Hizy commited on
Commit
4481768
·
verified ·
1 Parent(s): 440550f

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -41,3 +41,4 @@ web_rl_7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  osgenesis7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  osgenesis-llama/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  osgenesis-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
41
  osgenesis7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  osgenesis-llama/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  osgenesis-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ agenttrek-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
agenttrek-llama/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
agenttrek-llama/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128009,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "transformers_version": "4.57.1",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
agenttrek-llama/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128009,
6
+ 128001,
7
+ 128008,
8
+ 128009
9
+ ],
10
+ "pad_token_id": 128009,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
+ "transformers_version": "4.57.1"
14
+ }
agenttrek-llama/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a521ade18b8ae83283e0cbdd7e0f4085c799b6137e0d5ac1664a48d621b8ff72
3
+ size 4976698672
agenttrek-llama/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3765f472158689bcb0d7ce074d79b643a131addc0bcdfabf67b873901ca961f0
3
+ size 4999802720
agenttrek-llama/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20a77881c1a386158a432f8d261c5daf487cacedf79c1b85f220ee2869667cf
3
+ size 4915916176
agenttrek-llama/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581be640baaabea07ca26e23c1b721b570f943b1e43710f731adc0f041009efb
3
+ size 1168138808
agenttrek-llama/model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 266240,
4
+ "total_size": 16060522496
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.norm.weight": "model-00004-of-00004.safetensors"
298
+ }
299
+ }
agenttrek-llama/runs/Dec13_20-58-50_hgx002/events.out.tfevents.1765632347.hgx002 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69539b93cf85a2e06e40a5d2569468cb4a1ccca6a61c92ff384b9d3ab26a398
3
+ size 9389
agenttrek-llama/runs/Dec13_23-12-51_hgx002/events.out.tfevents.1765640509.hgx002 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711cbd7e0eeb8385532eb02426aaa8622e127706b4e838835fb738cb0f22836b
3
+ size 42696
agenttrek-llama/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
+ }
agenttrek-llama/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
agenttrek-llama/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
agenttrek-llama/trainer_log.jsonl ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 4440, "loss": 1.0305, "lr": 2.0270270270270273e-07, "epoch": 0.006760182524928173, "percentage": 0.23, "elapsed_time": "0:07:21", "remaining_time": "2 days, 6:17:05"}
2
+ {"current_steps": 20, "total_steps": 4440, "loss": 0.9433, "lr": 4.27927927927928e-07, "epoch": 0.013520365049856346, "percentage": 0.45, "elapsed_time": "0:13:21", "remaining_time": "2 days, 1:13:05"}
3
+ {"current_steps": 30, "total_steps": 4440, "loss": 0.7961, "lr": 6.531531531531532e-07, "epoch": 0.020280547574784518, "percentage": 0.68, "elapsed_time": "0:18:42", "remaining_time": "1 day, 21:50:11"}
4
+ {"current_steps": 40, "total_steps": 4440, "loss": 0.6703, "lr": 8.783783783783785e-07, "epoch": 0.027040730099712692, "percentage": 0.9, "elapsed_time": "0:24:20", "remaining_time": "1 day, 20:38:15"}
5
+ {"current_steps": 50, "total_steps": 4440, "loss": 0.5868, "lr": 1.1036036036036037e-06, "epoch": 0.03380091262464086, "percentage": 1.13, "elapsed_time": "0:30:05", "remaining_time": "1 day, 20:02:03"}
6
+ {"current_steps": 60, "total_steps": 4440, "loss": 0.5074, "lr": 1.328828828828829e-06, "epoch": 0.040561095149569036, "percentage": 1.35, "elapsed_time": "0:36:32", "remaining_time": "1 day, 20:27:27"}
7
+ {"current_steps": 70, "total_steps": 4440, "loss": 0.4983, "lr": 1.5540540540540541e-06, "epoch": 0.04732127767449721, "percentage": 1.58, "elapsed_time": "0:41:52", "remaining_time": "1 day, 19:34:41"}
8
+ {"current_steps": 80, "total_steps": 4440, "loss": 0.497, "lr": 1.7792792792792792e-06, "epoch": 0.054081460199425384, "percentage": 1.8, "elapsed_time": "0:47:46", "remaining_time": "1 day, 19:23:48"}
9
+ {"current_steps": 90, "total_steps": 4440, "loss": 0.4695, "lr": 2.0045045045045045e-06, "epoch": 0.06084164272435356, "percentage": 2.03, "elapsed_time": "0:53:25", "remaining_time": "1 day, 19:02:33"}
10
+ {"current_steps": 100, "total_steps": 4440, "loss": 0.4408, "lr": 2.22972972972973e-06, "epoch": 0.06760182524928172, "percentage": 2.25, "elapsed_time": "0:59:13", "remaining_time": "1 day, 18:50:41"}
11
+ {"current_steps": 110, "total_steps": 4440, "loss": 0.4215, "lr": 2.454954954954955e-06, "epoch": 0.0743620077742099, "percentage": 2.48, "elapsed_time": "1:05:12", "remaining_time": "1 day, 18:46:50"}
12
+ {"current_steps": 120, "total_steps": 4440, "loss": 0.4222, "lr": 2.6801801801801803e-06, "epoch": 0.08112219029913807, "percentage": 2.7, "elapsed_time": "1:10:49", "remaining_time": "1 day, 18:29:49"}
13
+ {"current_steps": 130, "total_steps": 4440, "loss": 0.4297, "lr": 2.9054054054054054e-06, "epoch": 0.08788237282406625, "percentage": 2.93, "elapsed_time": "1:16:34", "remaining_time": "1 day, 18:18:51"}
14
+ {"current_steps": 140, "total_steps": 4440, "loss": 0.4132, "lr": 3.130630630630631e-06, "epoch": 0.09464255534899442, "percentage": 3.15, "elapsed_time": "1:22:20", "remaining_time": "1 day, 18:09:03"}
15
+ {"current_steps": 150, "total_steps": 4440, "loss": 0.4123, "lr": 3.3558558558558565e-06, "epoch": 0.1014027378739226, "percentage": 3.38, "elapsed_time": "1:28:13", "remaining_time": "1 day, 18:03:20"}
16
+ {"current_steps": 160, "total_steps": 4440, "loss": 0.4022, "lr": 3.5810810810810816e-06, "epoch": 0.10816292039885077, "percentage": 3.6, "elapsed_time": "1:33:55", "remaining_time": "1 day, 17:52:40"}
17
+ {"current_steps": 170, "total_steps": 4440, "loss": 0.417, "lr": 3.8063063063063067e-06, "epoch": 0.11492310292377894, "percentage": 3.83, "elapsed_time": "1:39:44", "remaining_time": "1 day, 17:45:22"}
18
+ {"current_steps": 180, "total_steps": 4440, "loss": 0.4137, "lr": 4.031531531531531e-06, "epoch": 0.12168328544870712, "percentage": 4.05, "elapsed_time": "1:45:02", "remaining_time": "1 day, 17:25:54"}
19
+ {"current_steps": 190, "total_steps": 4440, "loss": 0.3838, "lr": 4.256756756756757e-06, "epoch": 0.1284434679736353, "percentage": 4.28, "elapsed_time": "1:50:46", "remaining_time": "1 day, 17:17:46"}
20
+ {"current_steps": 200, "total_steps": 4440, "loss": 0.3933, "lr": 4.4819819819819824e-06, "epoch": 0.13520365049856345, "percentage": 4.5, "elapsed_time": "1:56:27", "remaining_time": "1 day, 17:08:52"}
21
+ {"current_steps": 210, "total_steps": 4440, "loss": 0.418, "lr": 4.707207207207208e-06, "epoch": 0.14196383302349164, "percentage": 4.73, "elapsed_time": "2:02:05", "remaining_time": "1 day, 16:59:10"}
22
+ {"current_steps": 220, "total_steps": 4440, "loss": 0.4068, "lr": 4.932432432432433e-06, "epoch": 0.1487240155484198, "percentage": 4.95, "elapsed_time": "2:07:40", "remaining_time": "1 day, 16:48:54"}
23
+ {"current_steps": 230, "total_steps": 4440, "loss": 0.4122, "lr": 5.157657657657657e-06, "epoch": 0.15548419807334798, "percentage": 5.18, "elapsed_time": "2:13:02", "remaining_time": "1 day, 16:35:11"}
24
+ {"current_steps": 240, "total_steps": 4440, "loss": 0.4195, "lr": 5.382882882882884e-06, "epoch": 0.16224438059827614, "percentage": 5.41, "elapsed_time": "2:18:54", "remaining_time": "1 day, 16:30:59"}
25
+ {"current_steps": 250, "total_steps": 4440, "loss": 0.3922, "lr": 5.608108108108109e-06, "epoch": 0.16900456312320433, "percentage": 5.63, "elapsed_time": "2:24:42", "remaining_time": "1 day, 16:25:11"}
26
+ {"current_steps": 260, "total_steps": 4440, "loss": 0.3971, "lr": 5.833333333333334e-06, "epoch": 0.1757647456481325, "percentage": 5.86, "elapsed_time": "2:30:41", "remaining_time": "1 day, 16:22:41"}
27
+ {"current_steps": 270, "total_steps": 4440, "loss": 0.4135, "lr": 6.0585585585585595e-06, "epoch": 0.18252492817306068, "percentage": 6.08, "elapsed_time": "2:36:37", "remaining_time": "1 day, 16:19:03"}
28
