tejeshbhalla commited on
Commit
afdb73d
·
verified ·
1 Parent(s): b149046

Training in progress, step 10

Browse files
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "/root/dataDisk/output/v6-20250221-094059/checkpoint-110-merged",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
@@ -23,13 +23,10 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "v_proj",
27
- "k_proj",
28
  "down_proj",
29
- "o_proj",
30
- "q_proj",
31
- "up_proj",
32
- "gate_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/highspeedstorage/ft-volume/phi",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "gate_up_proj",
 
27
  "down_proj",
28
+ "qkv_proj",
29
+ "o_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b0d3c6fc7aa2e57da3d298cbb80eaa3c31d50160c0cf0d6b1cb544eebe74c08
3
- size 13254157312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be34401892f440442a28a0bb352c3d933cc710ba519babbd8354891f6dc1e9c7
3
+ size 3565203280
args.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "model": "/root/dataDisk/output/v6-20250221-094059/checkpoint-110-merged",
3
- "model_type": "llama3_2",
4
  "model_revision": null,
5
  "task_type": "causal_lm",
6
  "torch_dtype": "bfloat16",
@@ -9,12 +9,14 @@
9
  "rope_scaling": null,
10
  "device_map": null,
11
  "local_repo_path": null,
12
- "template": "llama3_2",
13
  "system": "",
14
- "max_length": 22000,
15
  "truncation_strategy": "left",
16
  "max_pixels": null,
17
  "tools_prompt": "react_en",
 
 
18
  "loss_scale": "default",
19
  "sequence_parallel_size": 1,
20
  "use_chat_template": true,
@@ -27,9 +29,11 @@
27
  "data_seed": 42,
28
  "dataset_num_proc": 1,
29
  "streaming": false,
30
- "load_from_cache_file": false,
31
  "download_mode": "reuse_dataset_if_exists",
 
32
  "strict": false,
 
33
  "model_name": [
34
  null,
35
  null
@@ -55,7 +59,8 @@
55
  "stream": false,
56
  "stop_words": [],
57
  "logprobs": false,
58
- "ckpt_dir": "/root/dataDisk/output/v6-20250221-094059/checkpoint-110-merged",
 
59
  "load_dataset_config": null,
60
  "lora_modules": [],
61
  "tuner_backend": "peft",
@@ -63,14 +68,14 @@
63
  "adapters": [],
64
  "seed": 42,
65
  "model_kwargs": {},
66
- "load_args": true,
67
  "load_data_args": false,
68
  "use_hf": true,
69
  "hub_token": null,
70
  "custom_register_path": [],
71
  "ignore_args_error": false,
72
  "use_swift_lora": false,
73
- "output_dir": "/root/dataDisk/output/v10-20250227-084327",
74
  "overwrite_output_dir": false,
75
  "do_train": false,
76
  "do_eval": false,
@@ -81,7 +86,7 @@
81
  "per_device_eval_batch_size": 1,
82
  "per_gpu_train_batch_size": null,
83
  "per_gpu_eval_batch_size": null,
84
- "gradient_accumulation_steps": 8,
85
  "eval_accumulation_steps": null,
86
  "eval_delay": 0,
87
  "torch_empty_cache_steps": null,
@@ -100,7 +105,7 @@
100
  "log_level": "passive",
101
  "log_level_replica": "warning",
102
  "log_on_each_node": true,
103
- "logging_dir": "/root/dataDisk/output/v10-20250227-084327/runs",
104
  "logging_strategy": "steps",
105
  "logging_first_step": true,
106
  "logging_steps": 1,
@@ -136,7 +141,6 @@
136
  "past_index": -1,
137
  "run_name": null,
138
  "disable_tqdm": null,
139
- "remove_unused_columns": false,
140
  "label_names": null,
141
  "load_best_model_at_end": false,
142
  "metric_for_best_model": "loss",
@@ -164,7 +168,7 @@
164
  "zero_optimization": {
165
  "stage": 3,
166
  "offload_optimizer": {
167
- "device": "none",
168
  "pin_memory": true
169
  },
170
  "offload_param": {
@@ -322,21 +326,29 @@
322
  "metric_warmup_step": 0,
323
  "fsdp_num": 1,
324
  "acc_steps": 1,
 
 
 
 
 
325
  "add_version": true,
326
  "resume_only_model": false,
327
  "check_model": true,
328
- "loss_type": null,
329
  "packing": false,
330
  "lazy_tokenize": false,
331
- "acc_strategy": "token",
 
332
  "optimizer": null,
333
  "metric": null,
 
334
  "rank": 0,
 
335
  "local_world_size": 8,
336
- "model_suffix": "checkpoint-110-merged",
337
- "model_info": "ModelInfo(model_type='llama3_2', model_dir='/root/dataDisk/output/v6-20250221-094059/checkpoint-110-merged', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, config={'factor': 8.0, 'high_freq_factor': 4.0, 'low_freq_factor': 1.0, 'original_max_position_embeddings': 8192, 'rope_type': 'llama3'}, task_type=None)",
338
- "model_meta": "ModelMeta(model_type='llama3_2', model_groups=[ModelGroup(models=[Model(ms_model_id='LLM-Research/Llama-3.2-1B', hf_model_id='meta-llama/Llama-3.2-1B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-3B', hf_model_id='meta-llama/Llama-3.2-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-1B-Instruct', hf_model_id='meta-llama/Llama-3.2-1B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-3B-Instruct', hf_model_id='meta-llama/Llama-3.2-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='LLM-Research/Llama-3.3-70B-Instruct', hf_model_id='meta-llama/Llama-3.3-70B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='unsloth/Llama-3.3-70B-Instruct-bnb-4bit', hf_model_id='unsloth/Llama-3.3-70B-Instruct-bnb-4bit', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='llama3_2', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f82ac0ea050>, model_arch='llama', architectures=['LlamaForCausalLM'], is_multimodal=False, additional_saved_files=[], torch_dtype=None, ignore_patterns=[], requires=['transformers>=4.45'], tags=[])",
339
- "model_dir": "/root/dataDisk/output/v6-20250221-094059/checkpoint-110-merged",
340
  "hub": "<class 'swift.hub.hub.HFHub'>",
341
- "training_args": "Seq2SeqTrainingArguments(output_dir='/root/dataDisk/output/v10-20250227-084327', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.LINEAR: 'linear'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/dataDisk/output/v10-20250227-084327/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=10, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=10, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/dataDisk/output/v10-20250227-084327', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'cpu', 'pin_memory': True}, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=True, resume_from_checkpoint=None, hub_model_id='TheAgenticAI/LLAMA-3.3-70B-Reasoning', hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=True, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': True}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='lora')"
342
  }
 
1
  {
2
+ "model": "/root/highspeedstorage/ft-volume/phi",
3
+ "model_type": "phi4",
4
  "model_revision": null,
5
  "task_type": "causal_lm",
6
  "torch_dtype": "bfloat16",
 
9
  "rope_scaling": null,
10
  "device_map": null,
11
  "local_repo_path": null,
12
+ "template": "phi4",
13
  "system": "",
14
+ "max_length": 15000,
15
  "truncation_strategy": "left",
16
  "max_pixels": null,
17
  "tools_prompt": "react_en",
18
+ "norm_bbox": null,
19
+ "padding_side": "right",
20
  "loss_scale": "default",
21
  "sequence_parallel_size": 1,
22
  "use_chat_template": true,
 
29
  "data_seed": 42,
30
  "dataset_num_proc": 1,
31
  "streaming": false,
32
+ "enable_cache": false,
33
  "download_mode": "reuse_dataset_if_exists",
34
+ "columns": {},
35
  "strict": false,
36
+ "remove_unused_columns": true,
37
  "model_name": [
38
  null,
39
  null
 
