923076925e-06,
2858
+ "loss": 1.9242,
2859
+ "step": 407
2860
+ },
2861
+ {
2862
+ "epoch": 0.7846153846153846,
2863
+ "grad_norm": 0.22997631132602692,
2864
+ "learning_rate": 2.173076923076923e-06,
2865
+ "loss": 1.5628,
2866
+ "step": 408
2867
+ },
2868
+ {
2869
+ "epoch": 0.7865384615384615,
2870
+ "grad_norm": 0.23151925206184387,
2871
+ "learning_rate": 2.153846153846154e-06,
2872
+ "loss": 1.581,
2873
+ "step": 409
2874
+ },
2875
+ {
2876
+ "epoch": 0.7884615384615384,
2877
+ "grad_norm": 0.26641565561294556,
2878
+ "learning_rate": 2.134615384615385e-06,
2879
+ "loss": 1.6023,
2880
+ "step": 410
2881
+ },
2882
+ {
2883
+ "epoch": 0.7903846153846154,
2884
+ "grad_norm": 0.2557229995727539,
2885
+ "learning_rate": 2.1153846153846155e-06,
2886
+ "loss": 1.5555,
2887
+ "step": 411
2888
+ },
2889
+ {
2890
+ "epoch": 0.7923076923076923,
2891
+ "grad_norm": 0.2465619444847107,
2892
+ "learning_rate": 2.096153846153846e-06,
2893
+ "loss": 1.5759,
2894
+ "step": 412
2895
+ },
2896
+ {
2897
+ "epoch": 0.7942307692307692,
2898
+ "grad_norm": 0.2585005760192871,
2899
+ "learning_rate": 2.0769230769230773e-06,
2900
+ "loss": 1.5927,
2901
+ "step": 413
2902
+ },
2903
+ {
2904
+ "epoch": 0.7961538461538461,
2905
+ "grad_norm": 0.35315144062042236,
2906
+ "learning_rate": 2.057692307692308e-06,
2907
+ "loss": 1.6754,
2908
+ "step": 414
2909
+ },
2910
+ {
2911
+ "epoch": 0.7980769230769231,
2912
+ "grad_norm": 0.2516288459300995,
2913
+ "learning_rate": 2.0384615384615386e-06,
2914
+ "loss": 1.7214,
2915
+ "step": 415
2916
+ },
2917
+ {
2918
+ "epoch": 0.8,
2919
+ "grad_norm": 0.26250702142715454,
2920
+ "learning_rate": 2.0192307692307692e-06,
2921
+ "loss": 1.7203,
2922
+ "step": 416
2923
+ },
2924
+ {
2925
+ "epoch": 0.801923076923077,
2926
+ "grad_norm": 0.2870039939880371,
2927
+ "learning_rate": 2.0000000000000003e-06,
2928
+ "loss": 2.1003,
2929
+ "step": 417
2930
+ },
2931
+ {
2932
+ "epoch": 0.8038461538461539,
2933
+ "grad_norm": 0.3824276030063629,
2934
+ "learning_rate": 1.980769230769231e-06,
2935
+ "loss": 1.6918,
2936
+ "step": 418
2937
+ },
2938
+ {
2939
+ "epoch": 0.8057692307692308,
2940
+ "grad_norm": 0.25719743967056274,
2941
+ "learning_rate": 1.9615384615384617e-06,
2942
+ "loss": 1.7682,
2943
+ "step": 419
2944
+ },
2945
+ {
2946
+ "epoch": 0.8076923076923077,
2947
+ "grad_norm": 0.2493806779384613,
2948
+ "learning_rate": 1.9423076923076923e-06,
2949
+ "loss": 1.5785,
2950
+ "step": 420
2951
+ },
2952
+ {
2953
+ "epoch": 0.8096153846153846,
2954
+ "grad_norm": 0.2641220986843109,
2955
+ "learning_rate": 1.9230769230769234e-06,
2956
+ "loss": 1.7473,
2957
+ "step": 421
2958
+ },
2959
+ {
2960
+ "epoch": 0.8115384615384615,
2961
