Initial commit from mrm8488
Browse files- config.json +167 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +526 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,167 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"EncoderDecoderModel"
|
| 4 |
+
],
|
| 5 |
+
"decoder": {
|
| 6 |
+
"_name_or_path": "bert-base-cased",
|
| 7 |
+
"add_cross_attention": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BertForMaskedLM"
|
| 10 |
+
],
|
| 11 |
+
"attention_probs_dropout_prob": 0.1,
|
| 12 |
+
"bad_words_ids": null,
|
| 13 |
+
"bos_token_id": null,
|
| 14 |
+
"chunk_size_feed_forward": 0,
|
| 15 |
+
"decoder_start_token_id": null,
|
| 16 |
+
"diversity_penalty": 0.0,
|
| 17 |
+
"do_sample": false,
|
| 18 |
+
"early_stopping": false,
|
| 19 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 20 |
+
"eos_token_id": null,
|
| 21 |
+
"finetuning_task": null,
|
| 22 |
+
"forced_bos_token_id": null,
|
| 23 |
+
"forced_eos_token_id": null,
|
| 24 |
+
"gradient_checkpointing": false,
|
| 25 |
+
"hidden_act": "gelu",
|
| 26 |
+
"hidden_dropout_prob": 0.1,
|
| 27 |
+
"hidden_size": 768,
|
| 28 |
+
"id2label": {
|
| 29 |
+
"0": "LABEL_0",
|
| 30 |
+
"1": "LABEL_1"
|
| 31 |
+
},
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"intermediate_size": 3072,
|
| 34 |
+
"is_decoder": true,
|
| 35 |
+
"is_encoder_decoder": false,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_eps": 1e-12,
|
| 41 |
+
"length_penalty": 1.0,
|
| 42 |
+
"max_length": 20,
|
| 43 |
+
"max_position_embeddings": 512,
|
| 44 |
+
"min_length": 0,
|
| 45 |
+
"model_type": "bert",
|
| 46 |
+
"no_repeat_ngram_size": 0,
|
| 47 |
+
"num_attention_heads": 12,
|
| 48 |
+
"num_beam_groups": 1,
|
| 49 |
+
"num_beams": 1,
|
| 50 |
+
"num_hidden_layers": 12,
|
| 51 |
+
"num_return_sequences": 1,
|
| 52 |
+
"output_attentions": false,
|
| 53 |
+
"output_hidden_states": false,
|
| 54 |
+
"output_scores": false,
|
| 55 |
+
"pad_token_id": 0,
|
| 56 |
+
"position_embedding_type": "absolute",
|
| 57 |
+
"prefix": null,
|
| 58 |
+
"problem_type": null,
|
| 59 |
+
"pruned_heads": {},
|
| 60 |
+
"remove_invalid_values": false,
|
| 61 |
+
"repetition_penalty": 1.0,
|
| 62 |
+
"return_dict": true,
|
| 63 |
+
"return_dict_in_generate": false,
|
| 64 |
+
"sep_token_id": null,
|
| 65 |
+
"task_specific_params": null,
|
| 66 |
+
"temperature": 1.0,
|
| 67 |
+
"tie_encoder_decoder": false,
|
| 68 |
+
"tie_word_embeddings": true,
|
| 69 |
+
"tokenizer_class": null,
|
| 70 |
+
"top_k": 50,
|
| 71 |
+
"top_p": 1.0,
|
| 72 |
+
"torchscript": false,
|
| 73 |
+
"transformers_version": "4.6.0.dev0",
|
| 74 |
+
"type_vocab_size": 2,
|
| 75 |
+
"use_bfloat16": false,
|
| 76 |
+
"use_cache": true,
|
| 77 |
+
"vocab_size": 28996
|
| 78 |
+
},
|
| 79 |
+
"decoder_start_token_id": 101,
|
| 80 |
+
"early_stopping": true,
|
| 81 |
+
"encoder": {
|
| 82 |
+
"_name_or_path": "bert-base-cased",
|
| 83 |
+
"add_cross_attention": false,
|
| 84 |
+
"architectures": [
|
| 85 |
+
"BertForMaskedLM"
|
| 86 |
+
],
|
| 87 |
+
"attention_probs_dropout_prob": 0.1,
|
| 88 |
+
"bad_words_ids": null,
|
| 89 |
+
"bos_token_id": null,
|
| 90 |
+
"chunk_size_feed_forward": 0,
|
| 91 |
+
"decoder_start_token_id": null,
|
| 92 |
+
"diversity_penalty": 0.0,
|
| 93 |
+
"do_sample": false,
|
| 94 |
+
"early_stopping": false,
|
| 95 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 96 |
+
"eos_token_id": null,
|
| 97 |
+
"finetuning_task": null,
|
| 98 |
+
"forced_bos_token_id": null,
|
| 99 |
+
"forced_eos_token_id": null,
|
| 100 |
+
"gradient_checkpointing": false,
|
| 101 |
+
"hidden_act": "gelu",
|
| 102 |
+
"hidden_dropout_prob": 0.1,
|
| 103 |
+
"hidden_size": 768,
