Training in progress, step 10

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/root/dataDisk/output/v68-20250313-073537/checkpoint-90-merged",
+  "base_model_name_or_path": "/root/highspeedstorage/ft-volume/mistral-agentic-turbo",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -12,26 +12,26 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 256,
   "lora_bias": false,
-  "lora_dropout": 0.2,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [],
   "peft_type": "LORA",
-  "r": 32,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "o_proj",
+    "down_proj",
     "k_proj",
     "gate_proj",
     "q_proj",
-    "up_proj",
-    "down_proj",
-    "v_proj",
-    "o_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,
-  "use_rslora": false
+  "use_rslora": true
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce04af93b650aa745681d6f16691431d088dd3e1f19c916dbd7e124d747f5ee5
-size 1656902648
+oid sha256:3301075aa1f1b7e190353e81cb8efe7860f1018f4a34d7aee5a645ae97ff9b19
+size 1478569432

args.json

@@ -1,6 +1,6 @@
 {
-  "model": "/root/dataDisk/output/v68-20250313-073537/checkpoint-90-merged",
-  "model_type": "llama3_2",
+  "model": "/root/highspeedstorage/ft-volume/mistral-agentic-turbo",
+  "model_type": "mistral_2501",
   "model_revision": null,
   "task_type": "causal_lm",
   "torch_dtype": "bfloat16",
@@ -8,28 +8,34 @@
   "num_labels": null,
   "rope_scaling": null,
   "device_map": null,
+  "max_memory": {},
   "local_repo_path": null,
-  "template": "llama3_2",
+  "template": "mistral_2501",
   "system": "",
-  "max_length": 64000,
+  "max_length": 80000,
   "truncation_strategy": "left",
   "max_pixels": null,
   "tools_prompt": "react_en",
+  "norm_bbox": null,
+  "response_prefix": null,
+  "padding_side": "right",
   "loss_scale": "default",
   "sequence_parallel_size": 1,
   "use_chat_template": true,
   "template_backend": "swift",
   "dataset": [
-    "dpo_data.jsonl"
+    "all_processed_logs.jsonl"
   ],
   "val_dataset": [],
   "split_dataset_ratio": 0.03,
   "data_seed": 42,
   "dataset_num_proc": 1,
   "streaming": false,
-  "load_from_cache_file": false,
+  "enable_cache": false,
   "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
   "strict": false,
+  "remove_unused_columns": true,
   "model_name": [
     null,
     null
@@ -55,22 +61,24 @@
   "stream": false,
   "stop_words": [],
   "logprobs": false,
-  "ckpt_dir": "/root/dataDisk/output/v68-20250313-073537/checkpoint-90-merged",
+  "top_logprobs": null,
+  "ckpt_dir": "/root/highspeedstorage/ft-volume/mistral-agentic-turbo",
   "load_dataset_config": null,
   "lora_modules": [],
   "tuner_backend": "peft",
   "train_type": "lora",
   "adapters": [],
+  "external_plugins": [],
   "seed": 42,
   "model_kwargs": {},
-  "load_args": true,
+  "load_args": false,
   "load_data_args": false,
   "use_hf": true,
   "hub_token": null,
   "custom_register_path": [],
   "ignore_args_error": false,
   "use_swift_lora": false,
-  "output_dir": "/root/dataDisk/output/v78-20250314-065341",
+  "output_dir": "/root/dataDisk/ms-swift/output/v37-20250327-184820",
   "overwrite_output_dir": false,
   "do_train": false,
   "do_eval": false,
@@ -100,7 +108,7 @@
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
-  "logging_dir": "/root/dataDisk/output/v78-20250314-065341/runs",
+  "logging_dir": "/root/dataDisk/ms-swift/output/v37-20250327-184820/runs",
   "logging_strategy": "steps",
   "logging_first_step": true,
   "logging_steps": 1,
@@ -124,7 +132,7 @@
   "bf16_full_eval": false,
   "fp16_full_eval": false,
   "tf32": null,
-  "local_rank": -1,
+  "local_rank": 0,
   "ddp_backend": null,
   "tpu_num_cores": null,
   "tpu_metrics_debug": false,
@@ -136,7 +144,6 @@
   "past_index": -1,
   "run_name": null,
