abarbosa commited on
Commit
e99d4f2
·
verified ·
1 Parent(s): 9e85445

Pushing fine-tuned model to Hugging Face Hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ language:
4
+ - pt
5
+ - en
6
+ tags:
7
+ - aes
8
+ datasets:
9
+ - kamel-usp/aes_enem_dataset
10
+ base_model: meta-llama/Llama-3.1-8B
11
+ metrics:
12
+ - accuracy
13
+ - qwk
14
+ library_name: peft
15
+ model-index:
16
+ - name: Llama-3.1-8B-llama31_classification_lora-C3-full_context
17
+ results:
18
+ - task:
19
+ type: text-classification
20
+ name: Automated Essay Score
21
+ dataset:
22
+ name: Automated Essay Score ENEM Dataset
23
+ type: kamel-usp/aes_enem_dataset
24
+ config: JBCS2025
25
+ split: test
26
+ metrics:
27
+ - name: Macro F1
28
+ type: f1
29
+ value: 0.2430887887213188
30
+ - name: QWK
31
+ type: qwk
32
+ value: 0.3373259954677889
33
+ - name: Weighted Macro F1
34
+ type: f1
35
+ value: 0.3410931961351028
36
+ ---
37
+ # Model ID: Llama-3.1-8B-llama31_classification_lora-C3-full_context
38
+ ## Results
39
+ | | test_data |
40
+ |:-----------------|------------:|
41
+ | eval_accuracy | 0.355072 |
42
+ | eval_RMSE | 55.6386 |
43
+ | eval_QWK | 0.337326 |
44
+ | eval_Macro_F1 | 0.243089 |
45
+ | eval_Weighted_F1 | 0.341093 |
46
+ | eval_Micro_F1 | 0.355072 |
47
+ | eval_HDIV | 0.101449 |
48
+
adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "classifier",
23
+ "score"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 8,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "gate_proj",
31
+ "q_proj",
32
+ "down_proj",
33
+ "k_proj",
34
+ "up_proj",
35
+ "v_proj",
36
+ "o_proj"
37
+ ],
38
+ "task_type": "SEQ_CLS",
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_rslora": false
42
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a430eddd16cf564be7c5f3ba52bc914667dc1b3d13775320e1e79aed7ca7a05
3
+ size 83994544
emissions.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
+ 2025-06-30T03:48:39,jbcs2025,c86015d0-a25f-4904-b953-6bb645d815ca,Llama-3.1-8B-llama31_classification_lora-C3-full_context,3924.981270377524,0.3845232224811884,9.796816748738347e-05,66.0,645.3430853796708,70.0,0.07086445274437617,0.6463139187173397,0.07501272868247344,0.7921911001441895,Japan,JPN,,,,Linux-5.15.0-130-generic-x86_64-with-glibc2.35,3.12.11,3.0.2,192,INTEL(R) XEON(R) PLATINUM 8558,1,1 x NVIDIA H200,139.69,35.69,2015.3516235351562,machine,N,1.0
evaluation_results.csv ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ eval_loss,eval_model_preparation_time,eval_accuracy,eval_RMSE,eval_QWK,eval_HDIV,eval_Macro_F1,eval_Micro_F1,eval_Weighted_F1,eval_TP_0,eval_TN_0,eval_FP_0,eval_FN_0,eval_TP_1,eval_TN_1,eval_FP_1,eval_FN_1,eval_TP_2,eval_TN_2,eval_FP_2,eval_FN_2,eval_TP_3,eval_TN_3,eval_FP_3,eval_FN_3,eval_TP_4,eval_TN_4,eval_FP_4,eval_FN_4,eval_TP_5,eval_TN_5,eval_FP_5,eval_FN_5,eval_runtime,eval_samples_per_second,eval_steps_per_second,epoch,reference,timestamp,id
2
+ 3.058149814605713,0.0126,0.3787878787878788,55.59594491425693,-0.06884288073161438,0.06060606060606055,0.1111111111111111,0.3787878787878788,0.24455077086656035,0,131,0,1,2,96,12,22,0,126,0,6,48,9,70,5,0,92,0,40,0,124,0,8,22.3664,5.902,0.402,-1,validation_before_training,2025-06-30 02:43:29,Llama-3.1-8B-llama31_classification_lora-C3-full_context
3
+ 1.8632748126983643,0.0126,0.4696969696969697,49.11335065052284,0.4302446642373763,0.06818181818181823,0.2994777444777445,0.4696969696969697,0.4585972108699382,0,131,0,1,6,94,14,18,2,118,8,4,24,65,14,29,29,61,31,11,1,121,3,7,22.2418,5.935,0.405,15.0,validation_after_training,2025-06-30 02:43:29,Llama-3.1-8B-llama31_classification_lora-C3-full_context
4
+ 1.99528968334198,0.0126,0.35507246376811596,55.638585297552666,0.33732599546778896,0.10144927536231885,0.24308878872131887,0.35507246376811596,0.34109319613510286,0,137,0,1,11,84,25,18,6,112,8,12,13,68,25,32,19,69,31,19,0,131,0,7,23.4624,5.882,0.384,15.0,test_results,2025-06-30 02:43:29,Llama-3.1-8B-llama31_classification_lora-C3-full_context
run_experiment.log ADDED
@@ -0,0 +1,860 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2025-06-30 02:43:10,543][__main__][INFO] - cache_dir: /tmp/
2
+ dataset:
3
+ name: kamel-usp/aes_enem_dataset
4
+ split: JBCS2025
5
+ training_params:
6
+ seed: 42
7
+ num_train_epochs: 20
8
+ logging_steps: 100
9
+ metric_for_best_model: QWK
10
+ bf16: true
11
+ bootstrap:
12
+ enabled: true
13
+ n_bootstrap: 10000
14
+ bootstrap_seed: 42
15
+ metrics:
16
+ - QWK
17
+ - Macro_F1
18
+ - Weighted_F1
19
+ post_training_results:
20
+ model_path: /workspace/jbcs2025/outputs/2025-03-24/20-42-59
21
+ experiments:
22
+ model:
23
+ name: meta-llama/Llama-3.1-8B
24
+ type: llama31_classification_lora
25
+ num_labels: 6
26
+ output_dir: ./results/
27
+ logging_dir: ./logs/
28
+ best_model_dir: ./results/best_model
29
+ lora_r: 8
30
+ lora_dropout: 0.05
31
+ lora_alpha: 16
32
+ lora_target_modules: all-linear
33
+ checkpoint_path: ''
34
+ tokenizer:
35
+ name: meta-llama/Llama-3.1-8B
36
+ dataset:
37
+ grade_index: 2
38
+ use_full_context: true
39
+ training_params:
40
+ weight_decay: 0.01
41
+ warmup_ratio: 0.1
42
+ learning_rate: 5.0e-05
43
+ train_batch_size: 1
44
+ eval_batch_size: 16
45
+ gradient_accumulation_steps: 16
46
+ gradient_checkpointing: false
47
+
48
+ [2025-06-30 02:43:14,579][__main__][INFO] - GPU 0: NVIDIA H200 | TDP ≈ 700 W
49
+ [2025-06-30 02:43:14,579][__main__][INFO] - Starting the Fine Tuning training process.