|
| 104 |
+
"id2label": {
|
| 105 |
+
"0": "LABEL_0",
|
| 106 |
+
"1": "LABEL_1"
|
| 107 |
+
},
|
| 108 |
+
"initializer_range": 0.02,
|
| 109 |
+
"intermediate_size": 3072,
|
| 110 |
+
"is_decoder": false,
|
| 111 |
+
"is_encoder_decoder": false,
|
| 112 |
+
"label2id": {
|
| 113 |
+
"LABEL_0": 0,
|
| 114 |
+
"LABEL_1": 1
|
| 115 |
+
},
|
| 116 |
+
"layer_norm_eps": 1e-12,
|
| 117 |
+
"length_penalty": 1.0,
|
| 118 |
+
"max_length": 20,
|
| 119 |
+
"max_position_embeddings": 512,
|
| 120 |
+
"min_length": 0,
|
| 121 |
+
"model_type": "bert",
|
| 122 |
+
"no_repeat_ngram_size": 0,
|
| 123 |
+
"num_attention_heads": 12,
|
| 124 |
+
"num_beam_groups": 1,
|
| 125 |
+
"num_beams": 1,
|
| 126 |
+
"num_hidden_layers": 12,
|
| 127 |
+
"num_return_sequences": 1,
|
| 128 |
+
"output_attentions": false,
|
| 129 |
+
"output_hidden_states": false,
|
| 130 |
+
"output_scores": false,
|
| 131 |
+
"pad_token_id": 0,
|
| 132 |
+
"position_embedding_type": "absolute",
|
| 133 |
+
"prefix": null,
|
| 134 |
+
"problem_type": null,
|
| 135 |
+
"pruned_heads": {},
|
| 136 |
+
"remove_invalid_values": false,
|
| 137 |
+
"repetition_penalty": 1.0,
|
| 138 |
+
"return_dict": true,
|
| 139 |
+
"return_dict_in_generate": false,
|
| 140 |
+
"sep_token_id": null,
|
| 141 |
+
"task_specific_params": null,
|
| 142 |
+
"temperature": 1.0,
|
| 143 |
+
"tie_encoder_decoder": false,
|
| 144 |
+
"tie_word_embeddings": true,
|
| 145 |
+
"tokenizer_class": null,
|
| 146 |
+
"top_k": 50,
|
| 147 |
+
"top_p": 1.0,
|
| 148 |
+
"torchscript": false,
|
| 149 |
+
"transformers_version": "4.6.0.dev0",
|
| 150 |
+
"type_vocab_size": 2,
|
| 151 |
+
"use_bfloat16": false,
|
| 152 |
+
"use_cache": true,
|
| 153 |
+
"vocab_size": 28996
|
| 154 |
+
},
|
| 155 |
+
"eos_token_id": 102,
|
| 156 |
+
"is_encoder_decoder": true,
|
| 157 |
+
"length_penalty": 2.0,
|
| 158 |
+
"max_length": 64,
|
| 159 |
+
"min_length": 4,
|
| 160 |
+
"model_type": "encoder-decoder",
|
| 161 |
+
"no_repeat_ngram_size": 3,
|
| 162 |
+
"num_beams": 4,
|
| 163 |
+
"pad_token_id": 0,
|
| 164 |
+
"tie_encoder_decoder": true,
|
| 165 |
+
"transformers_version": null,
|
| 166 |
+
"vocab_size": 28996
|
| 167 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99403856eb2ed1bb3b35ce60ba61b98a08e32484cd78f768c6f1ae60dc36b714
|
| 3 |
+
size 549391205
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,526 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.939195509822264,
|
| 5 |
+
"global_step": 42500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.12,
|
| 12 |
+
"learning_rate": 4.9415341440598695e-05,
|
| 13 |
+
"loss": 4.3211,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.23,
|
| 18 |
+
"learning_rate": 4.883068288119738e-05,
|
| 19 |
+
"loss": 3.4901,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.35,
|
| 24 |
+
"learning_rate": 4.8246024321796074e-05,
|
| 25 |
+
"loss": 3.1921,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.47,
|
| 30 |
+
"learning_rate": 4.766136576239477e-05,
|
| 31 |
+
"loss": 2.967,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.58,
|
| 36 |
+
"learning_rate": 4.7076707202993454e-05,
|
| 37 |
+
"loss": 2.8175,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.7,
|
| 42 |
+
"learning_rate": 4.6492048643592146e-05,
|
| 43 |
+
"loss": 2.7129,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.82,
|
| 48 |
+
"learning_rate": 4.590739008419083e-05,
|
| 49 |
+
"loss": 2.6442,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.94,
|
| 54 |
+
"learning_rate": 4.5322731524789526e-05,
|
| 55 |
+
"loss": 2.5971,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.05,
|
| 60 |
+
"learning_rate": 4.473807296538822e-05,
