Hizy commited on
Commit
440550f
·
verified ·
1 Parent(s): 5d3fcb4

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. .gitattributes +2 -0
  2. osgenesis-llama/README.md +67 -0
  3. osgenesis-llama/all_results.json +12 -0
  4. osgenesis-llama/chat_template.jinja +109 -0
  5. osgenesis-llama/checkpoint-500/chat_template.jinja +109 -0
  6. osgenesis-llama/checkpoint-500/config.json +36 -0
  7. osgenesis-llama/checkpoint-500/generation_config.json +14 -0
  8. osgenesis-llama/checkpoint-500/model-00001-of-00004.safetensors +3 -0
  9. osgenesis-llama/checkpoint-500/model-00002-of-00004.safetensors +3 -0
  10. osgenesis-llama/checkpoint-500/model-00003-of-00004.safetensors +3 -0
  11. osgenesis-llama/checkpoint-500/model-00004-of-00004.safetensors +3 -0
  12. osgenesis-llama/checkpoint-500/model.safetensors.index.json +299 -0
  13. osgenesis-llama/checkpoint-500/special_tokens_map.json +17 -0
  14. osgenesis-llama/checkpoint-500/tokenizer.json +3 -0
  15. osgenesis-llama/checkpoint-500/tokenizer_config.json +2065 -0
  16. osgenesis-llama/checkpoint-500/trainer_state.json +392 -0
  17. osgenesis-llama/checkpoint-500/training_args.bin +3 -0
  18. osgenesis-llama/config.json +36 -0
  19. osgenesis-llama/eval_results.json +7 -0
  20. osgenesis-llama/generation_config.json +14 -0
  21. osgenesis-llama/model-00001-of-00004.safetensors +3 -0
  22. osgenesis-llama/model-00002-of-00004.safetensors +3 -0
  23. osgenesis-llama/model-00003-of-00004.safetensors +3 -0
  24. osgenesis-llama/model-00004-of-00004.safetensors +3 -0
  25. osgenesis-llama/model.safetensors.index.json +299 -0
  26. osgenesis-llama/runs/Dec13_20-08-42_hgx002/events.out.tfevents.1765628701.hgx002 +3 -0
  27. osgenesis-llama/runs/Dec13_20-08-42_hgx002/events.out.tfevents.1765636326.hgx002 +3 -0
  28. osgenesis-llama/special_tokens_map.json +17 -0
  29. osgenesis-llama/tokenizer.json +3 -0
  30. osgenesis-llama/tokenizer_config.json +2065 -0
  31. osgenesis-llama/train_results.json +8 -0
  32. osgenesis-llama/trainer_log.jsonl +129 -0
  33. osgenesis-llama/trainer_state.json +941 -0
  34. osgenesis-llama/training_args.bin +3 -0
  35. osgenesis-llama/training_eval_loss.png +0 -0
  36. osgenesis-llama/training_loss.png +0 -0
.gitattributes CHANGED
@@ -39,3 +39,5 @@ web_rl_7b_lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  web_rl_7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  osgenesis7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
39
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  web_rl_7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  osgenesis7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ osgenesis-llama/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ osgenesis-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
osgenesis-llama/README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Meta-Llama/Meta-Llama-3.1-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: osgenesis_llama
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # osgenesis_llama
18
+
19
+ This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Meta-Llama-3.1-8B-Instruct](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Meta-Llama-3.1-8B-Instruct) on the osgenesis_sft dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4605
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 4
47
+ - total_train_batch_size: 16
48
+ - total_eval_batch_size: 4
49
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 3.0
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:------:|:----:|:---------------:|
58
+ | 0.2856 | 1.1849 | 500 | 0.4519 |
59
+ | 0.1072 | 2.3699 | 1000 | 0.4592 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.57.1
65
+ - Pytorch 2.7.1+cu126
66
+ - Datasets 4.0.0
67
+ - Tokenizers 0.22.2-rc0
osgenesis-llama/all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.46054548025131226,
4
+ "eval_runtime": 65.9074,
5
+ "eval_samples_per_second": 11.38,
6
+ "eval_steps_per_second": 2.852,
7
+ "total_flos": 54228985774080.0,
8
+ "train_loss": 0.2981918969472626,
9
+ "train_runtime": 7343.4841,
10
+ "train_samples_per_second": 2.756,
11
+ "train_steps_per_second": 0.172
12
+ }
osgenesis-llama/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
osgenesis-llama/checkpoint-500/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
osgenesis-llama/checkpoint-500/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128009,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "transformers_version": "4.57.1",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
osgenesis-llama/checkpoint-500/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128009,
6
+ 128001,
7
+ 128008,
8
+ 128009
9
+ ],
10
+ "pad_token_id": 128009,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
+ "transformers_version": "4.57.1"
14
+ }
osgenesis-llama/checkpoint-500/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d4b57898ec563037cf69153782d6f50bbdb64758e95dd52a6a32a31bc143385
3
+ size 4976698672
osgenesis-llama/checkpoint-500/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429cd1bf0e279044d2e7b669342778fa85b0030f66deb3ddeeb85493fdcc24ec
3
+ size 4999802720
osgenesis-llama/checkpoint-500/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9d61262a9a0b6789c04abe40434f0697c4185f8443b4ff0f77633dd6d457e5
3
+ size 4915916176
osgenesis-llama/checkpoint-500/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b7096d0c7dfc9ac2f44a09e4fbc528f2d0856e9e6b5bdfd9bec600252a106e
3
+ size 1168138808
osgenesis-llama/checkpoint-500/model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 266240,
4
+ "total_size": 16060522496
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.norm.weight": "model-00004-of-00004.safetensors"
298
+ }
299
+ }
osgenesis-llama/checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
osgenesis-llama/checkpoint-500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
osgenesis-llama/checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
osgenesis-llama/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.1849436870183758,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.023710729104919975,
14
+ "grad_norm": 21.654089677762492,
15
+ "learning_rate": 7.086614173228346e-07,
16
+ "loss": 0.9273,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.04742145820983995,
21
+ "grad_norm": 13.158033432354436,
22
+ "learning_rate": 1.4960629921259845e-06,
23
+ "loss": 0.7261,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.07113218731475993,
28
+ "grad_norm": 8.905781707547229,
29
+ "learning_rate": 2.283464566929134e-06,
30
+ "loss": 0.5949,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0948429164196799,
35
+ "grad_norm": 7.255255210581632,
36
+ "learning_rate": 3.0708661417322837e-06,
37
+ "loss": 0.5516,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.11855364552459988,
42
+ "grad_norm": 6.974161059541655,
43
+ "learning_rate": 3.858267716535433e-06,
44
+ "loss": 0.5111,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.14226437462951985,
49
+ "grad_norm": 5.651318484615861,
50
+ "learning_rate": 4.645669291338583e-06,
51
+ "loss": 0.5245,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.16597510373443983,
56
+ "grad_norm": 6.036940205072249,
57
+ "learning_rate": 5.433070866141733e-06,
58
+ "loss": 0.506,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.1896858328393598,
63
+ "grad_norm": 5.1755975857717536,
64
+ "learning_rate": 6.220472440944882e-06,
65
+ "loss": 0.4725,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.21339656194427978,
70
+ "grad_norm": 6.635004608042446,
71
+ "learning_rate": 7.0078740157480315e-06,
72
+ "loss": 0.5519,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.23710729104919975,
77
+ "grad_norm": 6.068189315595479,
78
+ "learning_rate": 7.79527559055118e-06,
79
+ "loss": 0.4936,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.26081802015411976,
84
+ "grad_norm": 5.090926729964026,
85
+ "learning_rate": 8.582677165354332e-06,
86
+ "loss": 0.5279,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.2845287492590397,
91
+ "grad_norm": 5.197075333191967,
92
+ "learning_rate": 9.370078740157481e-06,
93
+ "loss": 0.5046,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.3082394783639597,
98
+ "grad_norm": 4.854665516020856,
99
+ "learning_rate": 9.999923923382317e-06,
100
+ "loss": 0.5248,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.33195020746887965,
105
+ "grad_norm": 5.158338502799311,
106
+ "learning_rate": 9.997261484836916e-06,
107
