File size: 3,492 Bytes
ed5a986 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 | {
"fixture": "huggingface-mic/plbart-java-cs-mic",
"key": "cac9f40f742c39637b23fe32b8e6462905c9aa0788de7b679b9a6b6aa5fdd7d5",
"key_fields": {
"architectures": [
"PLBartForConditionalGeneration"
],
"output_hidden_states": false,
"return_dict": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": true,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"problem_type": null,
"vocab_size": 50005,
"max_position_embeddings": 1024,
"encoder_layers": 2,
"encoder_ffn_dim": 128,
"encoder_attention_heads": 4,
"decoder_layers": 2,
"decoder_ffn_dim": 128,
"decoder_attention_heads": 4,
"encoder_layerdrop": 0.0,
"decoder_layerdrop": 0.0,
"use_cache": true,
"activation_function": "gelu",
"d_model": 64,
"dropout": 0.1,
"attention_dropout": 0.1,
"activation_dropout": 0.0,
"init_std": 0.02,
"classifier_dropout": 0.0,
"scale_embedding": true,
"pad_token_id": 1,
"bos_token_id": 0,
"eos_token_id": 2,
"forced_eos_token_id": 2,
"is_decoder": false,
"tie_word_embeddings": true,
"model_type": "plbart",
"output_attentions": false
},
"covers": {
"uclanlp/plbart-java-cs": "0426c742606ceb3c2e12de0ae9c46a969bba6023"
},
"built_from": {
"repo": "uclanlp/plbart-java-cs",
"revision": "0426c742606ceb3c2e12de0ae9c46a969bba6023"
},
"seed": 17,
"dtype": "float32",
"builder": "example/build_fixtures.py",
"builder_revision": "e0a6b1514964849b9340055e7d6d8ac67e21e051",
"recipe": {
"seed": 17
},
"shrink": "rule",
"model_class": "PLBartForConditionalGeneration",
"parameters": 3499328,
"missing_parameters": [],
"serialization": {
"file": "model.safetensors",
"source_file": "pytorch_model.bin",
"reverted_conversions": []
},
"checkpoint_inspection": "parameter headers/indexes; bounded binary fallback",
"numeric_health_scope": "CPU float32/bfloat16/float16; autocast for low-precision losses",
"captured": {
"call": "training step",
"inputs": [
"attention_mask",
"input_ids",
"labels"
],
"class": "PLBartForConditionalGeneration"
},
"weights": "random",
"gate": {
"random": {
"pass": true,
"accepted_insensitive": {},
"threshold": 0.001,
"deltas": {
"input_ids:roll_batch": 0.006489932537078857,
"input_ids:reverse": 0.010007187724113464,
"attention_mask:all_ones": 0.0062996819615364075
},
"weakest": "attention_mask:all_ones",
"no_perturbation_defined": [],
"not_a_forward_parameter": []
}
},
"numeric_health": {
"float32": {
"outputs_finite": true,
"loss_finite": true,
"gradients_finite": true,
"finite": true
},
"bfloat16": {
"outputs_finite": true,
"loss_finite": true,
"gradients_finite": true,
"finite": true
},
"float16": {
"outputs_finite": true,
"loss_finite": true,
"unscaled_gradients_finite": true,
"finite": true
}
},
"copied_unchanged": [
"sentencepiece.bpe.model"
],
"environment": {
"python": "3.11.18",
"machine": "x86_64",
"torch": "2.15.0+cpu",
"transformers": "5.23.0.dev0",
"tokenizers": "0.23.3"
},
"sha256": {
"config.json": "ebb6aa6accc2252973c36573acc3a4dc75f870eef392223e385074b2755fc800",
"generation_config.json": "18d2ce2587071d5b671d7202b210c4813a2618d519b62cbcf4a7c08b77b74673",
"model.safetensors": "6a18bddb252cb458c8024db7ef08ad1b698d482e599724c6e341903eb36ce19e",
"sentencepiece.bpe.model": "f72f5d040a176945623a255484d24066f8c0da89a294359154e226efbe494b80"
}
}
|