+ "grad_norm": 0.2540389895439148,
2962
+ "learning_rate": 1.9038461538461538e-06,
2963
+ "loss": 1.7319,
2964
+ "step": 422
2965
+ },
2966
+ {
2967
+ "epoch": 0.8134615384615385,
2968
+ "grad_norm": 0.24150903522968292,
2969
+ "learning_rate": 1.8846153846153847e-06,
2970
+ "loss": 1.5777,
2971
+ "step": 423
2972
+ },
2973
+ {
2974
+ "epoch": 0.8153846153846154,
2975
+ "grad_norm": 0.2557712495326996,
2976
+ "learning_rate": 1.8653846153846156e-06,
2977
+ "loss": 1.8173,
2978
+ "step": 424
2979
+ },
2980
+ {
2981
+ "epoch": 0.8173076923076923,
2982
+ "grad_norm": 0.26369795203208923,
2983
+ "learning_rate": 1.8461538461538465e-06,
2984
+ "loss": 1.5932,
2985
+ "step": 425
2986
+ },
2987
+ {
2988
+ "epoch": 0.8192307692307692,
2989
+ "grad_norm": 0.27045026421546936,
2990
+ "learning_rate": 1.826923076923077e-06,
2991
+ "loss": 1.8156,
2992
+ "step": 426
2993
+ },
2994
+ {
2995
+ "epoch": 0.8211538461538461,
2996
+ "grad_norm": 0.24966885149478912,
2997
+ "learning_rate": 1.8076923076923078e-06,
2998
+ "loss": 1.8092,
2999
+ "step": 427
3000
+ },
3001
+ {
3002
+ "epoch": 0.823076923076923,
3003
+ "grad_norm": 0.25059932470321655,
3004
+ "learning_rate": 1.7884615384615387e-06,
3005
+ "loss": 1.7056,
3006
+ "step": 428
3007
+ },
3008
+ {
3009
+ "epoch": 0.825,
3010
+ "grad_norm": 0.276777058839798,
3011
+ "learning_rate": 1.7692307692307695e-06,
3012
+ "loss": 1.6466,
3013
+ "step": 429
3014
+ },
3015
+ {
3016
+ "epoch": 0.8269230769230769,
3017
+ "grad_norm": 0.25502729415893555,
3018
+ "learning_rate": 1.75e-06,
3019
+ "loss": 1.8679,
3020
+ "step": 430
3021
+ },
3022
+ {
3023
+ "epoch": 0.8288461538461539,
3024
+ "grad_norm": 0.2469128668308258,
3025
+ "learning_rate": 1.7307692307692308e-06,
3026
+ "loss": 1.7295,
3027
+ "step": 431
3028
+ },
3029
+ {
3030
+ "epoch": 0.8307692307692308,
3031
+ "grad_norm": 0.2856203615665436,
3032
+ "learning_rate": 1.7115384615384617e-06,
3033
+ "loss": 1.803,
3034
+ "step": 432
3035
+ },
3036
+ {
3037
+ "epoch": 0.8326923076923077,
3038
+ "grad_norm": 0.2536699175834656,
3039
+ "learning_rate": 1.6923076923076926e-06,
3040
+ "loss": 1.822,
3041
+ "step": 433
3042
+ },
3043
+ {
3044
+ "epoch": 0.8346153846153846,
3045
+ "grad_norm": 0.2514714300632477,
3046
+ "learning_rate": 1.673076923076923e-06,
3047
+ "loss": 1.5885,
3048
+ "step": 434
3049
+ },
3050
+ {
3051
+ "epoch": 0.8365384615384616,
3052
+ "grad_norm": 0.26350492238998413,
3053
+ "learning_rate": 1.653846153846154e-06,
3054
+ "loss": 1.5044,
3055
+ "step": 435
3056
+ },
3057
+ {
3058
+ "epoch": 0.8384615384615385,
3059
+ "grad_norm": 0.37345945835113525,
3060
+ "learning_rate": 1.6346153846153848e-06,
3061
+ "loss": 1.925,
3062
+ "step": 436
3063
