Hugging Face's logo

INFReasoning
/
metalimo

Safetensors
Model card Files
xet
Community
KublaiKhan1 commited on
Commit
f807433
·
verified ·
1 Parent(s): 9fd1afb

Add files using upload-large-folder tool

Browse files
Files changed (13) hide show
  1. qwen2_5_7b_instruct/limo/checkpoint-410/added_tokens.json +24 -0
  2. qwen2_5_7b_instruct/limo/checkpoint-410/chat_template.jinja +54 -0
  3. qwen2_5_7b_instruct/limo/checkpoint-410/config.json +58 -0
  4. qwen2_5_7b_instruct/limo/checkpoint-410/generation_config.json +7 -0
  5. qwen2_5_7b_instruct/limo/checkpoint-410/merges.txt +0 -0
  6. qwen2_5_7b_instruct/limo/checkpoint-410/model.safetensors.index.json +347 -0
  7. qwen2_5_7b_instruct/limo/checkpoint-410/special_tokens_map.json +31 -0
  8. qwen2_5_7b_instruct/limo/checkpoint-410/tokenizer_config.json +208 -0
  9. qwen2_5_7b_instruct/limo/checkpoint-410/trainer_state.json +2904 -0
  10. qwen2_5_7b_instruct/limo/checkpoint-410/vocab.json +0 -0
  11. qwen2_5_7b_instruct/limo/trainer_log.jsonl +0 -0
  12. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-185/merges.txt +0 -0
  13. qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-185/vocab.json +0 -0
qwen2_5_7b_instruct/limo/checkpoint-410/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2_5_7b_instruct/limo/checkpoint-410/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
qwen2_5_7b_instruct/limo/checkpoint-410/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 1000000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
qwen2_5_7b_instruct/limo/checkpoint-410/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.55.0",
6
+ "use_cache": false
7
+ }
qwen2_5_7b_instruct/limo/checkpoint-410/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_7b_instruct/limo/checkpoint-410/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1903904128,
4
+ "total_size": 30462466048
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
345
+ "model.norm.weight": "model-00006-of-00007.safetensors"
346
+ }
347
+ }
qwen2_5_7b_instruct/limo/checkpoint-410/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
qwen2_5_7b_instruct/limo/checkpoint-410/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
qwen2_5_7b_instruct/limo/checkpoint-410/trainer_state.json ADDED
@@ -0,0 +1,2904 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 410,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.004878048780487805,
14
+ "grad_norm": 6.251913070678711,
15
+ "learning_rate": 5e-06,
16
+ "loss": 0.7742,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.00975609756097561,
21
+ "grad_norm": 6.38546085357666,
22
+ "learning_rate": 4.999997064365715e-06,
23
+ "loss": 1.0365,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.014634146341463415,
28
+ "grad_norm": 3.223087787628174,
29
+ "learning_rate": 4.999988257469751e-06,
30
+ "loss": 0.6448,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.01951219512195122,
35
+ "grad_norm": 2.750905752182007,
36
+ "learning_rate": 4.999973579332793e-06,
37
+ "loss": 0.6328,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.024390243902439025,
42
+ "grad_norm": 4.2081828117370605,
43
+ "learning_rate": 4.999953029989312e-06,
44
+ "loss": 0.6984,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.02926829268292683,
49
+ "grad_norm": 4.167655944824219,
50
+ "learning_rate": 4.999926609487568e-06,
51
+ "loss": 0.9847,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.03414634146341464,
56
+ "grad_norm": 4.408457279205322,
57
+ "learning_rate": 4.9998943178896106e-06,
58
+ "loss": 0.8203,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.03902439024390244,
63
+ "grad_norm": 3.1360676288604736,
64
+ "learning_rate": 4.999856155271276e-06,
65
+ "loss": 0.6513,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.04390243902439024,
70
+ "grad_norm": 3.3297390937805176,
71
+ "learning_rate": 4.999812121722191e-06,
72
+ "loss": 0.7803,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.04878048780487805,
77
+ "grad_norm": 3.5323646068573,
78
+ "learning_rate": 4.999762217345766e-06,
79
+ "loss": 0.7527,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.05365853658536585,
84
+ "grad_norm": 1.9139900207519531,
85
+ "learning_rate": 4.999706442259205e-06,
86
+ "loss": 0.5721,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.05853658536585366,
91
+ "grad_norm": 2.2962052822113037,
92
+ "learning_rate": 4.999644796593492e-06,
93
+ "loss": 0.6354,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.06341463414634146,
98
+ "grad_norm": 1.8342329263687134,
99
+ "learning_rate": 4.999577280493407e-06,
100
+ "loss": 0.5259,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.06829268292682927,
105
+ "grad_norm": 2.8183422088623047,
106
+ "learning_rate": 4.99950389411751e-06,
107
+ "loss": 0.8089,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.07317073170731707,
112
+ "grad_norm": 2.2182018756866455,
113
+ "learning_rate": 4.999424637638148e-06,
114
+ "loss": 0.6002,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.07804878048780488,
119
+ "grad_norm": 2.4346132278442383,
120
+ "learning_rate": 4.999339511241458e-06,
121
+ "loss": 0.6651,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.08292682926829269,
126
+ "grad_norm": 1.9976483583450317,
127
+ "learning_rate": 4.9992485151273584e-06,
128
+ "loss": 0.655,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.08780487804878048,
133
+ "grad_norm": 2.1938087940216064,
134
+ "learning_rate": 4.999151649509554e-06,
135
+ "loss": 0.5523,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.09268292682926829,
140
+ "grad_norm": 2.5118227005004883,
141
+ "learning_rate": 4.9990489146155356e-06,
142
+ "loss": 0.8695,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.0975609756097561,
147
+ "grad_norm": 2.111804723739624,
148
+ "learning_rate": 4.9989403106865765e-06,
149
+ "loss": 0.8075,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.1024390243902439,
154
+ "grad_norm": 2.2701148986816406,
155
+ "learning_rate": 4.9988258379777334e-06,
156
+ "loss": 0.6715,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.1073170731707317,
161
+ "grad_norm": 2.2692644596099854,
162
+ "learning_rate": 4.998705496757846e-06,
163
+ "loss": 0.7627,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.11219512195121951,
168
+ "grad_norm": 1.8187084197998047,
169
+ "learning_rate": 4.998579287309538e-06,
170
+ "loss": 0.9055,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.11707317073170732,
175
+ "grad_norm": 1.498978614807129,
176
+ "learning_rate": 4.998447209929211e-06,
177
+ "loss": 0.4455,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.12195121951219512,
182
+ "grad_norm": 2.2440743446350098,
183
+ "learning_rate": 4.998309264927053e-06,
184
+ "loss": 0.4843,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.12682926829268293,
189
+ "grad_norm": 1.8050298690795898,
190
+ "learning_rate": 4.998165452627025e-06,
191
+ "loss": 0.6016,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.13170731707317074,
196
+ "grad_norm": 1.9306098222732544,
197
+ "learning_rate": 4.998015773366874e-06,
198
+ "loss": 0.5469,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.13658536585365855,
203
+ "grad_norm": 2.152693510055542,
204
+ "learning_rate": 4.997860227498122e-06,
205
+ "loss": 0.5583,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.14146341463414633,
210
+ "grad_norm": 2.3152549266815186,
211
+ "learning_rate": 4.99769881538607e-06,
212
+ "loss": 0.6947,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.14634146341463414,
217
+ "grad_norm": 1.830079197883606,
218
+ "learning_rate": 4.997531537409794e-06,
219
+ "loss": 0.6863,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.15121951219512195,
224
+ "grad_norm": 2.574989080429077,
225
+ "learning_rate": 4.99735839396215e-06,
226
+ "loss": 0.6081,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.15609756097560976,
231
+ "grad_norm": 1.9973617792129517,
232
+ "learning_rate": 4.9971793854497655e-06,
233
+ "loss": 0.5624,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.16097560975609757,
238
+ "grad_norm": 1.7976499795913696,
239
+ "learning_rate": 4.996994512293042e-06,
240
+ "loss": 0.514,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.16585365853658537,
245
+ "grad_norm": 1.865333914756775,
246
+ "learning_rate": 4.996803774926157e-06,
247
+ "loss": 0.5389,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.17073170731707318,
252
+ "grad_norm": 2.7497925758361816,
253
+ "learning_rate": 4.996607173797059e-06,
254
+ "loss": 1.092,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.17560975609756097,
259
+ "grad_norm": 2.1576943397521973,
260
+ "learning_rate": 4.996404709367466e-06,
261
+ "loss": 0.6338,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.18048780487804877,
266
+ "grad_norm": 1.9310261011123657,
267
+ "learning_rate": 4.996196382112868e-06,
268
+ "loss": 0.5288,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.18536585365853658,
273
+ "grad_norm": 2.566770553588867,
274
+ "learning_rate": 4.9959821925225235e-06,
275
+ "loss": 0.7568,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.1902439024390244,
280
+ "grad_norm": 1.8456333875656128,
281
+ "learning_rate": 4.995762141099456e-06,
282
+ "loss": 0.6288,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.1951219512195122,
287
+ "grad_norm": 2.9497272968292236,
288
+ "learning_rate": 4.995536228360461e-06,
289
+ "loss": 0.8085,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.2,
294
+ "grad_norm": 2.113572359085083,
295
+ "learning_rate": 4.995304454836095e-06,
296
+ "loss": 0.7446,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.2048780487804878,
301
