Upload folder using huggingface_hub
Browse files- config.json +186 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +176 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/data4/luyiheng/BARTfinetune/lr_5e-05/checkpoint-195",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForSequenceClassification"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.0,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 1024,
|
| 15 |
+
"decoder_attention_heads": 16,
|
| 16 |
+
"decoder_ffn_dim": 4096,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"encoder_attention_heads": 16,
|
| 22 |
+
"encoder_ffn_dim": 4096,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 12,
|
| 25 |
+
"eos_token_id": 2,
|
| 26 |
+
"forced_eos_token_id": 2,
|
| 27 |
+
"gradient_checkpointing": false,
|
| 28 |
+
"id2label": {
|
| 29 |
+
"0": "Accessibility",
|
| 30 |
+
"1": "Architectures",
|
| 31 |
+
"2": "Artificial intelligence",
|
| 32 |
+
"3": "Arts and humanities",
|
| 33 |
+
"4": "Collaborative and social computing",
|
| 34 |
+
"5": "Communication hardware, interfaces and storage",
|
| 35 |
+
"6": "Computational complexity and cryptography",
|
| 36 |
+
"7": "Computers in other domains",
|
| 37 |
+
"8": "Continuous mathematics",
|
| 38 |
+
"9": "Cross-computing tools and techniques",
|
| 39 |
+
"10": "Cryptography",
|
| 40 |
+
"11": "Data management systems",
|
| 41 |
+
"12": "Database and storage security",
|
| 42 |
+
"13": "Dependable and fault-tolerant systems and networks",
|
| 43 |
+
"14": "Design and analysis of algorithms",
|
| 44 |
+
"15": "Discrete mathematics",
|
| 45 |
+
"16": "Distributed computing methodologies",
|
| 46 |
+
"17": "Document management and text processing",
|
| 47 |
+
"18": "Document types",
|
| 48 |
+
"19": "Education",
|
| 49 |
+
"20": "Electronic commerce",
|
| 50 |
+
"21": "Electronic design automation",
|
| 51 |
+
"22": "Embedded and cyber-physical systems",
|
| 52 |
+
"23": "Emerging technologies",
|
| 53 |
+
"24": "Enterprise computing",
|
| 54 |
+
"25": "Formal languages and automata theory",
|
| 55 |
+
"26": "Formal methods and theory of security",
|
| 56 |
+
"27": "Hardware test",
|
| 57 |
+
"28": "Hardware validation",
|
| 58 |
+
"29": "Human and societal aspects of security and privacy",
|
| 59 |
+
"30": "Human computer interaction (HCI)",
|
| 60 |
+
"31": "Information retrieval",
|
| 61 |
+
"32": "Information storage systems",
|
| 62 |
+
"33": "Information systems applications",
|
| 63 |
+
"34": "Information theory",
|
| 64 |
+
"35": "Integrated circuits",
|
| 65 |
+
"36": "Interaction design",
|
| 66 |
+
"37": "Intrusion/anomaly detection and malware mitigation",
|
| 67 |
+
"38": "Logic",
|
| 68 |
+
"39": "Machine learning",
|
| 69 |
+
"40": "Mathematical analysis",
|
| 70 |
+
"41": "Mathematical software",
|
| 71 |
+
"42": "Modeling and simulation",
|
| 72 |
+
"43": "Models of computation",
|
| 73 |
+
"44": "Network algorithms",
|
| 74 |
+
"45": "Network architectures",
|
| 75 |
+
"46": "Network components",
|
| 76 |
+
"47": "Network performance evaluation",
|
| 77 |
+
"48": "Network properties",
|
| 78 |
+
"49": "Network protocols",
|
| 79 |
+
"50": "Network security",
|
| 80 |
+
"51": "Network services",
|
| 81 |
+
"52": "Network types",
|
| 82 |
+
"53": "Parallel computing methodologies",
|
| 83 |
+
"54": "Power and energy",
|
| 84 |
+
"55": "Probability and statistics",