|
| 61 |
+
"loss": 2.4775,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.17,
|
| 66 |
+
"learning_rate": 4.4153414405986905e-05,
|
| 67 |
+
"loss": 2.3784,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.29,
|
| 72 |
+
"learning_rate": 4.35687558465856e-05,
|
| 73 |
+
"loss": 2.3465,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.4,
|
| 78 |
+
"learning_rate": 4.298409728718429e-05,
|
| 79 |
+
"loss": 2.3377,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.52,
|
| 84 |
+
"learning_rate": 4.239943872778298e-05,
|
| 85 |
+
"loss": 2.3163,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.64,
|
| 90 |
+
"learning_rate": 4.181478016838167e-05,
|
| 91 |
+
"loss": 2.3037,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.75,
|
| 96 |
+
"learning_rate": 4.123012160898036e-05,
|
| 97 |
+
"loss": 2.2963,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.87,
|
| 102 |
+
"learning_rate": 4.064546304957905e-05,
|
| 103 |
+
"loss": 2.279,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.99,
|
| 108 |
+
"learning_rate": 4.006080449017774e-05,
|
| 109 |
+
"loss": 2.2744,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.1,
|
| 114 |
+
"learning_rate": 3.947614593077643e-05,
|
| 115 |
+
"loss": 2.0997,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.22,
|
| 120 |
+
"learning_rate": 3.889148737137512e-05,
|
| 121 |
+
"loss": 2.0715,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.34,
|
| 126 |
+
"learning_rate": 3.8306828811973814e-05,
|
| 127 |
+
"loss": 2.0789,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.46,
|
| 132 |
+
"learning_rate": 3.77221702525725e-05,
|
| 133 |
+
"loss": 2.075,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.57,
|
| 138 |
+
"learning_rate": 3.713751169317119e-05,
|
| 139 |
+
"loss": 2.0657,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.69,
|
| 144 |
+
"learning_rate": 3.655285313376988e-05,
|
| 145 |
+
"loss": 2.0795,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.81,
|
| 150 |
+
"learning_rate": 3.596819457436857e-05,
|
| 151 |
+
"loss": 2.0503,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.92,
|
| 156 |
+
"learning_rate": 3.538353601496726e-05,
|
| 157 |
+
"loss": 2.0637,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.04,
|
| 162 |
+
"learning_rate": 3.479887745556595e-05,
|
| 163 |
+
"loss": 1.9936,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.16,
|
| 168 |
+
"learning_rate": 3.421421889616464e-05,
|
| 169 |
+
"loss": 1.8791,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.27,
|
| 174 |
+
"learning_rate": 3.362956033676333e-05,
|
| 175 |
+
"loss": 1.8823,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.39,
|
| 180 |
+
"learning_rate": 3.304490177736202e-05,
|
| 181 |
+
"loss": 1.8947,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.51,
|
| 186 |
+
"learning_rate": 3.246024321796071e-05,
|
| 187 |
+
"loss": 1.8993,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.62,
|
| 192 |
+
"learning_rate": 3.18755846585594e-05,
|
| 193 |
+
"loss": 1.8999,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.74,
|
| 198 |
+
"learning_rate": 3.129092609915809e-05,
|
| 199 |
+
"loss": 1.8917,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.86,
|
| 204 |
+
"learning_rate": 3.070626753975678e-05,
|
| 205 |
+
"loss": 1.9039,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.98,
|
| 210 |
+
"learning_rate": 3.0121608980355477e-05,
|
| 211 |
+
"loss": 1.8958,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.09,
|
| 216 |
+
"learning_rate": 2.9536950420954164e-05,
|
| 217 |
+
"loss": 1.7626,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.21,
|
| 222 |