+ "grad_norm": 2.083073139190674,
302
+ "learning_rate": 4.9950668210706795e-06,
303
+ "loss": 0.61,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.2097560975609756,
308
+ "grad_norm": 1.7291383743286133,
309
+ "learning_rate": 4.994823327622299e-06,
310
+ "loss": 0.4961,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.2146341463414634,
315
+ "grad_norm": 2.4040563106536865,
316
+ "learning_rate": 4.9945739750628e-06,
317
+ "loss": 0.6091,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.21951219512195122,
322
+ "grad_norm": 1.6997170448303223,
323
+ "learning_rate": 4.994318763977789e-06,
324
+ "loss": 0.6408,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.22439024390243903,
329
+ "grad_norm": 1.5265686511993408,
330
+ "learning_rate": 4.994057694966632e-06,
331
+ "loss": 0.4422,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.22926829268292684,
336
+ "grad_norm": 1.6987519264221191,
337
+ "learning_rate": 4.993790768642449e-06,
338
+ "loss": 0.8084,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.23414634146341465,
343
+ "grad_norm": 1.9533758163452148,
344
+ "learning_rate": 4.99351798563212e-06,
345
+ "loss": 0.9267,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.23902439024390243,
350
+ "grad_norm": 2.0147147178649902,
351
+ "learning_rate": 4.993239346576278e-06,
352
+ "loss": 0.7258,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.24390243902439024,
357
+ "grad_norm": 1.7322336435317993,
358
+ "learning_rate": 4.99295485212931e-06,
359
+ "loss": 0.7664,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.24878048780487805,
364
+ "grad_norm": 1.972558856010437,
365
+ "learning_rate": 4.992664502959351e-06,
366
+ "loss": 0.6476,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.25365853658536586,
371
+ "grad_norm": 2.168142557144165,
372
+ "learning_rate": 4.99236829974829e-06,
373
+ "loss": 0.6274,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.25853658536585367,
378
+ "grad_norm": 2.1706929206848145,
379
+ "learning_rate": 4.992066243191762e-06,
380
+ "loss": 0.8237,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.2634146341463415,
385
+ "grad_norm": 1.7400177717208862,
386
+ "learning_rate": 4.991758333999148e-06,
387
+ "loss": 0.6377,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.2682926829268293,
392
+ "grad_norm": 2.02597713470459,
393
+ "learning_rate": 4.991444572893575e-06,
394
+ "loss": 0.5368,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.2731707317073171,
399
+ "grad_norm": 1.9592632055282593,
400
+ "learning_rate": 4.991124960611916e-06,
401
+ "loss": 0.4826,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.2780487804878049,
406
+ "grad_norm": 1.6813147068023682,
407
+ "learning_rate": 4.99079949790478e-06,
408
+ "loss": 0.5786,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.28292682926829266,
413
+ "grad_norm": 1.5665404796600342,
414
+ "learning_rate": 4.99046818553652e-06,
415
+ "loss": 0.6276,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.28780487804878047,
420
+ "grad_norm": 1.9345953464508057,
421
+ "learning_rate": 4.9901310242852246e-06,
422
+ "loss": 0.5943,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.2926829268292683,
427
+ "grad_norm": 1.4303550720214844,
428
+ "learning_rate": 4.9897880149427206e-06,
429
+ "loss": 0.5156,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.2975609756097561,
434
+ "grad_norm": 2.3535423278808594,
435
+ "learning_rate": 4.989439158314566e-06,
436
+ "loss": 0.6139,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.3024390243902439,
441
+ "grad_norm": 1.617553949356079,
442
+ "learning_rate": 4.989084455220056e-06,
443
+ "loss": 0.4543,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.3073170731707317,
448
+ "grad_norm": 2.2876179218292236,
449
+ "learning_rate": 4.988723906492212e-06,
450
+ "loss": 0.8291,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.3121951219512195,
455
+ "grad_norm": 1.781219720840454,
456
+ "learning_rate": 4.988357512977785e-06,
457
+ "loss": 0.4443,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.3170731707317073,
462
+ "grad_norm": 1.8858840465545654,
463
+ "learning_rate": 4.987985275537252e-06,
464
+ "loss": 0.4885,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.32195121951219513,
469
+ "grad_norm": 1.685311198234558,
470
+ "learning_rate": 4.9876071950448185e-06,
471
+ "loss": 0.6638,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.32682926829268294,
476
+ "grad_norm": 1.711588740348816,
477
+ "learning_rate": 4.987223272388407e-06,
478
+ "loss": 0.4916,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.33170731707317075,
483
+ "grad_norm": 1.9743118286132812,
484
+ "learning_rate": 4.986833508469663e-06,
485
+ "loss": 0.837,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.33658536585365856,
490
+ "grad_norm": 1.3840869665145874,
491
+ "learning_rate": 4.98643790420395e-06,
492
+ "loss": 0.4716,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.34146341463414637,
497
+ "grad_norm": 2.4423623085021973,
498
+ "learning_rate": 4.986036460520348e-06,
499
+ "loss": 0.7045,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.3463414634146341,
504
+ "grad_norm": 1.9470542669296265,
505
+ "learning_rate": 4.98562917836165e-06,
506
+ "loss": 0.6841,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.35121951219512193,
511
+ "grad_norm": 1.357690691947937,
512
+ "learning_rate": 4.985216058684362e-06,
513
+ "loss": 0.4278,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.35609756097560974,
518
+ "grad_norm": 1.6999742984771729,
519
+ "learning_rate": 4.984797102458697e-06,
520
+ "loss": 0.8335,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.36097560975609755,
525
+ "grad_norm": 2.0041823387145996,
526
+ "learning_rate": 4.984372310668579e-06,
527
+ "loss": 0.5316,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.36585365853658536,
532
+ "grad_norm": 1.8468217849731445,
533
+ "learning_rate": 4.983941684311633e-06,
534
+ "loss": 1.0183,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.37073170731707317,
539
+ "grad_norm": 1.5536184310913086,
540
+ "learning_rate": 4.983505224399188e-06,
541
+ "loss": 0.4932,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.375609756097561,
546
+ "grad_norm": 1.3191509246826172,
547
+ "learning_rate": 4.983062931956275e-06,
548
+ "loss": 0.5752,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.3804878048780488,
553
+ "grad_norm": 1.9427785873413086,
554
+ "learning_rate": 4.9826148080216195e-06,
555
+ "loss": 0.6428,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.3853658536585366,
560
+ "grad_norm": 2.217280387878418,
561
+ "learning_rate": 4.9821608536476445e-06,
562
+ "loss": 1.0444,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.3902439024390244,
567
+ "grad_norm": 1.7984737157821655,
568
+ "learning_rate": 4.981701069900465e-06,
569
+ "loss": 0.5578,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.3951219512195122,
574
+ "grad_norm": 1.859869122505188,
575
+ "learning_rate": 4.9812354578598876e-06,
576
+ "loss": 0.5875,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.4,
581
+ "grad_norm": 1.8699328899383545,
582
+ "learning_rate": 4.980764018619405e-06,
583
+ "loss": 0.6775,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.40487804878048783,
588
+ "grad_norm": 1.6898409128189087,
589
+ "learning_rate": 4.980286753286196e-06,
590
+ "loss": 0.6081,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.4097560975609756,
595
+ "grad_norm": 1.5678975582122803,
596
+ "learning_rate": 4.97980366298112e-06,
597
+ "loss": 0.5573,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.4146341463414634,
602
+ "grad_norm": 1.4087779521942139,
603
+ "learning_rate": 4.97931474883872e-06,
604
+ "loss": 0.6142,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.4195121951219512,
609
+ "grad_norm": 1.8441438674926758,
610
+ "learning_rate": 4.978820012007213e-06,
611
+ "loss": 0.6677,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.424390243902439,
616
+ "grad_norm": 1.7426705360412598,
617
+ "learning_rate": 4.978319453648495e-06,
618
+ "loss": 0.7166,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.4292682926829268,
623
+ "grad_norm": 1.7627829313278198,
624
+ "learning_rate": 4.977813074938128e-06,
625
+ "loss": 0.5965,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.43414634146341463,
630
+ "grad_norm": 1.6656118631362915,
631
+ "learning_rate": 4.977300877065347e-06,
632
+ "loss": 0.5908,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.43902439024390244,
637
+ "grad_norm": 1.2669886350631714,
638
+ "learning_rate": 4.976782861233053e-06,
639
+ "loss": 0.4368,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.44390243902439025,
644
+ "grad_norm": 1.2918105125427246,
645
+ "learning_rate": 4.976259028657812e-06,
646
+ "loss": 0.3848,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.44878048780487806,
651
+ "grad_norm": 1.3664082288742065,
652
+ "learning_rate": 4.975729380569845e-06,
653
+ "loss": 0.5376,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.45365853658536587,
658
+ "grad_norm": 1.9810562133789062,
659
+ "learning_rate": 4.975193918213035e-06,
660
+ "loss": 0.4396,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.4585365853658537,
665
+ "grad_norm": 1.5167036056518555,
666
+ "learning_rate": 4.974652642844921e-06,
667
+ "loss": 0.5573,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.4634146341463415,
672
+ "grad_norm": 3.6640360355377197,
673
+ "learning_rate": 4.974105555736693e-06,
674
+ "loss": 0.8419,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.4682926829268293,
679
+ "grad_norm": 2.480140209197998,
680