   "disable_tqdm": null,
-  "remove_unused_columns": false,
   "label_names": null,
   "load_best_model_at_end": false,
   "metric_for_best_model": "loss",
@@ -145,11 +152,50 @@
   "fsdp": "",
   "fsdp_min_num_params": 0,
   "fsdp_config": null,
+  "tp_size": 0,
   "fsdp_transformer_layer_cls_to_wrap": null,
   "accelerator_config": {
     "dispatch_batches": false
   },
-  "deepspeed": null,
+  "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": "adamw_torch",
   "optim_args": null,
@@ -157,7 +203,7 @@
   "group_by_length": false,
   "length_column_name": "length",
   "report_to": [
-    "wandb"
+    "tensorboard"
   ],
   "ddp_find_unused_parameters": null,
   "ddp_bucket_cap_mb": null,
@@ -220,13 +266,13 @@
   ],
   "target_regex": null,
   "modules_to_save": [],
-  "lora_rank": 32,
-  "lora_alpha": 64,
-  "lora_dropout": 0.2,
+  "lora_rank": 128,
+  "lora_alpha": 256,
+  "lora_dropout": 0.1,
   "lora_bias": "none",
   "lora_dtype": null,
   "lorap_lr_ratio": null,
-  "use_rslora": false,
+  "use_rslora": true,
   "use_dora": false,
   "lora_ga_batch_size": 2,
   "lora_ga_iters": 2,
@@ -284,21 +330,29 @@
   "metric_warmup_step": 0,
   "fsdp_num": 1,
   "acc_steps": 1,
+  "swanlab_token": null,
+  "swanlab_project": null,
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_mode": "cloud",
   "add_version": true,
   "resume_only_model": false,
   "check_model": true,
-  "loss_type": null,
+  "create_checkpoint_symlink": false,
   "packing": false,
   "lazy_tokenize": false,
-  "acc_strategy": "token",
+  "loss_type": null,
   "optimizer": null,
   "metric": null,
-  "rank": -1,
-  "local_world_size": 1,
-  "model_suffix": "checkpoint-90-merged",
-  "model_info": "ModelInfo(model_type='llama3_2', model_dir='/root/dataDisk/output/v68-20250313-073537/checkpoint-90-merged', torch_dtype=torch.bfloat16, max_model_len=131072, 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)",
-  "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 0x7fb82e3124d0>, model_arch='llama', architectures=['LlamaForCausalLM'], is_multimodal=False, additional_saved_files=[], torch_dtype=None, ignore_patterns=[], requires=['transformers>=4.45'], tags=[])",
-  "model_dir": "/root/dataDisk/output/v68-20250313-073537/checkpoint-90-merged",
+  "acc_strategy": "token",
+  "zero_hpz_partition_size": null,
+  "rank": 0,
+  "global_world_size": 8,
+  "local_world_size": 8,
+  "model_suffix": "mistral-agentic-turbo",
+  "model_info": "ModelInfo(model_type='mistral_2501', model_dir='/root/highspeedstorage/ft-volume/mistral-agentic-turbo', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling={'factor': 4.0, 'original_max_position_embeddings': 32768, 'type': 'dynamic'}, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='mistral_2501', model_groups=[ModelGroup(models=[Model(ms_model_id='mistralai/Mistral-Small-24B-Base-2501', hf_model_id='mistralai/Mistral-Small-24B-Base-2501', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Mistral-Small-24B-Instruct-2501', hf_model_id='mistralai/Mistral-Small-24B-Instruct-2501', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='mistral_2501', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f5b3cd2ac20>, model_arch='llama', architectures=['MistralForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=[], requires=[], tags=[])",
+  "model_dir": "/root/highspeedstorage/ft-volume/mistral-agentic-turbo",
   "hub": "<class 'swift.hub.hub.HFHub'>",
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/dataDisk/output/v78-20250314-065341', 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/v78-20250314-065341/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/v78-20250314-065341', 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=None, 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')"