+ },
3064
+ {
3065
+ "epoch": 0.8403846153846154,
3066
+ "grad_norm": 0.32454490661621094,
3067
+ "learning_rate": 1.6153846153846157e-06,
3068
+ "loss": 2.0257,
3069
+ "step": 437
3070
+ },
3071
+ {
3072
+ "epoch": 0.8423076923076923,
3073
+ "grad_norm": 0.2717486023902893,
3074
+ "learning_rate": 1.596153846153846e-06,
3075
+ "loss": 1.9406,
3076
+ "step": 438
3077
+ },
3078
+ {
3079
+ "epoch": 0.8442307692307692,
3080
+ "grad_norm": 0.2511124610900879,
3081
+ "learning_rate": 1.576923076923077e-06,
3082
+ "loss": 1.5494,
3083
+ "step": 439
3084
+ },
3085
+ {
3086
+ "epoch": 0.8461538461538461,
3087
+ "grad_norm": 0.3645758330821991,
3088
+ "learning_rate": 1.5576923076923078e-06,
3089
+ "loss": 1.9922,
3090
+ "step": 440
3091
+ },
3092
+ {
3093
+ "epoch": 0.8480769230769231,
3094
+ "grad_norm": 0.24735790491104126,
3095
+ "learning_rate": 1.5384615384615387e-06,
3096
+ "loss": 1.6998,
3097
+ "step": 441
3098
+ },
3099
+ {
3100
+ "epoch": 0.85,
3101
+ "grad_norm": 0.28394192457199097,
3102
+ "learning_rate": 1.5192307692307692e-06,
3103
+ "loss": 1.7959,
3104
+ "step": 442
3105
+ },
3106
+ {
3107
+ "epoch": 0.8519230769230769,
3108
+ "grad_norm": 0.25051411986351013,
3109
+ "learning_rate": 1.5e-06,
3110
+ "loss": 1.7294,
3111
+ "step": 443
3112
+ },
3113
+ {
3114
+ "epoch": 0.8538461538461538,
3115
+ "grad_norm": 0.2777117192745209,
3116
+ "learning_rate": 1.480769230769231e-06,
3117
+ "loss": 1.5858,
3118
+ "step": 444
3119
+ },
3120
+ {
3121
+ "epoch": 0.8557692307692307,
3122
+ "grad_norm": 0.2899523675441742,
3123
+ "learning_rate": 1.4615384615384618e-06,
3124
+ "loss": 1.9108,
3125
+ "step": 445
3126
+ },
3127
+ {
3128
+ "epoch": 0.8576923076923076,
3129
+ "grad_norm": 0.2494972050189972,
3130
+ "learning_rate": 1.4423076923076922e-06,
3131
+ "loss": 1.8374,
3132
+ "step": 446
3133
+ },
3134
+ {
3135
+ "epoch": 0.8596153846153847,
3136
+ "grad_norm": 0.2451220005750656,
3137
+ "learning_rate": 1.423076923076923e-06,
3138
+ "loss": 1.4877,
3139
+ "step": 447
3140
+ },
3141
+ {
3142
+ "epoch": 0.8615384615384616,
3143
+ "grad_norm": 0.29028716683387756,
3144
+ "learning_rate": 1.403846153846154e-06,
3145
+ "loss": 1.6063,
3146
+ "step": 448
3147
+ },
3148
+ {
3149
+ "epoch": 0.8634615384615385,
3150
+ "grad_norm": 0.26619985699653625,
3151
+ "learning_rate": 1.3846153846153848e-06,
3152
+ "loss": 1.8916,
3153
+ "step": 449
3154
+ },
3155
+ {
3156
+ "epoch": 0.8653846153846154,
3157
+ "grad_norm": 0.2383321225643158,
3158
+ "learning_rate": 1.3653846153846153e-06,
3159
+ "loss": 1.4759,
3160
+ "step": 450
3161
+ },
3162
+ {
3163
+ "epoch": 0.8673076923076923,
3164
+ "grad_norm": 0.24306997656822205,
3165
+ "learning_rate": 1.3461538461538462e-06,
