First Commit
Browse files- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +9 -0
- llamaboard_config.yaml +66 -0
- running_log.txt +590 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2065 -0
- train_results.json +9 -0
- trainer_log.jsonl +69 -0
- trainer_state.json +587 -0
- training_args.bin +3 -0
- training_args.yaml +39 -0
- training_loss.png +0 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": true,
|
| 33 |
+
"use_rslora": true
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95fa186e3f85b9ca7ec3c9fdd7faf75130b1a5928fc116f798ffaa12fd351a27
|
| 3 |
+
size 173368456
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.612048192771084,
|
| 3 |
+
"num_input_tokens_seen": 5052448,
|
| 4 |
+
"total_flos": 2.28822660837802e+17,
|
| 5 |
+
"train_loss": 0.2300173058541106,
|
| 6 |
+
"train_runtime": 12675.9679,
|
| 7 |
+
"train_samples_per_second": 0.655,
|
| 8 |
+
"train_steps_per_second": 0.04
|
| 9 |
+
}
|
llamaboard_config.yaml
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
top.booster: unsloth
|
| 2 |
+
top.checkpoint_path: []
|
| 3 |
+
top.finetuning_type: lora
|
| 4 |
+
top.model_name: LLaMA3-8B-Chat
|
| 5 |
+
top.quantization_bit: none
|
| 6 |
+
top.quantization_method: bitsandbytes
|
| 7 |
+
top.rope_scaling: linear
|
| 8 |
+
top.template: llama3
|
| 9 |
+
top.visual_inputs: false
|
| 10 |
+
train.additional_target: ''
|
| 11 |
+
train.badam_mode: layer
|
| 12 |
+
train.badam_switch_interval: 50
|
| 13 |
+
train.badam_switch_mode: ascending
|
| 14 |
+
train.badam_update_ratio: 0.05
|
| 15 |
+
train.batch_size: 2
|
| 16 |
+
train.compute_type: bf16
|
| 17 |
+
train.create_new_adapter: false
|
| 18 |
+
train.cutoff_len: 4096
|
| 19 |
+
train.dataset:
|
| 20 |
+
- gpt4_judge
|
| 21 |
+
- Judge
|
| 22 |
+
train.dataset_dir: data
|
| 23 |
+
train.ds_offload: false
|
| 24 |
+
train.ds_stage: none
|
| 25 |
+
train.freeze_extra_modules: ''
|
| 26 |
+
train.freeze_trainable_layers: 24
|
| 27 |
+
train.freeze_trainable_modules: all
|
| 28 |
+
train.galore_rank: 16
|
| 29 |
+
train.galore_scale: 0.25
|
| 30 |
+
train.galore_target: all
|
| 31 |
+
train.galore_update_interval: 200
|
| 32 |
+
train.gradient_accumulation_steps: 8
|
| 33 |
+
train.learning_rate: 5e-5
|
| 34 |
+
train.logging_steps: 5
|
| 35 |
+
train.lora_alpha: 16
|
| 36 |
+
train.lora_dropout: 0
|
| 37 |
+
train.lora_rank: 16
|
| 38 |
+
train.lora_target: ''
|
| 39 |
+
train.loraplus_lr_ratio: 0
|
| 40 |
+
train.lr_scheduler_type: cosine
|
| 41 |
+
train.max_grad_norm: '1.0'
|
| 42 |
+
train.max_samples: '100000'
|
| 43 |
+
train.neat_packing: false
|
| 44 |
+
train.neftune_alpha: 0
|
| 45 |
+
train.num_train_epochs: '10'
|
| 46 |
+
train.optim: adamw_torch
|
| 47 |
+
train.packing: false
|
| 48 |
+
train.ppo_score_norm: false
|
| 49 |
+
train.ppo_whiten_rewards: false
|
| 50 |
+
train.pref_beta: 0.1
|
| 51 |
+
train.pref_ftx: 0
|
| 52 |
+
train.pref_loss: sigmoid
|
| 53 |
+
train.report_to: false
|
| 54 |
+
train.resize_vocab: false
|
| 55 |
+
train.reward_model: []
|
| 56 |
+
train.save_steps: 100
|
| 57 |
+
train.shift_attn: false
|
| 58 |
+
train.training_stage: Supervised Fine-Tuning
|
| 59 |
+
train.use_badam: false
|
| 60 |
+
train.use_dora: true
|
| 61 |
+
train.use_galore: false
|
| 62 |
+
train.use_llama_pro: false
|
| 63 |
+
train.use_pissa: true
|
| 64 |
+
train.use_rslora: true
|
| 65 |
+
train.val_size: 0
|
| 66 |
+
train.warmup_steps: 0
|
running_log.txt
ADDED
|
@@ -0,0 +1,590 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[INFO|parser.py:325] 2024-09-19 15:01:40,415 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.bfloat16
|
| 2 |
+
|
| 3 |
+
[INFO|tokenization_utils_base.py:2287] 2024-09-19 15:01:40,419 >> loading file tokenizer.json
|
| 4 |
+
|
| 5 |
+
[INFO|tokenization_utils_base.py:2287] 2024-09-19 15:01:40,420 >> loading file added_tokens.json
|
| 6 |
+
|
| 7 |
+
[INFO|tokenization_utils_base.py:2287] 2024-09-19 15:01:40,420 >> loading file special_tokens_map.json
|
| 8 |
+
|
| 9 |
+
[INFO|tokenization_utils_base.py:2287] 2024-09-19 15:01:40,420 >> loading file tokenizer_config.json
|
| 10 |
+
|
| 11 |
+
[INFO|tokenization_utils_base.py:2533] 2024-09-19 15:01:40,699 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
| 12 |
+
|
| 13 |
+
[INFO|template.py:270] 2024-09-19 15:01:40,700 >> Replace eos token: <|eot_id|>
|
| 14 |
+
|
| 15 |
+
[INFO|template.py:372] 2024-09-19 15:01:40,700 >> Add pad token: <|eot_id|>
|
| 16 |
+
|
| 17 |
+
[INFO|loader.py:50] 2024-09-19 15:01:40,700 >> Loading dataset SUSTech/mt_bench_judge...
|
| 18 |
+
|
| 19 |
+
[INFO|loader.py:50] 2024-09-19 15:01:44,251 >> Loading dataset Judge.json...
|
| 20 |
+
|
| 21 |
+
[INFO|configuration_utils.py:731] 2024-09-19 15:01:44,965 >> loading configuration file /home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693/config.json
|
| 22 |
+
|
| 23 |
+
[INFO|configuration_utils.py:800] 2024-09-19 15:01:44,966 >> Model config LlamaConfig {
|
| 24 |
+
"_name_or_path": "/home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693",
|
| 25 |
+
"architectures": [
|
| 26 |
+
"LlamaForCausalLM"
|
| 27 |
+
],
|
| 28 |
+
"attention_bias": false,
|
| 29 |
+
"attention_dropout": 0.0,
|
| 30 |
+
"bos_token_id": 128000,
|
| 31 |
+
"eos_token_id": [
|
| 32 |
+
128001,
|
| 33 |
+
128008,
|
| 34 |
+
128009
|
| 35 |
+
],
|
| 36 |
+
"hidden_act": "silu",
|
| 37 |
+
"hidden_size": 4096,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 14336,
|
| 40 |
+
"max_position_embeddings": 131072,
|
| 41 |
+
"mlp_bias": false,
|
| 42 |
+
"model_type": "llama",
|
| 43 |
+
"num_attention_heads": 32,
|
| 44 |
+
"num_hidden_layers": 32,
|
| 45 |
+
"num_key_value_heads": 8,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": {
|
| 49 |
+
"factor": 8.0,
|
| 50 |
+
"high_freq_factor": 4.0,
|
| 51 |
+
"low_freq_factor": 1.0,
|
| 52 |
+
"original_max_position_embeddings": 8192,
|
| 53 |
+
"rope_type": "llama3"
|
| 54 |
+
},
|
| 55 |
+
"rope_theta": 500000.0,
|
| 56 |
+
"tie_word_embeddings": false,
|
| 57 |
+
"torch_dtype": "bfloat16",
|
| 58 |
+
"transformers_version": "4.43.2",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 128256
|
| 61 |
+
}
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
[WARNING|rope.py:57] 2024-09-19 15:01:44,967 >> Input length is smaller than max length. Consider increase input length.
|
| 65 |
+
|
| 66 |
+
[INFO|rope.py:63] 2024-09-19 15:01:44,967 >> Using linear scaling strategy and setting scaling factor to 1.0
|
| 67 |
+
|
| 68 |
+
[INFO|configuration_utils.py:731] 2024-09-19 15:01:46,306 >> loading configuration file /home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693/config.json
|
| 69 |
+
|
| 70 |
+
[INFO|configuration_utils.py:800] 2024-09-19 15:01:46,307 >> Model config LlamaConfig {
|
| 71 |
+
"_name_or_path": "/home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693",
|
| 72 |
+
"architectures": [
|
| 73 |
+
"LlamaForCausalLM"
|
| 74 |
+
],
|
| 75 |
+
"attention_bias": false,
|
| 76 |
+
"attention_dropout": 0.0,
|
| 77 |
+
"bos_token_id": 128000,
|
| 78 |
+
"eos_token_id": [
|
| 79 |
+
128001,
|
| 80 |
+
128008,
|
| 81 |
+
128009
|
| 82 |
+
],
|
| 83 |
+
"hidden_act": "silu",
|
| 84 |
+
"hidden_size": 4096,
|
| 85 |
+
"initializer_range": 0.02,
|
| 86 |
+
"intermediate_size": 14336,
|
| 87 |
+
"max_position_embeddings": 131072,
|
| 88 |
+
"mlp_bias": false,
|
| 89 |
+
"model_type": "llama",
|
| 90 |
+
"num_attention_heads": 32,
|
| 91 |
+
"num_hidden_layers": 32,
|
| 92 |
+
"num_key_value_heads": 8,
|
| 93 |
+
"pretraining_tp": 1,
|
| 94 |
+
"rms_norm_eps": 1e-05,
|
| 95 |
+
"rope_scaling": {
|
| 96 |
+
"factor": 8.0,
|
| 97 |
+
"high_freq_factor": 4.0,
|
| 98 |
+
"low_freq_factor": 1.0,
|
| 99 |
+
"original_max_position_embeddings": 8192,
|
| 100 |
+
"rope_type": "llama3"
|
| 101 |
+
},
|
| 102 |
+
"rope_theta": 500000.0,
|
| 103 |
+
"tie_word_embeddings": false,
|
| 104 |
+
"torch_dtype": "bfloat16",
|
| 105 |
+
"transformers_version": "4.43.2",
|
| 106 |
+
"use_cache": true,
|
| 107 |
+
"vocab_size": 128256
|
| 108 |
+
}
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
[INFO|configuration_utils.py:733] 2024-09-19 15:01:46,943 >> loading configuration file config.json from cache at /home/marl/.cache/huggingface/hub/models--unslothai--other/snapshots/43d9e0f2f19a5d7836895f648dc0e762816acf77/config.json
|
| 112 |
+
|
| 113 |
+
[INFO|configuration_utils.py:800] 2024-09-19 15:01:46,943 >> Model config LlamaConfig {
|
| 114 |
+
"_name_or_path": "unslothai/other",
|
| 115 |
+
"architectures": [
|
| 116 |
+
"LlamaModel"
|
| 117 |
+
],
|
| 118 |
+
"attention_bias": false,
|
| 119 |
+
"attention_dropout": 0.0,
|
| 120 |
+
"bos_token_id": 1,
|
| 121 |
+
"eos_token_id": 2,
|
| 122 |
+
"hidden_act": "silu",
|
| 123 |
+
"hidden_size": 0,
|
| 124 |
+
"initializer_range": 0.02,
|
| 125 |
+
"intermediate_size": 0,
|
| 126 |
+
"max_position_embeddings": 0,
|
| 127 |
+
"mlp_bias": false,
|
| 128 |
+
"model_type": "llama",
|
| 129 |
+
"num_attention_heads": 0,
|
| 130 |
+
"num_hidden_layers": 0,
|
| 131 |
+
"num_key_value_heads": 0,
|
| 132 |
+
"pretraining_tp": 1,
|
| 133 |
+
"rms_norm_eps": 1e-06,
|
| 134 |
+
"rope_scaling": null,
|
| 135 |
+
"rope_theta": 10000.0,
|
| 136 |
+
"tie_word_embeddings": false,
|
| 137 |
+
"torch_dtype": "float32",
|
| 138 |
+
"transformers_version": "4.43.2",
|
| 139 |
+
"use_cache": true,
|
| 140 |
+
"vocab_size": 0
|
| 141 |
+
}
|
| 142 |
+
|
| 143 |
+
|
| 144 |
+
[INFO|modeling_utils.py:3634] 2024-09-19 15:01:47,465 >> loading weights file model.safetensors from cache at /home/marl/.cache/huggingface/hub/models--unslothai--other/snapshots/43d9e0f2f19a5d7836895f648dc0e762816acf77/model.safetensors
|
| 145 |
+
|
| 146 |
+
[INFO|configuration_utils.py:1038] 2024-09-19 15:01:47,466 >> Generate config GenerationConfig {