50
+ [2025-06-30 02:43:20,425][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/tokenizer.json
51
+ [2025-06-30 02:43:20,425][transformers.tokenization_utils_base][INFO] - loading file tokenizer.model from cache at None
52
+ [2025-06-30 02:43:20,425][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None
53
+ [2025-06-30 02:43:20,425][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/special_tokens_map.json
54
+ [2025-06-30 02:43:20,425][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/tokenizer_config.json
55
+ [2025-06-30 02:43:20,425][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
56
+ [2025-06-30 02:43:20,706][transformers.tokenization_utils_base][INFO] - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
57
+ [2025-06-30 02:43:20,712][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False; Use Full Context: True
58
+ [2025-06-30 02:43:22,365][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
59
+ [2025-06-30 02:43:22,367][transformers.configuration_utils][INFO] - Model config LlamaConfig {
60
+ "architectures": [
61
+ "LlamaForCausalLM"
62
+ ],
63
+ "attention_bias": false,
64
+ "attention_dropout": 0.0,
65
+ "bos_token_id": 128000,
66
+ "eos_token_id": 128001,
67
+ "head_dim": 128,
68
+ "hidden_act": "silu",
69
+ "hidden_size": 4096,
70
+ "id2label": {
71
+ "0": "LABEL_0",
72
+ "1": "LABEL_1",
73
+ "2": "LABEL_2",
74
+ "3": "LABEL_3",
75
+ "4": "LABEL_4",
76
+ "5": "LABEL_5"
77
+ },
78
+ "initializer_range": 0.02,
79
+ "intermediate_size": 14336,
80
+ "label2id": {
81
+ "LABEL_0": 0,
82
+ "LABEL_1": 1,
83
+ "LABEL_2": 2,
84
+ "LABEL_3": 3,
85
+ "LABEL_4": 4,
86
+ "LABEL_5": 5
87
+ },
88
+ "max_position_embeddings": 131072,
89
+ "mlp_bias": false,
90
+ "model_type": "llama",
91
+ "num_attention_heads": 32,
92
+ "num_hidden_layers": 32,
93
+ "num_key_value_heads": 8,
94
+ "pretraining_tp": 1,
95
+ "rms_norm_eps": 1e-05,
96
+ "rope_scaling": {
97
+ "factor": 8.0,
98
+ "high_freq_factor": 4.0,
99
+ "low_freq_factor": 1.0,
100
+ "original_max_position_embeddings": 8192,
101
+ "rope_type": "llama3"
102
+ },
103
+ "rope_theta": 500000.0,
104
+ "tie_word_embeddings": false,
105
+ "torch_dtype": "bfloat16",
106
+ "transformers_version": "4.53.0",
107
+ "use_cache": true,
108
+ "vocab_size": 128256
109
+ }
110
+
111
+ [2025-06-30 02:43:22,507][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/model.safetensors.index.json
112
+ [2025-06-30 02:43:22,507][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object
113
+ [2025-06-30 02:43:22,508][transformers.modeling_utils][INFO] - Instantiating LlamaForSequenceClassification model under default dtype torch.bfloat16.
114
+ [2025-06-30 02:43:28,442][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at meta-llama/Llama-3.1-8B were not used when initializing LlamaForSequenceClassification: ['lm_head.weight']
115
+ - This IS expected if you are initializing LlamaForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
116
+ - This IS NOT expected if you are initializing LlamaForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
117
+ [2025-06-30 02:43:28,443][transformers.modeling_utils][WARNING] - Some weights of LlamaForSequenceClassification were not initialized from the model checkpoint at meta-llama/Llama-3.1-8B and are newly initialized: ['score.weight']
118
+ You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
119
+ [2025-06-30 02:43:29,505][__main__][INFO] - Initialized new PEFT model for ce loss
120
+ [2025-06-30 02:43:29,508][__main__][INFO] - None
121
+ [2025-06-30 02:43:29,509][transformers.training_args][INFO] - PyTorch: setting up devices
122
+ [2025-06-30 02:43:29,540][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
123
+ [2025-06-30 02:43:29,546][transformers.trainer][INFO] - You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching.
124
+ [2025-06-30 02:43:29,571][transformers.trainer][INFO] - Using auto half precision backend
125
+ [2025-06-30 02:43:29,571][transformers.trainer][WARNING] - No label_names provided for model class `PeftModelForSequenceClassification`. Since `PeftModel` hides base models input arguments, if label_names is not given, label_names can't be set automatically within `Trainer`. Note that empty label_names list will be used instead.