59
  "stream": false,
60
  "stop_words": [],
61
  "logprobs": false,
62
+ "top_logprobs": null,
63
+ "ckpt_dir": null,
64
  "load_dataset_config": null,
65
  "lora_modules": [],
66
  "tuner_backend": "peft",
 
68
  "adapters": [],
69
  "seed": 42,
70
  "model_kwargs": {},
71
+ "load_args": false,
72
  "load_data_args": false,
73
  "use_hf": true,
74
  "hub_token": null,
75
  "custom_register_path": [],
76
  "ignore_args_error": false,
77
  "use_swift_lora": false,
78
+ "output_dir": "/root/dataDisk/output/v15-20250301-174709",
79
  "overwrite_output_dir": false,
80
  "do_train": false,
81
  "do_eval": false,
 
86
  "per_device_eval_batch_size": 1,
87
  "per_gpu_train_batch_size": null,
88
  "per_gpu_eval_batch_size": null,
89
+ "gradient_accumulation_steps": 1,
90
  "eval_accumulation_steps": null,
91
  "eval_delay": 0,
92
  "torch_empty_cache_steps": null,
 
105
  "log_level": "passive",
106
  "log_level_replica": "warning",
107
  "log_on_each_node": true,
108
+ "logging_dir": "/root/dataDisk/output/v15-20250301-174709/runs",
109
  "logging_strategy": "steps",
110
  "logging_first_step": true,
111
  "logging_steps": 1,
 
141
  "past_index": -1,
142
  "run_name": null,
143
  "disable_tqdm": null,
 
144
  "label_names": null,
145
  "load_best_model_at_end": false,
146
  "metric_for_best_model": "loss",
 
168
  "zero_optimization": {
169
  "stage": 3,
170
  "offload_optimizer": {
171
+ "device": "cpu",
172
  "pin_memory": true
173
  },
174
  "offload_param": {
 