+ {"current_steps": 280, "total_steps": 4440, "loss": 0.4021, "lr": 6.283783783783784e-06, "epoch": 0.18928511069798884, "percentage": 6.31, "elapsed_time": "2:42:04", "remaining_time": "1 day, 16:08:04"}
29
+ {"current_steps": 290, "total_steps": 4440, "loss": 0.4159, "lr": 6.50900900900901e-06, "epoch": 0.19604529322291703, "percentage": 6.53, "elapsed_time": "2:47:39", "remaining_time": "1 day, 15:59:16"}
30
+ {"current_steps": 300, "total_steps": 4440, "loss": 0.4058, "lr": 6.734234234234235e-06, "epoch": 0.2028054757478452, "percentage": 6.76, "elapsed_time": "2:53:47", "remaining_time": "1 day, 15:58:23"}
31
+ {"current_steps": 310, "total_steps": 4440, "loss": 0.4202, "lr": 6.95945945945946e-06, "epoch": 0.20956565827277338, "percentage": 6.98, "elapsed_time": "2:59:36", "remaining_time": "1 day, 15:52:45"}
32
+ {"current_steps": 320, "total_steps": 4440, "loss": 0.4018, "lr": 7.1846846846846855e-06, "epoch": 0.21632584079770154, "percentage": 7.21, "elapsed_time": "3:05:17", "remaining_time": "1 day, 15:45:35"}
33
+ {"current_steps": 330, "total_steps": 4440, "loss": 0.3997, "lr": 7.40990990990991e-06, "epoch": 0.22308602332262972, "percentage": 7.43, "elapsed_time": "3:11:00", "remaining_time": "1 day, 15:39:00"}
34
+ {"current_steps": 340, "total_steps": 4440, "loss": 0.4172, "lr": 7.635135135135135e-06, "epoch": 0.22984620584755788, "percentage": 7.66, "elapsed_time": "3:16:54", "remaining_time": "1 day, 15:34:29"}
35
+ {"current_steps": 350, "total_steps": 4440, "loss": 0.3972, "lr": 7.860360360360361e-06, "epoch": 0.23660638837248607, "percentage": 7.88, "elapsed_time": "3:22:36", "remaining_time": "1 day, 15:27:43"}
36
+ {"current_steps": 360, "total_steps": 4440, "loss": 0.4076, "lr": 8.085585585585586e-06, "epoch": 0.24336657089741423, "percentage": 8.11, "elapsed_time": "3:28:42", "remaining_time": "1 day, 15:25:24"}
37
+ {"current_steps": 370, "total_steps": 4440, "loss": 0.4114, "lr": 8.31081081081081e-06, "epoch": 0.2501267534223424, "percentage": 8.33, "elapsed_time": "3:34:43", "remaining_time": "1 day, 15:22:03"}
38
+ {"current_steps": 380, "total_steps": 4440, "loss": 0.397, "lr": 8.536036036036037e-06, "epoch": 0.2568869359472706, "percentage": 8.56, "elapsed_time": "3:40:31", "remaining_time": "1 day, 15:16:09"}
39
+ {"current_steps": 390, "total_steps": 4440, "loss": 0.4213, "lr": 8.761261261261262e-06, "epoch": 0.26364711847219874, "percentage": 8.78, "elapsed_time": "3:46:19", "remaining_time": "1 day, 15:10:13"}
40
+ {"current_steps": 400, "total_steps": 4440, "loss": 0.42, "lr": 8.986486486486488e-06, "epoch": 0.2704073009971269, "percentage": 9.01, "elapsed_time": "3:52:02", "remaining_time": "1 day, 15:03:37"}
41
+ {"current_steps": 410, "total_steps": 4440, "loss": 0.4115, "lr": 9.211711711711713e-06, "epoch": 0.2771674835220551, "percentage": 9.23, "elapsed_time": "3:57:50", "remaining_time": "1 day, 14:57:45"}
42
+ {"current_steps": 420, "total_steps": 4440, "loss": 0.4276, "lr": 9.436936936936937e-06, "epoch": 0.2839276660469833, "percentage": 9.46, "elapsed_time": "4:03:35", "remaining_time": "1 day, 14:51:32"}
43
+ {"current_steps": 430, "total_steps": 4440, "loss": 0.4195, "lr": 9.662162162162164e-06, "epoch": 0.29068784857191143, "percentage": 9.68, "elapsed_time": "4:09:24", "remaining_time": "1 day, 14:45:49"}
44
+ {"current_steps": 440, "total_steps": 4440, "loss": 0.4181, "lr": 9.887387387387388e-06, "epoch": 0.2974480310968396, "percentage": 9.91, "elapsed_time": "4:14:45", "remaining_time": "1 day, 14:36:01"}
45
+ {"current_steps": 450, "total_steps": 4440, "loss": 0.4128, "lr": 9.999961369685454e-06, "epoch": 0.3042082136217678, "percentage": 10.14, "elapsed_time": "4:20:36", "remaining_time": "1 day, 14:30:43"}
46
+ {"current_steps": 460, "total_steps": 4440, "loss": 0.4055, "lr": 9.999652330750595e-06, "epoch": 0.31096839614669597, "percentage": 10.36, "elapsed_time": "4:26:48", "remaining_time": "1 day, 14:28:26"}
47
+ {"current_steps": 470, "total_steps": 4440, "loss": 0.4012, "lr": 9.99903427198204e-06, "epoch": 0.31772857867162413, "percentage": 10.59, "elapsed_time": "4:32:27", "remaining_time": "1 day, 14:21:27"}
48
+ {"current_steps": 480, "total_steps": 4440, "loss": 0.3968, "lr": 9.998107231580925e-06, "epoch": 0.3244887611965523, "percentage": 10.81, "elapsed_time": "4:38:38", "remaining_time": "1 day, 14:18:48"}
49
+ {"current_steps": 490, "total_steps": 4440, "loss": 0.4192, "lr": 9.99687126684601e-06, "epoch": 0.3312489437214805, "percentage": 11.04, "elapsed_time": "4:44:11", "remaining_time": "1 day, 14:10:55"}
50
+ {"current_steps": 500, "total_steps": 4440, "loss": 0.4109, "lr": 9.995326454170132e-06, "epoch": 0.33800912624640866, "percentage": 11.26, "elapsed_time": "4:49:44", "remaining_time": "1 day, 14:03:10"}
51
+ {"current_steps": 500, "total_steps": 4440, "eval_loss": 0.41546937823295593, "epoch": 0.33800912624640866, "percentage": 11.26, "elapsed_time": "5:11:48", "remaining_time": "1 day, 16:57:03"}
52
+ {"current_steps": 510, "total_steps": 4440, "loss": 0.4122, "lr": 9.993472889035478e-06, "epoch": 0.3447693087713368, "percentage": 11.49, "elapsed_time": "5:17:48", "remaining_time": "1 day, 16:48:57"}
53
+ {"current_steps": 520, "total_steps": 4440, "loss": 0.4068, "lr": 9.991310686007694e-06, "epoch": 0.351529491296265, "percentage": 11.71, "elapsed_time": "5:23:14", "remaining_time": "1 day, 16:36:40"}
54
+ {"current_steps": 530, "total_steps": 4440, "loss": 0.3922, "lr": 9.988839978728798e-06, "epoch": 0.3582896738211932, "percentage": 11.94, "elapsed_time": "5:28:53", "remaining_time": "1 day, 16:26:22"}
55
+ {"current_steps": 540, "total_steps": 4440, "loss": 0.4038, "lr": 9.986060919908917e-06, "epoch": 0.36504985634612136, "percentage": 12.16, "elapsed_time": "5:34:38", "remaining_time": "1 day, 16:16:50"}
56
+ {"current_steps": 550, "total_steps": 4440, "loss": 0.389, "lr": 9.982973681316854e-06, "epoch": 0.3718100388710495, "percentage": 12.39, "elapsed_time": "5:40:40", "remaining_time": "1 day, 16:09:27"}
57
+ {"current_steps": 560, "total_steps": 4440, "loss": 0.4, "lr": 9.97957845376947e-06, "epoch": 0.3785702213959777, "percentage": 12.61, "elapsed_time": "5:46:34", "remaining_time": "1 day, 16:01:13"}
58
+ {"current_steps": 570, "total_steps": 4440, "loss": 0.3925, "lr": 9.975875447119884e-06, "epoch": 0.38533040392090584, "percentage": 12.84, "elapsed_time": "5:51:46", "remaining_time": "1 day, 15:48:19"}
59
+ {"current_steps": 580, "total_steps": 4440, "loss": 0.4038, "lr": 9.971864890244514e-06, "epoch": 0.39209058644583406, "percentage": 13.06, "elapsed_time": "5:57:21", "remaining_time": "1 day, 15:38:17"}
60
+ {"current_steps": 590, "total_steps": 4440, "loss": 0.4008, "lr": 9.967547031028917e-06, "epoch": 0.3988507689707622, "percentage": 13.29, "elapsed_time": "6:03:04", "remaining_time": "1 day, 15:29:12"}
61
+ {"current_steps": 600, "total_steps": 4440, "loss": 0.4004, "lr": 9.962922136352482e-06, "epoch": 0.4056109514956904, "percentage": 13.51, "elapsed_time": "6:08:37", "remaining_time": "1 day, 15:19:10"}
62
+ {"current_steps": 610, "total_steps": 4440, "loss": 0.4057, "lr": 9.957990492071917e-06, "epoch": 0.41237113402061853, "percentage": 13.74, "elapsed_time": "6:14:30", "remaining_time": "1 day, 15:11:24"}
63
+ {"current_steps": 620, "total_steps": 4440, "loss": 0.4016, "lr": 9.9527524030036e-06, "epoch": 0.41913131654554675, "percentage": 13.96, "elapsed_time": "6:20:42", "remaining_time": "1 day, 15:05:38"}
64
+ {"current_steps": 630, "total_steps": 4440, "loss": 0.3788, "lr": 9.947208192904722e-06, "epoch": 0.4258914990704749, "percentage": 14.19, "elapsed_time": "6:26:24", "remaining_time": "1 day, 14:56:49"}
65
+ {"current_steps": 640, "total_steps": 4440, "loss": 0.4022, "lr": 9.941358204453294e-06, "epoch": 0.43265168159540307, "percentage": 14.41, "elapsed_time": "6:31:57", "remaining_time": "1 day, 14:47:14"}
66
+ {"current_steps": 650, "total_steps": 4440, "loss": 0.3795, "lr": 9.935202799226941e-06, "epoch": 0.43941186412033123, "percentage": 14.64, "elapsed_time": "6:37:47", "remaining_time": "1 day, 14:39:23"}
67
+ {"current_steps": 660, "total_steps": 4440, "loss": 0.3841, "lr": 9.928742357680586e-06, "epoch": 0.44617204664525945, "percentage": 14.86, "elapsed_time": "6:43:38", "remaining_time": "1 day, 14:31:45"}
68
+ {"current_steps": 670, "total_steps": 4440, "loss": 0.3809, "lr": 9.9219772791229e-06, "epoch": 0.4529322291701876, "percentage": 15.09, "elapsed_time": "6:49:30", "remaining_time": "1 day, 14:24:13"}
69
