Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +98 -0
- chat_template.jinja +5 -0
- config.json +29 -0
- generation_config.json +12 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +299 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2064 -0
- train/log.json +1190 -0
- train/training_loss.png +0 -0
- train/validation_loss.png +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3.2
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model: allura-forge/Llama-3.3-8B-Instruct
|
| 6 |
+
datasets:
|
| 7 |
+
- m-a-p/SuperGPQA
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
library_name: transformers
|
| 10 |
+
tags:
|
| 11 |
+
- sft
|
| 12 |
+
- trl
|
| 13 |
+
- unsloth
|
| 14 |
+
- llama
|
| 15 |
+
- llama3
|
| 16 |
+
- llama3.3
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
A fine-tune of [allura-forge/Llama-3.3-8B-Instruct](https://huggingface.co/allura-forge/Llama-3.3-8B-Instruct) on the [m-a-p/SuperGPQA](https://huggingface.co/datasets/m-a-p/SuperGPQA) dataset.
|
| 20 |
+
|
| 21 |
+
## Usage example
|
| 22 |
+
Set temperature as 0.0 for best results.
|
| 23 |
+
|
| 24 |
+
**System prompt**
|
| 25 |
+
```
|
| 26 |
+
You are a classifier. Categorize the following problem into discipline, field, and subfield in JSON format.
|
| 27 |
+
```
|
| 28 |
+
**User prompt**
|
| 29 |
+
```
|
| 30 |
+
Cotton and linen both readily catch fire. A batch of towels is composed of both cotton and linen, and is known to have caught fire. If it is known that the towels were ignited by a lit cigarette, which of the following arguments utilizes the most appropriate form of reasoning?
|
| 31 |
+
```
|
| 32 |
+
**Assistant response**
|
| 33 |
+
```
|
| 34 |
+
{"discipline": "Philosophy", "field": "Philosophy", "subfield": "Logic"}
|
| 35 |
+
```
|
| 36 |
+
# Possible output options
|
| 37 |
+
Discipline
|
| 38 |
+
```
|
| 39 |
+
['Medicine', 'Literature and Arts', 'History', 'Science', 'Philosophy', 'Law', 'Engineering', 'Management', 'Agronomy', 'Economics', 'Military Science', 'Sociology', 'Education']
|
| 40 |
+
```
|
| 41 |
+
Field
|
| 42 |
+
```
|
| 43 |
+
['Animal Husbandry', 'Political Science', 'Civil Engineering', 'Materials Science and Engineering', 'Weapon Science and Technology', 'History', 'Stomatology', 'Agricultural Engineering', 'Mechanical Engineering', 'Astronomy', 'Nuclear Science and Technology', 'Language and Literature', 'Forestry Engineering', 'Geology', 'Basic Medicine', 'Crop Science', 'Electronic Science and Technology', 'Military Science', 'Petroleum and Natural Gas Engineering', 'Metallurgical Engineering', 'Management Science and Engineering', 'Library, Information and Archival Management', 'Clinical Medicine', 'Art Studies', 'Food Science and Engineering', 'Systems Science', 'Aquaculture', 'Business Administration', 'Computer Science and Technology', 'Electrical Engineering', 'Forestry', 'Textile Science and Engineering', 'Physical Education', 'Oceanography', 'Musicology', 'Traditional Chinese Medicine', 'Mining Engineering', 'Psychology', 'Law', 'Control Science and Engineering', 'Chemistry', 'Hydraulic Engineering', 'Public Administration', 'Chemical Engineering and Technology', 'Geography', 'Optical Engineering', 'Applied Economics', 'Architecture', 'Power Engineering and Engineering Thermophysics', 'Education', 'Journalism and Communication', 'Aeronautical and Astronautical Science and Technology', 'Veterinary Medicine', 'Geophysics', 'Instrument Science and Technology', 'Mathematics', 'Information and Communication Engineering', 'Physical Oceanography', 'Theoretical Economics', 'Mechanics', 'Philosophy', 'Geological Resources and Geological Engineering', 'Physics', 'Pharmacy', 'Environmental Science and Engineering', 'Transportation Engineering', 'Biology', 'Naval Architecture and Ocean Engineering', 'Atmospheric Science', 'Sociology', 'Public Health and Preventive Medicine', 'Surveying and Mapping Science and Technology']
|
| 44 |
+
```
|
| 45 |
+
Subfield
|
| 46 |
+
```
|
| 47 |
+
['Political Science', 'Social Medicine and Health Management', 'Preschool Education', 'Geriatric Medicine', 'Civil and Commercial Law', 'Biophysics', 'Rigid Body Mechanics', 'Cartography and Geographic Information Engineering', 'Anesthesiology', 'Stellar and Interstellar Evolution', 'Chemical Transport Engineering', 'Structural Geology', 'Contract Law', 'Obstetrics and Gynecology', 'Pathology and Pathophysiology', 'Harmony', 'Aquaculture', 'Pharmaceutics', 'Vehicle Operation Engineering', 'Circuits and Systems', 'Solid State Physics', 'Theoretical Fluid Mechanics', 'Mineral Processing Engineering', 'Functions of Real Variables', 'Signal and Information Processing', 'Pathogen Biology', 'Computer Networks', 'Optical Fiber Communication', 'Genetics', 'Architectural History', 'Oil and Gas Field Development and Storage & Transportation Engineering', 'Tourism Management and Technological Economics Management', 'Drama and Opera Studies', 'Polynomials and Series Expansions', 'Cryptography', 'Polymer Chemistry and Physics', 'Principles of Seismic Exploration', 'Fuzzy Mathematics', 'Physiology', 'Pitch and Scales', 'Heat Transfer', 'Operating Systems', 'Fluid Physics', 'Microelectronics and Solid-State Electronics', 'Non-ferrous Metallurgy', 'Environmental Science', 'Power Electronics and Electrical Drives', 'Communication and Information Systems', 'Oncology', 'Military Thought and History', 'Procedural Law', 'Group Theory', 'Fine Arts', 'Transportation Planning and Management', 'Physical Chemistry', 'Physical Oceanography', 'Sports Science and Medicine', 'Animal Nutrition and Feed Science', 'Urban Planning and Design', 'Space physics', 'Electrical Theory and New Technologies', 'Economic History', 'Geotechnical Engineering', 'Ecology', 'Theory of Curriculum and Instruction', 'Radiation Medicine', 'Information Management Science', 'Functions of Complex Variables', 'Computer Software and Theory', 'Nursing and Rehabilitation Medicine', 'Wood Science and Technology', 'Mass Transport and Separation Process in Chemical Engineering', 'Religious Studies', 'Mineralogy, Petrology, and Economic Geology', 'Thermodynamics and Statistical Physics', 'Structural Engineering', 'Demography and Anthropology', 'Philology and Bibliography', 'Databases', 'Textile Materials Science', 'Textile Chemistry and Dyeing Engineering', 'Physical Chemistry of Metallurgical Process', 'Ethics', 'Internal Combustion Engineering', 'Design Arts', 'Refrigeration and Cryogenic Engineering', 'Mechatronic Engineering', 'Dermatology and Venereology', 'Economic Statistics', 'Applied Optics', 'Systems Science', 'Particle and Nuclear Physics', 'Information Management and Communication', 'French Language and Literature', 'Labor Economics', 'Medicinal Chemistry', 'Literary Theory', 'Microbiology', 'Physical Education and Training', 'Internal Medicine', 'Computer Architecture', 'Operations Research and Cybernetics', 'Dynamic Meteorology', 'Industrial Economics', 'Literary History', 'Marine Engineering', 'Optoelectronic Technology', 'Combinatorial Mathematics', 'Theoretical Optics', 'Materials Processing Engineering', 'Nutrition and Food Hygiene', 'Theoretical Mechanics', 'Graph Theory', 'Quantum Mechanics', 'Materials Physics and Chemistry', 'Marine Biology', 'Forest Cultivation and Genetic Breeding', 'National and Defense Economics', 'Poromechanics and Reservoir Physics', 'Road and Railway Engineering', 'Aeronautical and Astronautical Science and Technology', 'Data Structures', 'Historical Geography', 'Analytical Chemistry', 'Military Law', 'Pharmaceutical Analysis', 'Polymer Physics', 'Atmospheric Physics and Atmospheric Environment', 'Communication Principles', 'Underwater Acoustics', 'Journalism and News Practice', 'Water conservancy and Hydropower Engineering', 'Inorganic Chemistry', 'Animal Rearing and Breeding', 'Educational Technology and Principles', 'High Voltage and Insulation Technology', 'Advanced Algebra', 'Food Biochemistry', 'Philosophy of Science and Technology', 'Logic', 'Film Studies', 'Military Command and Information Systems', 'Fundamentals of Dynamics and Control', 'Neurology', 'Cosmology', 'Forest Engineering', 'Ophthalmology', 'Agricultural Environment and Soil-Water Engineering', 'Crop Science', 'Human Anatomy and Histology-Embryology', 'Probability and Statistics', 'Communication and Broadcasting', 'Maternal, Child and Adolescent Health', 'Thermodynamics', 'Surgery', 'Architectural Design and Theory', 'Western Economics', 'Ordinary Differential Equations', 'Management Science and Engineering', 'Military Logistics and Equipment', 'Discrete Mathematics', 'Mathematical Analysis', 'Astrophysics', 'Linguistics and Applied Linguistics', 'Quantitative Economics', 'Cell Biology', 'Urban Infrastructure Engineering', 