326
  "metric_warmup_step": 0,
327
  "fsdp_num": 1,
328
  "acc_steps": 1,
329
+ "swanlab_token": null,
330
+ "swanlab_project": null,
331
+ "swanlab_workspace": null,
332
+ "swanlab_exp_name": null,
333
+ "swanlab_mode": "cloud",
334
  "add_version": true,
335
  "resume_only_model": false,
336
  "check_model": true,
337
+ "create_checkpoint_symlink": false,
338
  "packing": false,
339
  "lazy_tokenize": false,
340
+ "external_plugins": [],
341
+ "loss_type": null,
342
  "optimizer": null,
343
  "metric": null,
344
+ "acc_strategy": "token",
345
  "rank": 0,
346
+ "global_world_size": 8,
347
  "local_world_size": 8,
348
+ "model_suffix": "phi",
349
+ "model_info": "ModelInfo(model_type='phi4', model_dir='/root/highspeedstorage/ft-volume/phi', torch_dtype=torch.bfloat16, max_model_len=16384, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
350
+ "model_meta": "ModelMeta(model_type='phi4', model_groups=[ModelGroup(models=[Model(ms_model_id='LLM-Research/phi-4', hf_model_id='microsoft/phi-4', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='phi4', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f201dfdb760>, model_arch='phi3', architectures=['Phi3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.36'], tags=[])",
351
+ "model_dir": "/root/highspeedstorage/ft-volume/phi",
352
  "hub": "<class 'swift.hub.hub.HFHub'>",
353
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/root/dataDisk/output/v15-20250301-174709', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=1, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.LINEAR: 'linear'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/dataDisk/output/v15-20250301-174709/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=10, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=10, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/dataDisk/output/v15-20250301-174709', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'cpu', 'pin_memory': True}, 'offload_param': {'device': 'cpu', 'pin_memory': True}, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=True, resume_from_checkpoint=None, hub_model_id='TheAgenticAI/LLAMA-3.3-70B-Reasoning', hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=True, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': True}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='lora', optimizer=None, galore_config=None)"
354
  }
logging.jsonl CHANGED
@@ -1,48 +1,32 @@
1
- {"loss": 0.4179382, "token_acc": 0.88285797, "grad_norm": 0.10827466, "learning_rate": 4.2e-07, "memory(GiB)": 63.89, "train_speed(iter/s)": 0.007958, "epoch": 0.00428036, "global_step/max_steps": "1/233", "percentage": "0.43%", "elapsed_time": "1m 58s", "remaining_time": "7h 40m 6s"}
2
- {"loss": 0.41379014, "token_acc": 0.85089987, "grad_norm": 0.05916129, "learning_rate": 8.3e-07, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007782, "epoch": 0.00856073, "global_step/max_steps": "2/233", "percentage": "0.86%", "elapsed_time": "4m 10s", "remaining_time": "8h 1m 53s"}
3
- {"loss": 0.45721838, "token_acc": 0.84262007, "grad_norm": 0.07875115, "learning_rate": 1.25e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008616, "epoch": 0.01284109, "global_step/max_steps": "3/233", "percentage": "1.29%", "elapsed_time": "5m 41s", "remaining_time": "7h 16m 24s"}
4
- {"loss": 0.42563128, "token_acc": 0.85337859, "grad_norm": 0.06428441, "learning_rate": 1.67e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.009438, "epoch": 0.01712146, "global_step/max_steps": "4/233", "percentage": "1.72%", "elapsed_time": "6m 57s", "remaining_time": "6h 38m 1s"}
5
- {"loss": 0.41374671, "token_acc": 0.86648579, "grad_norm": 0.06986246, "learning_rate": 2.08e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.010567, "epoch": 0.02140182, "global_step/max_steps": "5/233", "percentage": "2.15%", "elapsed_time": "7m 46s", "remaining_time": "5h 54m 32s"}
6
- {"loss": 0.43779808, "token_acc": 0.88343834, "grad_norm": 0.2552028, "learning_rate": 2.5e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.011222, "epoch": 0.02568218, "global_step/max_steps": "6/233", "percentage": "2.58%", "elapsed_time": "8m 47s", "remaining_time": "5h 32m 55s"}
7
- {"loss": 0.36451226, "token_acc": 0.9184565, "grad_norm": 0.06735256, "learning_rate": 2.92e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.011306, "epoch": 0.02996255, "global_step/max_steps": "7/233", "percentage": "3.00%", "elapsed_time": "10m 12s", "remaining_time": "5h 29m 34s"}
8
- {"loss": 0.44302452, "token_acc": 0.86073043, "grad_norm": 0.07273346, "learning_rate": 3.33e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.011192, "epoch": 0.03424291, "global_step/max_steps": "8/233", "percentage": "3.43%", "elapsed_time": "11m 48s", "remaining_time": "5h 31m 56s"}
9
- {"loss": 0.39761364, "token_acc": 0.8669034, "grad_norm": 0.06864315, "learning_rate": 3.75e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.011185, "epoch": 0.03852327, "global_step/max_steps": "9/233", "percentage": "3.86%", "elapsed_time": "13m 17s", "remaining_time": "5h 31m 0s"}
10
- {"loss": 0.43125862, "token_acc": 0.86674636, "grad_norm": 0.07020264, "learning_rate": 4.17e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.010729, "epoch": 0.04280364, "global_step/max_steps": "10/233", "percentage": "4.29%", "elapsed_time": "15m 25s", "remaining_time": "5h 43m 57s"}
11
- {"eval_loss": 0.40895963, "eval_token_acc": 0.85351903, "eval_runtime": 227.761, "eval_samples_per_second": 2.028, "eval_steps_per_second": 0.255, "epoch": 0.04280364, "global_step/max_steps": "10/233", "percentage": "4.29%", "elapsed_time": "19m 13s", "remaining_time": "7h 8m 36s"}
12
- {"loss": 0.48655376, "token_acc": 0.85153433, "grad_norm": 0.06110121, "learning_rate": 4.58e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.00799, "epoch": 0.047084, "global_step/max_steps": "11/233", "percentage": "4.72%", "elapsed_time": "22m 49s", "remaining_time": "7h 40m 48s"}
13
- {"loss": 0.40591419, "token_acc": 0.83642537, "grad_norm": 0.0714484, "learning_rate": 5e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008281, "epoch": 0.05136437, "global_step/max_steps": "12/233", "percentage": "5.15%", "elapsed_time": "24m 2s", "remaining_time": "7h 22m 45s"}
14
- {"loss": 0.44814104, "token_acc": 0.8389717, "grad_norm": 0.10586874, "learning_rate": 5.42e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.0084, "epoch": 0.05564473, "global_step/max_steps": "13/233", "percentage": "5.58%", "elapsed_time": "25m 41s", "remaining_time": "7h 14m 38s"}
15
- {"loss": 0.44621539, "token_acc": 0.88370314, "grad_norm": 0.07920404, "learning_rate": 5.83e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008328, "epoch": 0.05992509, "global_step/max_steps": "14/233", "percentage": "6.01%", "elapsed_time": "27m 54s", "remaining_time": "7h 16m 33s"}
16
- {"loss": 0.4110747, "token_acc": 0.91004475, "grad_norm": 0.16680683, "learning_rate": 6.25e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.00861, "epoch": 0.06420546, "global_step/max_steps": "15/233", "percentage": "6.44%", "elapsed_time": "28m 55s", "remaining_time": "7h 0m 22s"}
17
- {"loss": 0.40049636, "token_acc": 0.86266531, "grad_norm": 0.06213977, "learning_rate": 6.67e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008743, "epoch": 0.06848582, "global_step/max_steps": "16/233", "percentage": "6.87%", "elapsed_time": "30m 23s", "remaining_time": "6h 52m 10s"}
18
- {"loss": 0.44190305, "token_acc": 0.92750822, "grad_norm": 0.11570669, "learning_rate": 7.08e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008653, "epoch": 0.07276619, "global_step/max_steps": "17/233", "percentage": "7.30%", "elapsed_time": "32m 38s", "remaining_time": "6h 54m 38s"}
19
- {"loss": 0.3522746, "token_acc": 0.86087783, "grad_norm": 0.06850542, "learning_rate": 7.5e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.00869, "epoch": 0.07704655, "global_step/max_steps": "18/233", "percentage": "7.73%", "elapsed_time": "34m 24s", "remaining_time": "6h 51m 1s"}
20
- {"loss": 0.44357687, "token_acc": 0.84940076, "grad_norm": 0.06938745, "learning_rate": 7.92e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008753, "epoch": 0.08132691, "global_step/max_steps": "19/233", "percentage": "8.15%", "elapsed_time": "36m 4s", "remaining_time": "6h 46m 13s"}
21