|
| 85 |
+
"56": "Randomness, geometry and discrete structures",
|
| 86 |
+
"57": "Real-time systems",
|
| 87 |
+
"58": "Robustness",
|
| 88 |
+
"59": "Security in hardware",
|
| 89 |
+
"60": "Security services",
|
| 90 |
+
"61": "Semantics and reasoning",
|
| 91 |
+
"62": "Software and application security",
|
| 92 |
+
"63": "Symbolic and algebraic manipulation",
|
| 93 |
+
"64": "Systems security",
|
| 94 |
+
"65": "Theory and algorithms for application domains",
|
| 95 |
+
"66": "Ubiquitous and mobile computing",
|
| 96 |
+
"67": "Very large scale integration design",
|
| 97 |
+
"68": "Visualization",
|
| 98 |
+
"69": "World Wide Web"
|
| 99 |
+
},
|
| 100 |
+
"init_std": 0.02,
|
| 101 |
+
"is_encoder_decoder": true,
|
| 102 |
+
"label2id": {
|
| 103 |
+
"Accessibility": 0,
|
| 104 |
+
"Architectures": 1,
|
| 105 |
+
"Artificial intelligence": 2,
|
| 106 |
+
"Arts and humanities": 3,
|
| 107 |
+
"Collaborative and social computing": 4,
|
| 108 |
+
"Communication hardware, interfaces and storage": 5,
|
| 109 |
+
"Computational complexity and cryptography": 6,
|
| 110 |
+
"Computers in other domains": 7,
|
| 111 |
+
"Continuous mathematics": 8,
|
| 112 |
+
"Cross-computing tools and techniques": 9,
|
| 113 |
+
"Cryptography": 10,
|
| 114 |
+
"Data management systems": 11,
|
| 115 |
+
"Database and storage security": 12,
|
| 116 |
+
"Dependable and fault-tolerant systems and networks": 13,
|
| 117 |
+
"Design and analysis of algorithms": 14,
|
| 118 |
+
"Discrete mathematics": 15,
|
| 119 |
+
"Distributed computing methodologies": 16,
|
| 120 |
+
"Document management and text processing": 17,
|
| 121 |
+
"Document types": 18,
|
| 122 |
+
"Education": 19,
|
| 123 |
+
"Electronic commerce": 20,
|
| 124 |
+
"Electronic design automation": 21,
|
| 125 |
+
"Embedded and cyber-physical systems": 22,
|
| 126 |
+
"Emerging technologies": 23,
|
| 127 |
+
"Enterprise computing": 24,
|
| 128 |
+
"Formal languages and automata theory": 25,
|
| 129 |
+
"Formal methods and theory of security": 26,
|
| 130 |
+
"Hardware test": 27,
|
| 131 |
+
"Hardware validation": 28,
|
| 132 |
+
"Human and societal aspects of security and privacy": 29,
|
| 133 |
+
"Human computer interaction (HCI)": 30,
|
| 134 |
+
"Information retrieval": 31,
|
| 135 |
+
"Information storage systems": 32,
|
| 136 |
+
"Information systems applications": 33,
|
| 137 |
+
"Information theory": 34,
|
| 138 |
+
"Integrated circuits": 35,
|
| 139 |
+
"Interaction design": 36,
|
| 140 |
+
"Intrusion/anomaly detection and malware mitigation": 37,
|
| 141 |
+
"Logic": 38,
|
| 142 |
+
"Machine learning": 39,
|
| 143 |
+
"Mathematical analysis": 40,
|
| 144 |
+
"Mathematical software": 41,
|
| 145 |
+
"Modeling and simulation": 42,
|
| 146 |
+
"Models of computation": 43,
|
| 147 |
+
"Network algorithms": 44,
|
| 148 |
+
"Network architectures": 45,
|
| 149 |
+
"Network components": 46,
|
| 150 |
+
"Network performance evaluation": 47,
|
| 151 |
+
"Network properties": 48,
|
| 152 |
+
"Network protocols": 49,
|
| 153 |
+
"Network security": 50,
|
| 154 |
+
"Network services": 51,
|
| 155 |
+
"Network types": 52,
|
| 156 |
+
"Parallel computing methodologies": 53,
|
| 157 |
+
"Power and energy": 54,
|
| 158 |
+
"Probability and statistics": 55,
|
| 159 |
+
"Randomness, geometry and discrete structures": 56,
|
| 160 |
+
