Upload 11 files
Browse files- config.json +181 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +411 -0
- training_args.zip +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"EncoderDecoderModel"
|
| 4 |
+
],
|
| 5 |
+
"decoder": {
|
| 6 |
+
"_name_or_path": "bert-base-uncased",
|
| 7 |
+
"add_cross_attention": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BertForMaskedLM"
|
| 10 |
+
],
|
| 11 |
+
"attention_probs_dropout_prob": 0.1,
|
| 12 |
+
"bad_words_ids": null,
|
| 13 |
+
"begin_suppress_tokens": null,
|
| 14 |
+
"bos_token_id": null,
|
| 15 |
+
"chunk_size_feed_forward": 0,
|
| 16 |
+
"classifier_dropout": null,
|
| 17 |
+
"cross_attention_hidden_size": null,
|
| 18 |
+
"decoder_start_token_id": null,
|
| 19 |
+
"diversity_penalty": 0.0,
|
| 20 |
+
"do_sample": false,
|
| 21 |
+
"early_stopping": false,
|
| 22 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 23 |
+
"eos_token_id": null,
|
| 24 |
+
"exponential_decay_length_penalty": null,
|
| 25 |
+
"finetuning_task": null,
|
| 26 |
+
"forced_bos_token_id": null,
|
| 27 |
+
"forced_eos_token_id": null,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"hidden_act": "gelu",
|
| 30 |
+
"hidden_dropout_prob": 0.1,
|
| 31 |
+
"hidden_size": 768,
|
| 32 |
+
"id2label": {
|
| 33 |
+
"0": "LABEL_0",
|
| 34 |
+
"1": "LABEL_1"
|
| 35 |
+
},
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 3072,
|
| 38 |
+
"is_decoder": true,
|
| 39 |
+
"is_encoder_decoder": false,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1
|
| 43 |
+
},
|
| 44 |
+
"layer_norm_eps": 1e-12,
|
| 45 |
+
"length_penalty": 1.0,
|
| 46 |
+
"max_length": 20,
|
| 47 |
+
"max_position_embeddings": 512,
|
| 48 |
+
"min_length": 0,
|
| 49 |
+
"model_type": "bert",
|
| 50 |
+
"no_repeat_ngram_size": 0,
|
| 51 |
+
"num_attention_heads": 12,
|
| 52 |
+
"num_beam_groups": 1,
|
| 53 |
+
"num_beams": 1,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"num_return_sequences": 1,
|
| 56 |
+
"output_attentions": false,
|
| 57 |
+
"output_hidden_states": false,
|
| 58 |
+
"output_scores": false,
|
| 59 |
+
"pad_token_id": 0,
|
| 60 |
+
"position_embedding_type": "absolute",
|
| 61 |
+
"prefix": null,
|
| 62 |
+
"problem_type": null,
|
| 63 |
+
"pruned_heads": {},
|
| 64 |
+
"remove_invalid_values": false,
|
| 65 |
+
"repetition_penalty": 1.0,
|
| 66 |
+
"return_dict": true,
|
| 67 |
+
"return_dict_in_generate": false,
|
| 68 |
+
"sep_token_id": null,
|
| 69 |
+
"suppress_tokens": null,
|
| 70 |
+
"task_specific_params": null,
|
| 71 |
+
"temperature": 1.0,
|
| 72 |
+
"tf_legacy_loss": false,
|
| 73 |
+
"tie_encoder_decoder": false,
|
| 74 |
+
"tie_word_embeddings": true,
|
| 75 |
+
"tokenizer_class": null,
|
| 76 |
+
"top_k": 50,
|
| 77 |
+
"top_p": 1.0,
|
| 78 |
+
"torch_dtype": null,
|
| 79 |
+
"torchscript": false,
|
| 80 |
+
"type_vocab_size": 2,
|
| 81 |
+
"typical_p": 1.0,
|
| 82 |
+
"use_bfloat16": false,
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"vocab_size": 30522
|
| 85 |
+
},
|
| 86 |
+
"decoder_start_token_id": 101,
|
| 87 |
+
"early_stopping": true,
|
| 88 |
+
"encoder": {
|
| 89 |
+
"_name_or_path": "bert-base-uncased",
|
| 90 |
+
"add_cross_attention": false,
|
| 91 |
+
"architectures": [
|
| 92 |
+
"BertForMaskedLM"
|
| 93 |
+
],
|
| 94 |
+