- {"loss": 0.51861739, "token_acc": 0.848673, "grad_norm": 0.06488414, "learning_rate": 8.33e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008439, "epoch": 0.08560728, "global_step/max_steps": "20/233", "percentage": "8.58%", "elapsed_time": "39m 23s", "remaining_time": "6h 59m 29s"}
22
- {"eval_loss": 0.40213868, "eval_token_acc": 0.85390327, "eval_runtime": 226.6588, "eval_samples_per_second": 2.038, "eval_steps_per_second": 0.256, "epoch": 0.08560728, "global_step/max_steps": "20/233", "percentage": "8.58%", "elapsed_time": "43m 9s", "remaining_time": "7h 39m 43s"}
23
- {"loss": 0.43199539, "token_acc": 0.86117205, "grad_norm": 0.05164209, "learning_rate": 8.75e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007537, "epoch": 0.08988764, "global_step/max_steps": "21/233", "percentage": "9.01%", "elapsed_time": "46m 19s", "remaining_time": "7h 47m 41s"}
24
- {"loss": 0.40631753, "token_acc": 0.88783023, "grad_norm": 0.0736868, "learning_rate": 9.17e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007714, "epoch": 0.094168, "global_step/max_steps": "22/233", "percentage": "9.44%", "elapsed_time": "47m 25s", "remaining_time": "7h 34m 50s"}
25
- {"loss": 0.43007508, "token_acc": 0.84537907, "grad_norm": 0.07760287, "learning_rate": 9.58e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007856, "epoch": 0.09844837, "global_step/max_steps": "23/233", "percentage": "9.87%", "elapsed_time": "48m 40s", "remaining_time": "7h 24m 29s"}
26
- {"loss": 0.4541401, "token_acc": 0.90728287, "grad_norm": 0.07906581, "learning_rate": 1e-05, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007919, "epoch": 0.10272873, "global_step/max_steps": "24/233", "percentage": "10.30%", "elapsed_time": "50m 23s", "remaining_time": "7h 18m 52s"}
27
- {"loss": 0.40432471, "token_acc": 0.88812693, "grad_norm": 0.06518858, "learning_rate": 9.95e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008004, "epoch": 0.1070091, "global_step/max_steps": "25/233", "percentage": "10.73%", "elapsed_time": "51m 56s", "remaining_time": "7h 12m 11s"}
28
- {"loss": 0.39950103, "token_acc": 0.8830859, "grad_norm": 0.07344344, "learning_rate": 9.9e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008126, "epoch": 0.11128946, "global_step/max_steps": "26/233", "percentage": "11.16%", "elapsed_time": "53m 12s", "remaining_time": "7h 3m 39s"}
29
- {"loss": 0.40415633, "token_acc": 0.88295608, "grad_norm": 0.06576811, "learning_rate": 9.86e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008217, "epoch": 0.11556982, "global_step/max_steps": "27/233", "percentage": "11.59%", "elapsed_time": "54m 39s", "remaining_time": "6h 57m 0s"}
30
- {"loss": 0.42902291, "token_acc": 0.9096094, "grad_norm": 0.0687621, "learning_rate": 9.81e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008314, "epoch": 0.11985019, "global_step/max_steps": "28/233", "percentage": "12.02%", "elapsed_time": "56m 1s", "remaining_time": "6h 50m 7s"}
31
- {"loss": 0.41589683, "token_acc": 0.90562369, "grad_norm": 0.15414927, "learning_rate": 9.76e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008366, "epoch": 0.12413055, "global_step/max_steps": "29/233", "percentage": "12.45%", "elapsed_time": "57m 39s", "remaining_time": "6h 45m 36s"}
32
- {"loss": 0.38500765, "token_acc": 0.86961207, "grad_norm": 0.11320223, "learning_rate": 9.71e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008501, "epoch": 0.12841091, "global_step/max_steps": "30/233", "percentage": "12.88%", "elapsed_time": "58m 42s", "remaining_time": "6h 37m 14s"}
33
- {"eval_loss": 0.39565024, "eval_token_acc": 0.85503138, "eval_runtime": 226.8071, "eval_samples_per_second": 2.037, "eval_steps_per_second": 0.256, "epoch": 0.12841091, "global_step/max_steps": "30/233", "percentage": "12.88%", "elapsed_time": "1h 2m 29s", "remaining_time": "7h 2m 49s"}
34
- {"loss": 0.45793277, "token_acc": 0.85833734, "grad_norm": 0.06815999, "learning_rate": 9.67e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007862, "epoch": 0.13269128, "global_step/max_steps": "31/233", "percentage": "13.30%", "elapsed_time": "1h 5m 36s", "remaining_time": "7h 7m 29s"}
35
- {"loss": 0.42956412, "token_acc": 0.85953068, "grad_norm": 0.06743568, "learning_rate": 9.62e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007809, "epoch": 0.13697164, "global_step/max_steps": "32/233", "percentage": "13.73%", "elapsed_time": "1h 8m 11s", "remaining_time": "7h 8m 16s"}
36
- {"loss": 0.42277759, "token_acc": 0.86786451, "grad_norm": 0.07200071, "learning_rate": 9.57e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007834, "epoch": 0.14125201, "global_step/max_steps": "33/233", "percentage": "14.16%", "elapsed_time": "1h 10m 5s", "remaining_time": "7h 4m 50s"}
37
- {"loss": 0.36818027, "token_acc": 0.84394063, "grad_norm": 0.07575763, "learning_rate": 9.52e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007918, "epoch": 0.14553237, "global_step/max_steps": "34/233", "percentage": "14.59%", "elapsed_time": "1h 11m 27s", "remaining_time": "6h 58m 13s"}
38
- {"loss": 0.45469719, "token_acc": 0.91506725, "grad_norm": 0.09796806, "learning_rate": 9.47e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.00799, "epoch": 0.14981273, "global_step/max_steps": "35/233", "percentage": "15.02%", "elapsed_time": "1h 12m 54s", "remaining_time": "6h 52m 24s"}
39
- {"loss": 0.41282824, "token_acc": 0.84009711, "grad_norm": 0.06105305, "learning_rate": 9.43e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007899, "epoch": 0.1540931, "global_step/max_steps": "36/233", "percentage": "15.45%", "elapsed_time": "1h 15m 50s", "remaining_time": "6h 55m 2s"}
40
- {"loss": 0.40039772, "token_acc": 0.8619093, "grad_norm": 0.06266245, "learning_rate": 9.38e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007932, "epoch": 0.15837346, "global_step/max_steps": "37/233", "percentage": "15.88%", "elapsed_time": "1h 17m 37s", "remaining_time": "6h 51m 14s"}
41
- {"loss": 0.38020378, "token_acc": 0.87047564, "grad_norm": 0.07132945, "learning_rate": 9.33e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008009, "epoch": 0.16265383, "global_step/max_steps": "38/233", "percentage": "16.31%", "elapsed_time": "1h 18m 58s", "remaining_time": "6h 45m 13s"}
42
- {"loss": 0.38574731, "token_acc": 0.89365221, "grad_norm": 0.06270806, "learning_rate": 9.28e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.008092, "epoch": 0.16693419, "global_step/max_steps": "39/233", "percentage": "16.74%", "elapsed_time": "1h 20m 12s", "remaining_time": "6h 39m 1s"}
43
- {"loss": 0.42370051, "token_acc": 0.85167778, "grad_norm": 0.11293414, "learning_rate": 9.23e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.00813, "epoch": 0.17121455, "global_step/max_steps": "40/233", "percentage": "17.17%", "elapsed_time": "1h 21m 53s", "remaining_time": "6h 35m 6s"}
44
- {"eval_loss": 0.3909784, "eval_token_acc": 0.85583679, "eval_runtime": 226.762, "eval_samples_per_second": 2.037, "eval_steps_per_second": 0.256, "epoch": 0.17121455, "global_step/max_steps": "40/233", "percentage": "17.17%", "elapsed_time": "1h 25m 40s", "remaining_time": "6h 53m 20s"}
45
- {"loss": 0.40064281, "token_acc": 0.85875383, "grad_norm": 0.07210004, "learning_rate": 9.19e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007676, "epoch": 0.17549492, "global_step/max_steps": "41/233", "percentage": "17.60%", "elapsed_time": "1h 28m 54s", "remaining_time": "6h 56m 20s"}
46
- {"loss": 0.41132563, "token_acc": 0.86075278, "grad_norm": 0.13976674, "learning_rate": 9.14e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007708, "epoch": 0.17977528, "global_step/max_steps": "42/233", "percentage": "18.03%", "elapsed_time": "1h 30m 42s", "remaining_time": "6h 52m 30s"}
47
- {"loss": 0.41642624, "token_acc": 0.87107902, "grad_norm": 0.05876919, "learning_rate": 9.09e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.00774, "epoch": 0.18405564, "global_step/max_steps": "43/233", "percentage": "18.45%", "elapsed_time": "1h 32m 28s", "remaining_time": "6h 48m 37s"}
48
- {"loss": 0.42396358, "token_acc": 0.85352622, "grad_norm": 0.05592595, "learning_rate": 9.04e-06, "memory(GiB)": 127.12, "train_speed(iter/s)": 0.007724, "epoch": 0.18833601, "global_step/max_steps": "44/233", "percentage": "18.88%", "elapsed_time": "1h 34m 49s", "remaining_time": "6h 47m 19s"}
 