'Pattern Recognition', 'Forensic Medicine', 'Antenna and Radio Communication', 'Constitutional and Administrative Law', 'Laser Technology', 'Traditional Chinese Medicine Theory', 'Biochemistry and Molecular Biology', 'Mining and Safety Engineering', 'Geometry and Topology', 'Dance Studies', 'Semiconductor Physics', 'Computational Mathematics', 'Fluid Machinery and Engineering', 'Philosophical Aesthetics', 'Engineering Fluid Mechanics', 'Stochastic Processes', 'Psychology', 'Traditional Chinese Pharmacy', 'Environmental and Resource Protection', 'Physical Geography', 'Archaeology and Museology', 'Power Systems and Automation', 'Music History, Education, and Technology', 'Pediatrics', 'Modern and Contemporary Chinese Literature', 'Geodesy and Surveying Engineering', 'Zoology', 'Military Management', 'Iron and Steel Metallurgy', 'Epidemiology and Health Statistics', 'Weapon Systems Science and Engineering', 'Military Chemistry and Pyrotechnics', 'World History', 'Meteorology', 'Finance', 'Electrodynamics', 'Organic Chemistry', 'History and Theory of Journalism and Media Management', 'Solar System Science', 'Geochemistry', 'Veterinary Medicine', 'Geological Resources and Geological Engineering', 'Psychiatry and Mental Health', 'Manufacturing Automation', 'Traditional Chinese Health Preservation', 'Business and Accounting Management', 'Atomic and Molecular Physics', 'Education Economics, Management and Social Security', 'Hydraulics and Hydrology', 'Otorhinolaryngology', 'Number Theory', 'Principles of Metallurgy', 'Radiation Protection and Nuclear Technology Applications', 'Principles of Computer Organization', 'Special Education', 'Digital Surveying and Remote Sensing Applications', 'Marine Chemistry', 'Composition', 'Traffic Information Engineering and Control', 'Emergency Medicine', 'Fluid Flow and Heat Transfer in Chemical Engineering', 'Criminal Law', 'Classical Chinese Literature', 'Numerical Analysis', 'Food Processing and Storage Engineering', 'Electrochemistry', 'Russian Language and Literature', 'Special Number Theory', 'Political Economy', 'Imaging and Nuclear Medicine', 'Fundamental Mathematics', 'Pharmacology', 'Astronomical Observation and Technology', 'Human Geography', 'Subatomic and Atomic Physics', 'Bridge and Tunnel Engineering', 'Acoustics', 'Social and Folklore Studies', 'Radiochemistry', 'Musical Forms and Analysis', 'Control Theory and Control Engineering', 'Engineering Thermophysics', 'Health Toxicology and Environmental Health', 'Legal Theory and Legal History', 'Relativity', 'Nuclear Energy and Reactor Technology', 'Guidance, Navigation and Control', 'Library and Archival Science', 'Sports Humanities and Sociology', 'Agricultural Mechanization Engineering', 'Formal Languages', 'Thermal Energy Engineering', 'Law and Social Governance', 'International Trade', 'Electromagnetic Field and Microwave Technology', 'Instrumentation and Performance', 'Broadcasting and Television Art', 'Solid Mechanics', 'Environmental Engineering', 'Advanced Programming Languages', 'Solid Earth Geophysics', 'Statistical Mechanics', 'Hydrogeology', 'Land Resource Management and Administrative Management', 'Power Machinery and Engineering', 'Paleontology and Stratigraphy', 'Landscape Plants and Ornamental Horticulture', 'Instrument Science and Technology', 'Immunology', 'Clinical Stomatology', 'Clinical Laboratory Diagnostics', 'Botany', 'Microbiology and Biochemical Pharmacy', 'Ship Mechanics and Design Principles', 'International Law', 'Elements of Chemical Reaction Engineering', 'Basic Stomatology', 'Public Finance']
|
| 48 |
+
```
|
| 49 |
+
## Model Details
|
| 50 |
+
- Base Model: `allura-forge/Llama-3.3-8B-Instruct`
|
| 51 |
+
- Parameter Count: 8,030,261,248
|
| 52 |
+
- Precision: torch.bfloat16
|
| 53 |
+
|
| 54 |
+
## Hardware
|
| 55 |
+
- GPU: NVIDIA RTX PRO 6000 Blackwell Server Edition
|
| 56 |
+
- Announced: Mar 17th, 2025
|
| 57 |
+
- Release Date: Mar 18th, 2025
|
| 58 |
+
- Memory Type: GDDR7
|
| 59 |
+
- Bandwidth: 1.79 TB/s
|
| 60 |
+
- Memory Size: 96 GB
|
| 61 |
+
- Memory Bus: 512 bit
|
| 62 |
+
- Shading Units: 24064
|
| 63 |
+
- TDP: 600W
|
| 64 |
+
|
| 65 |
+
## Training Settings
|
| 66 |
+
### PEFT
|
| 67 |
+
- Rank: 32
|
| 68 |
+
- LoRA alpha: 64
|
| 69 |
+
- Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
|
| 70 |
+
- Gradient checkpointing: unsloth
|
| 71 |
+
|
| 72 |
+
### SFT
|
| 73 |
+
- Epoch: 2
|
| 74 |
+
- Batch size: 32
|
| 75 |
+
- Gradient Accumulation steps: 1
|
| 76 |
+
- Warmup ratio: 0.05
|
| 77 |
+
- Learning rate: 0.0002
|
| 78 |
+
- Optimizer: adamw_torch_fused
|
| 79 |
+
- Learning rate scheduler: cosine
|
| 80 |
+
|
| 81 |
+
## Training stats
|
| 82 |
+
- Date: 2026-03-26T03:53:29.234881
|
| 83 |
+
- Peak VRAM usage: 32.135 GB
|
| 84 |
+
- Global step: 1576
|
| 85 |
+
- Training runtime (seconds): 2681.8444
|
| 86 |
+
- Average training loss: 0.06838441643920647
|
| 87 |
+
- Final validation loss: 0.0504293330013752
|
| 88 |
+
|
| 89 |
+
## Framework versions
|
| 90 |
+
- Unsloth: 2026.3.15
|
| 91 |
+
- TRL: 0.22.2
|
| 92 |
+
- Transformers: 4.56.2
|
| 93 |
+
- Pytorch: 2.10.0+cu128
|
| 94 |
+
- Datasets: 4.8.4
|
| 95 |
+
- Tokenizers: 0.22.2
|
| 96 |
+
|
| 97 |
+
## License
|
| 98 |
+
This model is released under the Llama3 license. See the [Terms of Use](https://www.llama.com/llama3/license/) for details.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
| 2 |
+
|
| 3 |
+
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
|
| 4 |
+
|
| 5 |
+
' }}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 8192,
|
| 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 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 500000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"transformers_version": "4.56.2",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 128256
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128009
|
| 7 |
+
],
|
| 8 |
+
"max_length": 4096,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.56.2"
|
| 12 |
+
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60d42e32f551f12ce79b67b7d6a3959ae9367ab673298ecddd32778e8b8b8f75
|
| 3 |
+
size 4976698672
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e86540e301b30ce4d7315cbc99b835852b14405901816fcc96b8c60e3426aab
|
| 3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cc9b6bc2d9e7c7f3e8f19292c857ea68b600326ca602945a63505764bae0fd7
|
| 3 |
+
size 4915916176
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce3f749a1e7d3a08afe65b6f7beeffa960918d97b4e54449ae5af1ac77a71b49
|
| 3 |
+
size 1168138808
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,299 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8030261248,
|
| 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 |
+
}
|
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": "<|reserved_special_token_250|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
|
| 3 |
+
size 17209961
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|reserved_special_token_2|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_3|>",
|
| 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": "<|reserved_special_token_4|>",
|
| 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": "<|reserved_special_token_5|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_6|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_7|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_8|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_9|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_10|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_11|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_12|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_13|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_14|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_15|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_16|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_17|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_18|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_19|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_20|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_21|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_22|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_23|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_24|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_25|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_26|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_27|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_28|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_29|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_30|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_31|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