prateeky2806
commited on
Commit
•
707ff6c
1
Parent(s):
015709a
Training in progress, step 200
Browse files- adapter_config.json +26 -0
- adapter_model.bin +3 -0
- added_tokens.json +3 -0
- checkpoint-200/README.md +20 -0
- checkpoint-200/adapter_config.json +26 -0
- checkpoint-200/adapter_model.bin +3 -0
- checkpoint-200/added_tokens.json +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +6 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +35 -0
- checkpoint-200/trainer_state.json +207 -0
- checkpoint-200/training_args.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"o_proj",
|
18 |
+
"gate_proj",
|
19 |
+
"up_proj",
|
20 |
+
"down_proj",
|
21 |
+
"k_proj",
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4bcd2b46f70d5681370d5cb5eaa04a971592bc85bb67124e9c3a643fdbdef48
|
3 |
+
size 319977229
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: False
|
9 |
+
- load_in_4bit: True
|
10 |
+
- llm_int8_threshold: 6.0
|
11 |
+
- llm_int8_skip_modules: None
|
12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
13 |
+
- llm_int8_has_fp16_weight: False
|
14 |
+
- bnb_4bit_quant_type: nf4
|
15 |
+
- bnb_4bit_use_double_quant: True
|
16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
17 |
+
### Framework versions
|
18 |
+
|
19 |
+
|
20 |
+
- PEFT 0.4.0
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"o_proj",
|
18 |
+
"gate_proj",
|
19 |
+
"up_proj",
|
20 |
+
"down_proj",
|
21 |
+
"k_proj",
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
checkpoint-200/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4bcd2b46f70d5681370d5cb5eaa04a971592bc85bb67124e9c3a643fdbdef48
|
3 |
+
size 319977229
|
checkpoint-200/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a650394b7dfe157dff041d90839cbb47a386dfb8bb7ef00aebe2cb05d07abfce
|
3 |
+
size 1279539525
|
checkpoint-200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f078a5ef09c426d3a6069669845a570c0c9ce0e30b14901295b4d1005c6c2e7a
|
3 |
+
size 14511
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
|
3 |
+
size 627
|
checkpoint-200/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<unk>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-200/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-200/tokenizer_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6798371076583862,
|
3 |
+
"best_model_checkpoint": "./output_v2/7b_cluster012_Nous-Hermes-llama-2-7b_partitioned_v3_standardized_012/checkpoint-200",
|
4 |
+
"epoch": 0.23161551823972207,
|
5 |
+
"global_step": 200,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 0.0002,
|
13 |
+
"loss": 0.7418,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"learning_rate": 0.0002,
|
19 |
+
"loss": 0.7269,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.03,
|
24 |
+
"learning_rate": 0.0002,
|
25 |
+
"loss": 0.7061,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.05,
|
30 |
+
"learning_rate": 0.0002,
|
31 |
+
"loss": 0.6809,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.06,
|
36 |
+
"learning_rate": 0.0002,
|
37 |
+
"loss": 0.6742,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.07,
|
42 |
+
"learning_rate": 0.0002,
|
43 |
+
"loss": 0.6789,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.08,
|
48 |
+
"learning_rate": 0.0002,
|
49 |
+
"loss": 0.6628,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.09,
|
54 |
+
"learning_rate": 0.0002,
|
55 |
+
"loss": 0.6995,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.1,
|
60 |
+
"learning_rate": 0.0002,
|
61 |
+
"loss": 0.6774,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.12,
|
66 |
+
"learning_rate": 0.0002,
|
67 |
+
"loss": 0.6716,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.13,
|
72 |
+
"learning_rate": 0.0002,
|
73 |
+
"loss": 0.6628,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.14,
|
78 |
+
"learning_rate": 0.0002,
|
79 |
+
"loss": 0.6696,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.15,
|
84 |
+
"learning_rate": 0.0002,
|
85 |
+
"loss": 0.648,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.16,
|
90 |
+
"learning_rate": 0.0002,
|
91 |
+
"loss": 0.6823,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.17,
|
96 |
+
"learning_rate": 0.0002,
|
97 |
+
"loss": 0.6532,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.19,
|
102 |
+
"learning_rate": 0.0002,
|
103 |
+
"loss": 0.669,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.2,
|
108 |
+
"learning_rate": 0.0002,
|
109 |
+
"loss": 0.6639,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.21,
|
114 |
+
"learning_rate": 0.0002,
|
115 |
+
"loss": 0.6582,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.22,
|
120 |
+
"learning_rate": 0.0002,
|
121 |
+
"loss": 0.6381,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.23,
|
126 |
+
"learning_rate": 0.0002,
|
127 |
+
"loss": 0.6342,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.23,