1
+ {"loss": 0.93798834, "token_acc": 0.76758794, "grad_norm": 5.03938723, "learning_rate": 5e-08, "memory(GiB)": 8.05, "train_speed(iter/s)": 0.023691, "epoch": 0.00053505, "global_step/max_steps": "1/1869", "percentage": "0.05%", "elapsed_time": "12s", "remaining_time": "6h 35m 9s"}
2
+ {"loss": 0.92002016, "token_acc": 0.70787879, "grad_norm": 6.17990303, "learning_rate": 1.1e-07, "memory(GiB)": 13.83, "train_speed(iter/s)": 0.041561, "epoch": 0.00107009, "global_step/max_steps": "2/1869", "percentage": "0.11%", "elapsed_time": "18s", "remaining_time": "4h 49m 26s"}
3
+ {"loss": 0.93352824, "token_acc": 0.75027747, "grad_norm": 4.24871159, "learning_rate": 1.6e-07, "memory(GiB)": 13.83, "train_speed(iter/s)": 0.05581, "epoch": 0.00160514, "global_step/max_steps": "3/1869", "percentage": "0.16%", "elapsed_time": "24s", "remaining_time": "4h 11m 14s"}
4
+ {"loss": 0.97441375, "token_acc": 0.77185501, "grad_norm": 5.50236464, "learning_rate": 2.1e-07, "memory(GiB)": 15.32, "train_speed(iter/s)": 0.067326, "epoch": 0.00214018, "global_step/max_steps": "4/1869", "percentage": "0.21%", "elapsed_time": "29s", "remaining_time": "3h 52m 17s"}
5
+ {"loss": 0.86643094, "token_acc": 0.80839161, "grad_norm": 5.14204454, "learning_rate": 2.7e-07, "memory(GiB)": 15.32, "train_speed(iter/s)": 0.076809, "epoch": 0.00267523, "global_step/max_steps": "5/1869", "percentage": "0.27%", "elapsed_time": "35s", "remaining_time": "3h 41m 3s"}
6
+ {"loss": 0.88649535, "token_acc": 0.78010949, "grad_norm": 5.23055983, "learning_rate": 3.2e-07, "memory(GiB)": 15.87, "train_speed(iter/s)": 0.089255, "epoch": 0.00321027, "global_step/max_steps": "6/1869", "percentage": "0.32%", "elapsed_time": "37s", "remaining_time": "3h 15m 7s"}
7
+ {"loss": 0.92156661, "token_acc": 0.70940883, "grad_norm": 5.40514421, "learning_rate": 3.7e-07, "memory(GiB)": 16.45, "train_speed(iter/s)": 0.101701, "epoch": 0.00374532, "global_step/max_steps": "7/1869", "percentage": "0.37%", "elapsed_time": "39s", "remaining_time": "2h 54m 16s"}
8
+ {"loss": 0.94250065, "token_acc": 0.785, "grad_norm": 5.43437529, "learning_rate": 4.3e-07, "memory(GiB)": 16.45, "train_speed(iter/s)": 0.113564, "epoch": 0.00428036, "global_step/max_steps": "8/1869", "percentage": "0.43%", "elapsed_time": "40s", "remaining_time": "2h 38m 40s"}
9
+ {"loss": 0.94119352, "token_acc": 0.78978622, "grad_norm": 5.04455853, "learning_rate": 4.8e-07, "memory(GiB)": 16.45, "train_speed(iter/s)": 0.123471, "epoch": 0.00481541, "global_step/max_steps": "9/1869", "percentage": "0.48%", "elapsed_time": "43s", "remaining_time": "2h 29m 23s"}
10
+ {"loss": 0.89960265, "token_acc": 0.79014599, "grad_norm": 5.64693308, "learning_rate": 5.3e-07, "memory(GiB)": 16.45, "train_speed(iter/s)": 0.134192, "epoch": 0.00535045, "global_step/max_steps": "10/1869", "percentage": "0.54%", "elapsed_time": "45s", "remaining_time": "2h 19m 25s"}
11
+ {"eval_loss": 0.87941688, "eval_token_acc": 0.77941276, "eval_runtime": 47.0919, "eval_samples_per_second": 9.811, "eval_steps_per_second": 1.232, "epoch": 0.00535045, "global_step/max_steps": "10/1869", "percentage": "0.54%", "elapsed_time": "1m 32s", "remaining_time": "4h 45m 20s"}
12
+ {"loss": 0.78370821, "token_acc": 0.78277115, "grad_norm": 3.82993841, "learning_rate": 5.9e-07, "memory(GiB)": 42.26, "train_speed(iter/s)": 0.07966, "epoch": 0.0058855, "global_step/max_steps": "11/1869", "percentage": "0.59%", "elapsed_time": "1m 48s", "remaining_time": "5h 5m 38s"}
13
+ {"loss": 0.83504999, "token_acc": 0.76751592, "grad_norm": 4.17722225, "learning_rate": 6.4e-07, "memory(GiB)": 42.26, "train_speed(iter/s)": 0.083596, "epoch": 0.00642055, "global_step/max_steps": "12/1869", "percentage": "0.64%", "elapsed_time": "1m 54s", "remaining_time": "4h 54m 5s"}
14
+ {"loss": 0.95790565, "token_acc": 0.71612903, "grad_norm": 4.68048906, "learning_rate": 7e-07, "memory(GiB)": 42.26, "train_speed(iter/s)": 0.089234, "epoch": 0.00695559, "global_step/max_steps": "13/1869", "percentage": "0.70%", "elapsed_time": "1m 56s", "remaining_time": "4h 36m 24s"}
15
+ {"loss": 0.70565331, "token_acc": 0.84732824, "grad_norm": 3.35217595, "learning_rate": 7.5e-07, "memory(GiB)": 42.26, "train_speed(iter/s)": 0.092582, "epoch": 0.00749064, "global_step/max_steps": "14/1869", "percentage": "0.75%", "elapsed_time": "2m 1s", "remaining_time": "4h 28m 44s"}
16
+ {"loss": 0.81927258, "token_acc": 0.78723891, "grad_norm": 4.12418127, "learning_rate": 8e-07, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.095716, "epoch": 0.00802568, "global_step/max_steps": "15/1869", "percentage": "0.80%", "elapsed_time": "2m 7s", "remaining_time": "4h 22m 1s"}
17
+ {"loss": 0.7351442, "token_acc": 0.83187391, "grad_norm": 3.27488399, "learning_rate": 8.6e-07, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.101055, "epoch": 0.00856073, "global_step/max_steps": "16/1869", "percentage": "0.86%", "elapsed_time": "2m 8s", "remaining_time": "4h 8m 37s"}
18
+ {"loss": 0.77999592, "token_acc": 0.77183406, "grad_norm": 13.16994381, "learning_rate": 9.1e-07, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106293, "epoch": 0.00909577, "global_step/max_steps": "17/1869", "percentage": "0.91%", "elapsed_time": "2m 10s", "remaining_time": "3h 56m 47s"}
19
+ {"loss": 0.70006078, "token_acc": 0.85483871, "grad_norm": 3.84622741, "learning_rate": 9.6e-07, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111411, "epoch": 0.00963082, "global_step/max_steps": "18/1869", "percentage": "0.96%", "elapsed_time": "2m 12s", "remaining_time": "3h 46m 18s"}
20
+ {"loss": 0.69562626, "token_acc": 0.83034773, "grad_norm": 2.94428468, "learning_rate": 1.02e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.116139, "epoch": 0.01016586, "global_step/max_steps": "19/1869", "percentage": "1.02%", "elapsed_time": "2m 14s", "remaining_time": "3h 37m 35s"}
21
+ {"loss": 0.72194958, "token_acc": 0.74902975, "grad_norm": 2.36996722, "learning_rate": 1.07e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.119257, "epoch": 0.01070091, "global_step/max_steps": "20/1869", "percentage": "1.07%", "elapsed_time": "2m 18s", "remaining_time": "3h 32m 55s"}
22
+ {"eval_loss": 0.7312116, "eval_token_acc": 0.79288082, "eval_runtime": 47.2359, "eval_samples_per_second": 9.781, "eval_steps_per_second": 1.228, "epoch": 0.01070091, "global_step/max_steps": "20/1869", "percentage": "1.07%", "elapsed_time": "3m 5s", "remaining_time": "4h 45m 42s"}
23
+ {"loss": 0.70447195, "token_acc": 0.79690628, "grad_norm": 2.32526183, "learning_rate": 1.12e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.092843, "epoch": 0.01123596, "global_step/max_steps": "21/1869", "percentage": "1.12%", "elapsed_time": "3m 16s", "remaining_time": "4h 48m 26s"}
24
+ {"loss": 0.75664651, "token_acc": 0.78032037, "grad_norm": 2.3690176, "learning_rate": 1.18e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.094939, "epoch": 0.011771, "global_step/max_steps": "22/1869", "percentage": "1.18%", "elapsed_time": "3m 22s", "remaining_time": "4h 42m 56s"}
25
+ {"loss": 0.71143919, "token_acc": 0.77868852, "grad_norm": 1.86084819, "learning_rate": 1.23e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.096928, "epoch": 0.01230605, "global_step/max_steps": "23/1869", "percentage": "1.23%", "elapsed_time": "3m 27s", "remaining_time": "4h 37m 55s"}
26
+ {"loss": 0.57238525, "token_acc": 0.89502262, "grad_norm": 1.65031064, "learning_rate": 1.28e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.100248, "epoch": 0.01284109, "global_step/max_steps": "24/1869", "percentage": "1.28%", "elapsed_time": "3m 29s", "remaining_time": "4h 28m 55s"}
27
+ {"loss": 0.68685579, "token_acc": 0.79934211, "grad_norm": 2.21920037, "learning_rate": 1.34e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.103027, "epoch": 0.01337614, "global_step/max_steps": "25/1869", "percentage": "1.34%", "elapsed_time": "3m 33s", "remaining_time": "4h 22m 0s"}
28
+ {"loss": 0.67744565, "token_acc": 0.79525593, "grad_norm": 1.98912394, "learning_rate": 1.39e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106434, "epoch": 0.01391118, "global_step/max_steps": "26/1869", "percentage": "1.39%", "elapsed_time": "3m 34s", "remaining_time": "4h 13m 43s"}
29
+ {"loss": 0.60103244, "token_acc": 0.85245902, "grad_norm": 1.69945383, "learning_rate": 1.44e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.109795, "epoch": 0.01444623, "global_step/max_steps": "27/1869", "percentage": "1.44%", "elapsed_time": "3m 36s", "remaining_time": "4h 6m 2s"}
30
+ {"loss": 0.61611456, "token_acc": 0.88035639, "grad_norm": 1.65962636, "learning_rate": 1.5e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111339, "epoch": 0.01498127, "global_step/max_steps": "28/1869", "percentage": "1.50%", "elapsed_time": "3m 41s", "remaining_time": "4h 3m 14s"}
31
+ {"loss": 0.62859809, "token_acc": 0.80737705, "grad_norm": 1.79358125, "learning_rate": 1.55e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.114566, "epoch": 0.01551632, "global_step/max_steps": "29/1869", "percentage": "1.55%", "elapsed_time": "3m 43s", "remaining_time": "3h 56m 27s"}
32
+ {"loss": 0.56487948, "token_acc": 0.82064298, "grad_norm": 1.58352077, "learning_rate": 1.6e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.117766, "epoch": 0.01605136, "global_step/max_steps": "30/1869", "percentage": "1.61%", "elapsed_time": "3m 45s", "remaining_time": "3h 50m 6s"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,23 +1,24 @@
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": {
17
- "content": "<|eot_id|>",
18
- "lstrip": false,
19
  "normalized": false,
20
- "rstrip": false,
21
  "single_word": false
22
- }
 