+ {"current_steps": 680, "total_steps": 4440, "loss": 0.3934, "lr": 9.914907981691656e-06, "epoch": 0.45969241169511577, "percentage": 15.32, "elapsed_time": "6:55:29", "remaining_time": "1 day, 14:17:24"}
70
+ {"current_steps": 690, "total_steps": 4440, "loss": 0.3975, "lr": 9.907534902327855e-06, "epoch": 0.4664525942200439, "percentage": 15.54, "elapsed_time": "7:01:21", "remaining_time": "1 day, 14:09:58"}
71
+ {"current_steps": 700, "total_steps": 4440, "loss": 0.38, "lr": 9.899858496748738e-06, "epoch": 0.47321277674497214, "percentage": 15.77, "elapsed_time": "7:06:34", "remaining_time": "1 day, 13:59:08"}
72
+ {"current_steps": 710, "total_steps": 4440, "loss": 0.3789, "lr": 9.891879239419609e-06, "epoch": 0.4799729592699003, "percentage": 15.99, "elapsed_time": "7:12:25", "remaining_time": "1 day, 13:51:46"}
73
+ {"current_steps": 720, "total_steps": 4440, "loss": 0.3954, "lr": 9.883597623524518e-06, "epoch": 0.48673314179482846, "percentage": 16.22, "elapsed_time": "7:18:22", "remaining_time": "1 day, 13:44:56"}
74
+ {"current_steps": 730, "total_steps": 4440, "loss": 0.3816, "lr": 9.875014160935773e-06, "epoch": 0.4934933243197566, "percentage": 16.44, "elapsed_time": "7:24:17", "remaining_time": "1 day, 13:37:59"}
75
+ {"current_steps": 740, "total_steps": 4440, "loss": 0.3596, "lr": 9.866129382182295e-06, "epoch": 0.5002535068446848, "percentage": 16.67, "elapsed_time": "7:29:58", "remaining_time": "1 day, 13:29:53"}
76
+ {"current_steps": 750, "total_steps": 4440, "loss": 0.3723, "lr": 9.856943836416844e-06, "epoch": 0.507013689369613, "percentage": 16.89, "elapsed_time": "7:35:24", "remaining_time": "1 day, 13:20:34"}
77
+ {"current_steps": 760, "total_steps": 4440, "loss": 0.3836, "lr": 9.847458091382057e-06, "epoch": 0.5137738718945412, "percentage": 17.12, "elapsed_time": "7:41:13", "remaining_time": "1 day, 13:13:17"}
78
+ {"current_steps": 770, "total_steps": 4440, "loss": 0.3764, "lr": 9.837672733375377e-06, "epoch": 0.5205340544194693, "percentage": 17.34, "elapsed_time": "7:47:00", "remaining_time": "1 day, 13:05:53"}
79
+ {"current_steps": 780, "total_steps": 4440, "loss": 0.3801, "lr": 9.827588367212797e-06, "epoch": 0.5272942369443975, "percentage": 17.57, "elapsed_time": "7:52:37", "remaining_time": "1 day, 12:57:42"}
80
+ {"current_steps": 790, "total_steps": 4440, "loss": 0.3732, "lr": 9.81720561619149e-06, "epoch": 0.5340544194693256, "percentage": 17.79, "elapsed_time": "7:58:32", "remaining_time": "1 day, 12:50:57"}
81
+ {"current_steps": 800, "total_steps": 4440, "loss": 0.3607, "lr": 9.806525122051276e-06, "epoch": 0.5408146019942538, "percentage": 18.02, "elapsed_time": "8:04:28", "remaining_time": "1 day, 12:44:19"}
82
+ {"current_steps": 810, "total_steps": 4440, "loss": 0.3756, "lr": 9.795547544934964e-06, "epoch": 0.5475747845191821, "percentage": 18.24, "elapsed_time": "8:10:12", "remaining_time": "1 day, 12:36:50"}
83
+ {"current_steps": 820, "total_steps": 4440, "loss": 0.3597, "lr": 9.784273563347542e-06, "epoch": 0.5543349670441102, "percentage": 18.47, "elapsed_time": "8:15:37", "remaining_time": "1 day, 12:28:00"}
84
+ {"current_steps": 830, "total_steps": 4440, "loss": 0.3694, "lr": 9.772703874114246e-06, "epoch": 0.5610951495690384, "percentage": 18.69, "elapsed_time": "8:21:24", "remaining_time": "1 day, 12:20:48"}
85
+ {"current_steps": 840, "total_steps": 4440, "loss": 0.3799, "lr": 9.760839192337487e-06, "epoch": 0.5678553320939665, "percentage": 18.92, "elapsed_time": "8:27:05", "remaining_time": "1 day, 12:13:13"}
86
+ {"current_steps": 850, "total_steps": 4440, "loss": 0.3771, "lr": 9.74868025135266e-06, "epoch": 0.5746155146188947, "percentage": 19.14, "elapsed_time": "8:32:29", "remaining_time": "1 day, 12:04:30"}
87
+ {"current_steps": 860, "total_steps": 4440, "loss": 0.3817, "lr": 9.7362278026828e-06, "epoch": 0.5813756971438229, "percentage": 19.37, "elapsed_time": "8:38:15", "remaining_time": "1 day, 11:57:26"}
88
+ {"current_steps": 870, "total_steps": 4440, "loss": 0.3755, "lr": 9.723482615992153e-06, "epoch": 0.588135879668751, "percentage": 19.59, "elapsed_time": "8:44:14", "remaining_time": "1 day, 11:51:09"}
89
+ {"current_steps": 880, "total_steps": 4440, "loss": 0.379, "lr": 9.710445479038585e-06, "epoch": 0.5948960621936792, "percentage": 19.82, "elapsed_time": "8:49:56", "remaining_time": "1 day, 11:43:52"}
90
+ {"current_steps": 890, "total_steps": 4440, "loss": 0.3648, "lr": 9.697117197624903e-06, "epoch": 0.6016562447186073, "percentage": 20.05, "elapsed_time": "8:55:28", "remaining_time": "1 day, 11:35:54"}
91
+ {"current_steps": 900, "total_steps": 4440, "loss": 0.3537, "lr": 9.683498595549058e-06, "epoch": 0.6084164272435356, "percentage": 20.27, "elapsed_time": "9:01:00", "remaining_time": "1 day, 11:27:58"}
92
+ {"current_steps": 910, "total_steps": 4440, "loss": 0.3706, "lr": 9.669590514553202e-06, "epoch": 0.6151766097684638, "percentage": 20.5, "elapsed_time": "9:07:02", "remaining_time": "1 day, 11:22:01"}
93
+ {"current_steps": 920, "total_steps": 4440, "loss": 0.3829, "lr": 9.65539381427169e-06, "epoch": 0.6219367922933919, "percentage": 20.72, "elapsed_time": "9:12:44", "remaining_time": "1 day, 11:14:50"}
94
+ {"current_steps": 930, "total_steps": 4440, "loss": 0.3583, "lr": 9.640909372177923e-06, "epoch": 0.6286969748183201, "percentage": 20.95, "elapsed_time": "9:18:37", "remaining_time": "1 day, 11:08:20"}
95
+ {"current_steps": 940, "total_steps": 4440, "loss": 0.3846, "lr": 9.62613808353013e-06, "epoch": 0.6354571573432483, "percentage": 21.17, "elapsed_time": "9:24:38", "remaining_time": "1 day, 11:02:24"}
96
+ {"current_steps": 950, "total_steps": 4440, "loss": 0.376, "lr": 9.611080861316029e-06, "epoch": 0.6422173398681764, "percentage": 21.4, "elapsed_time": "9:30:20", "remaining_time": "1 day, 10:55:14"}
97
+ {"current_steps": 960, "total_steps": 4440, "loss": 0.3594, "lr": 9.595738636196392e-06, "epoch": 0.6489775223931046, "percentage": 21.62, "elapsed_time": "9:35:53", "remaining_time": "1 day, 10:47:35"}
98
+ {"current_steps": 970, "total_steps": 4440, "loss": 0.3763, "lr": 9.580112356447528e-06, "epoch": 0.6557377049180327, "percentage": 21.85, "elapsed_time": "9:42:03", "remaining_time": "1 day, 10:42:11"}
99
+ {"current_steps": 980, "total_steps": 4440, "loss": 0.3539, "lr": 9.56420298790267e-06, "epoch": 0.662497887442961, "percentage": 22.07, "elapsed_time": "9:47:53", "remaining_time": "1 day, 10:35:36"}
100
+ {"current_steps": 990, "total_steps": 4440, "loss": 0.3686, "lr": 9.548011513892274e-06, "epoch": 0.6692580699678892, "percentage": 22.3, "elapsed_time": "9:53:17", "remaining_time": "1 day, 10:27:30"}
101
+ {"current_steps": 1000, "total_steps": 4440, "loss": 0.3645, "lr": 9.531538935183252e-06, "epoch": 0.6760182524928173, "percentage": 22.52, "elapsed_time": "9:59:07", "remaining_time": "1 day, 10:21:01"}
102
+ {"current_steps": 1000, "total_steps": 4440, "eval_loss": 0.36739876866340637, "epoch": 0.6760182524928173, "percentage": 22.52, "elapsed_time": "10:21:11", "remaining_time": "1 day, 11:36:52"}
103
+ {"current_steps": 1010, "total_steps": 4440, "loss": 0.3686, "lr": 9.5147862699171e-06, "epoch": 0.6827784350177455, "percentage": 22.75, "elapsed_time": "10:27:08", "remaining_time": "1 day, 11:29:48"}
104
+ {"current_steps": 1020, "total_steps": 4440, "loss": 0.3736, "lr": 9.497754553546992e-06, "epoch": 0.6895386175426736, "percentage": 22.97, "elapsed_time": "10:32:55", "remaining_time": "1 day, 11:22:08"}
105
+ {"current_steps": 1030, "total_steps": 4440, "loss": 0.3542, "lr": 9.480444838773753e-06, "epoch": 0.6962988000676018, "percentage": 23.2, "elapsed_time": "10:38:23", "remaining_time": "1 day, 11:13:30"}
106
+ {"current_steps": 1040, "total_steps": 4440, "loss": 0.3647, "lr": 9.462858195480814e-06, "epoch": 0.70305898259253, "percentage": 23.42, "elapsed_time": "10:43:48", "remaining_time": "1 day, 11:04:46"}
107
+ {"current_steps": 1050, "total_steps": 4440, "loss": 0.3797, "lr": 9.444995710668074e-06, "epoch": 0.7098191651174581, "percentage": 23.65, "elapsed_time": "10:49:46", "remaining_time": "1 day, 10:57:51"}
108
+ {"current_steps": 1060, "total_steps": 4440, "loss": 0.3413, "lr": 9.42685848838472e-06, "epoch": 0.7165793476423864, "percentage": 23.87, "elapsed_time": "10:55:53", "remaining_time": "1 day, 10:51:26"}
109
+ {"current_steps": 1070, "total_steps": 4440, "loss": 0.3676, "lr": 9.408447649660985e-06, "epoch": 0.7233395301673146, "percentage": 24.1, "elapsed_time": "11:02:07", "remaining_time": "1 day, 10:45:24"}