+ "loss": 0.5139,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.35566093657379966,
112
+ "grad_norm": 4.94416310954264,
113
+ "learning_rate": 9.990797530151441e-06,
114
+ "loss": 0.53,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.3793716656787196,
119
+ "grad_norm": 5.336809452970413,
120
+ "learning_rate": 9.980536976584711e-06,
121
+ "loss": 0.5546,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.4030823947836396,
126
+ "grad_norm": 4.950482275472653,
127
+ "learning_rate": 9.966487629543766e-06,
128
+ "loss": 0.5364,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.42679312388855956,
133
+ "grad_norm": 4.323856432808166,
134
+ "learning_rate": 9.948660176646152e-06,
135
+ "loss": 0.5286,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.45050385299347956,
140
+ "grad_norm": 4.224858492109143,
141
+ "learning_rate": 9.92706817958964e-06,
142
+ "loss": 0.5404,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.4742145820983995,
147
+ "grad_norm": 7.159206766003931,
148
+ "learning_rate": 9.901728063835561e-06,
149
+ "loss": 0.521,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.4979253112033195,
154
+ "grad_norm": 4.79820944593641,
155
+ "learning_rate": 9.87265910611365e-06,
156
+ "loss": 0.5371,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.5216360403082395,
161
+ "grad_norm": 4.352275642498719,
162
+ "learning_rate": 9.839883419757838e-06,
163
+ "loss": 0.5409,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.5453467694131594,
168
+ "grad_norm": 3.0512515615824087,
169
+ "learning_rate": 9.803425937884202e-06,
170
+ "loss": 0.4904,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.5690574985180794,
175
+ "grad_norm": 3.6070996957510335,
176
+ "learning_rate": 9.763314394423855e-06,
177
+ "loss": 0.5059,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5927682276229994,
182
+ "grad_norm": 3.667369038644614,
183
+ "learning_rate": 9.719579303025188e-06,
184
+ "loss": 0.5044,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.6164789567279194,
189
+ "grad_norm": 3.762840357591941,
190
+ "learning_rate": 9.672253933841533e-06,
191
+ "loss": 0.4818,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.6401896858328393,
196
+ "grad_norm": 4.190173408376692,
197
+ "learning_rate": 9.621374288221896e-06,
198
+ "loss": 0.513,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.6639004149377593,
203
+ "grad_norm": 3.628061060797804,
204
+ "learning_rate": 9.566979071324014e-06,
205
+ "loss": 0.5029,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.6876111440426793,
210
+ "grad_norm": 3.3521609497091087,
211
+ "learning_rate": 9.509109662670573e-06,
212
+ "loss": 0.5063,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.7113218731475993,
217
+ "grad_norm": 3.5138596120651413,
218
+ "learning_rate": 9.44781008467098e-06,
219
+ "loss": 0.4757,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.7350326022525193,
224
+ "grad_norm": 3.537105322871914,
225
+ "learning_rate": 9.38312696913265e-06,
226
+ "loss": 0.5094,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.7587433313574392,
231
+ "grad_norm": 3.507194476519431,
232
+ "learning_rate": 9.315109521787252e-06,
233
+ "loss": 0.4819,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.7824540604623592,
238
+ "grad_norm": 3.5387079596783955,
239
+ "learning_rate": 9.243809484858936e-06,
240
+ "loss": 0.4519,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.8061647895672792,
245
+ "grad_norm": 3.4682051852004547,
246
+ "learning_rate": 9.169281097702997e-06,
247
+ "loss": 0.4535,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.8298755186721992,
252
+ "grad_norm": 3.2582589966291047,
253
+ "learning_rate": 9.091581055544913e-06,
254
+ "loss": 0.4649,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.8535862477771191,
259
+ "grad_norm": 3.7605884819584032,
260
+ "learning_rate": 9.01076846635117e-06,
261
+ "loss": 0.4717,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.8772969768820391,
266
+ "grad_norm": 3.0701941745829577,
267
+ "learning_rate": 8.926904805864642e-06,
268
+ "loss": 0.4548,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.9010077059869591,
273
+ "grad_norm": 3.9484221413414207,
274
+ "learning_rate": 8.84005387083879e-06,
275
+ "loss": 0.4771,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.9247184350918791,
280
+ "grad_norm": 3.628849408692728,
281
+ "learning_rate": 8.750281730506186e-06,
282
+ "loss": 0.4662,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.948429164196799,
287
+ "grad_norm": 2.714678598006085,
288
+ "learning_rate": 8.657656676318346e-06,
289
+ "loss": 0.4063,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.972139893301719,
294
+ "grad_norm": 2.862273936518975,
295
+ "learning_rate": 8.562249169995062e-06,
296
+ "loss": 0.4747,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.995850622406639,
301
+ "grad_norm": 4.015082243219481,
302
+ "learning_rate": 8.464131789922773e-06,
303
+ "loss": 0.4664,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.018968583283936,
308
+ "grad_norm": 3.317988973859346,
309
+ "learning_rate": 8.363379175942736e-06,
310
+ "loss": 0.3373,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.042679312388856,
315
+ "grad_norm": 2.66737361543537,
316
+ "learning_rate": 8.260067972571028e-06,
317
+ "loss": 0.2978,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.066390041493776,
322
+ "grad_norm": 3.690753100061689,
323
+ "learning_rate": 8.154276770693525e-06,
324
+ "loss": 0.3137,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.0901007705986958,
329
+ "grad_norm": 2.7421307138902224,
330
+ "learning_rate": 8.046086047780269e-06,
331
+ "loss": 0.3005,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.113811499703616,
336
+ "grad_norm": 3.2441433406106253,
337
+ "learning_rate": 7.93557810666464e-06,
338
+ "loss": 0.2991,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.1375222288085358,
343
+ "grad_norm": 2.8171872482828815,
344
+ "learning_rate": 7.822837012933968e-06,
345
+ "loss": 0.2881,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.161232957913456,
350
+ "grad_norm": 2.8540163878356157,
351
+ "learning_rate": 7.707948530979163e-06,
352
+ "loss": 0.2979,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.1849436870183758,
357
+ "grad_norm": 3.1607436486481273,
358
+ "learning_rate": 7.5910000587520406e-06,
359
+ "loss": 0.2856,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.1849436870183758,
364
+ "eval_loss": 0.45193034410476685,
365
+ "eval_runtime": 54.069,
366
+ "eval_samples_per_second": 13.871,
367
+ "eval_steps_per_second": 3.477,
368
+ "step": 500
369
+ }
370
+ ],
371
+ "logging_steps": 10,
372
+ "max_steps": 1266,
373
+ "num_input_tokens_seen": 0,
374
+ "num_train_epochs": 3,
375
+ "save_steps": 500,
376
+ "stateful_callbacks": {
377
+ "TrainerControl": {
378
+ "args": {
379
+ "should_epoch_stop": false,
380
+ "should_evaluate": false,
381
+ "should_log": false,
382
+ "should_save": true,
383
+ "should_training_stop": false
384
+ },
385
+ "attributes": {}
386
+ }
387
+ },
388
+ "total_flos": 21403957985280.0,
389
+ "train_batch_size": 1,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }
osgenesis-llama/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde35580b3b57f2821caace6e28a250ea4a6829eabf04747110a6888bc894f90
3
+ size 8081
osgenesis-llama/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128009,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "transformers_version": "4.57.1",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
osgenesis-llama/eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.46054548025131226,
4
+ "eval_runtime": 65.9074,
5
+ "eval_samples_per_second": 11.38,
6
+ "eval_steps_per_second": 2.852
7
+ }
osgenesis-llama/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128009,
6
+ 128001,
7
+ 128008,
8
+ 128009
9
+ ],
10
+ "pad_token_id": 128009,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
+ "transformers_version": "4.57.1"
14
+ }
osgenesis-llama/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6874b4ae3d4eee7b4253af9f672985c9a9375d2cf3693ffc0295bf3a019cef
3
+ size 4976698672
osgenesis-llama/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7e791e28d5cd87e88785b3a8b85cd8da3aeb9b8338d178f7b381777af70d2a
3
+ size 4999802720
osgenesis-llama/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ef5e2fa02ebb99788e6c46b4d8bc999301a02ee7eb8f065953821081748e08
3
+ size 4915916176