126
+ [2025-06-30 02:43:29,574][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
127
+ [2025-06-30 02:43:29,590][transformers.trainer][INFO] -
128
+ ***** Running Evaluation *****
129
+ [2025-06-30 02:43:29,590][transformers.trainer][INFO] - Num examples = 132
130
+ [2025-06-30 02:43:29,590][transformers.trainer][INFO] - Batch size = 16
131
+ [2025-06-30 02:43:52,158][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
132
+ [2025-06-30 02:43:52,211][transformers.trainer][INFO] - ***** Running training *****
133
+ [2025-06-30 02:43:52,211][transformers.trainer][INFO] - Num examples = 500
134
+ [2025-06-30 02:43:52,211][transformers.trainer][INFO] - Num Epochs = 20
135
+ [2025-06-30 02:43:52,211][transformers.trainer][INFO] - Instantaneous batch size per device = 1
136
+ [2025-06-30 02:43:52,211][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16
137
+ [2025-06-30 02:43:52,211][transformers.trainer][INFO] - Gradient Accumulation steps = 16
138
+ [2025-06-30 02:43:52,211][transformers.trainer][INFO] - Total optimization steps = 640
139
+ [2025-06-30 02:43:52,214][transformers.trainer][INFO] - Number of trainable parameters = 20,996,096
140
+ [2025-06-30 02:47:44,871][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
141
+ [2025-06-30 02:47:44,875][transformers.trainer][INFO] -
142
+ ***** Running Evaluation *****
143
+ [2025-06-30 02:47:44,875][transformers.trainer][INFO] - Num examples = 132
144
+ [2025-06-30 02:47:44,876][transformers.trainer][INFO] - Batch size = 16
145
+ [2025-06-30 02:48:07,149][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-32
146
+ [2025-06-30 02:48:07,948][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
147
+ [2025-06-30 02:48:07,948][transformers.configuration_utils][INFO] - Model config LlamaConfig {
148
+ "architectures": [
149
+ "LlamaForCausalLM"
150
+ ],
151
+ "attention_bias": false,
152
+ "attention_dropout": 0.0,
153
+ "bos_token_id": 128000,
154
+ "eos_token_id": 128001,
155
+ "head_dim": 128,
156
+ "hidden_act": "silu",
157
+ "hidden_size": 4096,
158
+ "initializer_range": 0.02,
159
+ "intermediate_size": 14336,
160
+ "max_position_embeddings": 131072,
161
+ "mlp_bias": false,
162
+ "model_type": "llama",
163
+ "num_attention_heads": 32,
164
+ "num_hidden_layers": 32,
165
+ "num_key_value_heads": 8,
166
+ "pretraining_tp": 1,
167
+ "rms_norm_eps": 1e-05,
168
+ "rope_scaling": {
169
+ "factor": 8.0,
170
+ "high_freq_factor": 4.0,
171
+ "low_freq_factor": 1.0,
172
+ "original_max_position_embeddings": 8192,
173
+ "rope_type": "llama3"
174
+ },
175
+ "rope_theta": 500000.0,
176
+ "tie_word_embeddings": false,
177
+ "torch_dtype": "bfloat16",
178
+ "transformers_version": "4.53.0",
179
+ "use_cache": true,
180
+ "vocab_size": 128256
181
+ }
182
+
183
+ [2025-06-30 02:52:00,705][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
184
+ [2025-06-30 02:52:00,708][transformers.trainer][INFO] -
185
+ ***** Running Evaluation *****
186
+ [2025-06-30 02:52:00,708][transformers.trainer][INFO] - Num examples = 132
187
+ [2025-06-30 02:52:00,708][transformers.trainer][INFO] - Batch size = 16
188
+ [2025-06-30 02:52:23,011][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-64
189
+ [2025-06-30 02:52:23,642][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
190
+ [2025-06-30 02:52:23,643][transformers.configuration_utils][INFO] - Model config LlamaConfig {
191
+ "architectures": [
192
+ "LlamaForCausalLM"
193
+ ],
194
+ "attention_bias": false,
195
+ "attention_dropout": 0.0,
196
+ "bos_token_id": 128000,
197
+ "eos_token_id": 128001,
198
+ "head_dim": 128,
199
+ "hidden_act": "silu",
200
+ "hidden_size": 4096,
201
+ "initializer_range": 0.02,
202
+ "intermediate_size": 14336,
203
+ "max_position_embeddings": 131072,
204
+ "mlp_bias": false,
205
+ "model_type": "llama",
206
+ "num_attention_heads": 32,
207
+ "num_hidden_layers": 32,
208
+ "num_key_value_heads": 8,
209
+ "pretraining_tp": 1,
210
+ "rms_norm_eps": 1e-05,
211
+ "rope_scaling": {
212
+ "factor": 8.0,
213
+ "high_freq_factor": 4.0,
214
+ "low_freq_factor": 1.0,
215
+ "original_max_position_embeddings": 8192,
216
+ "rope_type": "llama3"
217
+ },
218
+ "rope_theta": 500000.0,
219
+ "tie_word_embeddings": false,
220
+ "torch_dtype": "bfloat16",
221
+ "transformers_version": "4.53.0",
222
+ "use_cache": true,
223
+ "vocab_size": 128256
224
+ }
225
+
226
+ [2025-06-30 02:52:23,993][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-32] due to args.save_total_limit
227
+ [2025-06-30 02:56:16,734][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
228
+ [2025-06-30 02:56:16,738][transformers.trainer][INFO] -
229
+ ***** Running Evaluation *****
230
+ [2025-06-30 02:56:16,738][transformers.trainer][INFO] - Num examples = 132
231
+ [2025-06-30 02:56:16,738][transformers.trainer][INFO] - Batch size = 16
232
+ [2025-06-30 02:56:39,008][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-96
233
+ [2025-06-30 02:56:39,471][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
234
+ [2025-06-30 02:56:39,472][transformers.configuration_utils][INFO] - Model config LlamaConfig {
235
+ "architectures": [
236
+ "LlamaForCausalLM"
237
+ ],
238
+ "attention_bias": false,
239
+ "attention_dropout": 0.0,
240
+ "bos_token_id": 128000,
241
+ "eos_token_id": 128001,
242
+ "head_dim": 128,
243
+ "hidden_act": "silu",
244
+ "hidden_size": 4096,
245
+ "initializer_range": 0.02,