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/dataDisk/ms-swift/output/v37-20250327-184820', 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/ms-swift/output/v37-20250327-184820/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/ms-swift/output/v37-20250327-184820', 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}, tp_size=0, 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=['tensorboard'], 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, local_repo_path=None, galore_config=None)"
 }

logging.jsonl

@@ -1,34 +1,13 @@
-{"loss": 0.35729143, "token_acc": 0.89395794, "grad_norm": 0.21384092, "learning_rate": 3e-07, "memory(GiB)": 768.5, "train_speed(iter/s)": 0.004678, "epoch": 0.00304414, "global_step/max_steps": "1/328", "percentage": "0.30%", "elapsed_time": "3m 30s", "remaining_time": "19h 9m 30s"}
-{"loss": 0.32265121, "token_acc": 0.89477082, "grad_norm": 0.10401434, "learning_rate": 6.1e-07, "memory(GiB)": 768.53, "train_speed(iter/s)": 0.007188, "epoch": 0.00608828, "global_step/max_steps": "2/328", "percentage": "0.61%", "elapsed_time": "4m 35s", "remaining_time": "12h 28m 14s"}
-{"loss": 0.33431894, "token_acc": 0.88896965, "grad_norm": 0.13479018, "learning_rate": 9.1e-07, "memory(GiB)": 768.53, "train_speed(iter/s)": 0.008617, "epoch": 0.00913242, "global_step/max_steps": "3/328", "percentage": "0.91%", "elapsed_time": "5m 45s", "remaining_time": "10h 23m 30s"}
-{"loss": 0.21555151, "token_acc": 0.92855823, "grad_norm": 0.0987763, "learning_rate": 1.21e-06, "memory(GiB)": 768.53, "train_speed(iter/s)": 0.010151, "epoch": 0.01217656, "global_step/max_steps": "4/328", "percentage": "1.22%", "elapsed_time": "6m 31s", "remaining_time": "8h 48m 9s"}
-{"loss": 0.25857142, "token_acc": 0.91168183, "grad_norm": 0.1142064, "learning_rate": 1.52e-06, "memory(GiB)": 768.53, "train_speed(iter/s)": 0.011455, "epoch": 0.0152207, "global_step/max_steps": "5/328", "percentage": "1.52%", "elapsed_time": "7m 13s", "remaining_time": "7h 46m 54s"}
-{"loss": 0.24284926, "token_acc": 0.91845185, "grad_norm": 0.09238362, "learning_rate": 1.82e-06, "memory(GiB)": 768.53, "train_speed(iter/s)": 0.01237, "epoch": 0.01826484, "global_step/max_steps": "6/328", "percentage": "1.83%", "elapsed_time": "8m 2s", "remaining_time": "7h 11m 19s"}
-{"loss": 0.20129141, "token_acc": 0.93152436, "grad_norm": 0.11056672, "learning_rate": 2.12e-06, "memory(GiB)": 768.55, "train_speed(iter/s)": 0.013217, "epoch": 0.02130898, "global_step/max_steps": "7/328", "percentage": "2.13%", "elapsed_time": "8m 46s", "remaining_time": "6h 42m 37s"}
-{"loss": 0.26141307, "token_acc": 0.91274165, "grad_norm": 0.09076461, "learning_rate": 2.42e-06, "memory(GiB)": 768.55, "train_speed(iter/s)": 0.013447, "epoch": 0.02435312, "global_step/max_steps": "8/328", "percentage": "2.44%", "elapsed_time": "9m 52s", "remaining_time": "6h 34m 43s"}
-{"loss": 0.25274417, "token_acc": 0.91281625, "grad_norm": 0.07585815, "learning_rate": 2.73e-06, "memory(GiB)": 768.55, "train_speed(iter/s)": 0.013856, "epoch": 0.02739726, "global_step/max_steps": "9/328", "percentage": "2.74%", "elapsed_time": "10m 46s", "remaining_time": "6h 22m 2s"}
-{"loss": 0.24568725, "token_acc": 0.91618446, "grad_norm": 0.09478283, "learning_rate": 3.03e-06, "memory(GiB)": 768.55, "train_speed(iter/s)": 0.014157, "epoch": 0.0304414, "global_step/max_steps": "10/328", "percentage": "3.05%", "elapsed_time": "11m 43s", "remaining_time": "6h 12m 52s"}
-{"eval_loss": 0.30681169, "eval_token_acc": 0.89584491, "eval_runtime": 247.1437, "eval_samples_per_second": 0.328, "eval_steps_per_second": 0.328, "epoch": 0.0304414, "global_step/max_steps": "10/328", "percentage": "3.05%", "elapsed_time": "15m 50s", "remaining_time": "8h 23m 51s"}