23
  }
 
1
  {
2
  "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": true,
5
  "normalized": false,
6
+ "rstrip": true,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": true,
12
  "normalized": false,
13
+ "rstrip": true,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "<|dummy_85|>",
18
+ "lstrip": true,
19
  "normalized": false,
20
+ "rstrip": true,
21
  "single_word": false
22
+ },
23
+ "unk_token": "<|endoftext|>"
24
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
- size 17209961
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c612e57b2763204798271c0cdc14a373a565e6a371f1bfbd44e385a8391c9884
3
+ size 7153083
tokenizer_config.json CHANGED
@@ -1,2064 +1,782 @@
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
- "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ 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|>\n\n' }}{% endif %}",
2054
- "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|eot_id|>",
2056
  "extra_special_tokens": {},
2057
- "model_input_names": [
2058
- "input_ids",
2059
- "attention_mask"
2060
- ],
2061
- "model_max_length": 1000000000000000019884624838656,
2062
- "pad_token": "<|eot_id|>",
2063
- "tokenizer_class": "PreTrainedTokenizerFast"
2064
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|dummy_0|>",
6
+ "lstrip": true,
7
  "normalized": false,
8
+ "rstrip": true,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "100257": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": true,
15
  "normalized": false,
16
+ "rstrip": true,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": true,
23
  "normalized": false,
24
+ "rstrip": true,
25
  "single_word": false,
26
  "special": true
27
  },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": true,
31
  "normalized": false,
32
+ "rstrip": true,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": true,
39
  "normalized": false,
40
+ "rstrip": true,
41
  "single_word": false,
42
  "special": true
43
  },
44
+ "100261": {
45
+ "content": "<|dummy_1|>",
46
+ "lstrip": true,
47
  "normalized": false,
48
+ "rstrip": true,
49
  "single_word": false,
50
  "special": true
51
  },
52
+ "100262": {
53
+ "content": "<|dummy_2|>",
54
+ "lstrip": true,
55
  "normalized": false,
56
+ "rstrip": true,
57
  "single_word": false,
58
  "special": true
59
  },
60
+ "100263": {
61
+ "content": "<|dummy_3|>",
62
+ "lstrip": true,
63
  "normalized": false,
64
+ "rstrip": true,
65
  "single_word": false,
66
  "special": true
67
  },
68
+ "100264": {
69
+ "content": "<|im_start|>",
70
+ "lstrip": true,
71
  "normalized": false,
72
+ "rstrip": true,
73
  "single_word": false,
74
  "special": true
75
  },
76
+ "100265": {
77
+ "content": "<|im_end|>",
78
+ "lstrip": true,
79
  "normalized": false,
80
+ "rstrip": true,
81
  "single_word": false,
82
  "special": true
83
  },
84
+ "100266": {
85
+ "content": "<|im_sep|>",
86
+ "lstrip": true,
87
  "normalized": false,
88
+ "rstrip": true,
89
  "single_word": false,
90
  "special": true
91
  },
92
+ "100267": {
93
+ "content": "<|dummy_4|>",
94
+ "lstrip": true,
95
  "normalized": false,
96
+ "rstrip": true,
97
  "single_word": false,
98
  "special": true
99
  },
100
+ "100268": {
101
+ "content": "<|dummy_5|>",
102
+ "lstrip": true,
103
  "normalized": false,
104
+ "rstrip": true,
105
  "single_word": false,
106
  "special": true
107
  },
108
+ "100269": {
109
+ "content": "<|dummy_6|>",
110
+ "lstrip": true,
111
  "normalized": false,
112
+ "rstrip": true,
113
  "single_word": false,
114
  "special": true
115
  },
116
+ "100270": {
117
+ "content": "<|dummy_7|>",
118
+ "lstrip": true,
119
  "normalized": false,
120
+ "rstrip": true,
121
  "single_word": false,
122
  "special": true
123
  },
124
+ "100271": {
125
+ "content": "<|dummy_8|>",
126
+ "lstrip": true,
127
  "normalized": false,
128
+ "rstrip": true,
129
  "single_word": false,
130
  "special": true
131
  },
132
+ "100272": {
133
+ "content": "<|dummy_9|>",
134
+ "lstrip": true,
135
  "normalized": false,
136
+ "rstrip": true,
137
  "single_word": false,
138
  "special": true
139
  },
140
+ "100273": {
141
+ "content": "<|dummy_10|>",
142
+ "lstrip": true,
143
  "normalized": false,
144
+ "rstrip": true,
145
  "single_word": false,
146
  "special": true
147
  },
148
+ "100274": {
149
+ "content": "<|dummy_11|>",
150
+ "lstrip": true,
151
  "normalized": false,
152
+ "rstrip": true,
153
  "single_word": false,
154
  "special": true
155
  },
156
+ "100275": {
157
+ "content": "<|dummy_12|>",
158
+ "lstrip": true,
159
  "normalized": false,
160
+ "rstrip": true,
161
  "single_word": false,
162
  "special": true
163
  },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
+ "lstrip": true,
167
  "normalized": false,
168
+ "rstrip": true,
169
  "single_word": false,
170
  "special": true
171
  },
172
+ "100277": {
173
+ "content": "<|dummy_13|>",
174
+ "lstrip": true,
175
  "normalized": false,
176
+ "rstrip": true,
177
  "single_word": false,
178
  "special": true
179
  },
180
+ "100278": {
181
+ "content": "<|dummy_14|>",
182
+ "lstrip": true,
183
  "normalized": false,
184
+ "rstrip": true,
185
  "single_word": false,
186
  "special": true
187
  },
188
+ "100279": {
189
+ "content": "<|dummy_15|>",
190
+ "lstrip": true,
191
  "normalized": false,
192
+ "rstrip": true,
193
  "single_word": false,
194
  "special": true
195
  },
196
+ "100280": {
197
+ "content": "<|dummy_16|>",
198
+ "lstrip": true,
199
  "normalized": false,
200
+ "rstrip": true,
201
  "single_word": false,
202
  "special": true
203
  },
204
+ "100281": {
205
+ "content": "<|dummy_17|>",
206
+ "lstrip": true,
207
  "normalized": false,
208
+ "rstrip": true,
209
  "single_word": false,
210
  "special": true
211
  },
212
+ "100282": {
213
+ "content": "<|dummy_18|>",
214
+ "lstrip": true,
215
  "normalized": false,
216
+ "rstrip": true,
217
  "single_word": false,
218
  "special": true
219
  },
220
+ "100283": {
221
+ "content": "<|dummy_19|>",
222
+ "lstrip": true,
223
  "normalized": false,
224
+ "rstrip": true,
225
  "single_word": false,
226
  "special": true
227
  },
228
+ "100284": {
229
+ "content": "<|dummy_20|>",
230
+ "lstrip": true,
231
  "normalized": false,
232
+ "rstrip": true,
233
  "single_word": false,
234
  "special": true
235
  },
236
+ "100285": {
237
+ "content": "<|dummy_21|>",
238
+ "lstrip": true,
239
  "normalized": false,
240
+ "rstrip": true,
241