_32|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_33|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_34|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_35|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_36|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_37|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_38|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_39|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_40|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_41|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_42|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_43|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_44|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_45|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_46|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_47|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_48|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_49|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_50|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_51|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_52|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_53|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_54|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_55|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_56|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_57|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_58|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_59|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_60|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_61|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_62|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_63|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_64|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_65|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_66|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_67|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_68|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_69|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_70|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_71|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_72|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_73|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_74|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_75|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_76|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_77|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_78|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_79|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_80|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_81|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_82|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_83|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_84|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_85|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_86|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_87|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_88|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_89|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_90|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_91|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_92|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_93|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_94|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_95|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_96|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_97|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_98|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_99|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_100|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_101|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_102|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_103|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_104|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_105|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_106|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_107|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_108|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_109|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_110|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_111|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_112|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_113|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_114|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_115|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_116|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_117|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_118|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_119|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_120|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_121|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_122|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_123|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_124|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_125|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_126|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_127|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_128|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_129|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_130|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_131|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_132|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_133|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_134|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_135|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_136|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_137|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_138|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_139|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_140|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_141|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_142|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_143|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_144|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_145|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_146|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_147|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_148|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_149|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_150|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_151|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_152|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_153|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_154|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_155|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_156|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_157|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_158|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_159|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_160|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_161|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_162|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_163|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_164|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_165|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_166|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_167|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_168|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_169|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_170|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_171|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_172|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_173|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_174|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_175|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_176|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_177|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_178|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_179|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_180|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_181|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_182|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_183|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_184|