|
| 147 |
+
"bos_token_id": 1,
|
| 148 |
+
"eos_token_id": 2
|
| 149 |
+
}
|
| 150 |
+
|
| 151 |
+
|
| 152 |
+
[INFO|configuration_utils.py:733] 2024-09-19 15:01:47,618 >> loading configuration file config.json from cache at /home/marl/.cache/huggingface/hub/models--unslothai--repeat/snapshots/7c48478c02f84ed89f149b0815cc0216ee831fb0/config.json
|
| 153 |
+
|
| 154 |
+
[INFO|configuration_utils.py:800] 2024-09-19 15:01:47,619 >> Model config LlamaConfig {
|
| 155 |
+
"_name_or_path": "unslothai/repeat",
|
| 156 |
+
"architectures": [
|
| 157 |
+
"LlamaModel"
|
| 158 |
+
],
|
| 159 |
+
"attention_bias": false,
|
| 160 |
+
"attention_dropout": 0.0,
|
| 161 |
+
"bos_token_id": 1,
|
| 162 |
+
"eos_token_id": 2,
|
| 163 |
+
"hidden_act": "silu",
|
| 164 |
+
"hidden_size": 0,
|
| 165 |
+
"initializer_range": 0.02,
|
| 166 |
+
"intermediate_size": 0,
|
| 167 |
+
"max_position_embeddings": 0,
|
| 168 |
+
"mlp_bias": false,
|
| 169 |
+
"model_type": "llama",
|
| 170 |
+
"num_attention_heads": 0,
|
| 171 |
+
"num_hidden_layers": 0,
|
| 172 |
+
"num_key_value_heads": 0,
|
| 173 |
+
"pretraining_tp": 1,
|
| 174 |
+
"rms_norm_eps": 1e-06,
|
| 175 |
+
"rope_scaling": null,
|
| 176 |
+
"rope_theta": 10000.0,
|
| 177 |
+
"tie_word_embeddings": false,
|
| 178 |
+
"torch_dtype": "float32",
|
| 179 |
+
"transformers_version": "4.43.2",
|
| 180 |
+
"use_cache": true,
|
| 181 |
+
"vocab_size": 0
|
| 182 |
+
}
|
| 183 |
+
|
| 184 |
+
|
| 185 |
+
[INFO|modeling_utils.py:3634] 2024-09-19 15:01:47,620 >> loading weights file model.safetensors from cache at /home/marl/.cache/huggingface/hub/models--unslothai--repeat/snapshots/7c48478c02f84ed89f149b0815cc0216ee831fb0/model.safetensors
|
| 186 |
+
|
| 187 |
+
[INFO|configuration_utils.py:1038] 2024-09-19 15:01:47,621 >> Generate config GenerationConfig {
|
| 188 |
+
"bos_token_id": 1,
|
| 189 |
+
"eos_token_id": 2
|
| 190 |
+
}
|
| 191 |
+
|
| 192 |
+
|
| 193 |
+
[INFO|configuration_utils.py:733] 2024-09-19 15:01:48,251 >> loading configuration file config.json from cache at /home/marl/.cache/huggingface/hub/models--unslothai--vram-24/snapshots/61324ceeacd75b2b31f7a789a9c9d82058e6118c/config.json
|
| 194 |
+
|
| 195 |
+
[INFO|configuration_utils.py:800] 2024-09-19 15:01:48,252 >> Model config LlamaConfig {
|
| 196 |
+
"_name_or_path": "unslothai/vram-24",
|
| 197 |
+
"architectures": [
|
| 198 |
+
"LlamaModel"
|
| 199 |
+
],
|
| 200 |
+
"attention_bias": false,
|
| 201 |
+
"attention_dropout": 0.0,
|
| 202 |
+
"bos_token_id": 1,
|
| 203 |
+
"eos_token_id": 2,
|
| 204 |
+
"hidden_act": "silu",
|
| 205 |
+
"hidden_size": 0,
|
| 206 |
+
"initializer_range": 0.02,
|
| 207 |
+
"intermediate_size": 0,
|
| 208 |
+
"max_position_embeddings": 0,
|
| 209 |
+
"mlp_bias": false,
|
| 210 |
+
"model_type": "llama",
|
| 211 |
+
"num_attention_heads": 0,
|
| 212 |
+
"num_hidden_layers": 0,
|
| 213 |
+
"num_key_value_heads": 0,
|
| 214 |
+
"pretraining_tp": 1,
|
| 215 |
+
"rms_norm_eps": 1e-06,
|
| 216 |
+
"rope_scaling": null,
|
| 217 |
+
"rope_theta": 10000.0,
|
| 218 |
+
"tie_word_embeddings": false,
|
| 219 |
+
"torch_dtype": "float32",
|
| 220 |
+
"transformers_version": "4.43.2",
|
| 221 |
+
"use_cache": true,
|
| 222 |
+
"vocab_size": 0
|
| 223 |
+
}
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
[INFO|modeling_utils.py:3634] 2024-09-19 15:01:48,630 >> loading weights file model.safetensors from cache at /home/marl/.cache/huggingface/hub/models--unslothai--vram-24/snapshots/61324ceeacd75b2b31f7a789a9c9d82058e6118c/model.safetensors
|
| 227 |
+
|
| 228 |
+
[INFO|configuration_utils.py:1038] 2024-09-19 15:01:48,632 >> Generate config GenerationConfig {
|
| 229 |
+
"bos_token_id": 1,
|
| 230 |
+
"eos_token_id": 2
|
| 231 |
+
}
|
| 232 |
+
|
| 233 |
+
|
| 234 |
+
[INFO|configuration_utils.py:733] 2024-09-19 15:01:49,237 >> loading configuration file config.json from cache at /home/marl/.cache/huggingface/hub/models--unslothai--1/snapshots/7ec782b7604cd9ea0781c23a4270f031650f5617/config.json
|
| 235 |
+
|
| 236 |
+
[INFO|configuration_utils.py:800] 2024-09-19 15:01:49,237 >> Model config LlamaConfig {
|
| 237 |
+
"_name_or_path": "unslothai/1",
|
| 238 |
+
"architectures": [
|
| 239 |
+
"LlamaModel"
|
| 240 |
+
],
|
| 241 |
+
"attention_bias": false,
|
| 242 |
+
"attention_dropout": 0.0,
|
| 243 |
+
"bos_token_id": 1,
|
| 244 |
+
"eos_token_id": 2,
|
| 245 |
+
"hidden_act": "silu",
|
| 246 |
+
"hidden_size": 0,
|
| 247 |
+
"initializer_range": 0.02,
|
| 248 |
+
"intermediate_size": 0,
|
| 249 |
+
"max_position_embeddings": 2048,
|
| 250 |
+
"mlp_bias": false,
|
| 251 |
+
"model_type": "llama",
|
| 252 |
+
"num_attention_heads": 0,
|
| 253 |
+
"num_hidden_layers": 0,
|
| 254 |
+
"num_key_value_heads": 0,
|
| 255 |
+
"pretraining_tp": 1,
|
| 256 |
+
"rms_norm_eps": 1e-06,
|
| 257 |
+
"rope_scaling": null,
|
| 258 |
+
"rope_theta": 10000.0,
|
| 259 |
+
"tie_word_embeddings": false,
|
| 260 |
+
"torch_dtype": "float32",
|
| 261 |
+
"transformers_version": "4.43.2",
|
| 262 |
+
"use_cache": true,
|
| 263 |
+
"vocab_size": 0
|
| 264 |
+
}
|
| 265 |
+
|
| 266 |
+
|
| 267 |
+
[INFO|modeling_utils.py:3634] 2024-09-19 15:01:49,565 >> loading weights file model.safetensors from cache at /home/marl/.cache/huggingface/hub/models--unslothai--1/snapshots/7ec782b7604cd9ea0781c23a4270f031650f5617/model.safetensors
|
| 268 |
+
|
| 269 |
+
[INFO|configuration_utils.py:1038] 2024-09-19 15:01:49,566 >> Generate config GenerationConfig {
|
| 270 |
+
"bos_token_id": 1,
|
| 271 |
+
"eos_token_id": 2
|
| 272 |
+
}
|
| 273 |
+
|
| 274 |
+
|
| 275 |
+
[INFO|configuration_utils.py:731] 2024-09-19 15:01:49,567 >> loading configuration file /home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693/config.json
|
| 276 |
+
|
| 277 |
+
[INFO|configuration_utils.py:800] 2024-09-19 15:01:49,568 >> Model config LlamaConfig {
|
| 278 |
+
"_name_or_path": "/home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693",
|
| 279 |
+
"architectures": [
|
| 280 |
+
"LlamaForCausalLM"
|
| 281 |
+
],
|
| 282 |
+
"attention_bias": false,
|
| 283 |
+
"attention_dropout": 0.0,
|
| 284 |
+
"bos_token_id": 128000,
|
| 285 |
+
"eos_token_id": [
|
| 286 |
+
128001,
|
| 287 |
+
128008,
|
| 288 |
+
128009
|
| 289 |
+
],
|
| 290 |
+
"hidden_act": "silu",
|
| 291 |
+
"hidden_size": 4096,
|
| 292 |
+
"initializer_range": 0.02,
|
| 293 |
+
"intermediate_size": 14336,
|
| 294 |
+
"max_position_embeddings": 131072,
|
| 295 |
+
"mlp_bias": false,
|
| 296 |
+
"model_type": "llama",
|
| 297 |
+
"num_attention_heads": 32,
|
| 298 |
+
"num_hidden_layers": 32,
|
| 299 |
+
"num_key_value_heads": 8,
|
| 300 |
+
"pretraining_tp": 1,
|
| 301 |
+
"rms_norm_eps": 1e-05,
|
| 302 |
+
"rope_scaling": {
|
| 303 |
+
"factor": 8.0,
|
| 304 |
+
"high_freq_factor": 4.0,
|
| 305 |
+
"low_freq_factor": 1.0,
|
| 306 |
+
"original_max_position_embeddings": 8192,
|
| 307 |
+
"rope_type": "llama3"
|
| 308 |
+
},
|
| 309 |
+
"rope_theta": 500000.0,
|
| 310 |
+
"tie_word_embeddings": false,
|
| 311 |
+
"torch_dtype": "bfloat16",
|
| 312 |
+
"transformers_version": "4.43.2",
|
| 313 |
+
"use_cache": true,
|
| 314 |
+
"vocab_size": 128256
|
| 315 |
+
}
|
| 316 |
+
|
| 317 |
+
|
| 318 |
+
[INFO|configuration_utils.py:731] 2024-09-19 15:01:49,582 >> loading configuration file /home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693/config.json
|
| 319 |
+
|
| 320 |
+
[INFO|configuration_utils.py:800] 2024-09-19 15:01:49,583 >> Model config LlamaConfig {
|
| 321 |
+
"_name_or_path": "/home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693",
|
| 322 |
+
"architectures": [
|
| 323 |
+
"LlamaForCausalLM"
|
| 324 |
+
],
|
| 325 |
+
"attention_bias": false,
|
| 326 |
+
"attention_dropout": 0.0,
|
| 327 |
+
"bos_token_id": 128000,
|
| 328 |
+
"eos_token_id": [
|
| 329 |
+
128001,
|
| 330 |
+
128008,
|
| 331 |
+
128009
|
| 332 |
+
],
|
| 333 |
+
"hidden_act": "silu",
|
| 334 |
+
"hidden_size": 4096,
|
| 335 |
+
"initializer_range": 0.02,
|
| 336 |
+
"intermediate_size": 14336,
|
| 337 |
+
"max_position_embeddings": 131072,
|
| 338 |
+
"mlp_bias": false,
|
| 339 |
+
"model_type": "llama",
|
| 340 |
+
"num_attention_heads": 32,
|
| 341 |
+
"num_hidden_layers": 32,
|
| 342 |
+
"num_key_value_heads": 8,
|
| 343 |
+
"pretraining_tp": 1,
|
| 344 |
+
"rms_norm_eps": 1e-05,
|
| 345 |
+
"rope_scaling": {
|
| 346 |
+
"factor": 8.0,
|
| 347 |
+
"high_freq_factor": 4.0,
|
| 348 |
+
"low_freq_factor": 1.0,
|
| 349 |
+
"original_max_position_embeddings": 8192,
|
| 350 |
+
"rope_type": "llama3"
|
| 351 |
+
},
|
| 352 |
+
"rope_theta": 500000.0,
|
| 353 |
+
"tie_word_embeddings": false,
|
| 354 |
+
"torch_dtype": "bfloat16",
|
| 355 |
+
"transformers_version": "4.43.2",
|
| 356 |
+
"use_cache": true,
|
| 357 |
+
"vocab_size": 128256
|
| 358 |
+
}
|
| 359 |
+
|
| 360 |
+
|
| 361 |
+
[INFO|modeling_utils.py:3631] 2024-09-19 15:01:49,584 >> loading weights file /home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693/model.safetensors.index.json
|
| 362 |
+
|
| 363 |
+
[INFO|modeling_utils.py:1572] 2024-09-19 15:01:49,584 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
|
| 364 |
+
|
| 365 |
+
[INFO|configuration_utils.py:1038] 2024-09-19 15:01:49,585 >> Generate config GenerationConfig {
|
| 366 |
+
"bos_token_id": 128000,
|
| 367 |
+
"eos_token_id": [
|
| 368 |
+
128001,
|
| 369 |
+
128008,
|
| 370 |
+
128009
|
| 371 |
+
]
|
| 372 |
+
}
|
| 373 |
+
|
| 374 |
+
|
| 375 |
+
[INFO|modeling_utils.py:4463] 2024-09-19 15:01:56,537 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
|
| 376 |
+
|
| 377 |
+
|
| 378 |
+
[INFO|modeling_utils.py:4471] 2024-09-19 15:01:56,537 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at /home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693.