3166
+ "loss": 1.568,
3167
+ "step": 451
3168
+ },
3169
+ {
3170
+ "epoch": 0.8692307692307693,
3171
+ "grad_norm": 0.35179200768470764,
3172
+ "learning_rate": 1.326923076923077e-06,
3173
+ "loss": 2.1551,
3174
+ "step": 452
3175
+ },
3176
+ {
3177
+ "epoch": 0.8711538461538462,
3178
+ "grad_norm": 0.24707993865013123,
3179
+ "learning_rate": 1.307692307692308e-06,
3180
+ "loss": 1.6473,
3181
+ "step": 453
3182
+ },
3183
+ {
3184
+ "epoch": 0.8730769230769231,
3185
+ "grad_norm": 0.2762058675289154,
3186
+ "learning_rate": 1.2884615384615384e-06,
3187
+ "loss": 1.8111,
3188
+ "step": 454
3189
+ },
3190
+ {
3191
+ "epoch": 0.875,
3192
+ "grad_norm": 0.2691110670566559,
3193
+ "learning_rate": 1.2692307692307692e-06,
3194
+ "loss": 1.7669,
3195
+ "step": 455
3196
+ },
3197
+ {
3198
+ "epoch": 0.8769230769230769,
3199
+ "grad_norm": 0.2559700012207031,
3200
+ "learning_rate": 1.25e-06,
3201
+ "loss": 1.5294,
3202
+ "step": 456
3203
+ },
3204
+ {
3205
+ "epoch": 0.8788461538461538,
3206
+ "grad_norm": 0.2672431468963623,
3207
+ "learning_rate": 1.230769230769231e-06,
3208
+ "loss": 1.9571,
3209
+ "step": 457
3210
+ },
3211
+ {
3212
+ "epoch": 0.8807692307692307,
3213
+ "grad_norm": 0.253749281167984,
3214
+ "learning_rate": 1.2115384615384616e-06,
3215
+ "loss": 1.6117,
3216
+ "step": 458
3217
+ },
3218
+ {
3219
+ "epoch": 0.8826923076923077,
3220
+ "grad_norm": 0.26606205105781555,
3221
+ "learning_rate": 1.1923076923076925e-06,
3222
+ "loss": 1.736,
3223
+ "step": 459
3224
+ },
3225
+ {
3226
+ "epoch": 0.8846153846153846,
3227
+ "grad_norm": 0.2549211084842682,
3228
+ "learning_rate": 1.1730769230769232e-06,
3229
+ "loss": 1.7434,
3230
+ "step": 460
3231
+ },
3232
+ {
3233
+ "epoch": 0.8865384615384615,
3234
+ "grad_norm": 0.2654229700565338,
3235
+ "learning_rate": 1.153846153846154e-06,
3236
+ "loss": 1.7763,
3237
+ "step": 461
3238
+ },
3239
+ {
3240
+ "epoch": 0.8884615384615384,
3241
+ "grad_norm": 0.27833449840545654,
3242
+ "learning_rate": 1.1346153846153847e-06,
3243
+ "loss": 1.5596,
3244
+ "step": 462
3245
+ },
3246
+ {
3247
+ "epoch": 0.8903846153846153,
3248
+ "grad_norm": 0.2847915589809418,
3249
+ "learning_rate": 1.1153846153846156e-06,
3250
+ "loss": 1.6668,
3251
+ "step": 463
3252
+ },
3253
+ {
3254
+ "epoch": 0.8923076923076924,
3255
+ "grad_norm": 0.25849324464797974,
3256
+ "learning_rate": 1.0961538461538462e-06,
3257
+ "loss": 1.6263,
3258
+ "step": 464
3259
+ },
3260
+ {
3261
+ "epoch": 0.8942307692307693,
3262
+ "grad_norm": 0.2499273717403412,
3263
+ "learning_rate": 1.076923076923077e-06,
3264
+ "loss": 1.7538,
3265
+ "step": 465
3266
+ },
3267
+ {
3268
+ "epoch": 0.8961538461538462,
3269
+ "grad_norm": 0.2744547724723816,