osgenesis-llama/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a597d7ef2c9d3a0e245bfc499ffdd379052fb0818ea11c08cc8f6925a3538fe
3
+ size 1168138808
osgenesis-llama/model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 266240,
4
+ "total_size": 16060522496
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.norm.weight": "model-00004-of-00004.safetensors"
298
+ }
299
+ }
osgenesis-llama/runs/Dec13_20-08-42_hgx002/events.out.tfevents.1765628701.hgx002 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a455642a4622491978865e7d235f8733d3a7976130f96031687b5093f1b0f0
3
+ size 33073
osgenesis-llama/runs/Dec13_20-08-42_hgx002/events.out.tfevents.1765636326.hgx002 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df29d5800e76b2061b868eb48957635112b1c540ae2c409b44633321f24fad72
3
+ size 311
osgenesis-llama/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
osgenesis-llama/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
osgenesis-llama/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
osgenesis-llama/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 54228985774080.0,
4
+ "train_loss": 0.2981918969472626,
5
+ "train_runtime": 7343.4841,
6
+ "train_samples_per_second": 2.756,
7
+ "train_steps_per_second": 0.172
8
+ }
osgenesis-llama/trainer_log.jsonl ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1266, "loss": 0.9273, "lr": 7.086614173228346e-07, "epoch": 0.023710729104919975, "percentage": 0.79, "elapsed_time": "0:01:09", "remaining_time": "2:24:43"}
2
+ {"current_steps": 20, "total_steps": 1266, "loss": 0.7261, "lr": 1.4960629921259845e-06, "epoch": 0.04742145820983995, "percentage": 1.58, "elapsed_time": "0:02:02", "remaining_time": "2:06:48"}
3
+ {"current_steps": 30, "total_steps": 1266, "loss": 0.5949, "lr": 2.283464566929134e-06, "epoch": 0.07113218731475993, "percentage": 2.37, "elapsed_time": "0:02:52", "remaining_time": "1:58:24"}
4
+ {"current_steps": 40, "total_steps": 1266, "loss": 0.5516, "lr": 3.0708661417322837e-06, "epoch": 0.0948429164196799, "percentage": 3.16, "elapsed_time": "0:03:41", "remaining_time": "1:53:16"}
5
+ {"current_steps": 50, "total_steps": 1266, "loss": 0.5111, "lr": 3.858267716535433e-06, "epoch": 0.11855364552459988, "percentage": 3.95, "elapsed_time": "0:04:45", "remaining_time": "1:55:42"}
6
+ {"current_steps": 60, "total_steps": 1266, "loss": 0.5245, "lr": 4.645669291338583e-06, "epoch": 0.14226437462951985, "percentage": 4.74, "elapsed_time": "0:05:33", "remaining_time": "1:51:46"}
7
+ {"current_steps": 70, "total_steps": 1266, "loss": 0.506, "lr": 5.433070866141733e-06, "epoch": 0.16597510373443983, "percentage": 5.53, "elapsed_time": "0:06:26", "remaining_time": "1:50:01"}
8
+ {"current_steps": 80, "total_steps": 1266, "loss": 0.4725, "lr": 6.220472440944882e-06, "epoch": 0.1896858328393598, "percentage": 6.32, "elapsed_time": "0:07:21", "remaining_time": "1:48:58"}
9
+ {"current_steps": 90, "total_steps": 1266, "loss": 0.5519, "lr": 7.0078740157480315e-06, "epoch": 0.21339656194427978, "percentage": 7.11, "elapsed_time": "0:08:38", "remaining_time": "1:52:51"}
10
+ {"current_steps": 100, "total_steps": 1266, "loss": 0.4936, "lr": 7.79527559055118e-06, "epoch": 0.23710729104919975, "percentage": 7.9, "elapsed_time": "0:11:19", "remaining_time": "2:11:58"}
11
+ {"current_steps": 110, "total_steps": 1266, "loss": 0.5279, "lr": 8.582677165354332e-06, "epoch": 0.26081802015411976, "percentage": 8.69, "elapsed_time": "0:12:02", "remaining_time": "2:06:28"}
12
+ {"current_steps": 120, "total_steps": 1266, "loss": 0.5046, "lr": 9.370078740157481e-06, "epoch": 0.2845287492590397, "percentage": 9.48, "elapsed_time": "0:12:44", "remaining_time": "2:01:45"}
13
+ {"current_steps": 130, "total_steps": 1266, "loss": 0.5248, "lr": 9.999923923382317e-06, "epoch": 0.3082394783639597, "percentage": 10.27, "elapsed_time": "0:13:43", "remaining_time": "1:59:52"}
14
+ {"current_steps": 140, "total_steps": 1266, "loss": 0.5139, "lr": 9.997261484836916e-06, "epoch": 0.33195020746887965, "percentage": 11.06, "elapsed_time": "0:14:33", "remaining_time": "1:57:05"}
15
+ {"current_steps": 150, "total_steps": 1266, "loss": 0.53, "lr": 9.990797530151441e-06, "epoch": 0.35566093657379966, "percentage": 11.85, "elapsed_time": "0:15:17", "remaining_time": "1:53:48"}
16
+ {"current_steps": 160, "total_steps": 1266, "loss": 0.5546, "lr": 9.980536976584711e-06, "epoch": 0.3793716656787196, "percentage": 12.64, "elapsed_time": "0:16:23", "remaining_time": "1:53:16"}
17
+ {"current_steps": 170, "total_steps": 1266, "loss": 0.5364, "lr": 9.966487629543766e-06, "epoch": 0.4030823947836396, "percentage": 13.43, "elapsed_time": "0:19:22", "remaining_time": "2:04:53"}
18
+ {"current_steps": 180, "total_steps": 1266, "loss": 0.5286, "lr": 9.948660176646152e-06, "epoch": 0.42679312388855956, "percentage": 14.22, "elapsed_time": "0:20:05", "remaining_time": "2:01:16"}
19
+ {"current_steps": 190, "total_steps": 1266, "loss": 0.5404, "lr": 9.92706817958964e-06, "epoch": 0.45050385299347956, "percentage": 15.01, "elapsed_time": "0:20:53", "remaining_time": "1:58:19"}
20
+ {"current_steps": 200, "total_steps": 1266, "loss": 0.521, "lr": 9.901728063835561e-06, "epoch": 0.4742145820983995, "percentage": 15.8, "elapsed_time": "0:22:01", "remaining_time": "1:57:21"}
21
+ {"current_steps": 210, "total_steps": 1266, "loss": 0.5371, "lr": 9.87265910611365e-06, "epoch": 0.4979253112033195, "percentage": 16.59, "elapsed_time": "0:25:40", "remaining_time": "2:09:07"}
22
+ {"current_steps": 220, "total_steps": 1266, "loss": 0.5409, "lr": 9.839883419757838e-06, "epoch": 0.5216360403082395, "percentage": 17.38, "elapsed_time": "0:26:28", "remaining_time": "2:05:53"}
23
+ {"current_steps": 230, "total_steps": 1266, "loss": 0.4904, "lr": 9.803425937884202e-06, "epoch": 0.5453467694131594, "percentage": 18.17, "elapsed_time": "0:27:21", "remaining_time": "2:03:15"}
24
+ {"current_steps": 240, "total_steps": 1266, "loss": 0.5059, "lr": 9.763314394423855e-06, "epoch": 0.5690574985180794, "percentage": 18.96, "elapsed_time": "0:28:06", "remaining_time": "2:00:08"}
25
+ {"current_steps": 250, "total_steps": 1266, "loss": 0.5044, "lr": 9.719579303025188e-06, "epoch": 0.5927682276229994, "percentage": 19.75, "elapsed_time": "0:28:51", "remaining_time": "1:57:16"}
26
+ {"current_steps": 260, "total_steps": 1266, "loss": 0.4818, "lr": 9.672253933841533e-06, "epoch": 0.6164789567279194, "percentage": 20.54, "elapsed_time": "0:29:44", "remaining_time": "1:55:04"}
27
+ {"current_steps": 270, "total_steps": 1266, "loss": 0.513, "lr": 9.621374288221896e-06, "epoch": 0.6401896858328393, "percentage": 21.33, "elapsed_time": "0:30:29", "remaining_time": "1:52:30"}
28
+ {"current_steps": 280, "total_steps": 1266, "loss": 0.5029, "lr": 9.566979071324014e-06, "epoch": 0.6639004149377593, "percentage": 22.12, "elapsed_time": "0:31:27", "remaining_time": "1:50:46"}
29
+ {"current_steps": 290, "total_steps": 1266, "loss": 0.5063, "lr": 9.509109662670573e-06, "epoch": 0.6876111440426793, "percentage": 22.91, "elapsed_time": "0:33:54", "remaining_time": "1:54:07"}
30
+ {"current_steps": 300, "total_steps": 1266, "loss": 0.4757, "lr": 9.44781008467098e-06, "epoch": 0.7113218731475993, "percentage": 23.7, "elapsed_time": "0:34:38", "remaining_time": "1:51:31"}
31
+ {"current_steps": 310, "total_steps": 1266, "loss": 0.5094, "lr": 9.38312696913265e-06, "epoch": 0.7350326022525193, "percentage": 24.49, "elapsed_time": "0:35:20", "remaining_time": "1:49:00"}
32
+ {"current_steps": 320, "total_steps": 1266, "loss": 0.4819, "lr": 9.315109521787252e-06, "epoch": 0.7587433313574392, "percentage": 25.28, "elapsed_time": "0:36:04", "remaining_time": "1:46:40"}
33
+ {"current_steps": 330, "total_steps": 1266, "loss": 0.4519, "lr": 9.243809484858936e-06, "epoch": 0.7824540604623592, "percentage": 26.07, "elapsed_time": "0:37:08", "remaining_time": "1:45:20"}
34
+ {"current_steps": 340, "total_steps": 1266, "loss": 0.4535, "lr": 9.169281097702997e-06, "epoch": 0.8061647895672792, "percentage": 26.86, "elapsed_time": "0:37:52", "remaining_time": "1:43:08"}
35
+ {"current_steps": 350, "total_steps": 1266, "loss": 0.4649, "lr": 9.091581055544913e-06, "epoch": 0.8298755186721992, "percentage": 27.65, "elapsed_time": "0:38:36", "remaining_time": "1:41:02"}
36
+ {"current_steps": 360, "total_steps": 1266, "loss": 0.4717, "lr": 9.01076846635117e-06, "epoch": 0.8535862477771191, "percentage": 28.44, "elapsed_time": "0:39:29", "remaining_time": "1:39:22"}
37