110
+ {"current_steps": 1080, "total_steps": 4440, "loss": 0.3685, "lr": 9.38976433243886e-06, "epoch": 0.7300997126922427, "percentage": 24.32, "elapsed_time": "11:07:33", "remaining_time": "1 day, 10:36:52"}
111
+ {"current_steps": 1090, "total_steps": 4440, "loss": 0.3708, "lr": 9.370809691501753e-06, "epoch": 0.7368598952171709, "percentage": 24.55, "elapsed_time": "11:13:17", "remaining_time": "1 day, 10:29:18"}
112
+ {"current_steps": 1100, "total_steps": 4440, "loss": 0.3546, "lr": 9.351584898403129e-06, "epoch": 0.743620077742099, "percentage": 24.77, "elapsed_time": "11:18:58", "remaining_time": "1 day, 10:21:36"}
113
+ {"current_steps": 1110, "total_steps": 4440, "loss": 0.351, "lr": 9.332091141394082e-06, "epoch": 0.7503802602670272, "percentage": 25.0, "elapsed_time": "11:24:31", "remaining_time": "1 day, 10:13:33"}
114
+ {"current_steps": 1120, "total_steps": 4440, "loss": 0.3561, "lr": 9.312329625349903e-06, "epoch": 0.7571404427919554, "percentage": 25.23, "elapsed_time": "11:29:54", "remaining_time": "1 day, 10:05:04"}
115
+ {"current_steps": 1130, "total_steps": 4440, "loss": 0.3621, "lr": 9.292301571695603e-06, "epoch": 0.7639006253168835, "percentage": 25.45, "elapsed_time": "11:35:37", "remaining_time": "1 day, 9:57:37"}
116
+ {"current_steps": 1140, "total_steps": 4440, "loss": 0.3481, "lr": 9.27200821833042e-06, "epoch": 0.7706608078418117, "percentage": 25.68, "elapsed_time": "11:41:39", "remaining_time": "1 day, 9:51:06"}
117
+ {"current_steps": 1150, "total_steps": 4440, "loss": 0.3518, "lr": 9.251450819551305e-06, "epoch": 0.77742099036674, "percentage": 25.9, "elapsed_time": "11:47:09", "remaining_time": "1 day, 9:43:06"}
118
+ {"current_steps": 1160, "total_steps": 4440, "loss": 0.3578, "lr": 9.2306306459754e-06, "epoch": 0.7841811728916681, "percentage": 26.13, "elapsed_time": "11:53:17", "remaining_time": "1 day, 9:36:52"}
119
+ {"current_steps": 1170, "total_steps": 4440, "loss": 0.3561, "lr": 9.2095489844615e-06, "epoch": 0.7909413554165963, "percentage": 26.35, "elapsed_time": "11:58:51", "remaining_time": "1 day, 9:29:08"}
120
+ {"current_steps": 1180, "total_steps": 4440, "loss": 0.3547, "lr": 9.188207138030518e-06, "epoch": 0.7977015379415244, "percentage": 26.58, "elapsed_time": "12:04:30", "remaining_time": "1 day, 9:21:35"}
121
+ {"current_steps": 1190, "total_steps": 4440, "loss": 0.3353, "lr": 9.166606425784939e-06, "epoch": 0.8044617204664526, "percentage": 26.8, "elapsed_time": "12:10:37", "remaining_time": "1 day, 9:15:23"}
122
+ {"current_steps": 1200, "total_steps": 4440, "loss": 0.3641, "lr": 9.144748182827305e-06, "epoch": 0.8112219029913807, "percentage": 27.03, "elapsed_time": "12:16:30", "remaining_time": "1 day, 9:08:34"}
123
+ {"current_steps": 1210, "total_steps": 4440, "loss": 0.35, "lr": 9.122633760177674e-06, "epoch": 0.8179820855163089, "percentage": 27.25, "elapsed_time": "12:22:26", "remaining_time": "1 day, 9:01:52"}
124
+ {"current_steps": 1220, "total_steps": 4440, "loss": 0.3483, "lr": 9.10026452469013e-06, "epoch": 0.8247422680412371, "percentage": 27.48, "elapsed_time": "12:28:07", "remaining_time": "1 day, 8:54:33"}
125
+ {"current_steps": 1230, "total_steps": 4440, "loss": 0.3463, "lr": 9.077641858968302e-06, "epoch": 0.8315024505661653, "percentage": 27.7, "elapsed_time": "12:33:32", "remaining_time": "1 day, 8:46:34"}
126
+ {"current_steps": 1240, "total_steps": 4440, "loss": 0.3493, "lr": 9.054767161279891e-06, "epoch": 0.8382626330910935, "percentage": 27.93, "elapsed_time": "12:39:30", "remaining_time": "1 day, 8:40:00"}
127
+ {"current_steps": 1250, "total_steps": 4440, "loss": 0.3691, "lr": 9.031641845470265e-06, "epoch": 0.8450228156160217, "percentage": 28.15, "elapsed_time": "12:45:08", "remaining_time": "1 day, 8:32:39"}
128
+ {"current_steps": 1260, "total_steps": 4440, "loss": 0.3404, "lr": 9.008267340875062e-06, "epoch": 0.8517829981409498, "percentage": 28.38, "elapsed_time": "12:51:11", "remaining_time": "1 day, 8:26:19"}
129
+ {"current_steps": 1270, "total_steps": 4440, "loss": 0.337, "lr": 8.984645092231839e-06, "epoch": 0.858543180665878, "percentage": 28.6, "elapsed_time": "12:57:00", "remaining_time": "1 day, 8:19:27"}
130
+ {"current_steps": 1280, "total_steps": 4440, "loss": 0.3531, "lr": 8.960776559590794e-06, "epoch": 0.8653033631908061, "percentage": 28.83, "elapsed_time": "13:02:33", "remaining_time": "1 day, 8:11:57"}
131
+ {"current_steps": 1290, "total_steps": 4440, "loss": 0.3468, "lr": 8.936663218224504e-06, "epoch": 0.8720635457157343, "percentage": 29.05, "elapsed_time": "13:07:43", "remaining_time": "1 day, 8:03:31"}
132
+ {"current_steps": 1300, "total_steps": 4440, "loss": 0.3451, "lr": 8.91230655853675e-06, "epoch": 0.8788237282406625, "percentage": 29.28, "elapsed_time": "13:13:10", "remaining_time": "1 day, 7:55:50"}
133
+ {"current_steps": 1310, "total_steps": 4440, "loss": 0.3606, "lr": 8.887708085970395e-06, "epoch": 0.8855839107655906, "percentage": 29.5, "elapsed_time": "13:18:54", "remaining_time": "1 day, 7:48:50"}
134
+ {"current_steps": 1320, "total_steps": 4440, "loss": 0.3362, "lr": 8.862869320914342e-06, "epoch": 0.8923440932905189, "percentage": 29.73, "elapsed_time": "13:24:39", "remaining_time": "1 day, 7:41:55"}
135
+ {"current_steps": 1330, "total_steps": 4440, "loss": 0.3556, "lr": 8.837791798609548e-06, "epoch": 0.899104275815447, "percentage": 29.95, "elapsed_time": "13:30:20", "remaining_time": "1 day, 7:34:51"}
136
+ {"current_steps": 1340, "total_steps": 4440, "loss": 0.3478, "lr": 8.812477069054145e-06, "epoch": 0.9058644583403752, "percentage": 30.18, "elapsed_time": "13:36:13", "remaining_time": "1 day, 7:28:17"}
137
+ {"current_steps": 1350, "total_steps": 4440, "loss": 0.3367, "lr": 8.786926696907635e-06, "epoch": 0.9126246408653034, "percentage": 30.41, "elapsed_time": "13:41:34", "remaining_time": "1 day, 7:20:30"}
138
+ {"current_steps": 1360, "total_steps": 4440, "loss": 0.3384, "lr": 8.761142261394176e-06, "epoch": 0.9193848233902315, "percentage": 30.63, "elapsed_time": "13:47:11", "remaining_time": "1 day, 7:13:21"}
139
+ {"current_steps": 1370, "total_steps": 4440, "loss": 0.3409, "lr": 8.735125356204982e-06, "epoch": 0.9261450059151597, "percentage": 30.86, "elapsed_time": "13:52:43", "remaining_time": "1 day, 7:06:02"}
140
+ {"current_steps": 1380, "total_steps": 4440, "loss": 0.3571, "lr": 8.708877589399805e-06, "epoch": 0.9329051884400879, "percentage": 31.08, "elapsed_time": "13:58:44", "remaining_time": "1 day, 6:59:49"}
141
+ {"current_steps": 1390, "total_steps": 4440, "loss": 0.3434, "lr": 8.682400583307562e-06, "epoch": 0.939665370965016, "percentage": 31.31, "elapsed_time": "14:04:23", "remaining_time": "1 day, 6:52:48"}
142
+ {"current_steps": 1400, "total_steps": 4440, "loss": 0.3469, "lr": 8.655695974426049e-06, "epoch": 0.9464255534899443, "percentage": 31.53, "elapsed_time": "14:10:00", "remaining_time": "1 day, 6:45:44"}
143
+ {"current_steps": 1410, "total_steps": 4440, "loss": 0.3567, "lr": 8.628765413320793e-06, "epoch": 0.9531857360148724, "percentage": 31.76, "elapsed_time": "14:15:58", "remaining_time": "1 day, 6:39:26"}
144
+ {"current_steps": 1420, "total_steps": 4440, "loss": 0.3295, "lr": 8.60161056452304e-06, "epoch": 0.9599459185398006, "percentage": 31.98, "elapsed_time": "14:21:37", "remaining_time": "1 day, 6:32:28"}
145
+ {"current_steps": 1430, "total_steps": 4440, "loss": 0.331, "lr": 8.574233106426866e-06, "epoch": 0.9667061010647288, "percentage": 32.21, "elapsed_time": "14:27:37", "remaining_time": "1 day, 6:26:16"}
146
+ {"current_steps": 1440, "total_steps": 4440, "loss": 0.353, "lr": 8.546634731185446e-06, "epoch": 0.9734662835896569, "percentage": 32.43, "elapsed_time": "14:33:18", "remaining_time": "1 day, 6:19:23"}
147
+ {"current_steps": 1450, "total_steps": 4440, "loss": 0.3316, "lr": 8.518817144606451e-06, "epoch": 0.9802264661145851, "percentage": 32.66, "elapsed_time": "14:38:46", "remaining_time": "1 day, 6:12:05"}
148
+ {"current_steps": 1460, "total_steps": 4440, "loss": 0.3628, "lr": 8.490782066046634e-06, "epoch": 0.9869866486395132, "percentage": 32.88, "elapsed_time": "14:44:26", "remaining_time": "1 day, 6:05:12"}
149
+ {"current_steps": 1470, "total_steps": 4440, "loss": 0.3231, "lr": 8.462531228305546e-06, "epoch": 0.9937468311644414, "percentage": 33.11, "elapsed_time": "14:50:25", "remaining_time": "1 day, 5:59:02"}