-{"loss": 0.26882207, "token_acc": 0.89675909, "grad_norm": 0.10335801, "learning_rate": 3.33e-06, "memory(GiB)": 768.55, "train_speed(iter/s)": 0.010964, "epoch": 0.03348554, "global_step/max_steps": "11/328", "percentage": "3.35%", "elapsed_time": "16m 40s", "remaining_time": "8h 0m 30s"}
-{"loss": 0.27928257, "token_acc": 0.90756404, "grad_norm": 0.11043152, "learning_rate": 3.64e-06, "memory(GiB)": 815.51, "train_speed(iter/s)": 0.009228, "epoch": 0.03652968, "global_step/max_steps": "12/328", "percentage": "3.66%", "elapsed_time": "21m 37s", "remaining_time": "9h 29m 29s"}
-{"loss": 0.20683245, "token_acc": 0.92941097, "grad_norm": 0.08834656, "learning_rate": 3.94e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.00948, "epoch": 0.03957382, "global_step/max_steps": "13/328", "percentage": "3.96%", "elapsed_time": "22m 48s", "remaining_time": "9h 12m 40s"}
-{"loss": 0.1894401, "token_acc": 0.93424278, "grad_norm": 0.10855642, "learning_rate": 4.24e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.009895, "epoch": 0.04261796, "global_step/max_steps": "14/328", "percentage": "4.27%", "elapsed_time": "23m 31s", "remaining_time": "8h 47m 49s"}
-{"loss": 0.18465643, "token_acc": 0.93911768, "grad_norm": 0.10122923, "learning_rate": 4.55e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.009787, "epoch": 0.0456621, "global_step/max_steps": "15/328", "percentage": "4.57%", "elapsed_time": "25m 29s", "remaining_time": "8h 52m 1s"}
-{"loss": 0.30540073, "token_acc": 0.8956815, "grad_norm": 0.08773388, "learning_rate": 4.85e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.00999, "epoch": 0.04870624, "global_step/max_steps": "16/328", "percentage": "4.88%", "elapsed_time": "26m 38s", "remaining_time": "8h 39m 34s"}
-{"loss": 0.27026296, "token_acc": 0.90511308, "grad_norm": 0.10466376, "learning_rate": 5.15e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.010316, "epoch": 0.05175038, "global_step/max_steps": "17/328", "percentage": "5.18%", "elapsed_time": "27m 25s", "remaining_time": "8h 21m 36s"}
-{"loss": 0.18841991, "token_acc": 0.93332867, "grad_norm": 0.09853333, "learning_rate": 5.45e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.010012, "epoch": 0.05479452, "global_step/max_steps": "18/328", "percentage": "5.49%", "elapsed_time": "29m 54s", "remaining_time": "8h 35m 13s"}
-{"loss": 0.24658927, "token_acc": 0.91555587, "grad_norm": 0.12874357, "learning_rate": 5.76e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.009529, "epoch": 0.05783866, "global_step/max_steps": "19/328", "percentage": "5.79%", "elapsed_time": "33m 11s", "remaining_time": "8h 59m 40s"}
-{"loss": 0.26267582, "token_acc": 0.90973451, "grad_norm": 0.09905843, "learning_rate": 6.06e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.009347, "epoch": 0.0608828, "global_step/max_steps": "20/328", "percentage": "6.10%", "elapsed_time": "35m 36s", "remaining_time": "9h 8m 28s"}
-{"eval_loss": 0.30634969, "eval_token_acc": 0.8960476, "eval_runtime": 247.0826, "eval_samples_per_second": 0.328, "eval_steps_per_second": 0.328, "epoch": 0.0608828, "global_step/max_steps": "20/328", "percentage": "6.10%", "elapsed_time": "39m 44s", "remaining_time": "10h 11m 53s"}
-{"loss": 0.2819325, "token_acc": 0.89672202, "grad_norm": 0.10652838, "learning_rate": 6.36e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.008354, "epoch": 0.06392694, "global_step/max_steps": "21/328", "percentage": "6.40%", "elapsed_time": "41m 50s", "remaining_time": "10h 11m 46s"}
-{"loss": 0.2759549, "token_acc": 0.9119108, "grad_norm": 0.13444495, "learning_rate": 6.67e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.008204, "epoch": 0.06697108, "global_step/max_steps": "22/328", "percentage": "6.71%", "elapsed_time": "44m 38s", "remaining_time": "10h 20m 58s"}