+
"learning_rate": 2.8952291861552856e-05,
|
| 223 |
+
"loss": 1.7527,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.33,
|
| 228 |
+
"learning_rate": 2.8367633302151546e-05,
|
| 229 |
+
"loss": 1.7416,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.44,
|
| 234 |
+
"learning_rate": 2.7782974742750236e-05,
|
| 235 |
+
"loss": 1.7483,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.56,
|
| 240 |
+
"learning_rate": 2.7198316183348925e-05,
|
| 241 |
+
"loss": 1.7518,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.68,
|
| 246 |
+
"learning_rate": 2.6613657623947615e-05,
|
| 247 |
+
"loss": 1.7548,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.79,
|
| 252 |
+
"learning_rate": 2.6028999064546304e-05,
|
| 253 |
+
"loss": 1.7542,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.91,
|
| 258 |
+
"learning_rate": 2.5444340505144997e-05,
|
| 259 |
+
"loss": 1.7547,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.03,
|
| 264 |
+
"learning_rate": 2.4859681945743687e-05,
|
| 265 |
+
"loss": 1.7305,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.14,
|
| 270 |
+
"learning_rate": 2.4275023386342376e-05,
|
| 271 |
+
"loss": 1.6149,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.26,
|
| 276 |
+
"learning_rate": 2.3690364826941066e-05,
|
| 277 |
+
"loss": 1.6119,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 5.38,
|
| 282 |
+
"learning_rate": 2.310570626753976e-05,
|
| 283 |
+
"loss": 1.6279,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 5.5,
|
| 288 |
+
"learning_rate": 2.2521047708138448e-05,
|
| 289 |
+
"loss": 1.6463,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 5.61,
|
| 294 |
+
"learning_rate": 2.1936389148737138e-05,
|
| 295 |
+
"loss": 1.6341,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 5.73,
|
| 300 |
+
"learning_rate": 2.1351730589335827e-05,
|
| 301 |
+
"loss": 1.6401,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 5.85,
|
| 306 |
+
"learning_rate": 2.076707202993452e-05,
|
| 307 |
+
"loss": 1.647,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 5.96,
|
| 312 |
+
"learning_rate": 2.018241347053321e-05,
|
| 313 |
+
"loss": 1.6439,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 6.08,
|
| 318 |
+
"learning_rate": 1.95977549111319e-05,
|
| 319 |
+
"loss": 1.5445,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.2,
|
| 324 |
+
"learning_rate": 1.9013096351730592e-05,
|
| 325 |
+
"loss": 1.5145,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.31,
|
| 330 |
+
"learning_rate": 1.8428437792329282e-05,
|
| 331 |
+
"loss": 1.5314,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.43,
|
| 336 |
+
"learning_rate": 1.784377923292797e-05,
|
| 337 |
+
"loss": 1.534,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.55,
|
| 342 |
+
"learning_rate": 1.725912067352666e-05,
|
| 343 |
+
"loss": 1.5329,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.67,
|
| 348 |
+
"learning_rate": 1.6674462114125354e-05,
|
| 349 |
+
"loss": 1.5302,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.78,
|
| 354 |
+
"learning_rate": 1.6089803554724043e-05,
|
| 355 |
+
"loss": 1.5467,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.9,
|
| 360 |
+
"learning_rate": 1.5505144995322733e-05,
|
| 361 |
+
"loss": 1.5472,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 7.02,
|
| 366 |
+
"learning_rate": 1.492048643592142e-05,
|
| 367 |
+
"loss": 1.5257,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 7.13,
|
| 372 |
+
"learning_rate": 1.4335827876520114e-05,
|
| 373 |
+
"loss": 1.4319,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 7.25,
|
| 378 |
+
"learning_rate": 1.3751169317118803e-05,
|
| 379 |
+