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_185|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_186|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_187|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_188|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_189|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_190|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_191|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_192|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_193|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_194|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_195|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_196|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_197|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_198|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_199|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_200|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_201|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_202|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_203|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_204|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_205|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_206|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_207|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_208|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_209|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_210|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_211|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_212|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_213|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_214|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_215|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_216|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_217|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_218|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_219|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_220|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_221|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_222|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_223|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_224|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_225|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_226|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_227|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_228|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_229|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_230|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_231|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_232|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_233|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_234|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_235|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_236|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_237|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_238|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_239|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_240|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_241|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_242|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_243|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_244|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_245|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_246|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_247|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_248|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_249|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_250|>",
|
| 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": 1000000000000000019884624838656,
|
| 2061 |
+
"pad_token": "<|reserved_special_token_250|>",
|
| 2062 |
+
"padding_side": "left",
|
| 2063 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2064 |
+
}
|
train/log.json
ADDED
|
@@ -0,0 +1,1190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss": 1.8996,
|
| 4 |
+
"grad_norm": 5.035277843475342,
|
| 5 |
+
"learning_rate": 2.278481012658228e-05,
|
| 6 |
+
"epoch": 0.012690355329949238,
|
| 7 |
+
"step": 10
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"loss": 0.5315,
|
| 11 |
+
"grad_norm": 1.102072834968567,
|
| 12 |
+
"learning_rate": 4.810126582278481e-05,
|
| 13 |
+
"epoch": 0.025380710659898477,
|
| 14 |
+
"step": 20
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"loss": 0.3353,
|
| 18 |
+
"grad_norm": 0.7798988819122314,
|
| 19 |
+
"learning_rate": 7.341772151898734e-05,
|
| 20 |
+
"epoch": 0.03807106598984772,
|
| 21 |
+
"step": 30
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"loss": 0.2226,
|
| 25 |
+
"grad_norm": 0.8653473854064941,
|
| 26 |
+
"learning_rate": 9.873417721518988e-05,
|
| 27 |
+
"epoch": 0.050761421319796954,
|
| 28 |
+
"step": 40
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"loss": 0.164,
|
| 32 |
+
"grad_norm": 0.7569780349731445,
|
| 33 |
+
"learning_rate": 0.0001240506329113924,
|
| 34 |
+
"epoch": 0.06345177664974619,
|
| 35 |
+
"step": 50
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"loss": 0.1394,
|
| 39 |
+
"grad_norm": 1.0211968421936035,
|
| 40 |
+
"learning_rate": 0.00014936708860759494,
|
| 41 |
+
"epoch": 0.07614213197969544,
|
| 42 |
+
"step": 60
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"loss": 0.1201,
|
| 46 |
+
"grad_norm": 0.5370887517929077,
|
| 47 |
+
"learning_rate": 0.00017468354430379748,
|
| 48 |
+
"epoch": 0.08883248730964467,
|
| 49 |
+
"step": 70
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"loss": 0.122,
|
| 53 |
+
"grad_norm": 0.49917498230934143,
|
| 54 |
+
"learning_rate": 0.0002,
|
| 55 |
+
"epoch": 0.10152284263959391,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"loss": 0.1217,
|
| 60 |
+
"grad_norm": 0.4577413499355316,
|
| 61 |
+
"learning_rate": 0.0001999779803602204,
|
| 62 |
+
"epoch": 0.11421319796954314,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"loss": 0.0965,
|
| 67 |
+
"grad_norm": 0.48522070050239563,
|
| 68 |
+
"learning_rate": 0.00019991193113817244,
|
| 69 |
+
"epoch": 0.12690355329949238,
|
| 70 |
+
"step": 100
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"loss": 0.11,
|
| 74 |
+
"grad_norm": 0.41902250051498413,
|
| 75 |
+
"learning_rate": 0.00019980188142145754,
|
| 76 |
+
"epoch": 0.13959390862944163,
|
| 77 |
+
"step": 110
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"loss": 0.0823,
|
| 81 |
+
"grad_norm": 0.5561641454696655,
|
| 82 |
+
"learning_rate": 0.00019964787967517817,
|
| 83 |
+
"epoch": 0.15228426395939088,
|
| 84 |
+
"step": 120
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"loss": 0.0856,
|
| 88 |
+
"grad_norm": 0.3316971957683563,
|
| 89 |
+
"learning_rate": 0.00019944999372059388,
|
| 90 |
+
"epoch": 0.1649746192893401,
|
| 91 |
+
"step": 130
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"loss": 0.0849,
|
| 95 |
+
"grad_norm": 0.372153639793396,
|
| 96 |
+
"learning_rate": 0.00019920831070525342,
|
| 97 |
+
"epoch": 0.17766497461928935,
|
| 98 |
+
"step": 140
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"loss": 0.0929,
|
| 102 |
+
"grad_norm": 0.33250877261161804,
|
| 103 |
+
"learning_rate": 0.00019892293706461555,
|
| 104 |
+
"epoch": 0.19035532994923857,
|
| 105 |
+
"step": 150
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"eval_loss": 0.08791538327932358,
|
| 109 |
+
"eval_runtime": 29.62,
|
| 110 |
+
"eval_samples_per_second": 44.801,
|
| 111 |
+
"eval_steps_per_second": 11.209,
|
| 112 |
+
"epoch": 0.19923857868020303,
|
| 113 |
+
"step": 157
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"loss": 0.0824,
|
| 117 |
+
"grad_norm": 0.4130192995071411,
|
| 118 |
+
"learning_rate": 0.00019859399847517567,
|
| 119 |
+
"epoch": 0.20304568527918782,
|
| 120 |
+
"step": 160
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"loss": 0.0902,
|
| 124 |
+
"grad_norm": 0.3217241168022156,
|
| 125 |
+
"learning_rate": 0.0001982216397991188,
|
| 126 |
+
"epoch": 0.21573604060913706,
|
| 127 |
+
"step": 170
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"loss": 0.0766,
|
| 131 |
+
"grad_norm": 0.4728490710258484,
|
| 132 |
+
"learning_rate": 0.0001978060250205232,
|
| 133 |
+
"epoch": 0.22842639593908629,
|
| 134 |
+
"step": 180
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"loss": 0.0844,
|
| 138 |
+
"grad_norm": 0.5730077028274536,
|
| 139 |
+
"learning_rate": 0.0001973473371731431,
|
| 140 |
+
"epoch": 0.24111675126903553,
|
| 141 |
+
"step": 190
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"loss": 0.0841,