3270
+ "learning_rate": 1.0576923076923078e-06,
3271
+ "loss": 1.9274,
3272
+ "step": 466
3273
+ },
3274
+ {
3275
+ "epoch": 0.8980769230769231,
3276
+ "grad_norm": 0.2700127065181732,
3277
+ "learning_rate": 1.0384615384615386e-06,
3278
+ "loss": 1.7668,
3279
+ "step": 467
3280
+ },
3281
+ {
3282
+ "epoch": 0.9,
3283
+ "grad_norm": 0.2489522099494934,
3284
+ "learning_rate": 1.0192307692307693e-06,
3285
+ "loss": 1.7475,
3286
+ "step": 468
3287
+ },
3288
+ {
3289
+ "epoch": 0.9019230769230769,
3290
+ "grad_norm": 0.24912633001804352,
3291
+ "learning_rate": 1.0000000000000002e-06,
3292
+ "loss": 1.4687,
3293
+ "step": 469
3294
+ },
3295
+ {
3296
+ "epoch": 0.9038461538461539,
3297
+ "grad_norm": 0.25620830059051514,
3298
+ "learning_rate": 9.807692307692308e-07,
3299
+ "loss": 1.8543,
3300
+ "step": 470
3301
+ },
3302
+ {
3303
+ "epoch": 0.9057692307692308,
3304
+ "grad_norm": 0.27851760387420654,
3305
+ "learning_rate": 9.615384615384617e-07,
3306
+ "loss": 1.7882,
3307
+ "step": 471
3308
+ },
3309
+ {
3310
+ "epoch": 0.9076923076923077,
3311
+ "grad_norm": 0.279709130525589,
3312
+ "learning_rate": 9.423076923076924e-07,
3313
+ "loss": 1.7165,
3314
+ "step": 472
3315
+ },
3316
+ {
3317
+ "epoch": 0.9096153846153846,
3318
+ "grad_norm": 0.25235506892204285,
3319
+ "learning_rate": 9.230769230769232e-07,
3320
+ "loss": 1.5243,
3321
+ "step": 473
3322
+ },
3323
+ {
3324
+ "epoch": 0.9115384615384615,
3325
+ "grad_norm": 0.3857625126838684,
3326
+ "learning_rate": 9.038461538461539e-07,
3327
+ "loss": 1.7098,
3328
+ "step": 474
3329
+ },
3330
+ {
3331
+ "epoch": 0.9134615384615384,
3332
+ "grad_norm": 0.3038006126880646,
3333
+ "learning_rate": 8.846153846153848e-07,
3334
+ "loss": 2.0178,
3335
+ "step": 475
3336
+ },
3337
+ {
3338
+ "epoch": 0.9153846153846154,
3339
+ "grad_norm": 0.2800678312778473,
3340
+ "learning_rate": 8.653846153846154e-07,
3341
+ "loss": 1.8552,
3342
+ "step": 476
3343
+ },
3344
+ {
3345
+ "epoch": 0.9173076923076923,
3346
+ "grad_norm": 0.279078871011734,
3347
+ "learning_rate": 8.461538461538463e-07,
3348
+ "loss": 2.061,
3349
+ "step": 477
3350
+ },
3351
+ {
3352
+ "epoch": 0.9192307692307692,
3353
+ "grad_norm": 0.2629892826080322,
3354
+ "learning_rate": 8.26923076923077e-07,
3355
+ "loss": 1.7242,
3356
+ "step": 478
3357
+ },
3358
+ {
3359
+ "epoch": 0.9211538461538461,
3360
+ "grad_norm": 0.2715969383716583,
3361
+ "learning_rate": 8.076923076923078e-07,
3362
+ "loss": 1.6344,
3363
+ "step": 479
3364
+ },
3365
+ {
3366
+ "epoch": 0.9230769230769231,
3367
+ "grad_norm": 0.2412460297346115,
3368
+ "learning_rate": 7.884615384615385e-07,
3369
+ "loss": 1.4945,
3370
+ "step": 480
3371
+ },
3372
+ {
3373