"attention_probs_dropout_prob": 0.1,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"begin_suppress_tokens": null,
|
| 97 |
+
"bos_token_id": null,
|
| 98 |
+
"chunk_size_feed_forward": 0,
|
| 99 |
+
"classifier_dropout": null,
|
| 100 |
+
"cross_attention_hidden_size": null,
|
| 101 |
+
"decoder_start_token_id": null,
|
| 102 |
+
"diversity_penalty": 0.0,
|
| 103 |
+
"do_sample": false,
|
| 104 |
+
"early_stopping": false,
|
| 105 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 106 |
+
"eos_token_id": null,
|
| 107 |
+
"exponential_decay_length_penalty": null,
|
| 108 |
+
"finetuning_task": null,
|
| 109 |
+
"forced_bos_token_id": null,
|
| 110 |
+
"forced_eos_token_id": null,
|
| 111 |
+
"gradient_checkpointing": false,
|
| 112 |
+
"hidden_act": "gelu",
|
| 113 |
+
"hidden_dropout_prob": 0.1,
|
| 114 |
+
"hidden_size": 768,
|
| 115 |
+
"id2label": {
|
| 116 |
+
"0": "LABEL_0",
|
| 117 |
+
"1": "LABEL_1"
|
| 118 |
+
},
|
| 119 |
+
"initializer_range": 0.02,
|
| 120 |
+
"intermediate_size": 3072,
|
| 121 |
+
"is_decoder": false,
|
| 122 |
+
"is_encoder_decoder": false,
|
| 123 |
+
"label2id": {
|
| 124 |
+
"LABEL_0": 0,
|
| 125 |
+
"LABEL_1": 1
|
| 126 |
+
},
|
| 127 |
+
"layer_norm_eps": 1e-12,
|
| 128 |
+
"length_penalty": 1.0,
|
| 129 |
+
"max_length": 20,
|
| 130 |
+
"max_position_embeddings": 512,
|
| 131 |
+
"min_length": 0,
|
| 132 |
+
"model_type": "bert",
|
| 133 |
+
"no_repeat_ngram_size": 0,
|
| 134 |
+
"num_attention_heads": 12,
|
| 135 |
+
"num_beam_groups": 1,
|
| 136 |
+
"num_beams": 1,
|
| 137 |
+
"num_hidden_layers": 12,
|
| 138 |
+
"num_return_sequences": 1,
|
| 139 |
+
"output_attentions": false,
|
| 140 |
+
"output_hidden_states": false,
|
| 141 |
+
"output_scores": false,
|
| 142 |
+
"pad_token_id": 0,
|
| 143 |
+
"position_embedding_type": "absolute",
|
| 144 |
+
"prefix": null,
|
| 145 |
+
"problem_type": null,
|
| 146 |
+
"pruned_heads": {},
|
| 147 |
+
"remove_invalid_values": false,
|
| 148 |
+
"repetition_penalty": 1.0,
|
| 149 |
+
"return_dict": true,
|
| 150 |
+
"return_dict_in_generate": false,
|
| 151 |
+
"sep_token_id": null,
|
| 152 |
+
"suppress_tokens": null,
|
| 153 |
+
"task_specific_params": null,
|
| 154 |
+
"temperature": 1.0,
|
| 155 |
+
"tf_legacy_loss": false,
|
| 156 |
+
"tie_encoder_decoder": false,
|
| 157 |
+
"tie_word_embeddings": true,
|
| 158 |
+
"tokenizer_class": null,
|
| 159 |
+
"top_k": 50,
|
| 160 |
+
"top_p": 1.0,
|
| 161 |
+
"torch_dtype": null,
|
| 162 |
+
"torchscript": false,
|
| 163 |
+
"type_vocab_size": 2,
|
| 164 |
+
"typical_p": 1.0,
|
| 165 |
+
"use_bfloat16": false,
|
| 166 |
+
"use_cache": true,
|
| 167 |
+
"vocab_size": 30522
|
| 168 |
+
},
|
| 169 |
+
"eos_token_id": 102,
|
| 170 |
+
"is_encoder_decoder": true,
|
| 171 |
+
"length_penalty": 2.0,
|
| 172 |
+
"max_length": 142,
|
| 173 |
+
"min_length": 56,
|
| 174 |
+
"model_type": "encoder-decoder",
|
| 175 |
+
"no_repeat_ngram_size": 3,
|
| 176 |
+
"num_beams": 4,
|
| 177 |
+
"pad_token_id": 0,
|
| 178 |
+
"torch_dtype": "float32",
|
| 179 |
+
"transformers_version": "4.38.2",
|
| 180 |
+
"vocab_size": 30522
|
| 181 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e9eb56caa5001a28d4b6d48912ea7e6e45aff6559315cdcde1613956c49b8e2
|
| 3 |
+
size 989518784
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b24330d9571d48ff23ba30fd1fb550cd595deed8259bded8c87e9448f507d8af