+ "learning_rate": 4.973552658173186e-06,
681
+ "loss": 0.6014,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.47317073170731705,
686
+ "grad_norm": 1.6618154048919678,
687
+ "learning_rate": 4.972993951452887e-06,
688
+ "loss": 0.5581,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.47804878048780486,
693
+ "grad_norm": 1.291348934173584,
694
+ "learning_rate": 4.9724294368879214e-06,
695
+ "loss": 0.4499,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.48292682926829267,
700
+ "grad_norm": 1.8929156064987183,
701
+ "learning_rate": 4.971859115804055e-06,
702
+ "loss": 0.7873,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.4878048780487805,
707
+ "grad_norm": 1.57858145236969,
708
+ "learning_rate": 4.9712829895406935e-06,
709
+ "loss": 0.5793,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.4926829268292683,
714
+ "grad_norm": 1.1852738857269287,
715
+ "learning_rate": 4.970701059450872e-06,
716
+ "loss": 0.3179,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.4975609756097561,
721
+ "grad_norm": 1.8145536184310913,
722
+ "learning_rate": 4.970113326901258e-06,
723
+ "loss": 0.7649,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.5024390243902439,
728
+ "grad_norm": 1.5796900987625122,
729
+ "learning_rate": 4.9695197932721455e-06,
730
+ "loss": 0.6736,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.5073170731707317,
735
+ "grad_norm": 1.4091283082962036,
736
+ "learning_rate": 4.968920459957453e-06,
737
+ "loss": 0.6019,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.5121951219512195,
742
+ "grad_norm": 2.3007757663726807,
743
+ "learning_rate": 4.968315328364719e-06,
744
+ "loss": 0.8106,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.5170731707317073,
749
+ "grad_norm": 2.226351499557495,
750
+ "learning_rate": 4.9677043999151e-06,
751
+ "loss": 0.9389,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.5219512195121951,
756
+ "grad_norm": 1.713365912437439,
757
+ "learning_rate": 4.967087676043366e-06,
758
+ "loss": 0.3773,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.526829268292683,
763
+ "grad_norm": 1.6297917366027832,
764
+ "learning_rate": 4.966465158197897e-06,
765
+ "loss": 0.6278,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.5317073170731708,
770
+ "grad_norm": 1.7754937410354614,
771
+ "learning_rate": 4.965836847840681e-06,
772
+ "loss": 0.5086,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.5365853658536586,
777
+ "grad_norm": 1.6794660091400146,
778
+ "learning_rate": 4.96520274644731e-06,
779
+ "loss": 0.6123,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.5414634146341464,
784
+ "grad_norm": 1.934241533279419,
785
+ "learning_rate": 4.964562855506976e-06,
786
+ "loss": 0.5779,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.5463414634146342,
791
+ "grad_norm": 1.2584961652755737,
792
+ "learning_rate": 4.963917176522466e-06,
793
+ "loss": 0.4115,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.551219512195122,
798
+ "grad_norm": 2.1711580753326416,
799
+ "learning_rate": 4.963265711010164e-06,
800
+ "loss": 0.7418,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.5560975609756098,
805
+ "grad_norm": 1.650855541229248,
806
+ "learning_rate": 4.9626084605000395e-06,
807
+ "loss": 0.5725,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.5609756097560976,
812
+ "grad_norm": 1.9013773202896118,
813
+ "learning_rate": 4.961945426535652e-06,
814
+ "loss": 0.4464,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.5658536585365853,
819
+ "grad_norm": 1.4872888326644897,
820
+ "learning_rate": 4.961276610674141e-06,
821
+ "loss": 0.6751,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.5707317073170731,
826
+ "grad_norm": 1.5318901538848877,
827
+ "learning_rate": 4.960602014486225e-06,
828
+ "loss": 0.7975,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.5756097560975609,
833
+ "grad_norm": 1.2589044570922852,
834
+ "learning_rate": 4.959921639556199e-06,
835
+ "loss": 0.4939,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.5804878048780487,
840
+ "grad_norm": 1.881285548210144,
841
+ "learning_rate": 4.959235487481928e-06,
842
+ "loss": 0.8222,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.5853658536585366,
847
+ "grad_norm": 1.576146125793457,
848
+ "learning_rate": 4.958543559874846e-06,
849
+ "loss": 0.4076,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.5902439024390244,
854
+ "grad_norm": 2.0078847408294678,
855
+ "learning_rate": 4.9578458583599495e-06,
856
+ "loss": 0.562,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.5951219512195122,
861
+ "grad_norm": 1.4955941438674927,
862
+ "learning_rate": 4.957142384575795e-06,
863
+ "loss": 0.5184,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.6,
868
+ "grad_norm": 1.9556761980056763,
869
+ "learning_rate": 4.956433140174498e-06,
870
+ "loss": 0.7036,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.6048780487804878,
875
+ "grad_norm": 1.9274554252624512,
876
+ "learning_rate": 4.9557181268217225e-06,
877
+ "loss": 0.7137,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.6097560975609756,
882
+ "grad_norm": 1.672255277633667,
883
+ "learning_rate": 4.954997346196683e-06,
884
+ "loss": 1.0138,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.6146341463414634,
889
+ "grad_norm": 1.6470623016357422,
890
+ "learning_rate": 4.954270799992138e-06,
891
+ "loss": 0.6059,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.6195121951219512,
896
+ "grad_norm": 2.0698301792144775,
897
+ "learning_rate": 4.953538489914387e-06,
898
+ "loss": 0.6224,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.624390243902439,
903
+ "grad_norm": 1.7772653102874756,
904
+ "learning_rate": 4.9528004176832654e-06,
905
+ "loss": 0.4795,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.6292682926829268,
910
+ "grad_norm": 2.276451587677002,
911
+ "learning_rate": 4.952056585032142e-06,
912
+ "loss": 0.8591,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.6341463414634146,
917
+ "grad_norm": 2.058436870574951,
918
+ "learning_rate": 4.951306993707913e-06,
919
+ "loss": 0.6678,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.6390243902439025,
924
+ "grad_norm": 1.8003332614898682,
925
+ "learning_rate": 4.950551645470998e-06,
926
+ "loss": 0.617,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.6439024390243903,
931
+ "grad_norm": 2.0872535705566406,
932
+ "learning_rate": 4.9497905420953406e-06,
933
+ "loss": 0.611,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.6487804878048781,
938
+ "grad_norm": 2.1815896034240723,
939
+ "learning_rate": 4.949023685368395e-06,
940
+ "loss": 0.6445,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.6536585365853659,
945
+ "grad_norm": 1.7983999252319336,
946
+ "learning_rate": 4.948251077091131e-06,
947
+ "loss": 0.8733,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.6585365853658537,
952
+ "grad_norm": 1.6845791339874268,
953
+ "learning_rate": 4.947472719078025e-06,
954
+ "loss": 0.6613,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.6634146341463415,
959
+ "grad_norm": 1.6869384050369263,
960
+ "learning_rate": 4.9466886131570565e-06,
961
+ "loss": 0.7319,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.6682926829268293,
966
+ "grad_norm": 1.9151450395584106,
967
+ "learning_rate": 4.945898761169704e-06,
968
+ "loss": 0.8795,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.6731707317073171,
973
+ "grad_norm": 1.3423423767089844,
974
+ "learning_rate": 4.945103164970941e-06,
975
+ "loss": 0.4385,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.6780487804878049,
980
+ "grad_norm": 1.4854035377502441,
981
+ "learning_rate": 4.9443018264292304e-06,
982
+ "loss": 0.5341,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.6829268292682927,
987
+ "grad_norm": 1.805953025817871,
988
+ "learning_rate": 4.9434947474265225e-06,
989
+ "loss": 0.6463,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.6878048780487804,
994
+ "grad_norm": 1.7254730463027954,
995
+ "learning_rate": 4.942681929858249e-06,
996
+ "loss": 0.8897,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.6926829268292682,
1001
+ "grad_norm": 1.9024320840835571,
1002
+ "learning_rate": 4.941863375633315e-06,
1003
+ "loss": 0.7033,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.697560975609756,
1008
+ "grad_norm": 1.4351361989974976,
1009
+ "learning_rate": 4.9410390866741056e-06,
1010
+ "loss": 0.527,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.7024390243902439,
1015
+ "grad_norm": 1.4365131855010986,
1016
+ "learning_rate": 4.9402090649164655e-06,
1017
+ "loss": 0.5458,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.7073170731707317,
1022
+ "grad_norm": 2.144742965698242,
1023
+ "learning_rate": 4.9393733123097085e-06,
1024
+ "loss": 0.8133,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.7121951219512195,
1029
+ "grad_norm": 2.066554546356201,
1030
+ "learning_rate": 4.9385318308166065e-06,
1031
+ "loss": 0.7282,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.7170731707317073,
1036
+ "grad_norm": 1.5883394479751587,
1037
+ "learning_rate": 4.937684622413385e-06,
1038
+ "loss": 0.4144,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.7219512195121951,
1043
+ "grad_norm": 2.329960346221924,
1044
+ "learning_rate": 4.9368316890897185e-06,
1045
+ "loss": 0.8182,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.7268292682926829,
1050
+ "grad_norm": 1.5622303485870361,
1051
+ "learning_rate": 4.9359730328487264e-06,
1052
+ "loss": 0.412,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.7317073170731707,
1057
+ "grad_norm": 1.3020845651626587,
1058
+ "learning_rate": 4.935108655706972e-06,
1059