"loss": 1.4378,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 7.37,
|
| 384 |
+
"learning_rate": 1.3166510757717493e-05,
|
| 385 |
+
"loss": 1.4506,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 7.48,
|
| 390 |
+
"learning_rate": 1.2581852198316186e-05,
|
| 391 |
+
"loss": 1.4453,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 7.6,
|
| 396 |
+
"learning_rate": 1.1997193638914875e-05,
|
| 397 |
+
"loss": 1.4588,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 7.72,
|
| 402 |
+
"learning_rate": 1.1412535079513565e-05,
|
| 403 |
+
"loss": 1.4601,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 7.83,
|
| 408 |
+
"learning_rate": 1.0827876520112256e-05,
|
| 409 |
+
"loss": 1.4585,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 7.95,
|
| 414 |
+
"learning_rate": 1.0243217960710946e-05,
|
| 415 |
+
"loss": 1.4664,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 8.07,
|
| 420 |
+
"learning_rate": 9.658559401309635e-06,
|
| 421 |
+
"loss": 1.3973,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 8.19,
|
| 426 |
+
"learning_rate": 9.073900841908325e-06,
|
| 427 |
+
"loss": 1.3694,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 8.3,
|
| 432 |
+
"learning_rate": 8.489242282507016e-06,
|
| 433 |
+
"loss": 1.3876,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 8.42,
|
| 438 |
+
"learning_rate": 7.904583723105706e-06,
|
| 439 |
+
"loss": 1.3896,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 8.54,
|
| 444 |
+
"learning_rate": 7.319925163704397e-06,
|
| 445 |
+
"loss": 1.3918,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 8.65,
|
| 450 |
+
"learning_rate": 6.735266604303088e-06,
|
| 451 |
+
"loss": 1.382,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 8.77,
|
| 456 |
+
"learning_rate": 6.1506080449017775e-06,
|
| 457 |
+
"loss": 1.3942,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 8.89,
|
| 462 |
+
"learning_rate": 5.565949485500468e-06,
|
| 463 |
+
"loss": 1.3889,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 9.0,
|
| 468 |
+
"learning_rate": 4.981290926099158e-06,
|
| 469 |
+
"loss": 1.3951,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 9.12,
|
| 474 |
+
"learning_rate": 4.396632366697849e-06,
|
| 475 |
+
"loss": 1.3346,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 9.24,
|
| 480 |
+
"learning_rate": 3.811973807296539e-06,
|
| 481 |
+
"loss": 1.3361,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 9.35,
|
| 486 |
+
"learning_rate": 3.2273152478952295e-06,
|
| 487 |
+
"loss": 1.3329,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 9.47,
|
| 492 |
+
"learning_rate": 2.64265668849392e-06,
|
| 493 |
+
"loss": 1.3371,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 9.59,
|
| 498 |
+
"learning_rate": 2.0579981290926103e-06,
|
| 499 |
+
"loss": 1.3442,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 9.71,
|
| 504 |
+
"learning_rate": 1.4733395696913004e-06,
|
| 505 |
+
"loss": 1.3402,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 9.82,
|
| 510 |
+
"learning_rate": 8.886810102899906e-07,
|
| 511 |
+
"loss": 1.3439,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 9.94,
|
| 516 |
+
"learning_rate": 3.04022450888681e-07,
|
| 517 |
+
"loss": 1.3374,
|
| 518 |
+
"step": 42500
|
| 519 |
+
}
|
| 520 |
+
],
|
| 521 |
+
"max_steps": 42760,
|
| 522 |
+
"num_train_epochs": 10,
|
| 523 |
+
"total_flos": 1687120822272000.0,
|
| 524 |
+
"trial_name": null,
|
| 525 |
+
"trial_params": null
|
| 526 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7fa6e7af92ab62222c95de94b938bdd228b1bfefbf065f4598b4e87b9fdbd08
|
| 3 |
+
size 2543
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|