-{"loss": 0.2600477, "token_acc": 0.91032317, "grad_norm": 0.11379159, "learning_rate": 6.97e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.008384, "epoch": 0.07001522, "global_step/max_steps": "23/328", "percentage": "7.01%", "elapsed_time": "45m 40s", "remaining_time": "10h 5m 42s"}
-{"loss": 0.21677592, "token_acc": 0.92537639, "grad_norm": 0.10500745, "learning_rate": 7.27e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.00859, "epoch": 0.07305936, "global_step/max_steps": "24/328", "percentage": "7.32%", "elapsed_time": "46m 31s", "remaining_time": "9h 49m 15s"}
-{"loss": 0.24449337, "token_acc": 0.91679533, "grad_norm": 0.09542393, "learning_rate": 7.58e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.008704, "epoch": 0.0761035, "global_step/max_steps": "25/328", "percentage": "7.62%", "elapsed_time": "47m 49s", "remaining_time": "9h 39m 39s"}
-{"loss": 0.31512672, "token_acc": 0.89371783, "grad_norm": 0.10736728, "learning_rate": 7.88e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.00849, "epoch": 0.07914764, "global_step/max_steps": "26/328", "percentage": "7.93%", "elapsed_time": "50m 59s", "remaining_time": "9h 52m 20s"}
-{"loss": 0.26235914, "token_acc": 0.91197774, "grad_norm": 0.09094914, "learning_rate": 8.18e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.008173, "epoch": 0.08219178, "global_step/max_steps": "27/328", "percentage": "8.23%", "elapsed_time": "55m 0s", "remaining_time": "10h 13m 15s"}
-{"loss": 0.24826424, "token_acc": 0.91292023, "grad_norm": 0.10768829, "learning_rate": 8.48e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.008326, "epoch": 0.08523592, "global_step/max_steps": "28/328", "percentage": "8.54%", "elapsed_time": "56m 0s", "remaining_time": "10h 0m 2s"}
-{"loss": 0.15691531, "token_acc": 0.94420261, "grad_norm": 0.08934391, "learning_rate": 8.79e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.008529, "epoch": 0.08828006, "global_step/max_steps": "29/328", "percentage": "8.84%", "elapsed_time": "56m 37s", "remaining_time": "9h 43m 46s"}
-{"loss": 0.24090692, "token_acc": 0.91948326, "grad_norm": 0.10308056, "learning_rate": 9.09e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.008655, "epoch": 0.0913242, "global_step/max_steps": "30/328", "percentage": "9.15%", "elapsed_time": "57m 43s", "remaining_time": "9h 33m 21s"}
-{"eval_loss": 0.30391112, "eval_token_acc": 0.89699565, "eval_runtime": 246.9889, "eval_samples_per_second": 0.328, "eval_steps_per_second": 0.328, "epoch": 0.0913242, "global_step/max_steps": "30/328", "percentage": "9.15%", "elapsed_time": "1h 1m 50s", "remaining_time": "10h 14m 14s"}
-{"loss": 0.25271627, "token_acc": 0.8980103, "grad_norm": 0.17491929, "learning_rate": 9.39e-06, "memory(GiB)": 815.53, "train_speed(iter/s)": 0.008214, "epoch": 0.09436834, "global_step/max_steps": "31/328", "percentage": "9.45%", "elapsed_time": "1h 2m 51s", "remaining_time": "10h 2m 11s"}
+{"loss": 0.48510081, "token_acc": 0.84539138, "grad_norm": 14.7837925, "learning_rate": 5e-06, "memory(GiB)": 63.21, "train_speed(iter/s)": 0.018308, "epoch": 0.06557377, "global_step/max_steps": "1/15", "percentage": "6.67%", "elapsed_time": "45s", "remaining_time": "10m 36s"}
+{"loss": 0.49545321, "token_acc": 0.841411, "grad_norm": 14.93395615, "learning_rate": 1e-05, "memory(GiB)": 63.21, "train_speed(iter/s)": 0.019485, "epoch": 0.13114754, "global_step/max_steps": "2/15", "percentage": "13.33%", "elapsed_time": "1m 33s", "remaining_time": "10m 7s"}
+{"loss": 0.38048813, "token_acc": 0.89755256, "grad_norm": 18.88997841, "learning_rate": 9.23e-06, "memory(GiB)": 86.57, "train_speed(iter/s)": 0.019925, "epoch": 0.19672131, "global_step/max_steps": "3/15", "percentage": "20.00%", "elapsed_time": "2m 21s", "remaining_time": "9m 25s"}