|
| 3 |
+
size 1974617319
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15f60c92c82ace75f022db2fcaefed23804367bf564765981a6734aeaa60a012
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af75a50b66ed3783cb8d2e61914b50457b4ec826ed0f99042112e891be5ca245
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,411 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9719890036406866,
|
| 5 |
+
"eval_steps": 4000,
|
| 6 |
+
"global_step": 40000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"grad_norm": 0.2733132243156433,
|
| 14 |
+
"learning_rate": 5e-05,
|
| 15 |
+
"loss": 0.3088,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.15,
|
| 20 |
+
"grad_norm": 0.011344216763973236,
|
| 21 |
+
"learning_rate": 4.873022322675674e-05,
|
| 22 |
+
"loss": 0.0012,
|
| 23 |
+
"step": 2000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.22,
|
| 27 |
+
"grad_norm": 0.002656959230080247,
|
| 28 |
+
"learning_rate": 4.746044645351347e-05,
|
| 29 |
+
"loss": 0.0001,
|
| 30 |
+
"step": 3000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3,
|
| 34 |
+
"grad_norm": 0.0012492843670770526,
|
| 35 |
+
"learning_rate": 4.619066968027021e-05,
|
| 36 |
+
"loss": 0.0,
|
| 37 |
+
"step": 4000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3,
|
| 41 |
+
"eval_loss": 5.678263278241502e-06,
|
| 42 |
+
"eval_rouge2_fmeasure": 0.0,
|
| 43 |
+
"eval_rouge2_precision": 0.0,
|
| 44 |
+
"eval_rouge2_recall": 0.0,
|
| 45 |
+
"eval_runtime": 3660.3045,
|
| 46 |
+
"eval_samples_per_second": 2.739,
|
| 47 |
+
"eval_steps_per_second": 0.171,
|
| 48 |
+
"step": 4000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.37,
|
| 52 |
+
"grad_norm": 0.0005404581315815449,
|
| 53 |
+
"learning_rate": 4.4920892907026946e-05,
|
| 54 |
+
"loss": 0.0009,
|
| 55 |
+
"step": 5000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.45,
|
| 59 |
+
"grad_norm": 0.002274229424074292,
|
| 60 |
+
"learning_rate": 4.365111613378368e-05,
|
| 61 |
+
"loss": 0.0001,
|
| 62 |
+
"step": 6000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.52,
|
| 66 |
+
"grad_norm": 0.001682213624008,
|
| 67 |
+
"learning_rate": 4.2381339360540415e-05,
|
| 68 |
+
"loss": 0.0001,
|
| 69 |
+
"step": 7000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.59,
|
| 73 |
+
"grad_norm": 0.00026362488279119134,
|
| 74 |
+
"learning_rate": 4.1111562587297156e-05,
|
| 75 |
+
"loss": 0.0002,
|
| 76 |
+
"step": 8000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.59,
|
| 80 |
+
"eval_loss": 2.755745526883402e-06,
|
| 81 |
+
"eval_rouge2_fmeasure": 0.0,
|
| 82 |
+
"eval_rouge2_precision": 0.0,
|
| 83 |
+
"eval_rouge2_recall": 0.0,
|
| 84 |
+
"eval_runtime": 3669.0705,
|
| 85 |
+
"eval_samples_per_second": 2.733,
|
| 86 |
+
"eval_steps_per_second": 0.171,
|
| 87 |
+
"step": 8000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.67,
|
| 91 |
+
"grad_norm": 0.010094952769577503,
|
| 92 |
+
"learning_rate": 3.984178581405389e-05,
|
| 93 |
+
"loss": 0.0014,
|
| 94 |
+
"step": 9000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.74,
|
| 98 |
+
"grad_norm": 0.0005482935812324286,
|
| 99 |
+
"learning_rate": 3.8572009040810624e-05,
|
| 100 |
+
"loss": 0.0001,
|
| 101 |
+
"step": 10000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.82,