246
+ "intermediate_size": 14336,
247
+ "max_position_embeddings": 131072,
248
+ "mlp_bias": false,
249
+ "model_type": "llama",
250
+ "num_attention_heads": 32,
251
+ "num_hidden_layers": 32,
252
+ "num_key_value_heads": 8,
253
+ "pretraining_tp": 1,
254
+ "rms_norm_eps": 1e-05,
255
+ "rope_scaling": {
256
+ "factor": 8.0,
257
+ "high_freq_factor": 4.0,
258
+ "low_freq_factor": 1.0,
259
+ "original_max_position_embeddings": 8192,
260
+ "rope_type": "llama3"
261
+ },
262
+ "rope_theta": 500000.0,
263
+ "tie_word_embeddings": false,
264
+ "torch_dtype": "bfloat16",
265
+ "transformers_version": "4.53.0",
266
+ "use_cache": true,
267
+ "vocab_size": 128256
268
+ }
269
+
270
+ [2025-06-30 02:56:39,870][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-64] due to args.save_total_limit
271
+ [2025-06-30 03:00:32,709][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
272
+ [2025-06-30 03:00:32,712][transformers.trainer][INFO] -
273
+ ***** Running Evaluation *****
274
+ [2025-06-30 03:00:32,713][transformers.trainer][INFO] - Num examples = 132
275
+ [2025-06-30 03:00:32,713][transformers.trainer][INFO] - Batch size = 16
276
+ [2025-06-30 03:00:54,997][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-128
277
+ [2025-06-30 03:00:55,521][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
278
+ [2025-06-30 03:00:55,522][transformers.configuration_utils][INFO] - Model config LlamaConfig {
279
+ "architectures": [
280
+ "LlamaForCausalLM"
281
+ ],
282
+ "attention_bias": false,
283
+ "attention_dropout": 0.0,
284
+ "bos_token_id": 128000,
285
+ "eos_token_id": 128001,
286
+ "head_dim": 128,
287
+ "hidden_act": "silu",
288
+ "hidden_size": 4096,
289
+ "initializer_range": 0.02,
290
+ "intermediate_size": 14336,
291
+ "max_position_embeddings": 131072,
292
+ "mlp_bias": false,
293
+ "model_type": "llama",
294
+ "num_attention_heads": 32,
295
+ "num_hidden_layers": 32,
296
+ "num_key_value_heads": 8,
297
+ "pretraining_tp": 1,
298
+ "rms_norm_eps": 1e-05,
299
+ "rope_scaling": {
300
+ "factor": 8.0,
301
+ "high_freq_factor": 4.0,
302
+ "low_freq_factor": 1.0,
303
+ "original_max_position_embeddings": 8192,
304
+ "rope_type": "llama3"
305
+ },
306
+ "rope_theta": 500000.0,
307
+ "tie_word_embeddings": false,
308
+ "torch_dtype": "bfloat16",
309
+ "transformers_version": "4.53.0",
310
+ "use_cache": true,
311
+ "vocab_size": 128256
312
+ }
313
+
314
+ [2025-06-30 03:04:48,381][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
315
+ [2025-06-30 03:04:48,385][transformers.trainer][INFO] -
316
+ ***** Running Evaluation *****
317
+ [2025-06-30 03:04:48,385][transformers.trainer][INFO] - Num examples = 132
318
+ [2025-06-30 03:04:48,385][transformers.trainer][INFO] - Batch size = 16
319
+ [2025-06-30 03:05:10,656][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-160
320
+ [2025-06-30 03:05:11,129][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
321
+ [2025-06-30 03:05:11,130][transformers.configuration_utils][INFO] - Model config LlamaConfig {
322
+ "architectures": [
323
+ "LlamaForCausalLM"
324
+ ],
325
+ "attention_bias": false,
326
+ "attention_dropout": 0.0,
327
+ "bos_token_id": 128000,
328
+ "eos_token_id": 128001,
329
+ "head_dim": 128,
330
+ "hidden_act": "silu",
331
+ "hidden_size": 4096,
332
+ "initializer_range": 0.02,
333
+ "intermediate_size": 14336,
334
+ "max_position_embeddings": 131072,
335
+ "mlp_bias": false,
336
+ "model_type": "llama",
337
+ "num_attention_heads": 32,
338
+ "num_hidden_layers": 32,
339
+ "num_key_value_heads": 8,
340
+ "pretraining_tp": 1,
341
+ "rms_norm_eps": 1e-05,
342
+ "rope_scaling": {
343
+ "factor": 8.0,
344
+ "high_freq_factor": 4.0,
345
+ "low_freq_factor": 1.0,
346
+ "original_max_position_embeddings": 8192,
347
+ "rope_type": "llama3"
348
+ },
349
+ "rope_theta": 500000.0,
350
+ "tie_word_embeddings": false,
351
+ "torch_dtype": "bfloat16",
352
+ "transformers_version": "4.53.0",
353
+ "use_cache": true,
354
+ "vocab_size": 128256
355
+ }
356
+
357
+ [2025-06-30 03:05:11,486][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-128] due to args.save_total_limit
358
+ [2025-06-30 03:09:04,257][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
359
+ [2025-06-30 03:09:04,260][transformers.trainer][INFO] -
360
+ ***** Running Evaluation *****
361
+ [2025-06-30 03:09:04,261][transformers.trainer][INFO] - Num examples = 132
362
+ [2025-06-30 03:09:04,261][transformers.trainer][INFO] - Batch size = 16
363
+ [2025-06-30 03:09:26,513][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-192
364
+ [2025-06-30 03:09:27,003][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
365
+ [2025-06-30 03:09:27,004][transformers.configuration_utils][INFO] - Model config LlamaConfig {
366
+ "architectures": [
367
+ "LlamaForCausalLM"
368
+ ],
369
+ "attention_bias": false,
370
+ "attention_dropout": 0.0,
371
+ "bos_token_id": 128000,
372
+ "eos_token_id": 128001,
373
+ "head_dim": 128,
374
+ "hidden_act": "silu",
375
+ "hidden_size": 4096,
376
+ "initializer_range": 0.02,
377
+ "intermediate_size": 14336,
378
+ "max_position_embeddings": 131072,
379
+ "mlp_bias": false,
380
+ "model_type": "llama",
381
+ "num_attention_heads": 32,
382
+ "num_hidden_layers": 32,
383
+ "num_key_value_heads": 8,
384
+ "pretraining_tp": 1,
385
+ "rms_norm_eps": 1e-05,
386
+ "rope_scaling": {
387
+ "factor": 8.0,
388
+ "high_freq_factor": 4.0,
389