+ {"current_steps": 370, "total_steps": 1266, "loss": 0.4548, "lr": 8.926904805864642e-06, "epoch": 0.8772969768820391, "percentage": 29.23, "elapsed_time": "0:40:12", "remaining_time": "1:37:22"}
38
+ {"current_steps": 380, "total_steps": 1266, "loss": 0.4771, "lr": 8.84005387083879e-06, "epoch": 0.9010077059869591, "percentage": 30.02, "elapsed_time": "0:40:57", "remaining_time": "1:35:29"}
39
+ {"current_steps": 390, "total_steps": 1266, "loss": 0.4662, "lr": 8.750281730506186e-06, "epoch": 0.9247184350918791, "percentage": 30.81, "elapsed_time": "0:41:39", "remaining_time": "1:33:34"}
40
+ {"current_steps": 400, "total_steps": 1266, "loss": 0.4063, "lr": 8.657656676318346e-06, "epoch": 0.948429164196799, "percentage": 31.6, "elapsed_time": "0:42:27", "remaining_time": "1:31:55"}
41
+ {"current_steps": 410, "total_steps": 1266, "loss": 0.4747, "lr": 8.562249169995062e-06, "epoch": 0.972139893301719, "percentage": 32.39, "elapsed_time": "0:43:12", "remaining_time": "1:30:12"}
42
+ {"current_steps": 420, "total_steps": 1266, "loss": 0.4664, "lr": 8.464131789922773e-06, "epoch": 0.995850622406639, "percentage": 33.18, "elapsed_time": "0:43:59", "remaining_time": "1:28:36"}
43
+ {"current_steps": 430, "total_steps": 1266, "loss": 0.3373, "lr": 8.363379175942736e-06, "epoch": 1.018968583283936, "percentage": 33.97, "elapsed_time": "0:45:03", "remaining_time": "1:27:35"}
44
+ {"current_steps": 440, "total_steps": 1266, "loss": 0.2978, "lr": 8.260067972571028e-06, "epoch": 1.042679312388856, "percentage": 34.76, "elapsed_time": "0:45:49", "remaining_time": "1:26:00"}
45
+ {"current_steps": 450, "total_steps": 1266, "loss": 0.3137, "lr": 8.154276770693525e-06, "epoch": 1.066390041493776, "percentage": 35.55, "elapsed_time": "0:46:41", "remaining_time": "1:24:39"}
46
+ {"current_steps": 460, "total_steps": 1266, "loss": 0.3005, "lr": 8.046086047780269e-06, "epoch": 1.0901007705986958, "percentage": 36.33, "elapsed_time": "0:47:28", "remaining_time": "1:23:10"}
47
+ {"current_steps": 470, "total_steps": 1266, "loss": 0.2991, "lr": 7.93557810666464e-06, "epoch": 1.113811499703616, "percentage": 37.12, "elapsed_time": "0:48:10", "remaining_time": "1:21:35"}
48
+ {"current_steps": 480, "total_steps": 1266, "loss": 0.2881, "lr": 7.822837012933968e-06, "epoch": 1.1375222288085358, "percentage": 37.91, "elapsed_time": "0:48:53", "remaining_time": "1:20:04"}
49
+ {"current_steps": 490, "total_steps": 1266, "loss": 0.2979, "lr": 7.707948530979163e-06, "epoch": 1.161232957913456, "percentage": 38.7, "elapsed_time": "0:49:36", "remaining_time": "1:18:34"}
50
+ {"current_steps": 500, "total_steps": 1266, "loss": 0.2856, "lr": 7.5910000587520406e-06, "epoch": 1.1849436870183758, "percentage": 39.49, "elapsed_time": "0:50:23", "remaining_time": "1:17:12"}
51
+ {"current_steps": 500, "total_steps": 1266, "eval_loss": 0.45193034410476685, "epoch": 1.1849436870183758, "percentage": 39.49, "elapsed_time": "0:51:18", "remaining_time": "1:18:35"}
52
+ {"current_steps": 510, "total_steps": 1266, "loss": 0.2929, "lr": 7.472080561279961e-06, "epoch": 1.2086544161232957, "percentage": 40.28, "elapsed_time": "0:55:19", "remaining_time": "1:22:01"}
53
+ {"current_steps": 520, "total_steps": 1266, "loss": 0.2929, "lr": 7.351280502988366e-06, "epoch": 1.2323651452282158, "percentage": 41.07, "elapsed_time": "0:56:07", "remaining_time": "1:20:30"}
54
+ {"current_steps": 530, "total_steps": 1266, "loss": 0.3059, "lr": 7.2286917788826926e-06, "epoch": 1.2560758743331357, "percentage": 41.86, "elapsed_time": "0:56:56", "remaining_time": "1:19:04"}
55
+ {"current_steps": 540, "total_steps": 1266, "loss": 0.2907, "lr": 7.104407644642013e-06, "epoch": 1.2797866034380556, "percentage": 42.65, "elapsed_time": "0:57:41", "remaining_time": "1:17:33"}
56
+ {"current_steps": 550, "total_steps": 1266, "loss": 0.2891, "lr": 6.9785226456775925e-06, "epoch": 1.3034973325429757, "percentage": 43.44, "elapsed_time": "0:58:39", "remaining_time": "1:16:21"}
57
+ {"current_steps": 560, "total_steps": 1266, "loss": 0.2927, "lr": 6.851132545210307e-06, "epoch": 1.3272080616478956, "percentage": 44.23, "elapsed_time": "0:59:26", "remaining_time": "1:14:56"}
58
+ {"current_steps": 570, "total_steps": 1266, "loss": 0.2571, "lr": 6.722334251421665e-06, "epoch": 1.3509187907528157, "percentage": 45.02, "elapsed_time": "1:00:13", "remaining_time": "1:13:31"}
59
+ {"current_steps": 580, "total_steps": 1266, "loss": 0.2788, "lr": 6.592225743733822e-06, "epoch": 1.3746295198577356, "percentage": 45.81, "elapsed_time": "1:01:00", "remaining_time": "1:12:09"}
60
+ {"current_steps": 590, "total_steps": 1266, "loss": 0.2979, "lr": 6.460905998274691e-06, "epoch": 1.3983402489626555, "percentage": 46.6, "elapsed_time": "1:01:49", "remaining_time": "1:10:49"}
61
+ {"current_steps": 600, "total_steps": 1266, "loss": 0.2958, "lr": 6.328474912584832e-06, "epoch": 1.4220509780675756, "percentage": 47.39, "elapsed_time": "1:02:37", "remaining_time": "1:09:30"}
62
+ {"current_steps": 610, "total_steps": 1266, "loss": 0.2647, "lr": 6.19503322962341e-06, "epoch": 1.4457617071724955, "percentage": 48.18, "elapsed_time": "1:03:26", "remaining_time": "1:08:13"}
63
+ {"current_steps": 620, "total_steps": 1266, "loss": 0.2924, "lr": 6.0606824611310174e-06, "epoch": 1.4694724362774156, "percentage": 48.97, "elapsed_time": "1:04:19", "remaining_time": "1:07:01"}
64
+ {"current_steps": 630, "total_steps": 1266, "loss": 0.2847, "lr": 5.9255248104076865e-06, "epoch": 1.4931831653823355, "percentage": 49.76, "elapsed_time": "1:05:11", "remaining_time": "1:05:49"}
65
+ {"current_steps": 640, "total_steps": 1266, "loss": 0.2836, "lr": 5.789663094564794e-06, "epoch": 1.5168938944872554, "percentage": 50.55, "elapsed_time": "1:05:58", "remaining_time": "1:04:32"}
66
+ {"current_steps": 650, "total_steps": 1266, "loss": 0.2644, "lr": 5.653200666310051e-06, "epoch": 1.5406046235921753, "percentage": 51.34, "elapsed_time": "1:06:41", "remaining_time": "1:03:12"}
67
+ {"current_steps": 660, "total_steps": 1266, "loss": 0.302, "lr": 5.516241335325037e-06, "epoch": 1.5643153526970954, "percentage": 52.13, "elapsed_time": "1:07:38", "remaining_time": "1:02:06"}
68
+ {"current_steps": 670, "total_steps": 1266, "loss": 0.2752, "lr": 5.378889289295124e-06, "epoch": 1.5880260818020155, "percentage": 52.92, "elapsed_time": "1:08:34", "remaining_time": "1:01:00"}
69
+ {"current_steps": 680, "total_steps": 1266, "loss": 0.2581, "lr": 5.241249014651812e-06, "epoch": 1.6117368109069354, "percentage": 53.71, "elapsed_time": "1:09:29", "remaining_time": "0:59:53"}
70
+ {"current_steps": 690, "total_steps": 1266, "loss": 0.2717, "lr": 5.103425217087846e-06, "epoch": 1.6354475400118553, "percentage": 54.5, "elapsed_time": "1:10:13", "remaining_time": "0:58:37"}
71
+ {"current_steps": 700, "total_steps": 1266, "loss": 0.2742, "lr": 4.965522741905501e-06, "epoch": 1.6591582691167752, "percentage": 55.29, "elapsed_time": "1:11:00", "remaining_time": "0:57:24"}
72
+ {"current_steps": 710, "total_steps": 1266, "loss": 0.2735, "lr": 4.827646494258677e-06, "epoch": 1.6828689982216953, "percentage": 56.08, "elapsed_time": "1:11:49", "remaining_time": "0:56:15"}
73
+ {"current_steps": 720, "total_steps": 1266, "loss": 0.256, "lr": 4.6899013593494715e-06, "epoch": 1.7065797273266154, "percentage": 56.87, "elapsed_time": "1:12:40", "remaining_time": "0:55:06"}
74
+ {"current_steps": 730, "total_steps": 1266, "loss": 0.2754, "lr": 4.552392122639916e-06, "epoch": 1.7302904564315353, "percentage": 57.66, "elapsed_time": "1:13:26", "remaining_time": "0:53:55"}
75
+ {"current_steps": 740, "total_steps": 1266, "loss": 0.2759, "lr": 4.415223390139588e-06, "epoch": 1.7540011855364552, "percentage": 58.45, "elapsed_time": "1:14:12", "remaining_time": "0:52:44"}
76
+ {"current_steps": 750, "total_steps": 1266, "loss": 0.2631, "lr": 4.278499508829751e-06, "epoch": 1.7777119146413751, "percentage": 59.24, "elapsed_time": "1:15:06", "remaining_time": "0:51:40"}
77
+ {"current_steps": 760, "total_steps": 1266, "loss": 0.2621, "lr": 4.142324487284522e-06, "epoch": 1.8014226437462952, "percentage": 60.03, "elapsed_time": "1:15:58", "remaining_time": "0:50:34"}
78
+ {"current_steps": 770, "total_steps": 1266, "loss": 0.2494, "lr": 4.0068019165494864e-06, "epoch": 1.8251333728512151, "percentage": 60.82, "elapsed_time": "1:16:40", "remaining_time": "0:49:23"}
79
+ {"current_steps": 780, "total_steps": 1266, "loss": 0.2646, "lr": 3.872034891337929e-06, "epoch": 1.8488441019561352, "percentage": 61.61, "elapsed_time": "1:17:30", "remaining_time": "0:48:17"}