|
| 105 |
+
"grad_norm": 0.00010689393093343824,
|
| 106 |
+
"learning_rate": 3.730223226756736e-05,
|
| 107 |
+
"loss": 0.0,
|
| 108 |
+
"step": 11000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.89,
|
| 112 |
+
"grad_norm": 0.0003704932169057429,
|
| 113 |
+
"learning_rate": 3.60324554943241e-05,
|
| 114 |
+
"loss": 0.0006,
|
| 115 |
+
"step": 12000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.89,
|
| 119 |
+
"eval_loss": 3.983559054177022e-06,
|
| 120 |
+
"eval_rouge2_fmeasure": 0.0,
|
| 121 |
+
"eval_rouge2_precision": 0.0,
|
| 122 |
+
"eval_rouge2_recall": 0.0,
|
| 123 |
+
"eval_runtime": 3661.9564,
|
| 124 |
+
"eval_samples_per_second": 2.738,
|
| 125 |
+
"eval_steps_per_second": 0.171,
|
| 126 |
+
"step": 12000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.97,
|
| 130 |
+
"grad_norm": 0.00011691737017827109,
|
| 131 |
+
"learning_rate": 3.476267872108084e-05,
|
| 132 |
+
"loss": 0.0,
|
| 133 |
+
"step": 13000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.04,
|
| 137 |
+
"grad_norm": 8.349567360710353e-05,
|
| 138 |
+
"learning_rate": 3.3492901947837574e-05,
|
| 139 |
+
"loss": 0.0001,
|
| 140 |
+
"step": 14000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.11,
|
| 144 |
+
"grad_norm": 0.0001232757931575179,
|
| 145 |
+
"learning_rate": 3.222312517459431e-05,
|
| 146 |
+
"loss": 0.0001,
|
| 147 |
+
"step": 15000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.19,
|
| 151 |
+
"grad_norm": 0.00011773507139878348,
|
| 152 |
+
"learning_rate": 3.095334840135104e-05,
|
| 153 |
+
"loss": 0.0,
|
| 154 |
+
"step": 16000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.19,
|
| 158 |
+
"eval_loss": 1.058370685314003e-06,
|
| 159 |
+
"eval_rouge2_fmeasure": 0.0,
|
| 160 |
+
"eval_rouge2_precision": 0.0,
|
| 161 |
+
"eval_rouge2_recall": 0.0,
|
| 162 |
+
"eval_runtime": 3660.4191,
|
| 163 |
+
"eval_samples_per_second": 2.739,
|
| 164 |
+
"eval_steps_per_second": 0.171,
|
| 165 |
+
"step": 16000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.26,
|
| 169 |
+
"grad_norm": 0.0022140583023428917,
|
| 170 |
+
"learning_rate": 2.968357162810778e-05,
|
| 171 |
+
"loss": 0.0,
|
| 172 |
+
"step": 17000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.34,
|
| 176 |
+
"grad_norm": 3.650138387456536e-05,
|
| 177 |
+
"learning_rate": 2.8413794854864518e-05,
|
| 178 |
+
"loss": 0.0,
|
| 179 |
+
"step": 18000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.41,
|
| 183 |
+
"grad_norm": 0.010362447239458561,
|
| 184 |
+
"learning_rate": 2.7144018081621252e-05,
|
| 185 |
+
"loss": 0.0001,
|
| 186 |
+
"step": 19000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.49,
|
| 190 |
+
"grad_norm": 0.005041338969022036,
|
| 191 |
+
"learning_rate": 2.587424130837799e-05,
|
| 192 |
+
"loss": 0.0001,
|
| 193 |
+
"step": 20000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.49,
|
| 197 |
+
"eval_loss": 6.733321242791135e-06,
|
| 198 |
+
"eval_rouge2_fmeasure": 0.0,
|
| 199 |
+
"eval_rouge2_precision": 0.0,
|
| 200 |
+
"eval_rouge2_recall": 0.0,
|
| 201 |
+
"eval_runtime": 3656.0835,
|
| 202 |
+
"eval_samples_per_second": 2.742,
|
| 203 |
+
"eval_steps_per_second": 0.171,
|
| 204 |
+
"step": 20000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.56,
|
| 208 |
+
"grad_norm": 6.371775089064613e-05,