|
| 379 |
+
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
|
| 380 |
+
|
| 381 |
+
[INFO|configuration_utils.py:991] 2024-09-19 15:01:56,540 >> loading configuration file /home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693/generation_config.json
|
| 382 |
+
|
| 383 |
+
[INFO|configuration_utils.py:1038] 2024-09-19 15:01:56,541 >> Generate config GenerationConfig {
|
| 384 |
+
"bos_token_id": 128000,
|
| 385 |
+
"do_sample": true,
|
| 386 |
+
"eos_token_id": [
|
| 387 |
+
128001,
|
| 388 |
+
128008,
|
| 389 |
+
128009
|
| 390 |
+
],
|
| 391 |
+
"temperature": 0.6,
|
| 392 |
+
"top_p": 0.9
|
| 393 |
+
}
|
| 394 |
+
|
| 395 |
+
|
| 396 |
+
[WARNING|logging.py:328] 2024-09-19 15:01:56,848 >> Unsloth: We successfully patched the tokenizer to add a {% if add_generation_prompt %} to the chat_template.
|
| 397 |
+
This is not a bug, but please notify the Unsloth maintainers - thanks!
|
| 398 |
+
|
| 399 |
+
[WARNING|logging.py:328] 2024-09-19 15:01:56,849 >> /home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693 does not have a padding token! Will use pad_token = <|finetune_right_pad_id|>.
|
| 400 |
+
|
| 401 |
+
[INFO|checkpointing.py:103] 2024-09-19 15:01:57,352 >> Gradient checkpointing enabled.
|
| 402 |
+
|
| 403 |
+
[INFO|adapter.py:302] 2024-09-19 15:01:57,352 >> Upcasting trainable params to float32.
|
| 404 |
+
|
| 405 |
+
[INFO|adapter.py:158] 2024-09-19 15:01:57,352 >> Fine-tuning method: DoRA
|
| 406 |
+
|
| 407 |
+
[INFO|misc.py:51] 2024-09-19 15:01:57,353 >> Found linear modules: k_proj,v_proj,gate_proj,down_proj,q_proj,o_proj,up_proj
|
| 408 |
+
|
| 409 |
+
[WARNING|logging.py:328] 2024-09-19 15:01:58,892 >> Not an error, but Unsloth cannot patch MLP layers with our manual autograd engine since either LoRA adapters
|
| 410 |
+
are not enabled or a bias term (like in Qwen) is used.
|
| 411 |
+
|
| 412 |
+
[WARNING|logging.py:328] 2024-09-19 15:01:58,892 >> Not an error, but Unsloth cannot patch Attention layers with our manual autograd engine since either LoRA adapters
|
| 413 |
+
are not enabled or a bias term (like in Qwen) is used.
|
| 414 |
+
|
| 415 |
+
[WARNING|logging.py:328] 2024-09-19 15:01:58,892 >> Not an error, but Unsloth cannot patch O projection layer with our manual autograd engine since either LoRA adapters
|
| 416 |
+
are not enabled or a bias term (like in Qwen) is used.
|
| 417 |
+
|
| 418 |
+
[WARNING|logging.py:328] 2024-09-19 15:01:58,893 >> Unsloth 2024.9 patched 32 layers with 0 QKV layers, 0 O layers and 0 MLP layers.
|
| 419 |
+
|
| 420 |
+
[INFO|loader.py:196] 2024-09-19 15:01:59,917 >> trainable params: 43,319,296 || all params: 8,073,580,544 || trainable%: 0.5366
|
| 421 |
+
|
| 422 |
+
[INFO|trainer.py:648] 2024-09-19 15:01:59,932 >> Using auto half precision backend
|
| 423 |
+
|
| 424 |
+
[WARNING|<string>:213] 2024-09-19 15:02:00,225 >> ==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1
|
| 425 |
+
\\ /| Num examples = 830 | Num Epochs = 10
|
| 426 |
+
O^O/ \_/ \ Batch size per device = 2 | Gradient Accumulation steps = 8
|
| 427 |
+
\ / Total batch size = 16 | Total steps = 510
|
| 428 |
+
"-____-" Number of trainable parameters = 43,319,296
|
| 429 |
+
|
| 430 |
+
[INFO|callbacks.py:137] 2024-09-19 15:02:00,753 >> Initial PiSSA adatper will be saved at: saves/LLaMA3-8B-Chat/lora/JudgePierce/pissa_init.
|
| 431 |
+
|
| 432 |
+
[INFO|callbacks.py:310] 2024-09-19 15:05:11,452 >> {'loss': 0.8996, 'learning_rate': 4.9988e-05, 'epoch': 0.10, 'throughput': 411.79}
|
| 433 |
+
|
| 434 |
+
[INFO|callbacks.py:310] 2024-09-19 15:08:29,947 >> {'loss': 0.6806, 'learning_rate': 4.9953e-05, 'epoch': 0.19, 'throughput': 408.84}
|
| 435 |
+
|
| 436 |
+
[INFO|callbacks.py:310] 2024-09-19 15:11:13,747 >> {'loss': 0.6180, 'learning_rate': 4.9893e-05, 'epoch': 0.29, 'throughput': 404.26}
|
| 437 |
+
|
| 438 |
+
[INFO|callbacks.py:310] 2024-09-19 15:14:02,211 >> {'loss': 0.5594, 'learning_rate': 4.9811e-05, 'epoch': 0.39, 'throughput': 403.27}
|
| 439 |
+
|
| 440 |
+
[INFO|callbacks.py:310] 2024-09-19 15:17:18,092 >> {'loss': 0.5253, 'learning_rate': 4.9704e-05, 'epoch': 0.48, 'throughput': 396.87}
|
| 441 |
+
|
| 442 |
+
[INFO|callbacks.py:310] 2024-09-19 15:20:42,613 >> {'loss': 0.4794, 'learning_rate': 4.9574e-05, 'epoch': 0.58, 'throughput': 392.36}
|
| 443 |
+
|
| 444 |
+
[INFO|callbacks.py:310] 2024-09-19 15:23:53,577 >> {'loss': 0.4546, 'learning_rate': 4.9421e-05, 'epoch': 0.67, 'throughput': 393.95}
|
| 445 |
+
|
| 446 |
+
[INFO|callbacks.py:310] 2024-09-19 15:26:56,955 >> {'loss': 0.4703, 'learning_rate': 4.9245e-05, 'epoch': 0.77, 'throughput': 395.28}
|
| 447 |
+
|
| 448 |
+
[INFO|callbacks.py:310] 2024-09-19 15:29:57,393 >> {'loss': 0.4407, 'learning_rate': 4.9046e-05, 'epoch': 0.87, 'throughput': 395.30}
|
| 449 |
+
|
| 450 |
+
[INFO|callbacks.py:310] 2024-09-19 15:32:59,265 >> {'loss': 0.4425, 'learning_rate': 4.8824e-05, 'epoch': 0.96, 'throughput': 395.36}
|
| 451 |
+
|
| 452 |
+
[INFO|callbacks.py:310] 2024-09-19 15:36:03,653 >> {'loss': 0.4081, 'learning_rate': 4.8579e-05, 'epoch': 1.06, 'throughput': 395.68}
|
| 453 |
+
|
| 454 |
+
[INFO|callbacks.py:310] 2024-09-19 15:39:11,834 >> {'loss': 0.4002, 'learning_rate': 4.8312e-05, 'epoch': 1.16, 'throughput': 395.63}
|
| 455 |
+
|
| 456 |
+
[INFO|callbacks.py:310] 2024-09-19 15:41:57,790 >> {'loss': 0.3587, 'learning_rate': 4.8023e-05, 'epoch': 1.25, 'throughput': 395.35}
|
| 457 |
+
|
| 458 |
+
[INFO|callbacks.py:310] 2024-09-19 15:45:01,971 >> {'loss': 0.3560, 'learning_rate': 4.7712e-05, 'epoch': 1.35, 'throughput': 395.98}
|
| 459 |
+
|
| 460 |
+
[INFO|callbacks.py:310] 2024-09-19 15:47:56,540 >> {'loss': 0.3639, 'learning_rate': 4.7379e-05, 'epoch': 1.45, 'throughput': 396.16}
|
| 461 |
+
|
| 462 |
+
[INFO|callbacks.py:310] 2024-09-19 15:51:00,164 >> {'loss': 0.3288, 'learning_rate': 4.7025e-05, 'epoch': 1.54, 'throughput': 395.91}
|
| 463 |
+
|
| 464 |
+
[INFO|callbacks.py:310] 2024-09-19 15:54:25,445 >> {'loss': 0.3563, 'learning_rate': 4.6651e-05, 'epoch': 1.64, 'throughput': 396.14}
|
| 465 |
+
|
| 466 |
+
[INFO|callbacks.py:310] 2024-09-19 15:57:21,312 >> {'loss': 0.3642, 'learning_rate': 4.6255e-05, 'epoch': 1.73, 'throughput': 396.03}
|
| 467 |
+
|
| 468 |
+
[INFO|callbacks.py:310] 2024-09-19 16:00:32,266 >> {'loss': 0.3407, 'learning_rate': 4.5840e-05, 'epoch': 1.83, 'throughput': 396.47}
|
| 469 |
+
|
| 470 |
+
[INFO|callbacks.py:310] 2024-09-19 16:03:50,197 >> {'loss': 0.3216, 'learning_rate': 4.5405e-05, 'epoch': 1.93, 'throughput': 396.56}
|
| 471 |
+
|
| 472 |
+
[INFO|trainer.py:3503] 2024-09-19 16:03:50,197 >> Saving model checkpoint to saves/LLaMA3-8B-Chat/lora/JudgePierce/checkpoint-100
|
| 473 |
+
|
| 474 |
+
[INFO|callbacks.py:310] 2024-09-19 16:07:13,059 >> {'loss': 0.3197, 'learning_rate': 4.4950e-05, 'epoch': 2.02, 'throughput': 395.40}
|
| 475 |
+
|
| 476 |
+
[INFO|callbacks.py:310] 2024-09-19 16:10:02,255 >> {'loss': 0.2904, 'learning_rate': 4.4477e-05, 'epoch': 2.12, 'throughput': 394.79}
|
| 477 |
+
|
| 478 |
+
[INFO|callbacks.py:310] 2024-09-19 16:13:06,914 >> {'loss': 0.2498, 'learning_rate': 4.3985e-05, 'epoch': 2.22, 'throughput': 394.39}
|
| 479 |
+
|
| 480 |
+
[INFO|callbacks.py:310] 2024-09-19 16:16:07,251 >> {'loss': 0.2690, 'learning_rate': 4.3475e-05, 'epoch': 2.31, 'throughput': 393.99}
|
| 481 |
+
|
| 482 |
+
[INFO|callbacks.py:310] 2024-09-19 16:19:28,568 >> {'loss': 0.2838, 'learning_rate': 4.2948e-05, 'epoch': 2.41, 'throughput': 393.80}
|
| 483 |
+
|
| 484 |