+ "low_freq_factor": 1.0,
390
+ "original_max_position_embeddings": 8192,
391
+ "rope_type": "llama3"
392
+ },
393
+ "rope_theta": 500000.0,
394
+ "tie_word_embeddings": false,
395
+ "torch_dtype": "bfloat16",
396
+ "transformers_version": "4.53.0",
397
+ "use_cache": true,
398
+ "vocab_size": 128256
399
+ }
400
+
401
+ [2025-06-30 03:09:27,384][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-96] due to args.save_total_limit
402
+ [2025-06-30 03:09:27,400][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-160] due to args.save_total_limit
403
+ [2025-06-30 03:13:20,046][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
404
+ [2025-06-30 03:13:20,049][transformers.trainer][INFO] -
405
+ ***** Running Evaluation *****
406
+ [2025-06-30 03:13:20,049][transformers.trainer][INFO] - Num examples = 132
407
+ [2025-06-30 03:13:20,050][transformers.trainer][INFO] - Batch size = 16
408
+ [2025-06-30 03:13:42,319][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-224
409
+ [2025-06-30 03:13:42,771][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
410
+ [2025-06-30 03:13:42,771][transformers.configuration_utils][INFO] - Model config LlamaConfig {
411
+ "architectures": [
412
+ "LlamaForCausalLM"
413
+ ],
414
+ "attention_bias": false,
415
+ "attention_dropout": 0.0,
416
+ "bos_token_id": 128000,
417
+ "eos_token_id": 128001,
418
+ "head_dim": 128,
419
+ "hidden_act": "silu",
420
+ "hidden_size": 4096,
421
+ "initializer_range": 0.02,
422
+ "intermediate_size": 14336,
423
+ "max_position_embeddings": 131072,
424
+ "mlp_bias": false,
425
+ "model_type": "llama",
426
+ "num_attention_heads": 32,
427
+ "num_hidden_layers": 32,
428
+ "num_key_value_heads": 8,
429
+ "pretraining_tp": 1,
430
+ "rms_norm_eps": 1e-05,
431
+ "rope_scaling": {
432
+ "factor": 8.0,
433
+ "high_freq_factor": 4.0,
434
+ "low_freq_factor": 1.0,
435
+ "original_max_position_embeddings": 8192,
436
+ "rope_type": "llama3"
437
+ },
438
+ "rope_theta": 500000.0,
439
+ "tie_word_embeddings": false,
440
+ "torch_dtype": "bfloat16",
441
+ "transformers_version": "4.53.0",
442
+ "use_cache": true,
443
+ "vocab_size": 128256
444
+ }
445
+
446
+ [2025-06-30 03:17:36,075][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
447
+ [2025-06-30 03:17:36,079][transformers.trainer][INFO] -
448
+ ***** Running Evaluation *****
449
+ [2025-06-30 03:17:36,079][transformers.trainer][INFO] - Num examples = 132
450
+ [2025-06-30 03:17:36,079][transformers.trainer][INFO] - Batch size = 16
451
+ [2025-06-30 03:17:58,353][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-256
452
+ [2025-06-30 03:17:59,135][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
453
+ [2025-06-30 03:17:59,135][transformers.configuration_utils][INFO] - Model config LlamaConfig {
454
+ "architectures": [
455
+ "LlamaForCausalLM"
456
+ ],
457
+ "attention_bias": false,
458
+ "attention_dropout": 0.0,
459
+ "bos_token_id": 128000,
460
+ "eos_token_id": 128001,
461
+ "head_dim": 128,
462
+ "hidden_act": "silu",
463
+ "hidden_size": 4096,
464
+ "initializer_range": 0.02,
465
+ "intermediate_size": 14336,
466
+ "max_position_embeddings": 131072,
467
+ "mlp_bias": false,
468
+ "model_type": "llama",
469
+ "num_attention_heads": 32,
470
+ "num_hidden_layers": 32,
471
+ "num_key_value_heads": 8,
472
+ "pretraining_tp": 1,
473
+ "rms_norm_eps": 1e-05,
474
+ "rope_scaling": {
475
+ "factor": 8.0,
476
+ "high_freq_factor": 4.0,
477
+ "low_freq_factor": 1.0,
478
+ "original_max_position_embeddings": 8192,
479
+ "rope_type": "llama3"
480
+ },
481
+ "rope_theta": 500000.0,
482
+ "tie_word_embeddings": false,
483
+ "torch_dtype": "bfloat16",
484
+ "transformers_version": "4.53.0",
485
+ "use_cache": true,
486
+ "vocab_size": 128256
487
+ }
488
+
489
+ [2025-06-30 03:17:59,485][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-224] due to args.save_total_limit
490
+ [2025-06-30 03:21:51,776][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
491
+ [2025-06-30 03:21:51,780][transformers.trainer][INFO] -
492
+ ***** Running Evaluation *****
493
+ [2025-06-30 03:21:51,780][transformers.trainer][INFO] - Num examples = 132
494
+ [2025-06-30 03:21:51,780][transformers.trainer][INFO] - Batch size = 16
495
+ [2025-06-30 03:22:14,029][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-288
496
+ [2025-06-30 03:22:14,546][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
497
+ [2025-06-30 03:22:14,547][transformers.configuration_utils][INFO] - Model config LlamaConfig {
498
+ "architectures": [
499
+ "LlamaForCausalLM"
500
+ ],
501
+ "attention_bias": false,
502
+ "attention_dropout": 0.0,
503
+ "bos_token_id": 128000,
504
+ "eos_token_id": 128001,
505
+ "head_dim": 128,
506
+ "hidden_act": "silu",
507
+ "hidden_size": 4096,
508
+ "initializer_range": 0.02,
509
+ "intermediate_size": 14336,
510
+ "max_position_embeddings": 131072,
511
+ "mlp_bias": false,
512
+ "model_type": "llama",
513
+ "num_attention_heads": 32,
514
+ "num_hidden_layers": 32,
515
+ "num_key_value_heads": 8,
516
+ "pretraining_tp": 1,
517
+ "rms_norm_eps": 1e-05,
518
+ "rope_scaling": {
519
+ "factor": 8.0,
520
+ "high_freq_factor": 4.0,
521
+ "low_freq_factor": 1.0,
522
+ "original_max_position_embeddings": 8192,
523
+ "rope_type": "llama3"
524
+ },
525
+ "rope_theta": 500000.0,
526
+ "tie_word_embeddings": false,
527
+ "torch_dtype": "bfloat16",
528
+ "transformers_version": "4.53.0",