|
| 209 |
+
"learning_rate": 2.4604464535134724e-05,
|
| 210 |
+
"loss": 0.0,
|
| 211 |
+
"step": 21000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.63,
|
| 215 |
+
"grad_norm": 0.0006053569377399981,
|
| 216 |
+
"learning_rate": 2.3334687761891462e-05,
|
| 217 |
+
"loss": 0.0001,
|
| 218 |
+
"step": 22000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.71,
|
| 222 |
+
"grad_norm": 0.0021953503601253033,
|
| 223 |
+
"learning_rate": 2.2064910988648196e-05,
|
| 224 |
+
"loss": 0.0,
|
| 225 |
+
"step": 23000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.78,
|
| 229 |
+
"grad_norm": 2.853705154848285e-05,
|
| 230 |
+
"learning_rate": 2.0795134215404934e-05,
|
| 231 |
+
"loss": 0.0,
|
| 232 |
+
"step": 24000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.78,
|
| 236 |
+
"eval_loss": 4.6661673991366115e-07,
|
| 237 |
+
"eval_rouge2_fmeasure": 0.0,
|
| 238 |
+
"eval_rouge2_precision": 0.0,
|
| 239 |
+
"eval_rouge2_recall": 0.0,
|
| 240 |
+
"eval_runtime": 3661.0043,
|
| 241 |
+
"eval_samples_per_second": 2.739,
|
| 242 |
+
"eval_steps_per_second": 0.171,
|
| 243 |
+
"step": 24000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.86,
|
| 247 |
+
"grad_norm": 6.040197695256211e-05,
|
| 248 |
+
"learning_rate": 1.9525357442161668e-05,
|
| 249 |
+
"loss": 0.0,
|
| 250 |
+
"step": 25000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.93,
|
| 254 |
+
"grad_norm": 0.00013890626723878086,
|
| 255 |
+
"learning_rate": 1.8255580668918406e-05,
|
| 256 |
+
"loss": 0.0,
|
| 257 |
+
"step": 26000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.01,
|
| 261 |
+
"grad_norm": 2.3448434149031527e-05,
|
| 262 |
+
"learning_rate": 1.698580389567514e-05,
|
| 263 |
+
"loss": 0.0,
|
| 264 |
+
"step": 27000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.08,
|
| 268 |
+
"grad_norm": 0.00018542050383985043,
|
| 269 |
+
"learning_rate": 1.5716027122431877e-05,
|
| 270 |
+
"loss": 0.0,
|
| 271 |
+
"step": 28000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.08,
|
| 275 |
+
"eval_loss": 1.1049346539948601e-06,
|
| 276 |
+
"eval_rouge2_fmeasure": 0.0001,
|
| 277 |
+
"eval_rouge2_precision": 0.0,
|
| 278 |
+
"eval_rouge2_recall": 0.0001,
|
| 279 |
+
"eval_runtime": 3659.7337,
|
| 280 |
+
"eval_samples_per_second": 2.74,
|
| 281 |
+
"eval_steps_per_second": 0.171,
|
| 282 |
+
"step": 28000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.15,
|
| 286 |
+
"grad_norm": 1.2732043614960276e-05,
|
| 287 |
+
"learning_rate": 1.4446250349188615e-05,
|
| 288 |
+
"loss": 0.0,
|
| 289 |
+
"step": 29000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.23,
|
| 293 |
+
"grad_norm": 1.618100213818252e-05,
|
| 294 |
+
"learning_rate": 1.317647357594535e-05,
|
| 295 |
+
"loss": 0.0,
|
| 296 |
+
"step": 30000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.3,
|
| 300 |
+
"grad_norm": 5.8585923397913575e-05,
|
| 301 |
+
"learning_rate": 1.1906696802702085e-05,
|
| 302 |
+
"loss": 0.0,
|
| 303 |
+
"step": 31000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.38,
|
| 307 |
+
"grad_norm": 0.00015024282038211823,
|
| 308 |
+
"learning_rate": 1.0636920029458821e-05,
|
| 309 |
+
"loss": 0.0004,
|
| 310 |
+
"step": 32000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.38,
|
| 314 |
+
"eval_loss": 1.2435020835255273e-06,