+
[INFO|callbacks.py:310] 2024-09-19 16:22:40,612 >> {'loss': 0.2466, 'learning_rate': 4.2403e-05, 'epoch': 2.51, 'throughput': 393.67}
|
| 485 |
+
|
| 486 |
+
[INFO|callbacks.py:310] 2024-09-19 16:25:42,935 >> {'loss': 0.2272, 'learning_rate': 4.1842e-05, 'epoch': 2.60, 'throughput': 393.15}
|
| 487 |
+
|
| 488 |
+
[INFO|callbacks.py:310] 2024-09-19 16:29:16,509 >> {'loss': 0.2484, 'learning_rate': 4.1265e-05, 'epoch': 2.70, 'throughput': 393.10}
|
| 489 |
+
|
| 490 |
+
[INFO|callbacks.py:310] 2024-09-19 16:32:12,701 >> {'loss': 0.2339, 'learning_rate': 4.0673e-05, 'epoch': 2.80, 'throughput': 392.63}
|
| 491 |
+
|
| 492 |
+
[INFO|callbacks.py:310] 2024-09-19 16:35:55,248 >> {'loss': 0.2597, 'learning_rate': 4.0066e-05, 'epoch': 2.89, 'throughput': 392.84}
|
| 493 |
+
|
| 494 |
+
[INFO|callbacks.py:310] 2024-09-19 16:38:50,490 >> {'loss': 0.2525, 'learning_rate': 3.9444e-05, 'epoch': 2.99, 'throughput': 392.73}
|
| 495 |
+
|
| 496 |
+
[INFO|callbacks.py:310] 2024-09-19 16:41:47,937 >> {'loss': 0.1832, 'learning_rate': 3.8809e-05, 'epoch': 3.08, 'throughput': 392.41}
|
| 497 |
+
|
| 498 |
+
[INFO|callbacks.py:310] 2024-09-19 16:44:58,684 >> {'loss': 0.1519, 'learning_rate': 3.8161e-05, 'epoch': 3.18, 'throughput': 392.60}
|
| 499 |
+
|
| 500 |
+
[INFO|callbacks.py:310] 2024-09-19 16:47:53,818 >> {'loss': 0.1707, 'learning_rate': 3.7500e-05, 'epoch': 3.28, 'throughput': 392.58}
|
| 501 |
+
|
| 502 |
+
[INFO|callbacks.py:310] 2024-09-19 16:51:13,288 >> {'loss': 0.1603, 'learning_rate': 3.6827e-05, 'epoch': 3.37, 'throughput': 392.77}
|
| 503 |
+
|
| 504 |
+
[INFO|callbacks.py:310] 2024-09-19 16:54:40,189 >> {'loss': 0.1683, 'learning_rate': 3.6143e-05, 'epoch': 3.47, 'throughput': 393.19}
|
| 505 |
+
|
| 506 |
+
[INFO|callbacks.py:310] 2024-09-19 16:57:28,484 >> {'loss': 0.1734, 'learning_rate': 3.5449e-05, 'epoch': 3.57, 'throughput': 392.80}
|
| 507 |
+
|
| 508 |
+
[INFO|callbacks.py:310] 2024-09-19 17:00:50,184 >> {'loss': 0.1543, 'learning_rate': 3.4745e-05, 'epoch': 3.66, 'throughput': 392.50}
|
| 509 |
+
|
| 510 |
+
[INFO|callbacks.py:310] 2024-09-19 17:04:08,221 >> {'loss': 0.1601, 'learning_rate': 3.4031e-05, 'epoch': 3.76, 'throughput': 392.93}
|
| 511 |
+
|
| 512 |
+
[INFO|callbacks.py:310] 2024-09-19 17:06:58,844 >> {'loss': 0.1911, 'learning_rate': 3.3309e-05, 'epoch': 3.86, 'throughput': 393.04}
|
| 513 |
+
|
| 514 |
+
[INFO|trainer.py:3503] 2024-09-19 17:06:58,845 >> Saving model checkpoint to saves/LLaMA3-8B-Chat/lora/JudgePierce/checkpoint-200
|
| 515 |
+
|
| 516 |
+
[INFO|callbacks.py:310] 2024-09-19 17:09:52,758 >> {'loss': 0.1741, 'learning_rate': 3.2579e-05, 'epoch': 3.95, 'throughput': 393.20}
|
| 517 |
+
|
| 518 |
+
[INFO|callbacks.py:310] 2024-09-19 17:12:42,126 >> {'loss': 0.1334, 'learning_rate': 3.1842e-05, 'epoch': 4.05, 'throughput': 393.35}
|
| 519 |
+
|
| 520 |
+
[INFO|callbacks.py:310] 2024-09-19 17:16:01,091 >> {'loss': 0.1027, 'learning_rate': 3.1098e-05, 'epoch': 4.14, 'throughput': 393.86}
|
| 521 |
+
|
| 522 |
+
[INFO|callbacks.py:310] 2024-09-19 17:19:01,299 >> {'loss': 0.0955, 'learning_rate': 3.0348e-05, 'epoch': 4.24, 'throughput': 394.08}
|
| 523 |
+
|
| 524 |
+
[INFO|callbacks.py:310] 2024-09-19 17:22:03,579 >> {'loss': 0.1006, 'learning_rate': 2.9594e-05, 'epoch': 4.34, 'throughput': 394.31}
|
| 525 |
+
|
| 526 |
+
[INFO|callbacks.py:310] 2024-09-19 17:24:44,568 >> {'loss': 0.1007, 'learning_rate': 2.8835e-05, 'epoch': 4.43, 'throughput': 394.43}
|
| 527 |
+
|
| 528 |
+
[INFO|callbacks.py:310] 2024-09-19 17:27:55,254 >> {'loss': 0.1033, 'learning_rate': 2.8072e-05, 'epoch': 4.53, 'throughput': 394.76}
|
| 529 |
+
|
| 530 |
+
[INFO|callbacks.py:310] 2024-09-19 17:30:55,686 >> {'loss': 0.1023, 'learning_rate': 2.7307e-05, 'epoch': 4.63, 'throughput': 395.01}
|
| 531 |
+
|
| 532 |
+
[INFO|callbacks.py:310] 2024-09-19 17:34:01,751 >> {'loss': 0.1121, 'learning_rate': 2.6539e-05, 'epoch': 4.72, 'throughput': 395.28}
|
| 533 |
+
|
| 534 |
+
[INFO|callbacks.py:310] 2024-09-19 17:37:01,776 >> {'loss': 0.1028, 'learning_rate': 2.5770e-05, 'epoch': 4.82, 'throughput': 395.48}
|
| 535 |
+
|
| 536 |
+
[INFO|callbacks.py:310] 2024-09-19 17:40:04,358 >> {'loss': 0.1055, 'learning_rate': 2.5000e-05, 'epoch': 4.92, 'throughput': 395.69}
|
| 537 |
+
|
| 538 |
+
[INFO|callbacks.py:310] 2024-09-19 17:42:51,693 >> {'loss': 0.1037, 'learning_rate': 2.4230e-05, 'epoch': 5.01, 'throughput': 395.79}
|
| 539 |
+
|
| 540 |
+
[INFO|callbacks.py:310] 2024-09-19 17:45:59,478 >> {'loss': 0.0633, 'learning_rate': 2.3461e-05, 'epoch': 5.11, 'throughput': 396.05}
|
| 541 |
+
|
| 542 |
+
[INFO|callbacks.py:310] 2024-09-19 17:49:02,492 >> {'loss': 0.0521, 'learning_rate': 2.2693e-05, 'epoch': 5.20, 'throughput': 396.24}
|
| 543 |
+
|
| 544 |
+
[INFO|callbacks.py:310] 2024-09-19 17:52:17,309 >> {'loss': 0.0625, 'learning_rate': 2.1928e-05, 'epoch': 5.30, 'throughput': 396.59}
|
| 545 |
+
|
| 546 |
+
[INFO|callbacks.py:310] 2024-09-19 17:55:15,619 >> {'loss': 0.0590, 'learning_rate': 2.1165e-05, 'epoch': 5.40, 'throughput': 396.74}
|
| 547 |
+
|
| 548 |
+
[INFO|callbacks.py:310] 2024-09-19 17:57:57,249 >> {'loss': 0.0648, 'learning_rate': 2.0406e-05, 'epoch': 5.49, 'throughput': 396.77}
|
| 549 |
+
|
| 550 |
+
[INFO|callbacks.py:310] 2024-09-19 18:00:56,018 >> {'loss': 0.0709, 'learning_rate': 1.9652e-05, 'epoch': 5.59, 'throughput': 396.92}
|
| 551 |
+
|
| 552 |
+
[INFO|callbacks.py:310] 2024-09-19 18:03:45,922 >> {'loss': 0.0641, 'learning_rate': 1.8902e-05, 'epoch': 5.69, 'throughput': 396.97}
|
| 553 |
+
|
| 554 |
+
[INFO|callbacks.py:310] 2024-09-19 18:06:55,209 >> {'loss': 0.0689, 'learning_rate': 1.8158e-05, 'epoch': 5.78, 'throughput': 397.19}
|
| 555 |
+
|
| 556 |
+
[INFO|trainer.py:3503] 2024-09-19 18:06:55,210 >> Saving model checkpoint to saves/LLaMA3-8B-Chat/lora/JudgePierce/checkpoint-300
|
| 557 |
+
|
| 558 |
+
[INFO|callbacks.py:310] 2024-09-19 18:09:56,064 >> {'loss': 0.0550, 'learning_rate': 1.7421e-05, 'epoch': 5.88, 'throughput': 397.36}
|
| 559 |
+
|
| 560 |
+
[INFO|callbacks.py:310] 2024-09-19 18:12:55,928 >> {'loss': 0.0626, 'learning_rate': 1.6691e-05, 'epoch': 5.98, 'throughput': 397.56}
|
| 561 |
+
|
| 562 |
+
[INFO|callbacks.py:310] 2024-09-19 18:15:57,052 >> {'loss': 0.0465, 'learning_rate': 1.5969e-05, 'epoch': 6.07, 'throughput': 397.77}
|
| 563 |
+
|
| 564 |
+
[INFO|callbacks.py:310] 2024-09-19 18:19:01,654 >> {'loss': 0.0421, 'learning_rate': 1.5255e-05, 'epoch': 6.17, 'throughput': 397.98}
|
| 565 |
+
|
| 566 |
+
[INFO|callbacks.py:310] 2024-09-19 18:21:57,727 >> {'loss': 0.0303, 'learning_rate': 1.4551e-05, 'epoch': 6.27, 'throughput': 398.18}
|
| 567 |
+
|
| 568 |
+
[INFO|callbacks.py:310] 2024-09-19 18:25:07,621 >> {'loss': 0.0337, 'learning_rate': 1.3857e-05, 'epoch': 6.36, 'throughput': 398.43}
|
| 569 |
+
|
| 570 |
+
[INFO|callbacks.py:310] 2024-09-19 18:28:04,937 >> {'loss': 0.0333, 'learning_rate': 1.3173e-05, 'epoch': 6.46, 'throughput': 398.54}
|
| 571 |
+
|
| 572 |
+
[INFO|callbacks.py:310] 2024-09-19 18:31:08,310 >> {'loss': 0.0390, 'learning_rate': 1.2500e-05, 'epoch': 6.55, 'throughput': 398.74}
|
| 573 |
+
|
| 574 |
+
[INFO|<string>:478] 2024-09-19 18:33:16,716 >>
|
| 575 |
+
|
| 576 |
+
Training completed. Do not forget to share your model on huggingface.co/models =)
|
| 577 |
+
|
| 578 |
+
|
| 579 |
+
|
| 580 |
+
[INFO|callbacks.py:153] 2024-09-19 18:33:16,718 >> Converted PiSSA adapter will be saved at: saves/LLaMA3-8B-Chat/lora/JudgePierce/pissa_converted.