80
+ {"current_steps": 790, "total_steps": 1266, "loss": 0.2546, "lr": 3.7381259316046405e-06, "epoch": 1.8725548310610551, "percentage": 62.4, "elapsed_time": "1:18:25", "remaining_time": "0:47:15"}
81
+ {"current_steps": 800, "total_steps": 1266, "loss": 0.2584, "lr": 3.605176904556942e-06, "epoch": 1.896265560165975, "percentage": 63.19, "elapsed_time": "1:19:37", "remaining_time": "0:46:23"}
82
+ {"current_steps": 810, "total_steps": 1266, "loss": 0.2782, "lr": 3.4732889471622823e-06, "epoch": 1.919976289270895, "percentage": 63.98, "elapsed_time": "1:20:20", "remaining_time": "0:45:13"}
83
+ {"current_steps": 820, "total_steps": 1266, "loss": 0.2465, "lr": 3.34256238921134e-06, "epoch": 1.943687018375815, "percentage": 64.77, "elapsed_time": "1:21:05", "remaining_time": "0:44:06"}
84
+ {"current_steps": 830, "total_steps": 1266, "loss": 0.2321, "lr": 3.213096676995141e-06, "epoch": 1.9673977474807351, "percentage": 65.56, "elapsed_time": "1:21:53", "remaining_time": "0:43:01"}
85
+ {"current_steps": 840, "total_steps": 1266, "loss": 0.2383, "lr": 3.0849902976543113e-06, "epoch": 1.991108476585655, "percentage": 66.35, "elapsed_time": "1:22:44", "remaining_time": "0:41:57"}
86
+ {"current_steps": 850, "total_steps": 1266, "loss": 0.1732, "lr": 2.9583407042579325e-06, "epoch": 2.014226437462952, "percentage": 67.14, "elapsed_time": "1:23:33", "remaining_time": "0:40:53"}
87
+ {"current_steps": 860, "total_steps": 1266, "loss": 0.1078, "lr": 2.8332442416690625e-06, "epoch": 2.037937166567872, "percentage": 67.93, "elapsed_time": "1:24:18", "remaining_time": "0:39:48"}
88
+ {"current_steps": 870, "total_steps": 1266, "loss": 0.1107, "lr": 2.709796073253287e-06, "epoch": 2.0616478956727917, "percentage": 68.72, "elapsed_time": "1:25:15", "remaining_time": "0:38:48"}
89
+ {"current_steps": 880, "total_steps": 1266, "loss": 0.1185, "lr": 2.5880901084860503e-06, "epoch": 2.085358624777712, "percentage": 69.51, "elapsed_time": "1:26:04", "remaining_time": "0:37:45"}
90
+ {"current_steps": 890, "total_steps": 1266, "loss": 0.1063, "lr": 2.4682189315138484e-06, "epoch": 2.109069353882632, "percentage": 70.3, "elapsed_time": "1:27:01", "remaining_time": "0:36:45"}
91
+ {"current_steps": 900, "total_steps": 1266, "loss": 0.1154, "lr": 2.3502737307236355e-06, "epoch": 2.132780082987552, "percentage": 71.09, "elapsed_time": "1:27:44", "remaining_time": "0:35:40"}
92
+ {"current_steps": 910, "total_steps": 1266, "loss": 0.1053, "lr": 2.234344229374003e-06, "epoch": 2.1564908120924717, "percentage": 71.88, "elapsed_time": "1:28:33", "remaining_time": "0:34:38"}
93
+ {"current_steps": 920, "total_steps": 1266, "loss": 0.1063, "lr": 2.1205186173409116e-06, "epoch": 2.1802015411973916, "percentage": 72.67, "elapsed_time": "1:29:19", "remaining_time": "0:33:35"}
94
+ {"current_steps": 930, "total_steps": 1266, "loss": 0.1146, "lr": 2.008883484029902e-06, "epoch": 2.203912270302312, "percentage": 73.46, "elapsed_time": "1:30:03", "remaining_time": "0:32:32"}
95
+ {"current_steps": 940, "total_steps": 1266, "loss": 0.0987, "lr": 1.8995237525058057e-06, "epoch": 2.227622999407232, "percentage": 74.25, "elapsed_time": "1:30:49", "remaining_time": "0:31:29"}
96
+ {"current_steps": 950, "total_steps": 1266, "loss": 0.1049, "lr": 1.792522614890097e-06, "epoch": 2.2513337285121517, "percentage": 75.04, "elapsed_time": "1:31:42", "remaining_time": "0:30:30"}
97
+ {"current_steps": 960, "total_steps": 1266, "loss": 0.1091, "lr": 1.6879614690749796e-06, "epoch": 2.2750444576170716, "percentage": 75.83, "elapsed_time": "1:32:38", "remaining_time": "0:29:31"}
98
+ {"current_steps": 970, "total_steps": 1266, "loss": 0.0985, "lr": 1.5859198568023905e-06, "epoch": 2.2987551867219915, "percentage": 76.62, "elapsed_time": "1:33:38", "remaining_time": "0:28:34"}
99
+ {"current_steps": 980, "total_steps": 1266, "loss": 0.097, "lr": 1.486475403155027e-06, "epoch": 2.322465915826912, "percentage": 77.41, "elapsed_time": "1:34:28", "remaining_time": "0:27:34"}
100
+ {"current_steps": 990, "total_steps": 1266, "loss": 0.0979, "lr": 1.3897037575053968e-06, "epoch": 2.3461766449318318, "percentage": 78.2, "elapsed_time": "1:35:22", "remaining_time": "0:26:35"}
101
+ {"current_steps": 1000, "total_steps": 1266, "loss": 0.1072, "lr": 1.2956785359678365e-06, "epoch": 2.3698873740367516, "percentage": 78.99, "elapsed_time": "1:36:18", "remaining_time": "0:25:36"}
102
+ {"current_steps": 1000, "total_steps": 1266, "eval_loss": 0.4591856598854065, "epoch": 2.3698873740367516, "percentage": 78.99, "elapsed_time": "1:37:17", "remaining_time": "0:25:52"}
103
+ {"current_steps": 1010, "total_steps": 1266, "loss": 0.0939, "lr": 1.2044712653972713e-06, "epoch": 2.3935981031416715, "percentage": 79.78, "elapsed_time": "1:40:29", "remaining_time": "0:25:28"}
104
+ {"current_steps": 1020, "total_steps": 1266, "loss": 0.0977, "lr": 1.1161513289773145e-06, "epoch": 2.4173088322465914, "percentage": 80.57, "elapsed_time": "1:41:28", "remaining_time": "0:24:28"}
105
+ {"current_steps": 1030, "total_steps": 1266, "loss": 0.1014, "lr": 1.0307859134390985e-06, "epoch": 2.4410195613515118, "percentage": 81.36, "elapsed_time": "1:42:16", "remaining_time": "0:23:26"}
106
+ {"current_steps": 1040, "total_steps": 1266, "loss": 0.1004, "lr": 9.484399579509996e-07, "epoch": 2.4647302904564317, "percentage": 82.15, "elapsed_time": "1:43:06", "remaining_time": "0:22:24"}
107
+ {"current_steps": 1050, "total_steps": 1266, "loss": 0.1109, "lr": 8.691761047181157e-07, "epoch": 2.4884410195613516, "percentage": 82.94, "elapsed_time": "1:43:49", "remaining_time": "0:21:21"}
108
+ {"current_steps": 1060, "total_steps": 1266, "loss": 0.0912, "lr": 7.930546513290938e-07, "epoch": 2.5121517486662714, "percentage": 83.73, "elapsed_time": "1:44:43", "remaining_time": "0:20:21"}
109
+ {"current_steps": 1070, "total_steps": 1266, "loss": 0.1008, "lr": 7.201335048865627e-07, "epoch": 2.5358624777711913, "percentage": 84.52, "elapsed_time": "1:45:31", "remaining_time": "0:19:19"}
110
+ {"current_steps": 1080, "total_steps": 1266, "loss": 0.0888, "lr": 6.50468137956049e-07, "epoch": 2.5595732068761112, "percentage": 85.31, "elapsed_time": "1:46:16", "remaining_time": "0:18:18"}
111
+ {"current_steps": 1090, "total_steps": 1266, "loss": 0.0939, "lr": 5.841115463668834e-07, "epoch": 2.5832839359810316, "percentage": 86.1, "elapsed_time": "1:47:01", "remaining_time": "0:17:16"}
112
+ {"current_steps": 1100, "total_steps": 1266, "loss": 0.1018, "lr": 5.211142088972326e-07, "epoch": 2.6069946650859515, "percentage": 86.89, "elapsed_time": "1:47:51", "remaining_time": "0:16:16"}
113
+ {"current_steps": 1110, "total_steps": 1266, "loss": 0.0973, "lr": 4.6152404887388255e-07, "epoch": 2.6307053941908713, "percentage": 87.68, "elapsed_time": "1:48:42", "remaining_time": "0:15:16"}
114
+ {"current_steps": 1120, "total_steps": 1266, "loss": 0.0905, "lr": 4.0538639771601216e-07, "epoch": 2.6544161232957912, "percentage": 88.47, "elapsed_time": "1:49:30", "remaining_time": "0:14:16"}
115
+ {"current_steps": 1130, "total_steps": 1266, "loss": 0.096, "lr": 3.5274396045068324e-07, "epoch": 2.6781268524007116, "percentage": 89.26, "elapsed_time": "1:50:16", "remaining_time": "0:13:16"}
116
+ {"current_steps": 1140, "total_steps": 1266, "loss": 0.0886, "lr": 3.0363678322627597e-07, "epoch": 2.7018375815056315, "percentage": 90.05, "elapsed_time": "1:51:02", "remaining_time": "0:12:16"}
117
+ {"current_steps": 1150, "total_steps": 1266, "loss": 0.0875, "lr": 2.5810222284858797e-07, "epoch": 2.7255483106105514, "percentage": 90.84, "elapsed_time": "1:51:45", "remaining_time": "0:11:16"}
118
+ {"current_steps": 1160, "total_steps": 1266, "loss": 0.0934, "lr": 2.1617491836276982e-07, "epoch": 2.7492590397154713, "percentage": 91.63, "elapsed_time": "1:52:27", "remaining_time": "0:10:16"}
119
+ {"current_steps": 1170, "total_steps": 1266, "loss": 0.1074, "lr": 1.778867647027188e-07, "epoch": 2.772969768820391, "percentage": 92.42, "elapsed_time": "1:53:10", "remaining_time": "0:09:17"}
120
+ {"current_steps": 1180, "total_steps": 1266, "loss": 0.0966, "lr": 1.4326688842795977e-07, "epoch": 2.796680497925311, "percentage": 93.21, "elapsed_time": "1:53:56", "remaining_time": "0:08:18"}
121
+ {"current_steps": 1190, "total_steps": 1266, "loss": 0.0929, "lr": 1.1234162556650163e-07, "epoch": 2.820391227030231, "percentage": 94.0, "elapsed_time": "1:54:49", "remaining_time": "0:07:19"}