+ "loss": 0.5607,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.7365853658536585,
1064
+ "grad_norm": 2.0023865699768066,
1065
+ "learning_rate": 4.934238559694448e-06,
1066
+ "loss": 0.9273,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.7414634146341463,
1071
+ "grad_norm": 1.6495121717453003,
1072
+ "learning_rate": 4.9333627468545845e-06,
1073
+ "loss": 0.4775,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.7463414634146341,
1078
+ "grad_norm": 1.4878952503204346,
1079
+ "learning_rate": 4.932481219244231e-06,
1080
+ "loss": 0.562,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.751219512195122,
1085
+ "grad_norm": 2.352097511291504,
1086
+ "learning_rate": 4.931593978933666e-06,
1087
+ "loss": 0.6151,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.7560975609756098,
1092
+ "grad_norm": 1.3260765075683594,
1093
+ "learning_rate": 4.930701028006577e-06,
1094
+ "loss": 0.6572,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.7609756097560976,
1099
+ "grad_norm": 1.3987398147583008,
1100
+ "learning_rate": 4.929802368560066e-06,
1101
+ "loss": 0.5205,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.7658536585365854,
1106
+ "grad_norm": 2.636143922805786,
1107
+ "learning_rate": 4.928898002704642e-06,
1108
+ "loss": 0.7562,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.7707317073170732,
1113
+ "grad_norm": 2.312101125717163,
1114
+ "learning_rate": 4.927987932564215e-06,
1115
+ "loss": 0.6415,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.775609756097561,
1120
+ "grad_norm": 1.6384342908859253,
1121
+ "learning_rate": 4.927072160276092e-06,
1122
+ "loss": 0.6148,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.7804878048780488,
1127
+ "grad_norm": 1.3910821676254272,
1128
+ "learning_rate": 4.926150687990969e-06,
1129
+ "loss": 0.3866,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.7853658536585366,
1134
+ "grad_norm": 1.7929809093475342,
1135
+ "learning_rate": 4.925223517872934e-06,
1136
+ "loss": 0.7282,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.7902439024390244,
1141
+ "grad_norm": 2.1226377487182617,
1142
+ "learning_rate": 4.9242906520994484e-06,
1143
+ "loss": 0.8234,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.7951219512195122,
1148
+ "grad_norm": 1.6692653894424438,
1149
+ "learning_rate": 4.923352092861358e-06,
1150
+ "loss": 0.7111,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.8,
1155
+ "grad_norm": 1.7468419075012207,
1156
+ "learning_rate": 4.922407842362875e-06,
1157
+ "loss": 0.4963,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.8048780487804879,
1162
+ "grad_norm": 1.5026869773864746,
1163
+ "learning_rate": 4.921457902821578e-06,
1164
+ "loss": 0.7182,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.8097560975609757,
1169
+ "grad_norm": 1.565578818321228,
1170
+ "learning_rate": 4.920502276468408e-06,
1171
+ "loss": 0.6331,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.8146341463414634,
1176
+ "grad_norm": 1.5285255908966064,
1177
+ "learning_rate": 4.9195409655476605e-06,
1178
+ "loss": 0.5216,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.8195121951219512,
1183
+ "grad_norm": 2.1599016189575195,
1184
+ "learning_rate": 4.918573972316982e-06,
1185
+ "loss": 0.8197,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.824390243902439,
1190
+ "grad_norm": 1.9766514301300049,
1191
+ "learning_rate": 4.917601299047361e-06,
1192
+ "loss": 0.6364,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.8292682926829268,
1197
+ "grad_norm": 1.6226218938827515,
1198
+ "learning_rate": 4.916622948023129e-06,
1199
+ "loss": 0.5688,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.8341463414634146,
1204
+ "grad_norm": 2.169351100921631,
1205
+ "learning_rate": 4.915638921541952e-06,
1206
+ "loss": 0.5144,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.8390243902439024,
1211
+ "grad_norm": 2.0374093055725098,
1212
+ "learning_rate": 4.914649221914822e-06,
1213
+ "loss": 0.6684,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.8439024390243902,
1218
+ "grad_norm": 1.8811930418014526,
1219
+ "learning_rate": 4.913653851466057e-06,
1220
+ "loss": 0.4537,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.848780487804878,
1225
+ "grad_norm": 1.7003443241119385,
1226
+ "learning_rate": 4.912652812533291e-06,
1227
+ "loss": 0.5926,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.8536585365853658,
1232
+ "grad_norm": 1.6899495124816895,
1233
+ "learning_rate": 4.911646107467472e-06,
1234
+ "loss": 0.6797,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.8585365853658536,
1239
+ "grad_norm": 1.5597474575042725,
1240
+ "learning_rate": 4.9106337386328524e-06,
1241
+ "loss": 0.7363,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.8634146341463415,
1246
+ "grad_norm": 1.7820264101028442,
1247
+ "learning_rate": 4.909615708406991e-06,
1248
+ "loss": 0.7277,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.8682926829268293,
1253
+ "grad_norm": 1.5444871187210083,
1254
+ "learning_rate": 4.908592019180738e-06,
1255
+ "loss": 0.4991,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.8731707317073171,
1260
+ "grad_norm": 1.1890966892242432,
1261
+ "learning_rate": 4.907562673358234e-06,
1262
+ "loss": 0.4345,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.8780487804878049,
1267
+ "grad_norm": 1.6008920669555664,
1268
+ "learning_rate": 4.906527673356907e-06,
1269
+ "loss": 0.506,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.8829268292682927,
1274
+ "grad_norm": 1.3028374910354614,
1275
+ "learning_rate": 4.905487021607462e-06,
1276
+ "loss": 0.4031,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.8878048780487805,
1281
+ "grad_norm": 2.086660146713257,
1282
+ "learning_rate": 4.904440720553876e-06,
1283
+ "loss": 0.6167,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.8926829268292683,
1288
+ "grad_norm": 1.5964947938919067,
1289
+ "learning_rate": 4.903388772653396e-06,
1290
+ "loss": 0.5923,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.8975609756097561,
1295
+ "grad_norm": 1.7292804718017578,
1296
+ "learning_rate": 4.902331180376529e-06,
1297
+ "loss": 0.6047,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.9024390243902439,
1302
+ "grad_norm": 1.6994556188583374,
1303
+ "learning_rate": 4.901267946207038e-06,
1304
+ "loss": 0.7615,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.9073170731707317,
1309
+ "grad_norm": 1.9247877597808838,
1310
+ "learning_rate": 4.900199072641937e-06,
1311
+ "loss": 0.5834,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.9121951219512195,
1316
+ "grad_norm": 1.4916514158248901,
1317
+ "learning_rate": 4.899124562191484e-06,
1318
+ "loss": 0.4737,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.9170731707317074,
1323
+ "grad_norm": 1.9706366062164307,
1324
+ "learning_rate": 4.8980444173791735e-06,
1325
+ "loss": 0.4418,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.9219512195121952,
1330
+ "grad_norm": 2.295691728591919,
1331
+ "learning_rate": 4.896958640741735e-06,
1332
+ "loss": 0.7035,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.926829268292683,
1337
+ "grad_norm": 2.459785223007202,
1338
+ "learning_rate": 4.895867234829121e-06,
1339
+ "loss": 0.7988,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.9317073170731708,
1344
+ "grad_norm": 1.6266491413116455,
1345
+ "learning_rate": 4.894770202204509e-06,
1346
+ "loss": 0.5665,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.9365853658536586,
1351
+ "grad_norm": 1.549321174621582,
1352
+ "learning_rate": 4.893667545444285e-06,
1353
+ "loss": 0.5774,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.9414634146341463,
1358
+ "grad_norm": 2.014610767364502,
1359
+ "learning_rate": 4.8925592671380495e-06,
1360
+ "loss": 0.5668,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.9463414634146341,
1365
+ "grad_norm": 1.3015650510787964,
1366
+ "learning_rate": 4.891445369888601e-06,
1367
+ "loss": 0.427,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.9512195121951219,
1372
+ "grad_norm": 1.6933586597442627,
1373
+ "learning_rate": 4.890325856311936e-06,
1374
+ "loss": 0.7354,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.9560975609756097,
1379
+ "grad_norm": 2.1092705726623535,
1380
+ "learning_rate": 4.889200729037241e-06,
1381
+ "loss": 0.7039,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.9609756097560975,
1386
+ "grad_norm": 1.625111699104309,
1387
+ "learning_rate": 4.888069990706884e-06,
1388
+ "loss": 0.5369,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.9658536585365853,
1393
+ "grad_norm": 1.4547514915466309,
1394
+ "learning_rate": 4.886933643976414e-06,
1395
+ "loss": 0.3645,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.9707317073170731,
1400
+ "grad_norm": 1.832529902458191,
1401
+ "learning_rate": 4.885791691514548e-06,
1402
+ "loss": 0.422,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.975609756097561,
1407
+ "grad_norm": 1.533402442932129,
1408
+ "learning_rate": 4.884644136003172e-06,
1409
+ "loss": 0.4698,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.9804878048780488,
1414
+ "grad_norm": 1.9563912153244019,
1415
+ "learning_rate": 4.883490980137327e-06,
1416
+ "loss": 1.1273,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.9853658536585366,
1421
+ "grad_norm": 1.7044615745544434,
1422
+ "learning_rate": 4.882332226625208e-06,
1423
+ "loss": 0.6056,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.9902439024390244,
1428
+ "grad_norm": 1.6405285596847534,
1429
+ "learning_rate": 4.881167878188158e-06,
1430
+ "loss": 0.7204,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.9951219512195122,
1435