150
+ {"current_steps": 1480, "total_steps": 4440, "loss": 0.3394, "lr": 8.434066377518437e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "14:55:50", "remaining_time": "1 day, 5:51:41"}
151
+ {"current_steps": 1490, "total_steps": 4440, "loss": 0.2478, "lr": 8.405389273048334e-06, "epoch": 1.0067601825249282, "percentage": 33.56, "elapsed_time": "15:01:21", "remaining_time": "1 day, 5:44:33"}
152
+ {"current_steps": 1500, "total_steps": 4440, "loss": 0.2299, "lr": 8.376501687377297e-06, "epoch": 1.0135203650498563, "percentage": 33.78, "elapsed_time": "15:07:15", "remaining_time": "1 day, 5:38:13"}
153
+ {"current_steps": 1500, "total_steps": 4440, "eval_loss": 0.351112425327301, "epoch": 1.0135203650498563, "percentage": 33.78, "elapsed_time": "15:29:21", "remaining_time": "1 day, 6:21:33"}
154
+ {"current_steps": 1510, "total_steps": 4440, "loss": 0.2356, "lr": 8.347405405996862e-06, "epoch": 1.0202805475747845, "percentage": 34.01, "elapsed_time": "15:35:05", "remaining_time": "1 day, 6:14:26"}
155
+ {"current_steps": 1520, "total_steps": 4440, "loss": 0.2391, "lr": 8.318102227297683e-06, "epoch": 1.0270407300997126, "percentage": 34.23, "elapsed_time": "15:40:51", "remaining_time": "1 day, 6:07:25"}
156
+ {"current_steps": 1530, "total_steps": 4440, "loss": 0.2244, "lr": 8.288593962458379e-06, "epoch": 1.0338009126246408, "percentage": 34.46, "elapsed_time": "15:46:47", "remaining_time": "1 day, 6:00:45"}
157
+ {"current_steps": 1540, "total_steps": 4440, "loss": 0.2462, "lr": 8.25888243533359e-06, "epoch": 1.040561095149569, "percentage": 34.68, "elapsed_time": "15:52:29", "remaining_time": "1 day, 5:53:39"}
158
+ {"current_steps": 1550, "total_steps": 4440, "loss": 0.2415, "lr": 8.228969482341245e-06, "epoch": 1.0473212776744971, "percentage": 34.91, "elapsed_time": "15:58:11", "remaining_time": "1 day, 5:46:33"}
159
+ {"current_steps": 1560, "total_steps": 4440, "loss": 0.2361, "lr": 8.198856952349053e-06, "epoch": 1.0540814601994253, "percentage": 35.14, "elapsed_time": "16:03:45", "remaining_time": "1 day, 5:39:14"}
160
+ {"current_steps": 1570, "total_steps": 4440, "loss": 0.2338, "lr": 8.168546706560231e-06, "epoch": 1.0608416427243537, "percentage": 35.36, "elapsed_time": "16:09:22", "remaining_time": "1 day, 5:32:01"}
161
+ {"current_steps": 1580, "total_steps": 4440, "loss": 0.2316, "lr": 8.13804061839847e-06, "epoch": 1.0676018252492818, "percentage": 35.59, "elapsed_time": "16:15:05", "remaining_time": "1 day, 5:25:01"}
162
+ {"current_steps": 1590, "total_steps": 4440, "loss": 0.2455, "lr": 8.107340573392137e-06, "epoch": 1.07436200777421, "percentage": 35.81, "elapsed_time": "16:21:05", "remaining_time": "1 day, 5:18:33"}
163
+ {"current_steps": 1600, "total_steps": 4440, "loss": 0.2325, "lr": 8.076448469057733e-06, "epoch": 1.0811221902991381, "percentage": 36.04, "elapsed_time": "16:27:01", "remaining_time": "1 day, 5:11:57"}
164
+ {"current_steps": 1610, "total_steps": 4440, "loss": 0.2162, "lr": 8.045366214782613e-06, "epoch": 1.0878823728240663, "percentage": 36.26, "elapsed_time": "16:32:47", "remaining_time": "1 day, 5:05:06"}
165
+ {"current_steps": 1620, "total_steps": 4440, "loss": 0.2273, "lr": 8.014095731706972e-06, "epoch": 1.0946425553489945, "percentage": 36.49, "elapsed_time": "16:38:47", "remaining_time": "1 day, 4:58:37"}
166
+ {"current_steps": 1630, "total_steps": 4440, "loss": 0.2332, "lr": 7.982638952605097e-06, "epoch": 1.1014027378739226, "percentage": 36.71, "elapsed_time": "16:44:21", "remaining_time": "1 day, 4:51:25"}
167
+ {"current_steps": 1640, "total_steps": 4440, "loss": 0.2251, "lr": 7.950997821765915e-06, "epoch": 1.1081629203988508, "percentage": 36.94, "elapsed_time": "16:50:24", "remaining_time": "1 day, 4:45:05"}
168
+ {"current_steps": 1650, "total_steps": 4440, "loss": 0.2391, "lr": 7.919174294872807e-06, "epoch": 1.114923102923779, "percentage": 37.16, "elapsed_time": "16:56:23", "remaining_time": "1 day, 4:38:37"}
169
+ {"current_steps": 1660, "total_steps": 4440, "loss": 0.2455, "lr": 7.887170338882742e-06, "epoch": 1.121683285448707, "percentage": 37.39, "elapsed_time": "17:01:50", "remaining_time": "1 day, 4:31:16"}
170
+ {"current_steps": 1670, "total_steps": 4440, "loss": 0.2181, "lr": 7.854987931904696e-06, "epoch": 1.1284434679736353, "percentage": 37.61, "elapsed_time": "17:07:59", "remaining_time": "1 day, 4:25:06"}
171
+ {"current_steps": 1680, "total_steps": 4440, "loss": 0.2169, "lr": 7.822629063077395e-06, "epoch": 1.1352036504985634, "percentage": 37.84, "elapsed_time": "17:13:10", "remaining_time": "1 day, 4:17:21"}
172
+ {"current_steps": 1690, "total_steps": 4440, "loss": 0.2398, "lr": 7.790095732446359e-06, "epoch": 1.1419638330234916, "percentage": 38.06, "elapsed_time": "17:18:49", "remaining_time": "1 day, 4:10:23"}
173
+ {"current_steps": 1700, "total_steps": 4440, "loss": 0.2365, "lr": 7.757389950840294e-06, "epoch": 1.1487240155484197, "percentage": 38.29, "elapsed_time": "17:24:15", "remaining_time": "1 day, 4:03:05"}
174
+ {"current_steps": 1710, "total_steps": 4440, "loss": 0.2347, "lr": 7.724513739746801e-06, "epoch": 1.155484198073348, "percentage": 38.51, "elapsed_time": "17:30:08", "remaining_time": "1 day, 3:56:32"}
175
+ {"current_steps": 1720, "total_steps": 4440, "loss": 0.242, "lr": 7.691469131187432e-06, "epoch": 1.162244380598276, "percentage": 38.74, "elapsed_time": "17:35:58", "remaining_time": "1 day, 3:49:54"}
agenttrek-llama/trainer_state.json ADDED
@@ -0,0 +1,1108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0135203650498563,
6
+ "eval_steps": 500,
7
+ "global_step": 1500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.006760182524928173,
14
+ "grad_norm": 30.429955125606906,
15
+ "learning_rate": 2.0270270270270273e-07,
16
+ "loss": 1.0305,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.013520365049856346,
21
+ "grad_norm": 11.031569316357162,
22
+ "learning_rate": 4.27927927927928e-07,
23
+ "loss": 0.9433,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.020280547574784518,
28
+ "grad_norm": 7.568247729610925,
29
+ "learning_rate": 6.531531531531532e-07,
30
+ "loss": 0.7961,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.027040730099712692,
35
+ "grad_norm": 7.13506773134569,
36
+ "learning_rate": 8.783783783783785e-07,
37
+ "loss": 0.6703,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.03380091262464086,
42
+ "grad_norm": 5.13118234249973,
43
+ "learning_rate": 1.1036036036036037e-06,
44
+ "loss": 0.5868,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.040561095149569036,
49
+ "grad_norm": 5.539727298943678,
50
+ "learning_rate": 1.328828828828829e-06,
51
+ "loss": 0.5074,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.04732127767449721,
56
+ "grad_norm": 5.305287069709931,
57
+ "learning_rate": 1.5540540540540541e-06,
58
+ "loss": 0.4983,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.054081460199425384,
63
+ "grad_norm": 5.106611798846999,
64
+ "learning_rate": 1.7792792792792792e-06,
65
+ "loss": 0.497,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.06084164272435356,
70
+ "grad_norm": 4.582177338515729,
71
+ "learning_rate": 2.0045045045045045e-06,
72
+ "loss": 0.4695,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.06760182524928172,
77
+ "grad_norm": 4.739272582163485,
78
+ "learning_rate": 2.22972972972973e-06,
79
+ "loss": 0.4408,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.0743620077742099,
84
+ "grad_norm": 4.322112804201578,
85
+ "learning_rate": 2.454954954954955e-06,
86
+ "loss": 0.4215,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.08112219029913807,
91
+ "grad_norm": 4.480237396840778,
92
+ "learning_rate": 2.6801801801801803e-06,
93
+ "loss": 0.4222,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.08788237282406625,
98
+ "grad_norm": 4.588802640700157,
99
+ "learning_rate": 2.9054054054054054e-06,
100
+ "loss": 0.4297,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.09464255534899442,
105
+ "grad_norm": 3.634384371273362,
106
+ "learning_rate": 3.130630630630631e-06,
107
+ "loss": 0.4132,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.1014027378739226,
112
+ "grad_norm": 4.029617898426818,
113
+ "learning_rate": 3.3558558558558565e-06,
114
+ "loss": 0.4123,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.10816292039885077,
119
+ "grad_norm": 3.6780967071398005,
120