"Real-time systems": 57,
|
| 161 |
+
"Robustness": 58,
|
| 162 |
+
"Security in hardware": 59,
|
| 163 |
+
"Security services": 60,
|
| 164 |
+
"Semantics and reasoning": 61,
|
| 165 |
+
"Software and application security": 62,
|
| 166 |
+
"Symbolic and algebraic manipulation": 63,
|
| 167 |
+
"Systems security": 64,
|
| 168 |
+
"Theory and algorithms for application domains": 65,
|
| 169 |
+
"Ubiquitous and mobile computing": 66,
|
| 170 |
+
"Very large scale integration design": 67,
|
| 171 |
+
"Visualization": 68,
|
| 172 |
+
"World Wide Web": 69
|
| 173 |
+
},
|
| 174 |
+
"max_position_embeddings": 1024,
|
| 175 |
+
"model_type": "bart",
|
| 176 |
+
"normalize_before": false,
|
| 177 |
+
"num_hidden_layers": 12,
|
| 178 |
+
"output_past": false,
|
| 179 |
+
"pad_token_id": 1,
|
| 180 |
+
"problem_type": "single_label_classification",
|
| 181 |
+
"scale_embedding": false,
|
| 182 |
+
"torch_dtype": "float32",
|
| 183 |
+
"transformers_version": "4.49.0",
|
| 184 |
+
"use_cache": true,
|
| 185 |
+
"vocab_size": 50265
|
| 186 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da1bb4e130cb431e30e82781ccefd35a74d1b9c077d0e81d9c5c9e9c83aec85a
|
| 3 |
+
size 1629711664
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71893828336b4af1e66a1620d596c45fb1888e0e29516dabf4ee881693e2aaa4
|
| 3 |
+
size 3259734107
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af8e4284e62fb18a1f03355bf3caa2f34c3cec6fd080ed67ac48efaea98524f0
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15c6516ad83f6c129c8ca1c3fe1a783db9bbc27c576b8ea61ee6ccd4d6241d26
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1024,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "BartTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.886075949367089,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 195,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.25316455696202533,
|
| 13 |
+
"grad_norm": 15.541438102722168,
|
| 14 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 15 |
+
"loss": 4.3307,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5063291139240507,
|
| 20 |
+
"grad_norm": 16.98396110534668,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 4.3055,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.759493670886076,
|
| 27 |
+
"grad_norm": 17.21928596496582,
|
| 28 |
+
"learning_rate": 3e-06,
|
| 29 |
+
"loss": 4.1895,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.0,
|
| 34 |
+
"grad_norm": 13.936151504516602,
|
| 35 |
+
"learning_rate": 4.000000000000001e-06,
|
| 36 |
+
"loss": 3.8896,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.2531645569620253,
|
| 41 |
+
"grad_norm": 16.210145950317383,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 3.894,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.5063291139240507,
|
| 48 |
+
"grad_norm": 15.298253059387207,
|
| 49 |
+
"learning_rate": 6e-06,
|
| 50 |
+
"loss": 3.6968,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.759493670886076,
|
| 55 |
+
"grad_norm": 16.198633193969727,
|
| 56 |
+
"learning_rate": 7.000000000000001e-06,
|
| 57 |
+
"loss": 3.529,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.0,
|
| 62 |
+
"grad_norm": 12.727923393249512,
|
| 63 |
+
"learning_rate": 8.000000000000001e-06,
|
| 64 |
+
"loss": 3.1801,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.2531645569620253,
|
| 69 |
+