+ "grad_norm": 1.5838991403579712,
1436
+ "learning_rate": 4.8799979375606565e-06,
1437
+ "loss": 0.553,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 1.0,
1442
+ "grad_norm": 1.6604121923446655,
1443
+ "learning_rate": 4.878822407490319e-06,
1444
+ "loss": 0.4694,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 1.0048780487804878,
1449
+ "grad_norm": 1.4410219192504883,
1450
+ "learning_rate": 4.8776412907378845e-06,
1451
+ "loss": 0.3954,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 1.0097560975609756,
1456
+ "grad_norm": 1.3399821519851685,
1457
+ "learning_rate": 4.876454590077216e-06,
1458
+ "loss": 0.4453,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 1.0146341463414634,
1463
+ "grad_norm": 1.3594847917556763,
1464
+ "learning_rate": 4.875262308295289e-06,
1465
+ "loss": 0.5706,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 1.0195121951219512,
1470
+ "grad_norm": 1.4475713968276978,
1471
+ "learning_rate": 4.874064448192185e-06,
1472
+ "loss": 0.4708,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 1.024390243902439,
1477
+ "grad_norm": 2.237009286880493,
1478
+ "learning_rate": 4.872861012581088e-06,
1479
+ "loss": 0.4116,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 1.0292682926829269,
1484
+ "grad_norm": 1.9443275928497314,
1485
+ "learning_rate": 4.871652004288275e-06,
1486
+ "loss": 0.5268,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 1.0341463414634147,
1491
+ "grad_norm": 2.032132387161255,
1492
+ "learning_rate": 4.870437426153113e-06,
1493
+ "loss": 0.5144,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 1.0390243902439025,
1498
+ "grad_norm": 2.908564329147339,
1499
+ "learning_rate": 4.869217281028045e-06,
1500
+ "loss": 0.6369,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 1.0439024390243903,
1505
+ "grad_norm": 1.9555280208587646,
1506
+ "learning_rate": 4.867991571778592e-06,
1507
+ "loss": 0.6615,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 1.048780487804878,
1512
+ "grad_norm": 1.4361177682876587,
1513
+ "learning_rate": 4.866760301283342e-06,
1514
+ "loss": 0.3721,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 1.053658536585366,
1519
+ "grad_norm": 1.5162372589111328,
1520
+ "learning_rate": 4.865523472433942e-06,
1521
+ "loss": 0.5117,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 1.0585365853658537,
1526
+ "grad_norm": 1.4366101026535034,
1527
+ "learning_rate": 4.8642810881350935e-06,
1528
+ "loss": 0.4239,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 1.0634146341463415,
1533
+ "grad_norm": 1.6032313108444214,
1534
+ "learning_rate": 4.863033151304546e-06,
1535
+ "loss": 0.4752,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 1.0682926829268293,
1540
+ "grad_norm": 9.823326110839844,
1541
+ "learning_rate": 4.861779664873088e-06,
1542
+ "loss": 0.7429,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 1.0731707317073171,
1547
+ "grad_norm": 2.1821725368499756,
1548
+ "learning_rate": 4.8605206317845425e-06,
1549
+ "loss": 0.5409,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 1.078048780487805,
1554
+ "grad_norm": 1.8968735933303833,
1555
+ "learning_rate": 4.859256054995758e-06,
1556
+ "loss": 0.6201,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 1.0829268292682928,
1561
+ "grad_norm": 1.3566253185272217,
1562
+ "learning_rate": 4.8579859374766e-06,
1563
+ "loss": 0.3323,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 1.0878048780487806,
1568
+ "grad_norm": 1.2179781198501587,
1569
+ "learning_rate": 4.856710282209952e-06,
1570
+ "loss": 0.2767,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 1.0926829268292684,
1575
+ "grad_norm": 1.5012304782867432,
1576
+ "learning_rate": 4.855429092191698e-06,
1577
+ "loss": 0.5419,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 1.0975609756097562,
1582
+ "grad_norm": 1.361253261566162,
1583
+ "learning_rate": 4.854142370430725e-06,
1584
+ "loss": 0.4209,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 1.102439024390244,
1589
+ "grad_norm": 1.694344162940979,
1590
+ "learning_rate": 4.8528501199489045e-06,
1591
+ "loss": 0.5328,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 1.1073170731707318,
1596
+ "grad_norm": 1.9685852527618408,
1597
+ "learning_rate": 4.851552343781099e-06,
1598
+ "loss": 0.66,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 1.1121951219512196,
1603
+ "grad_norm": 1.3181688785552979,
1604
+ "learning_rate": 4.850249044975145e-06,
1605
+ "loss": 0.533,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 1.1170731707317074,
1610
+ "grad_norm": 1.7146031856536865,
1611
+ "learning_rate": 4.848940226591849e-06,
1612
+ "loss": 0.8205,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 1.1219512195121952,
1617
+ "grad_norm": 1.6150505542755127,
1618
+ "learning_rate": 4.847625891704982e-06,
1619
+ "loss": 0.4771,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 1.126829268292683,
1624
+ "grad_norm": 1.6849442720413208,
1625
+ "learning_rate": 4.846306043401268e-06,
1626
+ "loss": 0.4493,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 1.1317073170731708,
1631
+ "grad_norm": 1.8745028972625732,
1632
+ "learning_rate": 4.844980684780381e-06,
1633
+ "loss": 0.4396,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 1.1365853658536587,
1638
+ "grad_norm": 1.984281301498413,
1639
+ "learning_rate": 4.8436498189549345e-06,
1640
+ "loss": 0.4695,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 1.1414634146341462,
1645
+ "grad_norm": 1.1260443925857544,
1646
+ "learning_rate": 4.842313449050477e-06,
1647
+ "loss": 0.3695,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 1.146341463414634,
1652
+ "grad_norm": 1.3031764030456543,
1653
+ "learning_rate": 4.840971578205486e-06,
1654
+ "loss": 0.341,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 1.1512195121951219,
1659
+ "grad_norm": 1.3267005681991577,
1660
+ "learning_rate": 4.839624209571352e-06,
1661
+ "loss": 0.2757,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 1.1560975609756097,
1666
+ "grad_norm": 1.595441460609436,
1667
+ "learning_rate": 4.838271346312381e-06,
1668
+ "loss": 0.6283,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 1.1609756097560975,
1673
+ "grad_norm": 1.6265649795532227,
1674
+ "learning_rate": 4.836912991605782e-06,
1675
+ "loss": 0.6538,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 1.1658536585365853,
1680
+ "grad_norm": 1.6886593103408813,
1681
+ "learning_rate": 4.835549148641663e-06,
1682
+ "loss": 0.4063,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 1.170731707317073,
1687
+ "grad_norm": 1.7404961585998535,
1688
+ "learning_rate": 4.834179820623018e-06,
1689
+ "loss": 0.5187,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 1.175609756097561,
1694
+ "grad_norm": 1.246699571609497,
1695
+ "learning_rate": 4.832805010765724e-06,
1696
+ "loss": 0.4216,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 1.1804878048780487,
1701
+ "grad_norm": 1.2928248643875122,
1702
+ "learning_rate": 4.831424722298531e-06,
1703
+ "loss": 0.4373,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 1.1853658536585365,
1708
+ "grad_norm": 1.948778510093689,
1709
+ "learning_rate": 4.830038958463061e-06,
1710
+ "loss": 0.496,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 1.1902439024390243,
1715
+ "grad_norm": 1.8547722101211548,
1716
+ "learning_rate": 4.828647722513785e-06,
1717
+ "loss": 0.6239,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 1.1951219512195121,
1722
+ "grad_norm": 2.0558724403381348,
1723
+ "learning_rate": 4.827251017718034e-06,
1724
+ "loss": 0.6466,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 1.2,
1729
+ "grad_norm": 1.8790161609649658,
1730
+ "learning_rate": 4.8258488473559794e-06,
1731
+ "loss": 0.6918,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 1.2048780487804878,
1736
+ "grad_norm": 1.9804240465164185,
1737
+ "learning_rate": 4.824441214720629e-06,
1738
+ "loss": 0.6641,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 1.2097560975609756,
1743
+ "grad_norm": 1.229308009147644,
1744
+ "learning_rate": 4.823028123117818e-06,
1745
+ "loss": 0.267,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 1.2146341463414634,
1750
+ "grad_norm": 1.3673735857009888,
1751
+ "learning_rate": 4.8216095758662015e-06,
1752
+ "loss": 0.543,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 1.2195121951219512,
1757
+ "grad_norm": 1.4206926822662354,
1758
+ "learning_rate": 4.82018557629725e-06,
1759
+ "loss": 0.6299,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 1.224390243902439,
1764
+ "grad_norm": 1.400539517402649,
1765
+ "learning_rate": 4.8187561277552376e-06,
1766
+ "loss": 0.4163,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 1.2292682926829268,
1771
+ "grad_norm": 1.3771297931671143,
1772
+ "learning_rate": 4.817321233597232e-06,
1773
+ "loss": 0.6105,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 1.2341463414634146,
1778
+ "grad_norm": 1.6716666221618652,
1779
+ "learning_rate": 4.815880897193095e-06,
1780
+ "loss": 0.3741,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 1.2390243902439024,
1785
+ "grad_norm": 1.9220954179763794,
1786
+ "learning_rate": 4.814435121925466e-06,
1787
+ "loss": 0.6125,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 1.2439024390243902,
1792
+ "grad_norm": 1.3171087503433228,
1793
+ "learning_rate": 4.812983911189761e-06,
1794
+ "loss": 0.4345,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 1.248780487804878,
1799
+ "grad_norm": 1.500893473625183,
1800
+ "learning_rate": 4.811527268394157e-06,
1801
+ "loss": 0.3848,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 1.2536585365853659,
1806
+ "grad_norm": 1.8701486587524414,