|
| 145 |
+
"grad_norm": 0.5745298862457275,
|
| 146 |
+
"learning_rate": 0.00019684577825980192,
|
| 147 |
+
"epoch": 0.25380710659898476,
|
| 148 |
+
"step": 200
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"loss": 0.0797,
|
| 152 |
+
"grad_norm": 0.3141058683395386,
|
| 153 |
+
"learning_rate": 0.0001963015691634317,
|
| 154 |
+
"epoch": 0.26649746192893403,
|
| 155 |
+
"step": 210
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"loss": 0.0822,
|
| 159 |
+
"grad_norm": 0.3730680048465729,
|
| 160 |
+
"learning_rate": 0.00019571494954979775,
|
| 161 |
+
"epoch": 0.27918781725888325,
|
| 162 |
+
"step": 220
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"loss": 0.0677,
|
| 166 |
+
"grad_norm": 0.3915182650089264,
|
| 167 |
+
"learning_rate": 0.00019508617776195167,
|
| 168 |
+
"epoch": 0.2918781725888325,
|
| 169 |
+
"step": 230
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"loss": 0.08,
|
| 173 |
+
"grad_norm": 0.3052193820476532,
|
| 174 |
+
"learning_rate": 0.00019441553070645887,
|
| 175 |
+
"epoch": 0.30456852791878175,
|
| 176 |
+
"step": 240
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"loss": 0.0744,
|
| 180 |
+
"grad_norm": 0.3673352003097534,
|
| 181 |
+
"learning_rate": 0.000193703303731451,
|
| 182 |
+
"epoch": 0.31725888324873097,
|
| 183 |
+
"step": 250
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"loss": 0.0821,
|
| 187 |
+
"grad_norm": 0.39443644881248474,
|
| 188 |
+
"learning_rate": 0.00019294981049655668,
|
| 189 |
+
"epoch": 0.3299492385786802,
|
| 190 |
+
"step": 260
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"loss": 0.073,
|
| 194 |
+
"grad_norm": 0.44178199768066406,
|
| 195 |
+
"learning_rate": 0.0001921553828347681,
|
| 196 |
+
"epoch": 0.3426395939086294,
|
| 197 |
+
"step": 270
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"loss": 0.0784,
|
| 201 |
+
"grad_norm": 0.4202715754508972,
|
| 202 |
+
"learning_rate": 0.00019132037060630409,
|
| 203 |
+
"epoch": 0.3553299492385787,
|
| 204 |
+
"step": 280
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"loss": 0.0646,
|
| 208 |
+
"grad_norm": 0.23640507459640503,
|
| 209 |
+
"learning_rate": 0.00019044514154453434,
|
| 210 |
+
"epoch": 0.3680203045685279,
|
| 211 |
+
"step": 290
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"loss": 0.0785,
|
| 215 |
+
"grad_norm": 0.4354120194911957,
|
| 216 |
+
"learning_rate": 0.0001895300810940321,
|
| 217 |
+
"epoch": 0.38071065989847713,
|
| 218 |
+
"step": 300
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"loss": 0.0656,
|
| 222 |
+
"grad_norm": 0.2467317283153534,
|
| 223 |
+
"learning_rate": 0.00018857559224082736,
|
| 224 |
+
"epoch": 0.3934010152284264,
|
| 225 |
+
"step": 310
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"eval_loss": 0.0728072002530098,
|
| 229 |
+
"eval_runtime": 19.9827,
|
| 230 |
+
"eval_samples_per_second": 66.407,
|
| 231 |
+
"eval_steps_per_second": 16.614,
|
| 232 |
+
"epoch": 0.39847715736040606,
|
| 233 |
+
"step": 314
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"loss": 0.0738,
|
| 237 |
+
"grad_norm": 0.2969267666339874,
|
| 238 |
+
"learning_rate": 0.00018758209533493444,
|
| 239 |
+
"epoch": 0.40609137055837563,
|
| 240 |
+
"step": 320
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"loss": 0.067,
|
| 244 |
+
"grad_norm": 0.3527528643608093,
|
| 245 |
+
"learning_rate": 0.00018655002790523328,
|
| 246 |
+
"epoch": 0.41878172588832485,
|
| 247 |
+
"step": 330
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"loss": 0.0714,
|
| 251 |
+
"grad_norm": 0.2732889950275421,
|
| 252 |
+
"learning_rate": 0.00018547984446678437,
|
| 253 |
+
"epoch": 0.43147208121827413,
|
| 254 |
+
"step": 340
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"loss": 0.0602,
|
| 258 |
+
"grad_norm": 0.25770312547683716,
|
| 259 |
+
"learning_rate": 0.000184372016320664,
|
| 260 |
+
"epoch": 0.44416243654822335,
|
| 261 |
+
"step": 350
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"loss": 0.0624,
|
| 265 |
+
"grad_norm": 0.22473905980587006,
|
| 266 |
+
"learning_rate": 0.00018322703134640654,
|
| 267 |
+
"epoch": 0.45685279187817257,
|
| 268 |
+
"step": 360
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"loss": 0.0709,
|
| 272 |
+
"grad_norm": 0.3180300295352936,
|
| 273 |
+
"learning_rate": 0.00018204539378714561,
|
| 274 |
+
"epoch": 0.46954314720812185,
|
| 275 |
+
"step": 370
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"loss": 0.0698,
|
| 279 |
+
"grad_norm": 0.2796868085861206,
|
| 280 |
+
"learning_rate": 0.00018082762402754936,
|
| 281 |
+
"epoch": 0.48223350253807107,
|
| 282 |
+
"step": 380
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"loss": 0.0658,
|
| 286 |
+
"grad_norm": 0.3655967712402344,
|
| 287 |
+
"learning_rate": 0.0001795742583646466,
|
| 288 |
+
"epoch": 0.4949238578680203,
|
| 289 |
+
"step": 390
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"loss": 0.0682,
|
| 293 |
+
"grad_norm": 0.2886195182800293,
|
| 294 |
+
"learning_rate": 0.0001782858487716455,
|
| 295 |
+
"epoch": 0.5076142131979695,
|
| 296 |
+
"step": 400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"loss": 0.071,
|
| 300 |
+
"grad_norm": 0.27021610736846924,
|
| 301 |
+
"learning_rate": 0.00017696296265484862,
|
| 302 |
+
"epoch": 0.5203045685279187,
|
| 303 |
+
"step": 410
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"loss": 0.0636,
|
| 307 |
+
"grad_norm": 0.28307008743286133,
|
| 308 |
+
"learning_rate": 0.00017560618260377116,
|
| 309 |
+
"epoch": 0.5329949238578681,
|
| 310 |
+
"step": 420
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"loss": 0.0546,
|
| 314 |
+
"grad_norm": 0.28294482827186584,
|
| 315 |
+
"learning_rate": 0.00017421610613457282,
|
| 316 |
+
"epoch": 0.5456852791878173,
|
| 317 |
+
"step": 430
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"loss": 0.0612,
|
| 321 |
+
"grad_norm": 0.2255251258611679,
|
| 322 |
+
"learning_rate": 0.00017279334542691596,
|
| 323 |
+
"epoch": 0.5583756345177665,
|
| 324 |
+
"step": 440
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"loss": 0.0629,
|
| 328 |
+
"grad_norm": 0.22404751181602478,
|
| 329 |
+
"learning_rate": 0.0001713385270543661,
|
| 330 |
+
"epoch": 0.5710659898477157,
|
| 331 |
+
"step": 450
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"loss": 0.0596,
|
| 335 |
+
"grad_norm": 0.2632795572280884,
|
| 336 |
+
"learning_rate": 0.00016985229170845339,
|
| 337 |
+
"epoch": 0.583756345177665,
|
| 338 |
+
"step": 460
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"loss": 0.0717,
|
| 342 |
+
"grad_norm": 0.3002878427505493,
|
| 343 |
+
"learning_rate": 0.0001683352939165167,
|
| 344 |
+
"epoch": 0.5964467005076142,
|
| 345 |
+
"step": 470
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"eval_loss": 0.06722872704267502,
|
| 349 |
+
"eval_runtime": 20.1214,
|
| 350 |
+
"eval_samples_per_second": 65.95,
|
| 351 |
+
"eval_steps_per_second": 16.5,
|
| 352 |
+
"epoch": 0.5977157360406091,
|
| 353 |
+
"step": 471
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"loss": 0.0618,
|
| 357 |
+
"grad_norm": 0.15326248109340668,
|
| 358 |
+
"learning_rate": 0.00016678820175345454,
|
| 359 |
+
"epoch": 0.6091370558375635,
|
| 360 |
+
"step": 480
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"loss": 0.0718,
|
| 364 |
+
"grad_norm": 0.27122628688812256,
|
| 365 |
+
"learning_rate": 0.00016521169654750968,
|
| 366 |
+
"epoch": 0.6218274111675127,
|
| 367 |
+
"step": 490
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"loss": 0.0636,
|
| 371 |
+
"grad_norm": 0.29509711265563965,
|
| 372 |
+
"learning_rate": 0.00016360647258021696,
|
| 373 |
+
"epoch": 0.6345177664974619,
|
| 374 |
+
"step": 500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"loss": 0.0655,
|
| 378 |
+
"grad_norm": 0.4090014100074768,
|
| 379 |
+
"learning_rate": 0.00016197323678064697,
|
| 380 |
+
"epoch": 0.6472081218274112,
|
| 381 |
+
"step": 510
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"loss": 0.0606,
|
| 385 |
+
"grad_norm": 0.2687474191188812,
|
| 386 |
+
"learning_rate": 0.00016031270841407926,
|
| 387 |
+
"epoch": 0.6598984771573604,
|
| 388 |
+
"step": 520
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"loss": 0.0519,
|
| 392 |
+
"grad_norm": 0.25125357508659363,
|
| 393 |
+
"learning_rate": 0.00015862561876524338,
|
| 394 |
+
"epoch": 0.6725888324873096,
|
| 395 |
+
"step": 530
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"loss": 0.0623,
|
| 399 |
+
"grad_norm": 0.21579739451408386,
|
| 400 |
+
"learning_rate": 0.0001569127108162662,
|
| 401 |
+
"epoch": 0.6852791878172588,
|
| 402 |
+
"step": 540
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"loss": 0.0612,
|
| 406 |
+
"grad_norm": 0.24012021720409393,
|
| 407 |
+