122
+ {"current_steps": 1200, "total_steps": 1266, "loss": 0.0949, "lr": 8.513450158049109e-08, "epoch": 2.8441019561351513, "percentage": 94.79, "elapsed_time": "1:55:35", "remaining_time": "0:06:21"}
123
+ {"current_steps": 1210, "total_steps": 1266, "loss": 0.0908, "lr": 6.166621346993029e-08, "epoch": 2.867812685240071, "percentage": 95.58, "elapsed_time": "1:56:24", "remaining_time": "0:05:23"}
124
+ {"current_steps": 1220, "total_steps": 1266, "loss": 0.0935, "lr": 4.1954614028054674e-08, "epoch": 2.891523414344991, "percentage": 96.37, "elapsed_time": "1:57:19", "remaining_time": "0:04:25"}
125
+ {"current_steps": 1230, "total_steps": 1266, "loss": 0.0871, "lr": 2.6014698260358183e-08, "epoch": 2.915234143449911, "percentage": 97.16, "elapsed_time": "1:58:04", "remaining_time": "0:03:27"}
126
+ {"current_steps": 1240, "total_steps": 1266, "loss": 0.0875, "lr": 1.385859197759687e-08, "epoch": 2.9389448725548313, "percentage": 97.95, "elapsed_time": "1:58:50", "remaining_time": "0:02:29"}
127
+ {"current_steps": 1250, "total_steps": 1266, "loss": 0.0903, "lr": 5.495542571443135e-09, "epoch": 2.962655601659751, "percentage": 98.74, "elapsed_time": "1:59:37", "remaining_time": "0:01:31"}
128
+ {"current_steps": 1260, "total_steps": 1266, "loss": 0.0812, "lr": 9.31911979807909e-10, "epoch": 2.986366330764671, "percentage": 99.53, "elapsed_time": "2:00:21", "remaining_time": "0:00:34"}
129
+ {"current_steps": 1266, "total_steps": 1266, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:02:23", "remaining_time": "0:00:00"}
osgenesis-llama/trainer_state.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1266,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.023710729104919975,
14
+ "grad_norm": 21.654089677762492,
15
+ "learning_rate": 7.086614173228346e-07,
16
+ "loss": 0.9273,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.04742145820983995,
21
+ "grad_norm": 13.158033432354436,
22
+ "learning_rate": 1.4960629921259845e-06,
23
+ "loss": 0.7261,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.07113218731475993,
28
+ "grad_norm": 8.905781707547229,
29
+ "learning_rate": 2.283464566929134e-06,
30
+ "loss": 0.5949,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0948429164196799,
35
+ "grad_norm": 7.255255210581632,
36
+ "learning_rate": 3.0708661417322837e-06,
37
+ "loss": 0.5516,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.11855364552459988,
42
+ "grad_norm": 6.974161059541655,
43
+ "learning_rate": 3.858267716535433e-06,
44
+ "loss": 0.5111,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.14226437462951985,
49
+ "grad_norm": 5.651318484615861,
50
+ "learning_rate": 4.645669291338583e-06,
51
+ "loss": 0.5245,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.16597510373443983,
56
+ "grad_norm": 6.036940205072249,
57
+ "learning_rate": 5.433070866141733e-06,
58
+ "loss": 0.506,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.1896858328393598,
63
+ "grad_norm": 5.1755975857717536,
64
+ "learning_rate": 6.220472440944882e-06,
65
+ "loss": 0.4725,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.21339656194427978,
70
+ "grad_norm": 6.635004608042446,
71
+ "learning_rate": 7.0078740157480315e-06,
72
+ "loss": 0.5519,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.23710729104919975,
77
+ "grad_norm": 6.068189315595479,
78
+ "learning_rate": 7.79527559055118e-06,
79
+ "loss": 0.4936,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.26081802015411976,
84
+ "grad_norm": 5.090926729964026,
85
+ "learning_rate": 8.582677165354332e-06,
86
+ "loss": 0.5279,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.2845287492590397,
91
+ "grad_norm": 5.197075333191967,
92
+ "learning_rate": 9.370078740157481e-06,
93
+ "loss": 0.5046,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.3082394783639597,
98
+ "grad_norm": 4.854665516020856,
99
+ "learning_rate": 9.999923923382317e-06,
100
+ "loss": 0.5248,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.33195020746887965,
105
+ "grad_norm": 5.158338502799311,
106
+ "learning_rate": 9.997261484836916e-06,
107
+ "loss": 0.5139,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.35566093657379966,
112
+ "grad_norm": 4.94416310954264,
113
+ "learning_rate": 9.990797530151441e-06,
114
+ "loss": 0.53,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.3793716656787196,
119
+ "grad_norm": 5.336809452970413,
120
+ "learning_rate": 9.980536976584711e-06,
121
+ "loss": 0.5546,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.4030823947836396,
126
+ "grad_norm": 4.950482275472653,
127
+ "learning_rate": 9.966487629543766e-06,
128
+ "loss": 0.5364,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.42679312388855956,
133
+ "grad_norm": 4.323856432808166,
134
+ "learning_rate": 9.948660176646152e-06,
135
+ "loss": 0.5286,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.45050385299347956,
140
+ "grad_norm": 4.224858492109143,
141
+ "learning_rate": 9.92706817958964e-06,
142
+ "loss": 0.5404,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.4742145820983995,
147
+ "grad_norm": 7.159206766003931,
148
+ "learning_rate": 9.901728063835561e-06,
149
+ "loss": 0.521,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.4979253112033195,
154
+ "grad_norm": 4.79820944593641,
155
+ "learning_rate": 9.87265910611365e-06,
156
+ "loss": 0.5371,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.5216360403082395,
161
+ "grad_norm": 4.352275642498719,
162
+ "learning_rate": 9.839883419757838e-06,
163
+ "loss": 0.5409,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.5453467694131594,
168
+ "grad_norm": 3.0512515615824087,
169
+ "learning_rate": 9.803425937884202e-06,
170
+ "loss": 0.4904,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.5690574985180794,
175
+ "grad_norm": 3.6070996957510335,
176
+ "learning_rate": 9.763314394423855e-06,
177
+ "loss": 0.5059,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5927682276229994,
182
+ "grad_norm": 3.667369038644614,
183
+ "learning_rate": 9.719579303025188e-06,
184
+ "loss": 0.5044,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.6164789567279194,
189
+ "grad_norm": 3.762840357591941,
190
+ "learning_rate": 9.672253933841533e-06,
191
+ "loss": 0.4818,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.6401896858328393,
196
+ "grad_norm": 4.190173408376692,
197
+ "learning_rate": 9.621374288221896e-06,
198
+ "loss": 0.513,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.6639004149377593,
203
+ "grad_norm": 3.628061060797804,
204
+ "learning_rate": 9.566979071324014e-06,
205
+ "loss": 0.5029,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.6876111440426793,
210
+ "grad_norm": 3.3521609497091087,
211
+ "learning_rate": 9.509109662670573e-06,
212
+ "loss": 0.5063,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.7113218731475993,
217
+ "grad_norm": 3.5138596120651413,
218
+ "learning_rate": 9.44781008467098e-06,
219
+ "loss": 0.4757,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.7350326022525193,
224
+ "grad_norm": 3.537105322871914,
225
+ "learning_rate": 9.38312696913265e-06,
226
+ "loss": 0.5094,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.7587433313574392,
231
+ "grad_norm": 3.507194476519431,
232
+ "learning_rate": 9.315109521787252e-06,
233
+ "loss": 0.4819,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.7824540604623592,
238
+ "grad_norm": 3.5387079596783955,
239
+ "learning_rate": 9.243809484858936e-06,
240
+ "loss": 0.4519,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.8061647895672792,
245
+ "grad_norm": 3.4682051852004547,
246
+ "learning_rate": 9.169281097702997e-06,
247
+ "loss": 0.4535,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.8298755186721992,
252
+ "grad_norm": 3.2582589966291047,
253
+ "learning_rate": 9.091581055544913e-06,
254
+ "loss": 0.4649,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.8535862477771191,
259
+ "grad_norm": 3.7605884819584032,
260
+ "learning_rate": 9.01076846635117e-06,
261
+ "loss": 0.4717,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.8772969768820391,
266
+ "grad_norm": 3.0701941745829577,
267
+ "learning_rate": 8.926904805864642e-06,
268
+ "loss": 0.4548,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.9010077059869591,
273
+ "grad_norm": 3.9484221413414207,
274
+ "learning_rate": 8.84005387083879e-06,
275
+ "loss": 0.4771,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.9247184350918791,
280
+ "grad_norm": 3.628849408692728,
281