|
| 581 |
+
|
| 582 |
+
[INFO|trainer.py:3503] 2024-09-19 18:33:18,563 >> Saving model checkpoint to saves/LLaMA3-8B-Chat/lora/JudgePierce
|
| 583 |
+
|
| 584 |
+
[WARNING|ploting.py:89] 2024-09-19 18:33:18,991 >> No metric eval_loss to plot.
|
| 585 |
+
|
| 586 |
+
[WARNING|ploting.py:89] 2024-09-19 18:33:18,991 >> No metric eval_accuracy to plot.
|
| 587 |
+
|
| 588 |
+
[INFO|modelcard.py:449] 2024-09-19 18:33:18,992 >> Dropping the following result as it does not have all the necessary fields:
|
| 589 |
+
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
|
| 590 |
+
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"padding_side": "right",
|
| 2063 |
+
"split_special_tokens": false,
|
| 2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2065 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.612048192771084,
|
| 3 |
+
"num_input_tokens_seen": 5052448,
|
| 4 |
+
"total_flos": 2.28822660837802e+17,
|
| 5 |
+
"train_loss": 0.2300173058541106,
|
| 6 |
+
"train_runtime": 12675.9679,
|
| 7 |
+
"train_samples_per_second": 0.655,
|
| 8 |
+
"train_steps_per_second": 0.04
|
| 9 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 510, "loss": 0.8996, "learning_rate": 4.998814299283415e-05, "epoch": 0.0963855421686747, "percentage": 0.98, "elapsed_time": "0:03:10", "remaining_time": "5:21:00", "throughput": "411.79", "total_tokens": 78528}
|
| 2 |
+
{"current_steps": 10, "total_steps": 510, "loss": 0.6806, "learning_rate": 4.995258321842611e-05, "epoch": 0.1927710843373494, "percentage": 1.96, "elapsed_time": "0:06:29", "remaining_time": "5:24:19", "throughput": "408.84", "total_tokens": 159120}
|
| 3 |
+
{"current_steps": 15, "total_steps": 510, "loss": 0.618, "learning_rate": 4.989335440737586e-05, "epoch": 0.2891566265060241, "percentage": 2.94, "elapsed_time": "0:09:12", "remaining_time": "5:04:08", "throughput": "404.26", "total_tokens": 223552}
|
| 4 |
+
{"current_steps": 20, "total_steps": 510, "loss": 0.5594, "learning_rate": 4.98105127417984e-05, "epoch": 0.3855421686746988, "percentage": 3.92, "elapsed_time": "0:12:01", "remaining_time": "4:54:35", "throughput": "403.27", "total_tokens": 290944}
|
| 5 |
+
{"current_steps": 25, "total_steps": 510, "loss": 0.5253, "learning_rate": 4.9704136802031485e-05, "epoch": 0.4819277108433735, "percentage": 4.9, "elapsed_time": "0:15:17", "remaining_time": "4:56:36", "throughput": "396.87", "total_tokens": 364064}
|
| 6 |
+
{"current_steps": 30, "total_steps": 510, "loss": 0.4794, "learning_rate": 4.957432749209755e-05, "epoch": 0.5783132530120482, "percentage": 5.88, "elapsed_time": "0:18:41", "remaining_time": "4:59:09", "throughput": "392.36", "total_tokens": 440176}
|
| 7 |
+
{"current_steps": 35, "total_steps": 510, "loss": 0.4546, "learning_rate": 4.942120794399002e-05, "epoch": 0.6746987951807228, "percentage": 6.86, "elapsed_time": "0:21:52", "remaining_time": "4:56:56", "throughput": "393.95", "total_tokens": 517184}
|
| 8 |
+
{"current_steps": 40, "total_steps": 510, "loss": 0.4703, "learning_rate": 4.9244923400875245e-05, "epoch": 0.7710843373493976, "percentage": 7.84, "elapsed_time": "0:24:56", "remaining_time": "4:53:00", "throughput": "395.28", "total_tokens": 591424}
|
| 9 |
+
{"current_steps": 45, "total_steps": 510, "loss": 0.4407, "learning_rate": 4.9045641079320484e-05, "epoch": 0.8674698795180723, "percentage": 8.82, "elapsed_time": "0:27:56", "remaining_time": "4:48:45", "throughput": "395.30", "total_tokens": 662784}
|
| 10 |
+
{"current_steps": 50, "total_steps": 510, "loss": 0.4425, "learning_rate": 4.882355001067892e-05, "epoch": 0.963855421686747, "percentage": 9.8, "elapsed_time": "0:30:58", "remaining_time": "4:44:58", "throughput": "395.36", "total_tokens": 734784}
|
| 11 |
+
{"current_steps": 55, "total_steps": 510, "loss": 0.4081, "learning_rate": 4.857886086178194e-05, "epoch": 1.0602409638554218, "percentage": 10.78, "elapsed_time": "0:34:02", "remaining_time": "4:41:40", "throughput": "395.68", "total_tokens": 808336}
|
| 12 |
+
{"current_steps": 60, "total_steps": 510, "loss": 0.4002, "learning_rate": 4.8311805735108894e-05, "epoch": 1.1566265060240963, "percentage": 11.76, "elapsed_time": "0:37:11", "remaining_time": "4:38:53", "throughput": "395.63", "total_tokens": 882672}
|
| 13 |
+
{"current_steps": 65, "total_steps": 510, "loss": 0.3587, "learning_rate": 4.802263794862385e-05, "epoch": 1.2530120481927711, "percentage": 12.75, "elapsed_time": "0:39:57", "remaining_time": "4:33:30", "throughput": "395.35", "total_tokens": 947680}
|
| 14 |
+
{"current_steps": 70, "total_steps": 510, "loss": 0.356, "learning_rate": 4.7711631795488096e-05, "epoch": 1.3493975903614457, "percentage": 13.73, "elapsed_time": "0:43:01", "remaining_time": "4:30:24", "throughput": "395.98", "total_tokens": 1022112}
|
| 15 |
+
{"current_steps": 75, "total_steps": 510, "loss": 0.3639, "learning_rate": 4.7379082283876566e-05, "epoch": 1.4457831325301205, "percentage": 14.71, "elapsed_time": "0:45:55", "remaining_time": "4:26:23", "throughput": "396.16", "total_tokens": 1091744}
|
| 16 |
+
{"current_steps": 80, "total_steps": 510, "loss": 0.3288, "learning_rate": 4.702530485714461e-05, "epoch": 1.5421686746987953, "percentage": 15.69, "elapsed_time": "0:48:59", "remaining_time": "4:23:19", "throughput": "395.91", "total_tokens": 1163728}
|
| 17 |
+
{"current_steps": 85, "total_steps": 510, "loss": 0.3563, "learning_rate": 4.665063509461097e-05, "epoch": 1.6385542168674698, "percentage": 16.67, "elapsed_time": "0:52:24", "remaining_time": "4:22:03", "throughput": "396.14", "total_tokens": 1245728}
|
| 18 |
+
{"current_steps": 90, "total_steps": 510, "loss": 0.3642, "learning_rate": 4.625542839324036e-05, "epoch": 1.7349397590361446, "percentage": 17.65, "elapsed_time": "0:55:20", "remaining_time": "4:18:15", "throughput": "396.03", "total_tokens": 1315056}
|
| 19 |
+
{"current_steps": 95, "total_steps": 510, "loss": 0.3407, "learning_rate": 4.584005963052799e-05, "epoch": 1.8313253012048194, "percentage": 18.63, "elapsed_time": "0:58:31", "remaining_time": "4:15:39", "throughput": "396.47", "total_tokens": 1392224}
|
| 20 |
+
{"current_steps": 100, "total_steps": 510, "loss": 0.3216, "learning_rate": 4.540492280890555e-05, "epoch": 1.927710843373494, "percentage": 19.61, "elapsed_time": "1:01:49", "remaining_time": "4:13:28", "throughput": "396.56", "total_tokens": 1471008}
|
| 21 |
+
{"current_steps": 105, "total_steps": 510, "loss": 0.3197, "learning_rate": 4.4950430682006e-05, "epoch": 2.0240963855421685, "percentage": 20.59, "elapsed_time": "1:05:12", "remaining_time": "4:11:30", "throughput": "395.40", "total_tokens": 1546912}
|
| 22 |
+
{"current_steps": 110, "total_steps": 510, "loss": 0.2904, "learning_rate": 4.447701436314176e-05, "epoch": 2.1204819277108435, "percentage": 21.57, "elapsed_time": "1:08:01", "remaining_time": "4:07:21", "throughput": "394.79", "total_tokens": 1611328}
|
| 23 |
+
{"current_steps": 115, "total_steps": 510, "loss": 0.2498, "learning_rate": 4.398512291636768e-05, "epoch": 2.216867469879518, "percentage": 22.55, "elapsed_time": "1:11:06", "remaining_time": "4:04:13", "throughput": "394.39", "total_tokens": 1682528}
|
| 24 |
+
{"current_steps": 120, "total_steps": 510, "loss": 0.269, "learning_rate": 4.347522293051648e-05, "epoch": 2.3132530120481927, "percentage": 23.53, "elapsed_time": "1:14:06", "remaining_time": "4:00:51", "throughput": "393.99", "total_tokens": 1751856}
|
| 25 |
+
{"current_steps": 125, "total_steps": 510, "loss": 0.2838, "learning_rate": 4.294779807661105e-05, "epoch": 2.4096385542168672, "percentage": 24.51, "elapsed_time": "1:17:27", "remaining_time": "3:58:35", "throughput": "393.80", "total_tokens": 1830288}
|
| 26 |
+
{"current_steps": 130, "total_steps": 510, "loss": 0.2466, "learning_rate": 4.2403348649073174e-05, "epoch": 2.5060240963855422, "percentage": 25.49, "elapsed_time": "1:20:39", "remaining_time": "3:55:47", "throughput": "393.67", "total_tokens": 1905296}
|
| 27 |
+
{"current_steps": 135, "total_steps": 510, "loss": 0.2272, "learning_rate": 4.184239109116393e-05, "epoch": 2.602409638554217, "percentage": 26.47, "elapsed_time": "1:23:42", "remaining_time": "3:52:30", "throughput": "393.15", "total_tokens": 1974464}
|
| 28 |
+
{"current_steps": 140, "total_steps": 510, "loss": 0.2484, "learning_rate": 4.126545750510605e-05, "epoch": 2.6987951807228914, "percentage": 27.45, "elapsed_time": "1:27:15", "remaining_time": "3:50:37", "throughput": "393.10", "total_tokens": 2058176}
|
| 29 |
+
{"current_steps": 145, "total_steps": 510, "loss": 0.2339, "learning_rate": 4.067309514735267e-05, "epoch": 2.7951807228915664, "percentage": 28.43, "elapsed_time": "1:30:11", "remaining_time": "3:47:03", "throughput": "392.63", "total_tokens": 2124912}
|
| 30 |
+
{"current_steps": 150, "total_steps": 510, "loss": 0.2597, "learning_rate": 4.0065865909481417e-05, "epoch": 2.891566265060241, "percentage": 29.41, "elapsed_time": "1:33:54", "remaining_time": "3:45:22", "throughput": "392.84", "total_tokens": 2213456}
|
| 31 |
+
{"current_steps": 155, "total_steps": 510, "loss": 0.2525, "learning_rate": 3.9444345785206285e-05, "epoch": 2.9879518072289155, "percentage": 30.39, "elapsed_time": "1:36:49", "remaining_time": "3:41:46", "throughput": "392.73", "total_tokens": 2281680}
|
| 32 |
+
{"current_steps": 160, "total_steps": 510, "loss": 0.1832, "learning_rate": 3.880912432401265e-05, "epoch": 3.0843373493975905, "percentage": 31.37, "elapsed_time": "1:39:47", "remaining_time": "3:38:16", "throughput": "392.41", "total_tokens": 2349408}
|
| 33 |
+
{"current_steps": 165, "total_steps": 510, "loss": 0.1519, "learning_rate": 3.81608040719339e-05, "epoch": 3.180722891566265, "percentage": 32.35, "elapsed_time": "1:42:57", "remaining_time": "3:35:17", "throughput": "392.60", "total_tokens": 2425456}
|
| 34 |
+