"learning_rate": 0.000155174738919468,
|
| 408 |
+
"epoch": 0.6979695431472082,
|
| 409 |
+
"step": 550
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"loss": 0.0617,
|
| 413 |
+
"grad_norm": 0.22273781895637512,
|
| 414 |
+
"learning_rate": 0.00015341246846515096,
|
| 415 |
+
"epoch": 0.7106598984771574,
|
| 416 |
+
"step": 560
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"loss": 0.0627,
|
| 420 |
+
"grad_norm": 0.29965269565582275,
|
| 421 |
+
"learning_rate": 0.0001516266755445271,
|
| 422 |
+
"epoch": 0.7233502538071066,
|
| 423 |
+
"step": 570
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"loss": 0.0649,
|
| 427 |
+
"grad_norm": 0.2375640720129013,
|
| 428 |
+
"learning_rate": 0.00014981814660793314,
|
| 429 |
+
"epoch": 0.7360406091370558,
|
| 430 |
+
"step": 580
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"loss": 0.0653,
|
| 434 |
+
"grad_norm": 0.2595769166946411,
|
| 435 |
+
"learning_rate": 0.0001479876781184833,
|
| 436 |
+
"epoch": 0.748730964467005,
|
| 437 |
+
"step": 590
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"loss": 0.0634,
|
| 441 |
+
"grad_norm": 0.28185659646987915,
|
| 442 |
+
"learning_rate": 0.00014613607620131294,
|
| 443 |
+
"epoch": 0.7614213197969543,
|
| 444 |
+
"step": 600
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"loss": 0.0601,
|
| 448 |
+
"grad_norm": 0.20655085146427155,
|
| 449 |
+
"learning_rate": 0.00014426415628856663,
|
| 450 |
+
"epoch": 0.7741116751269036,
|
| 451 |
+
"step": 610
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"loss": 0.0632,
|
| 455 |
+
"grad_norm": 0.4992614686489105,
|
| 456 |
+
"learning_rate": 0.0001423727427602879,
|
| 457 |
+
"epoch": 0.7868020304568528,
|
| 458 |
+
"step": 620
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"eval_loss": 0.05841095373034477,
|
| 462 |
+
"eval_runtime": 20.0018,
|
| 463 |
+
"eval_samples_per_second": 66.344,
|
| 464 |
+
"eval_steps_per_second": 16.599,
|
| 465 |
+
"epoch": 0.7969543147208121,
|
| 466 |
+
"step": 628
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"loss": 0.0522,
|
| 470 |
+
"grad_norm": 0.2023015171289444,
|
| 471 |
+
"learning_rate": 0.0001404626685813681,
|
| 472 |
+
"epoch": 0.799492385786802,
|
| 473 |
+
"step": 630
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"loss": 0.0567,
|
| 477 |
+
"grad_norm": 0.20891991257667542,
|
| 478 |
+
"learning_rate": 0.00013853477493471468,
|
| 479 |
+
"epoch": 0.8121827411167513,
|
| 480 |
+
"step": 640
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"loss": 0.0555,
|
| 484 |
+
"grad_norm": 0.27132412791252136,
|
| 485 |
+
"learning_rate": 0.00013658991085080025,
|
| 486 |
+
"epoch": 0.8248730964467005,
|
| 487 |
+
"step": 650
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"loss": 0.0594,
|
| 491 |
+
"grad_norm": 0.22256866097450256,
|
| 492 |
+
"learning_rate": 0.0001346289328337558,
|
| 493 |
+
"epoch": 0.8375634517766497,
|
| 494 |
+
"step": 660
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"loss": 0.0556,
|
| 498 |
+
"grad_norm": 0.20859505236148834,
|
| 499 |
+
"learning_rate": 0.00013265270448417234,
|
| 500 |
+
"epoch": 0.850253807106599,
|
| 501 |
+
"step": 670
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"loss": 0.0557,
|
| 505 |
+
"grad_norm": 0.2204328030347824,
|
| 506 |
+
"learning_rate": 0.00013066209611877746,
|
| 507 |
+
"epoch": 0.8629441624365483,
|
| 508 |
+
"step": 680
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"loss": 0.059,
|
| 512 |
+
"grad_norm": 0.2515346109867096,
|
| 513 |
+
"learning_rate": 0.00012865798438715413,
|
| 514 |
+
"epoch": 0.8756345177664975,
|
| 515 |
+
"step": 690
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"loss": 0.0546,
|
| 519 |
+
"grad_norm": 0.3130325376987457,
|
| 520 |
+
"learning_rate": 0.00012664125188567056,
|
| 521 |
+
"epoch": 0.8883248730964467,
|
| 522 |
+
"step": 700
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"loss": 0.0475,
|
| 526 |
+
"grad_norm": 0.2509436011314392,
|
| 527 |
+
"learning_rate": 0.00012461278676879098,
|
| 528 |
+
"epoch": 0.9010152284263959,
|
| 529 |
+
"step": 710
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"loss": 0.0561,
|
| 533 |
+
"grad_norm": 0.23676852881908417,
|
| 534 |
+
"learning_rate": 0.00012257348235793897,
|
| 535 |
+
"epoch": 0.9137055837563451,
|
| 536 |
+
"step": 720
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"loss": 0.0536,
|
| 540 |
+
"grad_norm": 0.20894668996334076,
|
| 541 |
+
"learning_rate": 0.00012052423674808513,
|
| 542 |
+
"epoch": 0.9263959390862944,
|
| 543 |
+
"step": 730
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"loss": 0.0517,
|
| 547 |
+
"grad_norm": 0.18107716739177704,
|
| 548 |
+
"learning_rate": 0.00011846595241223247,
|
| 549 |
+
"epoch": 0.9390862944162437,
|
| 550 |
+
"step": 740
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"loss": 0.0623,
|
| 554 |
+
"grad_norm": 0.3013327717781067,
|
| 555 |
+
"learning_rate": 0.00011639953580397367,
|
| 556 |
+
"epoch": 0.9517766497461929,
|
| 557 |
+
"step": 750
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"loss": 0.0579,
|
| 561 |
+
"grad_norm": 0.19317802786827087,
|
| 562 |
+
"learning_rate": 0.00011432589695829576,
|
| 563 |
+
"epoch": 0.9644670050761421,
|
| 564 |
+
"step": 760
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"loss": 0.0559,
|
| 568 |
+
"grad_norm": 0.26291170716285706,
|
| 569 |
+
"learning_rate": 0.00011224594909080704,
|
| 570 |
+
"epoch": 0.9771573604060914,
|
| 571 |
+
"step": 770
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"loss": 0.0537,
|
| 575 |
+
"grad_norm": 0.28403881192207336,
|
| 576 |
+
"learning_rate": 0.00011016060819556353,
|
| 577 |
+
"epoch": 0.9898477157360406,
|
| 578 |
+
"step": 780
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"eval_loss": 0.05360769107937813,
|
| 582 |
+
"eval_runtime": 20.0465,
|
| 583 |
+
"eval_samples_per_second": 66.196,
|
| 584 |
+
"eval_steps_per_second": 16.562,
|
| 585 |
+
"epoch": 0.9961928934010152,
|
| 586 |
+
"step": 785
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"loss": 0.0502,
|
| 590 |
+
"grad_norm": 0.1471383273601532,
|
| 591 |
+
"learning_rate": 0.0001080707926416719,
|
| 592 |
+
"epoch": 1.00253807106599,
|
| 593 |
+
"step": 790
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"loss": 0.038,
|
| 597 |
+
"grad_norm": 0.17716127634048462,
|
| 598 |
+
"learning_rate": 0.00010597742276884614,
|
| 599 |
+
"epoch": 1.015228426395939,
|
| 600 |
+
"step": 800
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"loss": 0.0351,
|
| 604 |
+
"grad_norm": 0.2006382942199707,
|
| 605 |
+
"learning_rate": 0.00010388142048209676,
|
| 606 |
+
"epoch": 1.0279187817258884,
|
| 607 |
+
"step": 810
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"loss": 0.0375,
|
| 611 |
+
"grad_norm": 0.2539692521095276,
|
| 612 |
+
"learning_rate": 0.00010178370884573046,
|
| 613 |
+
"epoch": 1.0406091370558375,
|
| 614 |
+
"step": 820
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"loss": 0.0422,
|
| 618 |
+
"grad_norm": 0.2615308165550232,
|
| 619 |
+
"learning_rate": 9.968521167683905e-05,
|
| 620 |
+
"epoch": 1.0532994923857868,
|
| 621 |
+
"step": 830
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"loss": 0.0406,
|
| 625 |
+
"grad_norm": 0.23757147789001465,
|
| 626 |
+
"learning_rate": 9.758685313845727e-05,
|
| 627 |
+
"epoch": 1.0659898477157361,
|
| 628 |
+
"step": 840
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"loss": 0.0387,
|
| 632 |
+
"grad_norm": 0.16979315876960754,
|
| 633 |
+
"learning_rate": 9.548955733256803e-05,
|
| 634 |
+
"epoch": 1.0786802030456852,
|
| 635 |
+
"step": 850
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"loss": 0.0352,
|
| 639 |
+
"grad_norm": 0.1853126734495163,
|
| 640 |
+
"learning_rate": 9.339424789313445e-05,
|
| 641 |
+
"epoch": 1.0913705583756346,
|
| 642 |
+
"step": 860
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"loss": 0.0356,
|
| 646 |
+
"grad_norm": 0.15106192231178284,
|
| 647 |
+
"learning_rate": 9.13018475793382e-05,
|
| 648 |
+
"epoch": 1.1040609137055837,
|
| 649 |
+
"step": 870
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"loss": 0.037,
|
| 653 |
+
"grad_norm": 0.20427311956882477,
|
| 654 |
+
"learning_rate": 8.921327786920294e-05,
|
| 655 |
+
"epoch": 1.116751269035533,
|
| 656 |
+
"step": 880
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"loss": 0.0324,
|
| 660 |
+
"grad_norm": 0.1580514758825302,
|
| 661 |
+
"learning_rate": 8.712945855378218e-05,
|
| 662 |
+
"epoch": 1.1294416243654823,
|
| 663 |
+
"step": 890
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"loss": 0.0301,
|
| 667 |
+
"grad_norm": 0.2191898375749588,
|
| 668 |
+
"learning_rate": 8.505130733208968e-05,
|
| 669 |
+
"epoch": 1.1421319796954315,
|
| 670 |