1807
+ "learning_rate": 4.810065196959591e-06,
1808
+ "loss": 0.4871,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 1.2585365853658537,
1813
+ "grad_norm": 1.7081878185272217,
1814
+ "learning_rate": 4.8085977003197496e-06,
1815
+ "loss": 0.6514,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 1.2634146341463415,
1820
+ "grad_norm": 2.583132266998291,
1821
+ "learning_rate": 4.807124781921059e-06,
1822
+ "loss": 0.8608,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 1.2682926829268293,
1827
+ "grad_norm": 1.467129111289978,
1828
+ "learning_rate": 4.805646445222679e-06,
1829
+ "loss": 0.3865,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 1.273170731707317,
1834
+ "grad_norm": 1.349326729774475,
1835
+ "learning_rate": 4.804162693696494e-06,
1836
+ "loss": 0.376,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 1.278048780487805,
1841
+ "grad_norm": 1.9350008964538574,
1842
+ "learning_rate": 4.802673530827105e-06,
1843
+ "loss": 0.4269,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 1.2829268292682927,
1848
+ "grad_norm": 1.1973533630371094,
1849
+ "learning_rate": 4.801178960111823e-06,
1850
+ "loss": 0.4611,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 1.2878048780487805,
1855
+ "grad_norm": 1.703409194946289,
1856
+ "learning_rate": 4.799678985060658e-06,
1857
+ "loss": 0.664,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 1.2926829268292683,
1862
+ "grad_norm": 1.3793981075286865,
1863
+ "learning_rate": 4.798173609196314e-06,
1864
+ "loss": 0.6515,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 1.2975609756097561,
1869
+ "grad_norm": 1.6443597078323364,
1870
+ "learning_rate": 4.796662836054176e-06,
1871
+ "loss": 0.3316,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 1.302439024390244,
1876
+ "grad_norm": 1.2548167705535889,
1877
+ "learning_rate": 4.795146669182304e-06,
1878
+ "loss": 0.4344,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 1.3073170731707318,
1883
+ "grad_norm": 1.4349764585494995,
1884
+ "learning_rate": 4.793625112141431e-06,
1885
+ "loss": 0.3804,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 1.3121951219512196,
1890
+ "grad_norm": 1.5517576932907104,
1891
+ "learning_rate": 4.792098168504943e-06,
1892
+ "loss": 0.4546,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 1.3170731707317074,
1897
+ "grad_norm": 1.3105218410491943,
1898
+ "learning_rate": 4.790565841858879e-06,
1899
+ "loss": 0.3096,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 1.3219512195121952,
1904
+ "grad_norm": 1.6386523246765137,
1905
+ "learning_rate": 4.789028135801919e-06,
1906
+ "loss": 0.6408,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 1.326829268292683,
1911
+ "grad_norm": 2.0389583110809326,
1912
+ "learning_rate": 4.787485053945377e-06,
1913
+ "loss": 0.7108,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 1.3317073170731708,
1918
+ "grad_norm": 1.4428800344467163,
1919
+ "learning_rate": 4.785936599913193e-06,
1920
+ "loss": 0.5489,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 1.3365853658536586,
1925
+ "grad_norm": 1.7775859832763672,
1926
+ "learning_rate": 4.784382777341922e-06,
1927
+ "loss": 0.5516,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 1.3414634146341464,
1932
+ "grad_norm": 2.048654794692993,
1933
+ "learning_rate": 4.782823589880729e-06,
1934
+ "loss": 0.8822,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 1.346341463414634,
1939
+ "grad_norm": 1.6368885040283203,
1940
+ "learning_rate": 4.7812590411913755e-06,
1941
+ "loss": 0.6008,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 1.3512195121951218,
1946
+ "grad_norm": 1.6349594593048096,
1947
+ "learning_rate": 4.779689134948217e-06,
1948
+ "loss": 0.8552,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 1.3560975609756096,
1953
+ "grad_norm": 2.0282487869262695,
1954
+ "learning_rate": 4.77811387483819e-06,
1955
+ "loss": 0.399,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 1.3609756097560974,
1960
+ "grad_norm": 1.902794599533081,
1961
+ "learning_rate": 4.776533264560804e-06,
1962
+ "loss": 0.583,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 1.3658536585365852,
1967
+ "grad_norm": 1.82004714012146,
1968
+ "learning_rate": 4.774947307828134e-06,
1969
+ "loss": 0.7195,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 1.370731707317073,
1974
+ "grad_norm": 1.4813153743743896,
1975
+ "learning_rate": 4.773356008364812e-06,
1976
+ "loss": 0.4371,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 1.3756097560975609,
1981
+ "grad_norm": 1.408211588859558,
1982
+ "learning_rate": 4.771759369908017e-06,
1983
+ "loss": 0.3133,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 1.3804878048780487,
1988
+ "grad_norm": 1.4923700094223022,
1989
+ "learning_rate": 4.7701573962074635e-06,
1990
+ "loss": 0.4993,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 1.3853658536585365,
1995
+ "grad_norm": 1.2863298654556274,
1996
+ "learning_rate": 4.7685500910254015e-06,
1997
+ "loss": 0.3568,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 1.3902439024390243,
2002
+ "grad_norm": 1.2870134115219116,
2003
+ "learning_rate": 4.766937458136598e-06,
2004
+ "loss": 0.5413,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 1.395121951219512,
2009
+ "grad_norm": 1.6780668497085571,
2010
+ "learning_rate": 4.765319501328332e-06,
2011
+ "loss": 0.6028,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 1.4,
2016
+ "grad_norm": 1.4770684242248535,
2017
+ "learning_rate": 4.763696224400391e-06,
2018
+ "loss": 0.3658,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 1.4048780487804877,
2023
+ "grad_norm": 1.2198718786239624,
2024
+ "learning_rate": 4.762067631165049e-06,
2025
+ "loss": 0.3817,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 1.4097560975609755,
2030
+ "grad_norm": 1.5318330526351929,
2031
+ "learning_rate": 4.760433725447071e-06,
2032
+ "loss": 0.5163,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 1.4146341463414633,
2037
+ "grad_norm": 1.849548578262329,
2038
+ "learning_rate": 4.758794511083697e-06,
2039
+ "loss": 0.6594,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 1.4195121951219511,
2044
+ "grad_norm": 1.7906076908111572,
2045
+ "learning_rate": 4.757149991924633e-06,
2046
+ "loss": 0.5289,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 1.424390243902439,
2051
+ "grad_norm": 1.328231930732727,
2052
+ "learning_rate": 4.755500171832045e-06,
2053
+ "loss": 0.3258,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 1.4292682926829268,
2058
+ "grad_norm": 1.619766354560852,
2059
+ "learning_rate": 4.753845054680548e-06,
2060
+ "loss": 0.4876,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 1.4341463414634146,
2065
+ "grad_norm": 1.6691818237304688,
2066
+ "learning_rate": 4.752184644357197e-06,
2067
+ "loss": 0.3899,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 1.4390243902439024,
2072
+ "grad_norm": 1.4808595180511475,
2073
+ "learning_rate": 4.750518944761477e-06,
2074
+ "loss": 0.4277,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 1.4439024390243902,
2079
+ "grad_norm": 1.71161687374115,
2080
+ "learning_rate": 4.748847959805297e-06,
2081
+ "loss": 0.4172,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 1.448780487804878,
2086
+ "grad_norm": 1.4367694854736328,
2087
+ "learning_rate": 4.7471716934129774e-06,
2088
+ "loss": 0.4121,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 1.4536585365853658,
2093
+ "grad_norm": 1.582480549812317,
2094
+ "learning_rate": 4.745490149521242e-06,
2095
+ "loss": 0.392,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 1.4585365853658536,
2100
+ "grad_norm": 1.9606919288635254,
2101
+ "learning_rate": 4.743803332079209e-06,
2102
+ "loss": 0.4478,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 1.4634146341463414,
2107
+ "grad_norm": 1.3635920286178589,
2108
+ "learning_rate": 4.742111245048382e-06,
2109
+ "loss": 0.3971,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 1.4682926829268292,
2114
+ "grad_norm": 1.2133499383926392,
2115
+ "learning_rate": 4.740413892402639e-06,
2116
+ "loss": 0.3502,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 1.473170731707317,
2121
+ "grad_norm": 1.5149365663528442,
2122
+ "learning_rate": 4.738711278128228e-06,
2123
+ "loss": 0.4716,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 1.4780487804878049,
2128
+ "grad_norm": 1.8573330640792847,
2129
+ "learning_rate": 4.7370034062237476e-06,
2130
+ "loss": 0.3264,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 1.4829268292682927,
2135
+ "grad_norm": 1.2374138832092285,
2136
+ "learning_rate": 4.73529028070015e-06,
2137
+ "loss": 0.4316,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 1.4878048780487805,
2142
+ "grad_norm": 1.797386646270752,
2143
+ "learning_rate": 4.733571905580723e-06,
2144
+ "loss": 0.7425,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 1.4926829268292683,
2149
+ "grad_norm": 1.6922880411148071,
2150
+ "learning_rate": 4.731848284901082e-06,
2151
+ "loss": 0.6001,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 1.497560975609756,
2156
+ "grad_norm": 1.5501389503479004,
2157
+ "learning_rate": 4.730119422709165e-06,
2158
+ "loss": 0.3536,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 1.502439024390244,
2163
+ "grad_norm": 1.9408127069473267,
2164
+ "learning_rate": 4.728385323065215e-06,
2165
+ "loss": 0.5422,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 1.5073170731707317,
2170
+ "grad_norm": 1.4196149110794067,
2171
+ "learning_rate": 4.7266459900417815e-06,
2172
+ "loss": 0.3504,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 1.5121951219512195,
2177
+ "grad_norm": 1.5519887208938599,