|
132 |
+
"eval_loss": 0.6798371076583862,
|
133 |
+
"eval_runtime": 220.8775,
|
134 |
+
"eval_samples_per_second": 4.527,
|
135 |
+
"eval_steps_per_second": 2.264,
|
136 |
+
"step": 200
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.23,
|
140 |
+
"mmlu_eval_accuracy": 0.4661323913730994,
|
141 |
+
"mmlu_eval_accuracy_abstract_algebra": 0.18181818181818182,
|
142 |
+
"mmlu_eval_accuracy_anatomy": 0.5714285714285714,
|
143 |
+
"mmlu_eval_accuracy_astronomy": 0.5,
|
144 |
+
"mmlu_eval_accuracy_business_ethics": 0.5454545454545454,
|
145 |
+
"mmlu_eval_accuracy_clinical_knowledge": 0.4482758620689655,
|
146 |
+
"mmlu_eval_accuracy_college_biology": 0.4375,
|
147 |
+
"mmlu_eval_accuracy_college_chemistry": 0.125,
|
148 |
+
"mmlu_eval_accuracy_college_computer_science": 0.36363636363636365,
|
149 |
+
"mmlu_eval_accuracy_college_mathematics": 0.18181818181818182,
|
150 |
+
"mmlu_eval_accuracy_college_medicine": 0.36363636363636365,
|
151 |
+
"mmlu_eval_accuracy_college_physics": 0.45454545454545453,
|
152 |
+
"mmlu_eval_accuracy_computer_security": 0.36363636363636365,
|
153 |
+
"mmlu_eval_accuracy_conceptual_physics": 0.38461538461538464,
|
154 |
+
"mmlu_eval_accuracy_econometrics": 0.16666666666666666,
|
155 |
+
"mmlu_eval_accuracy_electrical_engineering": 0.3125,
|
156 |
+
"mmlu_eval_accuracy_elementary_mathematics": 0.3902439024390244,
|
157 |
+
"mmlu_eval_accuracy_formal_logic": 0.2857142857142857,
|
158 |
+
"mmlu_eval_accuracy_global_facts": 0.5,
|
159 |
+
"mmlu_eval_accuracy_high_school_biology": 0.375,
|
160 |
+
"mmlu_eval_accuracy_high_school_chemistry": 0.4090909090909091,
|
161 |
+
"mmlu_eval_accuracy_high_school_computer_science": 0.6666666666666666,
|
162 |
+
"mmlu_eval_accuracy_high_school_european_history": 0.6111111111111112,
|
163 |
+
"mmlu_eval_accuracy_high_school_geography": 0.6818181818181818,
|
164 |
+
"mmlu_eval_accuracy_high_school_government_and_politics": 0.6666666666666666,
|
165 |
+
"mmlu_eval_accuracy_high_school_macroeconomics": 0.32558139534883723,
|
166 |
+
"mmlu_eval_accuracy_high_school_mathematics": 0.2413793103448276,
|
167 |
+
"mmlu_eval_accuracy_high_school_microeconomics": 0.4230769230769231,
|
168 |
+
"mmlu_eval_accuracy_high_school_physics": 0.29411764705882354,
|
169 |
+
"mmlu_eval_accuracy_high_school_psychology": 0.7166666666666667,
|
170 |
+
"mmlu_eval_accuracy_high_school_statistics": 0.2608695652173913,
|
171 |
+
"mmlu_eval_accuracy_high_school_us_history": 0.7272727272727273,
|
172 |
+
"mmlu_eval_accuracy_high_school_world_history": 0.5769230769230769,
|
173 |
+
"mmlu_eval_accuracy_human_aging": 0.6956521739130435,
|
174 |
+
"mmlu_eval_accuracy_human_sexuality": 0.4166666666666667,
|
175 |
+
"mmlu_eval_accuracy_international_law": 0.7692307692307693,
|
176 |
+
"mmlu_eval_accuracy_jurisprudence": 0.36363636363636365,
|
177 |
+
"mmlu_eval_accuracy_logical_fallacies": 0.5555555555555556,
|
178 |
+
"mmlu_eval_accuracy_machine_learning": 0.2727272727272727,
|
179 |
+
"mmlu_eval_accuracy_management": 0.6363636363636364,
|
180 |
+
"mmlu_eval_accuracy_marketing": 0.76,
|
181 |
+
"mmlu_eval_accuracy_medical_genetics": 0.7272727272727273,
|
182 |
+
"mmlu_eval_accuracy_miscellaneous": 0.6627906976744186,
|
183 |
+
"mmlu_eval_accuracy_moral_disputes": 0.5263157894736842,
|
184 |
+
"mmlu_eval_accuracy_moral_scenarios": 0.24,
|
185 |
+
"mmlu_eval_accuracy_nutrition": 0.5757575757575758,
|
186 |
+
"mmlu_eval_accuracy_philosophy": 0.5,
|
187 |
+
"mmlu_eval_accuracy_prehistory": 0.45714285714285713,
|
188 |
+
"mmlu_eval_accuracy_professional_accounting": 0.3225806451612903,
|
189 |
+
"mmlu_eval_accuracy_professional_law": 0.35294117647058826,
|
190 |
+
"mmlu_eval_accuracy_professional_medicine": 0.41935483870967744,
|
191 |
+
"mmlu_eval_accuracy_professional_psychology": 0.391304347826087,
|
192 |
+
"mmlu_eval_accuracy_public_relations": 0.5,
|
193 |
+
"mmlu_eval_accuracy_security_studies": 0.5185185185185185,
|
194 |
+
"mmlu_eval_accuracy_sociology": 0.6818181818181818,
|
195 |
+
"mmlu_eval_accuracy_us_foreign_policy": 0.5454545454545454,
|
196 |
+
"mmlu_eval_accuracy_virology": 0.3888888888888889,
|
197 |
+
"mmlu_eval_accuracy_world_religions": 0.7368421052631579,
|
198 |
+
"mmlu_loss": 1.1315238676556718,
|
199 |
+
"step": 200
|
200 |
+
}
|
201 |
+
],
|
202 |
+
"max_steps": 5000,
|
203 |
+
"num_train_epochs": 6,
|
204 |
+
"total_flos": 5.082084345131827e+16,
|
205 |
+
"trial_name": null,
|
206 |
+
"trial_params": null
|
207 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de1718044df058d493a02df580cf2d03a18301bd3fb5c130230ece0994222cf6
|
3 |
+
size 6011
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<unk>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de1718044df058d493a02df580cf2d03a18301bd3fb5c130230ece0994222cf6
|
3 |
+
size 6011
|