+ "epoch": 0.925,
3374
+ "grad_norm": 0.23875723779201508,
3375
+ "learning_rate": 7.692307692307694e-07,
3376
+ "loss": 1.5076,
3377
+ "step": 481
3378
+ },
3379
+ {
3380
+ "epoch": 0.926923076923077,
3381
+ "grad_norm": 0.3029634654521942,
3382
+ "learning_rate": 7.5e-07,
3383
+ "loss": 2.0072,
3384
+ "step": 482
3385
+ },
3386
+ {
3387
+ "epoch": 0.9288461538461539,
3388
+ "grad_norm": 0.3063458800315857,
3389
+ "learning_rate": 7.307692307692309e-07,
3390
+ "loss": 2.1603,
3391
+ "step": 483
3392
+ },
3393
+ {
3394
+ "epoch": 0.9307692307692308,
3395
+ "grad_norm": 0.254506915807724,
3396
+ "learning_rate": 7.115384615384616e-07,
3397
+ "loss": 1.6177,
3398
+ "step": 484
3399
+ },
3400
+ {
3401
+ "epoch": 0.9326923076923077,
3402
+ "grad_norm": 0.26467716693878174,
3403
+ "learning_rate": 6.923076923076924e-07,
3404
+ "loss": 1.6588,
3405
+ "step": 485
3406
+ },
3407
+ {
3408
+ "epoch": 0.9346153846153846,
3409
+ "grad_norm": 0.24453574419021606,
3410
+ "learning_rate": 6.730769230769231e-07,
3411
+ "loss": 1.5381,
3412
+ "step": 486
3413
+ },
3414
+ {
3415
+ "epoch": 0.9365384615384615,
3416
+ "grad_norm": 0.25973954796791077,
3417
+ "learning_rate": 6.53846153846154e-07,
3418
+ "loss": 1.904,
3419
+ "step": 487
3420
+ },
3421
+ {
3422
+ "epoch": 0.9384615384615385,
3423
+ "grad_norm": 0.27177441120147705,
3424
+ "learning_rate": 6.346153846153846e-07,
3425
+ "loss": 1.7959,
3426
+ "step": 488
3427
+ },
3428
+ {
3429
+ "epoch": 0.9403846153846154,
3430
+ "grad_norm": 0.30401328206062317,
3431
+ "learning_rate": 6.153846153846155e-07,
3432
+ "loss": 1.8886,
3433
+ "step": 489
3434
+ },
3435
+ {
3436
+ "epoch": 0.9423076923076923,
3437
+ "grad_norm": 0.26204606890678406,
3438
+ "learning_rate": 5.961538461538463e-07,
3439
+ "loss": 1.7376,
3440
+ "step": 490
3441
+ },
3442
+ {
3443
+ "epoch": 0.9442307692307692,
3444
+ "grad_norm": 0.26420703530311584,
3445
+ "learning_rate": 5.76923076923077e-07,
3446
+ "loss": 1.898,
3447
+ "step": 491
3448
+ },
3449
+ {
3450
+ "epoch": 0.9461538461538461,
3451
+ "grad_norm": 0.28063708543777466,
3452
+ "learning_rate": 5.576923076923078e-07,
3453
+ "loss": 1.8349,
3454
+ "step": 492
3455
+ },
3456
+ {
3457
+ "epoch": 0.948076923076923,
3458
+ "grad_norm": 0.251138299703598,
3459
+ "learning_rate": 5.384615384615386e-07,
3460
+ "loss": 1.8723,
3461
+ "step": 493
3462
+ },
3463
+ {
3464
+ "epoch": 0.95,
3465
+ "grad_norm": 0.3090968430042267,
3466
+ "learning_rate": 5.192307692307693e-07,
3467
+ "loss": 2.2775,
3468
+ "step": 494
3469
+ },
3470
+ {
3471
+ "epoch": 0.9519230769230769,
3472
+ "grad_norm": 0.242737278342247,
3473
+ "learning_rate": 5.000000000000001e-07,
3474
+ "loss": 1.4098,
3475
+ "step": 495