2178
+ "learning_rate": 4.724901427723698e-06,
2179
+ "loss": 0.6354,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 1.5170731707317073,
2184
+ "grad_norm": 1.867122769355774,
2185
+ "learning_rate": 4.723151640208084e-06,
2186
+ "loss": 0.3166,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 1.5219512195121951,
2191
+ "grad_norm": 1.6368682384490967,
2192
+ "learning_rate": 4.721396631604327e-06,
2193
+ "loss": 0.3401,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 1.526829268292683,
2198
+ "grad_norm": 1.2231279611587524,
2199
+ "learning_rate": 4.7196364060340785e-06,
2200
+ "loss": 0.3504,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 1.5317073170731708,
2205
+ "grad_norm": 1.622697353363037,
2206
+ "learning_rate": 4.7178709676312416e-06,
2207
+ "loss": 0.6338,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 1.5365853658536586,
2212
+ "grad_norm": 1.7756884098052979,
2213
+ "learning_rate": 4.716100320541961e-06,
2214
+ "loss": 0.8673,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 1.5414634146341464,
2219
+ "grad_norm": 1.6664738655090332,
2220
+ "learning_rate": 4.714324468924614e-06,
2221
+ "loss": 0.5582,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 1.5463414634146342,
2226
+ "grad_norm": 1.8026777505874634,
2227
+ "learning_rate": 4.712543416949803e-06,
2228
+ "loss": 0.6161,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 1.551219512195122,
2233
+ "grad_norm": 2.3471832275390625,
2234
+ "learning_rate": 4.71075716880034e-06,
2235
+ "loss": 0.5923,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 1.5560975609756098,
2240
+ "grad_norm": 1.9087973833084106,
2241
+ "learning_rate": 4.708965728671243e-06,
2242
+ "loss": 0.7339,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 1.5609756097560976,
2247
+ "grad_norm": 1.8473851680755615,
2248
+ "learning_rate": 4.7071691007697214e-06,
2249
+ "loss": 0.5554,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 1.5658536585365854,
2254
+ "grad_norm": 1.3977913856506348,
2255
+ "learning_rate": 4.705367289315172e-06,
2256
+ "loss": 0.5699,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 1.5707317073170732,
2261
+ "grad_norm": 1.6106524467468262,
2262
+ "learning_rate": 4.703560298539158e-06,
2263
+ "loss": 0.3525,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 1.575609756097561,
2268
+ "grad_norm": 1.5842078924179077,
2269
+ "learning_rate": 4.701748132685415e-06,
2270
+ "loss": 0.3749,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 1.5804878048780489,
2275
+ "grad_norm": 1.3624794483184814,
2276
+ "learning_rate": 4.699930796009825e-06,
2277
+ "loss": 0.4388,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 1.5853658536585367,
2282
+ "grad_norm": 1.9962315559387207,
2283
+ "learning_rate": 4.698108292780418e-06,
2284
+ "loss": 0.6069,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 1.5902439024390245,
2289
+ "grad_norm": 1.354267954826355,
2290
+ "learning_rate": 4.696280627277356e-06,
2291
+ "loss": 0.4206,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 1.5951219512195123,
2296
+ "grad_norm": 1.3546578884124756,
2297
+ "learning_rate": 4.6944478037929255e-06,
2298
+ "loss": 0.416,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 1.6,
2303
+ "grad_norm": 1.5159077644348145,
2304
+ "learning_rate": 4.692609826631525e-06,
2305
+ "loss": 0.4456,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 1.604878048780488,
2310
+ "grad_norm": 1.7104778289794922,
2311
+ "learning_rate": 4.690766700109659e-06,
2312
+ "loss": 0.295,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 1.6097560975609757,
2317
+ "grad_norm": 1.1690094470977783,
2318
+ "learning_rate": 4.6889184285559234e-06,
2319
+ "loss": 0.2971,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 1.6146341463414635,
2324
+ "grad_norm": 2.9057915210723877,
2325
+ "learning_rate": 4.687065016310996e-06,
2326
+ "loss": 0.6427,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 1.6195121951219513,
2331
+ "grad_norm": 1.862723469734192,
2332
+ "learning_rate": 4.685206467727631e-06,
2333
+ "loss": 0.5023,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 1.6243902439024391,
2338
+ "grad_norm": 1.4070931673049927,
2339
+ "learning_rate": 4.683342787170644e-06,
2340
+ "loss": 0.4218,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 1.629268292682927,
2345
+ "grad_norm": 1.7011152505874634,
2346
+ "learning_rate": 4.6814739790169006e-06,
2347
+ "loss": 0.4429,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 1.6341463414634148,
2352
+ "grad_norm": 1.8267077207565308,
2353
+ "learning_rate": 4.679600047655313e-06,
2354
+ "loss": 0.6062,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 1.6390243902439026,
2359
+ "grad_norm": 2.120957612991333,
2360
+ "learning_rate": 4.6777209974868194e-06,
2361
+ "loss": 0.9207,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 1.6439024390243904,
2366
+ "grad_norm": 1.6445318460464478,
2367
+ "learning_rate": 4.675836832924387e-06,
2368
+ "loss": 0.4324,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 1.6487804878048782,
2373
+ "grad_norm": 1.2712141275405884,
2374
+ "learning_rate": 4.673947558392989e-06,
2375
+ "loss": 0.2775,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 1.653658536585366,
2380
+ "grad_norm": 1.1474132537841797,
2381
+ "learning_rate": 4.6720531783296e-06,
2382
+ "loss": 0.3437,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 1.6585365853658538,
2387
+ "grad_norm": 1.6361477375030518,
2388
+ "learning_rate": 4.670153697183185e-06,
2389
+ "loss": 0.4716,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 1.6634146341463416,
2394
+ "grad_norm": 1.6338160037994385,
2395
+ "learning_rate": 4.668249119414692e-06,
2396
+ "loss": 0.4693,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 1.6682926829268294,
2401
+ "grad_norm": 1.531384825706482,
2402
+ "learning_rate": 4.666339449497033e-06,
2403
+ "loss": 0.5064,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 1.6731707317073172,
2408
+ "grad_norm": 1.8817652463912964,
2409
+ "learning_rate": 4.664424691915084e-06,
2410
+ "loss": 0.4733,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 1.678048780487805,
2415
+ "grad_norm": 2.0723443031311035,
2416
+ "learning_rate": 4.6625048511656675e-06,
2417
+ "loss": 0.48,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 1.6829268292682928,
2422
+ "grad_norm": 1.6939678192138672,
2423
+ "learning_rate": 4.660579931757543e-06,
2424
+ "loss": 0.3561,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 1.6878048780487804,
2429
+ "grad_norm": 1.1976394653320312,
2430
+ "learning_rate": 4.6586499382113985e-06,
2431
+ "loss": 0.405,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 1.6926829268292682,
2436
+ "grad_norm": 1.6529325246810913,
2437
+ "learning_rate": 4.6567148750598375e-06,
2438
+ "loss": 0.6813,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 1.697560975609756,
2443
+ "grad_norm": 2.042006492614746,
2444
+ "learning_rate": 4.6547747468473705e-06,
2445
+ "loss": 0.7769,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 1.7024390243902439,
2450
+ "grad_norm": 1.7209240198135376,
2451
+ "learning_rate": 4.652829558130404e-06,
2452
+ "loss": 0.3444,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 1.7073170731707317,
2457
+ "grad_norm": 1.9713730812072754,
2458
+ "learning_rate": 4.6508793134772265e-06,
2459
+ "loss": 0.4758,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 1.7121951219512195,
2464
+ "grad_norm": 1.1846798658370972,
2465
+ "learning_rate": 4.648924017468003e-06,
2466
+ "loss": 0.3516,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 1.7170731707317073,
2471
+ "grad_norm": 1.9596673250198364,
2472
+ "learning_rate": 4.646963674694761e-06,
2473
+ "loss": 0.6718,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 1.721951219512195,
2478
+ "grad_norm": 1.368725061416626,
2479
+ "learning_rate": 4.64499828976138e-06,
2480
+ "loss": 0.2733,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 1.726829268292683,
2485
+ "grad_norm": 1.7530791759490967,
2486
+ "learning_rate": 4.64302786728358e-06,
2487
+ "loss": 0.384,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 1.7317073170731707,
2492
+ "grad_norm": 1.4671913385391235,
2493
+ "learning_rate": 4.641052411888913e-06,
2494
+ "loss": 0.4127,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 1.7365853658536585,
2499
+ "grad_norm": 2.0249969959259033,
2500
+ "learning_rate": 4.6390719282167515e-06,
2501
+ "loss": 0.3638,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 1.7414634146341463,
2506
+ "grad_norm": 1.5483126640319824,
2507
+ "learning_rate": 4.637086420918276e-06,
2508
+ "loss": 0.6348,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 1.7463414634146341,
2513
+ "grad_norm": 1.5062689781188965,
2514
+ "learning_rate": 4.635095894656465e-06,
2515
+ "loss": 0.5401,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 1.751219512195122,
2520
+ "grad_norm": 1.1978603601455688,
2521
+ "learning_rate": 4.633100354106085e-06,
2522
+ "loss": 0.2961,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 1.7560975609756098,
2527
+ "grad_norm": 1.768799901008606,
2528
+ "learning_rate": 4.631099803953677e-06,
2529
+ "loss": 0.7047,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 1.7609756097560976,
2534
+ "grad_norm": 1.4491766691207886,
2535
+ "learning_rate": 4.629094248897546e-06,
2536
+ "loss": 0.3413,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 1.7658536585365854,
2541
+ "grad_norm": 1.5324903726577759,
2542
+ "learning_rate": 4.627083693647757e-06,
2543
+ "loss": 0.3901,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 1.7707317073170732,
2548