+ "learning_rate": 8.750281730506186e-06,
282
+ "loss": 0.4662,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.948429164196799,
287
+ "grad_norm": 2.714678598006085,
288
+ "learning_rate": 8.657656676318346e-06,
289
+ "loss": 0.4063,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.972139893301719,
294
+ "grad_norm": 2.862273936518975,
295
+ "learning_rate": 8.562249169995062e-06,
296
+ "loss": 0.4747,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.995850622406639,
301
+ "grad_norm": 4.015082243219481,
302
+ "learning_rate": 8.464131789922773e-06,
303
+ "loss": 0.4664,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.018968583283936,
308
+ "grad_norm": 3.317988973859346,
309
+ "learning_rate": 8.363379175942736e-06,
310
+ "loss": 0.3373,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.042679312388856,
315
+ "grad_norm": 2.66737361543537,
316
+ "learning_rate": 8.260067972571028e-06,
317
+ "loss": 0.2978,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.066390041493776,
322
+ "grad_norm": 3.690753100061689,
323
+ "learning_rate": 8.154276770693525e-06,
324
+ "loss": 0.3137,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.0901007705986958,
329
+ "grad_norm": 2.7421307138902224,
330
+ "learning_rate": 8.046086047780269e-06,
331
+ "loss": 0.3005,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.113811499703616,
336
+ "grad_norm": 3.2441433406106253,
337
+ "learning_rate": 7.93557810666464e-06,
338
+ "loss": 0.2991,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.1375222288085358,
343
+ "grad_norm": 2.8171872482828815,
344
+ "learning_rate": 7.822837012933968e-06,
345
+ "loss": 0.2881,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.161232957913456,
350
+ "grad_norm": 2.8540163878356157,
351
+ "learning_rate": 7.707948530979163e-06,
352
+ "loss": 0.2979,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.1849436870183758,
357
+ "grad_norm": 3.1607436486481273,
358
+ "learning_rate": 7.5910000587520406e-06,
359
+ "loss": 0.2856,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.1849436870183758,
364
+ "eval_loss": 0.45193034410476685,
365
+ "eval_runtime": 54.069,
366
+ "eval_samples_per_second": 13.871,
367
+ "eval_steps_per_second": 3.477,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 1.2086544161232957,
372
+ "grad_norm": 3.2944246675174638,
373
+ "learning_rate": 7.472080561279961e-06,
374
+ "loss": 0.2929,
375
+ "step": 510
376
+ },
377
+ {
378
+ "epoch": 1.2323651452282158,
379
+ "grad_norm": 3.2281641735051014,
380
+ "learning_rate": 7.351280502988366e-06,
381
+ "loss": 0.2929,
382
+ "step": 520
383
+ },
384
+ {
385
+ "epoch": 1.2560758743331357,
386
+ "grad_norm": 2.8015683673163188,
387
+ "learning_rate": 7.2286917788826926e-06,
388
+ "loss": 0.3059,
389
+ "step": 530
390
+ },
391
+ {
392
+ "epoch": 1.2797866034380556,
393
+ "grad_norm": 3.050554341146833,
394
+ "learning_rate": 7.104407644642013e-06,
395
+ "loss": 0.2907,
396
+ "step": 540
397
+ },
398
+ {
399
+ "epoch": 1.3034973325429757,
400
+ "grad_norm": 2.889252453256635,
401
+ "learning_rate": 6.9785226456775925e-06,
402
+ "loss": 0.2891,
403
+ "step": 550
404
+ },
405
+ {
406
+ "epoch": 1.3272080616478956,
407
+ "grad_norm": 3.4640513175096896,
408
+ "learning_rate": 6.851132545210307e-06,
409
+ "loss": 0.2927,
410
+ "step": 560
411
+ },
412
+ {
413
+ "epoch": 1.3509187907528157,
414
+ "grad_norm": 2.352220161848988,
415
+ "learning_rate": 6.722334251421665e-06,
416
+ "loss": 0.2571,
417
+ "step": 570
418
+ },
419
+ {
420
+ "epoch": 1.3746295198577356,
421
+ "grad_norm": 2.008789556558702,
422
+ "learning_rate": 6.592225743733822e-06,
423
+ "loss": 0.2788,
424
+ "step": 580
425
+ },
426
+ {
427
+ "epoch": 1.3983402489626555,
428
+ "grad_norm": 3.2987011681047713,
429
+ "learning_rate": 6.460905998274691e-06,
430
+ "loss": 0.2979,
431
+ "step": 590
432
+ },
433
+ {
434
+ "epoch": 1.4220509780675756,
435
+ "grad_norm": 3.0841078417866568,
436
+ "learning_rate": 6.328474912584832e-06,
437
+ "loss": 0.2958,
438
+ "step": 600
439
+ },
440
+ {
441
+ "epoch": 1.4457617071724955,
442
+ "grad_norm": 2.9393120005152085,
443
+ "learning_rate": 6.19503322962341e-06,
444
+ "loss": 0.2647,
445
+ "step": 610
446
+ },
447
+ {
448
+ "epoch": 1.4694724362774156,
449
+ "grad_norm": 3.06407353610059,
450
+ "learning_rate": 6.0606824611310174e-06,
451
+ "loss": 0.2924,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 1.4931831653823355,
456
+ "grad_norm": 3.1813717056825213,
457
+ "learning_rate": 5.9255248104076865e-06,
458
+ "loss": 0.2847,
459
+ "step": 630
460
+ },
461
+ {
462
+ "epoch": 1.5168938944872554,
463
+ "grad_norm": 2.9941766880200618,
464
+ "learning_rate": 5.789663094564794e-06,
465
+ "loss": 0.2836,
466
+ "step": 640
467
+ },
468
+ {
469
+ "epoch": 1.5406046235921753,
470
+ "grad_norm": 2.87492102628301,
471
+ "learning_rate": 5.653200666310051e-06,
472
+ "loss": 0.2644,
473
+ "step": 650
474
+ },
475
+ {
476
+ "epoch": 1.5643153526970954,
477
+ "grad_norm": 2.563208387150386,
478
+ "learning_rate": 5.516241335325037e-06,
479
+ "loss": 0.302,
480
+ "step": 660
481
+ },
482
+ {
483
+ "epoch": 1.5880260818020155,
484
+ "grad_norm": 2.6849456075837206,
485
+ "learning_rate": 5.378889289295124e-06,
486
+ "loss": 0.2752,
487
+ "step": 670
488
+ },
489
+ {
490
+ "epoch": 1.6117368109069354,
491
+ "grad_norm": 2.8735707675131086,
492
+ "learning_rate": 5.241249014651812e-06,
493
+ "loss": 0.2581,
494
+ "step": 680
495
+ },
496
+ {
497
+ "epoch": 1.6354475400118553,
498
+ "grad_norm": 3.169189354995883,
499
+ "learning_rate": 5.103425217087846e-06,
500
+ "loss": 0.2717,
501
+ "step": 690
502
+ },
503
+ {
504
+ "epoch": 1.6591582691167752,
505
+ "grad_norm": 2.5953135830604217,
506
+ "learning_rate": 4.965522741905501e-06,
507
+ "loss": 0.2742,
508
+ "step": 700
509
+ },
510
+ {
511
+ "epoch": 1.6828689982216953,
512
+ "grad_norm": 2.9232012317165017,
513
+ "learning_rate": 4.827646494258677e-06,
514
+ "loss": 0.2735,
515
+ "step": 710
516
+ },
517
+ {
518
+ "epoch": 1.7065797273266154,
519
+ "grad_norm": 2.828576846386985,
520
+ "learning_rate": 4.6899013593494715e-06,
521
+ "loss": 0.256,
522
+ "step": 720
523
+ },
524
+ {
525
+ "epoch": 1.7302904564315353,
526
+ "grad_norm": 3.3593501771831407,
527
+ "learning_rate": 4.552392122639916e-06,
528
+ "loss": 0.2754,
529
+ "step": 730
530
+ },
531
+ {
532
+ "epoch": 1.7540011855364552,
533
+ "grad_norm": 2.684913788264115,
534
+ "learning_rate": 4.415223390139588e-06,
535
+ "loss": 0.2759,
536
+ "step": 740
537
+ },
538
+ {
539
+ "epoch": 1.7777119146413751,
540
+ "grad_norm": 3.6459408772256165,
541
+ "learning_rate": 4.278499508829751e-06,
542
+ "loss": 0.2631,
543
+ "step": 750
544
+ },
545
+ {
546
+ "epoch": 1.8014226437462952,
547
+ "grad_norm": 2.671017851213479,
548
+ "learning_rate": 4.142324487284522e-06,
549
+ "loss": 0.2621,
550
+ "step": 760
551
+ },
552
+ {
553
+ "epoch": 1.8251333728512151,
554
+ "grad_norm": 2.577763149729153,
555
+ "learning_rate": 4.0068019165494864e-06,
556
+ "loss": 0.2494,
557
+ "step": 770
558
+ },
559
+ {
560
+ "epoch": 1.8488441019561352,
561
+ "grad_norm": 2.7287163760970583,
562
+ "learning_rate": 3.872034891337929e-06,
563
+ "loss": 0.2646,
564
+ "step": 780
565
+ },
566
+ {
567
+ "epoch": 1.8725548310610551,
568
+ "grad_norm": 2.8636768931725376,
569
+ "learning_rate": 3.7381259316046405e-06,
570
+ "loss": 0.2546,
571
+ "step": 790
572
+ },
573
+ {
574
+ "epoch": 1.896265560165975,
575
+ "grad_norm": 3.0063769394151185,
576
+ "learning_rate": 3.605176904556942e-06,
577
+ "loss": 0.2584,
578
+ "step": 800
579
+ },
580
+ {
581
+ "epoch": 1.919976289270895,
582
+ "grad_norm": 3.3593335158013673,
583
+ "learning_rate": 3.4732889471622823e-06,
584
+ "loss": 0.2782,
585
+ "step": 810
586
+ },
587
+ {
588
+ "epoch": 1.943687018375815,
589
+ "grad_norm": 2.6023304988840037,
590
+ "learning_rate": 3.34256238921134e-06,
591
+ "loss": 0.2465,
592
+ "step": 820
593
+ },
594
+ {
595
+ "epoch": 1.9673977474807351,
596
+ "grad_norm": 3.0126201772670163,
597
+ "learning_rate": 3.213096676995141e-06,
598
+ "loss": 0.2321,
599
+ "step": 830
600
+ },
601
+ {
602
+ "epoch": 1.991108476585655,
603
+ "grad_norm": 2.6721326812012376,
604
+ "learning_rate": 3.0849902976543113e-06,
605
+ "loss": 0.2383,
606
+ "step": 840
607
+ },
608
+ {
609
+ "epoch": 2.014226437462952,
610
+ "grad_norm": 2.4611929134690986,
611
+ "learning_rate": 2.9583407042579325e-06,
612
+ "loss": 0.1732,
613
+ "step": 850
614
+ },
615
+ {
616
+ "epoch": 2.037937166567872,
617