+
"step": 900
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"loss": 0.0355,
|
| 674 |
+
"grad_norm": 0.16614247858524323,
|
| 675 |
+
"learning_rate": 8.297973940695163e-05,
|
| 676 |
+
"epoch": 1.1548223350253808,
|
| 677 |
+
"step": 910
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"loss": 0.0349,
|
| 681 |
+
"grad_norm": 0.18907427787780762,
|
| 682 |
+
"learning_rate": 8.091566708195786e-05,
|
| 683 |
+
"epoch": 1.16751269035533,
|
| 684 |
+
"step": 920
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"loss": 0.0336,
|
| 688 |
+
"grad_norm": 0.24296258389949799,
|
| 689 |
+
"learning_rate": 7.885999935968982e-05,
|
| 690 |
+
"epoch": 1.1802030456852792,
|
| 691 |
+
"step": 930
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"loss": 0.0372,
|
| 695 |
+
"grad_norm": 0.1817648708820343,
|
| 696 |
+
"learning_rate": 7.681364154140264e-05,
|
| 697 |
+
"epoch": 1.1928934010152283,
|
| 698 |
+
"step": 940
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"eval_loss": 0.057017017155885696,
|
| 702 |
+
"eval_runtime": 19.9628,
|
| 703 |
+
"eval_samples_per_second": 66.474,
|
| 704 |
+
"eval_steps_per_second": 16.631,
|
| 705 |
+
"epoch": 1.1954314720812182,
|
| 706 |
+
"step": 942
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"loss": 0.03,
|
| 710 |
+
"grad_norm": 0.19095705449581146,
|
| 711 |
+
"learning_rate": 7.47774948283366e-05,
|
| 712 |
+
"epoch": 1.2055837563451777,
|
| 713 |
+
"step": 950
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"loss": 0.035,
|
| 717 |
+
"grad_norm": 0.33682745695114136,
|
| 718 |
+
"learning_rate": 7.275245592483492e-05,
|
| 719 |
+
"epoch": 1.218274111675127,
|
| 720 |
+
"step": 960
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"loss": 0.0384,
|
| 724 |
+
"grad_norm": 0.2646084427833557,
|
| 725 |
+
"learning_rate": 7.073941664344152e-05,
|
| 726 |
+
"epoch": 1.2309644670050761,
|
| 727 |
+
"step": 970
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"loss": 0.0287,
|
| 731 |
+
"grad_norm": 0.1980791836977005,
|
| 732 |
+
"learning_rate": 6.873926351215312e-05,
|
| 733 |
+
"epoch": 1.2436548223350254,
|
| 734 |
+
"step": 980
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"loss": 0.0342,
|
| 738 |
+
"grad_norm": 0.18797655403614044,
|
| 739 |
+
"learning_rate": 6.67528773839989e-05,
|
| 740 |
+
"epoch": 1.2563451776649746,
|
| 741 |
+
"step": 990
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"loss": 0.0337,
|
| 745 |
+
"grad_norm": 0.24009937047958374,
|
| 746 |
+
"learning_rate": 6.478113304911886e-05,
|
| 747 |
+
"epoch": 1.2690355329949239,
|
| 748 |
+
"step": 1000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"loss": 0.0272,
|
| 752 |
+
"grad_norm": 0.29159170389175415,
|
| 753 |
+
"learning_rate": 6.282489884951295e-05,
|
| 754 |
+
"epoch": 1.281725888324873,
|
| 755 |
+
"step": 1010
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"loss": 0.036,
|
| 759 |
+
"grad_norm": 0.16352516412734985,
|
| 760 |
+
"learning_rate": 6.0885036296629064e-05,
|
| 761 |
+
"epoch": 1.2944162436548223,
|
| 762 |
+
"step": 1020
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"loss": 0.0292,
|
| 766 |
+
"grad_norm": 0.17807820439338684,
|
| 767 |
+
"learning_rate": 5.896239969195994e-05,
|
| 768 |
+
"epoch": 1.3071065989847717,
|
| 769 |
+
"step": 1030
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"loss": 0.0332,
|
| 773 |
+
"grad_norm": 0.2500491738319397,
|
| 774 |
+
"learning_rate": 5.7057835750814867e-05,
|
| 775 |
+
"epoch": 1.3197969543147208,
|
| 776 |
+
"step": 1040
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"loss": 0.0294,
|
| 780 |
+
"grad_norm": 0.2208271473646164,
|
| 781 |
+
"learning_rate": 5.517218322943224e-05,
|
| 782 |
+
"epoch": 1.33248730964467,
|
| 783 |
+
"step": 1050
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"loss": 0.0342,
|
| 787 |
+
"grad_norm": 0.23927471041679382,
|
| 788 |
+
"learning_rate": 5.3306272555597504e-05,
|
| 789 |
+
"epoch": 1.3451776649746192,
|
| 790 |
+
"step": 1060
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"loss": 0.0307,
|
| 794 |
+
"grad_norm": 0.20309758186340332,
|
| 795 |
+
"learning_rate": 5.1460925462928546e-05,
|
| 796 |
+
"epoch": 1.3578680203045685,
|
| 797 |
+
"step": 1070
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"loss": 0.0314,
|
| 801 |
+
"grad_norm": 0.23275193572044373,
|
| 802 |
+
"learning_rate": 4.96369546289904e-05,
|
| 803 |
+
"epoch": 1.3705583756345177,
|
| 804 |
+
"step": 1080
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"loss": 0.0333,
|
| 808 |
+
"grad_norm": 0.2078331708908081,
|
| 809 |
+
"learning_rate": 4.783516331739769e-05,
|
| 810 |
+
"epoch": 1.383248730964467,
|
| 811 |
+
"step": 1090
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"eval_loss": 0.05335332825779915,
|
| 815 |
+
"eval_runtime": 19.9859,
|
| 816 |
+
"eval_samples_per_second": 66.397,
|
| 817 |
+
"eval_steps_per_second": 16.612,
|
| 818 |
+
"epoch": 1.3946700507614214,
|
| 819 |
+
"step": 1099
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"loss": 0.0309,
|
| 823 |
+
"grad_norm": 0.18032079935073853,
|
| 824 |
+
"learning_rate": 4.605634502406321e-05,
|
| 825 |
+
"epoch": 1.3959390862944163,
|
| 826 |
+
"step": 1100
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"loss": 0.0328,
|
| 830 |
+
"grad_norm": 0.20803005993366241,
|
| 831 |
+
"learning_rate": 4.430128312774804e-05,
|
| 832 |
+
"epoch": 1.4086294416243654,
|
| 833 |
+
"step": 1110
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"loss": 0.027,
|
| 837 |
+
"grad_norm": 0.1680465191602707,
|
| 838 |
+
"learning_rate": 4.2570750545067076e-05,
|
| 839 |
+
"epoch": 1.4213197969543148,
|
| 840 |
+
"step": 1120
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"loss": 0.0317,
|
| 844 |
+
"grad_norm": 0.2528463900089264,
|
| 845 |
+
"learning_rate": 4.086550939010227e-05,
|
| 846 |
+
"epoch": 1.434010152284264,
|
| 847 |
+
"step": 1130
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"loss": 0.0313,
|
| 851 |
+
"grad_norm": 0.19024434685707092,
|
| 852 |
+
"learning_rate": 3.9186310638773047e-05,
|
| 853 |
+
"epoch": 1.4467005076142132,
|
| 854 |
+
"step": 1140
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"loss": 0.0287,
|
| 858 |
+
"grad_norm": 0.20934472978115082,
|
| 859 |
+
"learning_rate": 3.753389379811185e-05,
|
| 860 |
+
"epoch": 1.4593908629441623,
|
| 861 |
+
"step": 1150
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"loss": 0.0265,
|
| 865 |
+
"grad_norm": 0.29412180185317993,
|
| 866 |
+
"learning_rate": 3.590898658059062e-05,
|
| 867 |
+
"epoch": 1.4720812182741116,
|
| 868 |
+
"step": 1160
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"loss": 0.0298,
|
| 872 |
+
"grad_norm": 0.3268195390701294,
|
| 873 |
+
"learning_rate": 3.4312304583641484e-05,
|
| 874 |
+
"epoch": 1.484771573604061,
|
| 875 |
+
"step": 1170
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"loss": 0.0251,
|
| 879 |
+
"grad_norm": 0.17332251369953156,
|
| 880 |
+
"learning_rate": 3.274455097451269e-05,
|
| 881 |
+
"epoch": 1.49746192893401,
|
| 882 |
+
"step": 1180
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"loss": 0.0318,
|
| 886 |
+
"grad_norm": 0.3481772541999817,
|
| 887 |
+
"learning_rate": 3.1206416180598995e-05,
|
| 888 |
+
"epoch": 1.5101522842639594,
|
| 889 |
+
"step": 1190
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"loss": 0.0335,
|
| 893 |
+
"grad_norm": 0.24047453701496124,
|
| 894 |
+
"learning_rate": 2.9698577585382282e-05,
|
| 895 |
+
"epoch": 1.5228426395939088,
|
| 896 |
+
"step": 1200
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"loss": 0.0339,
|
| 900 |
+
"grad_norm": 0.21146714687347412,
|
| 901 |
+
"learning_rate": 2.8221699230116793e-05,
|
| 902 |
+
"epoch": 1.5355329949238579,
|
| 903 |
+
"step": 1210
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"loss": 0.0308,
|
| 907 |
+
"grad_norm": 0.140832781791687,
|
| 908 |
+
"learning_rate": 2.67764315213902e-05,
|
| 909 |
+
"epoch": 1.548223350253807,
|
| 910 |
+
"step": 1220
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"loss": 0.026,
|
| 914 |
+
"grad_norm": 0.1721792370080948,
|
| 915 |
+
"learning_rate": 2.536341094468906e-05,
|
| 916 |
+
"epoch": 1.5609137055837563,
|
| 917 |
+
"step": 1230
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"loss": 0.0277,
|
| 921 |
+
"grad_norm": 0.14980490505695343,
|
| 922 |
+
"learning_rate": 2.398325978409539e-05,
|
| 923 |
+
"epoch": 1.5736040609137056,
|
| 924 |
+
"step": 1240
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"loss": 0.028,
|
| 928 |
+
"grad_norm": 0.18908673524856567,
|
| 929 |
+
"learning_rate": 2.263658584823717e-05,
|
| 930 |
+
"epoch": 1.5862944162436547,
|
| 931 |
+
"step": 1250
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"eval_loss": 0.052472274750471115,