529
+ "use_cache": true,
530
+ "vocab_size": 128256
531
+ }
532
+
533
+ [2025-06-30 03:22:14,974][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-256] due to args.save_total_limit
534
+ [2025-06-30 03:26:08,004][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
535
+ [2025-06-30 03:26:08,007][transformers.trainer][INFO] -
536
+ ***** Running Evaluation *****
537
+ [2025-06-30 03:26:08,007][transformers.trainer][INFO] - Num examples = 132
538
+ [2025-06-30 03:26:08,007][transformers.trainer][INFO] - Batch size = 16
539
+ [2025-06-30 03:26:30,298][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-320
540
+ [2025-06-30 03:26:30,783][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
541
+ [2025-06-30 03:26:30,784][transformers.configuration_utils][INFO] - Model config LlamaConfig {
542
+ "architectures": [
543
+ "LlamaForCausalLM"
544
+ ],
545
+ "attention_bias": false,
546
+ "attention_dropout": 0.0,
547
+ "bos_token_id": 128000,
548
+ "eos_token_id": 128001,
549
+ "head_dim": 128,
550
+ "hidden_act": "silu",
551
+ "hidden_size": 4096,
552
+ "initializer_range": 0.02,
553
+ "intermediate_size": 14336,
554
+ "max_position_embeddings": 131072,
555
+ "mlp_bias": false,
556
+ "model_type": "llama",
557
+ "num_attention_heads": 32,
558
+ "num_hidden_layers": 32,
559
+ "num_key_value_heads": 8,
560
+ "pretraining_tp": 1,
561
+ "rms_norm_eps": 1e-05,
562
+ "rope_scaling": {
563
+ "factor": 8.0,
564
+ "high_freq_factor": 4.0,
565
+ "low_freq_factor": 1.0,
566
+ "original_max_position_embeddings": 8192,
567
+ "rope_type": "llama3"
568
+ },
569
+ "rope_theta": 500000.0,
570
+ "tie_word_embeddings": false,
571
+ "torch_dtype": "bfloat16",
572
+ "transformers_version": "4.53.0",
573
+ "use_cache": true,
574
+ "vocab_size": 128256
575
+ }
576
+
577
+ [2025-06-30 03:26:31,193][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-192] due to args.save_total_limit
578
+ [2025-06-30 03:26:31,213][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-288] due to args.save_total_limit
579
+ [2025-06-30 03:30:24,252][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
580
+ [2025-06-30 03:30:24,256][transformers.trainer][INFO] -
581
+ ***** Running Evaluation *****
582
+ [2025-06-30 03:30:24,256][transformers.trainer][INFO] - Num examples = 132
583
+ [2025-06-30 03:30:24,256][transformers.trainer][INFO] - Batch size = 16
584
+ [2025-06-30 03:30:46,525][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-352
585
+ [2025-06-30 03:30:47,023][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
586
+ [2025-06-30 03:30:47,023][transformers.configuration_utils][INFO] - Model config LlamaConfig {
587
+ "architectures": [
588
+ "LlamaForCausalLM"
589
+ ],
590
+ "attention_bias": false,
591
+ "attention_dropout": 0.0,
592
+ "bos_token_id": 128000,
593
+ "eos_token_id": 128001,
594
+ "head_dim": 128,
595
+ "hidden_act": "silu",
596
+ "hidden_size": 4096,
597
+ "initializer_range": 0.02,
598
+ "intermediate_size": 14336,
599
+ "max_position_embeddings": 131072,
600
+ "mlp_bias": false,
601
+ "model_type": "llama",
602
+ "num_attention_heads": 32,
603
+ "num_hidden_layers": 32,
604
+ "num_key_value_heads": 8,
605
+ "pretraining_tp": 1,
606
+ "rms_norm_eps": 1e-05,
607
+ "rope_scaling": {
608
+ "factor": 8.0,
609
+ "high_freq_factor": 4.0,
610
+ "low_freq_factor": 1.0,
611
+ "original_max_position_embeddings": 8192,
612
+ "rope_type": "llama3"
613
+ },
614
+ "rope_theta": 500000.0,
615
+ "tie_word_embeddings": false,
616
+ "torch_dtype": "bfloat16",
617
+ "transformers_version": "4.53.0",
618
+ "use_cache": true,
619
+ "vocab_size": 128256
620
+ }
621
+
622
+ [2025-06-30 03:34:40,147][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
623
+ [2025-06-30 03:34:40,150][transformers.trainer][INFO] -
624
+ ***** Running Evaluation *****
625
+ [2025-06-30 03:34:40,151][transformers.trainer][INFO] - Num examples = 132
626
+ [2025-06-30 03:34:40,151][transformers.trainer][INFO] - Batch size = 16
627
+ [2025-06-30 03:35:02,420][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-384
628
+ [2025-06-30 03:35:02,901][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
629
+ [2025-06-30 03:35:02,902][transformers.configuration_utils][INFO] - Model config LlamaConfig {
630
+ "architectures": [
631
+ "LlamaForCausalLM"
632
+ ],
633
+ "attention_bias": false,
634
+ "attention_dropout": 0.0,
635
+ "bos_token_id": 128000,
636
+ "eos_token_id": 128001,
637
+ "head_dim": 128,
638
+ "hidden_act": "silu",
639
+ "hidden_size": 4096,
640
+ "initializer_range": 0.02,
641
+ "intermediate_size": 14336,
642
+ "max_position_embeddings": 131072,
643
+ "mlp_bias": false,
644
+ "model_type": "llama",
645
+ "num_attention_heads": 32,
646
+ "num_hidden_layers": 32,
647
+ "num_key_value_heads": 8,
648
+ "pretraining_tp": 1,
649
+ "rms_norm_eps": 1e-05,
650
+ "rope_scaling": {
651
+ "factor": 8.0,
652
+ "high_freq_factor": 4.0,
653
+ "low_freq_factor": 1.0,
654
+ "original_max_position_embeddings": 8192,
655
+ "rope_type": "llama3"
656
+ },
657
+ "rope_theta": 500000.0,
658
+ "tie_word_embeddings": false,
659
+ "torch_dtype": "bfloat16",
660
+ "transformers_version": "4.53.0",
661
+ "use_cache": true,
662
+ "vocab_size": 128256
663
+ }
664
+
665
+ [2025-06-30 03:35:03,281][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-352] due to args.save_total_limit
666
+ [2025-06-30 03:38:56,300][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