+ "grad_norm": 1.7002991178217162,
618
+ "learning_rate": 2.8332442416690625e-06,
619
+ "loss": 0.1078,
620
+ "step": 860
621
+ },
622
+ {
623
+ "epoch": 2.0616478956727917,
624
+ "grad_norm": 2.457631852767717,
625
+ "learning_rate": 2.709796073253287e-06,
626
+ "loss": 0.1107,
627
+ "step": 870
628
+ },
629
+ {
630
+ "epoch": 2.085358624777712,
631
+ "grad_norm": 2.7991208883334835,
632
+ "learning_rate": 2.5880901084860503e-06,
633
+ "loss": 0.1185,
634
+ "step": 880
635
+ },
636
+ {
637
+ "epoch": 2.109069353882632,
638
+ "grad_norm": 2.1684746909568013,
639
+ "learning_rate": 2.4682189315138484e-06,
640
+ "loss": 0.1063,
641
+ "step": 890
642
+ },
643
+ {
644
+ "epoch": 2.132780082987552,
645
+ "grad_norm": 3.1226476997482293,
646
+ "learning_rate": 2.3502737307236355e-06,
647
+ "loss": 0.1154,
648
+ "step": 900
649
+ },
650
+ {
651
+ "epoch": 2.1564908120924717,
652
+ "grad_norm": 2.6013913944894833,
653
+ "learning_rate": 2.234344229374003e-06,
654
+ "loss": 0.1053,
655
+ "step": 910
656
+ },
657
+ {
658
+ "epoch": 2.1802015411973916,
659
+ "grad_norm": 2.3783236155096796,
660
+ "learning_rate": 2.1205186173409116e-06,
661
+ "loss": 0.1063,
662
+ "step": 920
663
+ },
664
+ {
665
+ "epoch": 2.203912270302312,
666
+ "grad_norm": 2.769713580668751,
667
+ "learning_rate": 2.008883484029902e-06,
668
+ "loss": 0.1146,
669
+ "step": 930
670
+ },
671
+ {
672
+ "epoch": 2.227622999407232,
673
+ "grad_norm": 2.5071916943558556,
674
+ "learning_rate": 1.8995237525058057e-06,
675
+ "loss": 0.0987,
676
+ "step": 940
677
+ },
678
+ {
679
+ "epoch": 2.2513337285121517,
680
+ "grad_norm": 2.8557405943035468,
681
+ "learning_rate": 1.792522614890097e-06,
682
+ "loss": 0.1049,
683
+ "step": 950
684
+ },
685
+ {
686
+ "epoch": 2.2750444576170716,
687
+ "grad_norm": 2.4734946546511387,
688
+ "learning_rate": 1.6879614690749796e-06,
689
+ "loss": 0.1091,
690
+ "step": 960
691
+ },
692
+ {
693
+ "epoch": 2.2987551867219915,
694
+ "grad_norm": 1.9669722904625795,
695
+ "learning_rate": 1.5859198568023905e-06,
696
+ "loss": 0.0985,
697
+ "step": 970
698
+ },
699
+ {
700
+ "epoch": 2.322465915826912,
701
+ "grad_norm": 3.111376603928081,
702
+ "learning_rate": 1.486475403155027e-06,
703
+ "loss": 0.097,
704
+ "step": 980
705
+ },
706
+ {
707
+ "epoch": 2.3461766449318318,
708
+ "grad_norm": 2.8389254276441602,
709
+ "learning_rate": 1.3897037575053968e-06,
710
+ "loss": 0.0979,
711
+ "step": 990
712
+ },
713
+ {
714
+ "epoch": 2.3698873740367516,
715
+ "grad_norm": 2.749594117292507,
716
+ "learning_rate": 1.2956785359678365e-06,
717
+ "loss": 0.1072,
718
+ "step": 1000
719
+ },
720
+ {
721
+ "epoch": 2.3698873740367516,
722
+ "eval_loss": 0.4591856598854065,
723
+ "eval_runtime": 58.6721,
724
+ "eval_samples_per_second": 12.783,
725
+ "eval_steps_per_second": 3.204,
726
+ "step": 1000
727
+ },
728
+ {
729
+ "epoch": 2.3935981031416715,
730
+ "grad_norm": 1.9013411296234148,
731
+ "learning_rate": 1.2044712653972713e-06,
732
+ "loss": 0.0939,
733
+ "step": 1010
734
+ },
735
+ {
736
+ "epoch": 2.4173088322465914,
737
+ "grad_norm": 2.592341028542664,
738
+ "learning_rate": 1.1161513289773145e-06,
739
+ "loss": 0.0977,
740
+ "step": 1020
741
+ },
742
+ {
743
+ "epoch": 2.4410195613515118,
744
+ "grad_norm": 2.197547583648026,
745
+ "learning_rate": 1.0307859134390985e-06,
746
+ "loss": 0.1014,
747
+ "step": 1030
748
+ },
749
+ {
750
+ "epoch": 2.4647302904564317,
751
+ "grad_norm": 2.6891568317348753,
752
+ "learning_rate": 9.484399579509996e-07,
753
+ "loss": 0.1004,
754
+ "step": 1040
755
+ },
756
+ {
757
+ "epoch": 2.4884410195613516,
758
+ "grad_norm": 2.620726987123096,
759
+ "learning_rate": 8.691761047181157e-07,
760
+ "loss": 0.1109,
761
+ "step": 1050
762
+ },
763
+ {
764
+ "epoch": 2.5121517486662714,
765
+ "grad_norm": 2.324887436431684,
766
+ "learning_rate": 7.930546513290938e-07,
767
+ "loss": 0.0912,
768
+ "step": 1060
769
+ },
770
+ {
771
+ "epoch": 2.5358624777711913,
772
+ "grad_norm": 2.3271508519205026,
773
+ "learning_rate": 7.201335048865627e-07,
774
+ "loss": 0.1008,
775
+ "step": 1070
776
+ },
777
+ {
778
+ "epoch": 2.5595732068761112,
779
+ "grad_norm": 2.6691442307978703,
780
+ "learning_rate": 6.50468137956049e-07,
781
+ "loss": 0.0888,
782
+ "step": 1080
783
+ },
784
+ {
785
+ "epoch": 2.5832839359810316,
786
+ "grad_norm": 3.5303646266829105,
787
+ "learning_rate": 5.841115463668834e-07,
788
+ "loss": 0.0939,
789
+ "step": 1090
790
+ },
791
+ {
792
+ "epoch": 2.6069946650859515,
793
+ "grad_norm": 2.091179897371891,
794
+ "learning_rate": 5.211142088972326e-07,
795
+ "loss": 0.1018,
796
+ "step": 1100
797
+ },
798
+ {
799
+ "epoch": 2.6307053941908713,
800
+ "grad_norm": 1.685341612592175,
801
+ "learning_rate": 4.6152404887388255e-07,
802
+ "loss": 0.0973,
803
+ "step": 1110
804
+ },
805
+ {
806
+ "epoch": 2.6544161232957912,
807
+ "grad_norm": 2.2444188487114887,
808
+ "learning_rate": 4.0538639771601216e-07,
809
+ "loss": 0.0905,
810
+ "step": 1120
811
+ },
812
+ {
813
+ "epoch": 2.6781268524007116,
814
+ "grad_norm": 2.7117966721609283,
815
+ "learning_rate": 3.5274396045068324e-07,
816
+ "loss": 0.096,
817
+ "step": 1130
818
+ },
819
+ {
820
+ "epoch": 2.7018375815056315,
821
+ "grad_norm": 2.244998430511972,
822
+ "learning_rate": 3.0363678322627597e-07,
823
+ "loss": 0.0886,
824
+ "step": 1140
825
+ },
826
+ {
827
+ "epoch": 2.7255483106105514,
828
+ "grad_norm": 2.4981067701744752,
829
+ "learning_rate": 2.5810222284858797e-07,
830
+ "loss": 0.0875,
831
+ "step": 1150
832
+ },
833
+ {
834
+ "epoch": 2.7492590397154713,
835
+ "grad_norm": 2.7328579885076723,
836
+ "learning_rate": 2.1617491836276982e-07,
837
+ "loss": 0.0934,
838
+ "step": 1160
839
+ },
840
+ {
841
+ "epoch": 2.772969768820391,
842
+ "grad_norm": 2.8298404120624667,
843
+ "learning_rate": 1.778867647027188e-07,
844
+ "loss": 0.1074,
845
+ "step": 1170
846
+ },
847
+ {
848
+ "epoch": 2.796680497925311,
849
+ "grad_norm": 1.8587335375726017,
850
+ "learning_rate": 1.4326688842795977e-07,
851
+ "loss": 0.0966,
852
+ "step": 1180
853
+ },
854
+ {
855
+ "epoch": 2.820391227030231,
856
+ "grad_norm": 2.824102318444297,
857
+ "learning_rate": 1.1234162556650163e-07,
858
+ "loss": 0.0929,
859
+ "step": 1190
860
+ },
861
+ {
862
+ "epoch": 2.8441019561351513,
863
+ "grad_norm": 2.160006396851401,
864
+ "learning_rate": 8.513450158049109e-08,
865
+ "loss": 0.0949,
866
+ "step": 1200
867
+ },
868
+ {
869
+ "epoch": 2.867812685240071,
870
+ "grad_norm": 2.4548803919506117,
871
+ "learning_rate": 6.166621346993029e-08,
872
+ "loss": 0.0908,
873
+ "step": 1210
874
+ },
875
+ {
876
+ "epoch": 2.891523414344991,
877
+ "grad_norm": 2.8986827593174747,
878
+ "learning_rate": 4.1954614028054674e-08,
879
+ "loss": 0.0935,
880
+ "step": 1220
881
+ },
882
+ {
883
+ "epoch": 2.915234143449911,
884
+ "grad_norm": 1.854461789517957,
885
+ "learning_rate": 2.6014698260358183e-08,
886
+ "loss": 0.0871,
887
+ "step": 1230
888
+ },
889
+ {
890
+ "epoch": 2.9389448725548313,
891
+ "grad_norm": 2.036424049182321,
892
+ "learning_rate": 1.385859197759687e-08,
893
+ "loss": 0.0875,
894
+ "step": 1240
895
+ },
896
+ {
897
+ "epoch": 2.962655601659751,
898
+ "grad_norm": 2.2598436193356752,
899
+ "learning_rate": 5.495542571443135e-09,
900
+ "loss": 0.0903,
901
+ "step": 1250
902
+ },
903
+ {
904
+ "epoch": 2.986366330764671,
905
+ "grad_norm": 2.4613374489970705,
906
+ "learning_rate": 9.31911979807909e-10,
907
+ "loss": 0.0812,
908
+ "step": 1260
909
+ },
910
+ {
911
+ "epoch": 3.0,
912
+ "step": 1266,
913
+ "total_flos": 54228985774080.0,
914
+ "train_loss": 0.2981918969472626,
915
+ "train_runtime": 7343.4841,
916
+ "train_samples_per_second": 2.756,
917
+ "train_steps_per_second": 0.172
918
+ }
919
+ ],
920
+ "logging_steps": 10,
921
+ "max_steps": 1266,
922
+ "num_input_tokens_seen": 0,
923
+ "num_train_epochs": 3,
924
+ "save_steps": 500,
925
+ "stateful_callbacks": {
926
+ "TrainerControl": {
927
+ "args": {
928
+ "should_epoch_stop": false,
929
+ "should_evaluate": false,
930
+ "should_log": false,
931
+ "should_save": true,
932
+ "should_training_stop": true
933
+ },
934
+ "attributes": {}
935
+ }
936
+ },
937
+ "total_flos": 54228985774080.0,
938
+ "train_batch_size": 1,
939
+ "trial_name": null,
940
+ "trial_params": null
941
+ }
osgenesis-llama/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde35580b3b57f2821caace6e28a250ea4a6829eabf04747110a6888bc894f90
3
+ size 8081
osgenesis-llama/training_eval_loss.png ADDED
osgenesis-llama/training_loss.png ADDED