+ "grad_norm": 1.591989517211914,
2549
+ "learning_rate": 4.625068142926111e-06,
2550
+ "loss": 0.6385,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 1.775609756097561,
2555
+ "grad_norm": 1.3414136171340942,
2556
+ "learning_rate": 4.623047601466144e-06,
2557
+ "loss": 0.4892,
2558
+ "step": 364
2559
+ },
2560
+ {
2561
+ "epoch": 1.7804878048780488,
2562
+ "grad_norm": 1.4184423685073853,
2563
+ "learning_rate": 4.621022074013114e-06,
2564
+ "loss": 0.458,
2565
+ "step": 365
2566
+ },
2567
+ {
2568
+ "epoch": 1.7853658536585366,
2569
+ "grad_norm": 1.8010565042495728,
2570
+ "learning_rate": 4.618991565323987e-06,
2571
+ "loss": 0.4202,
2572
+ "step": 366
2573
+ },
2574
+ {
2575
+ "epoch": 1.7902439024390244,
2576
+ "grad_norm": 1.34525728225708,
2577
+ "learning_rate": 4.616956080167426e-06,
2578
+ "loss": 0.4154,
2579
+ "step": 367
2580
+ },
2581
+ {
2582
+ "epoch": 1.7951219512195122,
2583
+ "grad_norm": 1.8559147119522095,
2584
+ "learning_rate": 4.614915623323786e-06,
2585
+ "loss": 0.7751,
2586
+ "step": 368
2587
+ },
2588
+ {
2589
+ "epoch": 1.8,
2590
+ "grad_norm": 1.462708830833435,
2591
+ "learning_rate": 4.612870199585092e-06,
2592
+ "loss": 0.3168,
2593
+ "step": 369
2594
+ },
2595
+ {
2596
+ "epoch": 1.8048780487804879,
2597
+ "grad_norm": 1.8187520503997803,
2598
+ "learning_rate": 4.610819813755038e-06,
2599
+ "loss": 0.4109,
2600
+ "step": 370
2601
+ },
2602
+ {
2603
+ "epoch": 1.8097560975609757,
2604
+ "grad_norm": 1.5606852769851685,
2605
+ "learning_rate": 4.608764470648971e-06,
2606
+ "loss": 0.3183,
2607
+ "step": 371
2608
+ },
2609
+ {
2610
+ "epoch": 1.8146341463414632,
2611
+ "grad_norm": 1.7732083797454834,
2612
+ "learning_rate": 4.606704175093879e-06,
2613
+ "loss": 0.3698,
2614
+ "step": 372
2615
+ },
2616
+ {
2617
+ "epoch": 1.819512195121951,
2618
+ "grad_norm": 1.7014015913009644,
2619
+ "learning_rate": 4.604638931928383e-06,
2620
+ "loss": 0.6874,
2621
+ "step": 373
2622
+ },
2623
+ {
2624
+ "epoch": 1.8243902439024389,
2625
+ "grad_norm": 1.4034913778305054,
2626
+ "learning_rate": 4.602568746002718e-06,
2627
+ "loss": 0.3915,
2628
+ "step": 374
2629
+ },
2630
+ {
2631
+ "epoch": 1.8292682926829267,
2632
+ "grad_norm": 1.9640151262283325,
2633
+ "learning_rate": 4.600493622178734e-06,
2634
+ "loss": 0.7138,
2635
+ "step": 375
2636
+ },
2637
+ {
2638
+ "epoch": 1.8341463414634145,
2639
+ "grad_norm": 1.7484368085861206,
2640
+ "learning_rate": 4.598413565329876e-06,
2641
+ "loss": 0.4021,
2642
+ "step": 376
2643
+ },
2644
+ {
2645
+ "epoch": 1.8390243902439023,
2646
+ "grad_norm": 1.303987979888916,
2647
+ "learning_rate": 4.596328580341169e-06,
2648
+ "loss": 0.435,
2649
+ "step": 377
2650
+ },
2651
+ {
2652
+ "epoch": 1.84390243902439,
2653
+ "grad_norm": 1.7868525981903076,
2654
+ "learning_rate": 4.5942386721092195e-06,
2655
+ "loss": 0.5827,
2656
+ "step": 378
2657
+ },
2658
+ {
2659
+ "epoch": 1.848780487804878,
2660
+ "grad_norm": 1.9132968187332153,
2661
+ "learning_rate": 4.592143845542189e-06,
2662
+ "loss": 0.5401,
2663
+ "step": 379
2664
+ },
2665
+ {
2666
+ "epoch": 1.8536585365853657,
2667
+ "grad_norm": 1.8668831586837769,
2668
+ "learning_rate": 4.590044105559797e-06,
2669
+ "loss": 0.7394,
2670
+ "step": 380
2671
+ },
2672
+ {
2673
+ "epoch": 1.8585365853658535,
2674
+ "grad_norm": 1.2784031629562378,
2675
+ "learning_rate": 4.587939457093296e-06,
2676
+ "loss": 0.378,
2677
+ "step": 381
2678
+ },
2679
+ {
2680
+ "epoch": 1.8634146341463413,
2681
+ "grad_norm": 2.4104111194610596,
2682
+ "learning_rate": 4.585829905085468e-06,
2683
+ "loss": 0.5195,
2684
+ "step": 382
2685
+ },
2686
+ {
2687
+ "epoch": 1.8682926829268292,
2688
+ "grad_norm": 1.7685518264770508,
2689
+ "learning_rate": 4.5837154544906135e-06,
2690
+ "loss": 0.649,
2691
+ "step": 383
2692
+ },
2693
+ {
2694
+ "epoch": 1.873170731707317,
2695
+ "grad_norm": 1.6093931198120117,
2696
+ "learning_rate": 4.581596110274535e-06,
2697
+ "loss": 0.529,
2698
+ "step": 384
2699
+ },
2700
+ {
2701
+ "epoch": 1.8780487804878048,
2702
+ "grad_norm": 1.6542202234268188,
2703
+ "learning_rate": 4.579471877414527e-06,
2704
+ "loss": 0.8192,
2705
+ "step": 385
2706
+ },
2707
+ {
2708
+ "epoch": 1.8829268292682926,
2709
+ "grad_norm": 2.2171826362609863,
2710
+ "learning_rate": 4.577342760899368e-06,
2711
+ "loss": 0.5918,
2712
+ "step": 386
2713
+ },
2714
+ {
2715
+ "epoch": 1.8878048780487804,
2716
+ "grad_norm": 1.5181479454040527,
2717
+ "learning_rate": 4.575208765729302e-06,
2718
+ "loss": 0.4064,
2719
+ "step": 387
2720
+ },
2721
+ {
2722
+ "epoch": 1.8926829268292682,
2723
+ "grad_norm": 1.5646779537200928,
2724
+ "learning_rate": 4.573069896916035e-06,
2725
+ "loss": 0.6088,
2726
+ "step": 388
2727
+ },
2728
+ {
2729
+ "epoch": 1.897560975609756,
2730
+ "grad_norm": 1.4816564321517944,
2731
+ "learning_rate": 4.5709261594827125e-06,
2732
+ "loss": 0.4965,
2733
+ "step": 389
2734
+ },
2735
+ {
2736
+ "epoch": 1.9024390243902438,
2737
+ "grad_norm": 1.4817956686019897,
2738
+ "learning_rate": 4.568777558463922e-06,
2739
+ "loss": 0.3348,
2740
+ "step": 390
2741
+ },
2742
+ {
2743
+ "epoch": 1.9073170731707316,
2744
+ "grad_norm": 1.482393503189087,
2745
+ "learning_rate": 4.566624098905665e-06,
2746
+ "loss": 0.5659,
2747
+ "step": 391
2748
+ },
2749
+ {
2750
+ "epoch": 1.9121951219512194,
2751
+ "grad_norm": 1.7307995557785034,
2752
+ "learning_rate": 4.564465785865359e-06,
2753
+ "loss": 0.4202,
2754
+ "step": 392
2755
+ },
2756
+ {
2757
+ "epoch": 1.9170731707317072,
2758
+ "grad_norm": 1.3334952592849731,
2759
+ "learning_rate": 4.56230262441182e-06,
2760
+ "loss": 0.3028,
2761
+ "step": 393
2762
+ },
2763
+ {
2764
+ "epoch": 1.921951219512195,
2765
+ "grad_norm": 1.3310606479644775,
2766
+ "learning_rate": 4.560134619625247e-06,
2767
+ "loss": 0.4366,
2768
+ "step": 394
2769
+ },
2770
+ {
2771
+ "epoch": 1.9268292682926829,
2772
+ "grad_norm": 1.4220263957977295,
2773
+ "learning_rate": 4.5579617765972155e-06,
2774
+ "loss": 0.4635,
2775
+ "step": 395
2776
+ },
2777
+ {
2778
+ "epoch": 1.9317073170731707,
2779
+ "grad_norm": 1.6790047883987427,
2780
+ "learning_rate": 4.555784100430662e-06,
2781
+ "loss": 0.4049,
2782
+ "step": 396
2783
+ },
2784
+ {
2785
+ "epoch": 1.9365853658536585,
2786
+ "grad_norm": 1.489020824432373,
2787
+ "learning_rate": 4.553601596239877e-06,
2788
+ "loss": 0.3564,
2789
+ "step": 397
2790
+ },
2791
+ {
2792
+ "epoch": 1.9414634146341463,
2793
+ "grad_norm": 1.3163279294967651,
2794
+ "learning_rate": 4.551414269150489e-06,
2795
+ "loss": 0.3862,
2796
+ "step": 398
2797
+ },
2798
+ {
2799
+ "epoch": 1.946341463414634,
2800
+ "grad_norm": 1.4149785041809082,
2801
+ "learning_rate": 4.54922212429945e-06,
2802
+ "loss": 0.3606,
2803
+ "step": 399
2804
+ },
2805
+ {
2806
+ "epoch": 1.951219512195122,
2807
+ "grad_norm": 1.5937131643295288,
2808
+ "learning_rate": 4.547025166835027e-06,
2809
+ "loss": 0.506,
2810
+ "step": 400
2811
+ },
2812
+ {
2813
+ "epoch": 1.9560975609756097,
2814
+ "grad_norm": 1.6854530572891235,
2815
+ "learning_rate": 4.544823401916794e-06,
2816
+ "loss": 0.6974,
2817
+ "step": 401
2818
+ },
2819
+ {
2820
+ "epoch": 1.9609756097560975,
2821
+ "grad_norm": 1.5636667013168335,
2822
+ "learning_rate": 4.542616834715612e-06,
2823
+ "loss": 0.4172,
2824
+ "step": 402
2825
+ },
2826
+ {
2827
+ "epoch": 1.9658536585365853,
2828
+ "grad_norm": 1.484148383140564,
2829
+ "learning_rate": 4.540405470413618e-06,
2830
+ "loss": 0.3189,
2831
+ "step": 403
2832
+ },
2833
+ {
2834
+ "epoch": 1.9707317073170731,
2835
+ "grad_norm": 1.4421648979187012,
2836
+ "learning_rate": 4.53818931420422e-06,
2837
+ "loss": 0.5316,
2838
+ "step": 404
2839
+ },
2840
+ {
2841
+ "epoch": 1.975609756097561,
2842
+ "grad_norm": 1.4186997413635254,
2843
+ "learning_rate": 4.535968371292076e-06,
2844
+ "loss": 0.4661,
2845
+ "step": 405
2846
+ },
2847
+ {
2848
+ "epoch": 1.9804878048780488,
2849
+ "grad_norm": 1.2781983613967896,
2850
+ "learning_rate": 4.533742646893086e-06,
2851
+ "loss": 0.4689,
2852
+ "step": 406
2853
+ },
2854
+ {
2855
+ "epoch": 1.9853658536585366,
2856
+ "grad_norm": 1.588996171951294,
2857
+ "learning_rate": 4.531512146234383e-06,
2858
+ "loss": 0.5309,
2859
+ "step": 407
2860
+ },
2861
+ {
2862
+ "epoch": 1.9902439024390244,
2863
+ "grad_norm": 1.7258890867233276,
2864
+ "learning_rate": 4.529276874554312e-06,
2865
+ "loss": 0.7082,
2866
+ "step": 408
2867
+ },
2868
+ {
2869
+ "epoch": 1.9951219512195122,
2870
+ "grad_norm": 1.4261395931243896,
2871
+ "learning_rate": 4.527036837102426e-06,
2872
+ "loss": 0.3534,
2873
+ "step": 409
2874
+ },
2875
+ {
2876
+ "epoch": 2.0,
2877
+ "grad_norm": 1.835606575012207,
2878
+ "learning_rate": 4.524792039139471e-06,
2879
+ "loss": 0.5411,
2880
+ "step": 410
2881
+ }
2882
+ ],
2883
+ "logging_steps": 1,
2884
+ "max_steps": 2050,
2885
+ "num_input_tokens_seen": 0,
2886
+ "num_train_epochs": 10,
2887
+ "save_steps": 208,
2888
+ "stateful_callbacks": {
2889
+ "TrainerControl": {
2890
+ "args": {
2891
+ "should_epoch_stop": false,
2892
+ "should_evaluate": false,
2893
+ "should_log": false,
2894
+ "should_save": true,
2895
+ "should_training_stop": false
2896
+ },
2897
+ "attributes": {}
2898
+ }
2899
+ },
2900
+ "total_flos": 1.2119917182163354e+17,
2901
+ "train_batch_size": 1,
2902
+ "trial_name": null,
2903
+ "trial_params": null
2904
+ }
qwen2_5_7b_instruct/limo/checkpoint-410/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_7b_instruct/limo/trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-185/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2_5_7b_instruct/limo_filtered_incorrect/checkpoint-185/vocab.json ADDED
The diff for this file is too large to render. See raw diff