3476
+ },
3477
+ {
3478
+ "epoch": 0.9538461538461539,
3479
+ "grad_norm": 0.24476881325244904,
3480
+ "learning_rate": 4.807692307692308e-07,
3481
+ "loss": 1.6145,
3482
+ "step": 496
3483
+ },
3484
+ {
3485
+ "epoch": 0.9557692307692308,
3486
+ "grad_norm": 0.3140285909175873,
3487
+ "learning_rate": 4.615384615384616e-07,
3488
+ "loss": 1.8621,
3489
+ "step": 497
3490
+ },
3491
+ {
3492
+ "epoch": 0.9576923076923077,
3493
+ "grad_norm": 0.2548242509365082,
3494
+ "learning_rate": 4.423076923076924e-07,
3495
+ "loss": 1.4782,
3496
+ "step": 498
3497
+ },
3498
+ {
3499
+ "epoch": 0.9596153846153846,
3500
+ "grad_norm": 0.25150105357170105,
3501
+ "learning_rate": 4.2307692307692315e-07,
3502
+ "loss": 1.3978,
3503
+ "step": 499
3504
+ },
3505
+ {
3506
+ "epoch": 0.9615384615384616,
3507
+ "grad_norm": 0.2646598219871521,
3508
+ "learning_rate": 4.038461538461539e-07,
3509
+ "loss": 1.8741,
3510
+ "step": 500
3511
+ },
3512
+ {
3513
+ "epoch": 0.9634615384615385,
3514
+ "grad_norm": 0.2567940950393677,
3515
+ "learning_rate": 3.846153846153847e-07,
3516
+ "loss": 1.8474,
3517
+ "step": 501
3518
+ },
3519
+ {
3520
+ "epoch": 0.9653846153846154,
3521
+ "grad_norm": 0.2500056326389313,
3522
+ "learning_rate": 3.6538461538461545e-07,
3523
+ "loss": 1.8728,
3524
+ "step": 502
3525
+ },
3526
+ {
3527
+ "epoch": 0.9673076923076923,
3528
+ "grad_norm": 0.26126691699028015,
3529
+ "learning_rate": 3.461538461538462e-07,
3530
+ "loss": 1.6122,
3531
+ "step": 503
3532
+ },
3533
+ {
3534
+ "epoch": 0.9692307692307692,
3535
+ "grad_norm": 0.29029861092567444,
3536
+ "learning_rate": 3.26923076923077e-07,
3537
+ "loss": 2.0278,
3538
+ "step": 504
3539
+ },
3540
+ {
3541
+ "epoch": 0.9711538461538461,
3542
+ "grad_norm": 0.26945146918296814,
3543
+ "learning_rate": 3.0769230769230774e-07,
3544
+ "loss": 1.9084,
3545
+ "step": 505
3546
+ },
3547
+ {
3548
+ "epoch": 0.9730769230769231,
3549
+ "grad_norm": 0.26542940735816956,
3550
+ "learning_rate": 2.884615384615385e-07,
3551
+ "loss": 1.745,
3552
+ "step": 506
3553
+ },
3554
+ {
3555
+ "epoch": 0.975,
3556
+ "grad_norm": 0.25256749987602234,
3557
+ "learning_rate": 2.692307692307693e-07,
3558
+ "loss": 1.6902,
3559
+ "step": 507
3560
+ },
3561
+ {
3562
+ "epoch": 0.9769230769230769,
3563
+ "grad_norm": 0.25919848680496216,
3564
+ "learning_rate": 2.5000000000000004e-07,
3565
+ "loss": 1.6899,
3566
+ "step": 508
3567
+ },
3568
+ {
3569
+ "epoch": 0.9788461538461538,
3570
+ "grad_norm": 0.2654649019241333,
3571
+ "learning_rate": 2.307692307692308e-07,
3572
+ "loss": 1.5859,
3573
+ "step": 509
3574
+ },
3575
+ {
3576
+ "epoch": 0.9807692307692307,
3577
+ "grad_norm": 0.2676642835140228,
3578