|
| 935 |
+
"eval_runtime": 19.9786,
|
| 936 |
+
"eval_samples_per_second": 66.421,
|
| 937 |
+
"eval_steps_per_second": 16.618,
|
| 938 |
+
"epoch": 1.5939086294416245,
|
| 939 |
+
"step": 1256
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"loss": 0.0272,
|
| 943 |
+
"grad_norm": 0.12164825201034546,
|
| 944 |
+
"learning_rate": 2.1323982202613735e-05,
|
| 945 |
+
"epoch": 1.598984771573604,
|
| 946 |
+
"step": 1260
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"loss": 0.0245,
|
| 950 |
+
"grad_norm": 0.2658851146697998,
|
| 951 |
+
"learning_rate": 2.004602690841414e-05,
|
| 952 |
+
"epoch": 1.6116751269035534,
|
| 953 |
+
"step": 1270
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"loss": 0.0304,
|
| 957 |
+
"grad_norm": 0.2891974151134491,
|
| 958 |
+
"learning_rate": 1.8803282767942954e-05,
|
| 959 |
+
"epoch": 1.6243654822335025,
|
| 960 |
+
"step": 1280
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"loss": 0.0292,
|
| 964 |
+
"grad_norm": 0.2979351580142975,
|
| 965 |
+
"learning_rate": 1.7596297076766455e-05,
|
| 966 |
+
"epoch": 1.6370558375634516,
|
| 967 |
+
"step": 1290
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"loss": 0.0284,
|
| 971 |
+
"grad_norm": 0.20141719281673431,
|
| 972 |
+
"learning_rate": 1.6425601382687405e-05,
|
| 973 |
+
"epoch": 1.649746192893401,
|
| 974 |
+
"step": 1300
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"loss": 0.0254,
|
| 978 |
+
"grad_norm": 0.1950131356716156,
|
| 979 |
+
"learning_rate": 1.5291711251655316e-05,
|
| 980 |
+
"epoch": 1.6624365482233503,
|
| 981 |
+
"step": 1310
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"loss": 0.0282,
|
| 985 |
+
"grad_norm": 0.21205022931098938,
|
| 986 |
+
"learning_rate": 1.41951260407149e-05,
|
| 987 |
+
"epoch": 1.6751269035532994,
|
| 988 |
+
"step": 1320
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"loss": 0.0247,
|
| 992 |
+
"grad_norm": 0.2470894753932953,
|
| 993 |
+
"learning_rate": 1.3136328678092746e-05,
|
| 994 |
+
"epoch": 1.6878172588832487,
|
| 995 |
+
"step": 1330
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"loss": 0.0257,
|
| 999 |
+
"grad_norm": 0.26378998160362244,
|
| 1000 |
+
"learning_rate": 1.2115785450519434e-05,
|
| 1001 |
+
"epoch": 1.700507614213198,
|
| 1002 |
+
"step": 1340
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"loss": 0.0282,
|
| 1006 |
+
"grad_norm": 0.12680888175964355,
|
| 1007 |
+
"learning_rate": 1.1133945797879908e-05,
|
| 1008 |
+
"epoch": 1.7131979695431472,
|
| 1009 |
+
"step": 1350
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"loss": 0.0251,
|
| 1013 |
+
"grad_norm": 0.19744935631752014,
|
| 1014 |
+
"learning_rate": 1.019124211528365e-05,
|
| 1015 |
+
"epoch": 1.7258883248730963,
|
| 1016 |
+
"step": 1360
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"loss": 0.0327,
|
| 1020 |
+
"grad_norm": 0.18419434130191803,
|
| 1021 |
+
"learning_rate": 9.288089562640844e-06,
|
| 1022 |
+
"epoch": 1.7385786802030458,
|
| 1023 |
+
"step": 1370
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"loss": 0.0282,
|
| 1027 |
+
"grad_norm": 0.19115136563777924,
|
| 1028 |
+
"learning_rate": 8.42488588182897e-06,
|
| 1029 |
+
"epoch": 1.751269035532995,
|
| 1030 |
+
"step": 1380
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"loss": 0.0245,
|
| 1034 |
+
"grad_norm": 0.17252641916275024,
|
| 1035 |
+
"learning_rate": 7.602011221530236e-06,
|
| 1036 |
+
"epoch": 1.763959390862944,
|
| 1037 |
+
"step": 1390
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"loss": 0.029,
|
| 1041 |
+
"grad_norm": 0.22253695130348206,
|
| 1042 |
+
"learning_rate": 6.819827969816661e-06,
|
| 1043 |
+
"epoch": 1.7766497461928934,
|
| 1044 |
+
"step": 1400
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"loss": 0.0269,
|
| 1048 |
+
"grad_norm": 0.21938475966453552,
|
| 1049 |
+
"learning_rate": 6.078680594557163e-06,
|
| 1050 |
+
"epoch": 1.7893401015228427,
|
| 1051 |
+
"step": 1410
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"eval_loss": 0.05091211572289467,
|
| 1055 |
+
"eval_runtime": 20.0145,
|
| 1056 |
+
"eval_samples_per_second": 66.302,
|
| 1057 |
+
"eval_steps_per_second": 16.588,
|
| 1058 |
+
"epoch": 1.7931472081218274,
|
| 1059 |
+
"step": 1413
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"loss": 0.0305,
|
| 1063 |
+
"grad_norm": 0.2024271935224533,
|
| 1064 |
+
"learning_rate": 5.378895491716285e-06,
|
| 1065 |
+
"epoch": 1.8020304568527918,
|
| 1066 |
+
"step": 1420
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"loss": 0.029,
|
| 1070 |
+
"grad_norm": 0.22723488509655,
|
| 1071 |
+
"learning_rate": 4.720780841611738e-06,
|
| 1072 |
+
"epoch": 1.8147208121827412,
|
| 1073 |
+
"step": 1430
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"loss": 0.0266,
|
| 1077 |
+
"grad_norm": 0.2747625410556793,
|
| 1078 |
+
"learning_rate": 4.104626473194151e-06,
|
| 1079 |
+
"epoch": 1.8274111675126905,
|
| 1080 |
+
"step": 1440
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"loss": 0.0262,
|
| 1084 |
+
"grad_norm": 0.18593831360340118,
|
| 1085 |
+
"learning_rate": 3.5307037364083253e-06,
|
| 1086 |
+
"epoch": 1.8401015228426396,
|
| 1087 |
+
"step": 1450
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"loss": 0.0291,
|
| 1091 |
+
"grad_norm": 0.2651998996734619,
|
| 1092 |
+
"learning_rate": 2.9992653826927508e-06,
|
| 1093 |
+
"epoch": 1.8527918781725887,
|
| 1094 |
+
"step": 1460
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"loss": 0.026,
|
| 1098 |
+
"grad_norm": 0.19439752399921417,
|
| 1099 |
+
"learning_rate": 2.510545453669744e-06,
|
| 1100 |
+
"epoch": 1.865482233502538,
|
| 1101 |
+
"step": 1470
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"loss": 0.03,
|
| 1105 |
+
"grad_norm": 0.17483021318912506,
|
| 1106 |
+
"learning_rate": 2.06475917807506e-06,
|
| 1107 |
+
"epoch": 1.8781725888324874,
|
| 1108 |
+
"step": 1480
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"loss": 0.029,
|
| 1112 |
+
"grad_norm": 0.22444817423820496,
|
| 1113 |
+
"learning_rate": 1.662102876972882e-06,
|
| 1114 |
+
"epoch": 1.8908629441624365,
|
| 1115 |
+
"step": 1490
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"loss": 0.0243,
|
| 1119 |
+
"grad_norm": 0.17885605990886688,
|
| 1120 |
+
"learning_rate": 1.3027538772973026e-06,
|
| 1121 |
+
"epoch": 1.9035532994923858,
|
| 1122 |
+
"step": 1500
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"loss": 0.0272,
|
| 1126 |
+
"grad_norm": 0.19312232732772827,
|
| 1127 |
+
"learning_rate": 9.868704337588797e-07,
|
| 1128 |
+
"epoch": 1.9162436548223352,
|
| 1129 |
+
"step": 1510
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"loss": 0.0254,
|
| 1133 |
+
"grad_norm": 0.1709776520729065,
|
| 1134 |
+
"learning_rate": 7.145916591504098e-07,
|
| 1135 |
+
"epoch": 1.9289340101522843,
|
| 1136 |
+
"step": 1520
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"loss": 0.0252,
|
| 1140 |
+
"grad_norm": 0.18656505644321442,
|
| 1141 |
+
"learning_rate": 4.860374630826004e-07,
|
| 1142 |
+
"epoch": 1.9416243654822334,
|
| 1143 |
+
"step": 1530
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"loss": 0.0267,
|
| 1147 |
+
"grad_norm": 0.11956395953893661,
|
| 1148 |
+
"learning_rate": 3.0130849917681114e-07,
|
| 1149 |
+
"epoch": 1.9543147208121827,
|
| 1150 |
+
"step": 1540
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"loss": 0.0305,
|
| 1154 |
+
"grad_norm": 0.25038954615592957,
|
| 1155 |
+
"learning_rate": 1.604861207378794e-07,
|
| 1156 |
+
"epoch": 1.967005076142132,
|
| 1157 |
+
"step": 1550
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"loss": 0.025,
|
| 1161 |
+
"grad_norm": 0.19318363070487976,
|
| 1162 |
+
"learning_rate": 6.363234492674507e-08,
|
| 1163 |
+
"epoch": 1.9796954314720812,
|
| 1164 |
+
"step": 1560
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"loss": 0.0276,
|
| 1168 |
+
"grad_norm": 0.26012641191482544,
|
| 1169 |
+
"learning_rate": 1.0789825448476177e-08,
|
| 1170 |
+
"epoch": 1.9923857868020305,
|
| 1171 |
+
"step": 1570
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"eval_loss": 0.0504293330013752,
|
| 1175 |
+
"eval_runtime": 19.8337,
|
| 1176 |
+
"eval_samples_per_second": 66.906,
|
| 1177 |
+
"eval_steps_per_second": 16.739,
|
| 1178 |
+
"epoch": 1.9923857868020305,
|
| 1179 |
+
"step": 1570
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"train_runtime": 2681.8444,
|
| 1183 |
+
"train_samples_per_second": 18.795,
|
| 1184 |
+
"train_steps_per_second": 0.588,
|
| 1185 |
+
"total_flos": 6.800278675429786e+17,
|
| 1186 |
+
"train_loss": 0.06838441643920647,
|
| 1187 |
+
"epoch": 2.0,
|
| 1188 |
+
"step": 1576
|
| 1189 |
+
}
|
| 1190 |
+
]
|
train/training_loss.png
ADDED
|
train/validation_loss.png
ADDED
|