+ "learning_rate": 3.5810810810810816e-06,
121
+ "loss": 0.4022,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.11492310292377894,
126
+ "grad_norm": 3.8355903508595155,
127
+ "learning_rate": 3.8063063063063067e-06,
128
+ "loss": 0.417,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.12168328544870712,
133
+ "grad_norm": 3.8796259132382604,
134
+ "learning_rate": 4.031531531531531e-06,
135
+ "loss": 0.4137,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.1284434679736353,
140
+ "grad_norm": 3.513646073103006,
141
+ "learning_rate": 4.256756756756757e-06,
142
+ "loss": 0.3838,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.13520365049856345,
147
+ "grad_norm": 3.280829869725974,
148
+ "learning_rate": 4.4819819819819824e-06,
149
+ "loss": 0.3933,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.14196383302349164,
154
+ "grad_norm": 3.8684728373816877,
155
+ "learning_rate": 4.707207207207208e-06,
156
+ "loss": 0.418,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.1487240155484198,
161
+ "grad_norm": 3.430012571317074,
162
+ "learning_rate": 4.932432432432433e-06,
163
+ "loss": 0.4068,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.15548419807334798,
168
+ "grad_norm": 3.4236933785478594,
169
+ "learning_rate": 5.157657657657657e-06,
170
+ "loss": 0.4122,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.16224438059827614,
175
+ "grad_norm": 3.337506294944149,
176
+ "learning_rate": 5.382882882882884e-06,
177
+ "loss": 0.4195,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.16900456312320433,
182
+ "grad_norm": 4.340322941603959,
183
+ "learning_rate": 5.608108108108109e-06,
184
+ "loss": 0.3922,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.1757647456481325,
189
+ "grad_norm": 3.079365176995162,
190
+ "learning_rate": 5.833333333333334e-06,
191
+ "loss": 0.3971,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.18252492817306068,
196
+ "grad_norm": 3.1303889674723857,
197
+ "learning_rate": 6.0585585585585595e-06,
198
+ "loss": 0.4135,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.18928511069798884,
203
+ "grad_norm": 3.2972741045149605,
204
+ "learning_rate": 6.283783783783784e-06,
205
+ "loss": 0.4021,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.19604529322291703,
210
+ "grad_norm": 6.693630492235905,
211
+ "learning_rate": 6.50900900900901e-06,
212
+ "loss": 0.4159,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.2028054757478452,
217
+ "grad_norm": 2.9729373757056456,
218
+ "learning_rate": 6.734234234234235e-06,
219
+ "loss": 0.4058,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.20956565827277338,
224
+ "grad_norm": 2.95948849243511,
225
+ "learning_rate": 6.95945945945946e-06,
226
+ "loss": 0.4202,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.21632584079770154,
231
+ "grad_norm": 2.8167543124734618,
232
+ "learning_rate": 7.1846846846846855e-06,
233
+ "loss": 0.4018,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.22308602332262972,
238
+ "grad_norm": 2.8063934885840314,
239
+ "learning_rate": 7.40990990990991e-06,
240
+ "loss": 0.3997,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.22984620584755788,
245
+ "grad_norm": 3.1516244053144,
246
+ "learning_rate": 7.635135135135135e-06,
247
+ "loss": 0.4172,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.23660638837248607,
252
+ "grad_norm": 2.6885724493695715,
253
+ "learning_rate": 7.860360360360361e-06,
254
+ "loss": 0.3972,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.24336657089741423,
259
+ "grad_norm": 2.6078839515038528,
260
+ "learning_rate": 8.085585585585586e-06,
261
+ "loss": 0.4076,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.2501267534223424,
266
+ "grad_norm": 2.5241273124658434,
267
+ "learning_rate": 8.31081081081081e-06,
268
+ "loss": 0.4114,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.2568869359472706,
273
+ "grad_norm": 2.811459731213271,
274
+ "learning_rate": 8.536036036036037e-06,
275
+ "loss": 0.397,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.26364711847219874,
280
+ "grad_norm": 3.049745389493281,
281
+ "learning_rate": 8.761261261261262e-06,
282
+ "loss": 0.4213,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.2704073009971269,
287
+ "grad_norm": 2.7296156561054303,
288
+ "learning_rate": 8.986486486486488e-06,
289
+ "loss": 0.42,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.2771674835220551,
294
+ "grad_norm": 2.8072799681272285,
295
+ "learning_rate": 9.211711711711713e-06,
296
+ "loss": 0.4115,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.2839276660469833,
301
+ "grad_norm": 2.45386826986572,
302
+ "learning_rate": 9.436936936936937e-06,
303
+ "loss": 0.4276,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.29068784857191143,
308
+ "grad_norm": 2.6328350388772703,
309
+ "learning_rate": 9.662162162162164e-06,
310
+ "loss": 0.4195,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.2974480310968396,
315
+ "grad_norm": 2.5446377303913392,
316
+ "learning_rate": 9.887387387387388e-06,
317
+ "loss": 0.4181,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.3042082136217678,
322
+ "grad_norm": 2.5969527355663975,
323
+ "learning_rate": 9.999961369685454e-06,
324
+ "loss": 0.4128,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.31096839614669597,
329
+ "grad_norm": 2.771780495890244,
330
+ "learning_rate": 9.999652330750595e-06,
331
+ "loss": 0.4055,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.31772857867162413,
336
+ "grad_norm": 2.4553977895620336,
337
+ "learning_rate": 9.99903427198204e-06,
338
+ "loss": 0.4012,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.3244887611965523,
343
+ "grad_norm": 2.4098745339341456,
344
+ "learning_rate": 9.998107231580925e-06,
345
+ "loss": 0.3968,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.3312489437214805,
350
+ "grad_norm": 2.545785489303096,
351
+ "learning_rate": 9.99687126684601e-06,
352
+ "loss": 0.4192,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.33800912624640866,
357
+ "grad_norm": 2.6063200322372575,
358
+ "learning_rate": 9.995326454170132e-06,
359
+ "loss": 0.4109,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.33800912624640866,
364
+ "eval_loss": 0.41546937823295593,
365
+ "eval_runtime": 1323.9234,
366
+ "eval_samples_per_second": 3.973,
367
+ "eval_steps_per_second": 0.497,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 0.3447693087713368,
372
+ "grad_norm": 2.5250471936075582,
373
+ "learning_rate": 9.993472889035478e-06,
374
+ "loss": 0.4122,
375
+ "step": 510
376
+ },
377
+ {
378
+ "epoch": 0.351529491296265,
379
+ "grad_norm": 2.226305697507818,
380
+ "learning_rate": 9.991310686007694e-06,
381
+ "loss": 0.4068,
382
+ "step": 520
383
+ },
384
+ {
385
+ "epoch": 0.3582896738211932,
386
+ "grad_norm": 2.305497784945858,
387
+ "learning_rate": 9.988839978728798e-06,
388
+ "loss": 0.3922,
389
+ "step": 530
390
+ },
391
+ {
392
+ "epoch": 0.36504985634612136,
393
+ "grad_norm": 2.2810190229102267,
394
+ "learning_rate": 9.986060919908917e-06,
395
+ "loss": 0.4038,
396
+ "step": 540
397
+ },
398
+ {
399
+ "epoch": 0.3718100388710495,
400
+ "grad_norm": 2.0830775327743534,
401
+ "learning_rate": 9.982973681316854e-06,
402
+ "loss": 0.389,
403
+ "step": 550
404
+ },
405
+ {
406
+ "epoch": 0.3785702213959777,
407
+ "grad_norm": 2.412349310792309,
408
+ "learning_rate": 9.97957845376947e-06,
409
+ "loss": 0.4,
410
+ "step": 560
411
+ },
412
+ {
413
+ "epoch": 0.38533040392090584,
414
+ "grad_norm": 2.334930606027013,
415
+ "learning_rate": 9.975875447119884e-06,
416
+ "loss": 0.3925,
417
+ "step": 570
418
+ },
419
+ {
420
+ "epoch": 0.39209058644583406,
421
+ "grad_norm": 2.373633114437491,
422
+ "learning_rate": 9.971864890244514e-06,
423
+ "loss": 0.4038,
424
+ "step": 580
425
+ },
426
+ {
427
+ "epoch": 0.3988507689707622,
428
+ "grad_norm": 2.309096972224613,
429
+ "learning_rate": 9.967547031028917e-06,
430
+ "loss": 0.4008,
431
+ "step": 590
432
+ },
433
+ {
434
+ "epoch": 0.4056109514956904,
435
+ "grad_norm": 2.140294095106148,
436
+ "learning_rate": 9.962922136352482e-06,
437
+ "loss": 0.4004,
438
+ "step": 600
439
+ },
440
+ {
441
+ "epoch": 0.41237113402061853,
442
+ "grad_norm": 2.2849655710928287,
443
+ "learning_rate": 9.957990492071917e-06,
444
+ "loss": 0.4057,
445
+ "step": 610
446
+ },
447
+ {
448
+ "epoch": 0.41913131654554675,
449
+ "grad_norm": 2.092617163224422,
450
+ "learning_rate": 9.9527524030036e-06,
451