  "single_word": false,
242
  "special": true
243
  },
244
+ "100286": {
245
+ "content": "<|dummy_22|>",
246
+ "lstrip": true,
247
  "normalized": false,
248
+ "rstrip": true,
249
  "single_word": false,
250
  "special": true
251
  },
252
+ "100287": {
253
+ "content": "<|dummy_23|>",
254
+ "lstrip": true,
255
  "normalized": false,
256
+ "rstrip": true,
257
  "single_word": false,
258
  "special": true
259
  },
260
+ "100288": {
261
+ "content": "<|dummy_24|>",
262
+ "lstrip": true,
263
  "normalized": false,
264
+ "rstrip": true,
265
  "single_word": false,
266
  "special": true
267
  },
268
+ "100289": {
269
+ "content": "<|dummy_25|>",
270
+ "lstrip": true,
271
  "normalized": false,
272
+ "rstrip": true,
273
  "single_word": false,
274
  "special": true
275
  },
276
+ "100290": {
277
+ "content": "<|dummy_26|>",
278
+ "lstrip": true,
279
  "normalized": false,
280
+ "rstrip": true,
281
  "single_word": false,
282
  "special": true
283
  },
284
+ "100291": {
285
+ "content": "<|dummy_27|>",
286
+ "lstrip": true,
287
  "normalized": false,
288
+ "rstrip": true,
289
  "single_word": false,
290
  "special": true
291
  },
292
+ "100292": {
293
+ "content": "<|dummy_28|>",
294
+ "lstrip": true,
295
  "normalized": false,
296
+ "rstrip": true,
297
  "single_word": false,
298
  "special": true
299
  },
300
+ "100293": {
301
+ "content": "<|dummy_29|>",
302
+ "lstrip": true,
303
  "normalized": false,
304
+ "rstrip": true,
305
  "single_word": false,
306
  "special": true
307
  },
308
+ "100294": {
309
+ "content": "<|dummy_30|>",
310
+ "lstrip": true,
311
  "normalized": false,
312
+ "rstrip": true,
313
  "single_word": false,
314
  "special": true
315
  },
316
+ "100295": {
317
+ "content": "<|dummy_31|>",
318
+ "lstrip": true,
319
  "normalized": false,
320
+ "rstrip": true,
321
  "single_word": false,
322
  "special": true
323
  },
324
+ "100296": {
325
+ "content": "<|dummy_32|>",
326
+ "lstrip": true,
327
  "normalized": false,
328
+ "rstrip": true,
329
  "single_word": false,
330
  "special": true
331
  },
332
+ "100297": {
333
+ "content": "<|dummy_33|>",
334
+ "lstrip": true,
335
  "normalized": false,
336
+ "rstrip": true,
337
  "single_word": false,
338
  "special": true
339
  },
340
+ "100298": {
341
+ "content": "<|dummy_34|>",
342
+ "lstrip": true,
343
  "normalized": false,
344
+ "rstrip": true,
345
  "single_word": false,
346
  "special": true
347
  },
348
+ "100299": {
349
+ "content": "<|dummy_35|>",
350
+ "lstrip": true,
351
  "normalized": false,
352
+ "rstrip": true,
353
  "single_word": false,
354
  "special": true
355
  },
356
+ "100300": {
357
+ "content": "<|dummy_36|>",
358
+ "lstrip": true,
359
  "normalized": false,
360
+ "rstrip": true,
361
  "single_word": false,
362
  "special": true
363
  },
364
+ "100301": {
365
+ "content": "<|dummy_37|>",
366
+ "lstrip": true,
367
  "normalized": false,
368
+ "rstrip": true,
369
  "single_word": false,
370
  "special": true
371
  },
372
+ "100302": {
373
+ "content": "<|dummy_38|>",
374
+ "lstrip": true,
375
  "normalized": false,
376
+ "rstrip": true,
377
  "single_word": false,
378
  "special": true
379
  },
380
+ "100303": {
381
+ "content": "<|dummy_39|>",
382
+ "lstrip": true,
383
  "normalized": false,
384
+ "rstrip": true,
385
  "single_word": false,
386
  "special": true
387
  },
388
+ "100304": {
389
+ "content": "<|dummy_40|>",
390
+ "lstrip": true,
391
  "normalized": false,
392
+ "rstrip": true,
393
  "single_word": false,
394
  "special": true
395
  },
396
+ "100305": {
397
+ "content": "<|dummy_41|>",
398
+ "lstrip": true,
399
  "normalized": false,
400
+ "rstrip": true,
401
  "single_word": false,
402
  "special": true
403
  },
404
+ "100306": {
405
+ "content": "<|dummy_42|>",
406
+ "lstrip": true,
407
  "normalized": false,
408
+ "rstrip": true,
409
  "single_word": false,
410
  "special": true
411
  },
412
+ "100307": {
413
+ "content": "<|dummy_43|>",
414
+ "lstrip": true,
415
  "normalized": false,
416
+ "rstrip": true,
417
  "single_word": false,
418
  "special": true
419
  },
420
+ "100308": {
421
+ "content": "<|dummy_44|>",
422
+ "lstrip": true,
423
  "normalized": false,
424
+ "rstrip": true,
425
  "single_word": false,
426
  "special": true
427
  },
428
+ "100309": {
429
+ "content": "<|dummy_45|>",
430
+ "lstrip": true,
431
  "normalized": false,
432
+ "rstrip": true,
433
  "single_word": false,
434
  "special": true
435
  },
436
+ "100310": {
437
+ "content": "<|dummy_46|>",
438
+ "lstrip": true,
439
  "normalized": false,
440
+ "rstrip": true,
441
  "single_word": false,
442
  "special": true
443
  },
444
+ "100311": {
445
+ "content": "<|dummy_47|>",
446
+ "lstrip": true,
447
  "normalized": false,
448
+ "rstrip": true,
449
  "single_word": false,
450
  "special": true
451
  },
452
+ "100312": {
453
+ "content": "<|dummy_48|>",
454
+ "lstrip": true,
455
  "normalized": false,
456
+ "rstrip": true,
457
  "single_word": false,
458
  "special": true
459
  },
460
+ "100313": {
461
+ "content": "<|dummy_49|>",
462
+ "lstrip": true,
463
  "normalized": false,
464
+ "rstrip": true,
465
  "single_word": false,
466
  "special": true
467
  },
468
+ "100314": {
469
+ "content": "<|dummy_50|>",
470
+ "lstrip": true,
471
  "normalized": false,
472
+ "rstrip": true,
473
  "single_word": false,
474
  "special": true
475
  },
476
+ "100315": {
477
+ "content": "<|dummy_51|>",
478
+ "lstrip": true,
479
  "normalized": false,
480
+ "rstrip": true,
481
  "single_word": false,
482
  "special": true
483
  },
484
+ "100316": {
485
+ "content": "<|dummy_52|>",
486
+ "lstrip": true,
487
  "normalized": false,
488
+ "rstrip": true,
489
  "single_word": false,
490
  "special": true
491
  },
492
+ "100317": {
493
+ "content": "<|dummy_53|>",
494
+ "lstrip": true,
495
  "normalized": false,
496
+ "rstrip": true,
497
  "single_word": false,
498
  "special": true
499
  },
500
+ "100318": {
501
+ "content": "<|dummy_54|>",
502
+ "lstrip": true,
503
  "normalized": false,
504
+ "rstrip": true,
505
  "single_word": false,
506
  "special": true
507
  },
508
+ "100319": {
509
+ "content": "<|dummy_55|>",
510
+ "lstrip": true,
511
  "normalized": false,
512
+ "rstrip": true,
513
  "single_word": false,
514
  "special": true
515
  },
516
+ "100320": {
517
+ "content": "<|dummy_56|>",
518
+ "lstrip": true,
519
  "normalized": false,
520
+ "rstrip": true,
521
  "single_word": false,
522
  "special": true