+{"loss": 0.37227625, "token_acc": 0.91562971, "grad_norm": 8.1224165, "learning_rate": 8.46e-06, "memory(GiB)": 87.82, "train_speed(iter/s)": 0.020139, "epoch": 0.26229508, "global_step/max_steps": "4/15", "percentage": "26.67%", "elapsed_time": "3m 9s", "remaining_time": "8m 40s"}
+{"loss": 0.29637671, "token_acc": 0.89964737, "grad_norm": 5.36969328, "learning_rate": 7.69e-06, "memory(GiB)": 87.82, "train_speed(iter/s)": 0.020924, "epoch": 0.32786885, "global_step/max_steps": "5/15", "percentage": "33.33%", "elapsed_time": "3m 49s", "remaining_time": "7m 39s"}
+{"loss": 0.28302842, "token_acc": 0.90767151, "grad_norm": 4.82790804, "learning_rate": 6.92e-06, "memory(GiB)": 87.82, "train_speed(iter/s)": 0.021064, "epoch": 0.39344262, "global_step/max_steps": "6/15", "percentage": "40.00%", "elapsed_time": "4m 35s", "remaining_time": "6m 53s"}
+{"loss": 0.23423848, "token_acc": 0.90778898, "grad_norm": 5.02321243, "learning_rate": 6.15e-06, "memory(GiB)": 127.02, "train_speed(iter/s)": 0.020018, "epoch": 0.45901639, "global_step/max_steps": "7/15", "percentage": "46.67%", "elapsed_time": "5m 40s", "remaining_time": "6m 29s"}
+{"loss": 0.21110272, "token_acc": 0.94392094, "grad_norm": 4.05730915, "learning_rate": 5.38e-06, "memory(GiB)": 127.02, "train_speed(iter/s)": 0.020303, "epoch": 0.52459016, "global_step/max_steps": "8/15", "percentage": "53.33%", "elapsed_time": "6m 24s", "remaining_time": "5m 36s"}
+{"loss": 0.19155277, "token_acc": 0.94833101, "grad_norm": 4.49223232, "learning_rate": 4.62e-06, "memory(GiB)": 127.02, "train_speed(iter/s)": 0.01977, "epoch": 0.59016393, "global_step/max_steps": "9/15", "percentage": "60.00%", "elapsed_time": "7m 26s", "remaining_time": "4m 57s"}
+{"loss": 0.18690804, "token_acc": 0.93399378, "grad_norm": 4.40774298, "learning_rate": 3.85e-06, "memory(GiB)": 127.02, "train_speed(iter/s)": 0.020146, "epoch": 0.6557377, "global_step/max_steps": "10/15", "percentage": "66.67%", "elapsed_time": "8m 7s", "remaining_time": "4m 3s"}
+{"eval_loss": 0.18784808, "eval_token_acc": 0.95191512, "eval_runtime": 5.2458, "eval_samples_per_second": 5.719, "eval_steps_per_second": 0.763, "epoch": 0.6557377, "global_step/max_steps": "10/15", "percentage": "66.67%", "elapsed_time": "8m 12s", "remaining_time": "4m 6s"}
+{"loss": 0.1912355, "token_acc": 0.95364897, "grad_norm": 4.21334696, "learning_rate": 3.08e-06, "memory(GiB)": 127.02, "train_speed(iter/s)": 0.019415, "epoch": 0.72131148, "global_step/max_steps": "11/15", "percentage": "73.33%", "elapsed_time": "9m 17s", "remaining_time": "3m 22s"}
+{"loss": 0.17585593, "token_acc": 0.93333333, "grad_norm": 4.19101381, "learning_rate": 2.31e-06, "memory(GiB)": 127.02, "train_speed(iter/s)": 0.019755, "epoch": 0.78688525, "global_step/max_steps": "12/15", "percentage": "80.00%", "elapsed_time": "9m 58s", "remaining_time": "2m 29s"}

runs/events.out.tfevents.1743101387.notebook-67532d59-da58-11ef-a92b-d22a634ff48d-0.226850.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a930881e631352cd4456f9cea7b56009ec271aab9804f70d971a7df141b099
+size 10951

special_tokens_map.json

@@ -1,20 +1,1023 @@
 {
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
   "bos_token": {
-    "content": "<|begin_of_text|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|eot_id|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|eot_id|>",
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
-size 17209920
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cbf4e59b7b424ef292a4078dbda221a4406c3652ba53be8253d0e4648ee22d6
-size 5880
+oid sha256:60e8bc9742d10a0fff50f87c479bf8c55dfb4859ec782bfebc64808772d1fac3
+size 8248