+ "loss": 0.4016,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 0.4258914990704749,
456
+ "grad_norm": 2.786668476771917,
457
+ "learning_rate": 9.947208192904722e-06,
458
+ "loss": 0.3788,
459
+ "step": 630
460
+ },
461
+ {
462
+ "epoch": 0.43265168159540307,
463
+ "grad_norm": 2.1368728170135873,
464
+ "learning_rate": 9.941358204453294e-06,
465
+ "loss": 0.4022,
466
+ "step": 640
467
+ },
468
+ {
469
+ "epoch": 0.43941186412033123,
470
+ "grad_norm": 2.03479655017632,
471
+ "learning_rate": 9.935202799226941e-06,
472
+ "loss": 0.3795,
473
+ "step": 650
474
+ },
475
+ {
476
+ "epoch": 0.44617204664525945,
477
+ "grad_norm": 2.1100436195870964,
478
+ "learning_rate": 9.928742357680586e-06,
479
+ "loss": 0.3841,
480
+ "step": 660
481
+ },
482
+ {
483
+ "epoch": 0.4529322291701876,
484
+ "grad_norm": 2.1376422874279952,
485
+ "learning_rate": 9.9219772791229e-06,
486
+ "loss": 0.3809,
487
+ "step": 670
488
+ },
489
+ {
490
+ "epoch": 0.45969241169511577,
491
+ "grad_norm": 2.2131150187295865,
492
+ "learning_rate": 9.914907981691656e-06,
493
+ "loss": 0.3934,
494
+ "step": 680
495
+ },
496
+ {
497
+ "epoch": 0.4664525942200439,
498
+ "grad_norm": 2.5997656656639023,
499
+ "learning_rate": 9.907534902327855e-06,
500
+ "loss": 0.3975,
501
+ "step": 690
502
+ },
503
+ {
504
+ "epoch": 0.47321277674497214,
505
+ "grad_norm": 1.9856693804357932,
506
+ "learning_rate": 9.899858496748738e-06,
507
+ "loss": 0.38,
508
+ "step": 700
509
+ },
510
+ {
511
+ "epoch": 0.4799729592699003,
512
+ "grad_norm": 2.217516603205192,
513
+ "learning_rate": 9.891879239419609e-06,
514
+ "loss": 0.3789,
515
+ "step": 710
516
+ },
517
+ {
518
+ "epoch": 0.48673314179482846,
519
+ "grad_norm": 2.0702819723867427,
520
+ "learning_rate": 9.883597623524518e-06,
521
+ "loss": 0.3954,
522
+ "step": 720
523
+ },
524
+ {
525
+ "epoch": 0.4934933243197566,
526
+ "grad_norm": 2.2207526501051387,
527
+ "learning_rate": 9.875014160935773e-06,
528
+ "loss": 0.3816,
529
+ "step": 730
530
+ },
531
+ {
532
+ "epoch": 0.5002535068446848,
533
+ "grad_norm": 2.0307571044715487,
534
+ "learning_rate": 9.866129382182295e-06,
535
+ "loss": 0.3596,
536
+ "step": 740
537
+ },
538
+ {
539
+ "epoch": 0.507013689369613,
540
+ "grad_norm": 2.0484361446295756,
541
+ "learning_rate": 9.856943836416844e-06,
542
+ "loss": 0.3723,
543
+ "step": 750
544
+ },
545
+ {
546
+ "epoch": 0.5137738718945412,
547
+ "grad_norm": 2.188933520806837,
548
+ "learning_rate": 9.847458091382057e-06,
549
+ "loss": 0.3836,
550
+ "step": 760
551
+ },
552
+ {
553
+ "epoch": 0.5205340544194693,
554
+ "grad_norm": 2.2059318749133343,
555
+ "learning_rate": 9.837672733375377e-06,
556
+ "loss": 0.3764,
557
+ "step": 770
558
+ },
559
+ {
560
+ "epoch": 0.5272942369443975,
561
+ "grad_norm": 2.0738552350322657,
562
+ "learning_rate": 9.827588367212797e-06,
563
+ "loss": 0.3801,
564
+ "step": 780
565
+ },
566
+ {
567
+ "epoch": 0.5340544194693256,
568
+ "grad_norm": 2.049788797772694,
569
+ "learning_rate": 9.81720561619149e-06,
570
+ "loss": 0.3732,
571
+ "step": 790
572
+ },
573
+ {
574
+ "epoch": 0.5408146019942538,
575
+ "grad_norm": 2.607021547053881,
576
+ "learning_rate": 9.806525122051276e-06,
577
+ "loss": 0.3607,
578
+ "step": 800
579
+ },
580
+ {
581
+ "epoch": 0.5475747845191821,
582
+ "grad_norm": 2.0297130039478573,
583
+ "learning_rate": 9.795547544934964e-06,
584
+ "loss": 0.3756,
585
+ "step": 810
586
+ },
587
+ {
588
+ "epoch": 0.5543349670441102,
589
+ "grad_norm": 2.135186067946862,
590
+ "learning_rate": 9.784273563347542e-06,
591
+ "loss": 0.3597,
592
+ "step": 820
593
+ },
594
+ {
595
+ "epoch": 0.5610951495690384,
596
+ "grad_norm": 1.8995362331712584,
597
+ "learning_rate": 9.772703874114246e-06,
598
+ "loss": 0.3694,
599
+ "step": 830
600
+ },
601
+ {
602
+ "epoch": 0.5678553320939665,
603
+ "grad_norm": 2.0415002686577775,
604
+ "learning_rate": 9.760839192337487e-06,
605
+ "loss": 0.3799,
606
+ "step": 840
607
+ },
608
+ {
609
+ "epoch": 0.5746155146188947,
610
+ "grad_norm": 2.1273417637254366,
611
+ "learning_rate": 9.74868025135266e-06,
612
+ "loss": 0.3771,
613
+ "step": 850
614
+ },
615
+ {
616
+ "epoch": 0.5813756971438229,
617
+ "grad_norm": 2.1781086970923575,
618
+ "learning_rate": 9.7362278026828e-06,
619
+ "loss": 0.3817,
620
+ "step": 860
621
+ },
622
+ {
623
+ "epoch": 0.588135879668751,
624
+ "grad_norm": 2.1564198664014667,
625
+ "learning_rate": 9.723482615992153e-06,
626
+ "loss": 0.3755,
627
+ "step": 870
628
+ },
629
+ {
630
+ "epoch": 0.5948960621936792,
631
+ "grad_norm": 2.2895864922611993,
632
+ "learning_rate": 9.710445479038585e-06,
633
+ "loss": 0.379,
634
+ "step": 880
635
+ },
636
+ {
637
+ "epoch": 0.6016562447186073,
638
+ "grad_norm": 1.983081982245503,
639
+ "learning_rate": 9.697117197624903e-06,
640
+ "loss": 0.3648,
641
+ "step": 890
642
+ },
643
+ {
644
+ "epoch": 0.6084164272435356,
645
+ "grad_norm": 2.091041703194283,
646
+ "learning_rate": 9.683498595549058e-06,
647
+ "loss": 0.3537,
648
+ "step": 900
649
+ },
650
+ {
651
+ "epoch": 0.6151766097684638,
652
+ "grad_norm": 2.236195435477624,
653
+ "learning_rate": 9.669590514553202e-06,
654
+ "loss": 0.3706,
655
+ "step": 910
656
+ },
657
+ {
658
+ "epoch": 0.6219367922933919,
659
+ "grad_norm": 1.8500568790108252,
660
+ "learning_rate": 9.65539381427169e-06,
661
+ "loss": 0.3829,
662
+ "step": 920
663
+ },
664
+ {
665
+ "epoch": 0.6286969748183201,
666
+ "grad_norm": 1.9798512403639599,
667
+ "learning_rate": 9.640909372177923e-06,
668
+ "loss": 0.3583,
669
+ "step": 930
670
+ },
671
+ {
672
+ "epoch": 0.6354571573432483,
673
+ "grad_norm": 2.001295874575185,
674
+ "learning_rate": 9.62613808353013e-06,
675
+ "loss": 0.3846,
676
+ "step": 940
677
+ },
678
+ {
679
+ "epoch": 0.6422173398681764,
680
+ "grad_norm": 2.119068814752592,
681
+ "learning_rate": 9.611080861316029e-06,
682
+ "loss": 0.376,
683
+ "step": 950
684
+ },
685
+ {
686
+ "epoch": 0.6489775223931046,
687
+ "grad_norm": 1.874754216889785,
688
+ "learning_rate": 9.595738636196392e-06,
689
+ "loss": 0.3594,
690
+ "step": 960
691
+ },
692
+ {
693
+ "epoch": 0.6557377049180327,
694
+ "grad_norm": 1.9814730374903968,
695
+ "learning_rate": 9.580112356447528e-06,
696
+ "loss": 0.3763,
697
+ "step": 970
698
+ },
699
+ {
700
+ "epoch": 0.662497887442961,
701
+ "grad_norm": 1.6054885549770077,
702
+ "learning_rate": 9.56420298790267e-06,
703
+ "loss": 0.3539,
704
+ "step": 980
705
+ },
706
+ {
707
+ "epoch": 0.6692580699678892,
708
+ "grad_norm": 1.9862942162587933,
709
+ "learning_rate": 9.548011513892274e-06,
710
+ "loss": 0.3686,
711
+ "step": 990
712
+ },
713
+ {
714
+ "epoch": 0.6760182524928173,
715
+ "grad_norm": 1.697925964076465,
716
+ "learning_rate": 9.531538935183252e-06,
717
+ "loss": 0.3645,
718
+ "step": 1000
719
+ },
720
+ {
721
+ "epoch": 0.6760182524928173,
722
+ "eval_loss": 0.36739876866340637,
723
+ "eval_runtime": 1323.0599,
724
+ "eval_samples_per_second": 3.976,
725
+ "eval_steps_per_second": 0.497,
726
+ "step": 1000
727
+ },
728
+ {
729
+ "epoch": 0.6827784350177455,
730
+ "grad_norm": 2.258646441282196,
731
+ "learning_rate": 9.5147862699171e-06,
732
+ "loss": 0.3686,
733
+ "step": 1010
734
+ },
735
+ {
736
+ "epoch": 0.6895386175426736,
737
+ "grad_norm": 1.9875295083096067,
738
+ "learning_rate": 9.497754553546992e-06,
739
+ "loss": 0.3736,
740
+ "step": 1020
741
+ },
742
+ {
743
+ "epoch": 0.6962988000676018,
744
+ "grad_norm": 1.9408896050189433,
745
+ "learning_rate": 9.480444838773753e-06,
746
+ "loss": 0.3542,
747
+ "step": 1030
748
+ },
749
+ {
750
+ "epoch": 0.70305898259253,
751
+ "grad_norm": 2.517314352432714,
752
+ "learning_rate": 9.462858195480814e-06,
753
+ "loss": 0.3647,
754
+ "step": 1040
755
+ },
756
+ {
757
+ "epoch": 0.7098191651174581,
758
+ "grad_norm": 2.045943843085583,
759
+ "learning_rate": 9.444995710668074e-06,
760
+ "loss": 0.3797,
761
+ "step": 1050
762
+ },
763
+ {
764
+ "epoch": 0.7165793476423864,
765
+ "grad_norm": 1.9093836961309305,
766
+ "learning_rate": 9.42685848838472e-06,
767
+ "loss": 0.3413,
768
+ "step": 1060
769
+ },
770
+ {
771
+ "epoch": 0.7233395301673146,
772
+ "grad_norm": 2.022174523080341,
773
+ "learning_rate": 9.408447649660985e-06,
774
+ "loss": 0.3676,
775
+ "step": 1070
776
+ },
777
+ {
778
+ "epoch": 0.7300997126922427,
779
+ "grad_norm": 1.8275705704002196,
780
+ "learning_rate": 9.38976433243886e-06,
781
+ "loss": 0.3685,
782
+ "step": 1080
783
+ },
784
+ {
785
+ "epoch": 0.7368598952171709,