667
+ [2025-06-30 03:38:56,304][transformers.trainer][INFO] -
668
+ ***** Running Evaluation *****
669
+ [2025-06-30 03:38:56,304][transformers.trainer][INFO] - Num examples = 132
670
+ [2025-06-30 03:38:56,304][transformers.trainer][INFO] - Batch size = 16
671
+ [2025-06-30 03:39:18,569][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-416
672
+ [2025-06-30 03:39:19,070][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
673
+ [2025-06-30 03:39:19,071][transformers.configuration_utils][INFO] - Model config LlamaConfig {
674
+ "architectures": [
675
+ "LlamaForCausalLM"
676
+ ],
677
+ "attention_bias": false,
678
+ "attention_dropout": 0.0,
679
+ "bos_token_id": 128000,
680
+ "eos_token_id": 128001,
681
+ "head_dim": 128,
682
+ "hidden_act": "silu",
683
+ "hidden_size": 4096,
684
+ "initializer_range": 0.02,
685
+ "intermediate_size": 14336,
686
+ "max_position_embeddings": 131072,
687
+ "mlp_bias": false,
688
+ "model_type": "llama",
689
+ "num_attention_heads": 32,
690
+ "num_hidden_layers": 32,
691
+ "num_key_value_heads": 8,
692
+ "pretraining_tp": 1,
693
+ "rms_norm_eps": 1e-05,
694
+ "rope_scaling": {
695
+ "factor": 8.0,
696
+ "high_freq_factor": 4.0,
697
+ "low_freq_factor": 1.0,
698
+ "original_max_position_embeddings": 8192,
699
+ "rope_type": "llama3"
700
+ },
701
+ "rope_theta": 500000.0,
702
+ "tie_word_embeddings": false,
703
+ "torch_dtype": "bfloat16",
704
+ "transformers_version": "4.53.0",
705
+ "use_cache": true,
706
+ "vocab_size": 128256
707
+ }
708
+
709
+ [2025-06-30 03:39:19,487][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-384] due to args.save_total_limit
710
+ [2025-06-30 03:43:12,725][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
711
+ [2025-06-30 03:43:12,729][transformers.trainer][INFO] -
712
+ ***** Running Evaluation *****
713
+ [2025-06-30 03:43:12,729][transformers.trainer][INFO] - Num examples = 132
714
+ [2025-06-30 03:43:12,729][transformers.trainer][INFO] - Batch size = 16
715
+ [2025-06-30 03:43:35,008][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-448
716
+ [2025-06-30 03:43:35,510][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
717
+ [2025-06-30 03:43:35,511][transformers.configuration_utils][INFO] - Model config LlamaConfig {
718
+ "architectures": [
719
+ "LlamaForCausalLM"
720
+ ],
721
+ "attention_bias": false,
722
+ "attention_dropout": 0.0,
723
+ "bos_token_id": 128000,
724
+ "eos_token_id": 128001,
725
+ "head_dim": 128,
726
+ "hidden_act": "silu",
727
+ "hidden_size": 4096,
728
+ "initializer_range": 0.02,
729
+ "intermediate_size": 14336,
730
+ "max_position_embeddings": 131072,
731
+ "mlp_bias": false,
732
+ "model_type": "llama",
733
+ "num_attention_heads": 32,
734
+ "num_hidden_layers": 32,
735
+ "num_key_value_heads": 8,
736
+ "pretraining_tp": 1,
737
+ "rms_norm_eps": 1e-05,
738
+ "rope_scaling": {
739
+ "factor": 8.0,
740
+ "high_freq_factor": 4.0,
741
+ "low_freq_factor": 1.0,
742
+ "original_max_position_embeddings": 8192,
743
+ "rope_type": "llama3"
744
+ },
745
+ "rope_theta": 500000.0,
746
+ "tie_word_embeddings": false,
747
+ "torch_dtype": "bfloat16",
748
+ "transformers_version": "4.53.0",
749
+ "use_cache": true,
750
+ "vocab_size": 128256
751
+ }
752
+
753
+ [2025-06-30 03:43:35,875][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-416] due to args.save_total_limit
754
+ [2025-06-30 03:47:28,746][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
755
+ [2025-06-30 03:47:28,750][transformers.trainer][INFO] -
756
+ ***** Running Evaluation *****
757
+ [2025-06-30 03:47:28,750][transformers.trainer][INFO] - Num examples = 132
758
+ [2025-06-30 03:47:28,750][transformers.trainer][INFO] - Batch size = 16
759
+ [2025-06-30 03:47:51,014][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-480
760
+ [2025-06-30 03:47:51,480][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
761
+ [2025-06-30 03:47:51,481][transformers.configuration_utils][INFO] - Model config LlamaConfig {
762
+ "architectures": [
763
+ "LlamaForCausalLM"
764
+ ],
765
+ "attention_bias": false,
766
+ "attention_dropout": 0.0,
767
+ "bos_token_id": 128000,
768
+ "eos_token_id": 128001,
769
+ "head_dim": 128,
770
+ "hidden_act": "silu",
771
+ "hidden_size": 4096,
772
+ "initializer_range": 0.02,
773
+ "intermediate_size": 14336,
774
+ "max_position_embeddings": 131072,
775
+ "mlp_bias": false,
776
+ "model_type": "llama",
777
+ "num_attention_heads": 32,
778
+ "num_hidden_layers": 32,
779
+ "num_key_value_heads": 8,
780
+ "pretraining_tp": 1,
781
+ "rms_norm_eps": 1e-05,
782
+ "rope_scaling": {
783
+ "factor": 8.0,
784
+ "high_freq_factor": 4.0,
785
+ "low_freq_factor": 1.0,
786
+ "original_max_position_embeddings": 8192,
787
+ "rope_type": "llama3"
788
+ },
789
+ "rope_theta": 500000.0,
790
+ "tie_word_embeddings": false,
791
+ "torch_dtype": "bfloat16",
792
+ "transformers_version": "4.53.0",
793
+ "use_cache": true,
794
+ "vocab_size": 128256
795
+ }
796
+
797
+ [2025-06-30 03:47:51,889][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-448] due to args.save_total_limit
798
+ [2025-06-30 03:47:51,903][transformers.trainer][INFO] -
799
+
800
+ Training completed. Do not forget to share your model on huggingface.co/models =)
801
+
802
+
803
+ [2025-06-30 03:47:51,903][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-320 (score: 0.4302446642373763).