523
  },
524
+ "100321": {
525
+ "content": "<|dummy_57|>",
526
+ "lstrip": true,
527
  "normalized": false,
528
+ "rstrip": true,
529
  "single_word": false,
530
  "special": true
531
  },
532
+ "100322": {
533
+ "content": "<|dummy_58|>",
534
+ "lstrip": true,
535
  "normalized": false,
536
+ "rstrip": true,
537
  "single_word": false,
538
  "special": true
539
  },
540
+ "100323": {
541
+ "content": "<|dummy_59|>",
542
+ "lstrip": true,
543
  "normalized": false,
544
+ "rstrip": true,
545
  "single_word": false,
546
  "special": true
547
  },
548
+ "100324": {
549
+ "content": "<|dummy_60|>",
550
+ "lstrip": true,
551
  "normalized": false,
552
+ "rstrip": true,
553
  "single_word": false,
554
  "special": true
555
  },
556
+ "100325": {
557
+ "content": "<|dummy_61|>",
558
+ "lstrip": true,
559
  "normalized": false,
560
+ "rstrip": true,
561
  "single_word": false,
562
  "special": true
563
  },
564
+ "100326": {
565
+ "content": "<|dummy_62|>",
566
+ "lstrip": true,
567
  "normalized": false,
568
+ "rstrip": true,
569
  "single_word": false,
570
  "special": true
571
  },
572
+ "100327": {
573
+ "content": "<|dummy_63|>",
574
+ "lstrip": true,
575
  "normalized": false,
576
+ "rstrip": true,
577
  "single_word": false,
578
  "special": true
579
  },
580
+ "100328": {
581
+ "content": "<|dummy_64|>",
582
+ "lstrip": true,
583
  "normalized": false,
584
+ "rstrip": true,
585
  "single_word": false,
586
  "special": true
587
  },
588
+ "100329": {
589
+ "content": "<|dummy_65|>",
590
+ "lstrip": true,
591
  "normalized": false,
592
+ "rstrip": true,
593
  "single_word": false,
594
  "special": true
595
  },
596
+ "100330": {
597
+ "content": "<|dummy_66|>",
598
+ "lstrip": true,
599
  "normalized": false,
600
+ "rstrip": true,
601
  "single_word": false,
602
  "special": true
603
  },
604
+ "100331": {
605
+ "content": "<|dummy_67|>",
606
+ "lstrip": true,
607
  "normalized": false,
608
+ "rstrip": true,
609
  "single_word": false,
610
  "special": true
611
  },
612
+ "100332": {
613
+ "content": "<|dummy_68|>",
614
+ "lstrip": true,
615
  "normalized": false,
616
+ "rstrip": true,
617
  "single_word": false,
618
  "special": true
619
  },
620
+ "100333": {
621
+ "content": "<|dummy_69|>",
622
+ "lstrip": true,
623
  "normalized": false,
624
+ "rstrip": true,
625
  "single_word": false,
626
  "special": true
627
  },
628
+ "100334": {
629
+ "content": "<|dummy_70|>",
630
+ "lstrip": true,
631
  "normalized": false,
632
+ "rstrip": true,
633
  "single_word": false,
634
  "special": true
635
  },
636
+ "100335": {
637
+ "content": "<|dummy_71|>",
638
+ "lstrip": true,
639
  "normalized": false,
640
+ "rstrip": true,
641
  "single_word": false,
642
  "special": true
643
  },
644
+ "100336": {
645
+ "content": "<|dummy_72|>",
646
+ "lstrip": true,
647
  "normalized": false,
648
+ "rstrip": true,
649
  "single_word": false,
650
  "special": true
651
  },
652
+ "100337": {
653
+ "content": "<|dummy_73|>",
654
+ "lstrip": true,
655
  "normalized": false,
656
+ "rstrip": true,
657
  "single_word": false,
658
  "special": true
659
  },
660
+ "100338": {
661
+ "content": "<|dummy_74|>",
662
+ "lstrip": true,
663
  "normalized": false,
664
+ "rstrip": true,
665
  "single_word": false,
666
  "special": true
667
  },
668
+ "100339": {
669
+ "content": "<|dummy_75|>",
670
+ "lstrip": true,
671
  "normalized": false,
672
+ "rstrip": true,
673
  "single_word": false,
674
  "special": true
675
  },
676
+ "100340": {
677
+ "content": "<|dummy_76|>",
678
+ "lstrip": true,
679
  "normalized": false,
680
+ "rstrip": true,
681
  "single_word": false,
682
  "special": true
683
  },
684
+ "100341": {
685
+ "content": "<|dummy_77|>",
686
+ "lstrip": true,
687
  "normalized": false,
688
+ "rstrip": true,
689
  "single_word": false,
690
  "special": true
691
  },
692
+ "100342": {
693
+ "content": "<|dummy_78|>",
694
+ "lstrip": true,
695
  "normalized": false,
696
+ "rstrip": true,
697
  "single_word": false,
698
  "special": true
699
  },
700
+ "100343": {
701
+ "content": "<|dummy_79|>",
702
+ "lstrip": true,
703
  "normalized": false,
704
+ "rstrip": true,
705
  "single_word": false,
706
  "special": true
707
  },
708
+ "100344": {
709
+ "content": "<|dummy_80|>",
710
+ "lstrip": true,
711
  "normalized": false,
712
+ "rstrip": true,
713
  "single_word": false,
714
  "special": true
715
  },
716
+ "100345": {
717
+ "content": "<|dummy_81|>",
718
+ "lstrip": true,
719
  "normalized": false,
720
+ "rstrip": true,
721
  "single_word": false,
722
  "special": true
723
  },
724
+ "100346": {
725
+ "content": "<|dummy_82|>",
726
+ "lstrip": true,
727
  "normalized": false,
728
+ "rstrip": true,
729
  "single_word": false,
730
  "special": true
731
  },
732
+ "100347": {
733
+ "content": "<|dummy_83|>",
734
+ "lstrip": true,
735
  "normalized": false,
736
+ "rstrip": true,
737
  "single_word": false,
738
  "special": true
739
  },
740
+ "100348": {
741
+ "content": "<|dummy_84|>",
742
+ "lstrip": true,
743
  "normalized": false,
744
+ "rstrip": true,
745
  "single_word": false,
746
  "special": true
747
  },
748
+ "100349": {
749
+ "content": "<|dummy_85|>",
750
+ "lstrip": true,
751
  "normalized": false,
752
+ "rstrip": true,
753
  "single_word": false,
754
  "special": true
755
  },
756
+ "100350": {
757
+ "content": "<|dummy_86|>",
758
+ "lstrip": true,
759
  "normalized": false,
760
+ "rstrip": true,
761
  "single_word": false,
762
  "special": true
763
  },
764
+ "100351": {
765
+ "content": "<|dummy_87|>",
766
+ "lstrip": true,
767
  "normalized": false,
768
+ "rstrip": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
769
  "single_word": false,
770
  "special": true
771
  }
772
  },
773
+ "bos_token": "<|endoftext|>",
774
+ "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
775
+ "clean_up_tokenization_spaces": false,
776
+ "eos_token": "<|im_end|>",
777
  "extra_special_tokens": {},
778
+ "model_max_length": 16384,
779
+ "pad_token": "<|dummy_85|>",
780
+ "tokenizer_class": "GPT2Tokenizer",
781
+ "unk_token": "<|endoftext|>"
 
 
 
782
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab0dd68fed41ad26a77c9859dec0c22ac01692fd35259f333395be7f70946225
3
  size 8120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a4e0c73890c635511853b8bc2cf58f0a92a64a7bd3940612c7e7028ef2a5d9
3
  size 8120
vocab.json ADDED
The diff for this file is too large to render. See raw diff