786
+ "grad_norm": 1.7772669666798888,
787
+ "learning_rate": 9.370809691501753e-06,
788
+ "loss": 0.3708,
789
+ "step": 1090
790
+ },
791
+ {
792
+ "epoch": 0.743620077742099,
793
+ "grad_norm": 1.9218973995164992,
794
+ "learning_rate": 9.351584898403129e-06,
795
+ "loss": 0.3546,
796
+ "step": 1100
797
+ },
798
+ {
799
+ "epoch": 0.7503802602670272,
800
+ "grad_norm": 1.8585271029759325,
801
+ "learning_rate": 9.332091141394082e-06,
802
+ "loss": 0.351,
803
+ "step": 1110
804
+ },
805
+ {
806
+ "epoch": 0.7571404427919554,
807
+ "grad_norm": 1.8921724238963678,
808
+ "learning_rate": 9.312329625349903e-06,
809
+ "loss": 0.3561,
810
+ "step": 1120
811
+ },
812
+ {
813
+ "epoch": 0.7639006253168835,
814
+ "grad_norm": 2.699199676621496,
815
+ "learning_rate": 9.292301571695603e-06,
816
+ "loss": 0.3621,
817
+ "step": 1130
818
+ },
819
+ {
820
+ "epoch": 0.7706608078418117,
821
+ "grad_norm": 1.7918758876099616,
822
+ "learning_rate": 9.27200821833042e-06,
823
+ "loss": 0.3481,
824
+ "step": 1140
825
+ },
826
+ {
827
+ "epoch": 0.77742099036674,
828
+ "grad_norm": 1.6841732472542632,
829
+ "learning_rate": 9.251450819551305e-06,
830
+ "loss": 0.3518,
831
+ "step": 1150
832
+ },
833
+ {
834
+ "epoch": 0.7841811728916681,
835
+ "grad_norm": 1.8263599680378415,
836
+ "learning_rate": 9.2306306459754e-06,
837
+ "loss": 0.3578,
838
+ "step": 1160
839
+ },
840
+ {
841
+ "epoch": 0.7909413554165963,
842
+ "grad_norm": 1.9440999538041503,
843
+ "learning_rate": 9.2095489844615e-06,
844
+ "loss": 0.3561,
845
+ "step": 1170
846
+ },
847
+ {
848
+ "epoch": 0.7977015379415244,
849
+ "grad_norm": 2.0375108827553725,
850
+ "learning_rate": 9.188207138030518e-06,
851
+ "loss": 0.3547,
852
+ "step": 1180
853
+ },
854
+ {
855
+ "epoch": 0.8044617204664526,
856
+ "grad_norm": 1.8656977480472188,
857
+ "learning_rate": 9.166606425784939e-06,
858
+ "loss": 0.3353,
859
+ "step": 1190
860
+ },
861
+ {
862
+ "epoch": 0.8112219029913807,
863
+ "grad_norm": 1.8340532352178343,
864
+ "learning_rate": 9.144748182827305e-06,
865
+ "loss": 0.3641,
866
+ "step": 1200
867
+ },
868
+ {
869
+ "epoch": 0.8179820855163089,
870
+ "grad_norm": 1.8770982817901785,
871
+ "learning_rate": 9.122633760177674e-06,
872
+ "loss": 0.35,
873
+ "step": 1210
874
+ },
875
+ {
876
+ "epoch": 0.8247422680412371,
877
+ "grad_norm": 1.7126903025921292,
878
+ "learning_rate": 9.10026452469013e-06,
879
+ "loss": 0.3483,
880
+ "step": 1220
881
+ },
882
+ {
883
+ "epoch": 0.8315024505661653,
884
+ "grad_norm": 1.845094017702633,
885
+ "learning_rate": 9.077641858968302e-06,
886
+ "loss": 0.3463,
887
+ "step": 1230
888
+ },
889
+ {
890
+ "epoch": 0.8382626330910935,
891
+ "grad_norm": 1.6919845905215602,
892
+ "learning_rate": 9.054767161279891e-06,
893
+ "loss": 0.3493,
894
+ "step": 1240
895
+ },
896
+ {
897
+ "epoch": 0.8450228156160217,
898
+ "grad_norm": 41.7754958887055,
899
+ "learning_rate": 9.031641845470265e-06,
900
+ "loss": 0.3691,
901
+ "step": 1250
902
+ },
903
+ {
904
+ "epoch": 0.8517829981409498,
905
+ "grad_norm": 1.6803994335239858,
906
+ "learning_rate": 9.008267340875062e-06,
907
+ "loss": 0.3404,
908
+ "step": 1260
909
+ },
910
+ {
911
+ "epoch": 0.858543180665878,
912
+ "grad_norm": 1.6747949593133225,
913
+ "learning_rate": 8.984645092231839e-06,
914
+ "loss": 0.337,
915
+ "step": 1270
916
+ },
917
+ {
918
+ "epoch": 0.8653033631908061,
919
+ "grad_norm": 1.9888542335284893,
920
+ "learning_rate": 8.960776559590794e-06,
921
+ "loss": 0.3531,
922
+ "step": 1280
923
+ },
924
+ {
925
+ "epoch": 0.8720635457157343,
926
+ "grad_norm": 1.8242235825875925,
927
+ "learning_rate": 8.936663218224504e-06,
928
+ "loss": 0.3468,
929
+ "step": 1290
930
+ },
931
+ {
932
+ "epoch": 0.8788237282406625,
933
+ "grad_norm": 1.8091464965495379,
934
+ "learning_rate": 8.91230655853675e-06,
935
+ "loss": 0.3451,
936
+ "step": 1300
937
+ },
938
+ {
939
+ "epoch": 0.8855839107655906,
940
+ "grad_norm": 1.6077172216059503,
941
+ "learning_rate": 8.887708085970395e-06,
942
+ "loss": 0.3606,
943
+ "step": 1310
944
+ },
945
+ {
946
+ "epoch": 0.8923440932905189,
947
+ "grad_norm": 1.863072270952894,
948
+ "learning_rate": 8.862869320914342e-06,
949
+ "loss": 0.3362,
950
+ "step": 1320
951
+ },
952
+ {
953
+ "epoch": 0.899104275815447,
954
+ "grad_norm": 1.6689485544997376,
955
+ "learning_rate": 8.837791798609548e-06,
956
+ "loss": 0.3556,
957
+ "step": 1330
958
+ },
959
+ {
960
+ "epoch": 0.9058644583403752,
961
+ "grad_norm": 1.7200717303760475,
962
+ "learning_rate": 8.812477069054145e-06,
963
+ "loss": 0.3478,
964
+ "step": 1340
965
+ },
966
+ {
967
+ "epoch": 0.9126246408653034,
968
+ "grad_norm": 2.137634965409493,
969
+ "learning_rate": 8.786926696907635e-06,
970
+ "loss": 0.3367,
971
+ "step": 1350
972
+ },
973
+ {
974
+ "epoch": 0.9193848233902315,
975
+ "grad_norm": 1.8766558650581284,
976
+ "learning_rate": 8.761142261394176e-06,
977
+ "loss": 0.3384,
978
+ "step": 1360
979
+ },
980
+ {
981
+ "epoch": 0.9261450059151597,
982
+ "grad_norm": 1.79644209869537,
983
+ "learning_rate": 8.735125356204982e-06,
984
+ "loss": 0.3409,
985
+ "step": 1370
986
+ },
987
+ {
988
+ "epoch": 0.9329051884400879,
989
+ "grad_norm": 1.878014748264182,
990
+ "learning_rate": 8.708877589399805e-06,
991
+ "loss": 0.3571,
992
+ "step": 1380
993
+ },
994
+ {
995
+ "epoch": 0.939665370965016,
996
+ "grad_norm": 1.6990828286145954,
997
+ "learning_rate": 8.682400583307562e-06,
998
+ "loss": 0.3434,
999
+ "step": 1390
1000
+ },
1001
+ {
1002
+ "epoch": 0.9464255534899443,
1003
+ "grad_norm": 1.7992025269775698,
1004
+ "learning_rate": 8.655695974426049e-06,
1005
+ "loss": 0.3469,
1006
+ "step": 1400
1007
+ },
1008
+ {
1009
+ "epoch": 0.9531857360148724,
1010
+ "grad_norm": 1.9318642460759288,
1011
+ "learning_rate": 8.628765413320793e-06,
1012
+ "loss": 0.3567,
1013
+ "step": 1410
1014
+ },
1015
+ {
1016
+ "epoch": 0.9599459185398006,
1017
+ "grad_norm": 1.7485812674142844,
1018
+ "learning_rate": 8.60161056452304e-06,
1019
+ "loss": 0.3295,
1020
+ "step": 1420
1021
+ },
1022
+ {
1023
+ "epoch": 0.9667061010647288,
1024
+ "grad_norm": 1.9314544861372662,
1025
+ "learning_rate": 8.574233106426866e-06,
1026
+ "loss": 0.331,
1027
+ "step": 1430
1028
+ },
1029
+ {
1030
+ "epoch": 0.9734662835896569,
1031
+ "grad_norm": 1.6993343654728899,
1032
+ "learning_rate": 8.546634731185446e-06,
1033
+ "loss": 0.353,
1034
+ "step": 1440
1035
+ },
1036
+ {
1037
+ "epoch": 0.9802264661145851,
1038
+ "grad_norm": 1.7502543394189403,
1039
+ "learning_rate": 8.518817144606451e-06,
1040
+ "loss": 0.3316,
1041
+ "step": 1450
1042
+ },
1043
+ {
1044
+ "epoch": 0.9869866486395132,
1045
+ "grad_norm": 1.9261600970610924,
1046
+ "learning_rate": 8.490782066046634e-06,
1047
+ "loss": 0.3628,
1048
+ "step": 1460
1049
+ },
1050
+ {
1051
+ "epoch": 0.9937468311644414,
1052
+ "grad_norm": 1.7416309439075797,
1053
+ "learning_rate": 8.462531228305546e-06,
1054
+ "loss": 0.3231,
1055
+ "step": 1470
1056
+ },
1057
+ {
1058
+ "epoch": 1.0,
1059
+ "grad_norm": 3.593217730508142,
1060
+ "learning_rate": 8.434066377518437e-06,
1061
+ "loss": 0.3394,
1062
+ "step": 1480
1063
+ },
1064
+ {
1065
+ "epoch": 1.0067601825249282,
1066
+ "grad_norm": 1.6132270094363823,
1067
+ "learning_rate": 8.405389273048334e-06,
1068
+ "loss": 0.2478,
1069
+ "step": 1490
1070
+ },
1071
+ {
1072
+ "epoch": 1.0135203650498563,
1073
+ "grad_norm": 1.6776338845512389,
1074
+ "learning_rate": 8.376501687377297e-06,
1075
+ "loss": 0.2299,
1076
+ "step": 1500
1077
+ },
1078
+ {
1079
+ "epoch": 1.0135203650498563,
1080
+ "eval_loss": 0.351112425327301,
1081
+ "eval_runtime": 1325.3556,
1082
+ "eval_samples_per_second": 3.969,
1083
+ "eval_steps_per_second": 0.496,
1084
+ "step": 1500
1085
+ }
1086
+ ],
1087
+ "logging_steps": 10,
1088
+ "max_steps": 4440,
1089
+ "num_input_tokens_seen": 0,
1090
+ "num_train_epochs": 3,
1091
+ "save_steps": 500,
1092
+ "stateful_callbacks": {
1093
+ "TrainerControl": {
1094
+ "args": {
1095
+ "should_epoch_stop": false,
1096
+ "should_evaluate": false,
1097
+ "should_log": false,
1098
+ "should_save": true,
1099
+ "should_training_stop": false
1100
+ },
1101
+ "attributes": {}
1102
+ }
1103
+ },
1104
+ "total_flos": 576417156300800.0,
1105
+ "train_batch_size": 1,
1106
+ "trial_name": null,
1107
+ "trial_params": null
1108
+ }
agenttrek-llama/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057d9005725ac247b927b3d218b221ccdf40c738f871da500bc9530b491760ce
3
+ size 8081