{"current_steps": 170, "total_steps": 510, "loss": 0.1707, "learning_rate": 3.7500000000000003e-05, "epoch": 3.2771084337349397, "percentage": 33.33, "elapsed_time": "1:45:53", "remaining_time": "3:31:46", "throughput": "392.58", "total_tokens": 2494064}
|
| 35 |
+
{"current_steps": 175, "total_steps": 510, "loss": 0.1603, "learning_rate": 3.6827338920900254e-05, "epoch": 3.3734939759036147, "percentage": 34.31, "elapsed_time": "1:49:12", "remaining_time": "3:29:03", "throughput": "392.77", "total_tokens": 2573616}
|
| 36 |
+
{"current_steps": 180, "total_steps": 510, "loss": 0.1683, "learning_rate": 3.6143458894413465e-05, "epoch": 3.4698795180722892, "percentage": 35.29, "elapsed_time": "1:52:39", "remaining_time": "3:26:32", "throughput": "393.19", "total_tokens": 2657744}
|
| 37 |
+
{"current_steps": 185, "total_steps": 510, "loss": 0.1734, "learning_rate": 3.544900862216959e-05, "epoch": 3.566265060240964, "percentage": 36.27, "elapsed_time": "1:55:27", "remaining_time": "3:22:50", "throughput": "392.80", "total_tokens": 2721200}
|
| 38 |
+
{"current_steps": 190, "total_steps": 510, "loss": 0.1543, "learning_rate": 3.474464683231698e-05, "epoch": 3.662650602409639, "percentage": 37.25, "elapsed_time": "1:58:49", "remaining_time": "3:20:07", "throughput": "392.50", "total_tokens": 2798320}
|
| 39 |
+
{"current_steps": 195, "total_steps": 510, "loss": 0.1601, "learning_rate": 3.403104165467883e-05, "epoch": 3.7590361445783134, "percentage": 38.24, "elapsed_time": "2:02:07", "remaining_time": "3:17:16", "throughput": "392.93", "total_tokens": 2879200}
|
| 40 |
+
{"current_steps": 200, "total_steps": 510, "loss": 0.1911, "learning_rate": 3.330886998699149e-05, "epoch": 3.855421686746988, "percentage": 39.22, "elapsed_time": "2:04:58", "remaining_time": "3:13:42", "throughput": "393.04", "total_tokens": 2947024}
|
| 41 |
+
{"current_steps": 205, "total_steps": 510, "loss": 0.1741, "learning_rate": 3.257881685282609e-05, "epoch": 3.9518072289156625, "percentage": 40.2, "elapsed_time": "2:07:52", "remaining_time": "3:10:14", "throughput": "393.20", "total_tokens": 3016656}
|
| 42 |
+
{"current_steps": 210, "total_steps": 510, "loss": 0.1334, "learning_rate": 3.1841574751802076e-05, "epoch": 4.048192771084337, "percentage": 41.18, "elapsed_time": "2:10:41", "remaining_time": "3:06:41", "throughput": "393.35", "total_tokens": 3084416}
|
| 43 |
+
{"current_steps": 215, "total_steps": 510, "loss": 0.1027, "learning_rate": 3.109784300270943e-05, "epoch": 4.144578313253012, "percentage": 42.16, "elapsed_time": "2:14:00", "remaining_time": "3:03:52", "throughput": "393.86", "total_tokens": 3166784}
|
| 44 |
+
{"current_steps": 220, "total_steps": 510, "loss": 0.0955, "learning_rate": 3.0348327080162435e-05, "epoch": 4.240963855421687, "percentage": 43.14, "elapsed_time": "2:17:00", "remaining_time": "3:00:36", "throughput": "394.08", "total_tokens": 3239584}
|
| 45 |
+
{"current_steps": 225, "total_steps": 510, "loss": 0.1006, "learning_rate": 2.9593737945414264e-05, "epoch": 4.337349397590361, "percentage": 44.12, "elapsed_time": "2:20:02", "remaining_time": "2:57:23", "throughput": "394.31", "total_tokens": 3313360}
|
| 46 |
+
{"current_steps": 230, "total_steps": 510, "loss": 0.1007, "learning_rate": 2.8834791371967142e-05, "epoch": 4.433734939759036, "percentage": 45.1, "elapsed_time": "2:22:43", "remaining_time": "2:53:45", "throughput": "394.43", "total_tokens": 3377840}
|
| 47 |
+
{"current_steps": 235, "total_steps": 510, "loss": 0.1033, "learning_rate": 2.8072207266617855e-05, "epoch": 4.530120481927711, "percentage": 46.08, "elapsed_time": "2:25:54", "remaining_time": "2:50:44", "throughput": "394.76", "total_tokens": 3455904}
|
| 48 |
+
{"current_steps": 240, "total_steps": 510, "loss": 0.1023, "learning_rate": 2.7306708986582553e-05, "epoch": 4.626506024096385, "percentage": 47.06, "elapsed_time": "2:28:54", "remaining_time": "2:47:31", "throughput": "395.01", "total_tokens": 3529360}
|
| 49 |
+
{"current_steps": 245, "total_steps": 510, "loss": 0.1121, "learning_rate": 2.653902265334858e-05, "epoch": 4.72289156626506, "percentage": 48.04, "elapsed_time": "2:32:00", "remaining_time": "2:44:25", "throughput": "395.28", "total_tokens": 3605344}
|
| 50 |
+
{"current_steps": 250, "total_steps": 510, "loss": 0.1028, "learning_rate": 2.5769876463904265e-05, "epoch": 4.8192771084337345, "percentage": 49.02, "elapsed_time": "2:35:01", "remaining_time": "2:41:13", "throughput": "395.48", "total_tokens": 3678352}
|
| 51 |
+
{"current_steps": 255, "total_steps": 510, "loss": 0.1055, "learning_rate": 2.5e-05, "epoch": 4.9156626506024095, "percentage": 50.0, "elapsed_time": "2:38:03", "remaining_time": "2:38:03", "throughput": "395.69", "total_tokens": 3752608}
|
| 52 |
+
{"current_steps": 260, "total_steps": 510, "loss": 0.1037, "learning_rate": 2.4230123536095748e-05, "epoch": 5.0120481927710845, "percentage": 50.98, "elapsed_time": "2:40:50", "remaining_time": "2:34:39", "throughput": "395.79", "total_tokens": 3819744}
|
| 53 |
+
{"current_steps": 265, "total_steps": 510, "loss": 0.0633, "learning_rate": 2.346097734665143e-05, "epoch": 5.108433734939759, "percentage": 51.96, "elapsed_time": "2:43:58", "remaining_time": "2:31:36", "throughput": "396.05", "total_tokens": 3896592}
|
| 54 |
+
{"current_steps": 270, "total_steps": 510, "loss": 0.0521, "learning_rate": 2.2693291013417453e-05, "epoch": 5.204819277108434, "percentage": 52.94, "elapsed_time": "2:47:01", "remaining_time": "2:28:28", "throughput": "396.24", "total_tokens": 3970976}
|
| 55 |
+
{"current_steps": 275, "total_steps": 510, "loss": 0.0625, "learning_rate": 2.192779273338215e-05, "epoch": 5.301204819277109, "percentage": 53.92, "elapsed_time": "2:50:16", "remaining_time": "2:25:30", "throughput": "396.59", "total_tokens": 4051760}
|
| 56 |
+
{"current_steps": 280, "total_steps": 510, "loss": 0.059, "learning_rate": 2.116520862803286e-05, "epoch": 5.397590361445783, "percentage": 54.9, "elapsed_time": "2:53:14", "remaining_time": "2:22:18", "throughput": "396.74", "total_tokens": 4124096}
|
| 57 |
+
{"current_steps": 285, "total_steps": 510, "loss": 0.0648, "learning_rate": 2.0406262054585738e-05, "epoch": 5.493975903614458, "percentage": 55.88, "elapsed_time": "2:55:56", "remaining_time": "2:18:54", "throughput": "396.77", "total_tokens": 4188448}
|
| 58 |
+
{"current_steps": 290, "total_steps": 510, "loss": 0.0709, "learning_rate": 1.965167291983757e-05, "epoch": 5.590361445783133, "percentage": 56.86, "elapsed_time": "2:58:55", "remaining_time": "2:15:43", "throughput": "396.92", "total_tokens": 4261056}
|
| 59 |
+
{"current_steps": 295, "total_steps": 510, "loss": 0.0641, "learning_rate": 1.890215699729057e-05, "epoch": 5.686746987951807, "percentage": 57.84, "elapsed_time": "3:01:45", "remaining_time": "2:12:27", "throughput": "396.97", "total_tokens": 4329024}
|
| 60 |
+
{"current_steps": 300, "total_steps": 510, "loss": 0.0689, "learning_rate": 1.815842524819793e-05, "epoch": 5.783132530120482, "percentage": 58.82, "elapsed_time": "3:04:54", "remaining_time": "2:09:26", "throughput": "397.19", "total_tokens": 4406624}
|
| 61 |
+
{"current_steps": 305, "total_steps": 510, "loss": 0.055, "learning_rate": 1.7421183147173915e-05, "epoch": 5.879518072289157, "percentage": 59.8, "elapsed_time": "3:07:55", "remaining_time": "2:06:18", "throughput": "397.36", "total_tokens": 4480352}
|
| 62 |
+
{"current_steps": 310, "total_steps": 510, "loss": 0.0626, "learning_rate": 1.6691130013008514e-05, "epoch": 5.975903614457831, "percentage": 60.78, "elapsed_time": "3:10:55", "remaining_time": "2:03:10", "throughput": "397.56", "total_tokens": 4554080}
|
| 63 |
+
{"current_steps": 315, "total_steps": 510, "loss": 0.0465, "learning_rate": 1.5968958345321178e-05, "epoch": 6.072289156626506, "percentage": 61.76, "elapsed_time": "3:13:56", "remaining_time": "2:00:03", "throughput": "397.77", "total_tokens": 4628576}
|
| 64 |
+
{"current_steps": 320, "total_steps": 510, "loss": 0.0421, "learning_rate": 1.5255353167683017e-05, "epoch": 6.168674698795181, "percentage": 62.75, "elapsed_time": "3:17:00", "remaining_time": "1:56:58", "throughput": "397.98", "total_tokens": 4704512}
|
| 65 |
+
{"current_steps": 325, "total_steps": 510, "loss": 0.0303, "learning_rate": 1.4550991377830426e-05, "epoch": 6.265060240963855, "percentage": 63.73, "elapsed_time": "3:19:56", "remaining_time": "1:53:49", "throughput": "398.18", "total_tokens": 4776912}
|
| 66 |
+
{"current_steps": 330, "total_steps": 510, "loss": 0.0337, "learning_rate": 1.3856541105586545e-05, "epoch": 6.36144578313253, "percentage": 64.71, "elapsed_time": "3:23:06", "remaining_time": "1:50:47", "throughput": "398.43", "total_tokens": 4855600}
|
| 67 |
+
{"current_steps": 335, "total_steps": 510, "loss": 0.0333, "learning_rate": 1.3172661079099752e-05, "epoch": 6.457831325301205, "percentage": 65.69, "elapsed_time": "3:26:04", "remaining_time": "1:47:38", "throughput": "398.54", "total_tokens": 4927600}
|
| 68 |
+
{"current_steps": 340, "total_steps": 510, "loss": 0.039, "learning_rate": 1.2500000000000006e-05, "epoch": 6.554216867469879, "percentage": 66.67, "elapsed_time": "3:29:07", "remaining_time": "1:44:33", "throughput": "398.74", "total_tokens": 5003184}
|
| 69 |
+
{"current_steps": 343, "total_steps": 510, "epoch": 6.612048192771084, "percentage": 67.25, "elapsed_time": "3:31:15", "remaining_time": "1:42:51", "throughput": "398.58", "total_tokens": 5052448}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,587 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.612048192771084,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 343,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0963855421686747,
|
| 13 |
+
"grad_norm": 1.7634485960006714,
|
| 14 |
+
"learning_rate": 4.998814299283415e-05,
|
| 15 |
+
"loss": 0.8996,
|
| 16 |
+
"num_input_tokens_seen": 78528,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.1927710843373494,
|
| 21 |
+
"grad_norm": 1.3068124055862427,
|
| 22 |
+
"learning_rate": 4.995258321842611e-05,
|
| 23 |
+
"loss": 0.6806,