804
+ [2025-06-30 03:47:52,000][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/02-43-10/results/checkpoint-480] due to args.save_total_limit
805
+ [2025-06-30 03:47:52,020][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
806
+ [2025-06-30 03:47:52,024][transformers.trainer][INFO] -
807
+ ***** Running Evaluation *****
808
+ [2025-06-30 03:47:52,024][transformers.trainer][INFO] - Num examples = 132
809
+ [2025-06-30 03:47:52,024][transformers.trainer][INFO] - Batch size = 16
810
+ [2025-06-30 03:48:14,279][__main__][INFO] - Training completed successfully.
811
+ [2025-06-30 03:48:14,279][__main__][INFO] - Running on Test
812
+ [2025-06-30 03:48:14,279][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades. If essay_text, reference, id, supporting_text, prompt, id_prompt, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
813
+ [2025-06-30 03:48:14,283][transformers.trainer][INFO] -
814
+ ***** Running Evaluation *****
815
+ [2025-06-30 03:48:14,283][transformers.trainer][INFO] - Num examples = 138
816
+ [2025-06-30 03:48:14,283][transformers.trainer][INFO] - Batch size = 16
817
+ [2025-06-30 03:48:37,758][__main__][INFO] - Test metrics: {'eval_loss': 1.99528968334198, 'eval_model_preparation_time': 0.0126, 'eval_accuracy': 0.35507246376811596, 'eval_RMSE': 55.638585297552666, 'eval_QWK': 0.33732599546778896, 'eval_HDIV': 0.10144927536231885, 'eval_Macro_F1': 0.24308878872131887, 'eval_Micro_F1': 0.35507246376811596, 'eval_Weighted_F1': 0.34109319613510286, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 11, 'eval_TN_1': 84, 'eval_FP_1': 25, 'eval_FN_1': 18, 'eval_TP_2': 6, 'eval_TN_2': 112, 'eval_FP_2': 8, 'eval_FN_2': 12, 'eval_TP_3': 13, 'eval_TN_3': 68, 'eval_FP_3': 25, 'eval_FN_3': 32, 'eval_TP_4': 19, 'eval_TN_4': 69, 'eval_FP_4': 31, 'eval_FN_4': 19, 'eval_TP_5': 0, 'eval_TN_5': 131, 'eval_FP_5': 0, 'eval_FN_5': 7, 'eval_runtime': 23.4624, 'eval_samples_per_second': 5.882, 'eval_steps_per_second': 0.384, 'epoch': 15.0}
818
+ [2025-06-30 03:48:37,758][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
819
+ [2025-06-30 03:48:38,192][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b/config.json
820
+ [2025-06-30 03:48:38,193][transformers.configuration_utils][INFO] - Model config LlamaConfig {
821
+ "architectures": [
822
+ "LlamaForCausalLM"
823
+ ],
824
+ "attention_bias": false,
825
+ "attention_dropout": 0.0,
826
+ "bos_token_id": 128000,
827
+ "eos_token_id": 128001,
828
+ "head_dim": 128,
829
+ "hidden_act": "silu",
830
+ "hidden_size": 4096,
831
+ "initializer_range": 0.02,
832
+ "intermediate_size": 14336,
833
+ "max_position_embeddings": 131072,
834
+ "mlp_bias": false,
835
+ "model_type": "llama",
836
+ "num_attention_heads": 32,
837
+ "num_hidden_layers": 32,
838
+ "num_key_value_heads": 8,
839
+ "pretraining_tp": 1,
840
+ "rms_norm_eps": 1e-05,
841
+ "rope_scaling": {
842
+ "factor": 8.0,
843
+ "high_freq_factor": 4.0,
844
+ "low_freq_factor": 1.0,
845
+ "original_max_position_embeddings": 8192,
846
+ "rope_type": "llama3"
847
+ },
848
+ "rope_theta": 500000.0,
849
+ "tie_word_embeddings": false,
850
+ "torch_dtype": "bfloat16",
851
+ "transformers_version": "4.53.0",
852
+ "use_cache": true,
853
+ "vocab_size": 128256
854
+ }
855
+
856
+ [2025-06-30 03:48:38,406][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
857
+ [2025-06-30 03:48:38,406][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
858
+ [2025-06-30 03:48:38,523][__main__][INFO] - Model and tokenizer saved to ./results/best_model
859
+ [2025-06-30 03:48:38,548][__main__][INFO] - Fine Tuning Finished.
860
+ [2025-06-30 03:48:39,055][__main__][INFO] - Total emissions: 0.3845 kg CO2eq
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|finetune_right_pad_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a65c6c5f9764771aa485e6a1f5e63d7d9af8477fe0777148c17476ecb2e09a05
3
+ size 17210099
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|finetune_right_pad_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e275ac0ecb1c8632e3af1d95c5efcb4d601bab37204eb9205bdd503b20e7b4b0
3
+ size 5777