|
| 315 |
+
"eval_rouge2_fmeasure": 0.0,
|
| 316 |
+
"eval_rouge2_precision": 0.0001,
|
| 317 |
+
"eval_rouge2_recall": 0.0,
|
| 318 |
+
"eval_runtime": 3675.9943,
|
| 319 |
+
"eval_samples_per_second": 2.727,
|
| 320 |
+
"eval_steps_per_second": 0.171,
|
| 321 |
+
"step": 32000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.45,
|
| 325 |
+
"grad_norm": 4.083578460267745e-05,
|
| 326 |
+
"learning_rate": 9.367143256215557e-06,
|
| 327 |
+
"loss": 0.0,
|
| 328 |
+
"step": 33000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.53,
|
| 332 |
+
"grad_norm": 8.640537998871878e-06,
|
| 333 |
+
"learning_rate": 8.097366482972293e-06,
|
| 334 |
+
"loss": 0.0,
|
| 335 |
+
"step": 34000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.6,
|
| 339 |
+
"grad_norm": 1.1439586160122417e-05,
|
| 340 |
+
"learning_rate": 6.8275897097290306e-06,
|
| 341 |
+
"loss": 0.0,
|
| 342 |
+
"step": 35000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.67,
|
| 346 |
+
"grad_norm": 0.00013945900718681514,
|
| 347 |
+
"learning_rate": 5.557812936485766e-06,
|
| 348 |
+
"loss": 0.0,
|
| 349 |
+
"step": 36000
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.67,
|
| 353 |
+
"eval_loss": 2.3348137290213344e-07,
|
| 354 |
+
"eval_rouge2_fmeasure": 0.0,
|
| 355 |
+
"eval_rouge2_precision": 0.0,
|
| 356 |
+
"eval_rouge2_recall": 0.0,
|
| 357 |
+
"eval_runtime": 3659.0736,
|
| 358 |
+
"eval_samples_per_second": 2.74,
|
| 359 |
+
"eval_steps_per_second": 0.171,
|
| 360 |
+
"step": 36000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.75,
|
| 364 |
+
"grad_norm": 0.0003026222693733871,
|
| 365 |
+
"learning_rate": 4.288036163242502e-06,
|
| 366 |
+
"loss": 0.0,
|
| 367 |
+
"step": 37000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.82,
|
| 371 |
+
"grad_norm": 6.744077109033242e-05,
|
| 372 |
+
"learning_rate": 3.018259389999238e-06,
|
| 373 |
+
"loss": 0.0,
|
| 374 |
+
"step": 38000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.9,
|
| 378 |
+
"grad_norm": 3.917148569598794e-05,
|
| 379 |
+
"learning_rate": 1.7484826167559743e-06,
|
| 380 |
+
"loss": 0.0,
|
| 381 |
+
"step": 39000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.97,
|
| 385 |
+
"grad_norm": 1.1611381523835007e-05,
|
| 386 |
+
"learning_rate": 4.787058435127105e-07,
|
| 387 |
+
"loss": 0.0,
|
| 388 |
+
"step": 40000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.97,
|
| 392 |
+
"eval_loss": 1.7171299759866088e-07,
|
| 393 |
+
"eval_rouge2_fmeasure": 0.0,
|
| 394 |
+
"eval_rouge2_precision": 0.0,
|
| 395 |
+
"eval_rouge2_recall": 0.0001,
|
| 396 |
+
"eval_runtime": 3666.3048,
|
| 397 |
+
"eval_samples_per_second": 2.735,
|
| 398 |
+
"eval_steps_per_second": 0.171,
|
| 399 |
+
"step": 40000
|
| 400 |
+
}
|
| 401 |
+
],
|
| 402 |
+
"logging_steps": 1000,
|
| 403 |
+
"max_steps": 40377,
|
| 404 |
+
"num_input_tokens_seen": 0,
|
| 405 |
+
"num_train_epochs": 3,
|
| 406 |
+
"save_steps": 500,
|
| 407 |
+
"total_flos": 3.9259958213339136e+17,
|
| 408 |
+
"train_batch_size": 16,
|
| 409 |
+
"trial_name": null,
|
| 410 |
+
"trial_params": null
|
| 411 |
+
}
|
training_args.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59d97c90ea505a93acbba0b29c18b6071bdba0e6835c781fef31afd0c102ecac
|
| 3 |
+
size 4984
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|