|
| 24 |
+
"num_input_tokens_seen": 159120,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.2891566265060241,
|
| 29 |
+
"grad_norm": 1.2104840278625488,
|
| 30 |
+
"learning_rate": 4.989335440737586e-05,
|
| 31 |
+
"loss": 0.618,
|
| 32 |
+
"num_input_tokens_seen": 223552,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.3855421686746988,
|
| 37 |
+
"grad_norm": 1.4112542867660522,
|
| 38 |
+
"learning_rate": 4.98105127417984e-05,
|
| 39 |
+
"loss": 0.5594,
|
| 40 |
+
"num_input_tokens_seen": 290944,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.4819277108433735,
|
| 45 |
+
"grad_norm": 0.9026587605476379,
|
| 46 |
+
"learning_rate": 4.9704136802031485e-05,
|
| 47 |
+
"loss": 0.5253,
|
| 48 |
+
"num_input_tokens_seen": 364064,
|
| 49 |
+
"step": 25
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.5783132530120482,
|
| 53 |
+
"grad_norm": 0.9427546858787537,
|
| 54 |
+
"learning_rate": 4.957432749209755e-05,
|
| 55 |
+
"loss": 0.4794,
|
| 56 |
+
"num_input_tokens_seen": 440176,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.6746987951807228,
|
| 61 |
+
"grad_norm": 1.0594468116760254,
|
| 62 |
+
"learning_rate": 4.942120794399002e-05,
|
| 63 |
+
"loss": 0.4546,
|
| 64 |
+
"num_input_tokens_seen": 517184,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7710843373493976,
|
| 69 |
+
"grad_norm": 0.9458279013633728,
|
| 70 |
+
"learning_rate": 4.9244923400875245e-05,
|
| 71 |
+
"loss": 0.4703,
|
| 72 |
+
"num_input_tokens_seen": 591424,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.8674698795180723,
|
| 77 |
+
"grad_norm": 1.1610336303710938,
|
| 78 |
+
"learning_rate": 4.9045641079320484e-05,
|
| 79 |
+
"loss": 0.4407,
|
| 80 |
+
"num_input_tokens_seen": 662784,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.963855421686747,
|
| 85 |
+
"grad_norm": 1.0153354406356812,
|
| 86 |
+
"learning_rate": 4.882355001067892e-05,
|
| 87 |
+
"loss": 0.4425,
|
| 88 |
+
"num_input_tokens_seen": 734784,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.0602409638554218,
|
| 93 |
+
"grad_norm": 1.0889695882797241,
|
| 94 |
+
"learning_rate": 4.857886086178194e-05,
|
| 95 |
+
"loss": 0.4081,
|
| 96 |
+
"num_input_tokens_seen": 808336,
|
| 97 |
+
"step": 55
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.1566265060240963,
|
| 101 |
+
"grad_norm": 0.9168598055839539,
|
| 102 |
+
"learning_rate": 4.8311805735108894e-05,
|
| 103 |
+
"loss": 0.4002,
|
| 104 |
+
"num_input_tokens_seen": 882672,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.2530120481927711,
|
| 109 |
+
"grad_norm": 0.8168660998344421,
|
| 110 |
+
"learning_rate": 4.802263794862385e-05,
|
| 111 |
+
"loss": 0.3587,
|
| 112 |
+
"num_input_tokens_seen": 947680,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.3493975903614457,
|
| 117 |
+
"grad_norm": 1.0652003288269043,
|
| 118 |
+
"learning_rate": 4.7711631795488096e-05,
|
| 119 |
+
"loss": 0.356,
|
| 120 |
+
"num_input_tokens_seen": 1022112,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.4457831325301205,
|
| 125 |
+
"grad_norm": 1.1781517267227173,
|
| 126 |
+
"learning_rate": 4.7379082283876566e-05,
|
| 127 |
+
"loss": 0.3639,
|
| 128 |
+
"num_input_tokens_seen": 1091744,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.5421686746987953,
|
| 133 |
+
"grad_norm": 1.0550976991653442,
|
| 134 |
+
"learning_rate": 4.702530485714461e-05,
|
| 135 |
+
"loss": 0.3288,
|
| 136 |
+
"num_input_tokens_seen": 1163728,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.6385542168674698,
|
| 141 |
+
"grad_norm": 1.3946661949157715,
|
| 142 |
+
"learning_rate": 4.665063509461097e-05,
|
| 143 |
+
"loss": 0.3563,
|
| 144 |
+
"num_input_tokens_seen": 1245728,
|
| 145 |
+
"step": 85
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.7349397590361446,
|
| 149 |
+
"grad_norm": 1.1458536386489868,
|
| 150 |
+
"learning_rate": 4.625542839324036e-05,
|
| 151 |
+
"loss": 0.3642,
|
| 152 |
+
"num_input_tokens_seen": 1315056,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.8313253012048194,
|
| 157 |
+
"grad_norm": 1.0227209329605103,
|
| 158 |
+
"learning_rate": 4.584005963052799e-05,
|
| 159 |
+
"loss": 0.3407,
|
| 160 |
+
"num_input_tokens_seen": 1392224,
|
| 161 |
+
"step": 95
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.927710843373494,
|
| 165 |
+
"grad_norm": 1.0699985027313232,
|
| 166 |
+
"learning_rate": 4.540492280890555e-05,
|
| 167 |
+
"loss": 0.3216,
|
| 168 |
+
"num_input_tokens_seen": 1471008,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.0240963855421685,
|
| 173 |
+
"grad_norm": 0.8573477268218994,
|
| 174 |
+
"learning_rate": 4.4950430682006e-05,
|
| 175 |
+
"loss": 0.3197,
|
| 176 |
+
"num_input_tokens_seen": 1546912,
|
| 177 |
+
"step": 105
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.1204819277108435,
|
| 181 |
+
"grad_norm": 1.1516242027282715,
|
| 182 |
+
"learning_rate": 4.447701436314176e-05,
|
| 183 |
+
"loss": 0.2904,
|
| 184 |
+
"num_input_tokens_seen": 1611328,
|
| 185 |
+
"step": 110
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.216867469879518,
|
| 189 |
+
"grad_norm": 1.0890793800354004,
|
| 190 |
+
"learning_rate": 4.398512291636768e-05,
|
| 191 |
+
"loss": 0.2498,
|
| 192 |
+
"num_input_tokens_seen": 1682528,
|
| 193 |
+
"step": 115
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.3132530120481927,
|
| 197 |
+
"grad_norm": 1.3621636629104614,
|
| 198 |
+
"learning_rate": 4.347522293051648e-05,
|
| 199 |
+
"loss": 0.269,
|
| 200 |
+
"num_input_tokens_seen": 1751856,
|
| 201 |
+
"step": 120
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.4096385542168672,
|
| 205 |
+
"grad_norm": 1.338083028793335,
|
| 206 |
+
"learning_rate": 4.294779807661105e-05,
|
| 207 |
+
"loss": 0.2838,
|
| 208 |
+
"num_input_tokens_seen": 1830288,
|
| 209 |
+
"step": 125
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.5060240963855422,
|
| 213 |
+
"grad_norm": 1.2083592414855957,
|
| 214 |
+
"learning_rate": 4.2403348649073174e-05,
|
| 215 |
+
"loss": 0.2466,
|
| 216 |
+
"num_input_tokens_seen": 1905296,
|
| 217 |
+
"step": 130
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.602409638554217,
|
| 221 |
+
"grad_norm": 1.35024094581604,
|
| 222 |
+
"learning_rate": 4.184239109116393e-05,
|
| 223 |
+
"loss": 0.2272,
|
| 224 |
+
"num_input_tokens_seen": 1974464,
|
| 225 |
+
"step": 135
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.6987951807228914,
|
| 229 |
+
"grad_norm": 1.3738912343978882,
|
| 230 |
+
"learning_rate": 4.126545750510605e-05,
|
| 231 |
+
"loss": 0.2484,
|
| 232 |
+
"num_input_tokens_seen": 2058176,
|
| 233 |
+
"step": 140
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.7951807228915664,
|
| 237 |
+
"grad_norm": 1.5877448320388794,
|
| 238 |
+
"learning_rate": 4.067309514735267e-05,
|
| 239 |
+
"loss": 0.2339,
|
| 240 |
+
"num_input_tokens_seen": 2124912,
|
| 241 |
+
"step": 145
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.891566265060241,
|
| 245 |
+
"grad_norm": 1.3735121488571167,
|
| 246 |
+
"learning_rate": 4.0065865909481417e-05,
|
| 247 |
+
"loss": 0.2597,
|
| 248 |
+
"num_input_tokens_seen": 2213456,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.9879518072289155,
|
| 253 |
+
"grad_norm": 1.6480368375778198,
|
| 254 |
+
"learning_rate": 3.9444345785206285e-05,
|
| 255 |
+
"loss": 0.2525,
|
| 256 |
+
"num_input_tokens_seen": 2281680,
|
| 257 |
+
"step": 155
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.0843373493975905,
|
| 261 |
+
"grad_norm": 1.2931358814239502,
|
| 262 |
+
"learning_rate": 3.880912432401265e-05,
|
| 263 |
+
"loss": 0.1832,
|
| 264 |
+
"num_input_tokens_seen": 2349408,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 3.180722891566265,
|
| 269 |
+
"grad_norm": 1.4131468534469604,
|
| 270 |
+
"learning_rate": 3.81608040719339e-05,
|
| 271 |
+
"loss": 0.1519,
|
| 272 |
+
"num_input_tokens_seen": 2425456,
|
| 273 |
+
"step": 165
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 3.2771084337349397,
|
| 277 |
+
"grad_norm": 1.6228159666061401,
|
| 278 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 279 |
+
"loss": 0.1707,
|
| 280 |
+
"num_input_tokens_seen": 2494064,
|
| 281 |
+
"step": 170
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.3734939759036147,
|
| 285 |
+
"grad_norm": 1.1356842517852783,
|
| 286 |
+
"learning_rate": 3.6827338920900254e-05,
|
| 287 |
+
"loss": 0.1603,
|
| 288 |
+
"num_input_tokens_seen": 2573616,
|
| 289 |
+
"step": 175
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.4698795180722892,
|
| 293 |
+
"grad_norm": 1.3535553216934204,
|
| 294 |
+
"learning_rate": 3.6143458894413465e-05,
|
| 295 |
+
"loss": 0.1683,
|
| 296 |
+
"num_input_tokens_seen": 2657744,
|
| 297 |
+
"step": 180
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.566265060240964,
|
| 301 |
+
"grad_norm": 1.3832409381866455,
|
| 302 |
+
"learning_rate": 3.544900862216959e-05,
|
| 303 |
+
"loss": 0.1734,
|
| 304 |
+
"num_input_tokens_seen": 2721200,
|
| 305 |
+
"step": 185
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.662650602409639,
|
| 309 |
+
"grad_norm": 1.6430705785751343,
|
| 310 |
+
"learning_rate": 3.474464683231698e-05,
|
| 311 |
+
"loss": 0.1543,
|
| 312 |
+
"num_input_tokens_seen": 2798320,
|
| 313 |
+
"step": 190
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.7590361445783134,
|
| 317 |
+
"grad_norm": 1.7706836462020874,
|
| 318 |
+
"learning_rate": 3.403104165467883e-05,
|
| 319 |
+
"loss": 0.1601,
|
| 320 |
+
"num_input_tokens_seen": 2879200,
|
| 321 |
+
"step": 195
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.855421686746988,
|
| 325 |
+
"grad_norm": 1.7721610069274902,
|
| 326 |
+
"learning_rate": 3.330886998699149e-05,
|
| 327 |
+
"loss": 0.1911,
|
| 328 |
+
"num_input_tokens_seen": 2947024,
|
| 329 |
+
"step": 200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.9518072289156625,
|
| 333 |
+
"grad_norm": 1.666278600692749,
|
| 334 |
+
"learning_rate": 3.257881685282609e-05,
|
| 335 |
+
"loss": 0.1741,