+ "learning_rate": 2.1153846153846157e-07,
3579
+ "loss": 1.804,
3580
+ "step": 510
3581
+ },
3582
+ {
3583
+ "epoch": 0.9826923076923076,
3584
+ "grad_norm": 0.23694384098052979,
3585
+ "learning_rate": 1.9230769230769234e-07,
3586
+ "loss": 1.6237,
3587
+ "step": 511
3588
+ },
3589
+ {
3590
+ "epoch": 0.9846153846153847,
3591
+ "grad_norm": 0.248484805226326,
3592
+ "learning_rate": 1.730769230769231e-07,
3593
+ "loss": 1.4356,
3594
+ "step": 512
3595
+ },
3596
+ {
3597
+ "epoch": 0.9865384615384616,
3598
+ "grad_norm": 0.3018724322319031,
3599
+ "learning_rate": 1.5384615384615387e-07,
3600
+ "loss": 1.8725,
3601
+ "step": 513
3602
+ },
3603
+ {
3604
+ "epoch": 0.9884615384615385,
3605
+ "grad_norm": 0.2987407445907593,
3606
+ "learning_rate": 1.3461538461538464e-07,
3607
+ "loss": 2.0642,
3608
+ "step": 514
3609
+ },
3610
+ {
3611
+ "epoch": 0.9903846153846154,
3612
+ "grad_norm": 0.267703652381897,
3613
+ "learning_rate": 1.153846153846154e-07,
3614
+ "loss": 1.8019,
3615
+ "step": 515
3616
+ },
3617
+ {
3618
+ "epoch": 0.9923076923076923,
3619
+ "grad_norm": 0.24708707630634308,
3620
+ "learning_rate": 9.615384615384617e-08,
3621
+ "loss": 1.5776,
3622
+ "step": 516
3623
+ },
3624
+ {
3625
+ "epoch": 0.9942307692307693,
3626
+ "grad_norm": 0.2372850626707077,
3627
+ "learning_rate": 7.692307692307694e-08,
3628
+ "loss": 1.5792,
3629
+ "step": 517
3630
+ },
3631
+ {
3632
+ "epoch": 0.9961538461538462,
3633
+ "grad_norm": 0.2609519362449646,
3634
+ "learning_rate": 5.76923076923077e-08,
3635
+ "loss": 1.6026,
3636
+ "step": 518
3637
+ },
3638
+ {
3639
+ "epoch": 0.9980769230769231,
3640
+ "grad_norm": 0.2747548818588257,
3641
+ "learning_rate": 3.846153846153847e-08,
3642
+ "loss": 1.9553,
3643
+ "step": 519
3644
+ },
3645
+ {
3646
+ "epoch": 1.0,
3647
+ "grad_norm": 0.2490331530570984,
3648
+ "learning_rate": 1.9230769230769234e-08,
3649
+ "loss": 1.7356,
3650
+ "step": 520
3651
+ },
3652
+ {
3653
+ "epoch": 1.0,
3654
+ "eval_loss": 1.7645896673202515,
3655
+ "eval_runtime": 1.1787,
3656
+ "eval_samples_per_second": 42.42,
3657
+ "eval_steps_per_second": 5.939,
3658
+ "step": 520
3659
+ }
3660
+ ],
3661
+ "logging_steps": 1.0,
3662
+ "max_steps": 520,
3663
+ "num_input_tokens_seen": 0,
3664
+ "num_train_epochs": 1,
3665
+ "save_steps": 0,
3666
+ "stateful_callbacks": {
3667
+ "TrainerControl": {
3668
+ "args": {
3669
+ "should_epoch_stop": false,
3670
+ "should_evaluate": false,
3671
+ "should_log": false,
3672
+ "should_save": true,
3673
+ "should_training_stop": true
3674
+ },
3675
+ "attributes": {}
3676
+ }
3677
+ },
3678
+ "total_flos": 2.602241188744397e+16,
3679
+ "train_batch_size": 1,
3680
+ "trial_name": null,
3681
+ "trial_params": null
3682
+ }