"grad_norm": 13.769573211669922,
|
| 70 |
+
"learning_rate": 9e-06,
|
| 71 |
+
"loss": 3.049,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.5063291139240507,
|
| 76 |
+
"grad_norm": 14.311426162719727,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 2.9882,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.5063291139240507,
|
| 83 |
+
"eval_accuracy": 0.22857142857142856,
|
| 84 |
+
"eval_f1": 0.14422788951090837,
|
| 85 |
+
"eval_loss": 2.718834161758423,
|
| 86 |
+
"eval_runtime": 22.0561,
|
| 87 |
+
"eval_samples_per_second": 3.174,
|
| 88 |
+
"eval_steps_per_second": 0.408,
|
| 89 |
+
"step": 100
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.759493670886076,
|
| 93 |
+
"grad_norm": 14.486056327819824,
|
| 94 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 95 |
+
"loss": 2.755,
|
| 96 |
+
"step": 110
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.0,
|
| 100 |
+
"grad_norm": 11.645160675048828,
|
| 101 |
+
"learning_rate": 1.2e-05,
|
| 102 |
+
"loss": 2.4722,
|
| 103 |
+
"step": 120
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.2531645569620253,
|
| 107 |
+
"grad_norm": 14.1466064453125,
|
| 108 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 109 |
+
"loss": 2.4231,
|
| 110 |
+
"step": 130
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.5063291139240507,
|
| 114 |
+
"grad_norm": 14.645957946777344,
|
| 115 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 116 |
+
"loss": 2.3087,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.759493670886076,
|
| 121 |
+
"grad_norm": 12.975454330444336,
|
| 122 |
+
"learning_rate": 1.5e-05,
|
| 123 |
+
"loss": 2.193,
|
| 124 |
+
"step": 150
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 4.0,
|
| 128 |
+
"grad_norm": 11.665339469909668,
|
| 129 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 130 |
+
"loss": 2.0295,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 4.253164556962025,
|
| 135 |
+
"grad_norm": 12.780133247375488,
|
| 136 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 137 |
+
"loss": 1.8715,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.506329113924051,
|
| 142 |
+
"grad_norm": 15.635778427124023,
|
| 143 |
+
"learning_rate": 1.8e-05,
|
| 144 |
+
"loss": 1.8326,
|
| 145 |
+
"step": 180
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.759493670886076,
|
| 149 |
+
"grad_norm": 12.904759407043457,
|
| 150 |
+
"learning_rate": 1.9e-05,
|
| 151 |
+
"loss": 1.7675,
|
| 152 |
+
"step": 190
|
| 153 |
+
}
|
| 154 |
+
],
|
| 155 |
+
"logging_steps": 10,
|
| 156 |
+
"max_steps": 195,
|
| 157 |
+
"num_input_tokens_seen": 0,
|
| 158 |
+
"num_train_epochs": 5,
|
| 159 |
+
"save_steps": 100,
|
| 160 |
+
"stateful_callbacks": {
|
| 161 |
+
"TrainerControl": {
|
| 162 |
+
"args": {
|
| 163 |
+
"should_epoch_stop": false,
|
| 164 |
+
"should_evaluate": false,
|
| 165 |
+
"should_log": false,
|
| 166 |
+
"should_save": true,
|
| 167 |
+
"should_training_stop": true
|
| 168 |
+
},
|
| 169 |
+
"attributes": {}
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"total_flos": 1673975515914240.0,
|
| 173 |
+
"train_batch_size": 8,
|
| 174 |
+
"trial_name": null,
|
| 175 |
+
"trial_params": null
|
| 176 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f76ebd3cf69886a286c10a6016b244dc275575b052b27c0adf08f36020754f66
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|