|
| 336 |
+
"num_input_tokens_seen": 3016656,
|
| 337 |
+
"step": 205
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4.048192771084337,
|
| 341 |
+
"grad_norm": 1.099639892578125,
|
| 342 |
+
"learning_rate": 3.1841574751802076e-05,
|
| 343 |
+
"loss": 0.1334,
|
| 344 |
+
"num_input_tokens_seen": 3084416,
|
| 345 |
+
"step": 210
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.144578313253012,
|
| 349 |
+
"grad_norm": 1.5020925998687744,
|
| 350 |
+
"learning_rate": 3.109784300270943e-05,
|
| 351 |
+
"loss": 0.1027,
|
| 352 |
+
"num_input_tokens_seen": 3166784,
|
| 353 |
+
"step": 215
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.240963855421687,
|
| 357 |
+
"grad_norm": 2.203794240951538,
|
| 358 |
+
"learning_rate": 3.0348327080162435e-05,
|
| 359 |
+
"loss": 0.0955,
|
| 360 |
+
"num_input_tokens_seen": 3239584,
|
| 361 |
+
"step": 220
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.337349397590361,
|
| 365 |
+
"grad_norm": 1.7183223962783813,
|
| 366 |
+
"learning_rate": 2.9593737945414264e-05,
|
| 367 |
+
"loss": 0.1006,
|
| 368 |
+
"num_input_tokens_seen": 3313360,
|
| 369 |
+
"step": 225
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.433734939759036,
|
| 373 |
+
"grad_norm": 1.4102908372879028,
|
| 374 |
+
"learning_rate": 2.8834791371967142e-05,
|
| 375 |
+
"loss": 0.1007,
|
| 376 |
+
"num_input_tokens_seen": 3377840,
|
| 377 |
+
"step": 230
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 4.530120481927711,
|
| 381 |
+
"grad_norm": 1.214020013809204,
|
| 382 |
+
"learning_rate": 2.8072207266617855e-05,
|
| 383 |
+
"loss": 0.1033,
|
| 384 |
+
"num_input_tokens_seen": 3455904,
|
| 385 |
+
"step": 235
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 4.626506024096385,
|
| 389 |
+
"grad_norm": 1.5255635976791382,
|
| 390 |
+
"learning_rate": 2.7306708986582553e-05,
|
| 391 |
+
"loss": 0.1023,
|
| 392 |
+
"num_input_tokens_seen": 3529360,
|
| 393 |
+
"step": 240
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.72289156626506,
|
| 397 |
+
"grad_norm": 1.6624009609222412,
|
| 398 |
+
"learning_rate": 2.653902265334858e-05,
|
| 399 |
+
"loss": 0.1121,
|
| 400 |
+
"num_input_tokens_seen": 3605344,
|
| 401 |
+
"step": 245
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.8192771084337345,
|
| 405 |
+
"grad_norm": 1.7999521493911743,
|
| 406 |
+
"learning_rate": 2.5769876463904265e-05,
|
| 407 |
+
"loss": 0.1028,
|
| 408 |
+
"num_input_tokens_seen": 3678352,
|
| 409 |
+
"step": 250
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.9156626506024095,
|
| 413 |
+
"grad_norm": 2.1297786235809326,
|
| 414 |
+
"learning_rate": 2.5e-05,
|
| 415 |
+
"loss": 0.1055,
|
| 416 |
+
"num_input_tokens_seen": 3752608,
|
| 417 |
+
"step": 255
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 5.0120481927710845,
|
| 421 |
+
"grad_norm": 1.215146780014038,
|
| 422 |
+
"learning_rate": 2.4230123536095748e-05,
|
| 423 |
+
"loss": 0.1037,
|
| 424 |
+
"num_input_tokens_seen": 3819744,
|
| 425 |
+
"step": 260
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 5.108433734939759,
|
| 429 |
+
"grad_norm": 1.448801040649414,
|
| 430 |
+
"learning_rate": 2.346097734665143e-05,
|
| 431 |
+
"loss": 0.0633,
|
| 432 |
+
"num_input_tokens_seen": 3896592,
|
| 433 |
+
"step": 265
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.204819277108434,
|
| 437 |
+
"grad_norm": 1.220989465713501,
|
| 438 |
+
"learning_rate": 2.2693291013417453e-05,
|
| 439 |
+
"loss": 0.0521,
|
| 440 |
+
"num_input_tokens_seen": 3970976,
|
| 441 |
+
"step": 270
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 5.301204819277109,
|
| 445 |
+
"grad_norm": 1.3077821731567383,
|
| 446 |
+
"learning_rate": 2.192779273338215e-05,
|
| 447 |
+
"loss": 0.0625,
|
| 448 |
+
"num_input_tokens_seen": 4051760,
|
| 449 |
+
"step": 275
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 5.397590361445783,
|
| 453 |
+
"grad_norm": 2.02695369720459,
|
| 454 |
+
"learning_rate": 2.116520862803286e-05,
|
| 455 |
+
"loss": 0.059,
|
| 456 |
+
"num_input_tokens_seen": 4124096,
|
| 457 |
+
"step": 280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 5.493975903614458,
|
| 461 |
+
"grad_norm": 1.6377320289611816,
|
| 462 |
+
"learning_rate": 2.0406262054585738e-05,
|
| 463 |
+
"loss": 0.0648,
|
| 464 |
+
"num_input_tokens_seen": 4188448,
|
| 465 |
+
"step": 285
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 5.590361445783133,
|
| 469 |
+
"grad_norm": 1.6187361478805542,
|
| 470 |
+
"learning_rate": 1.965167291983757e-05,
|
| 471 |
+
"loss": 0.0709,
|
| 472 |
+
"num_input_tokens_seen": 4261056,
|
| 473 |
+
"step": 290
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 5.686746987951807,
|
| 477 |
+
"grad_norm": 1.4855268001556396,
|
| 478 |
+
"learning_rate": 1.890215699729057e-05,
|
| 479 |
+
"loss": 0.0641,
|
| 480 |
+
"num_input_tokens_seen": 4329024,
|
| 481 |
+
"step": 295
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 5.783132530120482,
|
| 485 |
+
"grad_norm": 1.4216831922531128,
|
| 486 |
+
"learning_rate": 1.815842524819793e-05,
|
| 487 |
+
"loss": 0.0689,
|
| 488 |
+
"num_input_tokens_seen": 4406624,
|
| 489 |
+
"step": 300
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 5.879518072289157,
|
| 493 |
+
"grad_norm": 1.7383759021759033,
|
| 494 |
+
"learning_rate": 1.7421183147173915e-05,
|
| 495 |
+
"loss": 0.055,
|
| 496 |
+
"num_input_tokens_seen": 4480352,
|
| 497 |
+
"step": 305
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 5.975903614457831,
|
| 501 |
+
"grad_norm": 1.5599803924560547,
|
| 502 |
+
"learning_rate": 1.6691130013008514e-05,
|
| 503 |
+
"loss": 0.0626,
|
| 504 |
+
"num_input_tokens_seen": 4554080,
|
| 505 |
+
"step": 310
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 6.072289156626506,
|
| 509 |
+
"grad_norm": 1.028124213218689,
|
| 510 |
+
"learning_rate": 1.5968958345321178e-05,
|
| 511 |
+
"loss": 0.0465,
|
| 512 |
+
"num_input_tokens_seen": 4628576,
|
| 513 |
+
"step": 315
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 6.168674698795181,
|
| 517 |
+
"grad_norm": 1.4686311483383179,
|
| 518 |
+
"learning_rate": 1.5255353167683017e-05,
|
| 519 |
+
"loss": 0.0421,
|
| 520 |
+
"num_input_tokens_seen": 4704512,
|
| 521 |
+
"step": 320
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 6.265060240963855,
|
| 525 |
+
"grad_norm": 1.1644634008407593,
|
| 526 |
+
"learning_rate": 1.4550991377830426e-05,
|
| 527 |
+
"loss": 0.0303,
|
| 528 |
+
"num_input_tokens_seen": 4776912,
|
| 529 |
+
"step": 325
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 6.36144578313253,
|
| 533 |
+
"grad_norm": 1.090997338294983,
|
| 534 |
+
"learning_rate": 1.3856541105586545e-05,
|
| 535 |
+
"loss": 0.0337,
|
| 536 |
+
"num_input_tokens_seen": 4855600,
|
| 537 |
+
"step": 330
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 6.457831325301205,
|
| 541 |
+
"grad_norm": 1.4336110353469849,
|
| 542 |
+
"learning_rate": 1.3172661079099752e-05,
|
| 543 |
+
"loss": 0.0333,
|
| 544 |
+
"num_input_tokens_seen": 4927600,
|
| 545 |
+
"step": 335
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 6.554216867469879,
|
| 549 |
+
"grad_norm": 1.3488271236419678,
|
| 550 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 551 |
+
"loss": 0.039,
|
| 552 |
+
"num_input_tokens_seen": 5003184,
|
| 553 |
+
"step": 340
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.612048192771084,
|
| 557 |
+
"num_input_tokens_seen": 5052448,
|
| 558 |
+
"step": 343,
|
| 559 |
+
"total_flos": 2.28822660837802e+17,
|
| 560 |
+
"train_loss": 0.2300173058541106,
|
| 561 |
+
"train_runtime": 12675.9679,
|
| 562 |
+
"train_samples_per_second": 0.655,
|
| 563 |
+
"train_steps_per_second": 0.04
|
| 564 |
+
}
|
| 565 |
+
],
|
| 566 |
+
"logging_steps": 5,
|
| 567 |
+
"max_steps": 510,
|
| 568 |
+
"num_input_tokens_seen": 5052448,
|
| 569 |
+
"num_train_epochs": 10,
|
| 570 |
+
"save_steps": 100,
|
| 571 |
+
"stateful_callbacks": {
|
| 572 |
+
"TrainerControl": {
|
| 573 |
+
"args": {
|
| 574 |
+
"should_epoch_stop": false,
|
| 575 |
+
"should_evaluate": false,
|
| 576 |
+
"should_log": false,
|
| 577 |
+
"should_save": true,
|
| 578 |
+
"should_training_stop": false
|
| 579 |
+
},
|
| 580 |
+
"attributes": {}
|
| 581 |
+
}
|
| 582 |
+
},
|
| 583 |
+
"total_flos": 2.28822660837802e+17,
|
| 584 |
+
"train_batch_size": 2,
|
| 585 |
+
"trial_name": null,
|
| 586 |
+
"trial_params": null
|
| 587 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0f1ce65e694fb8d47352b5be6e30ed8bfc2d47f5d03fe1d7162c1813af93ef9
|
| 3 |
+
size 5368
|
training_args.yaml
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
bf16: true
|
| 2 |
+
cutoff_len: 4096
|
| 3 |
+
dataset: gpt4_judge,Judge
|
| 4 |
+
dataset_dir: data
|
| 5 |
+
ddp_timeout: 180000000
|
| 6 |
+
do_train: true
|
| 7 |
+
finetuning_type: lora
|
| 8 |
+
flash_attn: auto
|
| 9 |
+
gradient_accumulation_steps: 8
|
| 10 |
+
include_num_input_tokens_seen: true
|
| 11 |
+
learning_rate: 5.0e-05
|
| 12 |
+
logging_steps: 5
|
| 13 |
+
lora_alpha: 16
|
| 14 |
+
lora_dropout: 0
|
| 15 |
+
lora_rank: 16
|
| 16 |
+
lora_target: all
|
| 17 |
+
lr_scheduler_type: cosine
|
| 18 |
+
max_grad_norm: 1.0
|
| 19 |
+
max_samples: 100000
|
| 20 |
+
model_name_or_path: /home/marl/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/07eb05b21d191a58c577b4a45982fe0c049d0693
|
| 21 |
+
num_train_epochs: 10.0
|
| 22 |
+
optim: adamw_torch
|
| 23 |
+
output_dir: saves/LLaMA3-8B-Chat/lora/JudgePierce
|
| 24 |
+
packing: false
|
| 25 |
+
per_device_train_batch_size: 2
|
| 26 |
+
pissa_convert: true
|
| 27 |
+
pissa_init: true
|
| 28 |
+
plot_loss: true
|
| 29 |
+
preprocessing_num_workers: 16
|
| 30 |
+
quantization_method: bitsandbytes
|
| 31 |
+
report_to: none
|
| 32 |
+
rope_scaling: linear
|
| 33 |
+
save_steps: 100
|
| 34 |
+
stage: sft
|
| 35 |
+
template: llama3
|
| 36 |
+
use_dora: true
|
| 37 |
+
use_rslora: true
|
| 38 |
+
use_unsloth: true
|
| 39 |
+
warmup_steps: 0
|
training_loss.png
ADDED
|